Risk Prediction Models in Psychiatry: Toward a New Frontier for the Prevention of Mental Illnesses.

PubMed

Bernardini, Francesco; Attademo, Luigi; Cleary, Sean D; Luther, Charles; Shim, Ruth S; Quartesan, Roberto; Compton, Michael T

2017-05-01

We conducted a systematic, qualitative review of risk prediction models designed and tested for depression, bipolar disorder, generalized anxiety disorder, posttraumatic stress disorder, and psychotic disorders. Our aim was to understand the current state of research on risk prediction models for these 5 disorders and thus future directions as our field moves toward embracing prediction and prevention. Systematic searches of the entire MEDLINE electronic database were conducted independently by 2 of the authors (from 1960 through 2013) in July 2014 using defined search criteria. Search terms included risk prediction, predictive model, or prediction model combined with depression, bipolar, manic depressive, generalized anxiety, posttraumatic, PTSD, schizophrenia, or psychosis. We identified 268 articles based on the search terms and 3 criteria: published in English, provided empirical data (as opposed to review articles), and presented results pertaining to developing or validating a risk prediction model in which the outcome was the diagnosis of 1 of the 5 aforementioned mental illnesses. We selected 43 original research reports as a final set of articles to be qualitatively reviewed. The 2 independent reviewers abstracted 3 types of data (sample characteristics, variables included in the model, and reported model statistics) and reached consensus regarding any discrepant abstracted information. Twelve reports described models developed for prediction of major depressive disorder, 1 for bipolar disorder, 2 for generalized anxiety disorder, 4 for posttraumatic stress disorder, and 24 for psychotic disorders. Most studies reported on sensitivity, specificity, positive predictive value, negative predictive value, and area under the (receiver operating characteristic) curve. Recent studies demonstrate the feasibility of developing risk prediction models for psychiatric disorders (especially psychotic disorders). The field must now advance by (1) conducting more large-scale, longitudinal studies pertaining to depression, bipolar disorder, anxiety disorders, and other psychiatric illnesses; (2) replicating and carrying out external validations of proposed models; (3) further testing potential selective and indicated preventive interventions; and (4) evaluating effectiveness of such interventions in the context of risk stratification using risk prediction models. © Copyright 2017 Physicians Postgraduate Press, Inc.

Monitoring risk-adjusted outcomes in congenital heart surgery: does the appropriateness of a risk model change with time?

PubMed

Tsang, Victor T; Brown, Katherine L; Synnergren, Mats Johanssen; Kang, Nicholas; de Leval, Marc R; Gallivan, Steve; Utley, Martin

2009-02-01

Risk adjustment of outcomes in pediatric congenital heart surgery is challenging due to the great diversity in diagnoses and procedures. We have previously shown that variable life-adjusted display (VLAD) charts provide an effective graphic display of risk-adjusted outcomes in this specialty. A question arises as to whether the risk model used remains appropriate over time. We used a recently developed graphic technique to evaluate the performance of an existing risk model among those patients at a single center during 2000 to 2003 originally used in model development. We then compared the distribution of predicted risk among these patients with that among patients in 2004 to 2006. Finally, we constructed a VLAD chart of risk-adjusted outcomes for the latter period. Among 1083 patients between April 2000 and March 2003, the risk model performed well at predicted risks above 3%, underestimated mortality at 2% to 3% predicted risk, and overestimated mortality below 2% predicted risk. There was little difference in the distribution of predicted risk among these patients and among 903 patients between June 2004 and October 2006. Outcomes for the more recent period were appreciably better than those expected according to the risk model. This finding cannot be explained by any apparent bias in the risk model combined with changes in case-mix. Risk models can, and hopefully do, become out of date. There is scope for complacency in the risk-adjusted audit if the risk model used is not regularly recalibrated to reflect changing standards and expectations.

Development and Validation of a Risk Model for Prediction of Hazardous Alcohol Consumption in General Practice Attendees: The PredictAL Study

PubMed Central

King, Michael; Marston, Louise; Švab, Igor; Maaroos, Heidi-Ingrid; Geerlings, Mirjam I.; Xavier, Miguel; Benjamin, Vicente; Torres-Gonzalez, Francisco; Bellon-Saameno, Juan Angel; Rotar, Danica; Aluoja, Anu; Saldivia, Sandra; Correa, Bernardo; Nazareth, Irwin

2011-01-01

Background Little is known about the risk of progression to hazardous alcohol use in people currently drinking at safe limits. We aimed to develop a prediction model (predictAL) for the development of hazardous drinking in safe drinkers. Methods A prospective cohort study of adult general practice attendees in six European countries and Chile followed up over 6 months. We recruited 10,045 attendees between April 2003 to February 2005. 6193 European and 2462 Chilean attendees recorded AUDIT scores below 8 in men and 5 in women at recruitment and were used in modelling risk. 38 risk factors were measured to construct a risk model for the development of hazardous drinking using stepwise logistic regression. The model was corrected for over fitting and tested in an external population. The main outcome was hazardous drinking defined by an AUDIT score ≥8 in men and ≥5 in women. Results 69.0% of attendees were recruited, of whom 89.5% participated again after six months. The risk factors in the final predictAL model were sex, age, country, baseline AUDIT score, panic syndrome and lifetime alcohol problem. The predictAL model's average c-index across all six European countries was 0.839 (95% CI 0.805, 0.873). The Hedge's g effect size for the difference in log odds of predicted probability between safe drinkers in Europe who subsequently developed hazardous alcohol use and those who did not was 1.38 (95% CI 1.25, 1.51). External validation of the algorithm in Chilean safe drinkers resulted in a c-index of 0.781 (95% CI 0.717, 0.846) and Hedge's g of 0.68 (95% CI 0.57, 0.78). Conclusions The predictAL risk model for development of hazardous consumption in safe drinkers compares favourably with risk algorithms for disorders in other medical settings and can be a useful first step in prevention of alcohol misuse. PMID:21853028

Development and validation of a risk model for prediction of hazardous alcohol consumption in general practice attendees: the predictAL study.

PubMed

King, Michael; Marston, Louise; Švab, Igor; Maaroos, Heidi-Ingrid; Geerlings, Mirjam I; Xavier, Miguel; Benjamin, Vicente; Torres-Gonzalez, Francisco; Bellon-Saameno, Juan Angel; Rotar, Danica; Aluoja, Anu; Saldivia, Sandra; Correa, Bernardo; Nazareth, Irwin

2011-01-01

Little is known about the risk of progression to hazardous alcohol use in people currently drinking at safe limits. We aimed to develop a prediction model (predictAL) for the development of hazardous drinking in safe drinkers. A prospective cohort study of adult general practice attendees in six European countries and Chile followed up over 6 months. We recruited 10,045 attendees between April 2003 to February 2005. 6193 European and 2462 Chilean attendees recorded AUDIT scores below 8 in men and 5 in women at recruitment and were used in modelling risk. 38 risk factors were measured to construct a risk model for the development of hazardous drinking using stepwise logistic regression. The model was corrected for over fitting and tested in an external population. The main outcome was hazardous drinking defined by an AUDIT score ≥8 in men and ≥5 in women. 69.0% of attendees were recruited, of whom 89.5% participated again after six months. The risk factors in the final predictAL model were sex, age, country, baseline AUDIT score, panic syndrome and lifetime alcohol problem. The predictAL model's average c-index across all six European countries was 0.839 (95% CI 0.805, 0.873). The Hedge's g effect size for the difference in log odds of predicted probability between safe drinkers in Europe who subsequently developed hazardous alcohol use and those who did not was 1.38 (95% CI 1.25, 1.51). External validation of the algorithm in Chilean safe drinkers resulted in a c-index of 0.781 (95% CI 0.717, 0.846) and Hedge's g of 0.68 (95% CI 0.57, 0.78). The predictAL risk model for development of hazardous consumption in safe drinkers compares favourably with risk algorithms for disorders in other medical settings and can be a useful first step in prevention of alcohol misuse.

Population-Level Prediction of Type 2 Diabetes From Claims Data and Analysis of Risk Factors.

PubMed

Razavian, Narges; Blecker, Saul; Schmidt, Ann Marie; Smith-McLallen, Aaron; Nigam, Somesh; Sontag, David

2015-12-01

We present a new approach to population health, in which data-driven predictive models are learned for outcomes such as type 2 diabetes. Our approach enables risk assessment from readily available electronic claims data on large populations, without additional screening cost. Proposed model uncovers early and late-stage risk factors. Using administrative claims, pharmacy records, healthcare utilization, and laboratory results of 4.1 million individuals between 2005 and 2009, an initial set of 42,000 variables were derived that together describe the full health status and history of every individual. Machine learning was then used to methodically enhance predictive variable set and fit models predicting onset of type 2 diabetes in 2009-2011, 2010-2012, and 2011-2013. We compared the enhanced model with a parsimonious model consisting of known diabetes risk factors in a real-world environment, where missing values are common and prevalent. Furthermore, we analyzed novel and known risk factors emerging from the model at different age groups at different stages before the onset. Parsimonious model using 21 classic diabetes risk factors resulted in area under ROC curve (AUC) of 0.75 for diabetes prediction within a 2-year window following the baseline. The enhanced model increased the AUC to 0.80, with about 900 variables selected as predictive (p < 0.0001 for differences between AUCs). Similar improvements were observed for models predicting diabetes onset 1-3 years and 2-4 years after baseline. The enhanced model improved positive predictive value by at least 50% and identified novel surrogate risk factors for type 2 diabetes, such as chronic liver disease (odds ratio [OR] 3.71), high alanine aminotransferase (OR 2.26), esophageal reflux (OR 1.85), and history of acute bronchitis (OR 1.45). Liver risk factors emerge later in the process of diabetes development compared with obesity-related factors such as hypertension and high hemoglobin A1c. In conclusion, population-level risk prediction for type 2 diabetes using readily available administrative data is feasible and has better prediction performance than classical diabetes risk prediction algorithms on very large populations with missing data. The new model enables intervention allocation at national scale quickly and accurately and recovers potentially novel risk factors at different stages before the disease onset.

A microRNA-based prediction model for lymph node metastasis in hepatocellular carcinoma.

PubMed

Zhang, Li; Xiang, Zuo-Lin; Zeng, Zhao-Chong; Fan, Jia; Tang, Zhao-You; Zhao, Xiao-Mei

2016-01-19

We developed an efficient microRNA (miRNA) model that could predict the risk of lymph node metastasis (LNM) in hepatocellular carcinoma (HCC). We first evaluated a training cohort of 192 HCC patients after hepatectomy and found five LNM associated predictive factors: vascular invasion, Barcelona Clinic Liver Cancer stage, miR-145, miR-31, and miR-92a. The five statistically independent factors were used to develop a predictive model. The predictive value of the miRNA-based model was confirmed in a validation cohort of 209 consecutive HCC patients. The prediction model was scored for LNM risk from 0 to 8. The cutoff value 4 was used to distinguish high-risk and low-risk groups. The model sensitivity and specificity was 69.6 and 80.2%, respectively, during 5 years in the validation cohort. And the area under the curve (AUC) for the miRNA-based prognostic model was 0.860. The 5-year positive and negative predictive values of the model in the validation cohort were 30.3 and 95.5%, respectively. Cox regression analysis revealed that the LNM hazard ratio of the high-risk versus low-risk groups was 11.751 (95% CI, 5.110-27.021; P < 0.001) in the validation cohort. In conclusion, the miRNA-based model is reliable and accurate for the early prediction of LNM in patients with HCC.

Undergraduate Student Retention in Context: An Examination of First-Year Risk Prediction and Advising Practices within a College of Education

ERIC Educational Resources Information Center

Litchfield, Bradley C.

2013-01-01

This study examined the use of an institutionally-specific risk prediction model in the university's College of Education. Set in a large, urban, public university, the risk model predicted incoming students' first-semester GPAs, which, in turn, predicted the students' risk of attrition. Additionally, the study investigated advising practices…

Calibration plots for risk prediction models in the presence of competing risks.

PubMed

Gerds, Thomas A; Andersen, Per K; Kattan, Michael W

2014-08-15

A predicted risk of 17% can be called reliable if it can be expected that the event will occur to about 17 of 100 patients who all received a predicted risk of 17%. Statistical models can predict the absolute risk of an event such as cardiovascular death in the presence of competing risks such as death due to other causes. For personalized medicine and patient counseling, it is necessary to check that the model is calibrated in the sense that it provides reliable predictions for all subjects. There are three often encountered practical problems when the aim is to display or test if a risk prediction model is well calibrated. The first is lack of independent validation data, the second is right censoring, and the third is that when the risk scale is continuous, the estimation problem is as difficult as density estimation. To deal with these problems, we propose to estimate calibration curves for competing risks models based on jackknife pseudo-values that are combined with a nearest neighborhood smoother and a cross-validation approach to deal with all three problems. Copyright © 2014 John Wiley & Sons, Ltd.

A new risk prediction model for critical care: the Intensive Care National Audit & Research Centre (ICNARC) model.

PubMed

Harrison, David A; Parry, Gareth J; Carpenter, James R; Short, Alasdair; Rowan, Kathy

2007-04-01

To develop a new model to improve risk prediction for admissions to adult critical care units in the UK. Prospective cohort study. The setting was 163 adult, general critical care units in England, Wales, and Northern Ireland, December 1995 to August 2003. Patients were 216,626 critical care admissions. None. The performance of different approaches to modeling physiologic measurements was evaluated, and the best methods were selected to produce a new physiology score. This physiology score was combined with other information relating to the critical care admission-age, diagnostic category, source of admission, and cardiopulmonary resuscitation before admission-to develop a risk prediction model. Modeling interactions between diagnostic category and physiology score enabled the inclusion of groups of admissions that are frequently excluded from risk prediction models. The new model showed good discrimination (mean c index 0.870) and fit (mean Shapiro's R 0.665, mean Brier's score 0.132) in 200 repeated validation samples and performed well when compared with recalibrated versions of existing published risk prediction models in the cohort of patients eligible for all models. The hypothesis of perfect fit was rejected for all models, including the Intensive Care National Audit & Research Centre (ICNARC) model, as is to be expected in such a large cohort. The ICNARC model demonstrated better discrimination and overall fit than existing risk prediction models, even following recalibration of these models. We recommend it be used to replace previously published models for risk adjustment in the UK.

The Risk GP Model: the standard model of prediction in medicine.

PubMed

Fuller, Jonathan; Flores, Luis J

2015-12-01

With the ascent of modern epidemiology in the Twentieth Century came a new standard model of prediction in public health and clinical medicine. In this article, we describe the structure of the model. The standard model uses epidemiological measures-most commonly, risk measures-to predict outcomes (prognosis) and effect sizes (treatment) in a patient population that can then be transformed into probabilities for individual patients. In the first step, a risk measure in a study population is generalized or extrapolated to a target population. In the second step, the risk measure is particularized or transformed to yield probabilistic information relevant to a patient from the target population. Hence, we call the approach the Risk Generalization-Particularization (Risk GP) Model. There are serious problems at both stages, especially with the extent to which the required assumptions will hold and the extent to which we have evidence for the assumptions. Given that there are other models of prediction that use different assumptions, we should not inflexibly commit ourselves to one standard model. Instead, model pluralism should be standard in medical prediction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Development of a Risk Prediction Model and Clinical Risk Score for Isolated Tricuspid Valve Surgery.

PubMed

LaPar, Damien J; Likosky, Donald S; Zhang, Min; Theurer, Patty; Fonner, C Edwin; Kern, John A; Bolling, Stephen F; Drake, Daniel H; Speir, Alan M; Rich, Jeffrey B; Kron, Irving L; Prager, Richard L; Ailawadi, Gorav

2018-02-01

While tricuspid valve (TV) operations remain associated with high mortality (∼8-10%), no robust prediction models exist to support clinical decision-making. We developed a preoperative clinical risk model with an easily calculable clinical risk score (CRS) to predict mortality and major morbidity after isolated TV surgery. Multi-state Society of Thoracic Surgeons database records were evaluated for 2,050 isolated TV repair and replacement operations for any etiology performed at 50 hospitals (2002-2014). Parsimonious preoperative risk prediction models were developed using multi-level mixed effects regression to estimate mortality and composite major morbidity risk. Model results were utilized to establish a novel CRS for patients undergoing TV operations. Models were evaluated for discrimination and calibration. Operative mortality and composite major morbidity rates were 9% and 42%, respectively. Final regression models performed well (both P<0.001, AUC = 0.74 and 0.76) and included preoperative factors: age, gender, stroke, hemodialysis, ejection fraction, lung disease, NYHA class, reoperation and urgent or emergency status (all P<0.05). A simple CRS from 0-10+ was highly associated (P<0.001) with incremental increases in predicted mortality and major morbidity. Predicted mortality risk ranged from 2%-34% across CRS categories, while predicted major morbidity risk ranged from 13%-71%. Mortality and major morbidity after isolated TV surgery can be predicted using preoperative patient data from the STS Adult Cardiac Database. A simple clinical risk score predicts mortality and major morbidity after isolated TV surgery. This score may facilitate perioperative counseling and identification of suitable patients for TV surgery. Copyright © 2018 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved.

Recent development of risk-prediction models for incident hypertension: An updated systematic review

PubMed Central

Xiao, Lei; Liu, Ya; Wang, Zuoguang; Li, Chuang; Jin, Yongxin; Zhao, Qiong

2017-01-01

Background Hypertension is a leading global health threat and a major cardiovascular disease. Since clinical interventions are effective in delaying the disease progression from prehypertension to hypertension, diagnostic prediction models to identify patient populations at high risk for hypertension are imperative. Methods Both PubMed and Embase databases were searched for eligible reports of either prediction models or risk scores of hypertension. The study data were collected, including risk factors, statistic methods, characteristics of study design and participants, performance measurement, etc. Results From the searched literature, 26 studies reporting 48 prediction models were selected. Among them, 20 reports studied the established models using traditional risk factors, such as body mass index (BMI), age, smoking, blood pressure (BP) level, parental history of hypertension, and biochemical factors, whereas 6 reports used genetic risk score (GRS) as the prediction factor. AUC ranged from 0.64 to 0.97, and C-statistic ranged from 60% to 90%. Conclusions The traditional models are still the predominant risk prediction models for hypertension, but recently, more models have begun to incorporate genetic factors as part of their model predictors. However, these genetic predictors need to be well selected. The current reported models have acceptable to good discrimination and calibration ability, but whether the models can be applied in clinical practice still needs more validation and adjustment. PMID:29084293

Relationship of Predicted Risk of Developing Invasive Breast Cancer, as Assessed with Three Models, and Breast Cancer Mortality among Breast Cancer Patients

PubMed Central

Pfeiffer, Ruth M.; Miglioretti, Diana L.; Kerlikowske, Karla; Tice, Jeffery; Vacek, Pamela M.; Gierach, Gretchen L.

2016-01-01

Purpose Breast cancer risk prediction models are used to plan clinical trials and counsel women; however, relationships of predicted risks of breast cancer incidence and prognosis after breast cancer diagnosis are unknown. Methods Using largely pre-diagnostic information from the Breast Cancer Surveillance Consortium (BCSC) for 37,939 invasive breast cancers (1996–2007), we estimated 5-year breast cancer risk (<1%; 1–1.66%; ≥1.67%) with three models: BCSC 1-year risk model (BCSC-1; adapted to 5-year predictions); Breast Cancer Risk Assessment Tool (BCRAT); and BCSC 5-year risk model (BCSC-5). Breast cancer-specific mortality post-diagnosis (range: 1–13 years; median: 5.4–5.6 years) was related to predicted risk of developing breast cancer using unadjusted Cox proportional hazards models, and in age-stratified (35–44; 45–54; 55–69; 70–89 years) models adjusted for continuous age, BCSC registry, calendar period, income, mode of presentation, stage and treatment. Mean age at diagnosis was 60 years. Results Of 6,021 deaths, 2,993 (49.7%) were ascribed to breast cancer. In unadjusted case-only analyses, predicted breast cancer risk ≥1.67% versus <1.0% was associated with lower risk of breast cancer death; BCSC-1: hazard ratio (HR) = 0.82 (95% CI = 0.75–0.90); BCRAT: HR = 0.72 (95% CI = 0.65–0.81) and BCSC-5: HR = 0.84 (95% CI = 0.75–0.94). Age-stratified, adjusted models showed similar, although mostly non-significant HRs. Among women ages 55–69 years, HRs approximated 1.0. Generally, higher predicted risk was inversely related to percentages of cancers with unfavorable prognostic characteristics, especially among women 35–44 years. Conclusions Among cases assessed with three models, higher predicted risk of developing breast cancer was not associated with greater risk of breast cancer death; thus, these models would have limited utility in planning studies to evaluate breast cancer mortality reduction strategies. Further, when offering women counseling, it may be useful to note that high predicted risk of developing breast cancer does not imply that if cancer develops it will behave aggressively. PMID:27560501

Predictive genetic testing for the identification of high-risk groups: a simulation study on the impact of predictive ability

PubMed Central

2011-01-01

Background Genetic risk models could potentially be useful in identifying high-risk groups for the prevention of complex diseases. We investigated the performance of this risk stratification strategy by examining epidemiological parameters that impact the predictive ability of risk models. Methods We assessed sensitivity, specificity, and positive and negative predictive value for all possible risk thresholds that can define high-risk groups and investigated how these measures depend on the frequency of disease in the population, the frequency of the high-risk group, and the discriminative accuracy of the risk model, as assessed by the area under the receiver-operating characteristic curve (AUC). In a simulation study, we modeled genetic risk scores of 50 genes with equal odds ratios and genotype frequencies, and varied the odds ratios and the disease frequency across scenarios. We also performed a simulation of age-related macular degeneration risk prediction based on published odds ratios and frequencies for six genetic risk variants. Results We show that when the frequency of the high-risk group was lower than the disease frequency, positive predictive value increased with the AUC but sensitivity remained low. When the frequency of the high-risk group was higher than the disease frequency, sensitivity was high but positive predictive value remained low. When both frequencies were equal, both positive predictive value and sensitivity increased with increasing AUC, but higher AUC was needed to maximize both measures. Conclusions The performance of risk stratification is strongly determined by the frequency of the high-risk group relative to the frequency of disease in the population. The identification of high-risk groups with appreciable combinations of sensitivity and positive predictive value requires higher AUC. PMID:21797996

External validation of the Garvan nomograms for predicting absolute fracture risk: the Tromsø study.

PubMed

Ahmed, Luai A; Nguyen, Nguyen D; Bjørnerem, Åshild; Joakimsen, Ragnar M; Jørgensen, Lone; Størmer, Jan; Bliuc, Dana; Center, Jacqueline R; Eisman, John A; Nguyen, Tuan V; Emaus, Nina

2014-01-01

Absolute risk estimation is a preferred approach for assessing fracture risk and treatment decision making. This study aimed to evaluate and validate the predictive performance of the Garvan Fracture Risk Calculator in a Norwegian cohort. The analysis included 1637 women and 1355 aged 60+ years from the Tromsø study. All incident fragility fractures between 2001 and 2009 were registered. The predicted probabilities of non-vertebral osteoporotic and hip fractures were determined using models with and without BMD. The discrimination and calibration of the models were assessed. Reclassification analysis was used to compare the models performance. The incidence of osteoporotic and hip fracture was 31.5 and 8.6 per 1000 population in women, respectively; in men the corresponding incidence was 12.2 and 5.1. The predicted 5-year and 10-year probability of fractures was consistently higher in the fracture group than the non-fracture group for all models. The 10-year predicted probabilities of hip fracture in those with fracture was 2.8 (women) to 3.1 times (men) higher than those without fracture. There was a close agreement between predicted and observed risk in both sexes and up to the fifth quintile. Among those in the highest quintile of risk, the models over-estimated the risk of fracture. Models with BMD performed better than models with body weight in correct classification of risk in individuals with and without fracture. The overall net decrease in reclassification of the model with weight compared to the model with BMD was 10.6% (p = 0.008) in women and 17.2% (p = 0.001) in men for osteoporotic fractures, and 13.3% (p = 0.07) in women and 17.5% (p = 0.09) in men for hip fracture. The Garvan Fracture Risk Calculator is valid and clinically useful in identifying individuals at high risk of fracture. The models with BMD performed better than those with body weight in fracture risk prediction.

Prediction of Coronary Artery Disease Risk Based on Multiple Longitudinal Biomarkers

PubMed Central

Yang, Lili; Yu, Menggang; Gao, Sujuan

2016-01-01

In the last decade, few topics in the area of cardiovascular disease (CVD) research have received as much attention as risk prediction. One of the well documented risk factors for CVD is high blood pressure (BP). Traditional CVD risk prediction models consider BP levels measured at a single time and such models form the basis for current clinical guidelines for CVD prevention. However, in clinical practice, BP levels are often observed and recorded in a longitudinal fashion. Information on BP trajectories can be powerful predictors for CVD events. We consider joint modeling of time to coronary artery disease and individual longitudinal measures of systolic and diastolic BPs in a primary care cohort with up to 20 years of follow-up. We applied novel prediction metrics to assess the predictive performance of joint models. Predictive performances of proposed joint models and other models were assessed via simulations and illustrated using the primary care cohort. PMID:26439685

The ACC/AHA 2013 pooled cohort equations compared to a Korean Risk Prediction Model for atherosclerotic cardiovascular disease.

PubMed

Jung, Keum Ji; Jang, Yangsoo; Oh, Dong Joo; Oh, Byung-Hee; Lee, Sang Hoon; Park, Seong-Wook; Seung, Ki-Bae; Kim, Hong-Kyu; Yun, Young Duk; Choi, Sung Hee; Sung, Jidong; Lee, Tae-Yong; Kim, Sung Hi; Koh, Sang Baek; Kim, Moon Chan; Chang Kim, Hyeon; Kimm, Heejin; Nam, Chungmo; Park, Sungha; Jee, Sun Ha

2015-09-01

To evaluate the performance of the American College of Cardiology/American Heart Association (ACC/AHA) 2013 Pooled Cohort Equations in the Korean Heart Study (KHS) population and to develop a Korean Risk Prediction Model (KRPM) for atherosclerotic cardiovascular disease (ASCVD) events. The KHS cohort included 200,010 Korean adults aged 40-79 years who were free from ASCVD at baseline. Discrimination, calibration, and recalibration of the ACC/AHA Equations in predicting 10-year ASCVD risk in the KHS cohort were evaluated. The KRPM was derived using Cox model coefficients, mean risk factor values, and mean incidences from the KHS cohort. In the discriminatory analysis, the ACC/AHA Equations' White and African-American (AA) models moderately distinguished cases from non-cases, and were similar to the KRPM: For men, the area under the receiver operating characteristic curve (AUROCs) were 0.727 (White model), 0.725 (AA model), and 0.741 (KRPM); for women, the corresponding AUROCs were 0.738, 0.739, and 0.745. Absolute 10-year ASCVD risk for men in the KHS cohort was overestimated by 56.5% (White model) and 74.1% (AA model), while the risk for women was underestimated by 27.9% (White model) and overestimated by 29.1% (AA model). Recalibration of the ACC/AHA Equations did not affect discriminatory ability but improved calibration substantially, especially in men in the White model. Of the three ASCVD risk prediction models, the KRPM showed best calibration. The ACC/AHA Equations should not be directly applied for ASCVD risk prediction in a Korean population. The KRPM showed best predictive ability for ASCVD risk. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Scientific reporting is suboptimal for aspects that characterize genetic risk prediction studies: a review of published articles based on the Genetic RIsk Prediction Studies statement.

PubMed

Iglesias, Adriana I; Mihaescu, Raluca; Ioannidis, John P A; Khoury, Muin J; Little, Julian; van Duijn, Cornelia M; Janssens, A Cecile J W

2014-05-01

Our main objective was to raise awareness of the areas that need improvements in the reporting of genetic risk prediction articles for future publications, based on the Genetic RIsk Prediction Studies (GRIPS) statement. We evaluated studies that developed or validated a prediction model based on multiple DNA variants, using empirical data, and were published in 2010. A data extraction form based on the 25 items of the GRIPS statement was created and piloted. Forty-two studies met our inclusion criteria. Overall, more than half of the evaluated items (34 of 62) were reported in at least 85% of included articles. Seventy-seven percentage of the articles were identified as genetic risk prediction studies through title assessment, but only 31% used the keywords recommended by GRIPS in the title or abstract. Seventy-four percentage mentioned which allele was the risk variant. Overall, only 10% of the articles reported all essential items needed to perform external validation of the risk model. Completeness of reporting in genetic risk prediction studies is adequate for general elements of study design but is suboptimal for several aspects that characterize genetic risk prediction studies such as description of the model construction. Improvements in the transparency of reporting of these aspects would facilitate the identification, replication, and application of genetic risk prediction models. Copyright © 2014 Elsevier Inc. All rights reserved.

Multifactorial disease risk calculator: Risk prediction for multifactorial disease pedigrees.

PubMed

Campbell, Desmond D; Li, Yiming; Sham, Pak C

2018-03-01

Construction of multifactorial disease models from epidemiological findings and their application to disease pedigrees for risk prediction is nontrivial for all but the simplest of cases. Multifactorial Disease Risk Calculator is a web tool facilitating this. It provides a user-friendly interface, extending a reported methodology based on a liability-threshold model. Multifactorial disease models incorporating all the following features in combination are handled: quantitative risk factors (including polygenic scores), categorical risk factors (including major genetic risk loci), stratified age of onset curves, and the partition of the population variance in disease liability into genetic, shared, and unique environment effects. It allows the application of such models to disease pedigrees. Pedigree-related outputs are (i) individual disease risk for pedigree members, (ii) n year risk for unaffected pedigree members, and (iii) the disease pedigree's joint liability distribution. Risk prediction for each pedigree member is based on using the constructed disease model to appropriately weigh evidence on disease risk available from personal attributes and family history. Evidence is used to construct the disease pedigree's joint liability distribution. From this, lifetime and n year risk can be predicted. Example disease models and pedigrees are provided at the website and are used in accompanying tutorials to illustrate the features available. The website is built on an R package which provides the functionality for pedigree validation, disease model construction, and risk prediction. Website: http://grass.cgs.hku.hk:3838/mdrc/current. © 2017 WILEY PERIODICALS, INC.

Prediction impact curve is a new measure integrating intervention effects in the evaluation of risk models.

PubMed

Campbell, William; Ganna, Andrea; Ingelsson, Erik; Janssens, A Cecile J W

2016-01-01

We propose a new measure of assessing the performance of risk models, the area under the prediction impact curve (auPIC), which quantifies the performance of risk models in terms of their average health impact in the population. Using simulated data, we explain how the prediction impact curve (PIC) estimates the percentage of events prevented when a risk model is used to assign high-risk individuals to an intervention. We apply the PIC to the Atherosclerosis Risk in Communities (ARIC) Study to illustrate its application toward prevention of coronary heart disease. We estimated that if the ARIC cohort received statins at baseline, 5% of events would be prevented when the risk model was evaluated at a cutoff threshold of 20% predicted risk compared to 1% when individuals were assigned to the intervention without the use of a model. By calculating the auPIC, we estimated that an average of 15% of events would be prevented when considering performance across the entire interval. We conclude that the PIC is a clinically meaningful measure for quantifying the expected health impact of risk models that supplements existing measures of model performance. Copyright © 2016 Elsevier Inc. All rights reserved.

Limits of Risk Predictability in a Cascading Alternating Renewal Process Model.

PubMed

Lin, Xin; Moussawi, Alaa; Korniss, Gyorgy; Bakdash, Jonathan Z; Szymanski, Boleslaw K

2017-07-27

Most risk analysis models systematically underestimate the probability and impact of catastrophic events (e.g., economic crises, natural disasters, and terrorism) by not taking into account interconnectivity and interdependence of risks. To address this weakness, we propose the Cascading Alternating Renewal Process (CARP) to forecast interconnected global risks. However, assessments of the model's prediction precision are limited by lack of sufficient ground truth data. Here, we establish prediction precision as a function of input data size by using alternative long ground truth data generated by simulations of the CARP model with known parameters. We illustrate the approach on a model of fires in artificial cities assembled from basic city blocks with diverse housing. The results confirm that parameter recovery variance exhibits power law decay as a function of the length of available ground truth data. Using CARP, we also demonstrate estimation using a disparate dataset that also has dependencies: real-world prediction precision for the global risk model based on the World Economic Forum Global Risk Report. We conclude that the CARP model is an efficient method for predicting catastrophic cascading events with potential applications to emerging local and global interconnected risks.

Improving risk prediction accuracy for new soldiers in the U.S. Army by adding self-report survey data to administrative data.

PubMed

Bernecker, Samantha L; Rosellini, Anthony J; Nock, Matthew K; Chiu, Wai Tat; Gutierrez, Peter M; Hwang, Irving; Joiner, Thomas E; Naifeh, James A; Sampson, Nancy A; Zaslavsky, Alan M; Stein, Murray B; Ursano, Robert J; Kessler, Ronald C

2018-04-03

High rates of mental disorders, suicidality, and interpersonal violence early in the military career have raised interest in implementing preventive interventions with high-risk new enlistees. The Army Study to Assess Risk and Resilience in Servicemembers (STARRS) developed risk-targeting systems for these outcomes based on machine learning methods using administrative data predictors. However, administrative data omit many risk factors, raising the question whether risk targeting could be improved by adding self-report survey data to prediction models. If so, the Army may gain from routinely administering surveys that assess additional risk factors. The STARRS New Soldier Survey was administered to 21,790 Regular Army soldiers who agreed to have survey data linked to administrative records. As reported previously, machine learning models using administrative data as predictors found that small proportions of high-risk soldiers accounted for high proportions of negative outcomes. Other machine learning models using self-report survey data as predictors were developed previously for three of these outcomes: major physical violence and sexual violence perpetration among men and sexual violence victimization among women. Here we examined the extent to which this survey information increases prediction accuracy, over models based solely on administrative data, for those three outcomes. We used discrete-time survival analysis to estimate a series of models predicting first occurrence, assessing how model fit improved and concentration of risk increased when adding the predicted risk score based on survey data to the predicted risk score based on administrative data. The addition of survey data improved prediction significantly for all outcomes. In the most extreme case, the percentage of reported sexual violence victimization among the 5% of female soldiers with highest predicted risk increased from 17.5% using only administrative predictors to 29.4% adding survey predictors, a 67.9% proportional increase in prediction accuracy. Other proportional increases in concentration of risk ranged from 4.8% to 49.5% (median = 26.0%). Data from an ongoing New Soldier Survey could substantially improve accuracy of risk models compared to models based exclusively on administrative predictors. Depending upon the characteristics of interventions used, the increase in targeting accuracy from survey data might offset survey administration costs.

Proposals for enhanced health risk assessment and stratification in an integrated care scenario

PubMed Central

Dueñas-Espín, Ivan; Vela, Emili; Pauws, Steffen; Bescos, Cristina; Cano, Isaac; Cleries, Montserrat; Contel, Joan Carles; de Manuel Keenoy, Esteban; Garcia-Aymerich, Judith; Gomez-Cabrero, David; Kaye, Rachelle; Lahr, Maarten M H; Lluch-Ariet, Magí; Moharra, Montserrat; Monterde, David; Mora, Joana; Nalin, Marco; Pavlickova, Andrea; Piera, Jordi; Ponce, Sara; Santaeugenia, Sebastià; Schonenberg, Helen; Störk, Stefan; Tegner, Jesper; Velickovski, Filip; Westerteicher, Christoph; Roca, Josep

2016-01-01

Objectives Population-based health risk assessment and stratification are considered highly relevant for large-scale implementation of integrated care by facilitating services design and case identification. The principal objective of the study was to analyse five health-risk assessment strategies and health indicators used in the five regions participating in the Advancing Care Coordination and Telehealth Deployment (ACT) programme (http://www.act-programme.eu). The second purpose was to elaborate on strategies toward enhanced health risk predictive modelling in the clinical scenario. Settings The five ACT regions: Scotland (UK), Basque Country (ES), Catalonia (ES), Lombardy (I) and Groningen (NL). Participants Responsible teams for regional data management in the five ACT regions. Primary and secondary outcome measures We characterised and compared risk assessment strategies among ACT regions by analysing operational health risk predictive modelling tools for population-based stratification, as well as available health indicators at regional level. The analysis of the risk assessment tool deployed in Catalonia in 2015 (GMAs, Adjusted Morbidity Groups) was used as a basis to propose how population-based analytics could contribute to clinical risk prediction. Results There was consensus on the need for a population health approach to generate health risk predictive modelling. However, this strategy was fully in place only in two ACT regions: Basque Country and Catalonia. We found marked differences among regions in health risk predictive modelling tools and health indicators, and identified key factors constraining their comparability. The research proposes means to overcome current limitations and the use of population-based health risk prediction for enhanced clinical risk assessment. Conclusions The results indicate the need for further efforts to improve both comparability and flexibility of current population-based health risk predictive modelling approaches. Applicability and impact of the proposals for enhanced clinical risk assessment require prospective evaluation. PMID:27084274

Risk prediction and aversion by anterior cingulate cortex.

PubMed

Brown, Joshua W; Braver, Todd S

2007-12-01

The recently proposed error-likelihood hypothesis suggests that anterior cingulate cortex (ACC) and surrounding areas will become active in proportion to the perceived likelihood of an error. The hypothesis was originally derived from a computational model prediction. The same computational model now makes a further prediction that ACC will be sensitive not only to predicted error likelihood, but also to the predicted magnitude of the consequences, should an error occur. The product of error likelihood and predicted error consequence magnitude collectively defines the general "expected risk" of a given behavior in a manner analogous but orthogonal to subjective expected utility theory. New fMRI results from an incentivechange signal task now replicate the error-likelihood effect, validate the further predictions of the computational model, and suggest why some segments of the population may fail to show an error-likelihood effect. In particular, error-likelihood effects and expected risk effects in general indicate greater sensitivity to earlier predictors of errors and are seen in risk-averse but not risk-tolerant individuals. Taken together, the results are consistent with an expected risk model of ACC and suggest that ACC may generally contribute to cognitive control by recruiting brain activity to avoid risk.

Building and validating a prediction model for paediatric type 1 diabetes risk using next generation targeted sequencing of class II HLA genes.

PubMed

Zhao, Lue Ping; Carlsson, Annelie; Larsson, Helena Elding; Forsander, Gun; Ivarsson, Sten A; Kockum, Ingrid; Ludvigsson, Johnny; Marcus, Claude; Persson, Martina; Samuelsson, Ulf; Örtqvist, Eva; Pyo, Chul-Woo; Bolouri, Hamid; Zhao, Michael; Nelson, Wyatt C; Geraghty, Daniel E; Lernmark, Åke

2017-11-01

It is of interest to predict possible lifetime risk of type 1 diabetes (T1D) in young children for recruiting high-risk subjects into longitudinal studies of effective prevention strategies. Utilizing a case-control study in Sweden, we applied a recently developed next generation targeted sequencing technology to genotype class II genes and applied an object-oriented regression to build and validate a prediction model for T1D. In the training set, estimated risk scores were significantly different between patients and controls (P = 8.12 × 10 -92 ), and the area under the curve (AUC) from the receiver operating characteristic (ROC) analysis was 0.917. Using the validation data set, we validated the result with AUC of 0.886. Combining both training and validation data resulted in a predictive model with AUC of 0.903. Further, we performed a "biological validation" by correlating risk scores with 6 islet autoantibodies, and found that the risk score was significantly correlated with IA-2A (Z-score = 3.628, P < 0.001). When applying this prediction model to the Swedish population, where the lifetime T1D risk ranges from 0.5% to 2%, we anticipate identifying approximately 20 000 high-risk subjects after testing all newborns, and this calculation would identify approximately 80% of all patients expected to develop T1D in their lifetime. Through both empirical and biological validation, we have established a prediction model for estimating lifetime T1D risk, using class II HLA. This prediction model should prove useful for future investigations to identify high-risk subjects for prevention research in high-risk populations. Copyright © 2017 John Wiley & Sons, Ltd.

Chemotherapy effectiveness and mortality prediction in surgically treated osteosarcoma dogs: A validation study.

PubMed

Schmidt, A F; Nielen, M; Withrow, S J; Selmic, L E; Burton, J H; Klungel, O H; Groenwold, R H H; Kirpensteijn, J

2016-03-01

Canine osteosarcoma is the most common bone cancer, and an important cause of mortality and morbidity, in large purebred dogs. Previously we constructed two multivariable models to predict a dog's 5-month or 1-year mortality risk after surgical treatment for osteosarcoma. According to the 5-month model, dogs with a relatively low risk of 5-month mortality benefited most from additional chemotherapy treatment. In the present study, we externally validated these results using an independent cohort study of 794 dogs. External performance of our prediction models showed some disagreement between observed and predicted risk, mean difference: -0.11 (95% confidence interval [95% CI]-0.29; 0.08) for 5-month risk and 0.25 (95%CI 0.10; 0.40) for 1-year mortality risk. After updating the intercept, agreement improved: -0.0004 (95%CI-0.16; 0.16) and -0.002 (95%CI-0.15; 0.15). The chemotherapy by predicted mortality risk interaction (P-value=0.01) showed that the chemotherapy compared to no chemotherapy effectiveness was modified by 5-month mortality risk: dogs with a relatively lower risk of mortality benefited most from additional chemotherapy. Chemotherapy effectiveness on 1-year mortality was not significantly modified by predicted risk (P-value=0.28). In conclusion, this external validation study confirmed that our multivariable risk prediction models can predict a patient's mortality risk and that dogs with a relatively lower risk of 5-month mortality seem to benefit most from chemotherapy. Copyright © 2016 Elsevier B.V. All rights reserved.

68Ga-PSMA-617 PET/CT: a promising new technique for predicting risk stratification and metastatic risk of prostate cancer patients.

PubMed

Liu, Chen; Liu, Teli; Zhang, Ning; Liu, Yiqiang; Li, Nan; Du, Peng; Yang, Yong; Liu, Ming; Gong, Kan; Yang, Xing; Zhu, Hua; Yan, Kun; Yang, Zhi

2018-05-02

The purpose of this study was to investigate the performance of 68 Ga-PSMA-617 PET/CT in predicting risk stratification and metastatic risk of prostate cancer. Fifty newly diagnosed patients with prostate cancer as confirmed by needle biopsy were continuously included, 40 in a train set and ten in a test set. 68 Ga-PSMA-617 PET/CT and clinical data of all patients were retrospectively analyzed. Semi-quantitative analysis of PET images provided maximum standardized uptake (SUVmax) of primary prostate cancer and volumetric parameters including intraprostatic PSMA-derived tumor volume (iPSMA-TV) and intraprostatic total lesion PSMA (iTL-PSMA). According to prostate cancer risk stratification criteria of the NCCN Guideline, all patients were simplified into a low-intermediate risk group or a high-risk group. The semi-quantitative parameters of 68 Ga-PSMA-617 PET/CT were used to establish a univariate logistic regression model for high-risk prostate cancer and its metastatic risk, and to evaluate the diagnostic efficacy of the predictive model. In the train set, 30/40 (75%) patients had high-risk prostate cancer and 10/40 (25%) patients had low-to-moderate-risk prostate cancer; in the test set, 8/10 (80%) patients had high-risk prostate cancer while 2/10 (20%) had low-intermediate risk prostate cancer. The univariate logistic regression model established with SUVmax, iPSMA-TV and iTL-PSMA could all effectively predict high-risk prostate cancer; the AUC of ROC were 0.843, 0.802 and 0.900, respectively. Based on the test set, the sensitivity and specificity of each model were 87.5% and 50% for SUVmax, 62.5% and 100% for iPSMA-TV, and 87.5% and 100% for iTL-PSMA, respectively. The iPSMA-TV and iTL-PSMA-based predictive model could predict the metastatic risk of prostate cancer, the AUC of ROC was 0.863 and 0.848, respectively, but the SUVmax-based prediction model could not predict metastatic risk. Semi-quantitative analysis indexes of 68 Ga-PSMA-617 PET/CT imaging can be used as "imaging biomarkers" to predict risk stratification and metastatic risk of prostate cancer.

Improving Disease Prediction by Incorporating Family Disease History in Risk Prediction Models with Large-Scale Genetic Data.

PubMed

Gim, Jungsoo; Kim, Wonji; Kwak, Soo Heon; Choi, Hosik; Park, Changyi; Park, Kyong Soo; Kwon, Sunghoon; Park, Taesung; Won, Sungho

2017-11-01

Despite the many successes of genome-wide association studies (GWAS), the known susceptibility variants identified by GWAS have modest effect sizes, leading to notable skepticism about the effectiveness of building a risk prediction model from large-scale genetic data. However, in contrast to genetic variants, the family history of diseases has been largely accepted as an important risk factor in clinical diagnosis and risk prediction. Nevertheless, the complicated structures of the family history of diseases have limited their application in clinical practice. Here, we developed a new method that enables incorporation of the general family history of diseases with a liability threshold model, and propose a new analysis strategy for risk prediction with penalized regression analysis that incorporates both large numbers of genetic variants and clinical risk factors. Application of our model to type 2 diabetes in the Korean population (1846 cases and 1846 controls) demonstrated that single-nucleotide polymorphisms accounted for 32.5% of the variation explained by the predicted risk scores in the test data set, and incorporation of family history led to an additional 6.3% improvement in prediction. Our results illustrate that family medical history provides valuable information on the variation of complex diseases and improves prediction performance. Copyright © 2017 by the Genetics Society of America.

Fetal Substance Exposure and Cumulative Environmental Risk in an African American Cohort

ERIC Educational Resources Information Center

Yumoto, Chie; Jacobson, Sandra W.; Jacobson, Joseph L.

2008-01-01

Two models of vulnerability to socioenvironmental risk were examined in 337 African American children (M = 7.8 years) recruited to overrepresent prenatal alcohol or cocaine exposure: The cumulative risk model predicted synergistic effects from exposure to multiple risk factors, and the fetal patterning of disease model predicted that prenatal…

Estimating community health needs against a Triple Aim background: What can we learn from current predictive risk models?

PubMed

Elissen, Arianne M J; Struijs, Jeroen N; Baan, Caroline A; Ruwaard, Dirk

2015-05-01

To support providers and commissioners in accurately assessing their local populations' health needs, this study produces an overview of Dutch predictive risk models for health care, focusing specifically on the type, combination and relevance of included determinants for achieving the Triple Aim (improved health, better care experience, and lower costs). We conducted a mixed-methods study combining document analyses, interviews and a Delphi study. Predictive risk models were identified based on a web search and expert input. Participating in the study were Dutch experts in predictive risk modelling (interviews; n=11) and experts in healthcare delivery, insurance and/or funding methodology (Delphi panel; n=15). Ten predictive risk models were analysed, comprising 17 unique determinants. Twelve were considered relevant by experts for estimating community health needs. Although some compositional similarities were identified between models, the combination and operationalisation of determinants varied considerably. Existing predictive risk models provide a good starting point, but optimally balancing resources and targeting interventions on the community level will likely require a more holistic approach to health needs assessment. Development of additional determinants, such as measures of people's lifestyle and social network, may require policies pushing the integration of routine data from different (healthcare) sources. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Risk model for estimating the 1-year risk of deferred lesion intervention following deferred revascularization after fractional flow reserve assessment.

PubMed

Depta, Jeremiah P; Patel, Jayendrakumar S; Novak, Eric; Gage, Brian F; Masrani, Shriti K; Raymer, David; Facey, Gabrielle; Patel, Yogesh; Zajarias, Alan; Lasala, John M; Amin, Amit P; Kurz, Howard I; Singh, Jasvindar; Bach, Richard G

2015-02-21

Although lesions deferred revascularization following fractional flow reserve (FFR) assessment have a low risk of adverse cardiac events, variability in risk for deferred lesion intervention (DLI) has not been previously evaluated. The aim of this study was to develop a prediction model to estimate 1-year risk of DLI for coronary lesions where revascularization was not performed following FFR assessment. A prediction model for DLI was developed from a cohort of 721 patients with 882 coronary lesions where revascularization was deferred based on FFR between 10/2002 and 7/2010. Deferred lesion intervention was defined as any revascularization of a lesion previously deferred following FFR. The final DLI model was developed using stepwise Cox regression and validated using bootstrapping techniques. An algorithm was constructed to predict the 1-year risk of DLI. During a mean (±SD) follow-up period of 4.0 ± 2.3 years, 18% of lesions deferred after FFR underwent DLI; the 1-year incidence of DLI was 5.3%, while the predicted risk of DLI varied from 1 to 40%. The final Cox model included the FFR value, age, current or former smoking, history of coronary artery disease (CAD) or prior percutaneous coronary intervention, multi-vessel CAD, and serum creatinine. The c statistic for the DLI prediction model was 0.66 (95% confidence interval, CI: 0.61-0.70). Patients deferred revascularization based on FFR have variation in their risk for DLI. A clinical prediction model consisting of five clinical variables and the FFR value can help predict the risk of DLI in the first year following FFR assessment. Published on behalf of the European Society of Cardiology. All rights reserved. © The Author 2014. For permissions please email: journals.permissions@oup.com.

A Predictive Risk Model for A(H7N9) Human Infections Based on Spatial-Temporal Autocorrelation and Risk Factors: China, 2013–2014

PubMed Central

Dong, Wen; Yang, Kun; Xu, Quan-Li; Yang, Yu-Lian

2015-01-01

This study investigated the spatial distribution, spatial autocorrelation, temporal cluster, spatial-temporal autocorrelation and probable risk factors of H7N9 outbreaks in humans from March 2013 to December 2014 in China. The results showed that the epidemic spread with significant spatial-temporal autocorrelation. In order to describe the spatial-temporal autocorrelation of H7N9, an improved model was developed by introducing a spatial-temporal factor in this paper. Logistic regression analyses were utilized to investigate the risk factors associated with their distribution, and nine risk factors were significantly associated with the occurrence of A(H7N9) human infections: the spatial-temporal factor φ (OR = 2546669.382, p < 0.001), migration route (OR = 0.993, p < 0.01), river (OR = 0.861, p < 0.001), lake(OR = 0.992, p < 0.001), road (OR = 0.906, p < 0.001), railway (OR = 0.980, p < 0.001), temperature (OR = 1.170, p < 0.01), precipitation (OR = 0.615, p < 0.001) and relative humidity (OR = 1.337, p < 0.001). The improved model obtained a better prediction performance and a higher fitting accuracy than the traditional model: in the improved model 90.1% (91/101) of the cases during February 2014 occurred in the high risk areas (the predictive risk > 0.70) of the predictive risk map, whereas 44.6% (45/101) of which overlaid on the high risk areas (the predictive risk > 0.70) for the traditional model, and the fitting accuracy of the improved model was 91.6% which was superior to the traditional model (86.1%). The predictive risk map generated based on the improved model revealed that the east and southeast of China were the high risk areas of A(H7N9) human infections in February 2014. These results provided baseline data for the control and prevention of future human infections. PMID:26633446

Indoor tanning and the MC1R genotype: risk prediction for basal cell carcinoma risk in young people.

PubMed

Molinaro, Annette M; Ferrucci, Leah M; Cartmel, Brenda; Loftfield, Erikka; Leffell, David J; Bale, Allen E; Mayne, Susan T

2015-06-01

Basal cell carcinoma (BCC) incidence is increasing, particularly in young people, and can be associated with significant morbidity and treatment costs. To identify young individuals at risk of BCC, we assessed existing melanoma or overall skin cancer risk prediction models and built a novel risk prediction model, with a focus on indoor tanning and the melanocortin 1 receptor gene, MC1R. We evaluated logistic regression models among 759 non-Hispanic whites from a case-control study of patients seen between 2006 and 2010 in New Haven, Connecticut. In our data, the adjusted area under the receiver operating characteristic curve (AUC) for a model by Han et al. (Int J Cancer. 2006;119(8):1976-1984) with 7 MC1R variants was 0.72 (95% confidence interval (CI): 0.66, 0.78), while that by Smith et al. (J Clin Oncol. 2012;30(15 suppl):8574) with MC1R and indoor tanning had an AUC of 0.69 (95% CI: 0.63, 0.75). Our base model had greater predictive ability than existing models and was significantly improved when we added ever-indoor tanning, burns from indoor tanning, and MC1R (AUC = 0.77, 95% CI: 0.74, 0.81). Our early-onset BCC risk prediction model incorporating MC1R and indoor tanning extends the work of other skin cancer risk prediction models, emphasizes the value of both genotype and indoor tanning in skin cancer risk prediction in young people, and should be validated with an independent cohort. © The Author 2015. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Development and external validation of a risk-prediction model to predict 5-year overall survival in advanced larynx cancer.

PubMed

Petersen, Japke F; Stuiver, Martijn M; Timmermans, Adriana J; Chen, Amy; Zhang, Hongzhen; O'Neill, James P; Deady, Sandra; Vander Poorten, Vincent; Meulemans, Jeroen; Wennerberg, Johan; Skroder, Carl; Day, Andrew T; Koch, Wayne; van den Brekel, Michiel W M

2018-05-01

TNM-classification inadequately estimates patient-specific overall survival (OS). We aimed to improve this by developing a risk-prediction model for patients with advanced larynx cancer. Cohort study. We developed a risk prediction model to estimate the 5-year OS rate based on a cohort of 3,442 patients with T3T4N0N+M0 larynx cancer. The model was internally validated using bootstrapping samples and externally validated on patient data from five external centers (n = 770). The main outcome was performance of the model as tested by discrimination, calibration, and the ability to distinguish risk groups based on tertiles from the derivation dataset. The model performance was compared to a model based on T and N classification only. We included age, gender, T and N classification, and subsite as prognostic variables in the standard model. After external validation, the standard model had a significantly better fit than a model based on T and N classification alone (C statistic, 0.59 vs. 0.55, P < .001). The model was able to distinguish well among three risk groups based on tertiles of the risk score. Adding treatment modality to the model did not decrease the predictive power. As a post hoc analysis, we tested the added value of comorbidity as scored by American Society of Anesthesiologists score in a subsample, which increased the C statistic to 0.68. A risk prediction model for patients with advanced larynx cancer, consisting of readily available clinical variables, gives more accurate estimations of the estimated 5-year survival rate when compared to a model based on T and N classification alone. 2c. Laryngoscope, 128:1140-1145, 2018. © 2017 The American Laryngological, Rhinological and Otological Society, Inc.

Enhanced risk prediction model for emergency department use and hospitalizations in patients in a primary care medical home.

PubMed

Takahashi, Paul Y; Heien, Herbert C; Sangaralingham, Lindsey R; Shah, Nilay D; Naessens, James M

2016-07-01

With the advent of healthcare payment reform, identifying high-risk populations has become more important to providers. Existing risk-prediction models often focus on chronic conditions. This study sought to better understand other factors to improve identification of the highest risk population. A retrospective cohort study of a paneled primary care population utilizing 2010 data to calibrate a risk prediction model of hospital and emergency department (ED) use in 2011. Data were randomly split into development and validation data sets. We compared the enhanced model containing the additional risk predictors with the Minnesota medical tiering model. The study was conducted in the primary care practice of an integrated delivery system at an academic medical center in Rochester, Minnesota. The study focus was primary care medical home patients in 2010 and 2011 (n = 84,752), with the primary outcome of subsequent hospitalization or ED visit. A total of 42,384 individuals derived the enhanced risk-prediction model and 42,368 individuals validated the model. Predictors included Adjusted Clinical Groups-based Minnesota medical tiering, patient demographics, insurance status, and prior year healthcare utilization. Additional variables included specific mental and medical conditions, use of high-risk medications, and body mass index. The area under the curve in the enhanced model was 0.705 (95% CI, 0.698-0.712) compared with 0.662 (95% CI, 0.656-0.669) in the Minnesota medical tiering-only model. New high-risk patients in the enhanced model were more likely to have lack of health insurance, presence of Medicaid, diagnosed depression, and prior ED utilization. An enhanced model including additional healthcare-related factors improved the prediction of risk of hospitalization or ED visit.

External Validation of the Garvan Nomograms for Predicting Absolute Fracture Risk: The Tromsø Study

PubMed Central

Ahmed, Luai A.; Nguyen, Nguyen D.; Bjørnerem, Åshild; Joakimsen, Ragnar M.; Jørgensen, Lone; Størmer, Jan; Bliuc, Dana; Center, Jacqueline R.; Eisman, John A.; Nguyen, Tuan V.; Emaus, Nina

2014-01-01

Background Absolute risk estimation is a preferred approach for assessing fracture risk and treatment decision making. This study aimed to evaluate and validate the predictive performance of the Garvan Fracture Risk Calculator in a Norwegian cohort. Methods The analysis included 1637 women and 1355 aged 60+ years from the Tromsø study. All incident fragility fractures between 2001 and 2009 were registered. The predicted probabilities of non-vertebral osteoporotic and hip fractures were determined using models with and without BMD. The discrimination and calibration of the models were assessed. Reclassification analysis was used to compare the models performance. Results The incidence of osteoporotic and hip fracture was 31.5 and 8.6 per 1000 population in women, respectively; in men the corresponding incidence was 12.2 and 5.1. The predicted 5-year and 10-year probability of fractures was consistently higher in the fracture group than the non-fracture group for all models. The 10-year predicted probabilities of hip fracture in those with fracture was 2.8 (women) to 3.1 times (men) higher than those without fracture. There was a close agreement between predicted and observed risk in both sexes and up to the fifth quintile. Among those in the highest quintile of risk, the models over-estimated the risk of fracture. Models with BMD performed better than models with body weight in correct classification of risk in individuals with and without fracture. The overall net decrease in reclassification of the model with weight compared to the model with BMD was 10.6% (p = 0.008) in women and 17.2% (p = 0.001) in men for osteoporotic fractures, and 13.3% (p = 0.07) in women and 17.5% (p = 0.09) in men for hip fracture. Conclusions The Garvan Fracture Risk Calculator is valid and clinically useful in identifying individuals at high risk of fracture. The models with BMD performed better than those with body weight in fracture risk prediction. PMID:25255221

On the estimation of risk associated with an attenuation prediction

NASA Technical Reports Server (NTRS)

Crane, R. K.

1992-01-01

Viewgraphs from a presentation on the estimation of risk associated with an attenuation prediction is presented. Topics covered include: link failure - attenuation exceeding a specified threshold for a specified time interval or intervals; risk - the probability of one or more failures during the lifetime of the link or during a specified accounting interval; the problem - modeling the probability of attenuation by rainfall to provide a prediction of the attenuation threshold for a specified risk; and an accounting for the inadequacy of a model or models.

Characterizing Decision-Analysis Performances of Risk Prediction Models Using ADAPT Curves.

PubMed

Lee, Wen-Chung; Wu, Yun-Chun

2016-01-01

The area under the receiver operating characteristic curve is a widely used index to characterize the performance of diagnostic tests and prediction models. However, the index does not explicitly acknowledge the utilities of risk predictions. Moreover, for most clinical settings, what counts is whether a prediction model can guide therapeutic decisions in a way that improves patient outcomes, rather than to simply update probabilities.Based on decision theory, the authors propose an alternative index, the "average deviation about the probability threshold" (ADAPT).An ADAPT curve (a plot of ADAPT value against the probability threshold) neatly characterizes the decision-analysis performances of a risk prediction model.Several prediction models can be compared for their ADAPT values at a chosen probability threshold, for a range of plausible threshold values, or for the whole ADAPT curves. This should greatly facilitate the selection of diagnostic tests and prediction models.

A systematic review of breast cancer incidence risk prediction models with meta-analysis of their performance.

PubMed

Meads, Catherine; Ahmed, Ikhlaaq; Riley, Richard D

2012-04-01

A risk prediction model is a statistical tool for estimating the probability that a currently healthy individual with specific risk factors will develop a condition in the future such as breast cancer. Reliably accurate prediction models can inform future disease burdens, health policies and individual decisions. Breast cancer prediction models containing modifiable risk factors, such as alcohol consumption, BMI or weight, condom use, exogenous hormone use and physical activity, are of particular interest to women who might be considering how to reduce their risk of breast cancer and clinicians developing health policies to reduce population incidence rates. We performed a systematic review to identify and evaluate the performance of prediction models for breast cancer that contain modifiable factors. A protocol was developed and a sensitive search in databases including MEDLINE and EMBASE was conducted in June 2010. Extensive use was made of reference lists. Included were any articles proposing or validating a breast cancer prediction model in a general female population, with no language restrictions. Duplicate data extraction and quality assessment were conducted. Results were summarised qualitatively, and where possible meta-analysis of model performance statistics was undertaken. The systematic review found 17 breast cancer models, each containing a different but often overlapping set of modifiable and other risk factors, combined with an estimated baseline risk that was also often different. Quality of reporting was generally poor, with characteristics of included participants and fitted model results often missing. Only four models received independent validation in external data, most notably the 'Gail 2' model with 12 validations. None of the models demonstrated consistently outstanding ability to accurately discriminate between those who did and those who did not develop breast cancer. For example, random-effects meta-analyses of the performance of the 'Gail 2' model showed the average C statistic was 0.63 (95% CI 0.59-0.67), and the expected/observed ratio of events varied considerably across studies (95% prediction interval for E/O ratio when the model was applied in practice was 0.75-1.19). There is a need for models with better predictive performance but, given the large amount of work already conducted, further improvement of existing models based on conventional risk factors is perhaps unlikely. Research to identify new risk factors with large additionally predictive ability is therefore needed, alongside clearer reporting and continual validation of new models as they develop.

Development of a Melanoma Risk Prediction Model Incorporating MC1R Genotype and Indoor Tanning Exposure: Impact of Mole Phenotype on Model Performance

PubMed Central

Penn, Lauren A.; Qian, Meng; Zhang, Enhan; Ng, Elise; Shao, Yongzhao; Berwick, Marianne; Lazovich, DeAnn; Polsky, David

2014-01-01

Background Identifying individuals at increased risk for melanoma could potentially improve public health through targeted surveillance and early detection. Studies have separately demonstrated significant associations between melanoma risk, melanocortin receptor (MC1R) polymorphisms, and indoor ultraviolet light (UV) exposure. Existing melanoma risk prediction models do not include these factors; therefore, we investigated their potential to improve the performance of a risk model. Methods Using 875 melanoma cases and 765 controls from the population-based Minnesota Skin Health Study we compared the predictive ability of a clinical melanoma risk model (Model A) to an enhanced model (Model F) using receiver operating characteristic (ROC) curves. Model A used self-reported conventional risk factors including mole phenotype categorized as “none”, “few”, “some” or “many” moles. Model F added MC1R genotype and measures of indoor and outdoor UV exposure to Model A. We also assessed the predictive ability of these models in subgroups stratified by mole phenotype (e.g. nevus-resistant (“none” and “few” moles) and nevus-prone (“some” and “many” moles)). Results Model A (the reference model) yielded an area under the ROC curve (AUC) of 0.72 (95% CI = 0.69, 0.74). Model F was improved with an AUC = 0.74 (95% CI = 0.71–0.76, p<0.01). We also observed substantial variations in the AUCs of Models A & F when examined in the nevus-prone and nevus-resistant subgroups. Conclusions These results demonstrate that adding genotypic information and environmental exposure data can increase the predictive ability of a clinical melanoma risk model, especially among nevus-prone individuals. PMID:25003831

Predictive Accuracy of the Liverpool Lung Project Risk Model for Stratifying Patients for Computed Tomography Screening for Lung Cancer

PubMed Central

Raji, Olaide Y.; Duffy, Stephen W.; Agbaje, Olorunshola F.; Baker, Stuart G.; Christiani, David C.; Cassidy, Adrian; Field, John K.

2013-01-01

Background External validation of existing lung cancer risk prediction models is limited. Using such models in clinical practice to guide the referral of patients for computed tomography (CT) screening for lung cancer depends on external validation and evidence of predicted clinical benefit. Objective To evaluate the discrimination of the Liverpool Lung Project (LLP) risk model and demonstrate its predicted benefit for stratifying patients for CT screening by using data from 3 independent studies from Europe and North America. Design Case–control and prospective cohort study. Setting Europe and North America. Patients Participants in the European Early Lung Cancer (EUELC) and Harvard case–control studies and the LLP population-based prospective cohort (LLPC) study. Measurements 5-year absolute risks for lung cancer predicted by the LLP model. Results The LLP risk model had good discrimination in both the Harvard (area under the receiver-operating characteristic curve [AUC], 0.76 [95% CI, 0.75 to 0.78]) and the LLPC (AUC, 0.82 [CI, 0.80 to 0.85]) studies and modest discrimination in the EUELC (AUC, 0.67 [CI, 0.64 to 0.69]) study. The decision utility analysis, which incorporates the harms and benefit of using a risk model to make clinical decisions, indicates that the LLP risk model performed better than smoking duration or family history alone in stratifying high-risk patients for lung cancer CT screening. Limitations The model cannot assess whether including other risk factors, such as lung function or genetic markers, would improve accuracy. Lack of information on asbestos exposure in the LLPC limited the ability to validate the complete LLP risk model. Conclusion Validation of the LLP risk model in 3 independent external data sets demonstrated good discrimination and evidence of predicted benefits for stratifying patients for lung cancer CT screening. Further studies are needed to prospectively evaluate model performance and evaluate the optimal population risk thresholds for initiating lung cancer screening. Primary Funding Source Roy Castle Lung Cancer Foundation. PMID:22910935

Developing and validating risk prediction models in an individual participant data meta-analysis

PubMed Central

2014-01-01

Background Risk prediction models estimate the risk of developing future outcomes for individuals based on one or more underlying characteristics (predictors). We review how researchers develop and validate risk prediction models within an individual participant data (IPD) meta-analysis, in order to assess the feasibility and conduct of the approach. Methods A qualitative review of the aims, methodology, and reporting in 15 articles that developed a risk prediction model using IPD from multiple studies. Results The IPD approach offers many opportunities but methodological challenges exist, including: unavailability of requested IPD, missing patient data and predictors, and between-study heterogeneity in methods of measurement, outcome definitions and predictor effects. Most articles develop their model using IPD from all available studies and perform only an internal validation (on the same set of data). Ten of the 15 articles did not allow for any study differences in baseline risk (intercepts), potentially limiting their model’s applicability and performance in some populations. Only two articles used external validation (on different data), including a novel method which develops the model on all but one of the IPD studies, tests performance in the excluded study, and repeats by rotating the omitted study. Conclusions An IPD meta-analysis offers unique opportunities for risk prediction research. Researchers can make more of this by allowing separate model intercept terms for each study (population) to improve generalisability, and by using ‘internal-external cross-validation’ to simultaneously develop and validate their model. Methodological challenges can be reduced by prospectively planned collaborations that share IPD for risk prediction. PMID:24397587

The Development of Statistical Models for Predicting Surgical Site Infections in Japan: Toward a Statistical Model-Based Standardized Infection Ratio.

PubMed

Fukuda, Haruhisa; Kuroki, Manabu

2016-03-01

To develop and internally validate a surgical site infection (SSI) prediction model for Japan. Retrospective observational cohort study. We analyzed surveillance data submitted to the Japan Nosocomial Infections Surveillance system for patients who had undergone target surgical procedures from January 1, 2010, through December 31, 2012. Logistic regression analyses were used to develop statistical models for predicting SSIs. An SSI prediction model was constructed for each of the procedure categories by statistically selecting the appropriate risk factors from among the collected surveillance data and determining their optimal categorization. Standard bootstrapping techniques were applied to assess potential overfitting. The C-index was used to compare the predictive performances of the new statistical models with those of models based on conventional risk index variables. The study sample comprised 349,987 cases from 428 participant hospitals throughout Japan, and the overall SSI incidence was 7.0%. The C-indices of the new statistical models were significantly higher than those of the conventional risk index models in 21 (67.7%) of the 31 procedure categories (P<.05). No significant overfitting was detected. Japan-specific SSI prediction models were shown to generally have higher accuracy than conventional risk index models. These new models may have applications in assessing hospital performance and identifying high-risk patients in specific procedure categories.

Acute Brain Dysfunction: Development and Validation of a Daily Prediction Model.

PubMed

Marra, Annachiara; Pandharipande, Pratik P; Shotwell, Matthew S; Chandrasekhar, Rameela; Girard, Timothy D; Shintani, Ayumi K; Peelen, Linda M; Moons, Karl G M; Dittus, Robert S; Ely, E Wesley; Vasilevskis, Eduard E

2018-03-24

The goal of this study was to develop and validate a dynamic risk model to predict daily changes in acute brain dysfunction (ie, delirium and coma), discharge, and mortality in ICU patients. Using data from a multicenter prospective ICU cohort, a daily acute brain dysfunction-prediction model (ABD-pm) was developed by using multinomial logistic regression that estimated 15 transition probabilities (from one of three brain function states [normal, delirious, or comatose] to one of five possible outcomes [normal, delirious, comatose, ICU discharge, or died]) using baseline and daily risk factors. Model discrimination was assessed by using predictive characteristics such as negative predictive value (NPV). Calibration was assessed by plotting empirical vs model-estimated probabilities. Internal validation was performed by using a bootstrap procedure. Data were analyzed from 810 patients (6,711 daily transitions). The ABD-pm included individual risk factors: mental status, age, preexisting cognitive impairment, baseline and daily severity of illness, and daily administration of sedatives. The model yielded very high NPVs for "next day" delirium (NPV: 0.823), coma (NPV: 0.892), normal cognitive state (NPV: 0.875), ICU discharge (NPV: 0.905), and mortality (NPV: 0.981). The model demonstrated outstanding calibration when predicting the total number of patients expected to be in any given state across predicted risk. We developed and internally validated a dynamic risk model that predicts the daily risk for one of three cognitive states, ICU discharge, or mortality. The ABD-pm may be useful for predicting the proportion of patients for each outcome state across entire ICU populations to guide quality, safety, and care delivery activities. Copyright © 2018 American College of Chest Physicians. Published by Elsevier Inc. All rights reserved.

One vs. Two Breast Density Measures to Predict 5- and 10- Year Breast Cancer Risk

PubMed Central

Kerlikowske, Karla; Gard, Charlotte C.; Sprague, Brian L.; Tice, Jeffrey A.; Miglioretti, Diana L.

2015-01-01

Background One measure of Breast Imaging Reporting and Data System (BI-RADS) breast density improves 5-year breast cancer risk prediction, but the value of sequential measures is unknown. We determined if two BI-RADS density measures improves the predictive accuracy of the Breast Cancer Surveillance Consortium 5-year risk model compared to one measure. Methods We included 722,654 women aged 35–74 years with two mammograms with BI-RADS density measures on average 1.8 years apart; 13,715 developed invasive breast cancer. We used Cox regression to estimate the relative hazards of breast cancer for age, race/ethnicity, family history of breast cancer, history of breast biopsy, and one or two density measures. We developed a risk prediction model by combining these estimates with 2000–2010 Surveillance, Epidemiology, and End Results incidence and 2010 vital statistics for competing risk of death. Results The two-measure density model had marginally greater discriminatory accuracy than the one-measure model (AUC=0.640 vs. 0.635). Of 18.6% of women (134,404/722,654) who decreased density categories, 15.4% (20,741/134,404) of women whose density decreased from heterogeneously or extremely dense to a lower density category with one other risk factor had a clinically meaningful increase in 5-year risk from <1.67% with the one-density model to ≥1.67% with the two-density model. Conclusion The two-density model has similar overall discrimination to the one-density model for predicting 5-year breast cancer risk and improves risk classification for women with risk factors and a decrease in density. Impact A two-density model should be considered for women whose density decreases when calculating breast cancer risk. PMID:25824444

One versus Two Breast Density Measures to Predict 5- and 10-Year Breast Cancer Risk.

PubMed

Kerlikowske, Karla; Gard, Charlotte C; Sprague, Brian L; Tice, Jeffrey A; Miglioretti, Diana L

2015-06-01

One measure of Breast Imaging Reporting and Data System (BI-RADS) breast density improves 5-year breast cancer risk prediction, but the value of sequential measures is unknown. We determined whether two BI-RADS density measures improve the predictive accuracy of the Breast Cancer Surveillance Consortium 5-year risk model compared with one measure. We included 722,654 women of ages 35 to 74 years with two mammograms with BI-RADS density measures on average 1.8 years apart; 13,715 developed invasive breast cancer. We used Cox regression to estimate the relative hazards of breast cancer for age, race/ethnicity, family history of breast cancer, history of breast biopsy, and one or two density measures. We developed a risk prediction model by combining these estimates with 2000-2010 Surveillance, Epidemiology, and End Results incidence and 2010 vital statistics for competing risk of death. The two-measure density model had marginally greater discriminatory accuracy than the one-measure model (AUC, 0.640 vs. 0.635). Of 18.6% of women (134,404 of 722,654) who decreased density categories, 15.4% (20,741 of 134,404) of women whose density decreased from heterogeneously or extremely dense to a lower density category with one other risk factor had a clinically meaningful increase in 5-year risk from <1.67% with the one-density model to ≥1.67% with the two-density model. The two-density model has similar overall discrimination to the one-density model for predicting 5-year breast cancer risk and improves risk classification for women with risk factors and a decrease in density. A two-density model should be considered for women whose density decreases when calculating breast cancer risk. ©2015 American Association for Cancer Research.

Perception of Risk and Terrorism-Related Behavior Change: Dual Influences of Probabilistic Reasoning and Reality Testing.

PubMed

Denovan, Andrew; Dagnall, Neil; Drinkwater, Kenneth; Parker, Andrew; Clough, Peter

2017-01-01

The present study assessed the degree to which probabilistic reasoning performance and thinking style influenced perception of risk and self-reported levels of terrorism-related behavior change. A sample of 263 respondents, recruited via convenience sampling, completed a series of measures comprising probabilistic reasoning tasks (perception of randomness, base rate, probability, and conjunction fallacy), the Reality Testing subscale of the Inventory of Personality Organization (IPO-RT), the Domain-Specific Risk-Taking Scale, and a terrorism-related behavior change scale. Structural equation modeling examined three progressive models. Firstly, the Independence Model assumed that probabilistic reasoning, perception of risk and reality testing independently predicted terrorism-related behavior change. Secondly, the Mediation Model supposed that probabilistic reasoning and reality testing correlated, and indirectly predicted terrorism-related behavior change through perception of risk. Lastly, the Dual-Influence Model proposed that probabilistic reasoning indirectly predicted terrorism-related behavior change via perception of risk, independent of reality testing. Results indicated that performance on probabilistic reasoning tasks most strongly predicted perception of risk, and preference for an intuitive thinking style (measured by the IPO-RT) best explained terrorism-related behavior change. The combination of perception of risk with probabilistic reasoning ability in the Dual-Influence Model enhanced the predictive power of the analytical-rational route, with conjunction fallacy having a significant indirect effect on terrorism-related behavior change via perception of risk. The Dual-Influence Model possessed superior fit and reported similar predictive relations between intuitive-experiential and analytical-rational routes and terrorism-related behavior change. The discussion critically examines these findings in relation to dual-processing frameworks. This includes considering the limitations of current operationalisations and recommendations for future research that align outcomes and subsequent work more closely to specific dual-process models.

Perception of Risk and Terrorism-Related Behavior Change: Dual Influences of Probabilistic Reasoning and Reality Testing

PubMed Central

Denovan, Andrew; Dagnall, Neil; Drinkwater, Kenneth; Parker, Andrew; Clough, Peter

2017-01-01

The present study assessed the degree to which probabilistic reasoning performance and thinking style influenced perception of risk and self-reported levels of terrorism-related behavior change. A sample of 263 respondents, recruited via convenience sampling, completed a series of measures comprising probabilistic reasoning tasks (perception of randomness, base rate, probability, and conjunction fallacy), the Reality Testing subscale of the Inventory of Personality Organization (IPO-RT), the Domain-Specific Risk-Taking Scale, and a terrorism-related behavior change scale. Structural equation modeling examined three progressive models. Firstly, the Independence Model assumed that probabilistic reasoning, perception of risk and reality testing independently predicted terrorism-related behavior change. Secondly, the Mediation Model supposed that probabilistic reasoning and reality testing correlated, and indirectly predicted terrorism-related behavior change through perception of risk. Lastly, the Dual-Influence Model proposed that probabilistic reasoning indirectly predicted terrorism-related behavior change via perception of risk, independent of reality testing. Results indicated that performance on probabilistic reasoning tasks most strongly predicted perception of risk, and preference for an intuitive thinking style (measured by the IPO-RT) best explained terrorism-related behavior change. The combination of perception of risk with probabilistic reasoning ability in the Dual-Influence Model enhanced the predictive power of the analytical-rational route, with conjunction fallacy having a significant indirect effect on terrorism-related behavior change via perception of risk. The Dual-Influence Model possessed superior fit and reported similar predictive relations between intuitive-experiential and analytical-rational routes and terrorism-related behavior change. The discussion critically examines these findings in relation to dual-processing frameworks. This includes considering the limitations of current operationalisations and recommendations for future research that align outcomes and subsequent work more closely to specific dual-process models. PMID:29062288

The assisted prediction modelling frame with hybridisation and ensemble for business risk forecasting and an implementation

NASA Astrophysics Data System (ADS)

Li, Hui; Hong, Lu-Yao; Zhou, Qing; Yu, Hai-Jie

2015-08-01

The business failure of numerous companies results in financial crises. The high social costs associated with such crises have made people to search for effective tools for business risk prediction, among which, support vector machine is very effective. Several modelling means, including single-technique modelling, hybrid modelling, and ensemble modelling, have been suggested in forecasting business risk with support vector machine. However, existing literature seldom focuses on the general modelling frame for business risk prediction, and seldom investigates performance differences among different modelling means. We reviewed researches on forecasting business risk with support vector machine, proposed the general assisted prediction modelling frame with hybridisation and ensemble (APMF-WHAE), and finally, investigated the use of principal components analysis, support vector machine, random sampling, and group decision, under the general frame in forecasting business risk. Under the APMF-WHAE frame with support vector machine as the base predictive model, four specific predictive models were produced, namely, pure support vector machine, a hybrid support vector machine involved with principal components analysis, a support vector machine ensemble involved with random sampling and group decision, and an ensemble of hybrid support vector machine using group decision to integrate various hybrid support vector machines on variables produced from principle components analysis and samples from random sampling. The experimental results indicate that hybrid support vector machine and ensemble of hybrid support vector machines were able to produce dominating performance than pure support vector machine and support vector machine ensemble.

Multimethod Prediction of Physical Parent-Child Aggression Risk in Expectant Mothers and Fathers with Social Information Processing Theory

PubMed Central

Rodriguez, Christina M.; Smith, Tamika L.; Silvia, Paul J.

2015-01-01

The Social Information Processing (SIP) model postulates that parents undergo a series of stages in implementing physical discipline that can escalate into physical child abuse. The current study utilized a multimethod approach to investigate whether SIP factors can predict risk of parent-child aggression (PCA) in a diverse sample of expectant mothers and fathers. SIP factors of PCA attitudes, negative child attributions, reactivity, and empathy were considered as potential predictors of PCA risk; additionally, analyses considered whether personal history of PCA predicted participants’ own PCA risk through its influence on their attitudes and attributions. Findings indicate that, for both mothers and fathers, history influenced attitudes but not attributions in predicting PCA risk, and attitudes and attributions predicted PCA risk; empathy and reactivity predicted negative child attributions for expectant mothers, but only reactivity significantly predicted attributions for expectant fathers. Path models for expectant mothers and fathers were remarkably similar. Overall, the findings provide support for major aspects of the SIP model. Continued work is needed in studying the progression of these factors across time for both mothers and fathers as well as the inclusion of other relevant ecological factors to the SIP model. PMID:26631420

Cardiovascular risk prediction in HIV-infected patients: comparing the Framingham, atherosclerotic cardiovascular disease risk score (ASCVD), Systematic Coronary Risk Evaluation for the Netherlands (SCORE-NL) and Data Collection on Adverse Events of Anti-HIV Drugs (D:A:D) risk prediction models.

PubMed

Krikke, M; Hoogeveen, R C; Hoepelman, A I M; Visseren, F L J; Arends, J E

2016-04-01

The aim of the study was to compare the predictions of five popular cardiovascular disease (CVD) risk prediction models, namely the Data Collection on Adverse Events of Anti-HIV Drugs (D:A:D) model, the Framingham Heart Study (FHS) coronary heart disease (FHS-CHD) and general CVD (FHS-CVD) models, the American Heart Association (AHA) atherosclerotic cardiovascular disease risk score (ASCVD) model and the Systematic Coronary Risk Evaluation for the Netherlands (SCORE-NL) model. A cross-sectional design was used to compare the cumulative CVD risk predictions of the models. Furthermore, the predictions of the general CVD models were compared with those of the HIV-specific D:A:D model using three categories (< 10%, 10-20% and > 20%) to categorize the risk and to determine the degree to which patients were categorized similarly or in a higher/lower category. A total of 997 HIV-infected patients were included in the study: 81% were male and they had a median age of 46 [interquartile range (IQR) 40-52] years, a known duration of HIV infection of 6.8 (IQR 3.7-10.9) years, and a median time on ART of 6.4 (IQR 3.0-11.5) years. The D:A:D, ASCVD and SCORE-NL models gave a lower cumulative CVD risk, compared with that of the FHS-CVD and FHS-CHD models. Comparing the general CVD models with the D:A:D model, the FHS-CVD and FHS-CHD models only classified 65% and 79% of patients, respectively, in the same category as did the D:A:D model. However, for the ASCVD and SCORE-NL models, this percentage was 89% and 87%, respectively. Furthermore, FHS-CVD and FHS-CHD attributed a higher CVD risk to 33% and 16% of patients, respectively, while this percentage was < 6% for ASCVD and SCORE-NL. When using FHS-CVD and FHS-CHD, a higher overall CVD risk was attributed to the HIV-infected patients than when using the D:A:D, ASCVD and SCORE-NL models. This could have consequences regarding overtreatment, drug-related adverse events and drug-drug interactions. © 2015 British HIV Association.

Comparing motor-vehicle crash risk of EU and US vehicles.

PubMed

Flannagan, Carol A C; Bálint, András; Klinich, Kathleen D; Sander, Ulrich; Manary, Miriam A; Cuny, Sophie; McCarthy, Michael; Phan, Vuthy; Wallbank, Caroline; Green, Paul E; Sui, Bo; Forsman, Åsa; Fagerlind, Helen

2018-08-01

This study examined the hypotheses that passenger vehicles meeting European Union (EU) safety standards have similar crashworthiness to United States (US) -regulated vehicles in the US driving environment, and vice versa. The first step involved identifying appropriate databases of US and EU crashes that include in-depth crash information, such as estimation of crash severity using Delta-V and injury outcome based on medical records. The next step was to harmonize variable definitions and sampling criteria so that the EU data could be combined and compared to the US data using the same or equivalent parameters. Logistic regression models of the risk of a Maximum injury according to the Abbreviated Injury Scale of 3 or greater, or fatality (MAIS3+F) in EU-regulated and US-regulated vehicles were constructed. The injury risk predictions of the EU model and the US model were each applied to both the US and EU standard crash populations. Frontal, near-side, and far-side crashes were analyzed together (termed "front/side crashes") and a separate model was developed for rollover crashes. For the front/side model applied to the US standard population, the mean estimated risk for the US-vehicle model is 0.035 (sd = 0.012), and the mean estimated risk for the EU-vehicle model is 0.023 (sd = 0.016). When applied to the EU front/side population, the US model predicted a 0.065 risk (sd = 0.027), and the EU model predicted a 0.052 risk (sd = 0.025). For the rollover model applied to the US standard population, the US model predicted a risk of 0.071 (sd = 0.024), and the EU model predicted 0.128 risk (sd = 0.057). When applied to the EU rollover standard population, the US model predicted a 0.067 risk (sd = 0.024), and the EU model predicted 0.103 risk (sd = 0.040). The results based on these methods indicate that EU vehicles most likely have a lower risk of MAIS3+F injury in front/side impacts, while US vehicles most likely have a lower risk of MAIS3+F injury in llroovers. These results should be interpreted with an understanding of the uncertainty of the estimates, the study limitations, and our recommendations for further study detailed in the report. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

Evaluation of the DAVROS (Development And Validation of Risk-adjusted Outcomes for Systems of emergency care) risk-adjustment model as a quality indicator for healthcare

PubMed Central

Wilson, Richard; Goodacre, Steve W; Klingbajl, Marcin; Kelly, Anne-Maree; Rainer, Tim; Coats, Tim; Holloway, Vikki; Townend, Will; Crane, Steve

2014-01-01

Background and objective Risk-adjusted mortality rates can be used as a quality indicator if it is assumed that the discrepancy between predicted and actual mortality can be attributed to the quality of healthcare (ie, the model has attributional validity). The Development And Validation of Risk-adjusted Outcomes for Systems of emergency care (DAVROS) model predicts 7-day mortality in emergency medical admissions. We aimed to test this assumption by evaluating the attributional validity of the DAVROS risk-adjustment model. Methods We selected cases that had the greatest discrepancy between observed mortality and predicted probability of mortality from seven hospitals involved in validation of the DAVROS risk-adjustment model. Reviewers at each hospital assessed hospital records to determine whether the discrepancy between predicted and actual mortality could be explained by the healthcare provided. Results We received 232/280 (83%) completed review forms relating to 179 unexpected deaths and 53 unexpected survivors. The healthcare system was judged to have potentially contributed to 10/179 (8%) of the unexpected deaths and 26/53 (49%) of the unexpected survivors. Failure of the model to appropriately predict risk was judged to be responsible for 135/179 (75%) of the unexpected deaths and 2/53 (4%) of the unexpected survivors. Some 10/53 (19%) of the unexpected survivors died within a few months of the 7-day period of model prediction. Conclusions We found little evidence that deaths occurring in patients with a low predicted mortality from risk-adjustment could be attributed to the quality of healthcare provided. PMID:23605036

Estimating wildfire risk on a Mojave Desert landscape using remote sensing and field sampling

USGS Publications Warehouse

Van Linn, Peter F.; Nussear, Kenneth E.; Esque, Todd C.; DeFalco, Lesley A.; Inman, Richard D.; Abella, Scott R.

2013-01-01

Predicting wildfires that affect broad landscapes is important for allocating suppression resources and guiding land management. Wildfire prediction in the south-western United States is of specific concern because of the increasing prevalence and severe effects of fire on desert shrublands and the current lack of accurate fire prediction tools. We developed a fire risk model to predict fire occurrence in a north-eastern Mojave Desert landscape. First we developed a spatial model using remote sensing data to predict fuel loads based on field estimates of fuels. We then modelled fire risk (interactions of fuel characteristics and environmental conditions conducive to wildfire) using satellite imagery, our model of fuel loads, and spatial data on ignition potential (lightning strikes and distance to roads), topography (elevation and aspect) and climate (maximum and minimum temperatures). The risk model was developed during a fire year at our study landscape and validated at a nearby landscape; model performance was accurate and similar at both sites. This study demonstrates that remote sensing techniques used in combination with field surveys can accurately predict wildfire risk in the Mojave Desert and may be applicable to other arid and semiarid lands where wildfires are prevalent.

Predicting Risk of Suicide Attempt Using History of Physical Illnesses From Electronic Medical Records

PubMed Central

Luo, Wei; Tran, Truyen; Berk, Michael; Venkatesh, Svetha

2016-01-01

Background Although physical illnesses, routinely documented in electronic medical records (EMR), have been found to be a contributing factor to suicides, no automated systems use this information to predict suicide risk. Objective The aim of this study is to quantify the impact of physical illnesses on suicide risk, and develop a predictive model that captures this relationship using EMR data. Methods We used history of physical illnesses (except chapter V: Mental and behavioral disorders) from EMR data over different time-periods to build a lookup table that contains the probability of suicide risk for each chapter of the International Statistical Classification of Diseases and Related Health Problems, 10th Revision (ICD-10) codes. The lookup table was then used to predict the probability of suicide risk for any new assessment. Based on the different lengths of history of physical illnesses, we developed six different models to predict suicide risk. We tested the performance of developed models to predict 90-day risk using historical data over differing time-periods ranging from 3 to 48 months. A total of 16,858 assessments from 7399 mental health patients with at least one risk assessment was used for the validation of the developed model. The performance was measured using area under the receiver operating characteristic curve (AUC). Results The best predictive results were derived (AUC=0.71) using combined data across all time-periods, which significantly outperformed the clinical baseline derived from routine risk assessment (AUC=0.56). The proposed approach thus shows potential to be incorporated in the broader risk assessment processes used by clinicians. Conclusions This study provides a novel approach to exploit the history of physical illnesses extracted from EMR (ICD-10 codes without chapter V-mental and behavioral disorders) to predict suicide risk, and this model outperforms existing clinical assessments of suicide risk. PMID:27400764

Risk prediction models for graft failure in kidney transplantation: a systematic review.

PubMed

Kaboré, Rémi; Haller, Maria C; Harambat, Jérôme; Heinze, Georg; Leffondré, Karen

2017-04-01

Risk prediction models are useful for identifying kidney recipients at high risk of graft failure, thus optimizing clinical care. Our objective was to systematically review the models that have been recently developed and validated to predict graft failure in kidney transplantation recipients. We used PubMed and Scopus to search for English, German and French language articles published in 2005-15. We selected studies that developed and validated a new risk prediction model for graft failure after kidney transplantation, or validated an existing model with or without updating the model. Data on recipient characteristics and predictors, as well as modelling and validation methods were extracted. In total, 39 articles met the inclusion criteria. Of these, 34 developed and validated a new risk prediction model and 5 validated an existing one with or without updating the model. The most frequently predicted outcome was graft failure, defined as dialysis, re-transplantation or death with functioning graft. Most studies used the Cox model. There was substantial variability in predictors used. In total, 25 studies used predictors measured at transplantation only, and 14 studies used predictors also measured after transplantation. Discrimination performance was reported in 87% of studies, while calibration was reported in 56%. Performance indicators were estimated using both internal and external validation in 13 studies, and using external validation only in 6 studies. Several prediction models for kidney graft failure in adults have been published. Our study highlights the need to better account for competing risks when applicable in such studies, and to adequately account for post-transplant measures of predictors in studies aiming at improving monitoring of kidney transplant recipients. © The Author 2017. Published by Oxford University Press on behalf of ERA-EDTA. All rights reserved.

Use of Repeated Blood Pressure and Cholesterol Measurements to Improve Cardiovascular Disease Risk Prediction: An Individual-Participant-Data Meta-Analysis

PubMed Central

Barrett, Jessica; Pennells, Lisa; Sweeting, Michael; Willeit, Peter; Di Angelantonio, Emanuele; Gudnason, Vilmundur; Nordestgaard, Børge G.; Psaty, Bruce M; Goldbourt, Uri; Best, Lyle G; Assmann, Gerd; Salonen, Jukka T; Nietert, Paul J; Verschuren, W. M. Monique; Brunner, Eric J; Kronmal, Richard A; Salomaa, Veikko; Bakker, Stephan J L; Dagenais, Gilles R; Sato, Shinichi; Jansson, Jan-Håkan; Willeit, Johann; Onat, Altan; de la Cámara, Agustin Gómez; Roussel, Ronan; Völzke, Henry; Dankner, Rachel; Tipping, Robert W; Meade, Tom W; Donfrancesco, Chiara; Kuller, Lewis H; Peters, Annette; Gallacher, John; Kromhout, Daan; Iso, Hiroyasu; Knuiman, Matthew; Casiglia, Edoardo; Kavousi, Maryam; Palmieri, Luigi; Sundström, Johan; Davis, Barry R; Njølstad, Inger; Couper, David; Danesh, John; Thompson, Simon G; Wood, Angela

2017-01-01

Abstract The added value of incorporating information from repeated blood pressure and cholesterol measurements to predict cardiovascular disease (CVD) risk has not been rigorously assessed. We used data on 191,445 adults from the Emerging Risk Factors Collaboration (38 cohorts from 17 countries with data encompassing 1962–2014) with more than 1 million measurements of systolic blood pressure, total cholesterol, and high-density lipoprotein cholesterol. Over a median 12 years of follow-up, 21,170 CVD events occurred. Risk prediction models using cumulative mean values of repeated measurements and summary measures from longitudinal modeling of the repeated measurements were compared with models using measurements from a single time point. Risk discrimination (C-index) and net reclassification were calculated, and changes in C-indices were meta-analyzed across studies. Compared with the single-time-point model, the cumulative means and longitudinal models increased the C-index by 0.0040 (95% confidence interval (CI): 0.0023, 0.0057) and 0.0023 (95% CI: 0.0005, 0.0042), respectively. Reclassification was also improved in both models; compared with the single-time-point model, overall net reclassification improvements were 0.0369 (95% CI: 0.0303, 0.0436) for the cumulative-means model and 0.0177 (95% CI: 0.0110, 0.0243) for the longitudinal model. In conclusion, incorporating repeated measurements of blood pressure and cholesterol into CVD risk prediction models slightly improves risk prediction. PMID:28549073

Risk Prediction for Epithelial Ovarian Cancer in 11 United States–Based Case-Control Studies: Incorporation of Epidemiologic Risk Factors and 17 Confirmed Genetic Loci

PubMed Central

Clyde, Merlise A.; Palmieri Weber, Rachel; Iversen, Edwin S.; Poole, Elizabeth M.; Doherty, Jennifer A.; Goodman, Marc T.; Ness, Roberta B.; Risch, Harvey A.; Rossing, Mary Anne; Terry, Kathryn L.; Wentzensen, Nicolas; Whittemore, Alice S.; Anton-Culver, Hoda; Bandera, Elisa V.; Berchuck, Andrew; Carney, Michael E.; Cramer, Daniel W.; Cunningham, Julie M.; Cushing-Haugen, Kara L.; Edwards, Robert P.; Fridley, Brooke L.; Goode, Ellen L.; Lurie, Galina; McGuire, Valerie; Modugno, Francesmary; Moysich, Kirsten B.; Olson, Sara H.; Pearce, Celeste Leigh; Pike, Malcolm C.; Rothstein, Joseph H.; Sellers, Thomas A.; Sieh, Weiva; Stram, Daniel; Thompson, Pamela J.; Vierkant, Robert A.; Wicklund, Kristine G.; Wu, Anna H.; Ziogas, Argyrios; Tworoger, Shelley S.; Schildkraut, Joellen M.

2016-01-01

Previously developed models for predicting absolute risk of invasive epithelial ovarian cancer have included a limited number of risk factors and have had low discriminatory power (area under the receiver operating characteristic curve (AUC) < 0.60). Because of this, we developed and internally validated a relative risk prediction model that incorporates 17 established epidemiologic risk factors and 17 genome-wide significant single nucleotide polymorphisms (SNPs) using data from 11 case-control studies in the United States (5,793 cases; 9,512 controls) from the Ovarian Cancer Association Consortium (data accrued from 1992 to 2010). We developed a hierarchical logistic regression model for predicting case-control status that included imputation of missing data. We randomly divided the data into an 80% training sample and used the remaining 20% for model evaluation. The AUC for the full model was 0.664. A reduced model without SNPs performed similarly (AUC = 0.649). Both models performed better than a baseline model that included age and study site only (AUC = 0.563). The best predictive power was obtained in the full model among women younger than 50 years of age (AUC = 0.714); however, the addition of SNPs increased the AUC the most for women older than 50 years of age (AUC = 0.638 vs. 0.616). Adapting this improved model to estimate absolute risk and evaluating it in prospective data sets is warranted. PMID:27698005

Feasibility of dynamic risk prediction for hepatocellular carcinoma development in patients with chronic hepatitis B.

PubMed

Jeon, Mi Young; Lee, Hye Won; Kim, Seung Up; Kim, Beom Kyung; Park, Jun Yong; Kim, Do Young; Han, Kwang-Hyub; Ahn, Sang Hoon

2018-04-01

Several risk prediction models for hepatocellular carcinoma (HCC) development are available. We explored whether the use of risk prediction models can dynamically predict HCC development at different time points in chronic hepatitis B (CHB) patients. Between 2006 and 2014, 1397 CHB patients were recruited. All patients underwent serial transient elastography at intervals of >6 months. The median age of this study population (931 males and 466 females) was 49.0 years. The median CU-HCC, REACH-B, LSM-HCC and mREACH-B score at enrolment were 4.0, 9.0, 10.0 and 8.0 respectively. During the follow-up period (median, 68.0 months), 87 (6.2%) patients developed HCC. All risk prediction models were successful in predicting HCC development at both the first liver stiffness (LS) measurement (hazard ratio [HR] = 1.067-1.467 in the subgroup without antiviral therapy [AVT] and 1.096-1.458 in the subgroup with AVT) and second LS measurement (HR = 1.125-1.448 in the subgroup without AVT and 1.087-1.249 in the subgroup with AVT). In contrast, neither the absolute nor percentage change in the scores from the risk prediction models predicted HCC development (all P > .05). The mREACH-B score performed similarly or significantly better than did the other scores (AUROCs at 5 years, 0.694-0.862 vs 0.537-0.875). Dynamic prediction of HCC development at different time points was achieved using four risk prediction models, but not using the changes in the absolute and percentage values between two time points. The mREACH-B score was the most appropriate prediction model of HCC development among four prediction models. © 2017 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

The cardiovascular event reduction tool (CERT)--a simplified cardiac risk prediction model developed from the West of Scotland Coronary Prevention Study (WOSCOPS).

PubMed

L'Italien, G; Ford, I; Norrie, J; LaPuerta, P; Ehreth, J; Jackson, J; Shepherd, J

2000-03-15

The clinical decision to treat hypercholesterolemia is premised on an awareness of patient risk, and cardiac risk prediction models offer a practical means of determining such risk. However, these models are based on observational cohorts where estimates of the treatment benefit are largely inferred. The West of Scotland Coronary Prevention Study (WOSCOPS) provides an opportunity to develop a risk-benefit prediction model from the actual observed primary event reduction seen in the trial. Five-year Cox model risk estimates were derived from all WOSCOPS subjects (n = 6,595 men, aged 45 to 64 years old at baseline) using factors previously shown to be predictive of definite fatal coronary heart disease or nonfatal myocardial infarction. Model risk factors included age, diastolic blood pressure, total cholesterol/ high-density lipoprotein ratio (TC/HDL), current smoking, diabetes, family history of fatal coronary heart disease, nitrate use or angina, and treatment (placebo/ 40-mg pravastatin). All risk factors were expressed as categorical variables to facilitate risk assessment. Risk estimates were incorporated into a simple, hand-held slide rule or risk tool. Risk estimates were identified for 5-year age bands (45 to 65 years), 4 categories of TC/HDL ratio (<5.5, 5.5 to <6.5, 6.5 to <7.5, > or = 7.5), 2 levels of diastolic blood pressure (<90, > or = 90 mm Hg), from 0 to 3 additional risk factors (current smoking, diabetes, family history of premature fatal coronary heart disease, nitrate use or angina), and pravastatin treatment. Five-year risk estimates ranged from 2% in very low-risk subjects to 61% in the very high-risk subjects. Risk reduction due to pravastatin treatment averaged 31%. Thus, the Cardiovascular Event Reduction Tool (CERT) is a risk prediction model derived from the WOSCOPS trial. Its use will help physicians identify patients who will benefit from cholesterol reduction.

Predicting medical complications after spine surgery: a validated model using a prospective surgical registry.

PubMed

Lee, Michael J; Cizik, Amy M; Hamilton, Deven; Chapman, Jens R

2014-02-01

The possibility and likelihood of a postoperative medical complication after spine surgery undoubtedly play a major role in the decision making of the surgeon and patient alike. Although prior study has determined relative risk and odds ratio values to quantify risk factors, these values may be difficult to translate to the patient during counseling of surgical options. Ideally, a model that predicts absolute risk of medical complication, rather than relative risk or odds ratio values, would greatly enhance the discussion of safety of spine surgery. To date, there is no risk stratification model that specifically predicts the risk of medical complication. The purpose of this study was to create and validate a predictive model for the risk of medical complication during and after spine surgery. Statistical analysis using a prospective surgical spine registry that recorded extensive demographic, surgical, and complication data. Outcomes examined are medical complications that were specifically defined a priori. This analysis is a continuation of statistical analysis of our previously published report. Using a prospectively collected surgical registry of more than 1,476 patients with extensive demographic, comorbidity, surgical, and complication detail recorded for 2 years after surgery, we previously identified several risk factor for medical complications. Using the beta coefficients from those log binomial regression analyses, we created a model to predict the occurrence of medical complication after spine surgery. We split our data into two subsets for internal and cross-validation of our model. We created two predictive models: one predicting the occurrence of any medical complication and the other predicting the occurrence of a major medical complication. The final predictive model for any medical complications had a receiver operator curve characteristic of 0.76, considered to be a fair measure. The final predictive model for any major medical complications had receiver operator curve characteristic of 0.81, considered to be a good measure. The final model has been uploaded for use on SpineSage.com. We present a validated model for predicting medical complications after spine surgery. The value in this model is that it gives the user an absolute percent likelihood of complication after spine surgery based on the patient's comorbidity profile and invasiveness of surgery. Patients are far more likely to understand an absolute percentage, rather than relative risk and confidence interval values. A model such as this is of paramount importance in counseling patients and enhancing the safety of spine surgery. In addition, a tool such as this can be of great use particularly as health care trends toward pay-for-performance, quality metrics, and risk adjustment. To facilitate the use of this model, we have created a website (SpineSage.com) where users can enter in patient data to determine likelihood of medical complications after spine surgery. Copyright © 2014 Elsevier Inc. All rights reserved.

Multisite external validation of a risk prediction model for the diagnosis of blood stream infections in febrile pediatric oncology patients without severe neutropenia.

PubMed

Esbenshade, Adam J; Zhao, Zhiguo; Aftandilian, Catherine; Saab, Raya; Wattier, Rachel L; Beauchemin, Melissa; Miller, Tamara P; Wilkes, Jennifer J; Kelly, Michael J; Fernbach, Alison; Jeng, Michael; Schwartz, Cindy L; Dvorak, Christopher C; Shyr, Yu; Moons, Karl G M; Sulis, Maria-Luisa; Friedman, Debra L

2017-10-01

Pediatric oncology patients are at an increased risk of invasive bacterial infection due to immunosuppression. The risk of such infection in the absence of severe neutropenia (absolute neutrophil count ≥ 500/μL) is not well established and a validated prediction model for blood stream infection (BSI) risk offers clinical usefulness. A 6-site retrospective external validation was conducted using a previously published risk prediction model for BSI in febrile pediatric oncology patients without severe neutropenia: the Esbenshade/Vanderbilt (EsVan) model. A reduced model (EsVan2) excluding 2 less clinically reliable variables also was created using the initial EsVan model derivative cohort, and was validated using all 5 external validation cohorts. One data set was used only in sensitivity analyses due to missing some variables. From the 5 primary data sets, there were a total of 1197 febrile episodes and 76 episodes of bacteremia. The overall C statistic for predicting bacteremia was 0.695, with a calibration slope of 0.50 for the original model and a calibration slope of 1.0 when recalibration was applied to the model. The model performed better in predicting high-risk bacteremia (gram-negative or Staphylococcus aureus infection) versus BSI alone, with a C statistic of 0.801 and a calibration slope of 0.65. The EsVan2 model outperformed the EsVan model across data sets with a C statistic of 0.733 for predicting BSI and a C statistic of 0.841 for high-risk BSI. The results of this external validation demonstrated that the EsVan and EsVan2 models are able to predict BSI across multiple performance sites and, once validated and implemented prospectively, could assist in decision making in clinical practice. Cancer 2017;123:3781-3790. © 2017 American Cancer Society. © 2017 American Cancer Society.

Proposals for enhanced health risk assessment and stratification in an integrated care scenario.

PubMed

Dueñas-Espín, Ivan; Vela, Emili; Pauws, Steffen; Bescos, Cristina; Cano, Isaac; Cleries, Montserrat; Contel, Joan Carles; de Manuel Keenoy, Esteban; Garcia-Aymerich, Judith; Gomez-Cabrero, David; Kaye, Rachelle; Lahr, Maarten M H; Lluch-Ariet, Magí; Moharra, Montserrat; Monterde, David; Mora, Joana; Nalin, Marco; Pavlickova, Andrea; Piera, Jordi; Ponce, Sara; Santaeugenia, Sebastià; Schonenberg, Helen; Störk, Stefan; Tegner, Jesper; Velickovski, Filip; Westerteicher, Christoph; Roca, Josep

2016-04-15

Population-based health risk assessment and stratification are considered highly relevant for large-scale implementation of integrated care by facilitating services design and case identification. The principal objective of the study was to analyse five health-risk assessment strategies and health indicators used in the five regions participating in the Advancing Care Coordination and Telehealth Deployment (ACT) programme (http://www.act-programme.eu). The second purpose was to elaborate on strategies toward enhanced health risk predictive modelling in the clinical scenario. The five ACT regions: Scotland (UK), Basque Country (ES), Catalonia (ES), Lombardy (I) and Groningen (NL). Responsible teams for regional data management in the five ACT regions. We characterised and compared risk assessment strategies among ACT regions by analysing operational health risk predictive modelling tools for population-based stratification, as well as available health indicators at regional level. The analysis of the risk assessment tool deployed in Catalonia in 2015 (GMAs, Adjusted Morbidity Groups) was used as a basis to propose how population-based analytics could contribute to clinical risk prediction. There was consensus on the need for a population health approach to generate health risk predictive modelling. However, this strategy was fully in place only in two ACT regions: Basque Country and Catalonia. We found marked differences among regions in health risk predictive modelling tools and health indicators, and identified key factors constraining their comparability. The research proposes means to overcome current limitations and the use of population-based health risk prediction for enhanced clinical risk assessment. The results indicate the need for further efforts to improve both comparability and flexibility of current population-based health risk predictive modelling approaches. Applicability and impact of the proposals for enhanced clinical risk assessment require prospective evaluation. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://www.bmj.com/company/products-services/rights-and-licensing/

Predictive Modeling of Risk Factors and Complications of Cataract Surgery

PubMed Central

Gaskin, Gregory L; Pershing, Suzann; Cole, Tyler S; Shah, Nigam H

2016-01-01

Purpose To quantify the relationship between aggregated preoperative risk factors and cataract surgery complications, as well as to build a model predicting outcomes on an individual-level—given a constellation of demographic, baseline, preoperative, and intraoperative patient characteristics. Setting Stanford Hospital and Clinics between 1994 and 2013. Design Retrospective cohort study Methods Patients age 40 or older who received cataract surgery between 1994 and 2013. Risk factors, complications, and demographic information were extracted from the Electronic Health Record (EHR), based on International Classification of Diseases, 9th edition (ICD-9) codes, Current Procedural Terminology (CPT) codes, drug prescription information, and text data mining using natural language processing. We used a bootstrapped least absolute shrinkage and selection operator (LASSO) model to identify highly-predictive variables. We built random forest classifiers for each complication to create predictive models. Results Our data corroborated existing literature on postoperative complications—including the association of intraoperative complications, complex cataract surgery, black race, and/or prior eye surgery with an increased risk of any postoperative complications. We also found a number of other, less well-described risk factors, including systemic diabetes mellitus, young age (<60 years old), and hyperopia as risk factors for complex cataract surgery and intra- and post-operative complications. Our predictive models based on aggregated outperformed existing published models. Conclusions The constellations of risk factors and complications described here can guide new avenues of research and provide specific, personalized risk assessment for a patient considering cataract surgery. The predictive capacity of our models can enable risk stratification of patients, which has utility as a teaching tool as well as informing quality/value-based reimbursements. PMID:26692059

A New Scoring System to Predict the Risk for High-risk Adenoma and Comparison of Existing Risk Calculators.

PubMed

Murchie, Brent; Tandon, Kanwarpreet; Hakim, Seifeldin; Shah, Kinchit; O'Rourke, Colin; Castro, Fernando J

2017-04-01

Colorectal cancer (CRC) screening guidelines likely over-generalizes CRC risk, 35% of Americans are not up to date with screening, and there is growing incidence of CRC in younger patients. We developed a practical prediction model for high-risk colon adenomas in an average-risk population, including an expanded definition of high-risk polyps (≥3 nonadvanced adenomas), exposing higher than average-risk patients. We also compared results with previously created calculators. Patients aged 40 to 59 years, undergoing first-time average-risk screening or diagnostic colonoscopies were evaluated. Risk calculators for advanced adenomas and high-risk adenomas were created based on age, body mass index, sex, race, and smoking history. Previously established calculators with similar risk factors were selected for comparison of concordance statistic (c-statistic) and external validation. A total of 5063 patients were included. Advanced adenomas, and high-risk adenomas were seen in 5.7% and 7.4% of the patient population, respectively. The c-statistic for our calculator was 0.639 for the prediction of advanced adenomas, and 0.650 for high-risk adenomas. When applied to our population, all previous models had lower c-statistic results although one performed similarly. Our model compares favorably to previously established prediction models. Age and body mass index were used as continuous variables, likely improving the c-statistic. It also reports absolute predictive probabilities of advanced and high-risk polyps, allowing for more individualized risk assessment of CRC.

Adaptation of a Biomarker-Based Sepsis Mortality Risk Stratification Tool for Pediatric Acute Respiratory Distress Syndrome.

PubMed

Yehya, Nadir; Wong, Hector R

2018-01-01

The original Pediatric Sepsis Biomarker Risk Model and revised (Pediatric Sepsis Biomarker Risk Model-II) biomarker-based risk prediction models have demonstrated utility for estimating baseline 28-day mortality risk in pediatric sepsis. Given the paucity of prediction tools in pediatric acute respiratory distress syndrome, and given the overlapping pathophysiology between sepsis and acute respiratory distress syndrome, we tested the utility of Pediatric Sepsis Biomarker Risk Model and Pediatric Sepsis Biomarker Risk Model-II for mortality prediction in a cohort of pediatric acute respiratory distress syndrome, with an a priori plan to revise the model if these existing models performed poorly. Prospective observational cohort study. University affiliated PICU. Mechanically ventilated children with acute respiratory distress syndrome. Blood collection within 24 hours of acute respiratory distress syndrome onset and biomarker measurements. In 152 children with acute respiratory distress syndrome, Pediatric Sepsis Biomarker Risk Model performed poorly and Pediatric Sepsis Biomarker Risk Model-II performed modestly (areas under receiver operating characteristic curve of 0.61 and 0.76, respectively). Therefore, we randomly selected 80% of the cohort (n = 122) to rederive a risk prediction model for pediatric acute respiratory distress syndrome. We used classification and regression tree methodology, considering the Pediatric Sepsis Biomarker Risk Model biomarkers in addition to variables relevant to acute respiratory distress syndrome. The final model was comprised of three biomarkers and age, and more accurately estimated baseline mortality risk (area under receiver operating characteristic curve 0.85, p < 0.001 and p = 0.053 compared with Pediatric Sepsis Biomarker Risk Model and Pediatric Sepsis Biomarker Risk Model-II, respectively). The model was tested in the remaining 20% of subjects (n = 30) and demonstrated similar test characteristics. A validated, biomarker-based risk stratification tool designed for pediatric sepsis was adapted for use in pediatric acute respiratory distress syndrome. The newly derived Pediatric Acute Respiratory Distress Syndrome Biomarker Risk Model demonstrates good test characteristics internally and requires external validation in a larger cohort. Tools such as Pediatric Acute Respiratory Distress Syndrome Biomarker Risk Model have the potential to provide improved risk stratification and prognostic enrichment for future trials in pediatric acute respiratory distress syndrome.

A novel risk score model for prediction of contrast-induced nephropathy after emergent percutaneous coronary intervention.

PubMed

Lin, Kai-Yang; Zheng, Wei-Ping; Bei, Wei-Jie; Chen, Shi-Qun; Islam, Sheikh Mohammed Shariful; Liu, Yong; Xue, Lin; Tan, Ning; Chen, Ji-Yan

2017-03-01

A few studies developed simple risk model for predicting CIN with poor prognosis after emergent PCI. The study aimed to develop and validate a novel tool for predicting the risk of contrast-induced nephropathy (CIN) in patients undergoing emergent percutaneous coronary intervention (PCI). 692 consecutive patients undergoing emergent PCI between January 2010 and December 2013 were randomly (2:1) assigned to a development dataset (n=461) and a validation dataset (n=231). Multivariate logistic regression was applied to identify independent predictors of CIN, and established CIN predicting model, whose prognostic accuracy was assessed using the c-statistic for discrimination and the Hosmere Lemeshow test for calibration. The overall incidence of CIN was 55(7.9%). A total of 11 variables were analyzed, including age >75years old, baseline serum creatinine (SCr)>1.5mg/dl, hypotension and the use of intra-aortic balloon pump(IABP), which were identified to enter risk score model (Chen). The incidence of CIN was 32(6.9%) in the development dataset (in low risk (score=0), 1.0%, moderate risk (score:1-2), 13.4%, high risk (score≥3), 90.0%). Compared to the classical Mehran's and ACEF CIN risk score models, the risk score (Chen) across the subgroup of the study population exhibited similar discrimination and predictive ability on CIN (c-statistic:0.828, 0.776, 0.853, respectively), in-hospital mortality, 2, 3-years mortality (c-statistic:0.738.0.750, 0.845, respectively) in the validation population. Our data showed that this simple risk model exhibited good discrimination and predictive ability on CIN, similar to Mehran's and ACEF score, and even on long-term mortality after emergent PCI. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

In-hospital risk prediction for post-stroke depression: development and validation of the Post-stroke Depression Prediction Scale.

PubMed

de Man-van Ginkel, Janneke M; Hafsteinsdóttir, Thóra B; Lindeman, Eline; Ettema, Roelof G A; Grobbee, Diederick E; Schuurmans, Marieke J

2013-09-01

The timely detection of post-stroke depression is complicated by a decreasing length of hospital stay. Therefore, the Post-stroke Depression Prediction Scale was developed and validated. The Post-stroke Depression Prediction Scale is a clinical prediction model for the early identification of stroke patients at increased risk for post-stroke depression. The study included 410 consecutive stroke patients who were able to communicate adequately. Predictors were collected within the first week after stroke. Between 6 to 8 weeks after stroke, major depressive disorder was diagnosed using the Composite International Diagnostic Interview. Multivariable logistic regression models were fitted. A bootstrap-backward selection process resulted in a reduced model. Performance of the model was expressed by discrimination, calibration, and accuracy. The model included a medical history of depression or other psychiatric disorders, hypertension, angina pectoris, and the Barthel Index item dressing. The model had acceptable discrimination, based on an area under the receiver operating characteristic curve of 0.78 (0.72-0.85), and calibration (P value of the U-statistic, 0.96). Transforming the model to an easy-to-use risk-assessment table, the lowest risk category (sum score, <-10) showed a 2% risk of depression, which increased to 82% in the highest category (sum score, >21). The clinical prediction model enables clinicians to estimate the degree of the depression risk for an individual patient within the first week after stroke.

Predicting surgical site infection after spine surgery: a validated model using a prospective surgical registry.

PubMed

Lee, Michael J; Cizik, Amy M; Hamilton, Deven; Chapman, Jens R

2014-09-01

The impact of surgical site infection (SSI) is substantial. Although previous study has determined relative risk and odds ratio (OR) values to quantify risk factors, these values may be difficult to translate to the patient during counseling of surgical options. Ideally, a model that predicts absolute risk of SSI, rather than relative risk or OR values, would greatly enhance the discussion of safety of spine surgery. To date, there is no risk stratification model that specifically predicts the risk of medical complication. The purpose of this study was to create and validate a predictive model for the risk of SSI after spine surgery. This study performs a multivariate analysis of SSI after spine surgery using a large prospective surgical registry. Using the results of this analysis, this study will then create and validate a predictive model for SSI after spine surgery. The patient sample is from a high-quality surgical registry from our two institutions with prospectively collected, detailed demographic, comorbidity, and complication data. An SSI that required return to the operating room for surgical debridement. Using a prospectively collected surgical registry of more than 1,532 patients with extensive demographic, comorbidity, surgical, and complication details recorded for 2 years after the surgery, we identified several risk factors for SSI after multivariate analysis. Using the beta coefficients from those regression analyses, we created a model to predict the occurrence of SSI after spine surgery. We split our data into two subsets for internal and cross-validation of our model. We created a predictive model based on our beta coefficients from our multivariate analysis. The final predictive model for SSI had a receiver-operator curve characteristic of 0.72, considered to be a fair measure. The final model has been uploaded for use on SpineSage.com. We present a validated model for predicting SSI after spine surgery. The value in this model is that it gives the user an absolute percent likelihood of SSI after spine surgery based on the patient's comorbidity profile and invasiveness of surgery. Patients are far more likely to understand an absolute percentage, rather than relative risk and confidence interval values. A model such as this is of paramount importance in counseling patients and enhancing the safety of spine surgery. In addition, a tool such as this can be of great use particularly as health care trends toward pay for performance, quality metrics (such as SSI), and risk adjustment. To facilitate the use of this model, we have created a Web site (SpineSage.com) where users can enter patient data to determine likelihood for SSI. Copyright © 2014 Elsevier Inc. All rights reserved.

Utility of existing diabetes risk prediction tools for young black and white adults: Evidence from the Bogalusa Heart Study.

PubMed

Pollock, Benjamin D; Hu, Tian; Chen, Wei; Harville, Emily W; Li, Shengxu; Webber, Larry S; Fonseca, Vivian; Bazzano, Lydia A

2017-01-01

To evaluate several adult diabetes risk calculation tools for predicting the development of incident diabetes and pre-diabetes in a bi-racial, young adult population. Surveys beginning in young adulthood (baseline age ≥18) and continuing across multiple decades for 2122 participants of the Bogalusa Heart Study were used to test the associations of five well-known adult diabetes risk scores with incident diabetes and pre-diabetes using separate Cox models for each risk score. Racial differences were tested within each model. Predictive utility and discrimination were determined for each risk score using the Net Reclassification Index (NRI) and Harrell's c-statistic. All risk scores were strongly associated (p<.0001) with incident diabetes and pre-diabetes. The Wilson model indicated greater risk of diabetes for blacks versus whites with equivalent risk scores (HR=1.59; 95% CI 1.11-2.28; p=.01). C-statistics for the diabetes risk models ranged from 0.79 to 0.83. Non-event NRIs indicated high specificity (non-event NRIs: 76%-88%), but poor sensitivity (event NRIs: -23% to -3%). Five diabetes risk scores established in middle-aged, racially homogenous adult populations are generally applicable to younger adults with good specificity but poor sensitivity. The addition of race to these models did not result in greater predictive capabilities. A more sensitive risk score to predict diabetes in younger adults is needed. Copyright © 2017 Elsevier Inc. All rights reserved.

Developing EHR-driven heart failure risk prediction models using CPXR(Log) with the probabilistic loss function.

PubMed

Taslimitehrani, Vahid; Dong, Guozhu; Pereira, Naveen L; Panahiazar, Maryam; Pathak, Jyotishman

2016-04-01

Computerized survival prediction in healthcare identifying the risk of disease mortality, helps healthcare providers to effectively manage their patients by providing appropriate treatment options. In this study, we propose to apply a classification algorithm, Contrast Pattern Aided Logistic Regression (CPXR(Log)) with the probabilistic loss function, to develop and validate prognostic risk models to predict 1, 2, and 5year survival in heart failure (HF) using data from electronic health records (EHRs) at Mayo Clinic. The CPXR(Log) constructs a pattern aided logistic regression model defined by several patterns and corresponding local logistic regression models. One of the models generated by CPXR(Log) achieved an AUC and accuracy of 0.94 and 0.91, respectively, and significantly outperformed prognostic models reported in prior studies. Data extracted from EHRs allowed incorporation of patient co-morbidities into our models which helped improve the performance of the CPXR(Log) models (15.9% AUC improvement), although did not improve the accuracy of the models built by other classifiers. We also propose a probabilistic loss function to determine the large error and small error instances. The new loss function used in the algorithm outperforms other functions used in the previous studies by 1% improvement in the AUC. This study revealed that using EHR data to build prediction models can be very challenging using existing classification methods due to the high dimensionality and complexity of EHR data. The risk models developed by CPXR(Log) also reveal that HF is a highly heterogeneous disease, i.e., different subgroups of HF patients require different types of considerations with their diagnosis and treatment. Our risk models provided two valuable insights for application of predictive modeling techniques in biomedicine: Logistic risk models often make systematic prediction errors, and it is prudent to use subgroup based prediction models such as those given by CPXR(Log) when investigating heterogeneous diseases. Copyright © 2016 Elsevier Inc. All rights reserved.

Personalized Risk Prediction in Clinical Oncology Research: Applications and Practical Issues Using Survival Trees and Random Forests.

PubMed

Hu, Chen; Steingrimsson, Jon Arni

2018-01-01

A crucial component of making individualized treatment decisions is to accurately predict each patient's disease risk. In clinical oncology, disease risks are often measured through time-to-event data, such as overall survival and progression/recurrence-free survival, and are often subject to censoring. Risk prediction models based on recursive partitioning methods are becoming increasingly popular largely due to their ability to handle nonlinear relationships, higher-order interactions, and/or high-dimensional covariates. The most popular recursive partitioning methods are versions of the Classification and Regression Tree (CART) algorithm, which builds a simple interpretable tree structured model. With the aim of increasing prediction accuracy, the random forest algorithm averages multiple CART trees, creating a flexible risk prediction model. Risk prediction models used in clinical oncology commonly use both traditional demographic and tumor pathological factors as well as high-dimensional genetic markers and treatment parameters from multimodality treatments. In this article, we describe the most commonly used extensions of the CART and random forest algorithms to right-censored outcomes. We focus on how they differ from the methods for noncensored outcomes, and how the different splitting rules and methods for cost-complexity pruning impact these algorithms. We demonstrate these algorithms by analyzing a randomized Phase III clinical trial of breast cancer. We also conduct Monte Carlo simulations to compare the prediction accuracy of survival forests with more commonly used regression models under various scenarios. These simulation studies aim to evaluate how sensitive the prediction accuracy is to the underlying model specifications, the choice of tuning parameters, and the degrees of missing covariates.

[Community-acquired pneumonia: outcomes and costs].

PubMed

Putinati, Stefano; Ballerin, Licia; Gualandi, Malvina; Battaglia, Giuseppe; Piattella, Marco; Potena, Alfredo

2002-03-01

The number of patients admitted with community acquired pneumonias (CAP) varies greatly from one hospital to another. Prognostic models for CAP can help physicians decide which cases to treat on an outpatients basis. Our aims were: a) to validate a model for predicting low-risk CAP, and b) to estimate savings that would have resulted if the low-risk patients identified by the model had been treated at home rather than in hospital. The prediction rule of Fine et al. was used to classify retrospectively 260 CAP patients. Mortality in each category was compared with the mortality predicted. Patients in the lowest risk categories were considered to have been inappropriately admitted. The predictive model used has been found useful for identifying patients at very low-risk of dying from CAP. Application of the model can lead to savings.

Multimethod prediction of physical parent-child aggression risk in expectant mothers and fathers with Social Information Processing theory.

PubMed

Rodriguez, Christina M; Smith, Tamika L; Silvia, Paul J

2016-01-01

The Social Information Processing (SIP) model postulates that parents undergo a series of stages in implementing physical discipline that can escalate into physical child abuse. The current study utilized a multimethod approach to investigate whether SIP factors can predict risk of parent-child aggression (PCA) in a diverse sample of expectant mothers and fathers. SIP factors of PCA attitudes, negative child attributions, reactivity, and empathy were considered as potential predictors of PCA risk; additionally, analyses considered whether personal history of PCA predicted participants' own PCA risk through its influence on their attitudes and attributions. Findings indicate that, for both mothers and fathers, history influenced attitudes but not attributions in predicting PCA risk, and attitudes and attributions predicted PCA risk; empathy and reactivity predicted negative child attributions for expectant mothers, but only reactivity significantly predicted attributions for expectant fathers. Path models for expectant mothers and fathers were remarkably similar. Overall, the findings provide support for major aspects of the SIP model. Continued work is needed in studying the progression of these factors across time for both mothers and fathers as well as the inclusion of other relevant ecological factors to the SIP model. Copyright © 2015 Elsevier Ltd. All rights reserved.

Predictive risk models for proximal aortic surgery

PubMed Central

Díaz, Rocío; Pascual, Isaac; Álvarez, Rubén; Alperi, Alberto; Rozado, Jose; Morales, Carlos; Silva, Jacobo; Morís, César

2017-01-01

Predictive risk models help improve decision making, information to our patients and quality control comparing results between surgeons and between institutions. The use of these models promotes competitiveness and led to increasingly better results. All these virtues are of utmost importance when the surgical operation entails high-risk. Although proximal aortic surgery is less frequent than other cardiac surgery operations, this procedure itself is more challenging and technically demanding than other common cardiac surgery techniques. The aim of this study is to review the current status of predictive risk models for patients who undergo proximal aortic surgery, which means aortic root replacement, supracoronary ascending aortic replacement or aortic arch surgery. PMID:28616348

Personalized long-term prediction of cognitive function: Using sequential assessments to improve model performance.

PubMed

Chi, Chih-Lin; Zeng, Wenjun; Oh, Wonsuk; Borson, Soo; Lenskaia, Tatiana; Shen, Xinpeng; Tonellato, Peter J

2017-12-01

Prediction of onset and progression of cognitive decline and dementia is important both for understanding the underlying disease processes and for planning health care for populations at risk. Predictors identified in research studies are typically accessed at one point in time. In this manuscript, we argue that an accurate model for predicting cognitive status over relatively long periods requires inclusion of time-varying components that are sequentially assessed at multiple time points (e.g., in multiple follow-up visits). We developed a pilot model to test the feasibility of using either estimated or observed risk factors to predict cognitive status. We developed two models, the first using a sequential estimation of risk factors originally obtained from 8 years prior, then improved by optimization. This model can predict how cognition will change over relatively long time periods. The second model uses observed rather than estimated time-varying risk factors and, as expected, results in better prediction. This model can predict when newly observed data are acquired in a follow-up visit. Performances of both models that are evaluated in10-fold cross-validation and various patient subgroups show supporting evidence for these pilot models. Each model consists of multiple base prediction units (BPUs), which were trained using the same set of data. The difference in usage and function between the two models is the source of input data: either estimated or observed data. In the next step of model refinement, we plan to integrate the two types of data together to flexibly predict dementia status and changes over time, when some time-varying predictors are measured only once and others are measured repeatedly. Computationally, both data provide upper and lower bounds for predictive performance. Copyright © 2017 Elsevier Inc. All rights reserved.

Comparing toxicologic and epidemiologic studies: methylene chloride--a case study.

PubMed

Stayner, L T; Bailer, A J

1993-12-01

Exposure to methylene chloride induces lung and liver cancers in mice. The mouse bioassay data have been used as the basis for several cancer risk assessments. The results from epidemiologic studies of workers exposed to methylene chloride have been mixed with respect to demonstrating an increased cancer risk. The results from a negative epidemiologic study of Kodak workers have been used by two groups of investigators to test the predictions from the EPA risk assessment models. These two groups used very different approaches to this problem, which resulted in opposite conclusions regarding the consistency between the animal model predictions and the Kodak study results. The results from the Kodak study are used to test the predictions from OSHA's multistage models of liver and lung cancer risk. Confidence intervals for the standardized mortality ratios (SMRs) from the Kodak study are compared with the predicted confidence intervals derived from OSHA's risk assessment models. Adjustments for the "healthy worker effect," differences in length of follow-up, and dosimetry between animals and humans were incorporated into these comparisons. Based on these comparisons, we conclude that the negative results from the Kodak study are not inconsistent with the predictions from OSHA's risk assessment model.

Prediction and Informative Risk Factor Selection of Bone Diseases.

PubMed

Li, Hui; Li, Xiaoyi; Ramanathan, Murali; Zhang, Aidong

2015-01-01

With the booming of healthcare industry and the overwhelming amount of electronic health records (EHRs) shared by healthcare institutions and practitioners, we take advantage of EHR data to develop an effective disease risk management model that not only models the progression of the disease, but also predicts the risk of the disease for early disease control or prevention. Existing models for answering these questions usually fall into two categories: the expert knowledge based model or the handcrafted feature set based model. To fully utilize the whole EHR data, we will build a framework to construct an integrated representation of features from all available risk factors in the EHR data and use these integrated features to effectively predict osteoporosis and bone fractures. We will also develop a framework for informative risk factor selection of bone diseases. A pair of models for two contrast cohorts (e.g., diseased patients versus non-diseased patients) will be established to discriminate their characteristics and find the most informative risk factors. Several empirical results on a real bone disease data set show that the proposed framework can successfully predict bone diseases and select informative risk factors that are beneficial and useful to guide clinical decisions.

Web-based decision support system to predict risk level of long term rice production

NASA Astrophysics Data System (ADS)

Mukhlash, Imam; Maulidiyah, Ratna; Sutikno; Setiyono, Budi

2017-09-01

Appropriate decision making in risk management of rice production is very important in agricultural planning, especially for Indonesia which is an agricultural country. Good decision would be obtained if the supporting data required are satisfied and using appropriate methods. This study aims to develop a Decision Support System that can be used to predict the risk level of rice production in some districts which are central of rice production in East Java. Web-based decision support system is constructed so that the information can be easily accessed and understood. Components of the system are data management, model management, and user interface. This research uses regression models of OLS and Copula. OLS model used to predict rainfall while Copula model used to predict harvested area. Experimental results show that the models used are successfully predict the harvested area of rice production in some districts which are central of rice production in East Java at any given time based on the conditions and climate of a region. Furthermore, it can predict the amount of rice production with the level of risk. System generates prediction of production risk level in the long term for some districts that can be used as a decision support for the authorities.

Risk terrain modeling predicts child maltreatment.

PubMed

Daley, Dyann; Bachmann, Michael; Bachmann, Brittany A; Pedigo, Christian; Bui, Minh-Thuy; Coffman, Jamye

2016-12-01

As indicated by research on the long-term effects of adverse childhood experiences (ACEs), maltreatment has far-reaching consequences for affected children. Effective prevention measures have been elusive, partly due to difficulty in identifying vulnerable children before they are harmed. This study employs Risk Terrain Modeling (RTM), an analysis of the cumulative effect of environmental factors thought to be conducive for child maltreatment, to create a highly accurate prediction model for future substantiated child maltreatment cases in the City of Fort Worth, Texas. The model is superior to commonly used hotspot predictions and more beneficial in aiding prevention efforts in a number of ways: 1) it identifies the highest risk areas for future instances of child maltreatment with improved precision and accuracy; 2) it aids the prioritization of risk-mitigating efforts by informing about the relative importance of the most significant contributing risk factors; 3) since predictions are modeled as a function of easily obtainable data, practitioners do not have to undergo the difficult process of obtaining official child maltreatment data to apply it; 4) the inclusion of a multitude of environmental risk factors creates a more robust model with higher predictive validity; and, 5) the model does not rely on a retrospective examination of past instances of child maltreatment, but adapts predictions to changing environmental conditions. The present study introduces and examines the predictive power of this new tool to aid prevention efforts seeking to improve the safety, health, and wellbeing of vulnerable children. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

Applying Social Psychological Models to Predicting HIV-Related Sexual Risk Behaviors Among African Americans

PubMed Central

Cochran, Susan D.; Mays, Vickie M.

2011-01-01

Existing models of attitude-behavior relationships, including the Health Belief Model, the Theory of Reasoned Action, and the Self-Efficacy Theory, are increasingly being used by psychologists to predict human immunodeficiency virus (HIV)-related risk behaviors. The authors briefly highlight some of the difficulties that might arise in applying these models to predicting the risk behaviors of African Americans. These social psychological models tend to emphasize the importance of individualistic, direct control of behavioral choices and deemphasize factors, such as racism and poverty, particularly relevant to that segment of the African American population most at risk for HIV infection. Applications of these models without taking into account the unique issues associated with behavioral choices within the African American community may fail to capture the relevant determinants of risk behaviors. PMID:23529205

Breast cancer risks and risk prediction models.

PubMed

Engel, Christoph; Fischer, Christine

2015-02-01

BRCA1/2 mutation carriers have a considerably increased risk to develop breast and ovarian cancer. The personalized clinical management of carriers and other at-risk individuals depends on precise knowledge of the cancer risks. In this report, we give an overview of the present literature on empirical cancer risks, and we describe risk prediction models that are currently used for individual risk assessment in clinical practice. Cancer risks show large variability between studies. Breast cancer risks are at 40-87% for BRCA1 mutation carriers and 18-88% for BRCA2 mutation carriers. For ovarian cancer, the risk estimates are in the range of 22-65% for BRCA1 and 10-35% for BRCA2. The contralateral breast cancer risk is high (10-year risk after first cancer 27% for BRCA1 and 19% for BRCA2). Risk prediction models have been proposed to provide more individualized risk prediction, using additional knowledge on family history, mode of inheritance of major genes, and other genetic and non-genetic risk factors. User-friendly software tools have been developed that serve as basis for decision-making in family counseling units. In conclusion, further assessment of cancer risks and model validation is needed, ideally based on prospective cohort studies. To obtain such data, clinical management of carriers and other at-risk individuals should always be accompanied by standardized scientific documentation.

Discriminative value of FRAX for fracture prediction in a cohort of Chinese postmenopausal women.

PubMed

Cheung, E Y N; Bow, C H; Cheung, C L; Soong, C; Yeung, S; Loong, C; Kung, A

2012-03-01

We followed 2,266 postmenopausal Chinese women for 4.5 years to determine which model best predicts osteoporotic fracture. A model that contains ethnic-specific risk factors, some of which reflect frailty, performed as well as or better than the well-established FRAX model. Clinical risk assessment, with or without T-score, can predict fractures in Chinese postmenopausal women although it is unknown which combination of clinical risk factors is most effective. This prospective study sought to compare the accuracy for fracture prediction using various models including FRAX, our ethnic-specific clinical risk factors (CRF) and other simple models. This study is part of the Hong Kong Osteoporosis Study. A total of 2,266 treatment naïve postmenopausal women underwent clinical risk factor and bone mineral density assessment. Subjects were followed up for outcome of major osteoporotic fracture and receiver operating characteristic (ROC) curves for different models were compared. The percentage of subjects in different quartiles of risk according to various models who actually fractured was also compared. The mean age at baseline was 62.1 ± 8.5 years and mean follow-up time was 4.5 ± 2.8 years. A total of 106 new major osteoporotic fractures were reported, of which 21 were hip fractures. Ethnic-specific CRF with T-score performed better than FRAX with T-score (based on both Chinese normative and National Health and Nutrition Examination Survey (NHANES) databases) in terms of AUC comparison for prediction of major osteoporotic fracture. The two models were similar in hip fracture prediction. The ethnic-specific CRF model had a 10% higher sensitivity than FRAX at a specificity of 0.8 or above. CRF related to frailty and differences in lifestyle between populations are likely to be important in fracture prediction. Further work is required to determine which and how CRF can be applied to develop a fracture prediction model in our population.

Theory-Based Cartographic Risk Model Development and Application for Home Fire Safety.

PubMed

Furmanek, Stephen; Lehna, Carlee; Hanchette, Carol

There is a gap in the use of predictive risk models to identify areas at risk for home fires and burn injury. The purpose of this study was to describe the creation, validation, and application of such a model using a sample from an intervention study with parents of newborns in Jefferson County, KY, as an example. Performed was a literature search to identify risk factors for home fires and burn injury in the target population. Obtained from the American Community Survey at the census tract level and synthesized to create a predictive cartographic risk model was risk factor data. Model validation was performed through correlation, regression, and Moran's I with fire incidence data from open records. Independent samples t-tests were used to examine the model in relation to geocoded participant addresses. Participant risk level for fire rate was determined and proximity to fire station service areas and hospitals. The model showed high and severe risk clustering in the northwest section of the county. Strongly correlated with fire rate was modeled risk; the best predictive model for fire risk contained home value (low), race (black), and non high school graduates. Applying the model to the intervention sample, the majority of participants were at lower risk and mostly within service areas closest to a fire department and hospital. Cartographic risk models were useful in identifying areas at risk and analyzing participant risk level. The methods outlined in this study are generalizable to other public health issues.

Epidemiology and Long-term Clinical and Biologic Risk Factors for Pneumonia in Community-Dwelling Older Americans

PubMed Central

Alvarez, Karina; Loehr, Laura; Folsom, Aaron R.; Newman, Anne B.; Weissfeld, Lisa A.; Wunderink, Richard G.; Kritchevsky, Stephen B.; Mukamal, Kenneth J.; London, Stephanie J.; Harris, Tamara B.; Bauer, Doug C.; Angus, Derek C.

2013-01-01

Background: Preventing pneumonia requires better understanding of incidence, mortality, and long-term clinical and biologic risk factors, particularly in younger individuals. Methods: This was a cohort study in three population-based cohorts of community-dwelling individuals. A derivation cohort (n = 16,260) was used to determine incidence and survival and develop a risk prediction model. The prediction model was validated in two cohorts (n = 8,495). The primary outcome was 10-year risk of pneumonia hospitalization. Results: The crude and age-adjusted incidences of pneumonia were 6.71 and 9.43 cases/1,000 person-years (10-year risk was 6.15%). The 30-day and 1-year mortality were 16.5% and 31.5%. Although age was the most important risk factor (range of crude incidence rates, 1.69-39.13 cases/1,000 person-years for each 5-year increment from 45-85 years), 38% of pneumonia cases occurred in adults < 65 years of age. The 30-day and 1-year mortality were 12.5% and 25.7% in those < 65 years of age. Although most comorbidities were associated with higher risk of pneumonia, reduced lung function was the most important risk factor (relative risk = 6.61 for severe reduction based on FEV1 by spirometry). A clinical risk prediction model based on age, smoking, and lung function predicted 10-year risk (area under curve [AUC] = 0.77 and Hosmer-Lemeshow [HL] C statistic = 0.12). Model discrimination and calibration were similar in the internal validation cohort (AUC = 0.77; HL C statistic, 0.65) but lower in the external validation cohort (AUC = 0.62; HL C statistic, 0.45). The model also calibrated well in blacks and younger adults. C-reactive protein and IL-6 were associated with higher pneumonia risk but did not improve model performance. Conclusions: Pneumonia hospitalization is common and associated with high mortality, even in younger healthy adults. Long-term risk of pneumonia can be predicted in community-dwelling adults with a simple clinical risk prediction model. PMID:23744106

Utility of genetic and non-genetic risk factors in predicting coronary heart disease in Singaporean Chinese.

PubMed

Chang, Xuling; Salim, Agus; Dorajoo, Rajkumar; Han, Yi; Khor, Chiea-Chuen; van Dam, Rob M; Yuan, Jian-Min; Koh, Woon-Puay; Liu, Jianjun; Goh, Daniel Yt; Wang, Xu; Teo, Yik-Ying; Friedlander, Yechiel; Heng, Chew-Kiat

2017-01-01

Background Although numerous phenotype based equations for predicting risk of 'hard' coronary heart disease are available, data on the utility of genetic information for such risk prediction is lacking in Chinese populations. Design Case-control study nested within the Singapore Chinese Health Study. Methods A total of 1306 subjects comprising 836 men (267 incident cases and 569 controls) and 470 women (128 incident cases and 342 controls) were included. A Genetic Risk Score comprising 156 single nucleotide polymorphisms that have been robustly associated with coronary heart disease or its risk factors ( p < 5 × 10 -8 ) in at least two independent cohorts of genome-wide association studies was built. For each gender, three base models were used: recalibrated Adult Treatment Panel III (ATPIII) Model (M 1 ); ATP III model fitted using Singapore Chinese Health Study data (M 2 ) and M 3 : M 2 + C-reactive protein + creatinine. Results The Genetic Risk Score was significantly associated with incident 'hard' coronary heart disease ( p for men: 1.70 × 10 -10 -1.73 × 10 -9 ; p for women: 0.001). The inclusion of the Genetic Risk Score in the prediction models improved discrimination in both genders (c-statistics: 0.706-0.722 vs. 0.663-0.695 from base models for men; 0.788-0.790 vs. 0.765-0.773 for women). In addition, the inclusion of the Genetic Risk Score also improved risk classification with a net gain of cases being reclassified to higher risk categories (men: 12.4%-16.5%; women: 10.2% (M 3 )), while not significantly reducing the classification accuracy in controls. Conclusions The Genetic Risk Score is an independent predictor for incident 'hard' coronary heart disease in our ethnic Chinese population. Inclusion of genetic factors into coronary heart disease prediction models could significantly improve risk prediction performance.

Stress and anger as contextual factors and preexisting cognitive schemas: predicting parental child maltreatment risk.

PubMed

Rodriguez, Christina M; Richardson, Michael J

2007-11-01

Progress in the child maltreatment field depends on refinements in leading models. This study examines aspects of social information processing theory (Milner, 2000) in predicting physical maltreatment risk in a community sample. Consistent with this theory, selected preexisting schema (external locus-of-control orientation, inappropriate developmental expectations, low empathic perspective-taking ability, and low perceived attachment relationship to child) were expected to predict child abuse risk beyond contextual factors (parenting stress and anger expression). Based on 115 parents' self-report, results from this study support cognitive factors that predict abuse risk (with locus of control, perceived attachment, or empathy predicting different abuse risk measures, but not developmental expectations), although the broad contextual factors involving negative affectivity and stress were consistent predictors across abuse risk markers. Findings are discussed with regard to implications for future model evaluations, with indications the model may apply to other forms of maltreatment, such as psychological maltreatment or neglect.

Gene Expression Profiling Predicts the Development of Oral Cancer

PubMed Central

Saintigny, Pierre; Zhang, Li; Fan, You-Hong; El-Naggar, Adel K.; Papadimitrakopoulou, Vali; Feng, Lei; Lee, J. Jack; Kim, Edward S.; Hong, Waun Ki; Mao, Li

2011-01-01

Patients with oral preneoplastic lesion (OPL) have high risk of developing oral cancer. Although certain risk factors such as smoking status and histology are known, our ability to predict oral cancer risk remains poor. The study objective was to determine the value of gene expression profiling in predicting oral cancer development. Gene expression profile was measured in 86 of 162 OPL patients who were enrolled in a clinical chemoprevention trial that used the incidence of oral cancer development as a prespecified endpoint. The median follow-up time was 6.08 years and 35 of the 86 patients developed oral cancer over the course. Gene expression profiles were associated with oral cancer-free survival and used to develope multivariate predictive models for oral cancer prediction. We developed a 29-transcript predictive model which showed marked improvement in terms of prediction accuracy (with 8% predicting error rate) over the models using previously known clinico-pathological risk factors. Based on the gene expression profile data, we also identified 2182 transcripts significantly associated with oral cancer risk associated genes (P-value<0.01, single variate Cox proportional hazards model). Functional pathway analysis revealed proteasome machinery, MYC, and ribosomes components as the top gene sets associated with oral cancer risk. In multiple independent datasets, the expression profiles of the genes can differentiate head and neck cancer from normal mucosa. Our results show that gene expression profiles may improve the prediction of oral cancer risk in OPL patients and the significant genes identified may serve as potential targets for oral cancer chemoprevention. PMID:21292635

A Public-Private Partnership Develops and Externally Validates a 30-Day Hospital Readmission Risk Prediction Model

PubMed Central

Choudhry, Shahid A.; Li, Jing; Davis, Darcy; Erdmann, Cole; Sikka, Rishi; Sutariya, Bharat

2013-01-01

Introduction: Preventing the occurrence of hospital readmissions is needed to improve quality of care and foster population health across the care continuum. Hospitals are being held accountable for improving transitions of care to avert unnecessary readmissions. Advocate Health Care in Chicago and Cerner (ACC) collaborated to develop all-cause, 30-day hospital readmission risk prediction models to identify patients that need interventional resources. Ideally, prediction models should encompass several qualities: they should have high predictive ability; use reliable and clinically relevant data; use vigorous performance metrics to assess the models; be validated in populations where they are applied; and be scalable in heterogeneous populations. However, a systematic review of prediction models for hospital readmission risk determined that most performed poorly (average C-statistic of 0.66) and efforts to improve their performance are needed for widespread usage. Methods: The ACC team incorporated electronic health record data, utilized a mixed-method approach to evaluate risk factors, and externally validated their prediction models for generalizability. Inclusion and exclusion criteria were applied on the patient cohort and then split for derivation and internal validation. Stepwise logistic regression was performed to develop two predictive models: one for admission and one for discharge. The prediction models were assessed for discrimination ability, calibration, overall performance, and then externally validated. Results: The ACC Admission and Discharge Models demonstrated modest discrimination ability during derivation, internal and external validation post-recalibration (C-statistic of 0.76 and 0.78, respectively), and reasonable model fit during external validation for utility in heterogeneous populations. Conclusions: The ACC Admission and Discharge Models embody the design qualities of ideal prediction models. The ACC plans to continue its partnership to further improve and develop valuable clinical models. PMID:24224068

A calibration hierarchy for risk models was defined: from utopia to empirical data.

PubMed

Van Calster, Ben; Nieboer, Daan; Vergouwe, Yvonne; De Cock, Bavo; Pencina, Michael J; Steyerberg, Ewout W

2016-06-01

Calibrated risk models are vital for valid decision support. We define four levels of calibration and describe implications for model development and external validation of predictions. We present results based on simulated data sets. A common definition of calibration is "having an event rate of R% among patients with a predicted risk of R%," which we refer to as "moderate calibration." Weaker forms of calibration only require the average predicted risk (mean calibration) or the average prediction effects (weak calibration) to be correct. "Strong calibration" requires that the event rate equals the predicted risk for every covariate pattern. This implies that the model is fully correct for the validation setting. We argue that this is unrealistic: the model type may be incorrect, the linear predictor is only asymptotically unbiased, and all nonlinear and interaction effects should be correctly modeled. In addition, we prove that moderate calibration guarantees nonharmful decision making. Finally, results indicate that a flexible assessment of calibration in small validation data sets is problematic. Strong calibration is desirable for individualized decision support but unrealistic and counter productive by stimulating the development of overly complex models. Model development and external validation should focus on moderate calibration. Copyright © 2016 Elsevier Inc. All rights reserved.

Association of Coronary Artery Calcification with Estimated Coronary Heart Disease Risk from Prediction Models in a Community-Based Sample of Japanese Men: The Shiga Epidemiological Study of Subclinical Atherosclerosis (SESSA).

PubMed

Fujiyoshi, Akira; Arima, Hisatomi; Tanaka-Mizuno, Sachiko; Hisamatsu, Takahashi; Kadowaki, Sayaka; Kadota, Aya; Zaid, Maryam; Sekikawa, Akira; Yamamoto, Takashi; Horie, Minoru; Miura, Katsuyuki; Ueshima, Hirotsugu

2017-12-05

The clinical significance of coronary artery calcification (CAC) is not fully determined in general East Asian populations where background coronary heart disease (CHD) is less common than in USA/Western countries. We cross-sectionally assessed the association between CAC and estimated CHD risk as well as each major risk factor in general Japanese men. Participants were 996 randomly selected Japanese men aged 40-79 y, free of stroke, myocardial infarction, or revascularization. We examined an independent relationship between each risk factor used in prediction models and CAC score ≥100 by logistic regression. We then divided the participants into quintiles of estimated CHD risk per prediction model to calculate odds ratio of having CAC score ≥100. Receiver operating characteristic curve and c-index were used to examine discriminative ability of prevalent CAC for each prediction model. Age, smoking status, and systolic blood pressure were significantly associated with CAC score ≥100 in the multivariable analysis. The odds of having CAC score ≥100 were higher for those in higher quintiles in all prediction models (p-values for trend across quintiles ＜0.0001 for all models). All prediction models showed fair and similar discriminative abilities to detect CAC score ≥100, with similar c-statistics (around 0.70). In a community-based sample of Japanese men free of CHD and stroke, CAC score ≥100 was significantly associated with higher estimated CHD risk by prediction models. This finding supports the potential utility of CAC as a biomarker for CHD in a general Japanese male population.

Predicting risk of trace element pollution from municipal roads using site-specific soil samples and remotely sensed data.

PubMed

Reeves, Mari Kathryn; Perdue, Margaret; Munk, Lee Ann; Hagedorn, Birgit

2018-07-15

Studies of environmental processes exhibit spatial variation within data sets. The ability to derive predictions of risk from field data is a critical path forward in understanding the data and applying the information to land and resource management. Thanks to recent advances in predictive modeling, open source software, and computing, the power to do this is within grasp. This article provides an example of how we predicted relative trace element pollution risk from roads across a region by combining site specific trace element data in soils with regional land cover and planning information in a predictive model framework. In the Kenai Peninsula of Alaska, we sampled 36 sites (191 soil samples) adjacent to roads for trace elements. We then combined this site specific data with freely-available land cover and urban planning data to derive a predictive model of landscape scale environmental risk. We used six different model algorithms to analyze the dataset, comparing these in terms of their predictive abilities and the variables identified as important. Based on comparable predictive abilities (mean R 2 from 30 to 35% and mean root mean square error from 65 to 68%), we averaged all six model outputs to predict relative levels of trace element deposition in soils-given the road surface, traffic volume, sample distance from the road, land cover category, and impervious surface percentage. Mapped predictions of environmental risk from toxic trace element pollution can show land managers and transportation planners where to prioritize road renewal or maintenance by each road segment's relative environmental and human health risk. Published by Elsevier B.V.

A discriminant analysis prediction model of non-syndromic cleft lip with or without cleft palate based on risk factors.

PubMed

Li, Huixia; Luo, Miyang; Luo, Jiayou; Zheng, Jianfei; Zeng, Rong; Du, Qiyun; Fang, Junqun; Ouyang, Na

2016-11-23

A risk prediction model of non-syndromic cleft lip with or without cleft palate (NSCL/P) was established by a discriminant analysis to predict the individual risk of NSCL/P in pregnant women. A hospital-based case-control study was conducted with 113 cases of NSCL/P and 226 controls without NSCL/P. The cases and the controls were obtained from 52 birth defects' surveillance hospitals in Hunan Province, China. A questionnaire was administered in person to collect the variables relevant to NSCL/P by face to face interviews. Logistic regression models were used to analyze the influencing factors of NSCL/P, and a stepwise Fisher discriminant analysis was subsequently used to construct the prediction model. In the univariate analysis, 13 influencing factors were related to NSCL/P, of which the following 8 influencing factors as predictors determined the discriminant prediction model: family income, maternal occupational hazards exposure, premarital medical examination, housing renovation, milk/soymilk intake in the first trimester of pregnancy, paternal occupational hazards exposure, paternal strong tea drinking, and family history of NSCL/P. The model had statistical significance (lambda = 0.772, chi-square = 86.044, df = 8, P < 0.001). Self-verification showed that 83.8 % of the participants were correctly predicted to be NSCL/P cases or controls with a sensitivity of 74.3 % and a specificity of 88.5 %. The area under the receiver operating characteristic curve (AUC) was 0.846. The prediction model that was established using the risk factors of NSCL/P can be useful for predicting the risk of NSCL/P. Further research is needed to improve the model, and confirm the validity and reliability of the model.

New Zealand Diabetes Cohort Study cardiovascular risk score for people with Type 2 diabetes: validation in the PREDICT cohort.

PubMed

Robinson, Tom; Elley, C Raina; Wells, Sue; Robinson, Elizabeth; Kenealy, Tim; Pylypchuk, Romana; Bramley, Dale; Arroll, Bruce; Crengle, Sue; Riddell, Tania; Ameratunga, Shanthi; Metcalf, Patricia; Drury, Paul L

2012-09-01

New Zealand (NZ) guidelines recommend treating people for cardiovascular disease (CVD) risk on the basis of five-year absolute risk using a NZ adaptation of the Framingham risk equation. A diabetes-specific Diabetes Cohort Study (DCS) CVD predictive risk model has been developed and validated using NZ Get Checked data. To revalidate the DCS model with an independent cohort of people routinely assessed using PREDICT, a web-based CVD risk assessment and management programme. People with Type 2 diabetes without pre-existing CVD were identified amongst people who had a PREDICT risk assessment between 2002 and 2005. From this group we identified those with sufficient data to allow estimation of CVD risk with the DCS models. We compared the DCS models with the NZ Framingham risk equation in terms of discrimination, calibration, and reclassification implications. Of 3044 people in our study cohort, 1829 people had complete data and therefore had CVD risks calculated. Of this group, 12.8% (235) had a cardiovascular event during the five-year follow-up. The DCS models had better discrimination than the currently used equation, with C-statistics being 0.68 for the two DCS models and 0.65 for the NZ Framingham model. The DCS models were superior to the NZ Framingham equation at discriminating people with diabetes who will have a cardiovascular event. The adoption of a DCS model would lead to a small increase in the number of people with diabetes who are treated with medication, but potentially more CVD events would be avoided.

Cardiovascular risk assessment in elderly adults using SCORE OP model in a Latin American population: The experience from Ecuador.

PubMed

Sisa, Ivan

2018-02-09

Cardiovascular disease (CVD) mortality is predicted to increase in Latin America countries due to their rapidly aging population. However, there is very little information about CVD risk assessment as a primary preventive measure in this high-risk population. We predicted the national risk of developing CVD in Ecuadorian elderly population using the Systematic COronary Risk Evaluation in Older Persons (SCORE OP) High and Low models by risk categories/CVD risk region in 2009. Data on national cardiovascular risk factors were obtained from the Encuesta sobre Salud, Bienestar y Envejecimiento. We computed the predicted 5-year risk of CVD risk and compared the extent of agreement and reclassification in stratifying high-risk individuals between SCORE OP High and Low models. Analyses were done by risk categories, CVD risk region, and sex. In 2009, based on SCORE OP Low model almost 42% of elderly adults living in Ecuador were at high risk of suffering CVD over a 5-year period. The extent of agreement between SCORE OP High and Low risk prediction models was moderate (Cohen's kappa test of 0.5), 34% of individuals approximately were reclassified into different risk categories and a third of the population would benefit from a pharmacologic intervention to reduce the CVD risk. Forty-two percent of elderly Ecuadorians were at high risk of suffering CVD over a 5-year period, indicating an urgent need to tailor primary preventive measures for this vulnerable and high-risk population. Copyright © 2017 Elsevier España, S.L.U. All rights reserved.

The more from East-Asian, the better: risk prediction of colorectal cancer risk by GWAS-identified SNPs among Japanese.

PubMed

Abe, Makiko; Ito, Hidemi; Oze, Isao; Nomura, Masatoshi; Ogawa, Yoshihiro; Matsuo, Keitaro

2017-12-01

Little is known about the difference of genetic predisposition for CRC between ethnicities; however, many genetic traits common to colorectal cancer have been identified. This study investigated whether more SNPs identified in GWAS in East Asian population could improve the risk prediction of Japanese and explored possible application of genetic risk groups as an instrument of the risk communication. 558 Patients histologically verified colorectal cancer and 1116 first-visit outpatients were included for derivation study, and 547 cases and 547 controls were for replication study. Among each population, we evaluated prediction models for the risk of CRC that combined the genetic risk group based on SNPs from GWASs in European-population and a similarly developed model adding SNPs from GWASs in East Asian-population. We examined whether adding East Asian-specific SNPs would improve the discrimination. Six SNPs (rs6983267, rs4779584, rs4444235, rs9929218, rs10936599, rs16969681) from 23 SNPs by European-based GWAS and five SNPs (rs704017, rs11196172, rs10774214, rs647161, rs2423279) among ten SNPs by Asian-based GWAS were selected in CRC risk prediction model. Compared with a 6-SNP-based model, an 11-SNP model including Asian GWAS-SNPs showed improved discrimination capacity in Receiver operator characteristic analysis. A model with 11 SNPs resulted in statistically significant improvement in both derivation (P = 0.0039) and replication studies (P = 0.0018) compared with six SNP model. We estimated cumulative risk of CRC by using genetic risk group based on 11 SNPs and found that the cumulative risk at age 80 is approximately 13% in the high-risk group while 6% in the low-risk group. We constructed a more efficient CRC risk prediction model with 11 SNPs including newly identified East Asian-based GWAS SNPs (rs704017, rs11196172, rs10774214, rs647161, rs2423279). Risk grouping based on 11 SNPs depicted lifetime difference of CRC risk. This might be useful for effective individualized prevention for East Asian.

Risk prediction model for knee pain in the Nottingham community: a Bayesian modelling approach.

PubMed

Fernandes, G S; Bhattacharya, A; McWilliams, D F; Ingham, S L; Doherty, M; Zhang, W

2017-03-20

Twenty-five percent of the British population over the age of 50 years experiences knee pain. Knee pain can limit physical ability and cause distress and bears significant socioeconomic costs. The objectives of this study were to develop and validate the first risk prediction model for incident knee pain in the Nottingham community and validate this internally within the Nottingham cohort and externally within the Osteoarthritis Initiative (OAI) cohort. A total of 1822 participants from the Nottingham community who were at risk for knee pain were followed for 12 years. Of this cohort, two-thirds (n = 1203) were used to develop the risk prediction model, and one-third (n = 619) were used to validate the model. Incident knee pain was defined as pain on most days for at least 1 month in the past 12 months. Predictors were age, sex, body mass index, pain elsewhere, prior knee injury and knee alignment. A Bayesian logistic regression model was used to determine the probability of an OR >1. The Hosmer-Lemeshow χ 2 statistic (HLS) was used for calibration, and ROC curve analysis was used for discrimination. The OAI cohort from the United States was also used to examine the performance of the model. A risk prediction model for knee pain incidence was developed using a Bayesian approach. The model had good calibration, with an HLS of 7.17 (p = 0.52) and moderate discriminative ability (ROC 0.70) in the community. Individual scenarios are given using the model. However, the model had poor calibration (HLS 5866.28, p < 0.01) and poor discriminative ability (ROC 0.54) in the OAI cohort. To our knowledge, this is the first risk prediction model for knee pain, regardless of underlying structural changes of knee osteoarthritis, in the community using a Bayesian modelling approach. The model appears to work well in a community-based population but not in individuals with a higher risk for knee osteoarthritis, and it may provide a convenient tool for use in primary care to predict the risk of knee pain in the general population.

Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis.

PubMed

Perotte, Adler; Ranganath, Rajesh; Hirsch, Jamie S; Blei, David; Elhadad, Noémie

2015-07-01

As adoption of electronic health records continues to increase, there is an opportunity to incorporate clinical documentation as well as laboratory values and demographics into risk prediction modeling. The authors develop a risk prediction model for chronic kidney disease (CKD) progression from stage III to stage IV that includes longitudinal data and features drawn from clinical documentation. The study cohort consisted of 2908 primary-care clinic patients who had at least three visits prior to January 1, 2013 and developed CKD stage III during their documented history. Development and validation cohorts were randomly selected from this cohort and the study datasets included longitudinal inpatient and outpatient data from these populations. Time series analysis (Kalman filter) and survival analysis (Cox proportional hazards) were combined to produce a range of risk models. These models were evaluated using concordance, a discriminatory statistic. A risk model incorporating longitudinal data on clinical documentation and laboratory test results (concordance 0.849) predicts progression from state III CKD to stage IV CKD more accurately when compared to a similar model without laboratory test results (concordance 0.733, P<.001), a model that only considers the most recent laboratory test results (concordance 0.819, P < .031) and a model based on estimated glomerular filtration rate (concordance 0.779, P < .001). A risk prediction model that takes longitudinal laboratory test results and clinical documentation into consideration can predict CKD progression from stage III to stage IV more accurately than three models that do not take all of these variables into consideration. © The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association.

Testing the Predictive Validity of the Hendrich II Fall Risk Model.

PubMed

Jung, Hyesil; Park, Hyeoun-Ae

2018-03-01

Cumulative data on patient fall risk have been compiled in electronic medical records systems, and it is possible to test the validity of fall-risk assessment tools using these data between the times of admission and occurrence of a fall. The Hendrich II Fall Risk Model scores assessed during three time points of hospital stays were extracted and used for testing the predictive validity: (a) upon admission, (b) when the maximum fall-risk score from admission to falling or discharge, and (c) immediately before falling or discharge. Predictive validity was examined using seven predictive indicators. In addition, logistic regression analysis was used to identify factors that significantly affect the occurrence of a fall. Among the different time points, the maximum fall-risk score assessed between admission and falling or discharge showed the best predictive performance. Confusion or disorientation and having a poor ability to rise from a sitting position were significant risk factors for a fall.

Common carotid artery intima-media thickness is as good as carotid intima-media thickness of all carotid artery segments in improving prediction of coronary heart disease risk in the Atherosclerosis Risk in Communities (ARIC) study.

PubMed

Nambi, Vijay; Chambless, Lloyd; He, Max; Folsom, Aaron R; Mosley, Tom; Boerwinkle, Eric; Ballantyne, Christie M

2012-01-01

Carotid intima-media thickness (CIMT) and plaque information can improve coronary heart disease (CHD) risk prediction when added to traditional risk factors (TRF). However, obtaining adequate images of all carotid artery segments (A-CIMT) may be difficult. Of A-CIMT, the common carotid artery intima-media thickness (CCA-IMT) is relatively more reliable and easier to measure. We evaluated whether CCA-IMT is comparable to A-CIMT when added to TRF and plaque information in improving CHD risk prediction in the Atherosclerosis Risk in Communities (ARIC) study. Ten-year CHD risk prediction models using TRF alone, TRF + A-CIMT + plaque, and TRF + CCA-IMT + plaque were developed for the overall cohort, men, and women. The area under the receiver operator characteristic curve (AUC), per cent individuals reclassified, net reclassification index (NRI), and model calibration by the Grønnesby-Borgan test were estimated. There were 1722 incident CHD events in 12 576 individuals over a mean follow-up of 15.2 years. The AUC for TRF only, TRF + A-CIMT + plaque, and TRF + CCA-IMT + plaque models were 0.741, 0.754, and 0.753, respectively. Although there was some discordance when the CCA-IMT + plaque- and A-CIMT + plaque-based risk estimation was compared, the NRI and clinical NRI (NRI in the intermediate-risk group) when comparing the CIMT models with TRF-only model, per cent reclassified, and test for model calibration were not significantly different. Coronary heart disease risk prediction can be improved by adding A-CIMT + plaque or CCA-IMT + plaque information to TRF. Therefore, evaluating the carotid artery for plaque presence and measuring CCA-IMT, which is easier and more reliable than measuring A-CIMT, provide a good alternative to measuring A-CIMT for CHD risk prediction.

Age at exposure and attained age variations of cancer risk in the Japanese A-bomb and radiotherapy cohorts

DOE Office of Scientific and Technical Information (OSTI.GOV)

Schneider, Uwe, E-mail: uwe.schneider@uzh.ch; Walsh, Linda

Purpose: Phenomenological risk models for radiation-induced cancer are frequently applied to estimate the risk of radiation-induced cancers at radiotherapy doses. Such models often include the effect modification, of the main risk to radiation dose response, by age at exposure and attained age. The aim of this paper is to compare the patterns in risk effect modification by age, between models obtained from the Japanese atomic-bomb (A-bomb) survivor data and models for cancer risks previously reported for radiotherapy patients. Patterns in risk effect modification by age from the epidemiological studies of radiotherapy patients were also used to refine and extend themore » risk effect modification by age obtained from the A-bomb survivor data, so that more universal models can be presented here. Methods: Simple log-linear and power functions of age for the risk effect modification applied in models of the A-bomb survivor data are compared to risks from epidemiological studies of second cancers after radiotherapy. These functions of age were also refined and fitted to radiotherapy risks. The resulting age models provide a refined and extended functional dependence of risk with age at exposure and attained age especially beyond 40 and 65 yr, respectively, and provide a better representation than the currently available simple age functions. Results: It was found that the A-bomb models predict risk similarly to the outcomes of testicular cancer survivors. The survivors of Hodgkin’s disease show steeper variations of risk with both age at exposure and attained age. The extended models predict solid cancer risk increase as a function of age at exposure beyond 40 yr and the risk decrease as a function of attained age beyond 65 yr better than the simple models. Conclusions: The standard functions for risk effect modification by age, based on the A-bomb survivor data, predict second cancer risk in radiotherapy patients for ages at exposure prior to 40 yr and attained ages before 55 yr reasonably well. However, for larger ages, the refined and extended models can be applied to predict the risk as a function of age.« less

Age at exposure and attained age variations of cancer risk in the Japanese A-bomb and radiotherapy cohorts.

PubMed

Schneider, Uwe; Walsh, Linda

2015-08-01

Phenomenological risk models for radiation-induced cancer are frequently applied to estimate the risk of radiation-induced cancers at radiotherapy doses. Such models often include the effect modification, of the main risk to radiation dose response, by age at exposure and attained age. The aim of this paper is to compare the patterns in risk effect modification by age, between models obtained from the Japanese atomic-bomb (A-bomb) survivor data and models for cancer risks previously reported for radiotherapy patients. Patterns in risk effect modification by age from the epidemiological studies of radiotherapy patients were also used to refine and extend the risk effect modification by age obtained from the A-bomb survivor data, so that more universal models can be presented here. Simple log-linear and power functions of age for the risk effect modification applied in models of the A-bomb survivor data are compared to risks from epidemiological studies of second cancers after radiotherapy. These functions of age were also refined and fitted to radiotherapy risks. The resulting age models provide a refined and extended functional dependence of risk with age at exposure and attained age especially beyond 40 and 65 yr, respectively, and provide a better representation than the currently available simple age functions. It was found that the A-bomb models predict risk similarly to the outcomes of testicular cancer survivors. The survivors of Hodgkin's disease show steeper variations of risk with both age at exposure and attained age. The extended models predict solid cancer risk increase as a function of age at exposure beyond 40 yr and the risk decrease as a function of attained age beyond 65 yr better than the simple models. The standard functions for risk effect modification by age, based on the A-bomb survivor data, predict second cancer risk in radiotherapy patients for ages at exposure prior to 40 yr and attained ages before 55 yr reasonably well. However, for larger ages, the refined and extended models can be applied to predict the risk as a function of age.

Cumulative impact of common genetic variants and other risk factors on colorectal cancer risk in 42,103 individuals

PubMed Central

Dunlop, Malcolm G.; Tenesa, Albert; Farrington, Susan M.; Ballereau, Stephane; Brewster, David H.; Pharoah, Paul DP.; Schafmayer, Clemens; Hampe, Jochen; Völzke, Henry; Chang-Claude, Jenny; Hoffmeister, Michael; Brenner, Hermann; von Holst, Susanna; Picelli, Simone; Lindblom, Annika; Jenkins, Mark A.; Hopper, John L.; Casey, Graham; Duggan, David; Newcomb, Polly; Abulí, Anna; Bessa, Xavier; Ruiz-Ponte, Clara; Castellví-Bel, Sergi; Niittymäki, Iina; Tuupanen, Sari; Karhu, Auli; Aaltonen, Lauri; Zanke, Brent W.; Hudson, Thomas J.; Gallinger, Steven; Barclay, Ella; Martin, Lynn; Gorman, Maggie; Carvajal-Carmona, Luis; Walther, Axel; Kerr, David; Lubbe, Steven; Broderick, Peter; Chandler, Ian; Pittman, Alan; Penegar, Steven; Campbell, Harry; Tomlinson, Ian; Houlston, Richard S.

2016-01-01

Objective Colorectal cancer (CRC) has a substantial heritable component. Common genetic variation has been shown to contribute to CRC risk. In a large, multi-population study, we set out to assess the feasibility of CRC risk prediction using common genetic variant data, combined with other risk factors. We built a risk prediction model and applied it to the Scottish population using available data. Design Nine populations of European descent were studied to develop and validate colorectal cancer risk prediction models. Binary logistic regression was used to assess the combined effect of age, gender, family history (FH) and genotypes at 10 susceptibility loci that individually only modestly influence colorectal cancer risk. Risk models were generated from case-control data incorporating genotypes alone (n=39,266), and in combination with gender, age and family history (n=11,324). Model discriminatory performance was assessed using 10-fold internal cross-validation and externally using 4,187 independent samples. 10-year absolute risk was estimated by modelling genotype and FH with age- and gender-specific population risks. Results Median number of risk alleles was greater in cases than controls (10 vs 9, p<2.2×10−16), confirmed in external validation sets (Sweden p=1.2×10−6, Finland p=2×10−5). Mean per-allele increase in risk was 9% (OR 1.09; 95% CI 1.05–1.13). Discriminative performance was poor across the risk spectrum (area under curve (AUC) for genotypes alone - 0.57; AUC for genotype/age/gender/FH - 0.59). However, modelling genotype data, FH, age and gender with Scottish population data shows the practicalities of identifying a subgroup with >5% predicted 10-year absolute risk. Conclusion We show that genotype data provides additional information that complements age, gender and FH as risk factors. However, individualized genetic risk prediction is not currently feasible. Nonetheless, the modelling exercise suggests public health potential, since it is possible to stratify the population into CRC risk categories, thereby informing targeted prevention and surveillance. PMID:22490517

Mining geriatric assessment data for in-patient fall prediction models and high-risk subgroups

PubMed Central

2012-01-01

Background Hospital in-patient falls constitute a prominent problem in terms of costs and consequences. Geriatric institutions are most often affected, and common screening tools cannot predict in-patient falls consistently. Our objectives are to derive comprehensible fall risk classification models from a large data set of geriatric in-patients' assessment data and to evaluate their predictive performance (aim#1), and to identify high-risk subgroups from the data (aim#2). Methods A data set of n = 5,176 single in-patient episodes covering 1.5 years of admissions to a geriatric hospital were extracted from the hospital's data base and matched with fall incident reports (n = 493). A classification tree model was induced using the C4.5 algorithm as well as a logistic regression model, and their predictive performance was evaluated. Furthermore, high-risk subgroups were identified from extracted classification rules with a support of more than 100 instances. Results The classification tree model showed an overall classification accuracy of 66%, with a sensitivity of 55.4%, a specificity of 67.1%, positive and negative predictive values of 15% resp. 93.5%. Five high-risk groups were identified, defined by high age, low Barthel index, cognitive impairment, multi-medication and co-morbidity. Conclusions Our results show that a little more than half of the fallers may be identified correctly by our model, but the positive predictive value is too low to be applicable. Non-fallers, on the other hand, may be sorted out with the model quite well. The high-risk subgroups and the risk factors identified (age, low ADL score, cognitive impairment, institutionalization, polypharmacy and co-morbidity) reflect domain knowledge and may be used to screen certain subgroups of patients with a high risk of falling. Classification models derived from a large data set using data mining methods can compete with current dedicated fall risk screening tools, yet lack diagnostic precision. High-risk subgroups may be identified automatically from existing geriatric assessment data, especially when combined with domain knowledge in a hybrid classification model. Further work is necessary to validate our approach in a controlled prospective setting. PMID:22417403

Mining geriatric assessment data for in-patient fall prediction models and high-risk subgroups.

PubMed

Marschollek, Michael; Gövercin, Mehmet; Rust, Stefan; Gietzelt, Matthias; Schulze, Mareike; Wolf, Klaus-Hendrik; Steinhagen-Thiessen, Elisabeth

2012-03-14

Hospital in-patient falls constitute a prominent problem in terms of costs and consequences. Geriatric institutions are most often affected, and common screening tools cannot predict in-patient falls consistently. Our objectives are to derive comprehensible fall risk classification models from a large data set of geriatric in-patients' assessment data and to evaluate their predictive performance (aim#1), and to identify high-risk subgroups from the data (aim#2). A data set of n = 5,176 single in-patient episodes covering 1.5 years of admissions to a geriatric hospital were extracted from the hospital's data base and matched with fall incident reports (n = 493). A classification tree model was induced using the C4.5 algorithm as well as a logistic regression model, and their predictive performance was evaluated. Furthermore, high-risk subgroups were identified from extracted classification rules with a support of more than 100 instances. The classification tree model showed an overall classification accuracy of 66%, with a sensitivity of 55.4%, a specificity of 67.1%, positive and negative predictive values of 15% resp. 93.5%. Five high-risk groups were identified, defined by high age, low Barthel index, cognitive impairment, multi-medication and co-morbidity. Our results show that a little more than half of the fallers may be identified correctly by our model, but the positive predictive value is too low to be applicable. Non-fallers, on the other hand, may be sorted out with the model quite well. The high-risk subgroups and the risk factors identified (age, low ADL score, cognitive impairment, institutionalization, polypharmacy and co-morbidity) reflect domain knowledge and may be used to screen certain subgroups of patients with a high risk of falling. Classification models derived from a large data set using data mining methods can compete with current dedicated fall risk screening tools, yet lack diagnostic precision. High-risk subgroups may be identified automatically from existing geriatric assessment data, especially when combined with domain knowledge in a hybrid classification model. Further work is necessary to validate our approach in a controlled prospective setting.

An extended reinforcement learning model of basal ganglia to understand the contributions of serotonin and dopamine in risk-based decision making, reward prediction, and punishment learning

PubMed Central

Balasubramani, Pragathi P.; Chakravarthy, V. Srinivasa; Ravindran, Balaraman; Moustafa, Ahmed A.

2014-01-01

Although empirical and neural studies show that serotonin (5HT) plays many functional roles in the brain, prior computational models mostly focus on its role in behavioral inhibition. In this study, we present a model of risk based decision making in a modified Reinforcement Learning (RL)-framework. The model depicts the roles of dopamine (DA) and serotonin (5HT) in Basal Ganglia (BG). In this model, the DA signal is represented by the temporal difference error (δ), while the 5HT signal is represented by a parameter (α) that controls risk prediction error. This formulation that accommodates both 5HT and DA reconciles some of the diverse roles of 5HT particularly in connection with the BG system. We apply the model to different experimental paradigms used to study the role of 5HT: (1) Risk-sensitive decision making, where 5HT controls risk assessment, (2) Temporal reward prediction, where 5HT controls time-scale of reward prediction, and (3) Reward/Punishment sensitivity, in which the punishment prediction error depends on 5HT levels. Thus the proposed integrated RL model reconciles several existing theories of 5HT and DA in the BG. PMID:24795614

Predicting the cumulative risk of death during hospitalization by modeling weekend, weekday and diurnal mortality risks.

PubMed

Coiera, Enrico; Wang, Ying; Magrabi, Farah; Concha, Oscar Perez; Gallego, Blanca; Runciman, William

2014-05-21

Current prognostic models factor in patient and disease specific variables but do not consider cumulative risks of hospitalization over time. We developed risk models of the likelihood of death associated with cumulative exposure to hospitalization, based on time-varying risks of hospitalization over any given day, as well as day of the week. Model performance was evaluated alone, and in combination with simple disease-specific models. Patients admitted between 2000 and 2006 from 501 public and private hospitals in NSW, Australia were used for training and 2007 data for evaluation. The impact of hospital care delivered over different days of the week and or times of the day was modeled by separating hospitalization risk into 21 separate time periods (morning, day, night across the days of the week). Three models were developed to predict death up to 7-days post-discharge: 1/a simple background risk model using age, gender; 2/a time-varying risk model for exposure to hospitalization (admission time, days in hospital); 3/disease specific models (Charlson co-morbidity index, DRG). Combining these three generated a full model. Models were evaluated by accuracy, AUC, Akaike and Bayesian information criteria. There was a clear diurnal rhythm to hospital mortality in the data set, peaking in the evening, as well as the well-known 'weekend-effect' where mortality peaks with weekend admissions. Individual models had modest performance on the test data set (AUC 0.71, 0.79 and 0.79 respectively). The combined model which included time-varying risk however yielded an average AUC of 0.92. This model performed best for stays up to 7-days (93% of admissions), peaking at days 3 to 5 (AUC 0.94). Risks of hospitalization vary not just with the day of the week but also time of the day, and can be used to make predictions about the cumulative risk of death associated with an individual's hospitalization. Combining disease specific models with such time varying- estimates appears to result in robust predictive performance. Such risk exposure models should find utility both in enhancing standard prognostic models as well as estimating the risk of continuation of hospitalization.

Making predictions of mangrove deforestation: a comparison of two methods in Kenya.

PubMed

Rideout, Alasdair J R; Joshi, Neha P; Viergever, Karin M; Huxham, Mark; Briers, Robert A

2013-11-01

Deforestation of mangroves is of global concern given their importance for carbon storage, biogeochemical cycling and the provision of other ecosystem services, but the links between rates of loss and potential drivers or risk factors are rarely evaluated. Here, we identified key drivers of mangrove loss in Kenya and compared two different approaches to predicting risk. Risk factors tested included various possible predictors of anthropogenic deforestation, related to population, suitability for land use change and accessibility. Two approaches were taken to modelling risk; a quantitative statistical approach and a qualitative categorical ranking approach. A quantitative model linking rates of loss to risk factors was constructed based on generalized least squares regression and using mangrove loss data from 1992 to 2000. Population density, soil type and proximity to roads were the most important predictors. In order to validate this model it was used to generate a map of losses of Kenyan mangroves predicted to have occurred between 2000 and 2010. The qualitative categorical model was constructed using data from the same selection of variables, with the coincidence of different risk factors in particular mangrove areas used in an additive manner to create a relative risk index which was then mapped. Quantitative predictions of loss were significantly correlated with the actual loss of mangroves between 2000 and 2010 and the categorical risk index values were also highly correlated with the quantitative predictions. Hence, in this case the relatively simple categorical modelling approach was of similar predictive value to the more complex quantitative model of mangrove deforestation. The advantages and disadvantages of each approach are discussed, and the implications for mangroves are outlined. © 2013 Blackwell Publishing Ltd.

Individual risk of cutaneous melanoma in New Zealand: developing a clinical prediction aid.

PubMed

Sneyd, Mary Jane; Cameron, Claire; Cox, Brian

2014-05-22

New Zealand and Australia have the highest melanoma incidence rates worldwide. In New Zealand, both the incidence and thickness have been increasing. Clinical decisions require accurate risk prediction but a simple list of genetic, phenotypic and behavioural risk factors is inadequate to estimate individual risk as the risk factors for melanoma have complex interactions. In order to offer tailored clinical management strategies, we developed a New Zealand prediction model to estimate individual 5-year absolute risk of melanoma. A population-based case-control study (368 cases and 270 controls) of melanoma risk factors provided estimates of relative risks for fair-skinned New Zealanders aged 20-79 years. Model selection techniques and multivariate logistic regression were used to determine the important predictors. The relative risks for predictors were combined with baseline melanoma incidence rates and non-melanoma mortality rates to calculate individual probabilities of developing melanoma within 5 years. For women, the best model included skin colour, number of moles > =5 mm on the right arm, having a 1st degree relative with large moles, and a personal history of non-melanoma skin cancer (NMSC). The model correctly classified 68% of participants; the C-statistic was 0.74. For men, the best model included age, place of occupation up to age 18 years, number of moles > =5 mm on the right arm, birthplace, and a history of NMSC. The model correctly classified 67% of cases; the C-statistic was 0.71. We have developed the first New Zealand risk prediction model that calculates individual absolute 5-year risk of melanoma. This model will aid physicians to identify individuals at high risk, allowing them to individually target surveillance and other management strategies, and thereby reduce the high melanoma burden in New Zealand.

Risk assessment models to predict caries recurrence after oral rehabilitation under general anaesthesia: a pilot study.

PubMed

Lin, Yai-Tin; Kalhan, Ashish Chetan; Lin, Yng-Tzer Joseph; Kalhan, Tosha Ashish; Chou, Chein-Chin; Gao, Xiao Li; Hsu, Chin-Ying Stephen

2018-05-08

Oral rehabilitation under general anaesthesia (GA), commonly employed to treat high caries-risk children, has been associated with high economic and individual/family burden, besides high post-GA caries recurrence rates. As there is no caries prediction model available for paediatric GA patients, this study was performed to build caries risk assessment/prediction models using pre-GA data and to explore mid-term prognostic factors for early identification of high-risk children prone to caries relapse post-GA oral rehabilitation. Ninety-two children were identified and recruited with parental consent before oral rehabilitation under GA. Biopsychosocial data collection at baseline and the 6-month follow-up were conducted using questionnaire (Q), microbiological assessment (M) and clinical examination (C). The prediction models constructed using data collected from Q, Q + M and Q + M + C demonstrated an accuracy of 72%, 78% and 82%, respectively. Furthermore, of the 83 (90.2%) patients recalled 6 months after GA intervention, recurrent caries was identified in 54.2%, together with reduced bacterial counts, lower plaque index and increased percentage of children toothbrushing for themselves (all P < 0.05). Additionally, meal-time and toothbrushing duration were shown, through bivariate analyses, to be significant prognostic determinants for caries recurrence (both P < 0.05). Risk assessment/prediction models built using pre-GA data may be promising in identifying high-risk children prone to post-GA caries recurrence, although future internal and external validation of predictive models is warranted. © 2018 FDI World Dental Federation.

A prediction model for colon cancer surveillance data.

PubMed

Good, Norm M; Suresh, Krithika; Young, Graeme P; Lockett, Trevor J; Macrae, Finlay A; Taylor, Jeremy M G

2015-08-15

Dynamic prediction models make use of patient-specific longitudinal data to update individualized survival probability predictions based on current and past information. Colonoscopy (COL) and fecal occult blood test (FOBT) results were collected from two Australian surveillance studies on individuals characterized as high-risk based on a personal or family history of colorectal cancer. Motivated by a Poisson process, this paper proposes a generalized nonlinear model with a complementary log-log link as a dynamic prediction tool that produces individualized probabilities for the risk of developing advanced adenoma or colorectal cancer (AAC). This model allows predicted risk to depend on a patient's baseline characteristics and time-dependent covariates. Information on the dates and results of COLs and FOBTs were incorporated using time-dependent covariates that contributed to patient risk of AAC for a specified period following the test result. These covariates serve to update a person's risk as additional COL, and FOBT test information becomes available. Model selection was conducted systematically through the comparison of Akaike information criterion. Goodness-of-fit was assessed with the use of calibration plots to compare the predicted probability of event occurrence with the proportion of events observed. Abnormal COL results were found to significantly increase risk of AAC for 1 year following the test. Positive FOBTs were found to significantly increase the risk of AAC for 3 months following the result. The covariates that incorporated the updated test results were of greater significance and had a larger effect on risk than the baseline variables. Copyright © 2015 John Wiley & Sons, Ltd.

PP087. Multicenter external validation and recalibration of a model for preconceptional prediction of recurrent early-onset preeclampsia.

PubMed

van Kuijk, Sander; Delahaije, Denise; Dirksen, Carmen; Scheepers, Hubertina C J; Spaanderman, Marc; Ganzevoort, W; Duvekot, Hans; Oudijk, M A; van Pampus, M G; Dadelszen, Peter von; Peeters, Louis L; Smiths, Luc

2013-04-01

In an earlier paper we reported on the development of a model aimed at the prediction of preeclampsia recurrence, based on variables obtained before the next pregnancy (fasting glucose, BMI, previous birth of a small-for-gestational-age infant, duration of the previous pregnancy, and the presence of hypertension). To externally validate and recalibrate the prediction model for the risk of recurrence of early-onset preeclampsia. We collected data about course and outcome of the next ongoing pregnancy in 229 women with a history of early-onset preeclampsia. Recurrence was defined as preeclampsia requiring delivery before 34 weeks. We computed risk of recurrence and assessed model performance. In addition, we constructed a table comparing sensitivity, specificity, and predictive values for different suggested risk-thresholds. Early-onset preeclampsia recurred in 6.6% of women. The model systematically underestimated recurrence risk. The model's discriminative ability was modest, the area under the receiver operating characteristic curve was 58.9% (95% CI: 45.1 - 72.7). Using relevant risk-thresholds, the model created groups that were only moderately different in terms of their average risk of recurrent preeclampsia (Table 1). Compared to an AUC of 65% in the development cohort, the discriminate ability of the model was diminished. It had inadequate performance to classify women into clinically relevant risk groups. Copyright © 2013. Published by Elsevier B.V.

Simple Decision-Analytic Functions of the AUC for Ruling Out a Risk Prediction Model and an Added Predictor.

PubMed

Baker, Stuart G

2018-02-01

When using risk prediction models, an important consideration is weighing performance against the cost (monetary and harms) of ascertaining predictors. The minimum test tradeoff (MTT) for ruling out a model is the minimum number of all-predictor ascertainments per correct prediction to yield a positive overall expected utility. The MTT for ruling out an added predictor is the minimum number of added-predictor ascertainments per correct prediction to yield a positive overall expected utility. An approximation to the MTT for ruling out a model is 1/[P (H(AUC model )], where H(AUC) = AUC - {½ (1-AUC)} ½ , AUC is the area under the receiver operating characteristic (ROC) curve, and P is the probability of the predicted event in the target population. An approximation to the MTT for ruling out an added predictor is 1 /[P {(H(AUC Model:2 ) - H(AUC Model:1 )], where Model 2 includes an added predictor relative to Model 1. The latter approximation requires the Tangent Condition that the true positive rate at the point on the ROC curve with a slope of 1 is larger for Model 2 than Model 1. These approximations are suitable for back-of-the-envelope calculations. For example, in a study predicting the risk of invasive breast cancer, Model 2 adds to the predictors in Model 1 a set of 7 single nucleotide polymorphisms (SNPs). Based on the AUCs and the Tangent Condition, an MTT of 7200 was computed, which indicates that 7200 sets of SNPs are needed for every correct prediction of breast cancer to yield a positive overall expected utility. If ascertaining the SNPs costs $500, this MTT suggests that SNP ascertainment is not likely worthwhile for this risk prediction.

Prediction of breast cancer risk by genetic risk factors, overall and by hormone receptor status.

PubMed

Hüsing, Anika; Canzian, Federico; Beckmann, Lars; Garcia-Closas, Montserrat; Diver, W Ryan; Thun, Michael J; Berg, Christine D; Hoover, Robert N; Ziegler, Regina G; Figueroa, Jonine D; Isaacs, Claudine; Olsen, Anja; Viallon, Vivian; Boeing, Heiner; Masala, Giovanna; Trichopoulos, Dimitrios; Peeters, Petra H M; Lund, Eiliv; Ardanaz, Eva; Khaw, Kay-Tee; Lenner, Per; Kolonel, Laurence N; Stram, Daniel O; Le Marchand, Loïc; McCarty, Catherine A; Buring, Julie E; Lee, I-Min; Zhang, Shumin; Lindström, Sara; Hankinson, Susan E; Riboli, Elio; Hunter, David J; Henderson, Brian E; Chanock, Stephen J; Haiman, Christopher A; Kraft, Peter; Kaaks, Rudolf

2012-09-01

There is increasing interest in adding common genetic variants identified through genome wide association studies (GWAS) to breast cancer risk prediction models. First results from such models showed modest benefits in terms of risk discrimination. Heterogeneity of breast cancer as defined by hormone-receptor status has not been considered in this context. In this study we investigated the predictive capacity of 32 GWAS-detected common variants for breast cancer risk, alone and in combination with classical risk factors, and for tumours with different hormone receptor status. Within the Breast and Prostate Cancer Cohort Consortium, we analysed 6009 invasive breast cancer cases and 7827 matched controls of European ancestry, with data on classical breast cancer risk factors and 32 common gene variants identified through GWAS. Discriminatory ability with respect to breast cancer of specific hormone receptor-status was assessed with the age adjusted and cohort-adjusted concordance statistic (AUROC(a)). Absolute risk scores were calculated with external reference data. Integrated discrimination improvement was used to measure improvements in risk prediction. We found a small but steady increase in discriminatory ability with increasing numbers of genetic variants included in the model (difference in AUROC(a) going from 2.7% to 4%). Discriminatory ability for all models varied strongly by hormone receptor status. Adding information on common polymorphisms provides small but statistically significant improvements in the quality of breast cancer risk prediction models. We consistently observed better performance for receptor-positive cases, but the gain in discriminatory quality is not sufficient for clinical application.

When does risk perception predict protection motivation for health threats? A person-by-situation analysis.

PubMed

Ferrer, Rebecca A; Klein, William M P; Avishai, Aya; Jones, Katelyn; Villegas, Megan; Sheeran, Paschal

2018-01-01

Although risk perception is a key concept in many health behavior theories, little research has explicitly tested when risk perception predicts motivation to take protective action against a health threat (protection motivation). The present study tackled this question by (a) adopting a multidimensional model of risk perception that comprises deliberative, affective, and experiential components (the TRIRISK model), and (b) taking a person-by-situation approach. We leveraged a highly intensive within-subjects paradigm to test features of the health threat (i.e., perceived severity) and individual differences (e.g., emotion reappraisal) as moderators of the relationship between the three types of risk perception and protection motivation in a within-subjects design. Multi-level modeling of 2968 observations (32 health threats across 94 participants) showed interactions among the TRIRISK components and moderation both by person-level and situational factors. For instance, affective risk perception better predicted protection motivation when deliberative risk perception was high, when the threat was less severe, and among participants who engage less in emotional reappraisal. These findings support the TRIRISK model and offer new insights into when risk perceptions predict protection motivation.

When does risk perception predict protection motivation for health threats? A person-by-situation analysis

PubMed Central

Klein, William M. P.; Avishai, Aya; Jones, Katelyn; Villegas, Megan; Sheeran, Paschal

2018-01-01

Although risk perception is a key concept in many health behavior theories, little research has explicitly tested when risk perception predicts motivation to take protective action against a health threat (protection motivation). The present study tackled this question by (a) adopting a multidimensional model of risk perception that comprises deliberative, affective, and experiential components (the TRIRISK model), and (b) taking a person-by-situation approach. We leveraged a highly intensive within-subjects paradigm to test features of the health threat (i.e., perceived severity) and individual differences (e.g., emotion reappraisal) as moderators of the relationship between the three types of risk perception and protection motivation in a within-subjects design. Multi-level modeling of 2968 observations (32 health threats across 94 participants) showed interactions among the TRIRISK components and moderation both by person-level and situational factors. For instance, affective risk perception better predicted protection motivation when deliberative risk perception was high, when the threat was less severe, and among participants who engage less in emotional reappraisal. These findings support the TRIRISK model and offer new insights into when risk perceptions predict protection motivation. PMID:29494705

Listeria monocytogenes in Retail Delicatessens: an Interagency Risk Assessment-model and baseline results.

PubMed

Pouillot, Régis; Gallagher, Daniel; Tang, Jia; Hoelzer, Karin; Kause, Janell; Dennis, Sherri B

2015-01-01

The Interagency Risk Assessment-Listeria monocytogenes (Lm) in Retail Delicatessens provides a scientific assessment of the risk of listeriosis associated with the consumption of ready-to-eat (RTE) foods commonly prepared and sold in the delicatessen (deli) of a retail food store. The quantitative risk assessment (QRA) model simulates the behavior of retail employees in a deli department and tracks the Lm potentially present in this environment and in the food. Bacterial growth, bacterial inactivation (following washing and sanitizing actions), and cross-contamination (from object to object, from food to object, or from object to food) are evaluated through a discrete event modeling approach. The QRA evaluates the risk per serving of deli-prepared RTE food for the susceptible and general population, using a dose-response model from the literature. This QRA considers six separate retail baseline conditions and provides information on the predicted risk of listeriosis for each. Among the baseline conditions considered, the model predicts that (i) retail delis without an environmental source of Lm (such as niches), retail delis without niches that do apply temperature control, and retail delis with niches that do apply temperature control lead to lower predicted risk of listeriosis relative to retail delis with niches and (ii) retail delis with incoming RTE foods that are contaminated with Lm lead to higher predicted risk of listeriosis, directly or through cross-contamination, whether the contaminated incoming product supports growth or not. The risk assessment predicts that listeriosis cases associated with retail delicatessens result from a sequence of key events: (i) the contaminated RTE food supports Lm growth; (ii) improper retail and/or consumer storage temperature or handling results in the growth of Lm on the RTE food; and (iii) the consumer of this RTE food is susceptible to listeriosis. The risk assessment model, therefore, predicts that cross-contamination with Lm at retail predominantly results in sporadic cases.

Measurement error and timing of predictor values for multivariable risk prediction models are poorly reported.

PubMed

Whittle, Rebecca; Peat, George; Belcher, John; Collins, Gary S; Riley, Richard D

2018-05-18

Measurement error in predictor variables may threaten the validity of clinical prediction models. We sought to evaluate the possible extent of the problem. A secondary objective was to examine whether predictors are measured at the intended moment of model use. A systematic search of Medline was used to identify a sample of articles reporting the development of a clinical prediction model published in 2015. After screening according to a predefined inclusion criteria, information on predictors, strategies to control for measurement error and intended moment of model use were extracted. Susceptibility to measurement error for each predictor was classified into low and high risk. Thirty-three studies were reviewed, including 151 different predictors in the final prediction models. Fifty-one (33.7%) predictors were categorised as high risk of error, however this was not accounted for in the model development. Only 8 (24.2%) studies explicitly stated the intended moment of model use and when the predictors were measured. Reporting of measurement error and intended moment of model use is poor in prediction model studies. There is a need to identify circumstances where ignoring measurement error in prediction models is consequential and whether accounting for the error will improve the predictions. Copyright © 2018. Published by Elsevier Inc.

Utilization of the NSQIP-Pediatric Database in Development and Validation of a New Predictive Model of Pediatric Postoperative Wound Complications.

PubMed

Maizlin, Ilan I; Redden, David T; Beierle, Elizabeth A; Chen, Mike K; Russell, Robert T

2017-04-01

Surgical wound classification, introduced in 1964, stratifies the risk of surgical site infection (SSI) based on a clinical estimate of the inoculum of bacteria encountered during the procedure. Recent literature has questioned the accuracy of predicting SSI risk based on wound classification. We hypothesized that a more specific model founded on specific patient and perioperative factors would more accurately predict the risk of SSI. Using all observations from the 2012 to 2014 pediatric National Surgical Quality Improvement Program-Pediatric (NSQIP-P) Participant Use File, patients were randomized into model creation and model validation datasets. Potential perioperative predictive factors were assessed with univariate analysis for each of 4 outcomes: wound dehiscence, superficial wound infection, deep wound infection, and organ space infection. A multiple logistic regression model with a step-wise backwards elimination was performed. A receiver operating characteristic curve with c-statistic was generated to assess the model discrimination for each outcome. A total of 183,233 patients were included. All perioperative NSQIP factors were evaluated for clinical pertinence. Of the original 43 perioperative predictive factors selected, 6 to 9 predictors for each outcome were significantly associated with postoperative SSI. The predictive accuracy level of our model compared favorably with the traditional wound classification in each outcome of interest. The proposed model from NSQIP-P demonstrated a significantly improved predictive ability for postoperative SSIs than the current wound classification system. This model will allow providers to more effectively counsel families and patients of these risks, and more accurately reflect true risks for individual surgical patients to hospitals and payers. Copyright © 2017 American College of Surgeons. Published by Elsevier Inc. All rights reserved.

A Habitat-based Wind-Wildlife Collision Model with Application to the Upper Great Plains Region

DOE Office of Scientific and Technical Information (OSTI.GOV)

Forcey, Greg, M.

Most previous studies on collision impacts at wind facilities have taken place at the site-specific level and have only examined small-scale influences on mortality. In this study, we examine landscape-level influences using a hierarchical spatial model combined with existing datasets and life history knowledge for: Horned Lark, Red-eyed Vireo, Mallard, American Avocet, Golden Eagle, Whooping Crane, red bat, silver-haired bat, and hoary bat. These species were modeled in the central United States within Bird Conservation Regions 11, 17, 18, and 19. For the bird species, we modeled bird abundance from existing datasets as a function of habitat variables known tomore » be preferred by each species to develop a relative abundance prediction for each species. For bats, there are no existing abundance datasets so we identified preferred habitat in the landscape for each species and assumed that greater amounts of preferred habitat would equate to greater abundance of bats. The abundance predictions for bird and bats were modeled with additional exposure factors known to influence collisions such as visibility, wind, temperature, precipitation, topography, and behavior to form a final mapped output of predicted collision risk within the study region. We reviewed published mortality studies from wind farms in our study region and collected data on reported mortality of our focal species to compare to our modeled predictions. We performed a sensitivity analysis evaluating model performance of 6 different scenarios where habitat and exposure factors were weighted differently. We compared the model performance in each scenario by evaluating observed data vs. our model predictions using spearmans rank correlations. Horned Lark collision risk was predicted to be highest in the northwestern and west-central portions of the study region with lower risk predicted elsewhere. Red-eyed Vireo collision risk was predicted to be the highest in the eastern portions of the study region and in the forested areas of the western portion; the lowest risk was predicted in the treeless portions of the northwest portion of the study area. Mallard collision risk was predicted to be highest in the eastern central portion of the prairie potholes and in Iowa which has a high density of pothole wetlands; lower risk was predicted in the more arid portions of the study area. Predicted collision risk for American Avocet was similar to Mallard and was highest in the prairie pothole region and lower elsewhere. Golden Eagle collision risk was predicted to be highest in the mountainous areas of the western portion of the study area and lowest in the eastern portion of the prairie potholes. Whooping Crane predicted collision risk was highest within the migration corridor that the birds follow through in the central portion of the study region; predicted collision risk was much lower elsewhere. Red bat collision risk was highly driven by large tracts of forest and river corridors which made up most of the areas of higher collision risk. Silver-haired bat and hoary bat predicted collision risk were nearly identical and driven largely by forest and river corridors as well as locations with warmer temperatures, and lower average wind speeds. Horned Lark collisions were mostly influenced by abundance and predictions showed a moderate correlation between observed and predicted mortality (r = 0.55). Red bat, silver-haired bat, and hoary bat predictions were much higher and shown a strong correlations with observed mortality with correlations of 0.85, 0.90, and 0.91 respectively. Red bat collisions were influenced primarily by habitat, while hoary bat and silver-haired bat collisions were influenced mainly by exposure variables. Stronger correlations between observed and predicted collision for bats than for Horned Larks can likely be attributed to stronger habitat associations and greater influences of weather on behavior for bats. Although the collision predictions cannot be compared among species, our model outputs provide a convenient and easy landscape-level tool to quickly screen for siting issues at a high level. The model resolution is suitable for state or multi-county siting but users are cautioned against using these models for micrositing. The U.S. Fish and Wildlife Service recently released voluntary land-based wind energy guidelines for assessing impacts of a wind facility to wildlife using a tiered approach. The tiered approach uses an iterative approach for assessing impacts to wildlife in levels of increasing detail from landscape-level screening to site-specific field studies. Our models presented in this paper would be applicable to be used as tools to conduct screening at the tier 1 level and would not be appropriate to complete smaller scale tier 2 and tier 3 level studies. For smaller scale screening ancillary field studies should be conducted at the site-specific level to validate collision predictions.« less

Developing Risk Prediction Models for Kidney Injury and Assessing Incremental Value for Novel Biomarkers

PubMed Central

Kerr, Kathleen F.; Meisner, Allison; Thiessen-Philbrook, Heather; Coca, Steven G.

2014-01-01

The field of nephrology is actively involved in developing biomarkers and improving models for predicting patients’ risks of AKI and CKD and their outcomes. However, some important aspects of evaluating biomarkers and risk models are not widely appreciated, and statistical methods are still evolving. This review describes some of the most important statistical concepts for this area of research and identifies common pitfalls. Particular attention is paid to metrics proposed within the last 5 years for quantifying the incremental predictive value of a new biomarker. PMID:24855282

Predicting Risk of Type 2 Diabetes Mellitus with Genetic Risk Models on the Basis of Established Genome-wide Association Markers: A Systematic Review

PubMed Central

Bao, Wei; Hu, Frank B.; Rong, Shuang; Rong, Ying; Bowers, Katherine; Schisterman, Enrique F.; Liu, Liegang; Zhang, Cuilin

2013-01-01

This study aimed to evaluate the predictive performance of genetic risk models based on risk loci identified and/or confirmed in genome-wide association studies for type 2 diabetes mellitus. A systematic literature search was conducted in the PubMed/MEDLINE and EMBASE databases through April 13, 2012, and published data relevant to the prediction of type 2 diabetes based on genome-wide association marker–based risk models (GRMs) were included. Of the 1,234 potentially relevant articles, 21 articles representing 23 studies were eligible for inclusion. The median area under the receiver operating characteristic curve (AUC) among eligible studies was 0.60 (range, 0.55–0.68), which did not differ appreciably by study design, sample size, participants’ race/ethnicity, or the number of genetic markers included in the GRMs. In addition, the AUCs for type 2 diabetes did not improve appreciably with the addition of genetic markers into conventional risk factor–based models (median AUC, 0.79 (range, 0.63–0.91) vs. median AUC, 0.78 (range, 0.63–0.90), respectively). A limited number of included studies used reclassification measures and yielded inconsistent results. In conclusion, GRMs showed a low predictive performance for risk of type 2 diabetes, irrespective of study design, participants’ race/ethnicity, and the number of genetic markers included. Moreover, the addition of genome-wide association markers into conventional risk models produced little improvement in predictive performance. PMID:24008910

Development of a Korean Fracture Risk Score (KFRS) for Predicting Osteoporotic Fracture Risk: Analysis of Data from the Korean National Health Insurance Service

PubMed Central

Jang, Eun Jin; Park, ByeongJu; Kim, Tae-Young; Shin, Soon-Ae

2016-01-01

Background Asian-specific prediction models for estimating individual risk of osteoporotic fractures are rare. We developed a Korean fracture risk prediction model using clinical risk factors and assessed validity of the final model. Methods A total of 718,306 Korean men and women aged 50–90 years were followed for 7 years in a national system-based cohort study. In total, 50% of the subjects were assigned randomly to the development dataset and 50% were assigned to the validation dataset. Clinical risk factors for osteoporotic fracture were assessed at the biennial health check. Data on osteoporotic fractures during the follow-up period were identified by ICD-10 codes and the nationwide database of the National Health Insurance Service (NHIS). Results During the follow-up period, 19,840 osteoporotic fractures were reported (4,889 in men and 14,951 in women) in the development dataset. The assessment tool called the Korean Fracture Risk Score (KFRS) is comprised of a set of nine variables, including age, body mass index, recent fragility fracture, current smoking, high alcohol intake, lack of regular exercise, recent use of oral glucocorticoid, rheumatoid arthritis, and other causes of secondary osteoporosis. The KFRS predicted osteoporotic fractures over the 7 years. This score was validated using an independent dataset. A close relationship with overall fracture rate was observed when we compared the mean predicted scores after applying the KFRS with the observed risks after 7 years within each 10th of predicted risk. Conclusion We developed a Korean specific prediction model for osteoporotic fractures. The KFRS was able to predict risk of fracture in the primary population without bone mineral density testing and is therefore suitable for use in both clinical setting and self-assessment. The website is available at http://www.nhis.or.kr. PMID:27399597

Development of a Korean Fracture Risk Score (KFRS) for Predicting Osteoporotic Fracture Risk: Analysis of Data from the Korean National Health Insurance Service.

PubMed

Kim, Ha Young; Jang, Eun Jin; Park, ByeongJu; Kim, Tae-Young; Shin, Soon-Ae; Ha, Yong-Chan; Jang, Sunmee

2016-01-01

Asian-specific prediction models for estimating individual risk of osteoporotic fractures are rare. We developed a Korean fracture risk prediction model using clinical risk factors and assessed validity of the final model. A total of 718,306 Korean men and women aged 50-90 years were followed for 7 years in a national system-based cohort study. In total, 50% of the subjects were assigned randomly to the development dataset and 50% were assigned to the validation dataset. Clinical risk factors for osteoporotic fracture were assessed at the biennial health check. Data on osteoporotic fractures during the follow-up period were identified by ICD-10 codes and the nationwide database of the National Health Insurance Service (NHIS). During the follow-up period, 19,840 osteoporotic fractures were reported (4,889 in men and 14,951 in women) in the development dataset. The assessment tool called the Korean Fracture Risk Score (KFRS) is comprised of a set of nine variables, including age, body mass index, recent fragility fracture, current smoking, high alcohol intake, lack of regular exercise, recent use of oral glucocorticoid, rheumatoid arthritis, and other causes of secondary osteoporosis. The KFRS predicted osteoporotic fractures over the 7 years. This score was validated using an independent dataset. A close relationship with overall fracture rate was observed when we compared the mean predicted scores after applying the KFRS with the observed risks after 7 years within each 10th of predicted risk. We developed a Korean specific prediction model for osteoporotic fractures. The KFRS was able to predict risk of fracture in the primary population without bone mineral density testing and is therefore suitable for use in both clinical setting and self-assessment. The website is available at http://www.nhis.or.kr.

Anthropometric measures in cardiovascular disease prediction: comparison of laboratory-based versus non-laboratory-based model.

PubMed

Dhana, Klodian; Ikram, M Arfan; Hofman, Albert; Franco, Oscar H; Kavousi, Maryam

2015-03-01

Body mass index (BMI) has been used to simplify cardiovascular risk prediction models by substituting total cholesterol and high-density lipoprotein cholesterol. In the elderly, the ability of BMI as a predictor of cardiovascular disease (CVD) declines. We aimed to find the most predictive anthropometric measure for CVD risk to construct a non-laboratory-based model and to compare it with the model including laboratory measurements. The study included 2675 women and 1902 men aged 55-79 years from the prospective population-based Rotterdam Study. We used Cox proportional hazard regression analysis to evaluate the association of BMI, waist circumference, waist-to-hip ratio and a body shape index (ABSI) with CVD, including coronary heart disease and stroke. The performance of the laboratory-based and non-laboratory-based models was evaluated by studying the discrimination, calibration, correlation and risk agreement. Among men, ABSI was the most informative measure associated with CVD, therefore ABSI was used to construct the non-laboratory-based model. Discrimination of the non-laboratory-based model was not different than laboratory-based model (c-statistic: 0.680-vs-0.683, p=0.71); both models were well calibrated (15.3% observed CVD risk vs 16.9% and 17.0% predicted CVD risks by the non-laboratory-based and laboratory-based models, respectively) and Spearman rank correlation and the agreement between non-laboratory-based and laboratory-based models were 0.89 and 91.7%, respectively. Among women, none of the anthropometric measures were independently associated with CVD. Among middle-aged and elderly where the ability of BMI to predict CVD declines, the non-laboratory-based model, based on ABSI, could predict CVD risk as accurately as the laboratory-based model among men. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

Predictive Analytics for Identification of Patients at Risk for QT Interval Prolongation - A Systematic Review.

PubMed

Tomaselli Muensterman, Elena; Tisdale, James E

2018-06-08

Prolongation of the heart rate-corrected QT (QTc) interval increases the risk for torsades de pointes (TdP), a potentially fatal arrhythmia. The likelihood of TdP is higher in patients with risk factors, which include female sex, older age, heart failure with reduced ejection fraction, hypokalemia, hypomagnesemia, concomitant administration of ≥ 2 QTc interval-prolonging medications, among others. Assessment and quantification of risk factors may facilitate prediction of patients at highest risk for developing QTc interval prolongation and TdP. Investigators have utilized the field of predictive analytics, which generates predictions using techniques including data mining, modeling, machine learning, and others, to develop methods of risk quantification and prediction of QTc interval prolongation. Predictive analytics have also been incorporated into clinical decision support (CDS) tools to alert clinicians regarding patients at increased risk of developing QTc interval prolongation. The objectives of this paper are to assess the effectiveness of predictive analytics for identification of patients at risk of drug-induced QTc interval prolongation, and to discuss the efficacy of incorporation of predictive analytics into CDS tools in clinical practice. A systematic review of English language articles (human subjects only) was performed, yielding 57 articles, with an additional 4 articles identified from other sources; a total of 10 articles were included in this review. Risk scores for QTc interval prolongation have been developed in various patient populations including those in cardiac intensive care units (ICUs) and in broader populations of hospitalized or health system patients. One group developed a risk score that includes information regarding genetic polymorphisms; this score significantly predicted TdP. Development of QTc interval prolongation risk prediction models and incorporation of these models into CDS tools reduces the risk of QTc interval prolongation in cardiac ICUs and identifies health-system patients at increased risk for mortality. The impact of these QTc interval prolongation predictive analytics on overall patient safety outcomes, such as TdP and sudden cardiac death relative to the cost of development and implementation, requires further study. This article is protected by copyright. All rights reserved. This article is protected by copyright. All rights reserved.

External Validation and Recalibration of Risk Prediction Models for Acute Traumatic Brain Injury among Critically Ill Adult Patients in the United Kingdom

PubMed Central

Griggs, Kathryn A.; Prabhu, Gita; Gomes, Manuel; Lecky, Fiona E.; Hutchinson, Peter J. A.; Menon, David K.; Rowan, Kathryn M.

2015-01-01

Abstract This study validates risk prediction models for acute traumatic brain injury (TBI) in critical care units in the United Kingdom and recalibrates the models to this population. The Risk Adjustment In Neurocritical care (RAIN) Study was a prospective, observational cohort study in 67 adult critical care units. Adult patients admitted to critical care following acute TBI with a last pre-sedation Glasgow Coma Scale score of less than 15 were recruited. The primary outcomes were mortality and unfavorable outcome (death or severe disability, assessed using the Extended Glasgow Outcome Scale) at six months following TBI. Of 3626 critical care unit admissions, 2975 were analyzed. Following imputation of missing outcomes, mortality at six months was 25.7% and unfavorable outcome 57.4%. Ten risk prediction models were validated from Hukkelhoven and colleagues, the Medical Research Council (MRC) Corticosteroid Randomisation After Significant Head Injury (CRASH) Trial Collaborators, and the International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) group. The model with the best discrimination was the IMPACT “Lab” model (C index, 0.779 for mortality and 0.713 for unfavorable outcome). This model was well calibrated for mortality at six months but substantially under-predicted the risk of unfavorable outcome. Recalibration of the models resulted in small improvements in discrimination and excellent calibration for all models. The risk prediction models demonstrated sufficient statistical performance to support their use in research and audit but fell below the level required to guide individual patient decision-making. The published models for unfavorable outcome at six months had poor calibration in the UK critical care setting and the models recalibrated to this setting should be used in future research. PMID:25898072

External Validation and Recalibration of Risk Prediction Models for Acute Traumatic Brain Injury among Critically Ill Adult Patients in the United Kingdom.

PubMed

Harrison, David A; Griggs, Kathryn A; Prabhu, Gita; Gomes, Manuel; Lecky, Fiona E; Hutchinson, Peter J A; Menon, David K; Rowan, Kathryn M

2015-10-01

This study validates risk prediction models for acute traumatic brain injury (TBI) in critical care units in the United Kingdom and recalibrates the models to this population. The Risk Adjustment In Neurocritical care (RAIN) Study was a prospective, observational cohort study in 67 adult critical care units. Adult patients admitted to critical care following acute TBI with a last pre-sedation Glasgow Coma Scale score of less than 15 were recruited. The primary outcomes were mortality and unfavorable outcome (death or severe disability, assessed using the Extended Glasgow Outcome Scale) at six months following TBI. Of 3626 critical care unit admissions, 2975 were analyzed. Following imputation of missing outcomes, mortality at six months was 25.7% and unfavorable outcome 57.4%. Ten risk prediction models were validated from Hukkelhoven and colleagues, the Medical Research Council (MRC) Corticosteroid Randomisation After Significant Head Injury (CRASH) Trial Collaborators, and the International Mission for Prognosis and Analysis of Clinical Trials in TBI (IMPACT) group. The model with the best discrimination was the IMPACT "Lab" model (C index, 0.779 for mortality and 0.713 for unfavorable outcome). This model was well calibrated for mortality at six months but substantially under-predicted the risk of unfavorable outcome. Recalibration of the models resulted in small improvements in discrimination and excellent calibration for all models. The risk prediction models demonstrated sufficient statistical performance to support their use in research and audit but fell below the level required to guide individual patient decision-making. The published models for unfavorable outcome at six months had poor calibration in the UK critical care setting and the models recalibrated to this setting should be used in future research.

Risk prediction models of breast cancer: a systematic review of model performances.

PubMed

Anothaisintawee, Thunyarat; Teerawattananon, Yot; Wiratkapun, Chollathip; Kasamesup, Vijj; Thakkinstian, Ammarin

2012-05-01

The number of risk prediction models has been increasingly developed, for estimating about breast cancer in individual women. However, those model performances are questionable. We therefore have conducted a study with the aim to systematically review previous risk prediction models. The results from this review help to identify the most reliable model and indicate the strengths and weaknesses of each model for guiding future model development. We searched MEDLINE (PubMed) from 1949 and EMBASE (Ovid) from 1974 until October 2010. Observational studies which constructed models using regression methods were selected. Information about model development and performance were extracted. Twenty-five out of 453 studies were eligible. Of these, 18 developed prediction models and 7 validated existing prediction models. Up to 13 variables were included in the models and sample sizes for each study ranged from 550 to 2,404,636. Internal validation was performed in four models, while five models had external validation. Gail and Rosner and Colditz models were the significant models which were subsequently modified by other scholars. Calibration performance of most models was fair to good (expected/observe ratio: 0.87-1.12), but discriminatory accuracy was poor to fair both in internal validation (concordance statistics: 0.53-0.66) and in external validation (concordance statistics: 0.56-0.63). Most models yielded relatively poor discrimination in both internal and external validation. This poor discriminatory accuracy of existing models might be because of a lack of knowledge about risk factors, heterogeneous subtypes of breast cancer, and different distributions of risk factors across populations. In addition the concordance statistic itself is insensitive to measure the improvement of discrimination. Therefore, the new method such as net reclassification index should be considered to evaluate the improvement of the performance of a new develop model.

A Regularized Deep Learning Approach for Clinical Risk Prediction of Acute Coronary Syndrome Using Electronic Health Records.

PubMed

Huang, Zhengxing; Dong, Wei; Duan, Huilong; Liu, Jiquan

2018-05-01

Acute coronary syndrome (ACS), as a common and severe cardiovascular disease, is a leading cause of death and the principal cause of serious long-term disability globally. Clinical risk prediction of ACS is important for early intervention and treatment. Existing ACS risk scoring models are based mainly on a small set of hand-picked risk factors and often dichotomize predictive variables to simplify the score calculation. This study develops a regularized stacked denoising autoencoder (SDAE) model to stratify clinical risks of ACS patients from a large volume of electronic health records (EHR). To capture characteristics of patients at similar risk levels, and preserve the discriminating information across different risk levels, two constraints are added on SDAE to make the reconstructed feature representations contain more risk information of patients, which contribute to a better clinical risk prediction result. We validate our approach on a real clinical dataset consisting of 3464 ACS patient samples. The performance of our approach for predicting ACS risk remains robust and reaches 0.868 and 0.73 in terms of both AUC and accuracy, respectively. The obtained results show that the proposed approach achieves a competitive performance compared to state-of-the-art models in dealing with the clinical risk prediction problem. In addition, our approach can extract informative risk factors of ACS via a reconstructive learning strategy. Some of these extracted risk factors are not only consistent with existing medical domain knowledge, but also contain suggestive hypotheses that could be validated by further investigations in the medical domain.

Comparative Risk Predictions of Second Cancers After Carbon-Ion Therapy Versus Proton Therapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Eley, John G., E-mail: jeley@som.umaryland.edu; University of Texas Graduate School of Biomedical Sciences, Houston, Texas; Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, Maryland

Purpose: This work proposes a theoretical framework that enables comparative risk predictions for second cancer incidence after particle beam therapy for different ion species for individual patients, accounting for differences in relative biological effectiveness (RBE) for the competing processes of tumor initiation and cell inactivation. Our working hypothesis was that use of carbon-ion therapy instead of proton therapy would show a difference in the predicted risk of second cancer incidence in the breast for a sample of Hodgkin lymphoma (HL) patients. Methods and Materials: We generated biologic treatment plans and calculated relative predicted risks of second cancer in the breastmore » by using two proposed methods: a full model derived from the linear quadratic model and a simpler linear-no-threshold model. Results: For our reference calculation, we found the predicted risk of breast cancer incidence for carbon-ion plans-to-proton plan ratio, , to be 0.75 ± 0.07 but not significantly smaller than 1 (P=.180). Conclusions: Our findings suggest that second cancer risks are, on average, comparable between proton therapy and carbon-ion therapy.« less

Comparative Risk Predictions of Second Cancers After Carbon-Ion Therapy Versus Proton Therapy.

PubMed

Eley, John G; Friedrich, Thomas; Homann, Kenneth L; Howell, Rebecca M; Scholz, Michael; Durante, Marco; Newhauser, Wayne D

2016-05-01

This work proposes a theoretical framework that enables comparative risk predictions for second cancer incidence after particle beam therapy for different ion species for individual patients, accounting for differences in relative biological effectiveness (RBE) for the competing processes of tumor initiation and cell inactivation. Our working hypothesis was that use of carbon-ion therapy instead of proton therapy would show a difference in the predicted risk of second cancer incidence in the breast for a sample of Hodgkin lymphoma (HL) patients. We generated biologic treatment plans and calculated relative predicted risks of second cancer in the breast by using two proposed methods: a full model derived from the linear quadratic model and a simpler linear-no-threshold model. For our reference calculation, we found the predicted risk of breast cancer incidence for carbon-ion plans-to-proton plan ratio, , to be 0.75 ± 0.07 but not significantly smaller than 1 (P=.180). Our findings suggest that second cancer risks are, on average, comparable between proton therapy and carbon-ion therapy. Copyright © 2016 Elsevier Inc. All rights reserved.

Poisson Mixture Regression Models for Heart Disease Prediction.

PubMed

Mufudza, Chipo; Erol, Hamza

2016-01-01

Early heart disease control can be achieved by high disease prediction and diagnosis efficiency. This paper focuses on the use of model based clustering techniques to predict and diagnose heart disease via Poisson mixture regression models. Analysis and application of Poisson mixture regression models is here addressed under two different classes: standard and concomitant variable mixture regression models. Results show that a two-component concomitant variable Poisson mixture regression model predicts heart disease better than both the standard Poisson mixture regression model and the ordinary general linear Poisson regression model due to its low Bayesian Information Criteria value. Furthermore, a Zero Inflated Poisson Mixture Regression model turned out to be the best model for heart prediction over all models as it both clusters individuals into high or low risk category and predicts rate to heart disease componentwise given clusters available. It is deduced that heart disease prediction can be effectively done by identifying the major risks componentwise using Poisson mixture regression model.

Poisson Mixture Regression Models for Heart Disease Prediction

PubMed Central

Erol, Hamza

2016-01-01

Early heart disease control can be achieved by high disease prediction and diagnosis efficiency. This paper focuses on the use of model based clustering techniques to predict and diagnose heart disease via Poisson mixture regression models. Analysis and application of Poisson mixture regression models is here addressed under two different classes: standard and concomitant variable mixture regression models. Results show that a two-component concomitant variable Poisson mixture regression model predicts heart disease better than both the standard Poisson mixture regression model and the ordinary general linear Poisson regression model due to its low Bayesian Information Criteria value. Furthermore, a Zero Inflated Poisson Mixture Regression model turned out to be the best model for heart prediction over all models as it both clusters individuals into high or low risk category and predicts rate to heart disease componentwise given clusters available. It is deduced that heart disease prediction can be effectively done by identifying the major risks componentwise using Poisson mixture regression model. PMID:27999611

Pneumococcal vaccine targeting strategy for older adults: customized risk profiling.

PubMed

Balicer, Ran D; Cohen, Chandra J; Leibowitz, Morton; Feldman, Becca S; Brufman, Ilan; Roberts, Craig; Hoshen, Moshe

2014-02-12

Current pneumococcal vaccine campaigns take a broad, primarily age-based approach to immunization targeting, overlooking many clinical and administrative considerations necessary in disease prevention and resource planning for specific patient populations. We aim to demonstrate the utility of a population-specific predictive model for hospital-treated pneumonia to direct effective vaccine targeting. Data was extracted for 1,053,435 members of an Israeli HMO, age 50 and older, during the study period 2008-2010. We developed and validated a logistic regression model to predict hospital-treated pneumonia using training and test samples, including a set of standard and population-specific risk factors. The model's predictive value was tested for prospectively identifying cases of pneumonia and invasive pneumococcal disease (IPD), and was compared to the existing international paradigm for patient immunization targeting. In a multivariate regression, age, co-morbidity burden and previous pneumonia events were most strongly positively associated with hospital-treated pneumonia. The model predicting hospital-treated pneumonia yielded a c-statistic of 0.80. Utilizing the predictive model, the top 17% highest-risk within the study validation population were targeted to detect 54% of those members who were subsequently treated for hospitalized pneumonia in the follow up period. The high-risk population identified through this model included 46% of the follow-up year's IPD cases, and 27% of community-treated pneumonia cases. These outcomes were compared with international guidelines for risk for pneumococcal diseases that accurately identified only 35% of hospitalized pneumonia, 41% of IPD cases and 21% of community-treated pneumonia. We demonstrate that a customized model for vaccine targeting performs better than international guidelines, and therefore, risk modeling may allow for more precise vaccine targeting and resource allocation than current national and international guidelines. Health care managers and policy-makers may consider the strategic potential of utilizing clinical and administrative databases for creating population-specific risk prediction models to inform vaccination campaigns. Copyright © 2013 Elsevier Ltd. All rights reserved.

Dynamic Relationships Between Parental Monitoring, Peer Risk Involvement and Sexual Risk Behavior Among Bahamian Mid-Adolescents

PubMed Central

Wang, Bo; Stanton, Bonita; Deveaux, Lynette; Li, Xiaoming; Lunn, Sonja

2015-01-01

CONTEXT Considerable research has examined reciprocal relationships between parenting, peers and adolescent problem behavior; however, such studies have largely considered the influence of peers and parents separately. It is important to examine simultaneously the relationships between parental monitoring, peer risk involvement and adolescent sexual risk behavior, and whether increases in peer risk involvement and changes in parental monitoring longitudinally predict adolescent sexual risk behavior. METHODS Four waves of sexual behavior data were collected between 2008/2009 and 2011 from high school students aged 13–17 in the Bahamas. Structural equation and latent growth curve modeling were used to examine reciprocal relationships between parental monitoring, perceived peer risk involvement and adolescent sexual risk behavior. RESULTS For both male and female youth, greater perceived peer risk involvement predicted higher sexual risk behavior index scores, and greater parental monitoring predicted lower scores. Reciprocal relationships were found between parental monitoring and sexual risk behavior for males and between perceived peer risk involvement and sexual risk behavior for females. For males, greater sexual risk behavior predicted lower parental monitoring; for females, greater sexual risk behavior predicted higher perceived peer risk involvement. According to latent growth curve models, a higher initial level of parental monitoring predicted decreases in sexual risk behavior, whereas both a higher initial level and a higher growth rate of peer risk involvement predicted increases in sexual risk behavior. CONCLUSION Results highlight the important influence of peer risk involvement on youths’ sexual behavior and gender differences in reciprocal relationships between parental monitoring, peer influence and adolescent sexual risk behavior. PMID:26308261

Dynamic Relationships Between Parental Monitoring, Peer Risk Involvement and Sexual Risk Behavior Among Bahamian Mid-Adolescents.

PubMed

Wang, Bo; Stanton, Bonita; Deveaux, Lynette; Li, Xiaoming; Lunn, Sonja

2015-06-01

Considerable research has examined reciprocal relationships between parenting, peers and adolescent problem behavior; however, such studies have largely considered the influence of peers and parents separately. It is important to examine simultaneously the relationships between parental monitoring, peer risk involvement and adolescent sexual risk behavior, and whether increases in peer risk involvement and changes in parental monitoring longitudinally predict adolescent sexual risk behavior. Four waves of sexual behavior data were collected between 2008/2009 and 2011 from high school students aged 13-17 in the Bahamas. Structural equation and latent growth curve modeling were used to examine reciprocal relationships between parental monitoring, perceived peer risk involvement and adolescent sexual risk behavior. For both male and female youth, greater perceived peer risk involvement predicted higher sexual risk behavior index scores, and greater parental monitoring predicted lower scores. Reciprocal relationships were found between parental monitoring and sexual risk behavior for males and between perceived peer risk involvement and sexual risk behavior for females. For males, greater sexual risk behavior predicted lower parental monitoring; for females, greater sexual risk behavior predicted higher perceived peer risk involvement. According to latent growth curve models, a higher initial level of parental monitoring predicted decreases in sexual risk behavior, whereas both a higher initial level and a higher growth rate of peer risk involvement predicted increases in sexual risk behavior. Results highlight the important influence of peer risk involvement on youths' sexual behavior and gender differences in reciprocal relationships between parental monitoring, peer influence and adolescent sexual risk behavior.

Development of Predictive Models of Injury for the Lower Extremity, Lumbar, and Thoracic Spine after Discharge from Physical Rehabilitation

DTIC Science & Technology

2016-10-01

prediction models will vary by age and sex . Hypothesis 3: A multi-factorial prediction model that accurately predicts risk of new and recurring injuries...members for injury risk after they have been cleared to return to duty from an injury is of great importance. The purpose of this project is to determine ...It turns out that many patients are not formally discharged from rehabilitation. Many of them “ self -discharge” and just stop coming back, either

Incorporating Truncating Variants in PALB2, CHEK2 and ATM into the BOADICEA Breast Cancer Risk Model

PubMed Central

Lee, Andrew J.; Cunningham, Alex P.; Tischkowitz, Marc; Simard, Jacques; Pharoah, Paul D.; Easton, Douglas F.; Antoniou, Antonis C.

2016-01-01

Purpose The proliferation of gene-panel testing precipitates the need for a breast cancer (BC) risk model that incorporates the effects of mutations in several genes and family history (FH). We extended the BOADICEA model to incorporate the effects of truncating variants in PALB2, CHEK2 and ATM. Methods The BC incidence was modelled via the explicit effects of truncating variants in BRCA1/2, PALB2, CHEK2 and ATM and other unobserved genetic effects using segregation analysis methods. Results The predicted average BC risk by age 80 for an ATM mutation carrier is 28%, 30% for CHEK2, 50% for PALB2, 74% for BRCA1 and BRCA2. However, the BC risks are predicted to increase with FH-burden. In families with mutations, predicted risks for mutation-negative members depend on both FH and the specific mutation. The reduction in BC risk after negative predictive-testing is greatest when a BRCA1 mutation is identified in the family, but for women whose relatives carry a CHEK2 or ATM mutation, the risks decrease slightly. Conclusions The model may be a valuable tool for counselling women who have undergone gene-panel testing for providing consistent risks and harmonizing their clinical management. A web-application can be used to obtain BC- risks in clinical practice (http://ccge.medschl.cam.ac.uk/boadicea/). PMID:27464310

Incorporating truncating variants in PALB2, CHEK2, and ATM into the BOADICEA breast cancer risk model.

PubMed

Lee, Andrew J; Cunningham, Alex P; Tischkowitz, Marc; Simard, Jacques; Pharoah, Paul D; Easton, Douglas F; Antoniou, Antonis C

2016-12-01

The proliferation of gene panel testing precipitates the need for a breast cancer (BC) risk model that incorporates the effects of mutations in several genes and family history (FH). We extended the BOADICEA model to incorporate the effects of truncating variants in PALB2, CHEK2, and ATM. The BC incidence was modeled via the explicit effects of truncating variants in BRCA1/2, PALB2, CHEK2, and ATM and other unobserved genetic effects using segregation analysis methods. The predicted average BC risk by age 80 for an ATM mutation carrier is 28%, 30% for CHEK2, 50% for PALB2, and 74% for BRCA1 and BRCA2. However, the BC risks are predicted to increase with FH burden. In families with mutations, predicted risks for mutation-negative members depend on both FH and the specific mutation. The reduction in BC risk after negative predictive testing is greatest when a BRCA1 mutation is identified in the family, but for women whose relatives carry a CHEK2 or ATM mutation, the risks decrease slightly. The model may be a valuable tool for counseling women who have undergone gene panel testing for providing consistent risks and harmonizing their clinical management. A Web application can be used to obtain BC risks in clinical practice (http://ccge.medschl.cam.ac.uk/boadicea/).Genet Med 18 12, 1190-1198.

Using self-report surveys at the beginning of service to develop multi-outcome risk models for new soldiers in the U.S. Army.

PubMed

Rosellini, A J; Stein, M B; Benedek, D M; Bliese, P D; Chiu, W T; Hwang, I; Monahan, J; Nock, M K; Petukhova, M V; Sampson, N A; Street, A E; Zaslavsky, A M; Ursano, R J; Kessler, R C

2017-10-01

The U.S. Army uses universal preventives interventions for several negative outcomes (e.g. suicide, violence, sexual assault) with especially high risks in the early years of service. More intensive interventions exist, but would be cost-effective only if targeted at high-risk soldiers. We report results of efforts to develop models for such targeting from self-report surveys administered at the beginning of Army service. 21 832 new soldiers completed a self-administered questionnaire (SAQ) in 2011-2012 and consented to link administrative data to SAQ responses. Penalized regression models were developed for 12 administratively-recorded outcomes occurring by December 2013: suicide attempt, mental hospitalization, positive drug test, traumatic brain injury (TBI), other severe injury, several types of violence perpetration and victimization, demotion, and attrition. The best-performing models were for TBI (AUC = 0.80), major physical violence perpetration (AUC = 0.78), sexual assault perpetration (AUC = 0.78), and suicide attempt (AUC = 0.74). Although predicted risk scores were significantly correlated across outcomes, prediction was not improved by including risk scores for other outcomes in models. Of particular note: 40.5% of suicide attempts occurred among the 10% of new soldiers with highest predicted risk, 57.2% of male sexual assault perpetrations among the 15% with highest predicted risk, and 35.5% of female sexual assault victimizations among the 10% with highest predicted risk. Data collected at the beginning of service in self-report surveys could be used to develop risk models that define small proportions of new soldiers accounting for high proportions of negative outcomes over the first few years of service.

The potential of large studies for building genetic risk prediction models

Cancer.gov

NCI scientists have developed a new paradigm to assess hereditary risk prediction in common diseases, such as prostate cancer. This genetic risk prediction concept is based on polygenic analysis—the study of a group of common DNA sequences, known as singl

IL-8 predicts pediatric oncology patients with febrile neutropenia at low risk for bacteremia.

PubMed

Cost, Carrye R; Stegner, Martha M; Leonard, David; Leavey, Patrick

2013-04-01

Despite a low bacteremia rate, pediatric oncology patients are frequently admitted for febrile neutropenia. A pediatric risk prediction model with high sensitivity to identify patients at low risk for bacteremia is not available. We performed a single-institution prospective cohort study of pediatric oncology patients with febrile neutropenia to create a risk prediction model using clinical factors, respiratory viral infection, and cytokine expression. Pediatric oncology patients with febrile neutropenia were enrolled between March 30, 2010 and April 1, 2011 and managed per institutional protocol. Blood samples for C-reactive protein and cytokine expression and nasopharyngeal swabs for respiratory viral testing were obtained. Medical records were reviewed for clinical data. Statistical analysis utilized mixed multiple logistic regression modeling. During the 12-month period, 195 febrile neutropenia episodes were enrolled. There were 24 (12%) episodes of bacteremia. Univariate analysis revealed several factors predictive for bacteremia, and interleukin (IL)-8 was the most predictive variable in the multivariate stepwise logistic regression. Low serum IL-8 predicted patients at low risk for bacteremia with a sensitivity of 0.9 and negative predictive value of 0.98. IL-8 is a highly sensitive predictor for patients at low risk for bacteremia. IL-8 should be utilized in a multi-institution prospective trial to assign risk stratification to pediatric patients admitted with febrile neutropenia.

Predicting waist circumference from body mass index.

PubMed

Bozeman, Samuel R; Hoaglin, David C; Burton, Tanya M; Pashos, Chris L; Ben-Joseph, Rami H; Hollenbeak, Christopher S

2012-08-03

Being overweight or obese increases risk for cardiometabolic disorders. Although both body mass index (BMI) and waist circumference (WC) measure the level of overweight and obesity, WC may be more important because of its closer relationship to total body fat. Because WC is typically not assessed in clinical practice, this study sought to develop and verify a model to predict WC from BMI and demographic data, and to use the predicted WC to assess cardiometabolic risk. Data were obtained from the Third National Health and Nutrition Examination Survey (NHANES) and the Atherosclerosis Risk in Communities Study (ARIC). We developed linear regression models for men and women using NHANES data, fitting waist circumference as a function of BMI. For validation, those regressions were applied to ARIC data, assigning a predicted WC to each individual. We used the predicted WC to assess abdominal obesity and cardiometabolic risk. The model correctly classified 88.4% of NHANES subjects with respect to abdominal obesity. Median differences between actual and predicted WC were -0.07 cm for men and 0.11 cm for women. In ARIC, the model closely estimated the observed WC (median difference: -0.34 cm for men, +3.94 cm for women), correctly classifying 86.1% of ARIC subjects with respect to abdominal obesity and 91.5% to 99.5% as to cardiometabolic risk.The model is generalizable to Caucasian and African-American adult populations because it was constructed from data on a large, population-based sample of men and women in the United States, and then validated in a population with a larger representation of African-Americans. The model accurately estimates WC and identifies cardiometabolic risk. It should be useful for health care practitioners and public health officials who wish to identify individuals and populations at risk for cardiometabolic disease when WC data are unavailable.

Predictive Modeling and Concentration of the Risk of Suicide: Implications for Preventive Interventions in the US Department of Veterans Affairs

PubMed Central

McCarthy, John F.; Katz, Ira R.; Thompson, Caitlin; Kemp, Janet; Hannemann, Claire M.; Nielson, Christopher; Schoenbaum, Michael

2015-01-01

Objectives. The Veterans Health Administration (VHA) evaluated the use of predictive modeling to identify patients at risk for suicide and to supplement ongoing care with risk-stratified interventions. Methods. Suicide data came from the National Death Index. Predictors were measures from VHA clinical records incorporating patient-months from October 1, 2008, to September 30, 2011, for all suicide decedents and 1% of living patients, divided randomly into development and validation samples. We used data on all patients alive on September 30, 2010, to evaluate predictions of suicide risk over 1 year. Results. Modeling demonstrated that suicide rates were 82 and 60 times greater than the rate in the overall sample in the highest 0.01% stratum for calculated risk for the development and validation samples, respectively; 39 and 30 times greater in the highest 0.10%; 14 and 12 times greater in the highest 1.00%; and 6.3 and 5.7 times greater in the highest 5.00%. Conclusions. Predictive modeling can identify high-risk patients who were not identified on clinical grounds. VHA is developing modeling to enhance clinical care and to guide the delivery of preventive interventions. PMID:26066914

Predictive Modeling and Concentration of the Risk of Suicide: Implications for Preventive Interventions in the US Department of Veterans Affairs.

PubMed

McCarthy, John F; Bossarte, Robert M; Katz, Ira R; Thompson, Caitlin; Kemp, Janet; Hannemann, Claire M; Nielson, Christopher; Schoenbaum, Michael

2015-09-01

The Veterans Health Administration (VHA) evaluated the use of predictive modeling to identify patients at risk for suicide and to supplement ongoing care with risk-stratified interventions. Suicide data came from the National Death Index. Predictors were measures from VHA clinical records incorporating patient-months from October 1, 2008, to September 30, 2011, for all suicide decedents and 1% of living patients, divided randomly into development and validation samples. We used data on all patients alive on September 30, 2010, to evaluate predictions of suicide risk over 1 year. Modeling demonstrated that suicide rates were 82 and 60 times greater than the rate in the overall sample in the highest 0.01% stratum for calculated risk for the development and validation samples, respectively; 39 and 30 times greater in the highest 0.10%; 14 and 12 times greater in the highest 1.00%; and 6.3 and 5.7 times greater in the highest 5.00%. Predictive modeling can identify high-risk patients who were not identified on clinical grounds. VHA is developing modeling to enhance clinical care and to guide the delivery of preventive interventions.

Prediction of adolescent and adult adiposity outcomes from early life anthropometrics.

PubMed

Graversen, Lise; Sørensen, Thorkild I A; Gerds, Thomas A; Petersen, Liselotte; Sovio, Ulla; Kaakinen, Marika; Sandbaek, Annelli; Laitinen, Jaana; Taanila, Anja; Pouta, Anneli; Järvelin, Marjo-Riitta; Obel, Carsten

2015-01-01

Maternal body mass index (BMI), birth weight, and preschool BMI may help identify children at high risk of overweight as they are (1) similarly linked to adolescent overweight at different stages of the obesity epidemic, (2) linked to adult obesity and metabolic alterations, and (3) easily obtainable in health examinations in young children. The aim was to develop early childhood prediction models of adolescent overweight, adult overweight, and adult obesity. Prediction models at various ages in the Northern Finland Birth Cohort born in 1966 (NFBC1966) were developed. Internal validation was tested using a bootstrap design, and external validation was tested for the model predicting adolescent overweight using the Northern Finland Birth Cohort born in 1986 (NFBC1986). A prediction model developed in the NFBC1966 to predict adolescent overweight, applied to the NFBC1986, and aimed at labelling 10% as "at risk" on the basis of anthropometric information collected until 5 years of age showed that half of those at risk in fact did become overweight. This group constituted one-third of all who became overweight. Our prediction model identified a subgroup of children at very high risk of becoming overweight, which may be valuable in public health settings dealing with obesity prevention. © 2014 The Obesity Society.

Predicting Time to Hospital Discharge for Extremely Preterm Infants

PubMed Central

Hintz, Susan R.; Bann, Carla M.; Ambalavanan, Namasivayam; Cotten, C. Michael; Das, Abhik; Higgins, Rosemary D.

2010-01-01

As extremely preterm infant mortality rates have decreased, concerns regarding resource utilization have intensified. Accurate models to predict time to hospital discharge could aid in resource planning, family counseling, and perhaps stimulate quality improvement initiatives. Objectives For infants <27 weeks estimated gestational age (EGA), to develop, validate and compare several models to predict time to hospital discharge based on time-dependent covariates, and based on the presence of 5 key risk factors as predictors. Patients and Methods This was a retrospective analysis of infants <27 weeks EGA, born 7/2002-12/2005 and surviving to discharge from a NICHD Neonatal Research Network site. Time to discharge was modeled as continuous (postmenstrual age at discharge, PMAD), and categorical variables (“Early” and “Late” discharge). Three linear and logistic regression models with time-dependent covariate inclusion were developed (perinatal factors only, perinatal+early neonatal factors, perinatal+early+later factors). Models for Early and Late discharge using the cumulative presence of 5 key risk factors as predictors were also evaluated. Predictive capabilities were compared using coefficient of determination (R2) for linear models, and AUC of ROC curve for logistic models. Results Data from 2254 infants were included. Prediction of PMAD was poor, with only 38% of variation explained by linear models. However, models incorporating later clinical characteristics were more accurate in predicting “Early” or “Late” discharge (full models: AUC 0.76-0.83 vs. perinatal factor models: AUC 0.56-0.69). In simplified key risk factors models, predicted probabilities for Early and Late discharge compared favorably with observed rates. Furthermore, the AUC (0.75-0.77) were similar to those of models including the full factor set. Conclusions Prediction of Early or Late discharge is poor if only perinatal factors are considered, but improves substantially with knowledge of later-occurring morbidities. Prediction using a few key risk factors is comparable to full models, and may offer a clinically applicable strategy. PMID:20008430

EVALUATING RISK-PREDICTION MODELS USING DATA FROM ELECTRONIC HEALTH RECORDS.

PubMed

Wang, L E; Shaw, Pamela A; Mathelier, Hansie M; Kimmel, Stephen E; French, Benjamin

2016-03-01

The availability of data from electronic health records facilitates the development and evaluation of risk-prediction models, but estimation of prediction accuracy could be limited by outcome misclassification, which can arise if events are not captured. We evaluate the robustness of prediction accuracy summaries, obtained from receiver operating characteristic curves and risk-reclassification methods, if events are not captured (i.e., "false negatives"). We derive estimators for sensitivity and specificity if misclassification is independent of marker values. In simulation studies, we quantify the potential for bias in prediction accuracy summaries if misclassification depends on marker values. We compare the accuracy of alternative prognostic models for 30-day all-cause hospital readmission among 4548 patients discharged from the University of Pennsylvania Health System with a primary diagnosis of heart failure. Simulation studies indicate that if misclassification depends on marker values, then the estimated accuracy improvement is also biased, but the direction of the bias depends on the direction of the association between markers and the probability of misclassification. In our application, 29% of the 1143 readmitted patients were readmitted to a hospital elsewhere in Pennsylvania, which reduced prediction accuracy. Outcome misclassification can result in erroneous conclusions regarding the accuracy of risk-prediction models.

A Novel Early Pregnancy Risk Prediction Model for Gestational Diabetes Mellitus.

PubMed

Sweeting, Arianne N; Wong, Jencia; Appelblom, Heidi; Ross, Glynis P; Kouru, Heikki; Williams, Paul F; Sairanen, Mikko; Hyett, Jon A

2018-06-13

Accurate early risk prediction for gestational diabetes mellitus (GDM) would target intervention and prevention in women at the highest risk. We evaluated novel biomarker predictors to develop a first-trimester risk prediction model in a large multiethnic cohort. Maternal clinical, aneuploidy and pre-eclampsia screening markers (PAPP-A, free hCGβ, mean arterial pressure, uterine artery pulsatility index) were measured prospectively at 11-13+6 weeks' gestation in 980 women (248 with GDM; 732 controls). Nonfasting glucose, lipids, adiponectin, leptin, lipocalin-2, and plasminogen activator inhibitor-2 were measured on banked serum. The relationship between marker multiples-of-the-median and GDM was examined with multivariate regression. Model predictive performance for early (< 24 weeks' gestation) and overall GDM diagnosis was evaluated by receiver operating characteristic curves. Glucose, triglycerides, leptin, and lipocalin-2 were higher, while adiponectin was lower, in GDM (p < 0.05). Lipocalin-2 performed best in Caucasians, and triglycerides in South Asians with GDM. Family history of diabetes, previous GDM, South/East Asian ethnicity, parity, BMI, PAPP-A, triglycerides, and lipocalin-2 were significant independent GDM predictors (all p < 0.01), achieving an area under the curve of 0.91 (95% confidence interval [CI] 0.89-0.94) overall, and 0.93 (95% CI 0.89-0.96) for early GDM, in a combined multivariate prediction model. A first-trimester risk prediction model, which incorporates novel maternal lipid markers, accurately identifies women at high risk of GDM, including early GDM. © 2018 S. Karger AG, Basel.

Child-related cognitions and affective functioning of physically abusive and comparison parents.

PubMed

Haskett, Mary E; Smith Scott, Susan; Grant, Raven; Ward, Caryn Sabourin; Robinson, Canby

2003-06-01

The goal of this research was to utilize the cognitive behavioral model of abusive parenting to select and examine risk factors to illuminate the unique and combined influences of social cognitive and affective variables in predicting abuse group membership. Participants included physically abusive parents (n=56) and a closely-matched group of comparison parents (n=62). Social cognitive risk variables measured were (a) parent's expectations for children's abilities and maturity, (b) parental attributions of intentionality of child misbehavior, and (c) parents' perceptions of their children's adjustment. Affective risk variables included (a) psychopathology and (b) parenting stress. A series of logistic regression models were constructed to test the individual, combined, and interactive effects of risk variables on abuse group membership. The full set of five risk variables was predictive of abuse status; however, not all variables were predictive when considered individually and interactions did not contribute significantly to prediction. A risk composite score computed for each parent based on the five risk variables significantly predicted abuse status. Wide individual differences in risk across the five variables were apparent within the sample of abusive parents. Findings were generally consistent with a cognitive behavioral model of abuse, with cognitive variables being more salient in predicting abuse status than affective factors. Results point to the importance of considering diversity in characteristics of abusive parents.

Comparison of Different Risk Perception Measures in Predicting Seasonal Influenza Vaccination among Healthy Chinese Adults in Hong Kong: A Prospective Longitudinal Study

PubMed Central

Liao, Qiuyan; Wong, Wing Sze; Fielding, Richard

2013-01-01

Background Risk perception is a reported predictor of vaccination uptake, but which measures of risk perception best predict influenza vaccination uptake remain unclear. Methodology During the main influenza seasons (between January and March) of 2009 (Wave 1) and 2010 (Wave 2),505 Chinese students and employees from a Hong Kong university completed an online survey. Multivariate logistic regression models were conducted to assess how well different risk perceptions measures in Wave 1 predicted vaccination uptake against seasonal influenza in Wave 2. Principal Findings The results of the multivariate logistic regression models showed that feeling at risk (β = 0.25, p = 0.021) was the better predictor compared with probability judgment while probability judgment (β = 0.25, p = 0.029 ) was better than beliefs about risk in predicting subsequent influenza vaccination uptake. Beliefs about risk and feeling at risk seemed to predict the same aspect of subsequent vaccination uptake because their associations with vaccination uptake became insignificant when paired into the logistic regression model. Similarly, to compare the four scales for assessing probability judgment in predicting vaccination uptake, the 7-point verbal scale remained a significant and stronger predictor for vaccination uptake when paired with other three scales; the 6-point verbal scale was a significant and stronger predictor when paired with the percentage scale or the 2-point verbal scale; and the percentage scale was a significant and stronger predictor only when paired with the 2-point verbal scale. Conclusions/Significance Beliefs about risk and feeling at risk are not well differentiated by Hong Kong Chinese people. Feeling at risk, an affective-cognitive dimension of risk perception predicts subsequent vaccination uptake better than do probability judgments. Among the four scales for assessing risk probability judgment, the 7-point verbal scale offered the best predictive power for subsequent vaccination uptake. PMID:23894292

Comparison of different risk perception measures in predicting seasonal influenza vaccination among healthy Chinese adults in Hong Kong: a prospective longitudinal study.

PubMed

Liao, Qiuyan; Wong, Wing Sze; Fielding, Richard

2013-01-01

Risk perception is a reported predictor of vaccination uptake, but which measures of risk perception best predict influenza vaccination uptake remain unclear. During the main influenza seasons (between January and March) of 2009 (Wave 1) and 2010 (Wave 2),505 Chinese students and employees from a Hong Kong university completed an online survey. Multivariate logistic regression models were conducted to assess how well different risk perceptions measures in Wave 1 predicted vaccination uptake against seasonal influenza in Wave 2. The results of the multivariate logistic regression models showed that feeling at risk (β = 0.25, p = 0.021) was the better predictor compared with probability judgment while probability judgment (β = 0.25, p = 0.029 ) was better than beliefs about risk in predicting subsequent influenza vaccination uptake. Beliefs about risk and feeling at risk seemed to predict the same aspect of subsequent vaccination uptake because their associations with vaccination uptake became insignificant when paired into the logistic regression model. Similarly, to compare the four scales for assessing probability judgment in predicting vaccination uptake, the 7-point verbal scale remained a significant and stronger predictor for vaccination uptake when paired with other three scales; the 6-point verbal scale was a significant and stronger predictor when paired with the percentage scale or the 2-point verbal scale; and the percentage scale was a significant and stronger predictor only when paired with the 2-point verbal scale. Beliefs about risk and feeling at risk are not well differentiated by Hong Kong Chinese people. Feeling at risk, an affective-cognitive dimension of risk perception predicts subsequent vaccination uptake better than do probability judgments. Among the four scales for assessing risk probability judgment, the 7-point verbal scale offered the best predictive power for subsequent vaccination uptake.

Geo-environmental model for the prediction of potential transmission risk of Dirofilaria in an area with dry climate and extensive irrigated crops. The case of Spain.

PubMed

Simón, Luis; Afonin, Alexandr; López-Díez, Lucía Isabel; González-Miguel, Javier; Morchón, Rodrigo; Carretón, Elena; Montoya-Alonso, José Alberto; Kartashev, Vladimir; Simón, Fernando

2014-03-01

Zoonotic filarioses caused by Dirofilaria immitis and Dirofilaria repens are transmitted by culicid mosquitoes. Therefore Dirofilaria transmission depends on climatic factors like temperature and humidity. In spite of the dry climate of most of the Spanish territory, there are extensive irrigated crops areas providing moist habitats favourable for mosquito breeding. A GIS model to predict the risk of Dirofilaria transmission in Spain, based on temperatures and rainfall data as well as in the distribution of irrigated crops areas, is constructed. The model predicts that potential risk of Dirofilaria transmission exists in all the Spanish territory. Highest transmission risk exists in several areas of Andalucía, Extremadura, Castilla-La Mancha, Murcia, Valencia, Aragón and Cataluña, where moderate/high temperatures coincide with extensive irrigated crops. High risk in Balearic Islands and in some points of Canary Islands, is also predicted. The lowest risk is predicted in Northern cold and scarcely or non-irrigated dry Southeastern areas. The existence of irrigations locally increases transmission risk in low rainfall areas of the Spanish territory. The model can contribute to implement rational preventive therapy guidelines in accordance with the transmission characteristics of each local area. Moreover, the use of humidity-related factors could be of interest in future predictions to be performed in countries with similar environmental characteristics. Copyright © 2014 Elsevier B.V. All rights reserved.

Can theory predict the process of suicide on entry to prison? Predicting dynamic risk factors for suicide ideation in a high-risk prison population.

PubMed

Slade, Karen; Edelman, Robert

2014-01-01

Each year approximately 110,000 people are imprisoned in England and Wales and new prisoners remain one of the highest risk groups for suicide across the world. The reduction of suicide in prisoners remains difficult as assessments and interventions tend to rely on static risk factors with few theoretical or integrated models yet evaluated. To identify the dynamic factors that contribute to suicide ideation in this population based on Williams and Pollock's (2001) Cry of Pain (CoP) model. New arrivals (N = 198) into prison were asked to complete measures derived from the CoP model plus clinical and prison-specific factors. It was hypothesized that the factors of the CoP model would be predictive of suicide ideation. Support was provided for the defeat and entrapment aspects of the CoP model with previous self-harm, repeated times in prison, and suicide-permissive cognitions also key in predicting suicide ideation for prisoners on entry to prison. An integrated and dynamic model was developed that has utility in predicting suicide in early-stage prisoners. Implications for both theory and practice are discussed along with recommendations for future research.

A risk prediction model for severe intraventricular hemorrhage in very low birth weight infants and the effect of prophylactic indomethacin.

PubMed

Luque, M J; Tapia, J L; Villarroel, L; Marshall, G; Musante, G; Carlo, W; Kattan, J

2014-01-01

Develop a risk prediction model for severe intraventricular hemorrhage (IVH) in very low birth weight infants (VLBWI). Prospectively collected data of infants with birth weight 500 to 1249 g born between 2001 and 2010 in centers from the Neocosur Network were used. Forward stepwise logistic regression model was employed. The model was tested in the 2011 cohort and then applied to the population of VLBWI that received prophylactic indomethacin to analyze its effect in the risk of severe IVH. Data from 6538 VLBWI were analyzed. The area under ROC curve for the model was 0.79 and 0.76 when tested in the 2011 cohort. The prophylactic indomethacin group had lower incidence of severe IVH, especially in the highest-risk groups. A model for early severe IVH prediction was developed and tested in our population. Prophylactic indomethacin was associated with a lower risk-adjusted incidence of severe IVH.

The proposed 'concordance-statistic for benefit' provided a useful metric when modeling heterogeneous treatment effects.

PubMed

van Klaveren, David; Steyerberg, Ewout W; Serruys, Patrick W; Kent, David M

2018-02-01

Clinical prediction models that support treatment decisions are usually evaluated for their ability to predict the risk of an outcome rather than treatment benefit-the difference between outcome risk with vs. without therapy. We aimed to define performance metrics for a model's ability to predict treatment benefit. We analyzed data of the Synergy between Percutaneous Coronary Intervention with Taxus and Cardiac Surgery (SYNTAX) trial and of three recombinant tissue plasminogen activator trials. We assessed alternative prediction models with a conventional risk concordance-statistic (c-statistic) and a novel c-statistic for benefit. We defined observed treatment benefit by the outcomes in pairs of patients matched on predicted benefit but discordant for treatment assignment. The 'c-for-benefit' represents the probability that from two randomly chosen matched patient pairs with unequal observed benefit, the pair with greater observed benefit also has a higher predicted benefit. Compared to a model without treatment interactions, the SYNTAX score II had improved ability to discriminate treatment benefit (c-for-benefit 0.590 vs. 0.552), despite having similar risk discrimination (c-statistic 0.725 vs. 0.719). However, for the simplified stroke-thrombolytic predictive instrument (TPI) vs. the original stroke-TPI, the c-for-benefit (0.584 vs. 0.578) was similar. The proposed methodology has the potential to measure a model's ability to predict treatment benefit not captured with conventional performance metrics. Copyright © 2017 Elsevier Inc. All rights reserved.

Development of a risk assessment tool for projecting individualized probabilities of developing breast cancer for Chinese women.

PubMed

Wang, Yuan; Gao, Ying; Battsend, Munkhzul; Chen, Kexin; Lu, Wenli; Wang, Yaogang

2014-11-01

The optimal approach regarding breast cancer screening for Chinese women is unclear due to the relative low incidence rate. A risk assessment tool may be useful for selection of high-risk subsets of population for mammography screening in low-incidence and resource-limited developing country. The odd ratios for six main risk factors of breast cancer were pooled by review manager after a systematic research of literature. Health risk appraisal (HRA) model was developed to predict an individual's risk of developing breast cancer in the next 5 years from current age. The performance of this HRA model was assessed based on a first-round screening database. Estimated risk of breast cancer increased with age. Increases in the 5-year risk of developing breast cancer were found with the existence of any of included risk factors. When individuals who had risk above median risk (3.3‰) were selected from the validation database, the sensitivity is 60.0% and the specificity is 47.8%. The unweighted area under the curve (AUC) was 0.64 (95% CI = 0.50-0.78). The risk-prediction model reported in this article is based on a combination of risk factors and shows good overall predictive power, but it is still weak at predicting which particular women will develop the disease. It would be very helpful for the improvement of a current model if more population-based prospective follow-up studies were used for the validation.

Cross-national validation of prognostic models predicting sickness absence and the added value of work environment variables.

PubMed

Roelen, Corné A M; Stapelfeldt, Christina M; Heymans, Martijn W; van Rhenen, Willem; Labriola, Merete; Nielsen, Claus V; Bültmann, Ute; Jensen, Chris

2015-06-01

To validate Dutch prognostic models including age, self-rated health and prior sickness absence (SA) for ability to predict high SA in Danish eldercare. The added value of work environment variables to the models' risk discrimination was also investigated. 2,562 municipal eldercare workers (95% women) participated in the Working in Eldercare Survey. Predictor variables were measured by questionnaire at baseline in 2005. Prognostic models were validated for predictions of high (≥30) SA days and high (≥3) SA episodes retrieved from employer records during 1-year follow-up. The accuracy of predictions was assessed by calibration graphs and the ability of the models to discriminate between high- and low-risk workers was investigated by ROC-analysis. The added value of work environment variables was measured with Integrated Discrimination Improvement (IDI). 1,930 workers had complete data for analysis. The models underestimated the risk of high SA in eldercare workers and the SA episodes model had to be re-calibrated to the Danish data. Discrimination was practically useful for the re-calibrated SA episodes model, but not the SA days model. Physical workload improved the SA days model (IDI = 0.40; 95% CI 0.19-0.60) and psychosocial work factors, particularly the quality of leadership (IDI = 0.70; 95% CI 053-0.86) improved the SA episodes model. The prognostic model predicting high SA days showed poor performance even after physical workload was added. The prognostic model predicting high SA episodes could be used to identify high-risk workers, especially when psychosocial work factors are added as predictor variables.

Measures of Residual Risk with Connections to Regression, Risk Tracking, Surrogate Models, and Ambiguity

DTIC Science & Technology

2015-04-15

manage , predict, and mitigate the risk in the original variable. Residual risk can be exemplified as a quantification of the improved... the random variable of interest is viewed in concert with a related random vector that helps to manage , predict, and mitigate the risk in the original... manage , predict and mitigate the risk in the original variable. Residual risk can be exemplified as a quantification of the improved situation faced

A multiple biomarker risk score for guiding clinical decisions using a decision curve approach.

PubMed

Hughes, Maria F; Saarela, Olli; Blankenberg, Stefan; Zeller, Tanja; Havulinna, Aki S; Kuulasmaa, Kari; Yarnell, John; Schnabel, Renate B; Tiret, Laurence; Salomaa, Veikko; Evans, Alun; Kee, Frank

2012-08-01

We assessed whether a cardiovascular risk model based on classic risk factors (e.g. cholesterol, blood pressure) could refine disease prediction if it included novel biomarkers (C-reactive protein, N-terminal pro-B-type natriuretic peptide, troponin I) using a decision curve approach which can incorporate clinical consequences. We evaluated whether a model including biomarkers and classic risk factors could improve prediction of 10 year risk of cardiovascular disease (CVD; chronic heart disease and ischaemic stroke) against a classic risk factor model using a decision curve approach in two prospective MORGAM cohorts. This included 7739 men and women with 457 CVD cases from the FINRISK97 cohort; and 2524 men with 259 CVD cases from PRIME Belfast. The biomarker model improved disease prediction in FINRISK across the high-risk group (20-40%) but not in the intermediate risk group, at the 23% risk threshold net benefit was 0.0033 (95% CI 0.0013-0.0052). However, in PRIME Belfast the net benefit of decisions guided by the decision curve was improved across intermediate risk thresholds (10-20%). At p(t) = 10% in PRIME, the net benefit was 0.0059 (95% CI 0.0007-0.0112) with a net increase in 6 true positive cases per 1000 people screened and net decrease of 53 false positive cases per 1000 potentially leading to 5% fewer treatments in patients not destined for an event. The biomarker model improves 10-year CVD prediction at intermediate and high-risk thresholds and in particular, could be clinically useful at advising middle-aged European males of their CVD risk.

The development and testing of a skin tear risk assessment tool.

PubMed

Newall, Nelly; Lewin, Gill F; Bulsara, Max K; Carville, Keryln J; Leslie, Gavin D; Roberts, Pam A

2017-02-01

The aim of the present study is to develop a reliable and valid skin tear risk assessment tool. The six characteristics identified in a previous case control study as constituting the best risk model for skin tear development were used to construct a risk assessment tool. The ability of the tool to predict skin tear development was then tested in a prospective study. Between August 2012 and September 2013, 1466 tertiary hospital patients were assessed at admission and followed up for 10 days to see if they developed a skin tear. The predictive validity of the tool was assessed using receiver operating characteristic (ROC) analysis. When the tool was found not to have performed as well as hoped, secondary analyses were performed to determine whether a potentially better performing risk model could be identified. The tool was found to have high sensitivity but low specificity and therefore have inadequate predictive validity. Secondary analysis of the combined data from this and the previous case control study identified an alternative better performing risk model. The tool developed and tested in this study was found to have inadequate predictive validity. The predictive validity of an alternative, more parsimonious model now needs to be tested. © 2015 Medicalhelplines.com Inc and John Wiley & Sons Ltd.

A risk prediction score model for predicting occurrence of post-PCI vasovagal reflex syndrome: a single center study in Chinese population.

PubMed

Li, Hai-Yan; Guo, Yu-Tao; Tian, Cui; Song, Chao-Qun; Mu, Yang; Li, Yang; Chen, Yun-Dai

2017-08-01

The vasovagal reflex syndrome (VVRS) is common in the patients undergoing percutaneous coronary intervention (PCI). However, prediction and prevention of the risk for the VVRS have not been completely fulfilled. This study was conducted to develop a Risk Prediction Score Model to identify the determinants of VVRS in a large Chinese population cohort receiving PCI. From the hospital electronic medical database, we identified 3550 patients who received PCI (78.0% males, mean age 60 years) in Chinese PLA General Hospital from January 1, 2000 to August 30, 2016. The multivariate analysis and receiver operating characteristic (ROC) analysis were performed. The adverse events of VVRS in the patients were significantly increased after PCI procedure than before the operation (all P < 0.001). The rate of VVRS [95% confidence interval (CI)] in patients receiving PCI was 4.5% (4.1%-5.6%). Compared to the patients suffering no VVRS, incidence of VVRS involved the following factors, namely female gender, primary PCI, hypertension, over two stents implantation in the left anterior descending (LAD), and the femoral puncture site. The multivariate analysis suggested that they were independent risk factors for predicting the incidence of VVRS (all P < 0.001). We developed a risk prediction score model for VVRS. ROC analysis showed that the risk prediction score model was effectively predictive of the incidence of VVRS in patients receiving PCI (c-statistic 0.76, 95% CI: 0.72-0.79, P < 0.001). There were decreased events of VVRS in the patients receiving PCI whose diastolic blood pressure dropped by more than 30 mmHg and heart rate reduced by 10 times per minute (AUC: 0.84, 95% CI: 0.81-0.87, P < 0.001). The risk prediction score is quite efficient in predicting the incidence of VVRS in patients receiving PCI. In which, the following factors may be involved, the femoral puncture site, female gender, hypertension, primary PCI, and over 2 stents implanted in LAD.

Long-Term Survival Prediction for Coronary Artery Bypass Grafting: Validation of the ASCERT Model Compared With The Society of Thoracic Surgeons Predicted Risk of Mortality.

PubMed

Lancaster, Timothy S; Schill, Matthew R; Greenberg, Jason W; Ruaengsri, Chawannuch; Schuessler, Richard B; Lawton, Jennifer S; Maniar, Hersh S; Pasque, Michael K; Moon, Marc R; Damiano, Ralph J; Melby, Spencer J

2018-05-01

The recently developed American College of Cardiology Foundation-Society of Thoracic Surgeons (STS) Collaboration on the Comparative Effectiveness of Revascularization Strategy (ASCERT) Long-Term Survival Probability Calculator is a valuable addition to existing short-term risk-prediction tools for cardiac surgical procedures but has yet to be externally validated. Institutional data of 654 patients aged 65 years or older undergoing isolated coronary artery bypass grafting between 2005 and 2010 were reviewed. Predicted survival probabilities were calculated using the ASCERT model. Survival data were collected using the Social Security Death Index and institutional medical records. Model calibration and discrimination were assessed for the overall sample and for risk-stratified subgroups based on (1) ASCERT 7-year survival probability and (2) the predicted risk of mortality (PROM) from the STS Short-Term Risk Calculator. Logistic regression analysis was performed to evaluate additional perioperative variables contributing to death. Overall survival was 92.1% (569 of 597) at 1 year and 50.5% (164 of 325) at 7 years. Calibration assessment found no significant differences between predicted and actual survival curves for the overall sample or for the risk-stratified subgroups, whether stratified by predicted 7-year survival or by PROM. Discriminative performance was comparable between the ASCERT and PROM models for 7-year survival prediction (p < 0.001 for both; C-statistic = 0.815 for ASCERT and 0.781 for PROM). Prolonged ventilation, stroke, and hospital length of stay were also predictive of long-term death. The ASCERT survival probability calculator was externally validated for prediction of long-term survival after coronary artery bypass grafting in all risk groups. The widely used STS PROM performed comparably as a predictor of long-term survival. Both tools provide important information for preoperative decision making and patient counseling about potential outcomes after coronary artery bypass grafting. Copyright © 2018 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved.

Risk Prediction Models for Acute Kidney Injury in Critically Ill Patients: Opus in Progressu.

PubMed

Neyra, Javier A; Leaf, David E

2018-05-31

Acute kidney injury (AKI) is a complex systemic syndrome associated with high morbidity and mortality. Among critically ill patients admitted to intensive care units (ICUs), the incidence of AKI is as high as 50% and is associated with dismal outcomes. Thus, the development and validation of clinical risk prediction tools that accurately identify patients at high risk for AKI in the ICU is of paramount importance. We provide a comprehensive review of 3 clinical risk prediction tools that have been developed for incident AKI occurring in the first few hours or days following admission to the ICU. We found substantial heterogeneity among the clinical variables that were examined and included as significant predictors of AKI in the final models. The area under the receiver operating characteristic curves was ∼0.8 for all 3 models, indicating satisfactory model performance, though positive predictive values ranged from only 23 to 38%. Hence, further research is needed to develop more accurate and reproducible clinical risk prediction tools. Strategies for improved assessment of AKI susceptibility in the ICU include the incorporation of dynamic (time-varying) clinical parameters, as well as biomarker, functional, imaging, and genomic data. © 2018 S. Karger AG, Basel.

Developing risk prediction models for kidney injury and assessing incremental value for novel biomarkers.

PubMed

Kerr, Kathleen F; Meisner, Allison; Thiessen-Philbrook, Heather; Coca, Steven G; Parikh, Chirag R

2014-08-07

The field of nephrology is actively involved in developing biomarkers and improving models for predicting patients' risks of AKI and CKD and their outcomes. However, some important aspects of evaluating biomarkers and risk models are not widely appreciated, and statistical methods are still evolving. This review describes some of the most important statistical concepts for this area of research and identifies common pitfalls. Particular attention is paid to metrics proposed within the last 5 years for quantifying the incremental predictive value of a new biomarker. Copyright © 2014 by the American Society of Nephrology.

Stata Modules for Calculating Novel Predictive Performance Indices for Logistic Models.

PubMed

Barkhordari, Mahnaz; Padyab, Mojgan; Hadaegh, Farzad; Azizi, Fereidoun; Bozorgmanesh, Mohammadreza

2016-01-01

Prediction is a fundamental part of prevention of cardiovascular diseases (CVD). The development of prediction algorithms based on the multivariate regression models loomed several decades ago. Parallel with predictive models development, biomarker researches emerged in an impressively great scale. The key question is how best to assess and quantify the improvement in risk prediction offered by new biomarkers or more basically how to assess the performance of a risk prediction model. Discrimination, calibration, and added predictive value have been recently suggested to be used while comparing the predictive performances of the predictive models' with and without novel biomarkers. Lack of user-friendly statistical software has restricted implementation of novel model assessment methods while examining novel biomarkers. We intended, thus, to develop a user-friendly software that could be used by researchers with few programming skills. We have written a Stata command that is intended to help researchers obtain cut point-free and cut point-based net reclassification improvement index and (NRI) and relative and absolute Integrated discriminatory improvement index (IDI) for logistic-based regression analyses.We applied the commands to a real data on women participating the Tehran lipid and glucose study (TLGS) to examine if information of a family history of premature CVD, waist circumference, and fasting plasma glucose can improve predictive performance of the Framingham's "general CVD risk" algorithm. The command is addpred for logistic regression models. The Stata package provided herein can encourage the use of novel methods in examining predictive capacity of ever-emerging plethora of novel biomarkers.

The Lack of Utility of Circulating Biomarkers of Inflammation and Endothelial Dysfunction for Type 2 Diabetes Risk Prediction Among Postmenopausal Women

PubMed Central

Chao, Chun; Song, Yiqing; Cook, Nancy; Tseng, Chi-Hong; Manson, JoAnn E.; Eaton, Charles; Margolis, Karen L.; Rodriguez, Beatriz; Phillips, Lawrence S.; Tinker, Lesley F.; Liu, Simin

2011-01-01

Background Recent studies have linked plasma markers of inflammation and endothelial dysfunction to type 2 diabetes mellitus (DM) development. However, the utility of these novel biomarkers for type 2 DM risk prediction remains uncertain. Methods The Women’s Health Initiative Observational Study (WHIOS), a prospective cohort, and a nested case-control study within the WHIOS of 1584 incident type 2 DM cases and 2198 matched controls were used to evaluate the utility of plasma markers of inflammation and endothelial dysfunction for type 2 DM risk prediction. Between September 1994 and December 1998, 93 676 women aged 50 to 79 years were enrolled in the WHIOS. Fasting plasma levels of glucose, insulin, white blood cells, tumor necrosis factor receptor 2, interleukin 6, high-sensitivity C-reactive protein, E-selectin, soluble intercellular adhesion molecule 1, and vascular cell adhesion molecule 1 were measured using blood samples collected at baseline. A series of prediction models including traditional risk factors and novel plasma markers were evaluated on the basis of global model fit, model discrimination, net reclassification improvement, and positive and negative predictive values. Results Although white blood cell count and levels of interleukin 6, high-sensitivity C-reactive protein, and soluble intercellular adhesion molecule 1 significantly enhanced model fit, none of the inflammatory and endothelial dysfunction markers improved the ability of model discrimination (area under the receiver operating characteristic curve, 0.93 vs 0.93), net reclassification, or predictive values (positive, 0.22 vs 0.24; negative, 0.99 vs 0.99 [using 15% 6-year type 2 DM risk as the cutoff]) compared with traditional risk factors. Similar results were obtained in ethnic-specific analyses. Conclusion Beyond traditional risk factors, measurement of plasma markers of systemic inflammation and endothelial dysfunction contribute relatively little additional value in clinical type 2 DM risk prediction in a multiethnic cohort of postmenopausal women. PMID:20876407

Can We Predict Individual Combined Benefit and Harm of Therapy? Warfarin Therapy for Atrial Fibrillation as a Test Case

PubMed Central

Li, Guowei; Thabane, Lehana; Delate, Thomas; Witt, Daniel M.; Levine, Mitchell A. H.; Cheng, Ji; Holbrook, Anne

2016-01-01

Objectives To construct and validate a prediction model for individual combined benefit and harm outcomes (stroke with no major bleeding, major bleeding with no stroke, neither event, or both) in patients with atrial fibrillation (AF) with and without warfarin therapy. Methods Using the Kaiser Permanente Colorado databases, we included patients newly diagnosed with AF between January 1, 2005 and December 31, 2012 for model construction and validation. The primary outcome was a prediction model of composite of stroke or major bleeding using polytomous logistic regression (PLR) modelling. The secondary outcome was a prediction model of all-cause mortality using the Cox regression modelling. Results We included 9074 patients with 4537 and 4537 warfarin users and non-users, respectively. In the derivation cohort (n = 4632), there were 136 strokes (2.94%), 280 major bleedings (6.04%) and 1194 deaths (25.78%) occurred. In the prediction models, warfarin use was not significantly associated with risk of stroke, but increased the risk of major bleeding and decreased the risk of death. Both the PLR and Cox models were robust, internally and externally validated, and with acceptable model performances. Conclusions In this study, we introduce a new methodology for predicting individual combined benefit and harm outcomes associated with warfarin therapy for patients with AF. Should this approach be validated in other patient populations, it has potential advantages over existing risk stratification approaches as a patient-physician aid for shared decision-making PMID:27513986

Coupling of Bayesian Networks with GIS for wildfire risk assessment on natural and agricultural areas of the Mediterranean

NASA Astrophysics Data System (ADS)

Scherb, Anke; Papakosta, Panagiota; Straub, Daniel

2014-05-01

Wildfires cause severe damages to ecosystems, socio-economic assets, and human lives in the Mediterranean. To facilitate coping with wildfire risks, an understanding of the factors influencing wildfire occurrence and behavior (e.g. human activity, weather conditions, topography, fuel loads) and their interaction is of importance, as is the implementation of this knowledge in improved wildfire hazard and risk prediction systems. In this project, a probabilistic wildfire risk prediction model is developed, with integrated fire occurrence and fire propagation probability and potential impact prediction on natural and cultivated areas. Bayesian Networks (BNs) are used to facilitate the probabilistic modeling. The final BN model is a spatial-temporal prediction system at the meso scale (1 km2 spatial and 1 day temporal resolution). The modeled consequences account for potential restoration costs and production losses referred to forests, agriculture, and (semi-) natural areas. BNs and a geographic information system (GIS) are coupled within this project to support a semi-automated BN model parameter learning and the spatial-temporal risk prediction. The coupling also enables the visualization of prediction results by means of daily maps. The BN parameters are learnt for Cyprus with data from 2006-2009. Data from 2010 is used as validation data set. A special focus is put on the performance evaluation of the BN for fire occurrence, which is modeled as binary classifier and thus, could be validated by means of Receiver Operator Characteristic (ROC) curves. With the final best models, AUC values of more than 70% for validation could be achieved, which indicates potential for reliable prediction performance via BN. Maps of selected days in 2010 are shown to illustrate final prediction results. The resulting system can be easily expanded to predict additional expected damages in the mesoscale (e.g. building and infrastructure damages). The system can support planning of preventive measures (e.g. state resources allocation for wildfire prevention and preparedness) and assist recuperation plans of damaged areas.

Temporal and geographical external validation study and extension of the Mayo Clinic prediction model to predict eGFR in the younger population of Swiss ADPKD patients.

PubMed

Girardat-Rotar, Laura; Braun, Julia; Puhan, Milo A; Abraham, Alison G; Serra, Andreas L

2017-07-17

Prediction models in autosomal dominant polycystic kidney disease (ADPKD) are useful in clinical settings to identify patients with greater risk of a rapid disease progression in whom a treatment may have more benefits than harms. Mayo Clinic investigators developed a risk prediction tool for ADPKD patients using a single kidney value. Our aim was to perform an independent geographical and temporal external validation as well as evaluate the potential for improving the predictive performance by including additional information on total kidney volume. We used data from the on-going Swiss ADPKD study from 2006 to 2016. The main analysis included a sample size of 214 patients with Typical ADPKD (Class 1). We evaluated the Mayo Clinic model performance calibration and discrimination in our external sample and assessed whether predictive performance could be improved through the addition of subsequent kidney volume measurements beyond the baseline assessment. The calibration of both versions of the Mayo Clinic prediction model using continuous Height adjusted total kidney volume (HtTKV) and using risk subclasses was good, with R 2 of 78% and 70%, respectively. Accuracy was also good with 91.5% and 88.7% of the predicted within 30% of the observed, respectively. Additional information regarding kidney volume did not substantially improve the model performance. The Mayo Clinic prediction models are generalizable to other clinical settings and provide an accurate tool based on available predictors to identify patients at high risk for rapid disease progression.

Predicting survival across chronic interstitial lung disease: the ILD-GAP model.

PubMed

Ryerson, Christopher J; Vittinghoff, Eric; Ley, Brett; Lee, Joyce S; Mooney, Joshua J; Jones, Kirk D; Elicker, Brett M; Wolters, Paul J; Koth, Laura L; King, Talmadge E; Collard, Harold R

2014-04-01

Risk prediction is challenging in chronic interstitial lung disease (ILD) because of heterogeneity in disease-specific and patient-specific variables. Our objective was to determine whether mortality is accurately predicted in patients with chronic ILD using the GAP model, a clinical prediction model based on sex, age, and lung physiology, that was previously validated in patients with idiopathic pulmonary fibrosis. Patients with idiopathic pulmonary fibrosis (n=307), chronic hypersensitivity pneumonitis (n=206), connective tissue disease-associated ILD (n=281), idiopathic nonspecific interstitial pneumonia (n=45), or unclassifiable ILD (n=173) were selected from an ongoing database (N=1,012). Performance of the previously validated GAP model was compared with novel prediction models in each ILD subtype and the combined cohort. Patients with follow-up pulmonary function data were used for longitudinal model validation. The GAP model had good performance in all ILD subtypes (c-index, 74.6 in the combined cohort), which was maintained at all stages of disease severity and during follow-up evaluation. The GAP model had similar performance compared with alternative prediction models. A modified ILD-GAP Index was developed for application across all ILD subtypes to provide disease-specific survival estimates using a single risk prediction model. This was done by adding a disease subtype variable that accounted for better adjusted survival in connective tissue disease-associated ILD, chronic hypersensitivity pneumonitis, and idiopathic nonspecific interstitial pneumonia. The GAP model accurately predicts risk of death in chronic ILD. The ILD-GAP model accurately predicts mortality in major chronic ILD subtypes and at all stages of disease.

Quantifying and comparing dynamic predictive accuracy of joint models for longitudinal marker and time-to-event in presence of censoring and competing risks.

PubMed

Blanche, Paul; Proust-Lima, Cécile; Loubère, Lucie; Berr, Claudine; Dartigues, Jean-François; Jacqmin-Gadda, Hélène

2015-03-01

Thanks to the growing interest in personalized medicine, joint modeling of longitudinal marker and time-to-event data has recently started to be used to derive dynamic individual risk predictions. Individual predictions are called dynamic because they are updated when information on the subject's health profile grows with time. We focus in this work on statistical methods for quantifying and comparing dynamic predictive accuracy of this kind of prognostic models, accounting for right censoring and possibly competing events. Dynamic area under the ROC curve (AUC) and Brier Score (BS) are used to quantify predictive accuracy. Nonparametric inverse probability of censoring weighting is used to estimate dynamic curves of AUC and BS as functions of the time at which predictions are made. Asymptotic results are established and both pointwise confidence intervals and simultaneous confidence bands are derived. Tests are also proposed to compare the dynamic prediction accuracy curves of two prognostic models. The finite sample behavior of the inference procedures is assessed via simulations. We apply the proposed methodology to compare various prediction models using repeated measures of two psychometric tests to predict dementia in the elderly, accounting for the competing risk of death. Models are estimated on the French Paquid cohort and predictive accuracies are evaluated and compared on the French Three-City cohort. © 2014, The International Biometric Society.

How to interpret a small increase in AUC with an additional risk prediction marker: decision analysis comes through.

PubMed

Baker, Stuart G; Schuit, Ewoud; Steyerberg, Ewout W; Pencina, Michael J; Vickers, Andrew; Vickers, Andew; Moons, Karel G M; Mol, Ben W J; Lindeman, Karen S

2014-09-28

An important question in the evaluation of an additional risk prediction marker is how to interpret a small increase in the area under the receiver operating characteristic curve (AUC). Many researchers believe that a change in AUC is a poor metric because it increases only slightly with the addition of a marker with a large odds ratio. Because it is not possible on purely statistical grounds to choose between the odds ratio and AUC, we invoke decision analysis, which incorporates costs and benefits. For example, a timely estimate of the risk of later non-elective operative delivery can help a woman in labor decide if she wants an early elective cesarean section to avoid greater complications from possible later non-elective operative delivery. A basic risk prediction model for later non-elective operative delivery involves only antepartum markers. Because adding intrapartum markers to this risk prediction model increases AUC by 0.02, we questioned whether this small improvement is worthwhile. A key decision-analytic quantity is the risk threshold, here the risk of later non-elective operative delivery at which a patient would be indifferent between an early elective cesarean section and usual care. For a range of risk thresholds, we found that an increase in the net benefit of risk prediction requires collecting intrapartum marker data on 68 to 124 women for every correct prediction of later non-elective operative delivery. Because data collection is non-invasive, this test tradeoff of 68 to 124 is clinically acceptable, indicating the value of adding intrapartum markers to the risk prediction model. Copyright © 2014 John Wiley & Sons, Ltd.

A model to predict the risk of lethal nasopharyngeal necrosis after re-irradiation with intensity-modulated radiotherapy in nasopharyngeal carcinoma patients.

PubMed

Yu, Ya-Hui; Xia, Wei-Xiong; Shi, Jun-Li; Ma, Wen-Juan; Li, Yong; Ye, Yan-Fang; Liang, Hu; Ke, Liang-Ru; Lv, Xing; Yang, Jing; Xiang, Yan-Qun; Guo, Xiang

2016-06-29

For patients with nasopharyngeal carcinoma (NPC) who undergo re-irradiation with intensity-modulated radiotherapy (IMRT), lethal nasopharyngeal necrosis (LNN) is a severe late adverse event. The purpose of this study was to identify risk factors for LNN and develop a model to predict LNN after radical re-irradiation with IMRT in patients with recurrent NPC. Patients who underwent radical re-irradiation with IMRT for locally recurrent NPC between March 2001 and December 2011 and who had no evidence of distant metastasis were included in this study. Clinical characteristics, including recurrent carcinoma conditions and dosimetric features, were evaluated as candidate risk factors for LNN. Logistic regression analysis was used to identify independent risk factors and construct the predictive scoring model. Among 228 patients enrolled in this study, 204 were at risk of developing LNN based on risk analysis. Of the 204 patients treated, 31 (15.2%) developed LNN. Logistic regression analysis showed that female sex (P = 0.008), necrosis before re-irradiation (P = 0.008), accumulated total prescription dose to the gross tumor volume (GTV) ≥145.5 Gy (P = 0.043), and recurrent tumor volume ≥25.38 cm(3) (P = 0.009) were independent risk factors for LNN. A model to predict LNN was then constructed that included these four independent risk factors. A model that includes sex, necrosis before re-irradiation, accumulated total prescription dose to GTV, and recurrent tumor volume can effectively predict the risk of developing LNN in NPC patients who undergo radical re-irradiation with IMRT.

Assessing Academic Risk of Student-Athletes: Applicability of the NCAA Graduation Risk Overview Model to GPA

ERIC Educational Resources Information Center

Johnson, James

2013-01-01

In an effort to standardize academic risk assessment, the NCAA developed the graduation risk overview (GRO) model. Although this model was designed to assess graduation risk, its ability to predict grade-point average (GPA) remained unknown. Therefore, 134 individual risk assessments were made to determine GRO model effectiveness in the…

Mapping the Transmission Risk of Zika Virus using Machine Learning Models.

PubMed

Jiang, Dong; Hao, Mengmeng; Ding, Fangyu; Fu, Jingying; Li, Meng

2018-06-19

Zika virus, which has been linked to severe congenital abnormalities, is exacerbating global public health problems with its rapid transnational expansion fueled by increased global travel and trade. Suitability mapping of the transmission risk of Zika virus is essential for drafting public health plans and disease control strategies, which are especially important in areas where medical resources are relatively scarce. Predicting the risk of Zika virus outbreak has been studied in recent years, but the published literature rarely includes multiple model comparisons or predictive uncertainty analysis. Here, three relatively popular machine learning models including backward propagation neural network (BPNN), gradient boosting machine (GBM) and random forest (RF) were adopted to map the probability of Zika epidemic outbreak at the global level, pairing high-dimensional multidisciplinary covariate layers with comprehensive location data on recorded Zika virus infection in humans. The results show that the predicted high-risk areas for Zika transmission are concentrated in four regions: Southeastern North America, Eastern South America, Central Africa and Eastern Asia. To evaluate the performance of machine learning models, the 50 modeling processes were conducted based on a training dataset. The BPNN model obtained the highest predictive accuracy with a 10-fold cross-validation area under the curve (AUC) of 0.966 [95% confidence interval (CI) 0.965-0.967], followed by the GBM model (10-fold cross-validation AUC = 0.964[0.963-0.965]) and the RF model (10-fold cross-validation AUC = 0.963[0.962-0.964]). Based on training samples, compared with the BPNN-based model, we find that significant differences (p = 0.0258* and p = 0.0001***, respectively) are observed for prediction accuracies achieved by the GBM and RF models. Importantly, the prediction uncertainty introduced by the selection of absence data was quantified and could provide more accurate fundamental and scientific information for further study on disease transmission prediction and risk assessment. Copyright © 2018. Published by Elsevier B.V.

[Statistical prediction methods in violence risk assessment and its application].

PubMed

Liu, Yuan-Yuan; Hu, Jun-Mei; Yang, Min; Li, Xiao-Song

2013-06-01

It is an urgent global problem how to improve the violence risk assessment. As a necessary part of risk assessment, statistical methods have remarkable impacts and effects. In this study, the predicted methods in violence risk assessment from the point of statistics are reviewed. The application of Logistic regression as the sample of multivariate statistical model, decision tree model as the sample of data mining technique, and neural networks model as the sample of artificial intelligence technology are all reviewed. This study provides data in order to contribute the further research of violence risk assessment.

Prediction models for intracranial hemorrhage or major bleeding in patients on antiplatelet therapy: a systematic review and external validation study.

PubMed

Hilkens, N A; Algra, A; Greving, J P

2016-01-01

ESSENTIALS: Prediction models may help to identify patients at high risk of bleeding on antiplatelet therapy. We identified existing prediction models for bleeding and validated them in patients with cerebral ischemia. Five prediction models were identified, all of which had some methodological shortcomings. Performance in patients with cerebral ischemia was poor. Background Antiplatelet therapy is widely used in secondary prevention after a transient ischemic attack (TIA) or ischemic stroke. Bleeding is the main adverse effect of antiplatelet therapy and is potentially life threatening. Identification of patients at increased risk of bleeding may help target antiplatelet therapy. This study sought to identify existing prediction models for intracranial hemorrhage or major bleeding in patients on antiplatelet therapy and evaluate their performance in patients with cerebral ischemia. We systematically searched PubMed and Embase for existing prediction models up to December 2014. The methodological quality of the included studies was assessed with the CHARMS checklist. Prediction models were externally validated in the European Stroke Prevention Study 2, comprising 6602 patients with a TIA or ischemic stroke. We assessed discrimination and calibration of included prediction models. Five prediction models were identified, of which two were developed in patients with previous cerebral ischemia. Three studies assessed major bleeding, one studied intracerebral hemorrhage and one gastrointestinal bleeding. None of the studies met all criteria of good quality. External validation showed poor discriminative performance, with c-statistics ranging from 0.53 to 0.64 and poor calibration. A limited number of prediction models is available that predict intracranial hemorrhage or major bleeding in patients on antiplatelet therapy. The methodological quality of the models varied, but was generally low. Predictive performance in patients with cerebral ischemia was poor. In order to reliably predict the risk of bleeding in patients with cerebral ischemia, development of a prediction model according to current methodological standards is needed. © 2015 International Society on Thrombosis and Haemostasis.

Sex similarities and differences in risk factors for recurrence of major depression.

PubMed

van Loo, Hanna M; Aggen, Steven H; Gardner, Charles O; Kendler, Kenneth S

2017-11-27

Major depression (MD) occurs about twice as often in women as in men, but it is unclear whether sex differences subsist after disease onset. This study aims to elucidate potential sex differences in rates and risk factors for MD recurrence, in order to improve prediction of course of illness and understanding of its underlying mechanisms. We used prospective data from a general population sample (n = 653) that experienced a recent episode of MD. A diverse set of potential risk factors for recurrence of MD was analyzed using Cox models subject to elastic net regularization for males and females separately. Accuracy of the prediction models was tested in same-sex and opposite-sex test data. Additionally, interactions between sex and each of the risk factors were investigated to identify potential sex differences. Recurrence rates and the impact of most risk factors were similar for men and women. For both sexes, prediction models were highly multifactorial including risk factors such as comorbid anxiety, early traumas, and family history. Some subtle sex differences were detected: for men, prediction models included more risk factors concerning characteristics of the depressive episode and family history of MD and generalized anxiety, whereas for women, models included more risk factors concerning early and recent adverse life events and socioeconomic problems. No prominent sex differences in risk factors for recurrence of MD were found, potentially indicating similar disease maintaining mechanisms for both sexes. Course of MD is a multifactorial phenomenon for both males and females.

Cancer Risk Prediction and Assessment

Cancer.gov

Cancer prediction models provide an important approach to assessing risk and prognosis by identifying individuals at high risk, facilitating the design and planning of clinical cancer trials, fostering the development of benefit-risk indices, and enabling estimates of the population burden and cost of cancer.

Predicting microbiologically defined infection in febrile neutropenic episodes in children: global individual participant data multivariable meta-analysis

PubMed Central

Phillips, Robert S; Sung, Lillian; Amman, Roland A; Riley, Richard D; Castagnola, Elio; Haeusler, Gabrielle M; Klaassen, Robert; Tissing, Wim J E; Lehrnbecher, Thomas; Chisholm, Julia; Hakim, Hana; Ranasinghe, Neil; Paesmans, Marianne; Hann, Ian M; Stewart, Lesley A

2016-01-01

Background: Risk-stratified management of fever with neutropenia (FN), allows intensive management of high-risk cases and early discharge of low-risk cases. No single, internationally validated, prediction model of the risk of adverse outcomes exists for children and young people. An individual patient data (IPD) meta-analysis was undertaken to devise one. Methods: The ‘Predicting Infectious Complications in Children with Cancer' (PICNICC) collaboration was formed by parent representatives, international clinical and methodological experts. Univariable and multivariable analyses, using random effects logistic regression, were undertaken to derive and internally validate a risk-prediction model for outcomes of episodes of FN based on clinical and laboratory data at presentation. Results: Data came from 22 different study groups from 15 countries, of 5127 episodes of FN in 3504 patients. There were 1070 episodes in 616 patients from seven studies available for multivariable analysis. Univariable analyses showed associations with microbiologically defined infection (MDI) in many items, including higher temperature, lower white cell counts and acute myeloid leukaemia, but not age. Patients with osteosarcoma/Ewings sarcoma and those with more severe mucositis were associated with a decreased risk of MDI. The predictive model included: malignancy type, temperature, clinically ‘severely unwell', haemoglobin, white cell count and absolute monocyte count. It showed moderate discrimination (AUROC 0.723, 95% confidence interval 0.711–0.759) and good calibration (calibration slope 0.95). The model was robust to bootstrap and cross-validation sensitivity analyses. Conclusions: This new prediction model for risk of MDI appears accurate. It requires prospective studies assessing implementation to assist clinicians and parents/patients in individualised decision making. PMID:26954719

A Random Forest Based Risk Model for Reliable and Accurate Prediction of Receipt of Transfusion in Patients Undergoing Percutaneous Coronary Intervention

PubMed Central

Gurm, Hitinder S.; Kooiman, Judith; LaLonde, Thomas; Grines, Cindy; Share, David; Seth, Milan

2014-01-01

Background Transfusion is a common complication of Percutaneous Coronary Intervention (PCI) and is associated with adverse short and long term outcomes. There is no risk model for identifying patients most likely to receive transfusion after PCI. The objective of our study was to develop and validate a tool for predicting receipt of blood transfusion in patients undergoing contemporary PCI. Methods Random forest models were developed utilizing 45 pre-procedural clinical and laboratory variables to estimate the receipt of transfusion in patients undergoing PCI. The most influential variables were selected for inclusion in an abbreviated model. Model performance estimating transfusion was evaluated in an independent validation dataset using area under the ROC curve (AUC), with net reclassification improvement (NRI) used to compare full and reduced model prediction after grouping in low, intermediate, and high risk categories. The impact of procedural anticoagulation on observed versus predicted transfusion rates were assessed for the different risk categories. Results Our study cohort was comprised of 103,294 PCI procedures performed at 46 hospitals between July 2009 through December 2012 in Michigan of which 72,328 (70%) were randomly selected for training the models, and 30,966 (30%) for validation. The models demonstrated excellent calibration and discrimination (AUC: full model  = 0.888 (95% CI 0.877–0.899), reduced model AUC = 0.880 (95% CI, 0.868–0.892), p for difference 0.003, NRI = 2.77%, p = 0.007). Procedural anticoagulation and radial access significantly influenced transfusion rates in the intermediate and high risk patients but no clinically relevant impact was noted in low risk patients, who made up 70% of the total cohort. Conclusions The risk of transfusion among patients undergoing PCI can be reliably calculated using a novel easy to use computational tool (https://bmc2.org/calculators/transfusion). This risk prediction algorithm may prove useful for both bed side clinical decision making and risk adjustment for assessment of quality. PMID:24816645

Measures of Residual Risk with Connections to Regression, Risk Tracking, Surrogate Models, and Ambiguity

DTIC Science & Technology

2015-01-07

vector that helps to manage , predict, and mitigate the risk in the original variable. Residual risk can be exemplified as a quantification of the improved... the random variable of interest is viewed in concert with a related random vector that helps to manage , predict, and mitigate the risk in the original...measures of risk. They view a random variable of interest in concert with an auxiliary random vector that helps to manage , predict and mitigate the risk

An individual risk prediction model for lung cancer based on a study in a Chinese population.

PubMed

Wang, Xu; Ma, Kewei; Cui, Jiuwei; Chen, Xiao; Jin, Lina; Li, Wei

2015-01-01

Early detection and diagnosis remains an effective yet challenging approach to improve the clinical outcome of patients with cancer. Low-dose computed tomography screening has been suggested to improve the diagnosis of lung cancer in high-risk individuals. To make screening more efficient, it is necessary to identify individuals who are at high risk. We conducted a case-control study to develop a predictive model for identification of such high-risk individuals. Clinical data from 705 lung cancer patients and 988 population-based controls were used for the development and evaluation of the model. Associations between environmental variants and lung cancer risk were analyzed with a logistic regression model. The predictive accuracy of the model was determined by calculating the area under the receiver operating characteristic curve and the optimal operating point. Our results indicate that lung cancer risk factors included older age, male gender, lower education level, family history of cancer, history of chronic obstructive pulmonary disease, lower body mass index, smoking cigarettes, a diet with less seafood, vegetables, fruits, dairy products, soybean products and nuts, a diet rich in meat, and exposure to pesticides and cooking emissions. The area under the curve was 0.8851 and the optimal operating point was obtained. With a cutoff of 0.35, the false positive rate, true positive rate, and Youden index were 0.21, 0.87, and 0.66, respectively. The risk prediction model for lung cancer developed in this study could discriminate high-risk from low-risk individuals.

Clinical Predictive Models for Chemotherapy-Induced Febrile Neutropenia in Breast Cancer Patients: A Validation Study

PubMed Central

Zhu, Liling; Su, Fengxi; Jia, Weijuan; Deng, Xiaogeng

2014-01-01

Background Predictive models for febrile neutropenia (FN) would be informative for physicians in clinical decision making. This study aims to validate a predictive model (Jenkin’s model) that comprises pretreatment hematological parameters in early-stage breast cancer patients. Patients and Methods A total of 428 breast cancer patients who received neoadjuvant/adjuvant chemotherapy without any prophylactic use of colony-stimulating factor were included. Pretreatment absolute neutrophil counts (ANC) and absolute lymphocyte counts (ALC) were used by the Jenkin’s model to assess the risk of FN. In addition, we modified the threshold of Jenkin’s model and generated Model-A and B. We also developed Model-C by incorporating the absolute monocyte count (AMC) as a predictor into Model-A. The rates of FN in the 1st chemotherapy cycle were calculated. A valid model should be able to significantly identify high-risk subgroup of patients with FN rate >20%. Results Jenkin’s model (Predicted as high-risk when ANC≦3.1*10∧9/L;ALC≦1.5*10∧9/L) did not identify any subgroups with significantly high risk (>20%) of FN in our population, even if we used different thresholds in Model-A(ANC≦4.4*10∧9/L;ALC≦2.1*10∧9/L) or B(ANC≦3.8*10∧9/L;ALC≦1.8*10∧9/L). However, with AMC added as an additional predictor, Model-C(ANC≦4.4*10∧9/L;ALC≦2.1*10∧9/L; AMC≦0.28*10∧9/L) identified a subgroup of patients with a significantly high risk of FN (23.1%). Conclusions In our population, Jenkin’s model, cannot accurately identify patients with a significant risk of FN. The threshold should be changed and the AMC should be incorporated as a predictor, to have excellent predictive ability. PMID:24945817

Two-Step Approach for the Prediction of Future Type 2 Diabetes Risk

PubMed Central

Abdul-Ghani, Muhammad A.; Abdul-Ghani, Tamam; Stern, Michael P.; Karavic, Jasmina; Tuomi, Tiinamaija; Bo, Insoma; DeFronzo, Ralph A.; Groop, Leif

2011-01-01

OBJECTIVE To develop a model for the prediction of type 2 diabetes mellitus (T2DM) risk on the basis of a multivariate logistic model and 1-h plasma glucose concentration (1-h PG). RESEARCH DESIGN AND METHODS The model was developed in a cohort of 1,562 nondiabetic subjects from the San Antonio Heart Study (SAHS) and validated in 2,395 nondiabetic subjects in the Botnia Study. A risk score on the basis of anthropometric parameters, plasma glucose and lipid profile, and blood pressure was computed for each subject. Subjects with a risk score above a certain cut point were considered to represent high-risk individuals, and their 1-h PG concentration during the oral glucose tolerance test was used to further refine their future T2DM risk. RESULTS We used the San Antonio Diabetes Prediction Model (SADPM) to generate the initial risk score. A risk-score value of 0.065 was found to be an optimal cut point for initial screening and selection of high-risk individuals. A 1-h PG concentration >140 mg/dL in high-risk individuals (whose risk score was >0.065) was the optimal cut point for identification of subjects at increased risk. The two cut points had 77.8, 77.4, and 44.8% (for the SAHS) and 75.8, 71.6, and 11.9% (for the Botnia Study) sensitivity, specificity, and positive predictive value, respectively, in the SAHS and Botnia Study. CONCLUSIONS A two-step model, based on the combination of the SADPM and 1-h PG, is a useful tool for the identification of high-risk Mexican-American and Caucasian individuals. PMID:21788628

Longitudinal histories as predictors of future diagnoses of domestic abuse: modelling study

PubMed Central

Kohane, Isaac S; Mandl, Kenneth D

2009-01-01

Objective To determine whether longitudinal data in patients’ historical records, commonly available in electronic health record systems, can be used to predict a patient’s future risk of receiving a diagnosis of domestic abuse. Design Bayesian models, known as intelligent histories, used to predict a patient’s risk of receiving a future diagnosis of abuse, based on the patient’s diagnostic history. Retrospective evaluation of the model’s predictions using an independent testing set. Setting A state-wide claims database covering six years of inpatient admissions to hospital, admissions for observation, and encounters in emergency departments. Population All patients aged over 18 who had at least four years between their earliest and latest visits recorded in the database (561 216 patients). Main outcome measures Timeliness of detection, sensitivity, specificity, positive predictive values, and area under the ROC curve. Results 1.04% (5829) of the patients met the narrow case definition for abuse, while 3.44% (19 303) met the broader case definition for abuse. The model achieved sensitive, specific (area under the ROC curve of 0.88), and early (10-30 months in advance, on average) prediction of patients’ future risk of receiving a diagnosis of abuse. Analysis of model parameters showed important differences between sexes in the risks associated with certain diagnoses. Conclusions Commonly available longitudinal diagnostic data can be useful for predicting a patient’s future risk of receiving a diagnosis of abuse. This modelling approach could serve as the basis for an early warning system to help doctors identify high risk patients for further screening. PMID:19789406

Predicting the risk for colorectal cancer with personal characteristics and fecal immunochemical test.

PubMed

Li, Wen; Zhao, Li-Zhong; Ma, Dong-Wang; Wang, De-Zheng; Shi, Lei; Wang, Hong-Lei; Dong, Mo; Zhang, Shu-Yi; Cao, Lei; Zhang, Wei-Hua; Zhang, Xi-Peng; Zhang, Qing-Huai; Yu, Lin; Qin, Hai; Wang, Xi-Mo; Chen, Sam Li-Sheng

2018-05-01

We aimed to predict colorectal cancer (CRC) based on the demographic features and clinical correlates of personal symptoms and signs from Tianjin community-based CRC screening data.A total of 891,199 residents who were aged 60 to 74 and were screened in 2012 were enrolled. The Lasso logistic regression model was used to identify the predictors for CRC. Predictive validity was assessed by the receiver operating characteristic (ROC) curve. Bootstrapping method was also performed to validate this prediction model.CRC was best predicted by a model that included age, sex, education level, occupations, diarrhea, constipation, colon mucosa and bleeding, gallbladder disease, a stressful life event, family history of CRC, and a positive fecal immunochemical test (FIT). The area under curve (AUC) for the questionnaire with a FIT was 84% (95% CI: 82%-86%), followed by 76% (95% CI: 74%-79%) for a FIT alone, and 73% (95% CI: 71%-76%) for the questionnaire alone. With 500 bootstrap replications, the estimated optimism (<0.005) shows good discrimination in validation of prediction model.A risk prediction model for CRC based on a series of symptoms and signs related to enteric diseases in combination with a FIT was developed from first round of screening. The results of the current study are useful for increasing the awareness of high-risk subjects and for individual-risk-guided invitations or strategies to achieve mass screening for CRC.

Recalibration of risk prediction models in a large multicenter cohort of admissions to adult, general critical care units in the United Kingdom.

PubMed

Harrison, David A; Brady, Anthony R; Parry, Gareth J; Carpenter, James R; Rowan, Kathy

2006-05-01

To assess the performance of published risk prediction models in common use in adult critical care in the United Kingdom and to recalibrate these models in a large representative database of critical care admissions. Prospective cohort study. A total of 163 adult general critical care units in England, Wales, and Northern Ireland, during the period of December 1995 to August 2003. A total of 231,930 admissions, of which 141,106 met inclusion criteria and had sufficient data recorded for all risk prediction models. None. The published versions of the Acute Physiology and Chronic Health Evaluation (APACHE) II, APACHE II UK, APACHE III, Simplified Acute Physiology Score (SAPS) II, and Mortality Probability Models (MPM) II were evaluated for discrimination and calibration by means of a combination of appropriate statistical measures recommended by an expert steering committee. All models showed good discrimination (the c index varied from 0.803 to 0.832) but imperfect calibration. Recalibration of the models, which was performed by both the Cox method and re-estimating coefficients, led to improved discrimination and calibration, although all models still showed significant departures from perfect calibration. Risk prediction models developed in another country require validation and recalibration before being used to provide risk-adjusted outcomes within a new country setting. Periodic reassessment is beneficial to ensure calibration is maintained.

The Tripartite Model of Risk Perception (TRIRISK): Distinguishing Deliberative, Affective, and Experiential Components of Perceived Risk.

PubMed

Ferrer, Rebecca A; Klein, William M P; Persoskie, Alexander; Avishai-Yitshak, Aya; Sheeran, Paschal

2016-10-01

Although risk perception is a key predictor in health behavior theories, current conceptions of risk comprise only one (deliberative) or two (deliberative vs. affective/experiential) dimensions. This research tested a tripartite model that distinguishes among deliberative, affective, and experiential components of risk perception. In two studies, and in relation to three common diseases (cancer, heart disease, diabetes), we used confirmatory factor analyses to examine the factor structure of the tripartite risk perception (TRIRISK) model and compared the fit of the TRIRISK model to dual-factor and single-factor models. In a third study, we assessed concurrent validity by examining the impact of cancer diagnosis on (a) levels of deliberative, affective, and experiential risk perception, and (b) the strength of relations among risk components, and tested predictive validity by assessing relations with behavioral intentions to prevent cancer. The tripartite factor structure was supported, producing better model fit across diseases (studies 1 and 2). Inter-correlations among the components were significantly smaller among participants who had been diagnosed with cancer, suggesting that affected populations make finer-grained distinctions among risk perceptions (study 3). Moreover, all three risk perception components predicted unique variance in intentions to engage in preventive behavior (study 3). The TRIRISK model offers both a novel conceptualization of health-related risk perceptions, and new measures that enhance predictive validity beyond that engendered by unidimensional and bidimensional models. The present findings have implications for the ways in which risk perceptions are targeted in health behavior change interventions, health communications, and decision aids.

A Bayesian network model for predicting type 2 diabetes risk based on electronic health records

NASA Astrophysics Data System (ADS)

Xie, Jiang; Liu, Yan; Zeng, Xu; Zhang, Wu; Mei, Zhen

2017-07-01

An extensive, in-depth study of diabetes risk factors (DBRF) is of crucial importance to prevent (or reduce) the chance of suffering from type 2 diabetes (T2D). Accumulation of electronic health records (EHRs) makes it possible to build nonlinear relationships between risk factors and diabetes. However, the current DBRF researches mainly focus on qualitative analyses, and the inconformity of physical examination items makes the risk factors likely to be lost, which drives us to study the novel machine learning approach for risk model development. In this paper, we use Bayesian networks (BNs) to analyze the relationship between physical examination information and T2D, and to quantify the link between risk factors and T2D. Furthermore, with the quantitative analyses of DBRF, we adopt EHR and propose a machine learning approach based on BNs to predict the risk of T2D. The experiments demonstrate that our approach can lead to better predictive performance than the classical risk model.

Assessing patient risk of central line-associated bacteremia via machine learning.

PubMed

Beeler, Cole; Dbeibo, Lana; Kelley, Kristen; Thatcher, Levi; Webb, Douglas; Bah, Amadou; Monahan, Patrick; Fowler, Nicole R; Nicol, Spencer; Judy-Malcolm, Alisa; Azar, Jose

2018-04-13

Central line-associated bloodstream infections (CLABSIs) contribute to increased morbidity, length of hospital stay, and cost. Despite progress in understanding the risk factors, there remains a need to accurately predict the risk of CLABSIs and, in real time, prevent them from occurring. A predictive model was developed using retrospective data from a large academic healthcare system. Models were developed with machine learning via construction of random forests using validated input variables. Fifteen variables accounted for the most significant effect on CLABSI prediction based on a retrospective study of 70,218 unique patient encounters between January 1, 2013, and May 31, 2016. The area under the receiver operating characteristic curve for the best-performing model was 0.82 in production. This model has multiple applications for resource allocation for CLABSI prevention, including serving as a tool to target patients at highest risk for potentially cost-effective but otherwise time-limited interventions. Machine learning can be used to develop accurate models to predict the risk of CLABSI in real time prior to the development of infection. Copyright © 2018 Association for Professionals in Infection Control and Epidemiology, Inc. Published by Elsevier Inc. All rights reserved.

Self-reported clothing size as a proxy measure for body size.

PubMed

Hughes, Laura A E; Schouten, Leo J; Goldbohm, R Alexandra; van den Brandt, Piet A; Weijenberg, Matty P

2009-09-01

Few studies have considered the potential utility of clothing size as a predictor of diseases associated with body weight. We used data on weight-stable men and women from a subcohort of the Netherlands Cohort Study to assess the correlation of clothing size with other anthropometric variables. Cox regression using the case-cohort approach was performed to establish whether clothing size can predict cancer risk after 13.3 years of follow-up, and if additionally considering body mass index (BMI) in the model improves the prediction. Trouser and skirt size correlated well with circumference measurements. Skirt size predicted endometrial cancer risk, and this effect was slightly attenuated when BMI was added to the model. Trouser size predicted risk of renal cell carcinoma, regardless of whether BMI was in the model. Clothing size appears to predict cancer risk independently of BMI, suggesting that clothing size is a useful measure to consider in epidemiologic studies when waist circumference is not available.

Predicting drug-induced liver injury in human with Naïve Bayes classifier approach.

PubMed

Zhang, Hui; Ding, Lan; Zou, Yi; Hu, Shui-Qing; Huang, Hai-Guo; Kong, Wei-Bao; Zhang, Ji

2016-10-01

Drug-induced liver injury (DILI) is one of the major safety concerns in drug development. Although various toxicological studies assessing DILI risk have been developed, these methods were not sufficient in predicting DILI in humans. Thus, developing new tools and approaches to better predict DILI risk in humans has become an important and urgent task. In this study, we aimed to develop a computational model for assessment of the DILI risk with using a larger scale human dataset and Naïve Bayes classifier. The established Naïve Bayes prediction model was evaluated by 5-fold cross validation and an external test set. For the training set, the overall prediction accuracy of the 5-fold cross validation was 94.0 %. The sensitivity, specificity, positive predictive value and negative predictive value were 97.1, 89.2, 93.5 and 95.1 %, respectively. The test set with the concordance of 72.6 %, sensitivity of 72.5 %, specificity of 72.7 %, positive predictive value of 80.4 %, negative predictive value of 63.2 %. Furthermore, some important molecular descriptors related to DILI risk and some toxic/non-toxic fragments were identified. Thus, we hope the prediction model established here would be employed for the assessment of human DILI risk, and the obtained molecular descriptors and substructures should be taken into consideration in the design of new candidate compounds to help medicinal chemists rationally select the chemicals with the best prospects to be effective and safe.

Robust human body model injury prediction in simulated side impact crashes.

PubMed

Golman, Adam J; Danelson, Kerry A; Stitzel, Joel D

2016-01-01

This study developed a parametric methodology to robustly predict occupant injuries sustained in real-world crashes using a finite element (FE) human body model (HBM). One hundred and twenty near-side impact motor vehicle crashes were simulated over a range of parameters using a Toyota RAV4 (bullet vehicle), Ford Taurus (struck vehicle) FE models and a validated human body model (HBM) Total HUman Model for Safety (THUMS). Three bullet vehicle crash parameters (speed, location and angle) and two occupant parameters (seat position and age) were varied using a Latin hypercube design of Experiments. Four injury metrics (head injury criterion, half deflection, thoracic trauma index and pelvic force) were used to calculate injury risk. Rib fracture prediction and lung strain metrics were also analysed. As hypothesized, bullet speed had the greatest effect on each injury measure. Injury risk was reduced when bullet location was further from the B-pillar or when the bullet angle was more oblique. Age had strong correlation to rib fractures frequency and lung strain severity. The injuries from a real-world crash were predicted using two different methods by (1) subsampling the injury predictors from the 12 best crush profile matching simulations and (2) using regression models. Both injury prediction methods successfully predicted the case occupant's low risk for pelvic injury, high risk for thoracic injury, rib fractures and high lung strains with tight confidence intervals. This parametric methodology was successfully used to explore crash parameter interactions and to robustly predict real-world injuries.

NT-proBNP is associated with coronary heart disease risk in healthy older women but fails to enhance prediction beyond established risk factors: results from the British Women's Heart and Health Study.

PubMed

Sattar, Naveed; Welsh, Paul; Sarwar, Nadeem; Danesh, John; Di Angelantonio, Emanuele; Gudnason, Vilmundur; Davey Smith, George; Ebrahim, Shah; Lawlor, Debbie A

2010-03-01

Limited evidence suggests NT-proBNP improves prediction of coronary heart disease (CHD) events but further data are needed, especially in people without pre-existing CHD and in women. We measured NT-proBNP in serum from 162 women with incident CHD events and 1226 controls (60-79 years) in a case-control study nested within the prospective British Women's Heart and Health Study. All cases and controls were free from CHD at baseline. We related NT-proBNP to CHD event risk, and determined to what extent NT-proBNP enhanced CHD risk prediction beyond established risk factors. The odds ratio for CHD per 1 standard deviation increase in log(e)NT-proBNP was 1.37 (95% CI: 1.13-1.68) in analyses adjusted for established CHD risk factors, social class, CRP and insulin. However, addition of log(e)NT-proBNP did not improve the discrimination of a prediction model including age, social class, smoking, physical activity, lipids, fasting glucose, waist:hip ratio, hypertension, statin and aspirin use, nor a standard Framingham risk score model; area under the receiver operator curve for the former model increased from 0.676 to 0.687 on inclusion of NT-proBNP (p=0.3). Furthermore, adding NT-proBNP did not improve calibration of a prediction model containing established risk factors, nor did inclusion more appropriately re-classify participants in relation to their final outcome. Findings were similar (independent associations, but no prediction improvement) for fasting insulin and CRP. These results caution against use of NT-proBNP for CHD risk prediction in healthy women and suggest a need for larger studies in both genders to resolve outstanding uncertainties.

A Model-Free Machine Learning Method for Risk Classification and Survival Probability Prediction.

PubMed

Geng, Yuan; Lu, Wenbin; Zhang, Hao Helen

2014-01-01

Risk classification and survival probability prediction are two major goals in survival data analysis since they play an important role in patients' risk stratification, long-term diagnosis, and treatment selection. In this article, we propose a new model-free machine learning framework for risk classification and survival probability prediction based on weighted support vector machines. The new procedure does not require any specific parametric or semiparametric model assumption on data, and is therefore capable of capturing nonlinear covariate effects. We use numerous simulation examples to demonstrate finite sample performance of the proposed method under various settings. Applications to a glioma tumor data and a breast cancer gene expression survival data are shown to illustrate the new methodology in real data analysis.

Incremental Value of Repeated Risk Factor Measurements for Cardiovascular Disease Prediction in Middle-Aged Korean Adults: Results From the NHIS-HEALS (National Health Insurance System-National Health Screening Cohort).

PubMed

Cho, In-Jeong; Sung, Ji Min; Chang, Hyuk-Jae; Chung, Namsik; Kim, Hyeon Chang

2017-11-01

Increasing evidence suggests that repeatedly measured cardiovascular disease (CVD) risk factors may have an additive predictive value compared with single measured levels. Thus, we evaluated the incremental predictive value of incorporating periodic health screening data for CVD prediction in a large nationwide cohort with periodic health screening tests. A total of 467 708 persons aged 40 to 79 years and free from CVD were randomly divided into development (70%) and validation subcohorts (30%). We developed 3 different CVD prediction models: a single measure model using single time point screening data; a longitudinal average model using average risk factor values from periodic screening data; and a longitudinal summary model using average values and the variability of risk factors. The development subcohort included 327 396 persons who had 3.2 health screenings on average and 25 765 cases of CVD over 12 years. The C statistics (95% confidence interval [CI]) for the single measure, longitudinal average, and longitudinal summary models were 0.690 (95% CI, 0.682-0.698), 0.695 (95% CI, 0.687-0.703), and 0.752 (95% CI, 0.744-0.760) in men and 0.732 (95% CI, 0.722-0.742), 0.735 (95% CI, 0.725-0.745), and 0.790 (95% CI, 0.780-0.800) in women, respectively. The net reclassification index from the single measure model to the longitudinal average model was 1.78% in men and 1.33% in women, and the index from the longitudinal average model to the longitudinal summary model was 32.71% in men and 34.98% in women. Using averages of repeatedly measured risk factor values modestly improves CVD predictability compared with single measurement values. Incorporating the average and variability information of repeated measurements can lead to great improvements in disease prediction. URL: https://www.clinicaltrials.gov. Unique identifier: NCT02931500. © 2017 American Heart Association, Inc.

Using remote sensing, ecological niche modeling, and Geographic Information Systems for Rift Valley fever risk assessment in the United States

NASA Astrophysics Data System (ADS)

Tedrow, Christine Atkins

The primary goal in this study was to explore remote sensing, ecological niche modeling, and Geographic Information Systems (GIS) as aids in predicting candidate Rift Valley fever (RVF) competent vector abundance and distribution in Virginia, and as means of estimating where risk of establishment in mosquitoes and risk of transmission to human populations would be greatest in Virginia. A second goal in this study was to determine whether the remotely-sensed Normalized Difference Vegetation Index (NDVI) can be used as a proxy variable of local conditions for the development of mosquitoes to predict mosquito species distribution and abundance in Virginia. As part of this study, a mosquito surveillance database was compiled to archive the historical patterns of mosquito species abundance in Virginia. In addition, linkages between mosquito density and local environmental and climatic patterns were spatially and temporally examined. The present study affirms the potential role of remote sensing imagery for species distribution prediction, and it demonstrates that ecological niche modeling is a valuable predictive tool to analyze the distributions of populations. The MaxEnt ecological niche modeling program was used to model predicted ranges for potential RVF competent vectors in Virginia. The MaxEnt model was shown to be robust, and the candidate RVF competent vector predicted distribution map is presented. The Normalized Difference Vegetation Index (NDVI) was found to be the most useful environmental-climatic variable to predict mosquito species distribution and abundance in Virginia. However, these results indicate that a more robust prediction is obtained by including other environmental-climatic factors correlated to mosquito densities (e.g., temperature, precipitation, elevation) with NDVI. The present study demonstrates that remote sensing and GIS can be used with ecological niche and risk modeling methods to estimate risk of virus establishment in mosquitoes and transmission to humans. Maps delineating the geographic areas in Virginia with highest risk for RVF establishment in mosquito populations and RVF disease transmission to human populations were generated in a GIS using human, domestic animal, and white-tailed deer population estimates and the MaxEnt potential RVF competent vector species distribution prediction. The candidate RVF competent vector predicted distribution and RVF risk maps presented in this study can help vector control agencies and public health officials focus Rift Valley fever surveillance efforts in geographic areas with large co-located populations of potential RVF competent vectors and human, domestic animal, and wildlife hosts. Keywords. Rift Valley fever, risk assessment, Ecological Niche Modeling, MaxEnt, Geographic Information System, remote sensing, Pearson's Product-Moment Correlation Coefficient, vectors, mosquito distribution, mosquito density, mosquito surveillance, United States, Virginia, domestic animals, white-tailed deer, ArcGIS

Plasma Free Amino Acid Profiles Predict Four-Year Risk of Developing Diabetes, Metabolic Syndrome, Dyslipidemia, and Hypertension in Japanese Population

PubMed Central

Yamakado, Minoru; Nagao, Kenji; Imaizumi, Akira; Tani, Mizuki; Toda, Akiko; Tanaka, Takayuki; Jinzu, Hiroko; Miyano, Hiroshi; Yamamoto, Hiroshi; Daimon, Takashi; Horimoto, Katsuhisa; Ishizaka, Yuko

2015-01-01

Plasma free amino acid (PFAA) profile is highlighted in its association with visceral obesity and hyperinsulinemia, and future diabetes. Indeed PFAA profiling potentially can evaluate individuals’ future risks of developing lifestyle-related diseases, in addition to diabetes. However, few studies have been performed especially in Asian populations, about the optimal combination of PFAAs for evaluating health risks. We quantified PFAA levels in 3,701 Japanese subjects, and determined visceral fat area (VFA) and two-hour post-challenge insulin (Ins120 min) values in 865 and 1,160 subjects, respectively. Then, models between PFAA levels and the VFA or Ins120 min values were constructed by multiple linear regression analysis with variable selection. Finally, a cohort study of 2,984 subjects to examine capabilities of the obtained models for predicting four-year risk of developing new-onset lifestyle-related diseases was conducted. The correlation coefficients of the obtained PFAA models against VFA or Ins120 min were higher than single PFAA level. Our models work well for future risk prediction. Even after adjusting for commonly accepted multiple risk factors, these models can predict future development of diabetes, metabolic syndrome, and dyslipidemia. PFAA profiles confer independent and differing contributions to increasing the lifestyle-related disease risks in addition to the currently known factors in a general Japanese population. PMID:26156880

Validation of Predictors of Fall Events in Hospitalized Patients With Cancer.

PubMed

Weed-Pfaff, Samantha H; Nutter, Benjamin; Bena, James F; Forney, Jennifer; Field, Rosemary; Szoka, Lynn; Karius, Diana; Akins, Patti; Colvin, Christina M; Albert, Nancy M

2016-10-01

A seven-item cancer-specific fall risk tool (Cleveland Clinic Capone-Albert [CC-CA] Fall Risk Score) was shown to have a strong concordance index for predicting falls; however, validation of the model is needed. The aims of this study were to validate that the CC-CA Fall Risk Score, made up of six factors, predicts falls in patients with cancer and to determine if the CC-CA Fall Risk Score performs better than the Morse Fall Tool. Using a prospective, comparative methodology, data were collected from electronic health records of patients hospitalized for cancer care in four hospitals. Risk factors from each tool were recorded, when applicable. Multivariable models were created to predict the probability of a fall. A concordance index for each fall tool was calculated. The CC-CA Fall Risk Score provided higher discrimination than the Morse Fall Tool in predicting fall events in patients hospitalized for cancer management.

Predicting Rib Fracture Risk With Whole-Body Finite Element Models: Development and Preliminary Evaluation of a Probabilistic Analytical Framework

PubMed Central

Forman, Jason L.; Kent, Richard W.; Mroz, Krystoffer; Pipkorn, Bengt; Bostrom, Ola; Segui-Gomez, Maria

2012-01-01

This study sought to develop a strain-based probabilistic method to predict rib fracture risk with whole-body finite element (FE) models, and to describe a method to combine the results with collision exposure information to predict injury risk and potential intervention effectiveness in the field. An age-adjusted ultimate strain distribution was used to estimate local rib fracture probabilities within an FE model. These local probabilities were combined to predict injury risk and severity within the whole ribcage. The ultimate strain distribution was developed from a literature dataset of 133 tests. Frontal collision simulations were performed with the THUMS (Total HUman Model for Safety) model with four levels of delta-V and two restraints: a standard 3-point belt and a progressive 3.5–7 kN force-limited, pretensioned (FL+PT) belt. The results of three simulations (29 km/h standard, 48 km/h standard, and 48 km/h FL+PT) were compared to matched cadaver sled tests. The numbers of fractures predicted for the comparison cases were consistent with those observed experimentally. Combining these results with field exposure informantion (ΔV, NASS-CDS 1992–2002) suggests a 8.9% probability of incurring AIS3+ rib fractures for a 60 year-old restrained by a standard belt in a tow-away frontal collision with this restraint, vehicle, and occupant configuration, compared to 4.6% for the FL+PT belt. This is the first study to describe a probabilistic framework to predict rib fracture risk based on strains observed in human-body FE models. Using this analytical framework, future efforts may incorporate additional subject or collision factors for multi-variable probabilistic injury prediction. PMID:23169122

Claims-based risk model for first severe COPD exacerbation.

PubMed

Stanford, Richard H; Nag, Arpita; Mapel, Douglas W; Lee, Todd A; Rosiello, Richard; Schatz, Michael; Vekeman, Francis; Gauthier-Loiselle, Marjolaine; Merrigan, J F Philip; Duh, Mei Sheng

2018-02-01

To develop and validate a predictive model for first severe chronic obstructive pulmonary disease (COPD) exacerbation using health insurance claims data and to validate the risk measure of controller medication to total COPD treatment (controller and rescue) ratio (CTR). A predictive model was developed and validated in 2 managed care databases: Truven Health MarketScan database and Reliant Medical Group database. This secondary analysis assessed risk factors, including CTR, during the baseline period (Year 1) to predict risk of severe exacerbation in the at-risk period (Year 2). Patients with COPD who were 40 years or older and who had at least 1 COPD medication dispensed during the year following COPD diagnosis were included. Subjects with severe exacerbations in the baseline year were excluded. Risk factors in the baseline period were included as potential predictors in multivariate analysis. Performance was evaluated using C-statistics. The analysis included 223,824 patients. The greatest risk factors for first severe exacerbation were advanced age, chronic oxygen therapy usage, COPD diagnosis type, dispensing of 4 or more canisters of rescue medication, and having 2 or more moderate exacerbations. A CTR of 0.3 or greater was associated with a 14% lower risk of severe exacerbation. The model performed well with C-statistics, ranging from 0.711 to 0.714. This claims-based risk model can predict the likelihood of first severe COPD exacerbation. The CTR could also potentially be used to target populations at greatest risk for severe exacerbations. This could be relevant for providers and payers in approaches to prevent severe exacerbations and reduce costs.

Validation of a multifactorial risk factor model used for predicting future caries risk with Nevada adolescents.

PubMed

Ditmyer, Marcia M; Dounis, Georgia; Howard, Katherine M; Mobley, Connie; Cappelli, David

2011-05-20

The objective of this study was to measure the validity and reliability of a multifactorial Risk Factor Model developed for use in predicting future caries risk in Nevada adolescents in a public health setting. This study examined retrospective data from an oral health surveillance initiative that screened over 51,000 students 13-18 years of age, attending public/private schools in Nevada across six academic years (2002/2003-2007/2008). The Risk Factor Model included ten demographic variables: exposure to fluoridation in the municipal water supply, environmental smoke exposure, race, age, locale (metropolitan vs. rural), tobacco use, Body Mass Index, insurance status, sex, and sealant application. Multiple regression was used in a previous study to establish which significantly contributed to caries risk. Follow-up logistic regression ascertained the weight of contribution and odds ratios of the ten variables. Researchers in this study computed sensitivity, specificity, positive predictive value (PVP), negative predictive value (PVN), and prevalence across all six years of screening to assess the validity of the Risk Factor Model. Subjects' overall mean caries prevalence across all six years was 66%. Average sensitivity across all six years was 79%; average specificity was 81%; average PVP was 89% and average PVN was 67%. Overall, the Risk Factor Model provided a relatively constant, valid measure of caries that could be used in conjunction with a comprehensive risk assessment in population-based screenings by school nurses/nurse practitioners, health educators, and physicians to guide them in assessing potential future caries risk for use in prevention and referral practices.

Risk assessment and remedial policy evaluation using predictive modeling

DOE Office of Scientific and Technical Information (OSTI.GOV)

Linkov, L.; Schell, W.R.

1996-06-01

As a result of nuclear industry operation and accidents, large areas of natural ecosystems have been contaminated by radionuclides and toxic metals. Extensive societal pressure has been exerted to decrease the radiation dose to the population and to the environment. Thus, in making abatement and remediation policy decisions, not only economic costs but also human and environmental risk assessments are desired. This paper introduces a general framework for risk assessment and remedial policy evaluation using predictive modeling. Ecological risk assessment requires evaluation of the radionuclide distribution in ecosystems. The FORESTPATH model is used for predicting the radionuclide fate in forestmore » compartments after deposition as well as for evaluating the efficiency of remedial policies. Time of intervention and radionuclide deposition profile was predicted as being crucial for the remediation efficiency. Risk assessment conducted for a critical group of forest users in Belarus shows that consumption of forest products (berries and mushrooms) leads to about 0.004% risk of a fatal cancer annually. Cost-benefit analysis for forest cleanup suggests that complete removal of organic layer is too expensive for application in Belarus and a better methodology is required. In conclusion, FORESTPATH modeling framework could have wide applications in environmental remediation of radionuclides and toxic metals as well as in dose reconstruction and, risk-assessment.« less

BOADICEA breast cancer risk prediction model: updates to cancer incidences, tumour pathology and web interface

PubMed Central

Lee, A J; Cunningham, A P; Kuchenbaecker, K B; Mavaddat, N; Easton, D F; Antoniou, A C

2014-01-01

Background: The Breast and Ovarian Analysis of Disease Incidence and Carrier Estimation Algorithm (BOADICEA) is a risk prediction model that is used to compute probabilities of carrying mutations in the high-risk breast and ovarian cancer susceptibility genes BRCA1 and BRCA2, and to estimate the future risks of developing breast or ovarian cancer. In this paper, we describe updates to the BOADICEA model that extend its capabilities, make it easier to use in a clinical setting and yield more accurate predictions. Methods: We describe: (1) updates to the statistical model to include cancer incidences from multiple populations; (2) updates to the distributions of tumour pathology characteristics using new data on BRCA1 and BRCA2 mutation carriers and women with breast cancer from the general population; (3) improvements to the computational efficiency of the algorithm so that risk calculations now run substantially faster; and (4) updates to the model's web interface to accommodate these new features and to make it easier to use in a clinical setting. Results: We present results derived using the updated model, and demonstrate that the changes have a significant impact on risk predictions. Conclusion: All updates have been implemented in a new version of the BOADICEA web interface that is now available for general use: http://ccge.medschl.cam.ac.uk/boadicea/. PMID:24346285

Problematic Dichotomization of Risk for Intensive Care Unit (ICU)-Acquired Invasive Candidiasis: Results Using a Risk-Predictive Model to Categorize 3 Levels of Risk From a Multicenter Prospective Cohort of Australian ICU Patients.

PubMed

Playford, E Geoffrey; Lipman, Jeffrey; Jones, Michael; Lau, Anna F; Kabir, Masrura; Chen, Sharon C-A; Marriott, Deborah J; Seppelt, Ian; Gottlieb, Thomas; Cheung, Winston; Iredell, Jonathan R; McBryde, Emma S; Sorrell, Tania C

2016-12-01

 Delayed antifungal therapy for invasive candidiasis (IC) contributes to poor outcomes. Predictive risk models may allow targeted antifungal prophylaxis to those at greatest risk.  A prospective cohort study of 6685 consecutive nonneutropenic patients admitted to 7 Australian intensive care units (ICUs) for ≥72 hours was performed. Clinical risk factors for IC occurring prior to and following ICU admission, colonization with Candida species on surveillance cultures from 3 sites assessed twice weekly, and the occurrence of IC ≥72 hours following ICU admission or ≤72 hours following ICU discharge were measured. From these parameters, a risk-predictive model for the development of ICU-acquired IC was then derived.  Ninety-six patients (1.43%) developed ICU-acquired IC. A simple summation risk-predictive model using the 10 independently significant variables associated with IC demonstrated overall moderate accuracy (area under the receiver operating characteristic curve = 0.82). No single threshold score could categorize patients into clinically useful high- and low-risk groups. However, using 2 threshold scores, 3 patient cohorts could be identified: those at high risk (score ≥6, 4.8% of total cohort, positive predictive value [PPV] 11.7%), those at low risk (score ≤2, 43.1% of total cohort, PPV 0.24%), and those at intermediate risk (score 3-5, 52.1% of total cohort, PPV 1.46%).  Dichotomization of ICU patients into high- and low-risk groups for IC risk is problematic. Categorizing patients into high-, intermediate-, and low-risk groups may more efficiently target early antifungal strategies and utilization of newer diagnostic tests. © The Author 2016. Published by Oxford University Press for the Infectious Diseases Society of America. All rights reserved. For permissions, e-mail journals.permissions@oup.com.

Predicting the Risk of Attrition for Undergraduate Students with Time Based Modelling

ERIC Educational Resources Information Center

Chai, Kevin E. K.; Gibson, David

2015-01-01

Improving student retention is an important and challenging problem for universities. This paper reports on the development of a student attrition model for predicting which first year students are most at-risk of leaving at various points in time during their first semester of study. The objective of developing such a model is to assist…

Predicting Child Abuse Potential: An Empirical Investigation of Two Theoretical Frameworks

ERIC Educational Resources Information Center

Begle, Angela Moreland; Dumas, Jean E.; Hanson, Rochelle F.

2010-01-01

This study investigated two theoretical risk models predicting child maltreatment potential: (a) Belsky's (1993) developmental-ecological model and (b) the cumulative risk model in a sample of 610 caregivers (49% African American, 46% European American; 53% single) with a child between 3 and 6 years old. Results extend the literature by using a…

Prediction model with metabolic syndrome to predict recurrent vascular events in patients with clinically manifest vascular diseases.

PubMed

Wassink, Annemarie M; van der Graaf, Yolanda; Janssen, Kristel J; Cook, Nancy R; Visseren, Frank L

2012-12-01

Although the overall average 10-year cardiovascular risk for patients with manifest atherosclerosis is considered to be more than 20%, actual risk for individual patients ranges from much lower to much higher. We investigated whether information on metabolic syndrome (MetS) or its individual components improves cardiovascular risk stratification in these patients. We conducted a prospective cohort study in 3679 patients with clinical manifest atherosclerosis from the Secondary Manifestations of ARTerial disease (SMART) study. Primary outcome was defined as any cardiovascular event (cardiovascular death, ischemic stroke or myocardial infarction). Three pre-specified prediction models were derived, all including information on established MetS components. The association between outcome and predictors was quantified using a Cox proportional hazard analysis. Model performance was assessed using global goodness-of-fit fit (χ(2)), discrimination (C-index) and ability to improve risk stratification. A total of 417 cardiovascular events occurred among 3679 patients with 15,102 person-years of follow-up (median follow-up 3.7 years, range 1.6-6.4 years). Compared to a model with age and gender only, all MetS-based models performed slightly better in terms of global model fit (χ(2)) but not C-index. The Net Reclassification Index associated with the addition of MetS (yes/no), the dichotomous MetS-components or the continuous MetS-components on top of age and gender was 2.1% (p = 0.29), 2.3% (p = 0.31) and 7.5% (p = 0.01), respectively. Prediction models incorporating age, gender and MetS can discriminate between patients with clinical manifest atherosclerosis at the highest vascular risk and those at lower risk. The addition of MetS components to a model with age and gender correctly reclassifies only a small proportion of patients into higher- and lower-risk categories. The clinical utility of a prediction model with MetS is therefore limited.

Prediction of violent reoffending on release from prison: derivation and external validation of a scalable tool.

PubMed

Fazel, Seena; Chang, Zheng; Fanshawe, Thomas; Långström, Niklas; Lichtenstein, Paul; Larsson, Henrik; Mallett, Susan

2016-06-01

More than 30 million people are released from prison worldwide every year, who include a group at high risk of perpetrating interpersonal violence. Because there is considerable inconsistency and inefficiency in identifying those who would benefit from interventions to reduce this risk, we developed and validated a clinical prediction rule to determine the risk of violent offending in released prisoners. We did a cohort study of a population of released prisoners in Sweden. Through linkage of population-based registers, we developed predictive models for violent reoffending for the cohort. First, we developed a derivation model to determine the strength of prespecified, routinely obtained criminal history, sociodemographic, and clinical risk factors using multivariable Cox proportional hazard regression, and then tested them in an external validation. We measured discrimination and calibration for prediction of our primary outcome of violent reoffending at 1 and 2 years using cutoffs of 10% for 1-year risk and 20% for 2-year risk. We identified a cohort of 47 326 prisoners released in Sweden between 2001 and 2009, with 11 263 incidents of violent reoffending during this period. We developed a 14-item derivation model to predict violent reoffending and tested it in an external validation (assigning 37 100 individuals to the derivation sample and 10 226 to the validation sample). The model showed good measures of discrimination (Harrell's c-index 0·74) and calibration. For risk of violent reoffending at 1 year, sensitivity was 76% (95% CI 73-79) and specificity was 61% (95% CI 60-62). Positive and negative predictive values were 21% (95% CI 19-22) and 95% (95% CI 94-96), respectively. At 2 years, sensitivity was 67% (95% CI 64-69) and specificity was 70% (95% CI 69-72). Positive and negative predictive values were 37% (95% CI 35-39) and 89% (95% CI 88-90), respectively. Of individuals with a predicted risk of violent reoffending of 50% or more, 88% had drug and alcohol use disorders. We used the model to generate a simple, web-based, risk calculator (OxRec) that is free to use. We have developed a prediction model in a Swedish prison population that can assist with decision making on release by identifying those who are at low risk of future violent offending, and those at high risk of violent reoffending who might benefit from drug and alcohol treatment. Further assessments in other populations and countries are needed. Wellcome Trust, the Swedish Research Council, and the Swedish Research Council for Health, Working Life and Welfare. Copyright © 2016 Fazel et al. Open Access article distributed under the terms of CC BY. Published by Elsevier Ltd.. All rights reserved.

Biomarkers for predicting type 2 diabetes development-Can metabolomics improve on existing biomarkers?

PubMed

Savolainen, Otto; Fagerberg, Björn; Vendelbo Lind, Mads; Sandberg, Ann-Sofie; Ross, Alastair B; Bergström, Göran

2017-01-01

The aim was to determine if metabolomics could be used to build a predictive model for type 2 diabetes (T2D) risk that would improve prediction of T2D over current risk markers. Gas chromatography-tandem mass spectrometry metabolomics was used in a nested case-control study based on a screening sample of 64-year-old Caucasian women (n = 629). Candidate metabolic markers of T2D were identified in plasma obtained at baseline and the power to predict diabetes was tested in 69 incident cases occurring during 5.5 years follow-up. The metabolomics results were used as a standalone prediction model and in combination with established T2D predictive biomarkers for building eight T2D prediction models that were compared with each other based on their sensitivity and selectivity for predicting T2D. Established markers of T2D (impaired fasting glucose, impaired glucose tolerance, insulin resistance (HOMA), smoking, serum adiponectin)) alone, and in combination with metabolomics had the largest areas under the curve (AUC) (0.794 (95% confidence interval [0.738-0.850]) and 0.808 [0.749-0.867] respectively), with the standalone metabolomics model based on nine fasting plasma markers having a lower predictive power (0.657 [0.577-0.736]). Prediction based on non-blood based measures was 0.638 [0.565-0.711]). Established measures of T2D risk remain the best predictor of T2D risk in this population. Additional markers detected using metabolomics are likely related to these measures as they did not enhance the overall prediction in a combined model.

Biomarkers for predicting type 2 diabetes development—Can metabolomics improve on existing biomarkers?

PubMed Central

Savolainen, Otto; Fagerberg, Björn; Vendelbo Lind, Mads; Sandberg, Ann-Sofie; Ross, Alastair B.; Bergström, Göran

2017-01-01

Aim The aim was to determine if metabolomics could be used to build a predictive model for type 2 diabetes (T2D) risk that would improve prediction of T2D over current risk markers. Methods Gas chromatography-tandem mass spectrometry metabolomics was used in a nested case-control study based on a screening sample of 64-year-old Caucasian women (n = 629). Candidate metabolic markers of T2D were identified in plasma obtained at baseline and the power to predict diabetes was tested in 69 incident cases occurring during 5.5 years follow-up. The metabolomics results were used as a standalone prediction model and in combination with established T2D predictive biomarkers for building eight T2D prediction models that were compared with each other based on their sensitivity and selectivity for predicting T2D. Results Established markers of T2D (impaired fasting glucose, impaired glucose tolerance, insulin resistance (HOMA), smoking, serum adiponectin)) alone, and in combination with metabolomics had the largest areas under the curve (AUC) (0.794 (95% confidence interval [0.738–0.850]) and 0.808 [0.749–0.867] respectively), with the standalone metabolomics model based on nine fasting plasma markers having a lower predictive power (0.657 [0.577–0.736]). Prediction based on non-blood based measures was 0.638 [0.565–0.711]). Conclusions Established measures of T2D risk remain the best predictor of T2D risk in this population. Additional markers detected using metabolomics are likely related to these measures as they did not enhance the overall prediction in a combined model. PMID:28692646

Implications of Nine Risk Prediction Models for Selecting Ever-Smokers for Computed Tomography Lung Cancer Screening.

PubMed

Katki, Hormuzd A; Kovalchik, Stephanie A; Petito, Lucia C; Cheung, Li C; Jacobs, Eric; Jemal, Ahmedin; Berg, Christine D; Chaturvedi, Anil K

2018-05-15

Lung cancer screening guidelines recommend using individualized risk models to refer ever-smokers for screening. However, different models select different screening populations. The performance of each model in selecting ever-smokers for screening is unknown. To compare the U.S. screening populations selected by 9 lung cancer risk models (the Bach model; the Spitz model; the Liverpool Lung Project [LLP] model; the LLP Incidence Risk Model [LLPi]; the Hoggart model; the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial Model 2012 [PLCOM2012]; the Pittsburgh Predictor; the Lung Cancer Risk Assessment Tool [LCRAT]; and the Lung Cancer Death Risk Assessment Tool [LCDRAT]) and to examine their predictive performance in 2 cohorts. Population-based prospective studies. United States. Models selected U.S. screening populations by using data from the National Health Interview Survey from 2010 to 2012. Model performance was evaluated using data from 337 388 ever-smokers in the National Institutes of Health-AARP Diet and Health Study and 72 338 ever-smokers in the CPS-II (Cancer Prevention Study II) Nutrition Survey cohort. Model calibration (ratio of model-predicted to observed cases [expected-observed ratio]) and discrimination (area under the curve [AUC]). At a 5-year risk threshold of 2.0%, the models chose U.S. screening populations ranging from 7.6 million to 26 million ever-smokers. These disagreements occurred because, in both validation cohorts, 4 models (the Bach model, PLCOM2012, LCRAT, and LCDRAT) were well-calibrated (expected-observed ratio range, 0.92 to 1.12) and had higher AUCs (range, 0.75 to 0.79) than 5 models that generally overestimated risk (expected-observed ratio range, 0.83 to 3.69) and had lower AUCs (range, 0.62 to 0.75). The 4 best-performing models also had the highest sensitivity at a fixed specificity (and vice versa) and similar discrimination at a fixed risk threshold. These models showed better agreement on size of the screening population (7.6 million to 10.9 million) and achieved consensus on 73% of persons chosen. No consensus on risk thresholds for screening. The 9 lung cancer risk models chose widely differing U.S. screening populations. However, 4 models (the Bach model, PLCOM2012, LCRAT, and LCDRAT) most accurately predicted risk and performed best in selecting ever-smokers for screening. Intramural Research Program of the National Institutes of Health/National Cancer Institute.

Predicting Adverse Outcomes After Myocardial Infarction Among Patients With Diabetes Mellitus.

PubMed

Arnold, Suzanne V; Spertus, John A; Jones, Philip G; McGuire, Darren K; Lipska, Kasia J; Xu, Yaping; Stolker, Joshua M; Goyal, Abhinav; Kosiborod, Mikhail

2016-07-01

Although patients with diabetes mellitus experience high rates of adverse events after acute myocardial infarction (AMI), including death and recurrent ischemia, some diabetic patients are likely at low risk, whereas others are at high risk. We sought to develop prediction models to stratify risk after AMI in patients with diabetes mellitus. We developed prediction models for long-term mortality and angina among 1613 patients with diabetes mellitus discharged alive after AMI from 24 US hospitals and then validated the models in a separate, multicenter registry of 786 patients with diabetes mellitus. Event rates in the derivation cohort were 27% for 5-year mortality and 27% for 1-year angina. Parsimonious prediction models demonstrated good discrimination (c-indices=0.78 and 0.69, respectively) and excellent calibration. Within the context of the predictors we estimated, the strongest predictors for mortality were higher creatinine, not working at the time of the AMI, older age, lower hemoglobin, left ventricular dysfunction, and chronic heart failure. The strongest predictors for angina were angina burden in the 4 weeks before the AMI, younger age, history of prior coronary bypass graft surgery, and non-white race. The lowest and highest deciles of predicted risk ranged from 4% to 80% for mortality and 12% to 59% for angina. The models also performed well in external validation (c-indices=0.78 and 0.73, respectively). We found a wide range of risk for adverse outcomes after AMI in diabetic patients. Predictive models can identify patients with diabetes mellitus for whom closer follow-up and aggressive secondary prevention strategies should be considered. © 2016 American Heart Association, Inc.

An updated PREDICT breast cancer prognostication and treatment benefit prediction model with independent validation.

PubMed

Candido Dos Reis, Francisco J; Wishart, Gordon C; Dicks, Ed M; Greenberg, David; Rashbass, Jem; Schmidt, Marjanka K; van den Broek, Alexandra J; Ellis, Ian O; Green, Andrew; Rakha, Emad; Maishman, Tom; Eccles, Diana M; Pharoah, Paul D P

2017-05-22

PREDICT is a breast cancer prognostic and treatment benefit model implemented online. The overall fit of the model has been good in multiple independent case series, but PREDICT has been shown to underestimate breast cancer specific mortality in women diagnosed under the age of 40. Another limitation is the use of discrete categories for tumour size and node status resulting in 'step' changes in risk estimates on moving between categories. We have refitted the PREDICT prognostic model using the original cohort of cases from East Anglia with updated survival time in order to take into account age at diagnosis and to smooth out the survival function for tumour size and node status. Multivariable Cox regression models were used to fit separate models for ER negative and ER positive disease. Continuous variables were fitted using fractional polynomials and a smoothed baseline hazard was obtained by regressing the baseline cumulative hazard for each patients against time using fractional polynomials. The fit of the prognostic models were then tested in three independent data sets that had also been used to validate the original version of PREDICT. In the model fitting data, after adjusting for other prognostic variables, there is an increase in risk of breast cancer specific mortality in younger and older patients with ER positive disease, with a substantial increase in risk for women diagnosed before the age of 35. In ER negative disease the risk increases slightly with age. The association between breast cancer specific mortality and both tumour size and number of positive nodes was non-linear with a more marked increase in risk with increasing size and increasing number of nodes in ER positive disease. The overall calibration and discrimination of the new version of PREDICT (v2) was good and comparable to that of the previous version in both model development and validation data sets. However, the calibration of v2 improved over v1 in patients diagnosed under the age of 40. The PREDICT v2 is an improved prognostication and treatment benefit model compared with v1. The online version should continue to aid clinical decision making in women with early breast cancer.

Readmission prediction via deep contextual embedding of clinical concepts.

PubMed

Xiao, Cao; Ma, Tengfei; Dieng, Adji B; Blei, David M; Wang, Fei

2018-01-01

Hospital readmission costs a lot of money every year. Many hospital readmissions are avoidable, and excessive hospital readmissions could also be harmful to the patients. Accurate prediction of hospital readmission can effectively help reduce the readmission risk. However, the complex relationship between readmission and potential risk factors makes readmission prediction a difficult task. The main goal of this paper is to explore deep learning models to distill such complex relationships and make accurate predictions. We propose CONTENT, a deep model that predicts hospital readmissions via learning interpretable patient representations by capturing both local and global contexts from patient Electronic Health Records (EHR) through a hybrid Topic Recurrent Neural Network (TopicRNN) model. The experiment was conducted using the EHR of a real world Congestive Heart Failure (CHF) cohort of 5,393 patients. The proposed model outperforms state-of-the-art methods in readmission prediction (e.g. 0.6103 ± 0.0130 vs. second best 0.5998 ± 0.0124 in terms of ROC-AUC). The derived patient representations were further utilized for patient phenotyping. The learned phenotypes provide more precise understanding of readmission risks. Embedding both local and global context in patient representation not only improves prediction performance, but also brings interpretable insights of understanding readmission risks for heterogeneous chronic clinical conditions. This is the first of its kind model that integrates the power of both conventional deep neural network and the probabilistic generative models for highly interpretable deep patient representation learning. Experimental results and case studies demonstrate the improved performance and interpretability of the model.

Failure prediction using machine learning and time series in optical network.

PubMed

Wang, Zhilong; Zhang, Min; Wang, Danshi; Song, Chuang; Liu, Min; Li, Jin; Lou, Liqi; Liu, Zhuo

2017-08-07

In this paper, we propose a performance monitoring and failure prediction method in optical networks based on machine learning. The primary algorithms of this method are the support vector machine (SVM) and double exponential smoothing (DES). With a focus on risk-aware models in optical networks, the proposed protection plan primarily investigates how to predict the risk of an equipment failure. To the best of our knowledge, this important problem has not yet been fully considered. Experimental results showed that the average prediction accuracy of our method was 95% when predicting the optical equipment failure state. This finding means that our method can forecast an equipment failure risk with high accuracy. Therefore, our proposed DES-SVM method can effectively improve traditional risk-aware models to protect services from possible failures and enhance the optical network stability.

Assessment of a remote sensing-based model for predicting malaria transmission risk in villages of Chiapas, Mexico

NASA Technical Reports Server (NTRS)

Beck, L. R.; Rodriguez, M. H.; Dister, S. W.; Rodriguez, A. D.; Washino, R. K.; Roberts, D. R.; Spanner, M. A.

1997-01-01

A blind test of two remote sensing-based models for predicting adult populations of Anopheles albimanus in villages, an indicator of malaria transmission risk, was conducted in southern Chiapas, Mexico. One model was developed using a discriminant analysis approach, while the other was based on regression analysis. The models were developed in 1992 for an area around Tapachula, Chiapas, using Landsat Thematic Mapper (TM) satellite data and geographic information system functions. Using two remotely sensed landscape elements, the discriminant model was able to successfully distinguish between villages with high and low An. albimanus abundance with an overall accuracy of 90%. To test the predictive capability of the models, multitemporal TM data were used to generate a landscape map of the Huixtla area, northwest of Tapachula, where the models were used to predict risk for 40 villages. The resulting predictions were not disclosed until the end of the test. Independently, An. albimanus abundance data were collected in the 40 randomly selected villages for which the predictions had been made. These data were subsequently used to assess the models' accuracies. The discriminant model accurately predicted 79% of the high-abundance villages and 50% of the low-abundance villages, for an overall accuracy of 70%. The regression model correctly identified seven of the 10 villages with the highest mosquito abundance. This test demonstrated that remote sensing-based models generated for one area can be used successfully in another, comparable area.

Risk prediction models for selection of lung cancer screening candidates: A retrospective validation study

PubMed Central

ten Haaf, Kevin; Tammemägi, Martin C.; Han, Summer S.; Kong, Chung Yin; Plevritis, Sylvia K.; de Koning, Harry J.; Steyerberg, Ewout W.

2017-01-01

Background Selection of candidates for lung cancer screening based on individual risk has been proposed as an alternative to criteria based on age and cumulative smoking exposure (pack-years). Nine previously established risk models were assessed for their ability to identify those most likely to develop or die from lung cancer. All models considered age and various aspects of smoking exposure (smoking status, smoking duration, cigarettes per day, pack-years smoked, time since smoking cessation) as risk predictors. In addition, some models considered factors such as gender, race, ethnicity, education, body mass index, chronic obstructive pulmonary disease, emphysema, personal history of cancer, personal history of pneumonia, and family history of lung cancer. Methods and findings Retrospective analyses were performed on 53,452 National Lung Screening Trial (NLST) participants (1,925 lung cancer cases and 884 lung cancer deaths) and 80,672 Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial (PLCO) ever-smoking participants (1,463 lung cancer cases and 915 lung cancer deaths). Six-year lung cancer incidence and mortality risk predictions were assessed for (1) calibration (graphically) by comparing the agreement between the predicted and the observed risks, (2) discrimination (area under the receiver operating characteristic curve [AUC]) between individuals with and without lung cancer (death), and (3) clinical usefulness (net benefit in decision curve analysis) by identifying risk thresholds at which applying risk-based eligibility would improve lung cancer screening efficacy. To further assess performance, risk model sensitivities and specificities in the PLCO were compared to those based on the NLST eligibility criteria. Calibration was satisfactory, but discrimination ranged widely (AUCs from 0.61 to 0.81). The models outperformed the NLST eligibility criteria over a substantial range of risk thresholds in decision curve analysis, with a higher sensitivity for all models and a slightly higher specificity for some models. The PLCOm2012, Bach, and Two-Stage Clonal Expansion incidence models had the best overall performance, with AUCs >0.68 in the NLST and >0.77 in the PLCO. These three models had the highest sensitivity and specificity for predicting 6-y lung cancer incidence in the PLCO chest radiography arm, with sensitivities >79.8% and specificities >62.3%. In contrast, the NLST eligibility criteria yielded a sensitivity of 71.4% and a specificity of 62.2%. Limitations of this study include the lack of identification of optimal risk thresholds, as this requires additional information on the long-term benefits (e.g., life-years gained and mortality reduction) and harms (e.g., overdiagnosis) of risk-based screening strategies using these models. In addition, information on some predictor variables included in the risk prediction models was not available. Conclusions Selection of individuals for lung cancer screening using individual risk is superior to selection criteria based on age and pack-years alone. The benefits, harms, and feasibility of implementing lung cancer screening policies based on risk prediction models should be assessed and compared with those of current recommendations. PMID:28376113

A risk prediction model for xerostomia: a retrospective cohort study.

PubMed

Villa, Alessandro; Nordio, Francesco; Gohel, Anita

2016-12-01

We investigated the prevalence of xerostomia in dental patients and built a xerostomia risk prediction model by incorporating a wide range of risk factors. Socio-demographic data, past medical history, self-reported dry mouth and related symptoms were collected retrospectively from January 2010 to September 2013 for all new dental patients. A logistic regression framework was used to build a risk prediction model for xerostomia. External validation was performed using an independent data set to test the prediction power. A total of 12 682 patients were included in this analysis (54.3%, females). Xerostomia was reported by 12.2% of patients. The proportion of people reporting xerostomia was higher among those who were taking more medications (OR = 1.11, 95% CI = 1.08-1.13) or recreational drug users (OR = 1.4, 95% CI = 1.1-1.9). Rheumatic diseases (OR = 2.17, 95% CI = 1.88-2.51), psychiatric diseases (OR = 2.34, 95% CI = 2.05-2.68), eating disorders (OR = 2.28, 95% CI = 1.55-3.36) and radiotherapy (OR = 2.00, 95% CI = 1.43-2.80) were good predictors of xerostomia. For the test model performance, the ROC-AUC was 0.816 and in the external validation sample, the ROC-AUC was 0.799. The xerostomia risk prediction model had high accuracy and discriminated between high- and low-risk individuals. Clinicians could use this model to identify the classes of medications and systemic diseases associated with xerostomia. © 2015 John Wiley & Sons A/S and The Gerodontology Association. Published by John Wiley & Sons Ltd.

Improving coeliac disease risk prediction by testing non-HLA variants additional to HLA variants.

PubMed

Romanos, Jihane; Rosén, Anna; Kumar, Vinod; Trynka, Gosia; Franke, Lude; Szperl, Agata; Gutierrez-Achury, Javier; van Diemen, Cleo C; Kanninga, Roan; Jankipersadsing, Soesma A; Steck, Andrea; Eisenbarth, Georges; van Heel, David A; Cukrowska, Bozena; Bruno, Valentina; Mazzilli, Maria Cristina; Núñez, Concepcion; Bilbao, Jose Ramon; Mearin, M Luisa; Barisani, Donatella; Rewers, Marian; Norris, Jill M; Ivarsson, Anneli; Boezen, H Marieke; Liu, Edwin; Wijmenga, Cisca

2014-03-01

The majority of coeliac disease (CD) patients are not being properly diagnosed and therefore remain untreated, leading to a greater risk of developing CD-associated complications. The major genetic risk heterodimer, HLA-DQ2 and DQ8, is already used clinically to help exclude disease. However, approximately 40% of the population carry these alleles and the majority never develop CD. We explored whether CD risk prediction can be improved by adding non-HLA-susceptible variants to common HLA testing. We developed an average weighted genetic risk score with 10, 26 and 57 single nucleotide polymorphisms (SNP) in 2675 cases and 2815 controls and assessed the improvement in risk prediction provided by the non-HLA SNP. Moreover, we assessed the transferability of the genetic risk model with 26 non-HLA variants to a nested case-control population (n=1709) and a prospective cohort (n=1245) and then tested how well this model predicted CD outcome for 985 independent individuals. Adding 57 non-HLA variants to HLA testing showed a statistically significant improvement compared to scores from models based on HLA only, HLA plus 10 SNP and HLA plus 26 SNP. With 57 non-HLA variants, the area under the receiver operator characteristic curve reached 0.854 compared to 0.823 for HLA only, and 11.1% of individuals were reclassified to a more accurate risk group. We show that the risk model with HLA plus 26 SNP is useful in independent populations. Predicting risk with 57 additional non-HLA variants improved the identification of potential CD patients. This demonstrates a possible role for combined HLA and non-HLA genetic testing in diagnostic work for CD.

How to make predictions about future infectious disease risks

PubMed Central

Woolhouse, Mark

2011-01-01

Formal, quantitative approaches are now widely used to make predictions about the likelihood of an infectious disease outbreak, how the disease will spread, and how to control it. Several well-established methodologies are available, including risk factor analysis, risk modelling and dynamic modelling. Even so, predictive modelling is very much the ‘art of the possible’, which tends to drive research effort towards some areas and away from others which may be at least as important. Building on the undoubted success of quantitative modelling of the epidemiology and control of human and animal diseases such as AIDS, influenza, foot-and-mouth disease and BSE, attention needs to be paid to developing a more holistic framework that captures the role of the underlying drivers of disease risks, from demography and behaviour to land use and climate change. At the same time, there is still considerable room for improvement in how quantitative analyses and their outputs are communicated to policy makers and other stakeholders. A starting point would be generally accepted guidelines for ‘good practice’ for the development and the use of predictive models. PMID:21624924

Pre-operative prediction of surgical morbidity in children: comparison of five statistical models.

PubMed

Cooper, Jennifer N; Wei, Lai; Fernandez, Soledad A; Minneci, Peter C; Deans, Katherine J

2015-02-01

The accurate prediction of surgical risk is important to patients and physicians. Logistic regression (LR) models are typically used to estimate these risks. However, in the fields of data mining and machine-learning, many alternative classification and prediction algorithms have been developed. This study aimed to compare the performance of LR to several data mining algorithms for predicting 30-day surgical morbidity in children. We used the 2012 National Surgical Quality Improvement Program-Pediatric dataset to compare the performance of (1) a LR model that assumed linearity and additivity (simple LR model) (2) a LR model incorporating restricted cubic splines and interactions (flexible LR model) (3) a support vector machine, (4) a random forest and (5) boosted classification trees for predicting surgical morbidity. The ensemble-based methods showed significantly higher accuracy, sensitivity, specificity, PPV, and NPV than the simple LR model. However, none of the models performed better than the flexible LR model in terms of the aforementioned measures or in model calibration or discrimination. Support vector machines, random forests, and boosted classification trees do not show better performance than LR for predicting pediatric surgical morbidity. After further validation, the flexible LR model derived in this study could be used to assist with clinical decision-making based on patient-specific surgical risks. Copyright © 2014 Elsevier Ltd. All rights reserved.

Assessment of the Ability of Contemporary Climate Models to Assess Adequately the Risk of Possible Regional Anomalies and Trends

NASA Astrophysics Data System (ADS)

Mokhov, I. I.

2018-04-01

The results describing the ability of contemporary global and regional climate models not only to assess the risk of general trends of changes but also to predict qualitatively new regional effects are presented. In particular, model simulations predicted spatially inhomogeneous changes in the wind and wave conditions in the Arctic basins, which have been confirmed in recent years. According to satellite and reanalysis data, a qualitative transition to the regime predicted by model simulations occurred about a decade ago.

Testing a hydraulic trait based model of stomatal control: results from a controlled drought experiment on aspen (Populus tremuloides, Michx.) and ponderosa pine (Pinus ponderosa, Douglas)

NASA Astrophysics Data System (ADS)

Love, D. M.; Venturas, M.; Sperry, J.; Wang, Y.; Anderegg, W.

2017-12-01

Modeling approaches for tree stomatal control often rely on empirical fitting to provide accurate estimates of whole tree transpiration (E) and assimilation (A), which are limited in their predictive power by the data envelope used to calibrate model parameters. Optimization based models hold promise as a means to predict stomatal behavior under novel climate conditions. We designed an experiment to test a hydraulic trait based optimization model, which predicts stomatal conductance from a gain/risk approach. Optimal stomatal conductance is expected to maximize the potential carbon gain by photosynthesis, and minimize the risk to hydraulic transport imposed by cavitation. The modeled risk to the hydraulic network is assessed from cavitation vulnerability curves, a commonly measured physiological trait in woody plant species. Over a growing season garden grown plots of aspen (Populus tremuloides, Michx.) and ponderosa pine (Pinus ponderosa, Douglas) were subjected to three distinct drought treatments (moderate, severe, severe with rehydration) relative to a control plot to test model predictions. Model outputs of predicted E, A, and xylem pressure can be directly compared to both continuous data (whole tree sapflux, soil moisture) and point measurements (leaf level E, A, xylem pressure). The model also predicts levels of whole tree hydraulic impairment expected to increase mortality risk. This threshold is used to estimate survivorship in the drought treatment plots. The model can be run at two scales, either entirely from climate (meteorological inputs, irrigation) or using the physiological measurements as a starting point. These data will be used to study model performance and utility, and aid in developing the model for larger scale applications.

FOOD RISK ANALYSIS

USDA-ARS?s Scientific Manuscript database

Food risk analysis is a holistic approach to food safety because it considers all aspects of the problem. Risk assessment modeling is the foundation of food risk analysis. Proper design and simulation of the risk assessment model is important to properly predict and control risk. Because of knowl...

Modelling the influence of predicted future climate change on the risk of wind damage within New Zealand's planted forests.

PubMed

Moore, John R; Watt, Michael S

2015-08-01

Wind is the major abiotic disturbance in New Zealand's planted forests, but little is known about how the risk of wind damage may be affected by future climate change. We linked a mechanistic wind damage model (ForestGALES) to an empirical growth model for radiata pine (Pinus radiata D. Don) and a process-based growth model (cenw) to predict the risk of wind damage under different future emissions scenarios and assumptions about the future wind climate. The cenw model was used to estimate site productivity for constant CO2 concentration at 1990 values and for assumed increases in CO2 concentration from current values to those expected during 2040 and 2090 under the B1 (low), A1B (mid-range) and A2 (high) emission scenarios. Stand development was modelled for different levels of site productivity, contrasting silvicultural regimes and sites across New Zealand. The risk of wind damage was predicted for each regime and emission scenario combination using the ForestGALES model. The sensitivity to changes in the intensity of the future wind climate was also examined. Results showed that increased tree growth rates under the different emissions scenarios had the greatest impact on the risk of wind damage. The increase in risk was greatest for stands growing at high stand density under the A2 emissions scenario with increased CO2 concentration. The increased productivity under this scenario resulted in increased tree height, without a corresponding increase in diameter, leading to more slender trees that were predicted to be at greater risk from wind damage. The risk of wind damage was further increased by the modest increases in the extreme wind climate that are predicted to occur. These results have implications for the development of silvicultural regimes that are resilient to climate change and also indicate that future productivity gains may be offset by greater losses from disturbances. © 2015 John Wiley & Sons Ltd.

A Field Synopsis of Sex in Clinical Prediction Models for Cardiovascular Disease

PubMed Central

Paulus, Jessica K.; Wessler, Benjamin S.; Lundquist, Christine; Lai, Lana L.Y.; Raman, Gowri; Lutz, Jennifer S.; Kent, David M.

2017-01-01

Background Several widely-used risk scores for cardiovascular disease (CVD) incorporate sex effects, yet there has been no systematic summary of the role of sex in clinical prediction models (CPMs). To better understand the potential of these models to support sex-specific care, we conducted a field synopsis of sex effects in CPMs for CVD. Methods and Results We identified CPMs in the Tufts Predictive Analytics and Comparative Effectiveness (PACE) CPM Registry, a comprehensive database of CVD CPMs published from 1/1990–5/2012. We report the proportion of models including sex effects on CVD incidence or prognosis, summarize the directionality of the predictive effects of sex, and explore factors influencing the inclusion of sex. Of 592 CVD-related CPMs, 193 (33%) included sex as a predictor or presented sex-stratified models. Sex effects were included in 78% (53/68) of models predicting incidence of CVD in a general population, versus only 35% (59/171), 21% (12/58) and 17% (12/72) of models predicting outcomes in patients with coronary artery disease (CAD), stroke, and heart failure, respectively. Among sex-including CPMs, women with heart failure were at lower mortality risk in 8/8 models; women undergoing revascularization for CAD were at higher mortality risk in 10/12 models. Factors associated with the inclusion of sex effects included the number of outcome events and using cohorts at-risk for CVD (rather than with established CVD). Conclusions While CPMs hold promise for supporting sex-specific decision making in CVD clinical care, sex effects are included in only one third of published CPMs. PMID:26908865

XplOit: An Ontology-Based Data Integration Platform Supporting the Development of Predictive Models for Personalized Medicine.

PubMed

Weiler, Gabriele; Schwarz, Ulf; Rauch, Jochen; Rohm, Kerstin; Lehr, Thorsten; Theobald, Stefan; Kiefer, Stephan; Götz, Katharina; Och, Katharina; Pfeifer, Nico; Handl, Lisa; Smola, Sigrun; Ihle, Matthias; Turki, Amin T; Beelen, Dietrich W; Rissland, Jürgen; Bittenbring, Jörg; Graf, Norbert

2018-01-01

Predictive models can support physicians to tailor interventions and treatments to their individual patients based on their predicted response and risk of disease and help in this way to put personalized medicine into practice. In allogeneic stem cell transplantation risk assessment is to be enhanced in order to respond to emerging viral infections and transplantation reactions. However, to develop predictive models it is necessary to harmonize and integrate high amounts of heterogeneous medical data that is stored in different health information systems. Driven by the demand for predictive instruments in allogeneic stem cell transplantation we present in this paper an ontology-based platform that supports data owners and model developers to share and harmonize their data for model development respecting data privacy.

Development of Rock Engineering Systems-Based Models for Flyrock Risk Analysis and Prediction of Flyrock Distance in Surface Blasting

NASA Astrophysics Data System (ADS)

Faramarzi, Farhad; Mansouri, Hamid; Farsangi, Mohammad Ali Ebrahimi

2014-07-01

The environmental effects of blasting must be controlled in order to comply with regulatory limits. Because of safety concerns and risk of damage to infrastructures, equipment, and property, and also having a good fragmentation, flyrock control is crucial in blasting operations. If measures to decrease flyrock are taken, then the flyrock distance would be limited, and, in return, the risk of damage can be reduced or eliminated. This paper deals with modeling the level of risk associated with flyrock and, also, flyrock distance prediction based on the rock engineering systems (RES) methodology. In the proposed models, 13 effective parameters on flyrock due to blasting are considered as inputs, and the flyrock distance and associated level of risks as outputs. In selecting input data, the simplicity of measuring input data was taken into account as well. The data for 47 blasts, carried out at the Sungun copper mine, western Iran, were used to predict the level of risk and flyrock distance corresponding to each blast. The obtained results showed that, for the 47 blasts carried out at the Sungun copper mine, the level of estimated risks are mostly in accordance with the measured flyrock distances. Furthermore, a comparison was made between the results of the flyrock distance predictive RES-based model, the multivariate regression analysis model (MVRM), and, also, the dimensional analysis model. For the RES-based model, R 2 and root mean square error (RMSE) are equal to 0.86 and 10.01, respectively, whereas for the MVRM and dimensional analysis, R 2 and RMSE are equal to (0.84 and 12.20) and (0.76 and 13.75), respectively. These achievements confirm the better performance of the RES-based model over the other proposed models.

Validation of the CRASH model in the prediction of 18-month mortality and unfavorable outcome in severe traumatic brain injury requiring decompressive craniectomy.

PubMed

Honeybul, Stephen; Ho, Kwok M; Lind, Christopher R P; Gillett, Grant R

2014-05-01

The goal in this study was to assess the validity of the corticosteroid randomization after significant head injury (CRASH) collaborators prediction model in predicting mortality and unfavorable outcome at 18 months in patients with severe traumatic brain injury (TBI) requiring decompressive craniectomy. In addition, the authors aimed to assess whether this model was well calibrated in predicting outcome across a wide spectrum of severity of TBI requiring decompressive craniectomy. This prospective observational cohort study included all patients who underwent a decompressive craniectomy following severe TBI at the two major trauma hospitals in Western Australia between 2004 and 2012 and for whom 18-month follow-up data were available. Clinical and radiological data on initial presentation were entered into the Web-based model and the predicted outcome was compared with the observed outcome. In validating the CRASH model, the authors used area under the receiver operating characteristic curve to assess the ability of the CRASH model to differentiate between favorable and unfavorable outcomes. The ability of the CRASH 6-month unfavorable prediction model to differentiate between unfavorable and favorable outcomes at 18 months after decompressive craniectomy was good (area under the receiver operating characteristic curve 0.85, 95% CI 0.80-0.90). However, the model's calibration was not perfect. The slope and the intercept of the calibration curve were 1.66 (SE 0.21) and -1.11 (SE 0.14), respectively, suggesting that the predicted risks of unfavorable outcomes were not sufficiently extreme or different across different risk strata and were systematically too high (or overly pessimistic), respectively. The CRASH collaborators prediction model can be used as a surrogate index of injury severity to stratify patients according to injury severity. However, clinical decisions should not be based solely on the predicted risks derived from the model, because the number of patients in each predicted risk stratum was still relatively small and hence the results were relatively imprecise. Notwithstanding these limitations, the model may add to a clinician's ability to have better-informed conversations with colleagues and patients' relatives about prognosis.

Construction of a model predicting the risk of tube feeding intolerance after gastrectomy for gastric cancer based on 225 cases from a single Chinese center

PubMed Central

Xiaoyong, Wu; Xuzhao, Li; Deliang, Yu; Pengfei, Yu; Zhenning, Hang; Bin, Bai; zhengyan, Li; Fangning, Pang; Shiqi, Wang; Qingchuan, Zhao

2017-01-01

Identifying patients at high risk of tube feeding intolerance (TFI) after gastric cancer surgery may prevent the occurrence of TFI; however, a predictive model is lacking. We therefore analyzed the incidence of TFI and its associated risk factors after gastric cancer surgery in 225 gastric cancer patients divided into without-TFI (n = 114) and with-TFI (n = 111) groups. A total of 49.3% of patients experienced TFI after gastric cancer. Multivariate analysis identified a history of functional constipation (FC), a preoperative American Society of Anesthesiologists (ASA) score of III, a high pain score at 6-hour postoperation, and a high white blood cell (WBC) count on the first day after surgery as independent risk factors for TFI. The area under the curve (AUC) was 0.756, with an optimal cut-off value of 0.5410. In order to identify patients at high risk of TFI after gastric cancer surgery, we constructed a predictive nomogram model based on the selected independent risk factors to indicate the probability of developing TFI. Use of our predictive nomogram model in screening, if a probability > 0.5410, indicated a high-risk patients would with a 70.1% likelihood of developing TFI. These high-risk individuals should take measures to prevent TFI before feeding with enteral nutrition. PMID:29245951

An initial investigation on developing a new method to predict short-term breast cancer risk based on deep learning technology

NASA Astrophysics Data System (ADS)

Qiu, Yuchen; Wang, Yunzhi; Yan, Shiju; Tan, Maxine; Cheng, Samuel; Liu, Hong; Zheng, Bin

2016-03-01

In order to establish a new personalized breast cancer screening paradigm, it is critically important to accurately predict the short-term risk of a woman having image-detectable cancer after a negative mammographic screening. In this study, we developed and tested a novel short-term risk assessment model based on deep learning method. During the experiment, a number of 270 "prior" negative screening cases was assembled. In the next sequential ("current") screening mammography, 135 cases were positive and 135 cases remained negative. These cases were randomly divided into a training set with 200 cases and a testing set with 70 cases. A deep learning based computer-aided diagnosis (CAD) scheme was then developed for the risk assessment, which consists of two modules: adaptive feature identification module and risk prediction module. The adaptive feature identification module is composed of three pairs of convolution-max-pooling layers, which contains 20, 10, and 5 feature maps respectively. The risk prediction module is implemented by a multiple layer perception (MLP) classifier, which produces a risk score to predict the likelihood of the woman developing short-term mammography-detectable cancer. The result shows that the new CAD-based risk model yielded a positive predictive value of 69.2% and a negative predictive value of 74.2%, with a total prediction accuracy of 71.4%. This study demonstrated that applying a new deep learning technology may have significant potential to develop a new short-term risk predicting scheme with improved performance in detecting early abnormal symptom from the negative mammograms.

Risk and the physics of clinical prediction.

PubMed

McEvoy, John W; Diamond, George A; Detrano, Robert C; Kaul, Sanjay; Blaha, Michael J; Blumenthal, Roger S; Jones, Steven R

2014-04-15

The current paradigm of primary prevention in cardiology uses traditional risk factors to estimate future cardiovascular risk. These risk estimates are based on prediction models derived from prospective cohort studies and are incorporated into guideline-based initiation algorithms for commonly used preventive pharmacologic treatments, such as aspirin and statins. However, risk estimates are more accurate for populations of similar patients than they are for any individual patient. It may be hazardous to presume that the point estimate of risk derived from a population model represents the most accurate estimate for a given patient. In this review, we exploit principles derived from physics as a metaphor for the distinction between predictions regarding populations versus patients. We identify the following: (1) predictions of risk are accurate at the level of populations but do not translate directly to patients, (2) perfect accuracy of individual risk estimation is unobtainable even with the addition of multiple novel risk factors, and (3) direct measurement of subclinical disease (screening) affords far greater certainty regarding the personalized treatment of patients, whereas risk estimates often remain uncertain for patients. In conclusion, shifting our focus from prediction of events to detection of disease could improve personalized decision-making and outcomes. We also discuss innovative future strategies for risk estimation and treatment allocation in preventive cardiology. Copyright © 2014 Elsevier Inc. All rights reserved.

Comparison between Frailty Index of Deficit Accumulation and Phenotypic Model to Predict Risk of Falls: Data from the Global Longitudinal Study of Osteoporosis in Women (GLOW) Hamilton Cohort

PubMed Central

Thabane, Lehana; Ioannidis, George; Kennedy, Courtney; Papaioannou, Alexandra

2015-01-01

Objectives To compare the predictive accuracy of the frailty index (FI) of deficit accumulation and the phenotypic frailty (PF) model in predicting risks of future falls, fractures and death in women aged ≥55 years. Methods Based on the data from the Global Longitudinal Study of Osteoporosis in Women (GLOW) 3-year Hamilton cohort (n = 3,985), we compared the predictive accuracy of the FI and PF in risks of falls, fractures and death using three strategies: (1) investigated the relationship with adverse health outcomes by increasing per one-fifth (i.e., 20%) of the FI and PF; (2) trichotomized the FI based on the overlap in the density distribution of the FI by the three groups (robust, pre-frail and frail) which were defined by the PF; (3) categorized the women according to a predicted probability function of falls during the third year of follow-up predicted by the FI. Logistic regression models were used for falls and death, while survival analyses were conducted for fractures. Results The FI and PF agreed with each other at a good level of consensus (correlation coefficients ≥ 0.56) in all the three strategies. Both the FI and PF approaches predicted adverse health outcomes significantly. The FI quantified the risks of future falls, fractures and death more precisely than the PF. Both the FI and PF discriminated risks of adverse outcomes in multivariable models with acceptable and comparable area under the curve (AUCs) for falls (AUCs ≥ 0.68) and death (AUCs ≥ 0.79), and c-indices for fractures (c-indices ≥ 0.69) respectively. Conclusions The FI is comparable with the PF in predicting risks of adverse health outcomes. These findings may indicate the flexibility in the choice of frailty model for the elderly in the population-based settings. PMID:25764521

Comparison between frailty index of deficit accumulation and phenotypic model to predict risk of falls: data from the global longitudinal study of osteoporosis in women (GLOW) Hamilton cohort.

PubMed

Li, Guowei; Thabane, Lehana; Ioannidis, George; Kennedy, Courtney; Papaioannou, Alexandra; Adachi, Jonathan D

2015-01-01

To compare the predictive accuracy of the frailty index (FI) of deficit accumulation and the phenotypic frailty (PF) model in predicting risks of future falls, fractures and death in women aged ≥55 years. Based on the data from the Global Longitudinal Study of Osteoporosis in Women (GLOW) 3-year Hamilton cohort (n = 3,985), we compared the predictive accuracy of the FI and PF in risks of falls, fractures and death using three strategies: (1) investigated the relationship with adverse health outcomes by increasing per one-fifth (i.e., 20%) of the FI and PF; (2) trichotomized the FI based on the overlap in the density distribution of the FI by the three groups (robust, pre-frail and frail) which were defined by the PF; (3) categorized the women according to a predicted probability function of falls during the third year of follow-up predicted by the FI. Logistic regression models were used for falls and death, while survival analyses were conducted for fractures. The FI and PF agreed with each other at a good level of consensus (correlation coefficients ≥ 0.56) in all the three strategies. Both the FI and PF approaches predicted adverse health outcomes significantly. The FI quantified the risks of future falls, fractures and death more precisely than the PF. Both the FI and PF discriminated risks of adverse outcomes in multivariable models with acceptable and comparable area under the curve (AUCs) for falls (AUCs ≥ 0.68) and death (AUCs ≥ 0.79), and c-indices for fractures (c-indices ≥ 0.69) respectively. The FI is comparable with the PF in predicting risks of adverse health outcomes. These findings may indicate the flexibility in the choice of frailty model for the elderly in the population-based settings.

Neonatal Candidiasis: Epidemiology, Risk Factors, and Clinical Judgment

PubMed Central

Benjamin, Daniel K.; Stoll, Barbara J.; Gantz, Marie G.; Walsh, Michele C.; Sanchez, Pablo J.; Das, Abhik; Shankaran, Seetha; Higgins, Rosemary D.; Auten, Kathy J.; Miller, Nancy A.; Walsh, Thomas J.; Laptook, Abbot R.; Carlo, Waldemar A.; Kennedy, Kathleen A.; Finer, Neil N.; Duara, Shahnaz; Schibler, Kurt; Chapman, Rachel L.; Van Meurs, Krisa P.; Frantz, Ivan D.; Phelps, Dale L.; Poindexter, Brenda B.; Bell, Edward F.; O’Shea, T. Michael; Watterberg, Kristi L.; Goldberg, Ronald N.

2011-01-01

OBJECTIVE Invasive candidiasis is a leading cause of infection-related morbidity and mortality in extremely low-birth-weight (<1000 g) infants. We quantify risk factors predicting infection in high-risk premature infants and compare clinical judgment with a prediction model of invasive candidiasis. METHODS The study involved a prospective observational cohort of infants <1000 g birth weight at 19 centers of the NICHD Neonatal Research Network. At each sepsis evaluation, clinical information was recorded, cultures obtained, and clinicians prospectively recorded their estimate of the probability of invasive candidiasis. Two models were generated with invasive candidiasis as their outcome: 1) potentially modifiable risk factors and 2) a clinical model at time of blood culture to predict candidiasis. RESULTS Invasive candidiasis occurred in 137/1515 (9.0%) infants and was documented by positive culture from ≥ 1 of these sources: blood (n=96), cerebrospinal fluid (n=9), urine obtained by catheterization (n=52), or other sterile body fluid (n=10). Mortality was not different from infants who had positive blood culture compared to those with isolated positive urine culture. Incidence varied from 2–28% at the 13 centers enrolling ≥ 50 infants. Potentially modifiable risk factors (model 1) included central catheter, broad-spectrum antibiotics (e.g., third-generation cephalosporins), intravenous lipid emulsion, endotracheal tube, and antenatal antibiotics. The clinical prediction model (model 2) had an area under the receiver operating characteristic curve of 0.79, and was superior to clinician judgment (0.70) in predicting subsequent invasive candidiasis. Performance of clinical judgment did not vary significantly with level of training. CONCLUSION Prior antibiotics, presence of a central catheter, endotracheal tube, and center were strongly associated with invasive candidiasis. Modeling was more accurate in predicting invasive candidiasis than clinical judgment. PMID:20876174

Application of discriminant analysis-based model for prediction of risk of low back disorders due to workplace design in industrial jobs.

PubMed

Ganga, G M D; Esposto, K F; Braatz, D

2012-01-01

The occupational exposure limits of different risk factors for development of low back disorders (LBDs) have not yet been established. One of the main problems in setting such guidelines is the limited understanding of how different risk factors for LBDs interact in causing injury, since the nature and mechanism of these disorders are relatively unknown phenomena. Industrial ergonomists' role becomes further complicated because the potential risk factors that may contribute towards the onset of LBDs interact in a complex manner, which makes it difficult to discriminate in detail among the jobs that place workers at high or low risk of LBDs. The purpose of this paper was to develop a comparative study between predictions based on the neural network-based model proposed by Zurada, Karwowski & Marras (1997) and a linear discriminant analysis model, for making predictions about industrial jobs according to their potential risk of low back disorders due to workplace design. The results obtained through applying the discriminant analysis-based model proved that it is as effective as the neural network-based model. Moreover, the discriminant analysis-based model proved to be more advantageous regarding cost and time savings for future data gathering.

Population-based absolute risk estimation with survey data

PubMed Central

Kovalchik, Stephanie A.; Pfeiffer, Ruth M.

2013-01-01

Absolute risk is the probability that a cause-specific event occurs in a given time interval in the presence of competing events. We present methods to estimate population-based absolute risk from a complex survey cohort that can accommodate multiple exposure-specific competing risks. The hazard function for each event type consists of an individualized relative risk multiplied by a baseline hazard function, which is modeled nonparametrically or parametrically with a piecewise exponential model. An influence method is used to derive a Taylor-linearized variance estimate for the absolute risk estimates. We introduce novel measures of the cause-specific influences that can guide modeling choices for the competing event components of the model. To illustrate our methodology, we build and validate cause-specific absolute risk models for cardiovascular and cancer deaths using data from the National Health and Nutrition Examination Survey. Our applications demonstrate the usefulness of survey-based risk prediction models for predicting health outcomes and quantifying the potential impact of disease prevention programs at the population level. PMID:23686614

An RES-Based Model for Risk Assessment and Prediction of Backbreak in Bench Blasting

NASA Astrophysics Data System (ADS)

Faramarzi, F.; Ebrahimi Farsangi, M. A.; Mansouri, H.

2013-07-01

Most blasting operations are associated with various forms of energy loss, emerging as environmental side effects of rock blasting, such as flyrock, vibration, airblast, and backbreak. Backbreak is an adverse phenomenon in rock blasting operations, which imposes risk and increases operation expenses because of safety reduction due to the instability of walls, poor fragmentation, and uneven burden in subsequent blasts. In this paper, based on the basic concepts of a rock engineering systems (RES) approach, a new model for the prediction of backbreak and the risk associated with a blast is presented. The newly suggested model involves 16 effective parameters on backbreak due to blasting, while retaining simplicity as well. The data for 30 blasts, carried out at Sungun copper mine, western Iran, were used to predict backbreak and the level of risk corresponding to each blast by the RES-based model. The results obtained were compared with the backbreak measured for each blast, which showed that the level of risk achieved is in consistence with the backbreak measured. The maximum level of risk [vulnerability index (VI) = 60] was associated with blast No. 2, for which the corresponding average backbreak was the highest achieved (9.25 m). Also, for blasts with levels of risk under 40, the minimum average backbreaks (<4 m) were observed. Furthermore, to evaluate the model performance for backbreak prediction, the coefficient of correlation ( R 2) and root mean square error (RMSE) of the model were calculated ( R 2 = 0.8; RMSE = 1.07), indicating the good performance of the model.

Using the weighted area under the net benefit curve for decision curve analysis.

PubMed

Talluri, Rajesh; Shete, Sanjay

2016-07-18

Risk prediction models have been proposed for various diseases and are being improved as new predictors are identified. A major challenge is to determine whether the newly discovered predictors improve risk prediction. Decision curve analysis has been proposed as an alternative to the area under the curve and net reclassification index to evaluate the performance of prediction models in clinical scenarios. The decision curve computed using the net benefit can evaluate the predictive performance of risk models at a given or range of threshold probabilities. However, when the decision curves for 2 competing models cross in the range of interest, it is difficult to identify the best model as there is no readily available summary measure for evaluating the predictive performance. The key deterrent for using simple measures such as the area under the net benefit curve is the assumption that the threshold probabilities are uniformly distributed among patients. We propose a novel measure for performing decision curve analysis. The approach estimates the distribution of threshold probabilities without the need of additional data. Using the estimated distribution of threshold probabilities, the weighted area under the net benefit curve serves as the summary measure to compare risk prediction models in a range of interest. We compared 3 different approaches, the standard method, the area under the net benefit curve, and the weighted area under the net benefit curve. Type 1 error and power comparisons demonstrate that the weighted area under the net benefit curve has higher power compared to the other methods. Several simulation studies are presented to demonstrate the improvement in model comparison using the weighted area under the net benefit curve compared to the standard method. The proposed measure improves decision curve analysis by using the weighted area under the curve and thereby improves the power of the decision curve analysis to compare risk prediction models in a clinical scenario.

Livestock Helminths in a Changing Climate: Approaches and Restrictions to Meaningful Predictions

PubMed Central

Fox, Naomi J.; Marion, Glenn; Davidson, Ross S.; White, Piran C. L.; Hutchings, Michael R.

2012-01-01

Simple Summary Parasitic helminths represent one of the most pervasive challenges to livestock, and their intensity and distribution will be influenced by climate change. There is a need for long-term predictions to identify potential risks and highlight opportunities for control. We explore the approaches to modelling future helminth risk to livestock under climate change. One of the limitations to model creation is the lack of purpose driven data collection. We also conclude that models need to include a broad view of the livestock system to generate meaningful predictions. Abstract Climate change is a driving force for livestock parasite risk. This is especially true for helminths including the nematodes Haemonchus contortus, Teladorsagia circumcincta, Nematodirus battus, and the trematode Fasciola hepatica, since survival and development of free-living stages is chiefly affected by temperature and moisture. The paucity of long term predictions of helminth risk under climate change has driven us to explore optimal modelling approaches and identify current bottlenecks to generating meaningful predictions. We classify approaches as correlative or mechanistic, exploring their strengths and limitations. Climate is one aspect of a complex system and, at the farm level, husbandry has a dominant influence on helminth transmission. Continuing environmental change will necessitate the adoption of mitigation and adaptation strategies in husbandry. Long term predictive models need to have the architecture to incorporate these changes. Ultimately, an optimal modelling approach is likely to combine mechanistic processes and physiological thresholds with correlative bioclimatic modelling, incorporating changes in livestock husbandry and disease control. Irrespective of approach, the principal limitation to parasite predictions is the availability of active surveillance data and empirical data on physiological responses to climate variables. By combining improved empirical data and refined models with a broad view of the livestock system, robust projections of helminth risk can be developed. PMID:26486780

Lung Cancer Risk Prediction Model Incorporating Lung Function: Development and Validation in the UK Biobank Prospective Cohort Study.

PubMed

Muller, David C; Johansson, Mattias; Brennan, Paul

2017-03-10

Purpose Several lung cancer risk prediction models have been developed, but none to date have assessed the predictive ability of lung function in a population-based cohort. We sought to develop and internally validate a model incorporating lung function using data from the UK Biobank prospective cohort study. Methods This analysis included 502,321 participants without a previous diagnosis of lung cancer, predominantly between 40 and 70 years of age. We used flexible parametric survival models to estimate the 2-year probability of lung cancer, accounting for the competing risk of death. Models included predictors previously shown to be associated with lung cancer risk, including sex, variables related to smoking history and nicotine addiction, medical history, family history of lung cancer, and lung function (forced expiratory volume in 1 second [FEV1]). Results During accumulated follow-up of 1,469,518 person-years, there were 738 lung cancer diagnoses. A model incorporating all predictors had excellent discrimination (concordance (c)-statistic [95% CI] = 0.85 [0.82 to 0.87]). Internal validation suggested that the model will discriminate well when applied to new data (optimism-corrected c-statistic = 0.84). The full model, including FEV1, also had modestly superior discriminatory power than one that was designed solely on the basis of questionnaire variables (c-statistic = 0.84 [0.82 to 0.86]; optimism-corrected c-statistic = 0.83; p FEV1 = 3.4 × 10 -13 ). The full model had better discrimination than standard lung cancer screening eligibility criteria (c-statistic = 0.66 [0.64 to 0.69]). Conclusion A risk prediction model that includes lung function has strong predictive ability, which could improve eligibility criteria for lung cancer screening programs.

A time series modeling approach in risk appraisal of violent and sexual recidivism.

PubMed

Bani-Yaghoub, Majid; Fedoroff, J Paul; Curry, Susan; Amundsen, David E

2010-10-01

For over half a century, various clinical and actuarial methods have been employed to assess the likelihood of violent recidivism. Yet there is a need for new methods that can improve the accuracy of recidivism predictions. This study proposes a new time series modeling approach that generates high levels of predictive accuracy over short and long periods of time. The proposed approach outperformed two widely used actuarial instruments (i.e., the Violence Risk Appraisal Guide and the Sex Offender Risk Appraisal Guide). Furthermore, analysis of temporal risk variations based on specific time series models can add valuable information into risk assessment and management of violent offenders.

Application of a predictive Bayesian model to environmental accounting.

PubMed

Anex, R P; Englehardt, J D

2001-03-30

Environmental accounting techniques are intended to capture important environmental costs and benefits that are often overlooked in standard accounting practices. Environmental accounting methods themselves often ignore or inadequately represent large but highly uncertain environmental costs and costs conditioned by specific prior events. Use of a predictive Bayesian model is demonstrated for the assessment of such highly uncertain environmental and contingent costs. The predictive Bayesian approach presented generates probability distributions for the quantity of interest (rather than parameters thereof). A spreadsheet implementation of a previously proposed predictive Bayesian model, extended to represent contingent costs, is described and used to evaluate whether a firm should undertake an accelerated phase-out of its PCB containing transformers. Variability and uncertainty (due to lack of information) in transformer accident frequency and severity are assessed simultaneously using a combination of historical accident data, engineering model-based cost estimates, and subjective judgement. Model results are compared using several different risk measures. Use of the model for incorporation of environmental risk management into a company's overall risk management strategy is discussed.

Risk-adjusted performance evaluation in three academic thoracic surgery units using the Eurolung risk models.

PubMed

Pompili, Cecilia; Shargall, Yaron; Decaluwe, Herbert; Moons, Johnny; Chari, Madhu; Brunelli, Alessandro

2018-01-03

The objective of this study was to evaluate the performance of 3 thoracic surgery centres using the Eurolung risk models for morbidity and mortality. This was a retrospective analysis performed on data collected from 3 academic centres (2014-2016). Seven hundred and twenty-one patients in Centre 1, 857 patients in Centre 2 and 433 patients in Centre 3 who underwent anatomical lung resections were analysed. The Eurolung1 and Eurolung2 models were used to predict risk-adjusted cardiopulmonary morbidity and 30-day mortality rates. Observed and risk-adjusted outcomes were compared within each centre. The observed morbidity of Centre 1 was in line with the predicted morbidity (observed 21.1% vs predicted 22.7%, P = 0.31). Centre 2 performed better than expected (observed morbidity 20.2% vs predicted 26.7%, P < 0.001), whereas the observed morbidity of Centre 3 was higher than the predicted morbidity (observed 41.1% vs predicted 24.3%, P < 0.001). Centre 1 had higher observed mortality when compared with the predicted mortality (3.6% vs 2.1%, P = 0.005), whereas Centre 2 had an observed mortality rate significantly lower than the predicted mortality rate (1.2% vs 2.5%, P = 0.013). Centre 3 had an observed mortality rate in line with the predicted mortality rate (observed 1.4% vs predicted 2.4%, P = 0.17). The observed mortality rates in the patients with major complications were 30.8% in Centre 1 (versus predicted mortality rate 3.8%, P < 0.001), 8.2% in Centre 2 (versus predicted mortality rate 4.1%, P = 0.030) and 9.0% in Centre 3 (versus predicted mortality rate 3.5%, P = 0.014). The Eurolung models were successfully used as risk-adjusting instruments to internally audit the outcomes of 3 different centres, showing their applicability for future quality improvement initiatives. © The Author(s) 2018. Published by Oxford University Press on behalf of the European Association for Cardio-Thoracic Surgery. All rights reserved.

Application of a degree-day model of West Nile virus transmission risk to the East Coast of the United States of America.

PubMed

Konrad, Sarah K; Miller, Scott N

2012-11-01

A geographical information systems model that identifies regions of the United States of America (USA) susceptible to West Nile virus (WNV) transmission risk is presented. This system has previously been calibrated and tested in the western USA; in this paper we use datasets of WNV-killed birds from South Carolina and Connecticut to test the model in the eastern USA. Because their response to WNV infection is highly predictable, American crows were chosen as the primary source for model calibration and testing. Where crow data are absent, other birds are shown to be an effective substitute. Model results show that the same calibrated model demonstrated to work in the western USA has the same predictive ability in the eastern USA, allowing for a continental-scale evaluation of the transmission risk of WNV at a daily time step. The calibrated model is independent of mosquito species and requires inputs of only local maximum and minimum temperatures. Of benefit to the general public and vector control districts, the model predicts the onset of seasonal transmission risk, although it is less effective at identifying the end of the transmission risk season.

Predictors of incident heart failure in patients after an acute coronary syndrome: The LIPID heart failure risk-prediction model.

PubMed

Driscoll, Andrea; Barnes, Elizabeth H; Blankenberg, Stefan; Colquhoun, David M; Hunt, David; Nestel, Paul J; Stewart, Ralph A; West, Malcolm J; White, Harvey D; Simes, John; Tonkin, Andrew

2017-12-01

Coronary heart disease is a major cause of heart failure. Availability of risk-prediction models that include both clinical parameters and biomarkers is limited. We aimed to develop such a model for prediction of incident heart failure. A multivariable risk-factor model was developed for prediction of first occurrence of heart failure death or hospitalization. A simplified risk score was derived that enabled subjects to be grouped into categories of 5-year risk varying from <5% to >20%. Among 7101 patients from the LIPID study (84% male), with median age 61years (interquartile range 55-67years), 558 (8%) died or were hospitalized because of heart failure. Older age, history of claudication or diabetes mellitus, body mass index>30kg/m 2 , LDL-cholesterol >2.5mmol/L, heart rate>70 beats/min, white blood cell count, and the nature of the qualifying acute coronary syndrome (myocardial infarction or unstable angina) were associated with an increase in heart failure events. Coronary revascularization was associated with a lower event rate. Incident heart failure increased with higher concentrations of B-type natriuretic peptide >50ng/L, cystatin C>0.93nmol/L, D-dimer >273nmol/L, high-sensitivity C-reactive protein >4.8nmol/L, and sensitive troponin I>0.018μg/L. Addition of biomarkers to the clinical risk model improved the model's C statistic from 0.73 to 0.77. The net reclassification improvement incorporating biomarkers into the clinical model using categories of 5-year risk was 23%. Adding a multibiomarker panel to conventional parameters markedly improved discrimination and risk classification for future heart failure events. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Validation of prediction models: examining temporal and geographic stability of baseline risk and estimated covariate effects

PubMed Central

Austin, Peter C.; van Klaveren, David; Vergouwe, Yvonne; Nieboer, Daan; Lee, Douglas S.; Steyerberg, Ewout W.

2018-01-01

Background Stability in baseline risk and estimated predictor effects both geographically and temporally is a desirable property of clinical prediction models. However, this issue has received little attention in the methodological literature. Our objective was to examine methods for assessing temporal and geographic heterogeneity in baseline risk and predictor effects in prediction models. Methods We studied 14,857 patients hospitalized with heart failure at 90 hospitals in Ontario, Canada, in two time periods. We focussed on geographic and temporal variation in baseline risk (intercept) and predictor effects (regression coefficients) of the EFFECT-HF mortality model for predicting 1-year mortality in patients hospitalized for heart failure. We used random effects logistic regression models for the 14,857 patients. Results The baseline risk of mortality displayed moderate geographic variation, with the hospital-specific probability of 1-year mortality for a reference patient lying between 0.168 and 0.290 for 95% of hospitals. Furthermore, the odds of death were 11% lower in the second period than in the first period. However, we found minimal geographic or temporal variation in predictor effects. Among 11 tests of differences in time for predictor variables, only one had a modestly significant P value (0.03). Conclusions This study illustrates how temporal and geographic heterogeneity of prediction models can be assessed in settings with a large sample of patients from a large number of centers at different time periods. PMID:29350215

Comparison of time series models for predicting campylobacteriosis risk in New Zealand.

PubMed

Al-Sakkaf, A; Jones, G

2014-05-01

Predicting campylobacteriosis cases is a matter of considerable concern in New Zealand, after the number of the notified cases was the highest among the developed countries in 2006. Thus, there is a need to develop a model or a tool to predict accurately the number of campylobacteriosis cases as the Microbial Risk Assessment Model used to predict the number of campylobacteriosis cases failed to predict accurately the number of actual cases. We explore the appropriateness of classical time series modelling approaches for predicting campylobacteriosis. Finding the most appropriate time series model for New Zealand data has additional practical considerations given a possible structural change, that is, a specific and sudden change in response to the implemented interventions. A univariate methodological approach was used to predict monthly disease cases using New Zealand surveillance data of campylobacteriosis incidence from 1998 to 2009. The data from the years 1998 to 2008 were used to model the time series with the year 2009 held out of the data set for model validation. The best two models were then fitted to the full 1998-2009 data and used to predict for each month of 2010. The Holt-Winters (multiplicative) and ARIMA (additive) intervention models were considered the best models for predicting campylobacteriosis in New Zealand. It was noticed that the prediction by an additive ARIMA with intervention was slightly better than the prediction by a Holt-Winter multiplicative method for the annual total in year 2010, the former predicting only 23 cases less than the actual reported cases. It is confirmed that classical time series techniques such as ARIMA with intervention and Holt-Winters can provide a good prediction performance for campylobacteriosis risk in New Zealand. The results reported by this study are useful to the New Zealand Health and Safety Authority's efforts in addressing the problem of the campylobacteriosis epidemic. © 2013 Blackwell Verlag GmbH.

Benefit and harm of intensive blood pressure treatment: Derivation and validation of risk models using data from the SPRINT and ACCORD trials

PubMed Central

Denton, Brian T.; Hayward, Rodney A.

2017-01-01

Background Intensive blood pressure (BP) treatment can avert cardiovascular disease (CVD) events but can cause some serious adverse events. We sought to develop and validate risk models for predicting absolute risk difference (increased risk or decreased risk) for CVD events and serious adverse events from intensive BP therapy. A secondary aim was to test if the statistical method of elastic net regularization would improve the estimation of risk models for predicting absolute risk difference, as compared to a traditional backwards variable selection approach. Methods and findings Cox models were derived from SPRINT trial data and validated on ACCORD-BP trial data to estimate risk of CVD events and serious adverse events; the models included terms for intensive BP treatment and heterogeneous response to intensive treatment. The Cox models were then used to estimate the absolute reduction in probability of CVD events (benefit) and absolute increase in probability of serious adverse events (harm) for each individual from intensive treatment. We compared the method of elastic net regularization, which uses repeated internal cross-validation to select variables and estimate coefficients in the presence of collinearity, to a traditional backwards variable selection approach. Data from 9,069 SPRINT participants with complete data on covariates were utilized for model development, and data from 4,498 ACCORD-BP participants with complete data were utilized for model validation. Participants were exposed to intensive (goal systolic pressure < 120 mm Hg) versus standard (<140 mm Hg) treatment. Two composite primary outcome measures were evaluated: (i) CVD events/deaths (myocardial infarction, acute coronary syndrome, stroke, congestive heart failure, or CVD death), and (ii) serious adverse events (hypotension, syncope, electrolyte abnormalities, bradycardia, or acute kidney injury/failure). The model for CVD chosen through elastic net regularization included interaction terms suggesting that older age, black race, higher diastolic BP, and higher lipids were associated with greater CVD risk reduction benefits from intensive treatment, while current smoking was associated with fewer benefits. The model for serious adverse events chosen through elastic net regularization suggested that male sex, current smoking, statin use, elevated creatinine, and higher lipids were associated with greater risk of serious adverse events from intensive treatment. SPRINT participants in the highest predicted benefit subgroup had a number needed to treat (NNT) of 24 to prevent 1 CVD event/death over 5 years (absolute risk reduction [ARR] = 0.042, 95% CI: 0.018, 0.066; P = 0.001), those in the middle predicted benefit subgroup had a NNT of 76 (ARR = 0.013, 95% CI: −0.0001, 0.026; P = 0.053), and those in the lowest subgroup had no significant risk reduction (ARR = 0.006, 95% CI: −0.007, 0.018; P = 0.71). Those in the highest predicted harm subgroup had a number needed to harm (NNH) of 27 to induce 1 serious adverse event (absolute risk increase [ARI] = 0.038, 95% CI: 0.014, 0.061; P = 0.002), those in the middle predicted harm subgroup had a NNH of 41 (ARI = 0.025, 95% CI: 0.012, 0.038; P < 0.001), and those in the lowest subgroup had no significant risk increase (ARI = −0.007, 95% CI: −0.043, 0.030; P = 0.72). In ACCORD-BP, participants in the highest subgroup of predicted benefit had significant absolute CVD risk reduction, but the overall ACCORD-BP participant sample was skewed towards participants with less predicted benefit and more predicted risk than in SPRINT. The models chosen through traditional backwards selection had similar ability to identify absolute risk difference for CVD as the elastic net models, but poorer ability to correctly identify absolute risk difference for serious adverse events. A key limitation of the analysis is the limited sample size of the ACCORD-BP trial, which expanded confidence intervals for ARI among persons with type 2 diabetes. Additionally, it is not possible to mechanistically explain the physiological relationships explaining the heterogeneous treatment effects captured by the models, since the study was an observational secondary data analysis. Conclusions We found that predictive models could help identify subgroups of participants in both SPRINT and ACCORD-BP who had lower versus higher ARRs in CVD events/deaths with intensive BP treatment, and participants who had lower versus higher ARIs in serious adverse events. PMID:29040268

Challenges of developing a cardiovascular risk calculator for patients with rheumatoid arthritis.

PubMed

Crowson, Cynthia S; Rollefstad, Silvia; Kitas, George D; van Riel, Piet L C M; Gabriel, Sherine E; Semb, Anne Grete

2017-01-01

Cardiovascular disease (CVD) risk calculators designed for use in the general population do not accurately predict the risk of CVD among patients with rheumatoid arthritis (RA), who are at increased risk of CVD. The process of developing risk prediction models involves numerous issues. Our goal was to develop a CVD risk calculator for patients with RA. Thirteen cohorts of patients with RA originating from 10 different countries (UK, Norway, Netherlands, USA, Sweden, Greece, South Africa, Spain, Canada and Mexico) were combined. CVD risk factors and RA characteristics at baseline, in addition to information on CVD outcomes were collected. Cox models were used to develop a CVD risk calculator, considering traditional CVD risk factors and RA characteristics. Model performance was assessed using measures of discrimination and calibration with 10-fold cross-validation. A total of 5638 RA patients without prior CVD were included (mean age: 55 [SD: 14] years, 76% female). During a mean follow-up of 5.8 years (30139 person years), 389 patients developed a CVD event. Event rates varied between cohorts, necessitating inclusion of high and low risk strata in the models. The multivariable analyses revealed 2 risk prediction models including either a disease activity score including a 28 joint count and erythrocyte sedimentation rate (DAS28ESR) or a health assessment questionnaire (HAQ) along with age, sex, presence of hypertension, current smoking and ratio of total cholesterol to high-density lipoprotein cholesterol. Unfortunately, performance of these models was similar to general population CVD risk calculators. Efforts to develop a specific CVD risk calculator for patients with RA yielded 2 potential models including RA disease characteristics, but neither demonstrated improved performance compared to risk calculators designed for use in the general population. Challenges encountered and lessons learned are discussed in detail.

Risk Prediction Models of Locoregional Failure After Radical Cystectomy for Urothelial Carcinoma: External Validation in a Cohort of Korean Patients

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ku, Ja Hyeon; Kim, Myong; Jeong, Chang Wook

2014-08-01

Purpose: To evaluate the predictive accuracy and general applicability of the locoregional failure model in a different cohort of patients treated with radical cystectomy. Methods and Materials: A total of 398 patients were included in the analysis. Death and isolated distant metastasis were considered competing events, and patients without any events were censored at the time of last follow-up. The model included the 3 variables pT classification, the number of lymph nodes identified, and margin status, as follows: low risk (≤pT2), intermediate risk (≥pT3 with ≥10 nodes removed and negative margins), and high risk (≥pT3 with <10 nodes removed ormore » positive margins). Results: The bootstrap-corrected concordance index of the model 5 years after radical cystectomy was 66.2%. When the risk stratification was applied to the validation cohort, the 5-year locoregional failure estimates were 8.3%, 21.2%, and 46.3% for the low-risk, intermediate-risk, and high-risk groups, respectively. The risk of locoregional failure differed significantly between the low-risk and intermediate-risk groups (subhazard ratio [SHR], 2.63; 95% confidence interval [CI], 1.35-5.11; P<.001) and between the low-risk and high-risk groups (SHR, 4.28; 95% CI, 2.17-8.45; P<.001). Although decision curves were appropriately affected by the incidence of the competing risk, decisions about the value of the models are not likely to be affected because the model remains of value over a wide range of threshold probabilities. Conclusions: The model is not completely accurate, but it demonstrates a modest level of discrimination, adequate calibration, and meaningful net benefit gain for prediction of locoregional failure after radical cystectomy.« less

Enteric disease episodes and the risk of acquiring a future sexually transmitted infection: a prediction model in Montreal residents.

PubMed

Caron, Melissa; Allard, Robert; Bédard, Lucie; Latreille, Jérôme; Buckeridge, David L

2016-11-01

The sexual transmission of enteric diseases poses an important public health challenge. We aimed to build a prediction model capable of identifying individuals with a reported enteric disease who could be at risk of acquiring future sexually transmitted infections (STIs). Passive surveillance data on Montreal residents with at least 1 enteric disease report was used to construct the prediction model. Cases were defined as all subjects with at least 1 STI report following their initial enteric disease episode. A final logistic regression prediction model was chosen using forward stepwise selection. The prediction model with the greatest validity included age, sex, residential location, number of STI episodes experienced prior to the first enteric disease episode, type of enteric disease acquired, and an interaction term between age and male sex. This model had an area under the curve of 0.77 and had acceptable calibration. A coordinated public health response to the sexual transmission of enteric diseases requires that a distinction be made between cases of enteric diseases transmitted through sexual activity from those transmitted through contaminated food or water. A prediction model can aid public health officials in identifying individuals who may have a higher risk of sexually acquiring a reportable disease. Once identified, these individuals could receive specialized intervention to prevent future infection. The information produced from a prediction model capable of identifying higher risk individuals can be used to guide efforts in investigating and controlling reported cases of enteric diseases and STIs. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

DOSIMETRY MODELING OF INHALED FORMALDEHYDE: BINNING NASAL FLUX PREDICTIONS FOR QUANTITATIVE RISK ASSESSMENT

EPA Science Inventory

Dosimetry Modeling of Inhaled Formaldehyde: Binning Nasal Flux Predictions for Quantitative Risk Assessment. Kimbell, J.S., Overton, J.H., Subramaniam, R.P., Schlosser, P.M., Morgan, K.T., Conolly, R.B., and Miller, F.J. (2001). Toxicol. Sci. 000, 000:000.

Interspecies e...

A Predictive Model Has Identified Tick-Borne Encephalitis High-Risk Areas in Regions Where No Cases Were Reported Previously, Poland, 1999–2012

PubMed Central

Rubikowska, Barbara; Bratkowski, Jakub; Ustrnul, Zbigniew; Vanwambeke, Sophie O.

2018-01-01

During 1999–2012, 77% of the cases of tick-borne encephalitis (TBE) were recorded in two out of 16 Polish provinces. However, historical data, mostly from national serosurveys, suggest that the disease could be undetected in many areas. The aim of this study was to identify which routinely-measured meteorological, environmental, and socio-economic factors are associated to TBE human risk across Poland, with a particular focus on areas reporting few cases, but where serosurveys suggest higher incidence. We fitted a zero-inflated Poisson model using data on TBE incidence recorded in 108 NUTS-5 administrative units in high-risk areas over the period 1999–2012. Subsequently we applied the best fitting model to all Polish municipalities. Keeping the remaining variables constant, the predicted rate increased with the increase of air temperature over the previous 10–20 days, precipitation over the previous 20–30 days, in forestation, forest edge density, forest road density, and unemployment. The predicted rate decreased with increasing distance from forests. The map of predicted rates was consistent with the established risk areas. It predicted, however, high rates in provinces considered TBE-free. We recommend raising awareness among physicians working in the predicted high-risk areas and considering routine use of household animal surveys for risk mapping. PMID:29617333

A Predictive Model Has Identified Tick-Borne Encephalitis High-Risk Areas in Regions Where No Cases Were Reported Previously, Poland, 1999-2012.

PubMed

Stefanoff, Pawel; Rubikowska, Barbara; Bratkowski, Jakub; Ustrnul, Zbigniew; Vanwambeke, Sophie O; Rosinska, Magdalena

2018-04-04

During 1999–2012, 77% of the cases of tick-borne encephalitis (TBE) were recorded in two out of 16 Polish provinces. However, historical data, mostly from national serosurveys, suggest that the disease could be undetected in many areas. The aim of this study was to identify which routinely-measured meteorological, environmental, and socio-economic factors are associated to TBE human risk across Poland, with a particular focus on areas reporting few cases, but where serosurveys suggest higher incidence. We fitted a zero-inflated Poisson model using data on TBE incidence recorded in 108 NUTS-5 administrative units in high-risk areas over the period 1999–2012. Subsequently we applied the best fitting model to all Polish municipalities. Keeping the remaining variables constant, the predicted rate increased with the increase of air temperature over the previous 10–20 days, precipitation over the previous 20–30 days, in forestation, forest edge density, forest road density, and unemployment. The predicted rate decreased with increasing distance from forests. The map of predicted rates was consistent with the established risk areas. It predicted, however, high rates in provinces considered TBE-free. We recommend raising awareness among physicians working in the predicted high-risk areas and considering routine use of household animal surveys for risk mapping.

Pretreatment Nomogram to Predict the Risk of Acute Urinary Retention After I-125 Prostate Brachytherapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Roeloffzen, Ellen M., E-mail: e.m.a.roeloffzen@umcutrecht.nl; Vulpen, Marco van; Battermann, Jan J.

Purpose: Acute urinary retention (AUR) after iodine-125 (I-125) prostate brachytherapy negatively influences long-term quality of life and therefore should be prevented. We aimed to develop a nomogram to preoperatively predict the risk of AUR. Methods: Using the preoperative data of 714 consecutive patients who underwent I-125 prostate brachytherapy between 2005 and 2008 at our department, we modeled the probability of AUR. Multivariate logistic regression analysis was used to assess the predictive ability of a set of pretreatment predictors and the additional value of a new risk factor (the extent of prostate protrusion into the bladder). The performance of the finalmore » model was assessed with calibration and discrimination measures. Results: Of the 714 patients, 57 patients (8.0%) developed AUR after implantation. Multivariate analysis showed that the combination of prostate volume, IPSS score, neoadjuvant hormonal treatment and the extent of prostate protrusion contribute to the prediction of AUR. The discriminative value (receiver operator characteristic area, ROC) of the basic model (including prostate volume, International Prostate Symptom Score, and neoadjuvant hormonal treatment) to predict the development of AUR was 0.70. The addition of prostate protrusion significantly increased the discriminative power of the model (ROC 0.82). Calibration of this final model was good. The nomogram showed that among patients with a low sum score (<18 points), the risk of AUR was only 0%-5%. However, in patients with a high sum score (>35 points), the risk of AUR was more than 20%. Conclusion: This nomogram is a useful tool for physicians to predict the risk of AUR after I-125 prostate brachytherapy. The nomogram can aid in individualized treatment decision-making and patient counseling.« less

Predicting Risk Sensitivity in Humans and Lower Animals: Risk as Variance or Coefficient of Variation

ERIC Educational Resources Information Center

Weber, Elke U.; Shafir, Sharoni; Blais, Ann-Renee

2004-01-01

This article examines the statistical determinants of risk preference. In a meta-analysis of animal risk preference (foraging birds and insects), the coefficient of variation (CV), a measure of risk per unit of return, predicts choices far better than outcome variance, the risk measure of normative models. In a meta-analysis of human risk…

Advantages of new cardiovascular risk-assessment strategies in high-risk patients with hypertension.

PubMed

Ruilope, Luis M; Segura, Julian

2005-10-01

Accurate assessment of cardiovascular disease (CVD) risk in patients with hypertension is important when planning appropriate treatment of modifiable risk factors. The causes of CVD are multifactorial, and hypertension seldom exists as an isolated risk factor. Classic models of risk assessment are more accurate than a simple counting of risk factors, but they are not generalizable to all populations. In addition, the risk associated with hypertension is graded, continuous, and independent of other risk factors, and this is not reflected in classic models of risk assessment. This article is intended to review both classic and newer models of CVD risk assessment. MEDLINE was searched for articles published between 1990 and 2005 that contained the terms cardiovascular disease, hypertension, or risk assessment. Articles describing major clinical trials, new data about cardiovascular risk, or global risk stratification were selected for review. Some patients at high long-term risk for CVD events (eg, patients aged <50 years with multiple risk factors) may go untreated because they do not meet the absolute risk-intervention threshold of 20% risk over 10 years with the classic model. Recognition of the limitations of classic risk-assessment models led to new guidelines, particularly those of the European Society of Hypertension-European Society of Cardiology. These guidelines view hypertension as one of many risk and disease factors that require treatment to decrease risk. These newer guidelines include a more comprehensive range of risk factors and more finely graded blood pressure ranges to stratify patients by degree of risk. Whether they accurately predict CVD risk in most populations is not known. Evidence from the Valsartan Antihypertensive Long-term Use Evaluation (VALUE) study, which stratified patients by several risk and disease factors, highlights the predictive value of some newer CVD risk assessments. Modern risk assessments, which include blood pressure along with a wide array of modifiable risk factors, may be more accurate than classic models for CVD risk prediction.

Review and developments of dissemination models for airborne carbon fibers

NASA Technical Reports Server (NTRS)

Elber, W.

1980-01-01

Dissemination prediction models were reviewed to determine their applicability to a risk assessment for airborne carbon fibers. The review showed that the Gaussian prediction models using partial reflection at the ground agreed very closely with a more elaborate diffusion analysis developed for the study. For distances beyond 10,000 m the Gaussian models predicted a slower fall-off in exposure levels than the diffusion models. This resulting level of conservatism was preferred for the carbon fiber risk assessment. The results also showed that the perfect vertical-mixing models developed herein agreed very closely with the diffusion analysis for all except the most stable atmospheric conditions.

Risk models for post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP): smoking and chronic liver disease are predictors of protection against PEP.

PubMed

DiMagno, Matthew J; Spaete, Joshua P; Ballard, Darren D; Wamsteker, Erik-Jan; Saini, Sameer D

2013-08-01

We investigated which variables independently associated with protection against or development of postendoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP) and severity of PEP. Subsequently, we derived predictive risk models for PEP. In a case-control design, 6505 patients had 8264 ERCPs, 211 patients had PEP, and 22 patients had severe PEP. We randomly selected 348 non-PEP controls. We examined 7 established- and 9 investigational variables. In univariate analysis, 7 variables predicted PEP: younger age, female sex, suspected sphincter of Oddi dysfunction (SOD), pancreatic sphincterotomy, moderate-difficult cannulation (MDC), pancreatic stent placement, and lower Charlson score. Protective variables were current smoking, former drinking, diabetes, and chronic liver disease (CLD, biliary/transplant complications). Multivariate analysis identified seven independent variables for PEP, three protective (current smoking, CLD-biliary, CLD-transplant/hepatectomy complications) and 4 predictive (younger age, suspected SOD, pancreatic sphincterotomy, MDC). Pre- and post-ERCP risk models of 7 variables have a C-statistic of 0.74. Removing age (seventh variable) did not significantly affect the predictive value (C-statistic of 0.73) and reduced model complexity. Severity of PEP did not associate with any variables by multivariate analysis. By using the newly identified protective variables with 3 predictive variables, we derived 2 risk models with a higher predictive value for PEP compared to prior studies.

Comparison of the predictive validity of diagnosis-based risk adjusters for clinical outcomes.

PubMed

Petersen, Laura A; Pietz, Kenneth; Woodard, LeChauncy D; Byrne, Margaret

2005-01-01

Many possible methods of risk adjustment exist, but there is a dearth of comparative data on their performance. We compared the predictive validity of 2 widely used methods (Diagnostic Cost Groups [DCGs] and Adjusted Clinical Groups [ACGs]) for 2 clinical outcomes using a large national sample of patients. We studied all patients who used Veterans Health Administration (VA) medical services in fiscal year (FY) 2001 (n = 3,069,168) and assigned both a DCG and an ACG to each. We used logistic regression analyses to compare predictive ability for death or long-term care (LTC) hospitalization for age/gender models, DCG models, and ACG models. We also assessed the effect of adding age to the DCG and ACG models. Patients in the highest DCG categories, indicating higher severity of illness, were more likely to die or to require LTC hospitalization. Surprisingly, the age/gender model predicted death slightly more accurately than the ACG model (c-statistic of 0.710 versus 0.700, respectively). The addition of age to the ACG model improved the c-statistic to 0.768. The highest c-statistic for prediction of death was obtained with a DCG/age model (0.830). The lowest c-statistics were obtained for age/gender models for LTC hospitalization (c-statistic 0.593). The c-statistic for use of ACGs to predict LTC hospitalization was 0.783, and improved to 0.792 with the addition of age. The c-statistics for use of DCGs and DCG/age to predict LTC hospitalization were 0.885 and 0.890, respectively, indicating the best prediction. We found that risk adjusters based upon diagnoses predicted an increased likelihood of death or LTC hospitalization, exhibiting good predictive validity. In this comparative analysis using VA data, DCG models were generally superior to ACG models in predicting clinical outcomes, although ACG model performance was enhanced by the addition of age.

Individualized pharmacokinetic risk assessment for development of diabetes in high risk population.

PubMed

Gupta, N; Al-Huniti, N H; Veng-Pedersen, P

2007-10-01

The objective of this study is to propose a non-parametric pharmacokinetic prediction model that addresses the individualized risk of developing type-2 diabetes in subjects with family history of type-2 diabetes. All selected 191 healthy subjects had both parents as type-2 diabetic. Glucose was administered intravenously (0.5 g/kg body weight) and 13 blood samples taken at specified times were analyzed for plasma insulin and glucose concentrations. All subjects were followed for an average of 13-14 years for diabetic or normal (non-diabetic) outcome. The new logistic regression model predicts the development of diabetes based on body mass index and only one blood sample at 90 min analyzed for insulin concentration. Our model correctly identified 4.5 times more subjects (54% versus 11.6%) predicted to develop diabetes and more than twice the subjects (99% versus 46.4%) predicted not to develop diabetes compared to current non-pharmacokinetic probability estimates for development of type-2 diabetes. Our model can be useful for individualized prediction of development of type-2 diabetes in subjects with family history of type-2 diabetes. This improved prediction may be an important mediating factor for better perception of risk and may result in an improved intervention.

Genetic risk prediction using a spatial autoregressive model with adaptive lasso.

PubMed

Wen, Yalu; Shen, Xiaoxi; Lu, Qing

2018-05-31

With rapidly evolving high-throughput technologies, studies are being initiated to accelerate the process toward precision medicine. The collection of the vast amounts of sequencing data provides us with great opportunities to systematically study the role of a deep catalog of sequencing variants in risk prediction. Nevertheless, the massive amount of noise signals and low frequencies of rare variants in sequencing data pose great analytical challenges on risk prediction modeling. Motivated by the development in spatial statistics, we propose a spatial autoregressive model with adaptive lasso (SARAL) for risk prediction modeling using high-dimensional sequencing data. The SARAL is a set-based approach, and thus, it reduces the data dimension and accumulates genetic effects within a single-nucleotide variant (SNV) set. Moreover, it allows different SNV sets having various magnitudes and directions of effect sizes, which reflects the nature of complex diseases. With the adaptive lasso implemented, SARAL can shrink the effects of noise SNV sets to be zero and, thus, further improve prediction accuracy. Through simulation studies, we demonstrate that, overall, SARAL is comparable to, if not better than, the genomic best linear unbiased prediction method. The method is further illustrated by an application to the sequencing data from the Alzheimer's Disease Neuroimaging Initiative. Copyright © 2018 John Wiley & Sons, Ltd.

Multifactorial risk index for prediction of intraoperative blood transfusion in endovascular aneurysm repair.

PubMed

Mahmood, Eitezaz; Matyal, Robina; Mueller, Ariel; Mahmood, Feroze; Tung, Avery; Montealegre-Gallegos, Mario; Schermerhorn, Marc; Shahul, Sajid

2018-03-01

In some institutions, the current blood ordering practice does not discriminate minimally invasive endovascular aneurysm repair (EVAR) from open procedures, with consequent increasing costs and likelihood of blood product wastage for EVARs. This limitation in practice can possibly be addressed with the development of a reliable prediction model for transfusion risk in EVAR patients. We used the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) database to create a model for prediction of intraoperative blood transfusion occurrence in patients undergoing EVAR. Afterward, we tested our predictive model on the Vascular Study Group of New England (VSGNE) database. We used the ACS NSQIP database for patients who underwent EVAR from 2011 to 2013 (N = 4709) as our derivation set for identifying a risk index for predicting intraoperative blood transfusion. We then developed a clinical risk score and validated this model using patients who underwent EVAR from 2003 to 2014 in the VSGNE database (N = 4478). The transfusion rates were 8.4% and 6.1% for the ACS NSQIP (derivation set) and VSGNE (validation) databases, respectively. Hemoglobin concentration, American Society of Anesthesiologists class, age, and aneurysm diameter predicted blood transfusion in the derivation set. When it was applied on the validation set, our risk index demonstrated good discrimination in both the derivation and validation set (C statistic = 0.73 and 0.70, respectively) and calibration using the Hosmer-Lemeshow test (P = .27 and 0.31) for both data sets. We developed and validated a risk index for predicting the likelihood of intraoperative blood transfusion in EVAR patients. Implementation of this index may facilitate the blood management strategies specific for EVAR. Copyright © 2017 Society for Vascular Surgery. Published by Elsevier Inc. All rights reserved.

Sexual risk behavior among youth: modeling the influence of prosocial activities and socioeconomic factors.

PubMed

Ramirez-Valles, J; Zimmerman, M A; Newcomb, M D

1998-09-01

Sexual activity among high-school-aged youths has steadily increased since the 1970s, emerging as a significant public health concern. Yet, patterns of youth sexual risk behavior are shaped by social class, race, and gender. Based on sociological theories of financial deprivation and collective socialization, we develop and test a model of the relationships among neighborhood poverty; family structure and social class position; parental involvement; prosocial activities; race; and gender as they predict youth sexual risk behavior. We employ structural equation modeling to test this model on a cross-sectional sample of 370 sexually active high-school students from a midwestern city; 57 percent (n = 209) are males and 86 percent are African American. We find that family structure indirectly predicts sexual risk behavior through neighborhood poverty, parental involvement, and prosocial activities. In addition, family class position indirectly predicts sexual risk behavior through neighborhood poverty and prosocial activities. We address implications for theory and health promotion.

Risk-adjusted predictive models of mortality after index arterial operations using a minimal data set.

PubMed

Prytherch, D R; Ridler, B M F; Ashley, S

2005-06-01

Reducing the data required for a national vascular database (NVD) without compromising the statistical basis of comparative audit is an important goal. This work attempted to model outcomes (mortality and morbidity) from a small and simple subset of the NVD data items, specifically urea, sodium, potassium, haemoglobin, white cell count, age and mode of admission. Logistic regression models of risk of adverse outcome were built from the 2001 submission to the NVD using all records that contained the complete data required by the models. These models were applied prospectively against the equivalent data from the 2002 submission to the NVD. As had previously been found using the P-POSSUM (Portsmouth POSSUM) approach, although elective abdominal aortic aneurysm (AAA) repair and infrainguinal bypass (IIB) operations could be described by the same model, separate models were required for carotid endarterectomy (CEA) and emergency AAA repair. For CEA there were insufficient adverse events recorded to allow prospective testing of the models. The overall mean predicted risk of death in 530 patients undergoing elective AAA repair or IIB operations was 5.6 per cent, predicting 30 deaths. There were 28 reported deaths (chi(2) = 2.75, 4 d.f., P = 0.600; no evidence of lack of fit). Similarly, accurate predictions were obtained across a range of predicted risks as well as for patients undergoing repair of ruptured AAA and for morbidity. A 'data economic' model for risk stratification of national data is feasible. The ability to use a minimal data set may facilitate the process of comparative audit within the NVD. Copyright (c) 2005 British Journal of Surgery Society Ltd. Published by John Wiley & Sons, Ltd.

A Nomogram to Predict Anastomotic Leakage in Open Rectal Surgery-Hope or Hype?

PubMed

Klose, Johannes; Tarantino, Ignazio; von Fournier, Armin; Stowitzki, Moritz J; Kulu, Yakup; Bruckner, Thomas; Volz, Claudia; Schmidt, Thomas; Schneider, Martin; Büchler, Markus W; Ulrich, Alexis

2018-05-18

Anastomotic leakage is the most dreaded complication after rectal resection and total mesorectal excision, leading to increased morbidity and mortality. Formation of a diverting ileostomy is generally performed to protect anastomotic healing. Identification of variables predicting anastomotic leakage might help to select patients who are under increased risk for the development of anastomotic leakage prior to surgery. The objective of this study was to assess the applicability of a nomogram as prognostic model for the occurrence of anastomotic leakage after rectal resection in a cohort of rectal cancer patients. Nine hundred seventy-two consecutive patients who underwent surgery for rectal cancer were retrospectively analyzed. Univariate and multivariable Cox regression analyses were used to determine independent risk factors associated with anastomotic leakage. Receiver operating characteristics (ROC) curve analysis was performed to calculate the sensitivity, specificity, and overall model correctness of a recently published nomogram and an adopted risk score based on the variables identified in this study as a predictive model. Male sex (p = 0.042), obesity (p = 0.017), smoking (p = 0.012), postoperative bleeding (p = 0.024), and total protein level ≤ 5.6 g/dl (p = 0.007) were identified as independent risk factors for anastomotic leakage. The investigated nomogram and the adopted risk score failed to reach relevant areas under the ROC curve greater than 0.700 for the prediction of anastomotic leakage. The proposed nomogram and the adopted risk score failed to reliably predict the occurrence of anastomotic leakage after rectal resection. Risk scores as prognostic models for the prediction of anastomotic leakage, independently of the study population, still need to be identified.

Pretreatment data is highly predictive of liver chemistry signals in clinical trials.

PubMed

Cai, Zhaohui; Bresell, Anders; Steinberg, Mark H; Silberg, Debra G; Furlong, Stephen T

2012-01-01

The goal of this retrospective analysis was to assess how well predictive models could determine which patients would develop liver chemistry signals during clinical trials based on their pretreatment (baseline) information. Based on data from 24 late-stage clinical trials, classification models were developed to predict liver chemistry outcomes using baseline information, which included demographics, medical history, concomitant medications, and baseline laboratory results. Predictive models using baseline data predicted which patients would develop liver signals during the trials with average validation accuracy around 80%. Baseline levels of individual liver chemistry tests were most important for predicting their own elevations during the trials. High bilirubin levels at baseline were not uncommon and were associated with a high risk of developing biochemical Hy's law cases. Baseline γ-glutamyltransferase (GGT) level appeared to have some predictive value, but did not increase predictability beyond using established liver chemistry tests. It is possible to predict which patients are at a higher risk of developing liver chemistry signals using pretreatment (baseline) data. Derived knowledge from such predictions may allow proactive and targeted risk management, and the type of analysis described here could help determine whether new biomarkers offer improved performance over established ones.

Contemporary model for cardiovascular risk prediction in people with type 2 diabetes.

PubMed

Kengne, Andre Pascal; Patel, Anushka; Marre, Michel; Travert, Florence; Lievre, Michel; Zoungas, Sophia; Chalmers, John; Colagiuri, Stephen; Grobbee, Diederick E; Hamet, Pavel; Heller, Simon; Neal, Bruce; Woodward, Mark

2011-06-01

Existing cardiovascular risk prediction equations perform non-optimally in different populations with diabetes. Thus, there is a continuing need to develop new equations that will reliably estimate cardiovascular disease (CVD) risk and offer flexibility for adaptation in various settings. This report presents a contemporary model for predicting cardiovascular risk in people with type 2 diabetes mellitus. A 4.5-year follow-up of the Action in Diabetes and Vascular disease: preterax and diamicron-MR controlled evaluation (ADVANCE) cohort was used to estimate coefficients for significant predictors of CVD using Cox models. Similar Cox models were used to fit the 4-year risk of CVD in 7168 participants without previous CVD. The model's applicability was tested on the same sample and another dataset. A total of 473 major cardiovascular events were recorded during follow-up. Age at diagnosis, known duration of diabetes, sex, pulse pressure, treated hypertension, atrial fibrillation, retinopathy, HbA1c, urinary albumin/creatinine ratio and non-HDL cholesterol at baseline were significant predictors of cardiovascular events. The model developed using these predictors displayed an acceptable discrimination (c-statistic: 0.70) and good calibration during internal validation. The external applicability of the model was tested on an independent cohort of individuals with type 2 diabetes, where similar discrimination was demonstrated (c-statistic: 0.69). Major cardiovascular events in contemporary populations with type 2 diabetes can be predicted on the basis of routinely measured clinical and biological variables. The model presented here can be used to quantify risk and guide the intensity of treatment in people with diabetes.

Terrestrial population models for ecological risk assessment: A state-of-the-art review

USGS Publications Warehouse

Emlen, J.M.

1989-01-01

Few attempts have been made to formulate models for predicting impacts of xenobiotic chemicals on wildlife populations. However, considerable effort has been invested in wildlife optimal exploitation models. Because death from intoxication has a similar effect on population dynamics as death by harvesting, these management models are applicable to ecological risk assessment. An underlying Leslie-matrix bookkeeping formulation is widely applicable to vertebrate wildlife populations. Unfortunately, however, the various submodels that track birth, death, and dispersal rates as functions of the physical, chemical, and biotic environment are by their nature almost inevitably highly species- and locale-specific. Short-term prediction of one-time chemical applications requires only information on mortality before and after contamination. In such cases a simple matrix formulation may be adequate for risk assessment. But generally, risk must be projected over periods of a generation or more. This precludes generic protocols for risk assessment and also the ready and inexpensive predictions of a chemical's influence on a given population. When designing and applying models for ecological risk assessment at the population level, the endpoints (output) of concern must be carefully and rigorously defined. The most easily accessible and appropriate endpoints are (1) pseudoextinction (the frequency or probability of a population falling below a prespecified density), and (2) temporal mean population density. Spatial and temporal extent of predicted changes must be clearly specified a priori to avoid apparent contradictions and confusion.

Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review.

PubMed

Goldstein, Benjamin A; Navar, Ann Marie; Pencina, Michael J; Ioannidis, John P A

2017-01-01

Electronic health records (EHRs) are an increasingly common data source for clinical risk prediction, presenting both unique analytic opportunities and challenges. We sought to evaluate the current state of EHR based risk prediction modeling through a systematic review of clinical prediction studies using EHR data. We searched PubMed for articles that reported on the use of an EHR to develop a risk prediction model from 2009 to 2014. Articles were extracted by two reviewers, and we abstracted information on study design, use of EHR data, model building, and performance from each publication and supplementary documentation. We identified 107 articles from 15 different countries. Studies were generally very large (median sample size = 26 100) and utilized a diverse array of predictors. Most used validation techniques (n = 94 of 107) and reported model coefficients for reproducibility (n = 83). However, studies did not fully leverage the breadth of EHR data, as they uncommonly used longitudinal information (n = 37) and employed relatively few predictor variables (median = 27 variables). Less than half of the studies were multicenter (n = 50) and only 26 performed validation across sites. Many studies did not fully address biases of EHR data such as missing data or loss to follow-up. Average c-statistics for different outcomes were: mortality (0.84), clinical prediction (0.83), hospitalization (0.71), and service utilization (0.71). EHR data present both opportunities and challenges for clinical risk prediction. There is room for improvement in designing such studies. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Know the risk, take the win: how executive functions and probability processing influence advantageous decision making under risk conditions.

PubMed

Brand, Matthias; Schiebener, Johannes; Pertl, Marie-Theres; Delazer, Margarete

2014-01-01

Recent models on decision making under risk conditions have suggested that numerical abilities are important ingredients of advantageous decision-making performance, but empirical evidence is still limited. The results of our first study show that logical reasoning and basic mental calculation capacities predict ratio processing and that ratio processing predicts decision making under risk. In the second study, logical reasoning together with executive functions predicted probability processing (numeracy and probability knowledge), and probability processing predicted decision making under risk. These findings suggest that increasing an individual's understanding of ratios and probabilities should lead to more advantageous decisions under risk conditions.

Validation of a new mortality risk prediction model for people 65 years and older in northwest Russia: The Crystal risk score.

PubMed

Turusheva, Anna; Frolova, Elena; Bert, Vaes; Hegendoerfer, Eralda; Degryse, Jean-Marie

2017-07-01

Prediction models help to make decisions about further management in clinical practice. This study aims to develop a mortality risk score based on previously identified risk predictors and to perform internal and external validations. In a population-based prospective cohort study of 611 community-dwelling individuals aged 65+ in St. Petersburg (Russia), all-cause mortality risks over 2.5 years follow-up were determined based on the results obtained from anthropometry, medical history, physical performance tests, spirometry and laboratory tests. C-statistic, risk reclassification analysis, integrated discrimination improvement analysis, decision curves analysis, internal validation and external validation were performed. Older adults were at higher risk for mortality [HR (95%CI)=4.54 (3.73-5.52)] when two or more of the following components were present: poor physical performance, low muscle mass, poor lung function, and anemia. If anemia was combined with high C-reactive protein (CRP) and high B-type natriuretic peptide (BNP) was added the HR (95%CI) was slightly higher (5.81 (4.73-7.14)) even after adjusting for age, sex and comorbidities. Our models were validated in an external population of adults 80+. The extended model had a better predictive capacity for cardiovascular mortality [HR (95%CI)=5.05 (2.23-11.44)] compared to the baseline model [HR (95%CI)=2.17 (1.18-4.00)] in the external population. We developed and validated a new risk prediction score that may be used to identify older adults at higher risk for mortality in Russia. Additional studies need to determine which targeted interventions improve the outcomes of these at-risk individuals. Copyright © 2017 Elsevier B.V. All rights reserved.

Delirium prediction in the intensive care unit: comparison of two delirium prediction models.

PubMed

Wassenaar, Annelies; Schoonhoven, Lisette; Devlin, John W; van Haren, Frank M P; Slooter, Arjen J C; Jorens, Philippe G; van der Jagt, Mathieu; Simons, Koen S; Egerod, Ingrid; Burry, Lisa D; Beishuizen, Albertus; Matos, Joaquim; Donders, A Rogier T; Pickkers, Peter; van den Boogaard, Mark

2018-05-05

Accurate prediction of delirium in the intensive care unit (ICU) may facilitate efficient use of early preventive strategies and stratification of ICU patients by delirium risk in clinical research, but the optimal delirium prediction model to use is unclear. We compared the predictive performance and user convenience of the prediction  model for delirium (PRE-DELIRIC) and early prediction model for delirium (E-PRE-DELIRIC) in ICU patients and determined the value of a two-stage calculation. This 7-country, 11-hospital, prospective cohort study evaluated consecutive adults admitted to the ICU who could be reliably assessed for delirium using the Confusion Assessment Method-ICU or the Intensive Care Delirium Screening Checklist. The predictive performance of the models was measured using the area under the receiver operating characteristic curve. Calibration was assessed graphically. A physician questionnaire evaluated user convenience. For the two-stage calculation we used E-PRE-DELIRIC immediately after ICU admission and updated the prediction using PRE-DELIRIC after 24 h. In total 2178 patients were included. The area under the receiver operating characteristic curve was significantly greater for PRE-DELIRIC (0.74 (95% confidence interval 0.71-0.76)) compared to E-PRE-DELIRIC (0.68 (95% confidence interval 0.66-0.71)) (z score of - 2.73 (p < 0.01)). Both models were well-calibrated. The sensitivity improved when using the two-stage calculation in low-risk patients. Compared to PRE-DELIRIC, ICU physicians (n = 68) rated the E-PRE-DELIRIC model more feasible. While both ICU delirium prediction models have moderate-to-good performance, the PRE-DELIRIC model predicts delirium better. However, ICU physicians rated the user convenience of E-PRE-DELIRIC superior to PRE-DELIRIC. In low-risk patients the delirium prediction further improves after an update with the PRE-DELIRIC model after 24 h. ClinicalTrials.gov, NCT02518646 . Registered on 21 July 2015.

Modelling the seasonality of Lyme disease risk and the potential impacts of a warming climate within the heterogeneous landscapes of Scotland.

PubMed

Li, Sen; Gilbert, Lucy; Harrison, Paula A; Rounsevell, Mark D A

2016-03-01

Lyme disease is the most prevalent vector-borne disease in the temperate Northern Hemisphere. The abundance of infected nymphal ticks is commonly used as a Lyme disease risk indicator. Temperature can influence the dynamics of disease by shaping the activity and development of ticks and, hence, altering the contact pattern and pathogen transmission between ticks and their host animals. A mechanistic, agent-based model was developed to study the temperature-driven seasonality of Ixodes ricinus ticks and transmission of Borrelia burgdorferi sensu lato across mainland Scotland. Based on 12-year averaged temperature surfaces, our model predicted that Lyme disease risk currently peaks in autumn, approximately six weeks after the temperature peak. The risk was predicted to decrease with increasing altitude. Increases in temperature were predicted to prolong the duration of the tick questing season and expand the risk area to higher altitudinal and latitudinal regions. These predicted impacts on tick population ecology may be expected to lead to greater tick-host contacts under climate warming and, hence, greater risks of pathogen transmission. The model is useful in improving understanding of the spatial determinants and system mechanisms of Lyme disease pathogen transmission and its sensitivity to temperature changes. © 2016 The Author(s).

Modelling the seasonality of Lyme disease risk and the potential impacts of a warming climate within the heterogeneous landscapes of Scotland

PubMed Central

Gilbert, Lucy; Harrison, Paula A.; Rounsevell, Mark D. A.

2016-01-01

Lyme disease is the most prevalent vector-borne disease in the temperate Northern Hemisphere. The abundance of infected nymphal ticks is commonly used as a Lyme disease risk indicator. Temperature can influence the dynamics of disease by shaping the activity and development of ticks and, hence, altering the contact pattern and pathogen transmission between ticks and their host animals. A mechanistic, agent-based model was developed to study the temperature-driven seasonality of Ixodes ricinus ticks and transmission of Borrelia burgdorferi sensu lato across mainland Scotland. Based on 12-year averaged temperature surfaces, our model predicted that Lyme disease risk currently peaks in autumn, approximately six weeks after the temperature peak. The risk was predicted to decrease with increasing altitude. Increases in temperature were predicted to prolong the duration of the tick questing season and expand the risk area to higher altitudinal and latitudinal regions. These predicted impacts on tick population ecology may be expected to lead to greater tick–host contacts under climate warming and, hence, greater risks of pathogen transmission. The model is useful in improving understanding of the spatial determinants and system mechanisms of Lyme disease pathogen transmission and its sensitivity to temperature changes. PMID:27030039

Bankruptcy prediction for credit risk using neural networks: a survey and new results.

PubMed

Atiya, A F

2001-01-01

The prediction of corporate bankruptcies is an important and widely studied topic since it can have significant impact on bank lending decisions and profitability. This work presents two contributions. First we review the topic of bankruptcy prediction, with emphasis on neural-network (NN) models. Second, we develop an NN bankruptcy prediction model. Inspired by one of the traditional credit risk models developed by Merton (1974), we propose novel indicators for the NN system. We show that the use of these indicators in addition to traditional financial ratio indicators provides a significant improvement in the (out-of-sample) prediction accuracy (from 81.46% to 85.5% for a three-year-ahead forecast).

Risk stratification for arrhythmic death in an emergency department cohort: a new method of nonlinear PD2i analysis of the ECG

PubMed Central

Skinner, James E; Meyer, Michael; Dalsey, William C; Nester, Brian A; Ramalanjaona, George; O’Neil, Brian J; Mangione, Antoinette; Terregino, Carol; Moreyra, Abel; Weiss, Daniel N; Anchin, Jerry M; Geary, Una; Taggart, Pamela

2008-01-01

Heart rate variability (HRV) reflects both cardiac autonomic function and risk of sudden arrhythmic death (AD). Indices of HRV based on linear stochastic models are independent risk factors for AD in postmyocardial infarction (MI) cohorts. Indices based on nonlinear deterministic models have a higher sensitivity and specificity for predicting AD in retrospective data. A new nonlinear deterministic model, the automated Point Correlation Dimension (PD2i), was prospectively evaluated for prediction of AD. Patients were enrolled (N = 918) in 6 emergency departments (EDs) upon presentation with chest pain and being determined to be at risk of acute MI (AMI) >7%. Brief digital ECGs (>1000 heartbeats, ∼15 min) were recorded and automated PD2i results obtained. Out-of-hospital AD was determined by modified Hinkle-Thaler criteria. All-cause mortality at 1 year was 6.2%, with 3.5% being ADs. Of the AD fatalities, 34% were without previous history of MI or diagnosis of AMI. The PD2i prediction of AD had sensitivity = 96%, specificity = 85%, negative predictive value = 99%, and relative risk >24.2 (p ≤ 0.001). HRV analysis by the time-dependent nonlinear PD2i algorithm can accurately predict risk of AD in an ED cohort and may have both life-saving and resource-saving implications for individual risk assessment. PMID:19209249

Multivariate logistic regression analysis of postoperative complications and risk model establishment of gastrectomy for gastric cancer: A single-center cohort report.

PubMed

Zhou, Jinzhe; Zhou, Yanbing; Cao, Shougen; Li, Shikuan; Wang, Hao; Niu, Zhaojian; Chen, Dong; Wang, Dongsheng; Lv, Liang; Zhang, Jian; Li, Yu; Jiao, Xuelong; Tan, Xiaojie; Zhang, Jianli; Wang, Haibo; Zhang, Bingyuan; Lu, Yun; Sun, Zhenqing

2016-01-01

Reporting of surgical complications is common, but few provide information about the severity and estimate risk factors of complications. If have, but lack of specificity. We retrospectively analyzed data on 2795 gastric cancer patients underwent surgical procedure at the Affiliated Hospital of Qingdao University between June 2007 and June 2012, established multivariate logistic regression model to predictive risk factors related to the postoperative complications according to the Clavien-Dindo classification system. Twenty-four out of 86 variables were identified statistically significant in univariate logistic regression analysis, 11 significant variables entered multivariate analysis were employed to produce the risk model. Liver cirrhosis, diabetes mellitus, Child classification, invasion of neighboring organs, combined resection, introperative transfusion, Billroth II anastomosis of reconstruction, malnutrition, surgical volume of surgeons, operating time and age were independent risk factors for postoperative complications after gastrectomy. Based on logistic regression equation, p=Exp∑BiXi / (1+Exp∑BiXi), multivariate logistic regression predictive model that calculated the risk of postoperative morbidity was developed, p = 1/(1 + e((4.810-1.287X1-0.504X2-0.500X3-0.474X4-0.405X5-0.318X6-0.316X7-0.305X8-0.278X9-0.255X10-0.138X11))). The accuracy, sensitivity and specificity of the model to predict the postoperative complications were 86.7%, 76.2% and 88.6%, respectively. This risk model based on Clavien-Dindo grading severity of complications system and logistic regression analysis can predict severe morbidity specific to an individual patient's risk factors, estimate patients' risks and benefits of gastric surgery as an accurate decision-making tool and may serve as a template for the development of risk models for other surgical groups.

Prediction of near-term breast cancer risk using a Bayesian belief network

NASA Astrophysics Data System (ADS)

Zheng, Bin; Ramalingam, Pandiyarajan; Hariharan, Harishwaran; Leader, Joseph K.; Gur, David

2013-03-01

Accurately predicting near-term breast cancer risk is an important prerequisite for establishing an optimal personalized breast cancer screening paradigm. In previous studies, we investigated and tested the feasibility of developing a unique near-term breast cancer risk prediction model based on a new risk factor associated with bilateral mammographic density asymmetry between the left and right breasts of a woman using a single feature. In this study we developed a multi-feature based Bayesian belief network (BBN) that combines bilateral mammographic density asymmetry with three other popular risk factors, namely (1) age, (2) family history, and (3) average breast density, to further increase the discriminatory power of our cancer risk model. A dataset involving "prior" negative mammography examinations of 348 women was used in the study. Among these women, 174 had breast cancer detected and verified in the next sequential screening examinations, and 174 remained negative (cancer-free). A BBN was applied to predict the risk of each woman having cancer detected six to 18 months later following the negative screening mammography. The prediction results were compared with those using single features. The prediction accuracy was significantly increased when using the BBN. The area under the ROC curve increased from an AUC=0.70 to 0.84 (p<0.01), while the positive predictive value (PPV) and negative predictive value (NPV) also increased from a PPV=0.61 to 0.78 and an NPV=0.65 to 0.75, respectively. This study demonstrates that a multi-feature based BBN can more accurately predict the near-term breast cancer risk than with a single feature.

Predictive model for serious bacterial infections among infants younger than 3 months of age.

PubMed

Bachur, R G; Harper, M B

2001-08-01

To develop a data-derived model for predicting serious bacterial infection (SBI) among febrile infants <3 months old. All infants /=38.0 degrees C seen in an urban emergency department (ED) were retrospectively identified. SBI was defined as a positive culture of urine, blood, or cerebrospinal fluid. Tree-structured analysis via recursive partitioning was used to develop the model. SBI or No-SBI was the dichotomous outcome variable, and age, temperature, urinalysis (UA), white blood cell (WBC) count, absolute neutrophil count, and cerebrospinal fluid WBC were entered as potential predictors. The model was tested by V-fold cross-validation. Of 5279 febrile infants studied, SBI was diagnosed in 373 patients (7%): 316 urinary tract infections (UTIs), 17 meningitis, and 59 bacteremia (8 with meningitis, 11 with UTIs). The model sequentially used 4 clinical parameters to define high-risk patients: positive UA, WBC count >/=20 000/mm(3) or /=39.6 degrees C, and age <13 days. The sensitivity of the model for SBI is 82% (95% confidence interval [CI]: 78%-86%) and the negative predictive value is 98.3% (95% CI: 97.8%-98.7%). The negative predictive value for bacteremia or meningitis is 99.6% (95% CI: 99.4%-99.8%). The relative risk between high- and low-risk groups is 12.1 (95% CI: 9.3-15.6). Sixty-six SBI patients (18%) were misclassified into the lower risk group: 51 UTIs, 14 with bacteremia, and 1 with meningitis. Decision-tree analysis using common clinical variables can reasonably predict febrile infants at high-risk for SBI. Sequential use of UA, WBC count, temperature, and age can identify infants who are at high risk of SBI with a relative risk of 12.1 compared with lower-risk infants.

Prediction of First Cardiovascular Disease Event in Type 1 Diabetes Mellitus: The Steno Type 1 Risk Engine.

PubMed

Vistisen, Dorte; Andersen, Gregers Stig; Hansen, Christian Stevns; Hulman, Adam; Henriksen, Jan Erik; Bech-Nielsen, Henning; Jørgensen, Marit Eika

2016-03-15

Patients with type 1 diabetes mellitus are at increased risk of developing cardiovascular disease (CVD), but they are currently undertreated. There are no risk scores used on a regular basis in clinical practice for assessing the risk of CVD in type 1 diabetes mellitus. From 4306 clinically diagnosed adult patients with type 1 diabetes mellitus, we developed a prediction model for estimating the risk of first fatal or nonfatal CVD event (ischemic heart disease, ischemic stroke, heart failure, and peripheral artery disease). Detailed clinical data including lifestyle factors were linked to event data from validated national registers. The risk prediction model was developed by using a 2-stage approach. First, a nonparametric, data-driven approach was used to identify potentially informative risk factors and interactions (random forest and survival tree analysis). Second, based on results from the first step, Poisson regression analysis was used to derive the final model. The final CVD prediction model was externally validated in a different population of 2119 patients with type 1 diabetes mellitus. During a median follow-up of 6.8 years (interquartile range, 2.9-10.9) a total of 793 (18.4%) patients developed CVD. The final prediction model included age, sex, diabetes duration, systolic blood pressure, low-density lipoprotein cholesterol, hemoglobin A1c, albuminuria, glomerular filtration rate, smoking, and exercise. Discrimination was excellent for a 5-year CVD event with a C-statistic of 0.826 (95% confidence interval, 0.807-0.845) in the derivation data and a C-statistic of 0.803 (95% confidence interval, 0.767-0.839) in the validation data. The Hosmer-Lemeshow test showed good calibration (P>0.05) in both cohorts. This high-performing CVD risk model allows for the implementation of decision rules in a clinical setting. © 2016 American Heart Association, Inc.

Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges

PubMed Central

Goldstein, Benjamin A.; Navar, Ann Marie; Carter, Rickey E.

2017-01-01

Abstract Risk prediction plays an important role in clinical cardiology research. Traditionally, most risk models have been based on regression models. While useful and robust, these statistical methods are limited to using a small number of predictors which operate in the same way on everyone, and uniformly throughout their range. The purpose of this review is to illustrate the use of machine-learning methods for development of risk prediction models. Typically presented as black box approaches, most machine-learning methods are aimed at solving particular challenges that arise in data analysis that are not well addressed by typical regression approaches. To illustrate these challenges, as well as how different methods can address them, we consider trying to predicting mortality after diagnosis of acute myocardial infarction. We use data derived from our institution's electronic health record and abstract data on 13 regularly measured laboratory markers. We walk through different challenges that arise in modelling these data and then introduce different machine-learning approaches. Finally, we discuss general issues in the application of machine-learning methods including tuning parameters, loss functions, variable importance, and missing data. Overall, this review serves as an introduction for those working on risk modelling to approach the diffuse field of machine learning. PMID:27436868

A growing degree-day model for determination of Fasciola hepatica infection risk in New Zealand with future predictions using climate change models.

PubMed

Haydock, L A J; Pomroy, W E; Stevenson, M A; Lawrence, K E

2016-09-15

Infections of ruminants with Fasciola hepatica are considered to be of regional importance within New Zealand but there is very little recent information on its prevalence or severity other than anecdotal reports. Generally they are considered to be of secondary importance compared to gastrointestinal nematode infections. Utilizing data from Virtual Climate Stations (n=11491) distributed on a 5km grid around New Zealand a growing degree-day model was used to describe the risk of infection with liver fluke from 1972 to 2012 and then to apply the predictions to estimate the risk of fluke infections within New Zealand for the years 2040 and 2090. The growing degree-day model was validated against the most recent survey of infection within New Zealand in 1984. A strong positive linear relationship for 1984 between F. hepatica prevalence in lambs and infection risk (p<0.001; R 2 =0.71) was found indicating the model was effective for New Zealand. A linear regression for risk values from 14 regions in New Zealand for 1972-2012 did not show any discernible change in risk of infection over this time period (p>0.05). Post-hoc comparisons indicate the risk in Westland was found to be substantially higher (p<0.05) than all other regions with Northland ranked second highest. Notable predicted changes in F. hepatica infection risk in 2040 and 2090 were detected although they did vary between different climate change scenarios. The highest average percentage changes in infection risk were found in regions with low initial risk values such as Canterbury and Otago; in these regions 2090 infection risk is expected to rise by an average of 186% and 184%, respectively. Despite the already high levels of infection risk in Westland, values are expected to rise by a further 76% by 2090. The model does show some areas with little change with Taranaki predicted to experience only very minor increases in infection risk with average 2040 and 2090 predicted changes of 0% and 29%, respectively. Overall, these results suggest the significance of F. hepatica in New Zealand farming systems is probably underestimated and that this risk will generally increase with global warming following climate change. Copyright © 2016 Elsevier B.V. All rights reserved.

Predicting suicides after outpatient mental health visits in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS)

PubMed Central

Kessler, Ronald C.; Stein, Murray B.; Petukhova, Maria V.; Bliese, Paul; Bossarte, Robert M.; Bromet, Evelyn J.; Fullerton, Carol S.; Gilman, Stephen E.; Ivany, Christopher; Lewandowski-Romps, Lisa; Bell, Amy Millikan; Naifeh, James A.; Nock, Matthew K.; Reis, Benjamin Y.; Rosellini, Anthony J.; Sampson, Nancy A.; Zaslavsky, Alan M.; Ursano, Robert J.

2016-01-01

The 2013 U.S. Veterans Administration/Department of Defense Clinical Practice Guidelines (VA/DoD CPG) require comprehensive suicide risk assessments for VA/DoD patients with mental disorders but provide minimal guidance on how to carry out these assessments. Given that clinician-based assessments are known not to be strong predictors of suicide, we investigated whether a precision medicine model using administrative data after outpatient mental health specialty visits could be developed to predict suicides among outpatients. We focused on male non-deployed Regular U.S. Army soldiers because they account for the vast majority of such suicides. Four machine learning classifiers (naïve Bayes, random forests, support vector regression, elastic net penalized regression) were explored. 41.5% of Army suicides in 2004-2009 occurred among the 12.0% of soldiers seen as outpatient by mental health specialists, with risk especially high within 26 weeks of visits. An elastic net classifier with 10-14 predictors optimized sensitivity (45.6% of suicide deaths occurring after the 15% of visits with highest predicted risk). Good model stability was found for a model using 2004-2007 data to predict 2008-2009 suicides, although stability decreased in a model using 2008-2009 data to predict 2010-2012 suicides. The 5% of visits with highest risk included only 0.1% of soldiers (1047.1 suicides/100,000 person-years in the 5 weeks after the visit). This is a high enough concentration of risk to have implications for targeting preventive interventions. An even better model might be developed in the future by including the enriched information on clinician-evaluated suicide risk mandated by the VA/DoD CPG to be recorded. PMID:27431294

Reduced risk estimations after remediation of lead (Pb) in drinking water at two US school districts.

PubMed

Triantafyllidou, Simoni; Le, Trung; Gallagher, Daniel; Edwards, Marc

2014-01-01

The risk of students to develop elevated blood lead from drinking water consumption at schools was assessed, which is a different approach from predictions of geometric mean blood lead levels. Measured water lead levels (WLLs) from 63 elementary schools in Seattle and 601 elementary schools in Los Angeles were acquired before and after voluntary remediation of water lead contamination problems. Combined exposures to measured school WLLs (first-draw and flushed, 50% of water consumption) and home WLLs (50% of water consumption) were used as inputs to the Integrated Exposure Uptake Biokinetic (IEUBK) model for each school. In Seattle an average 11.2% of students were predicted to exceed a blood lead threshold of 5 μg/dL across 63 schools pre-remediation, but predicted risks at individual schools varied (7% risk of exceedance at a "low exposure school", 11% risk at a "typical exposure school", and 31% risk at a "high exposure school"). Addition of water filters and removal of lead plumbing lowered school WLL inputs to the model, and reduced the predicted risk output to 4.8% on average for Seattle elementary students across all 63 schools. The remnant post-remediation risk was attributable to other assumed background lead sources in the model (air, soil, dust, diet and home WLLs), with school WLLs practically eliminated as a health threat. Los Angeles schools instead instituted a flushing program which was assumed to eliminate first-draw WLLs as inputs to the model. With assumed benefits of remedial flushing, the predicted average risk of students to exceed a BLL threshold of 5 μg/dL dropped from 8.6% to 6.0% across 601 schools. In an era with increasingly stringent public health goals (e.g., reduction of blood lead safety threshold from 10 to 5 μg/dL), quantifiable health benefits to students were predicted after water lead remediation at two large US school systems. © 2013.

Predicting readmission risk with institution-specific prediction models.

PubMed

Yu, Shipeng; Farooq, Faisal; van Esbroeck, Alexander; Fung, Glenn; Anand, Vikram; Krishnapuram, Balaji

2015-10-01

The ability to predict patient readmission risk is extremely valuable for hospitals, especially under the Hospital Readmission Reduction Program of the Center for Medicare and Medicaid Services which went into effect starting October 1, 2012. There is a plethora of work in the literature that deals with developing readmission risk prediction models, but most of them do not have sufficient prediction accuracy to be deployed in a clinical setting, partly because different hospitals may have different characteristics in their patient populations. We propose a generic framework for institution-specific readmission risk prediction, which takes patient data from a single institution and produces a statistical risk prediction model optimized for that particular institution and, optionally, for a specific condition. This provides great flexibility in model building, and is also able to provide institution-specific insights in its readmitted patient population. We have experimented with classification methods such as support vector machines, and prognosis methods such as the Cox regression. We compared our methods with industry-standard methods such as the LACE model, and showed the proposed framework is not only more flexible but also more effective. We applied our framework to patient data from three hospitals, and obtained some initial results for heart failure (HF), acute myocardial infarction (AMI), pneumonia (PN) patients as well as patients with all conditions. On Hospital 2, the LACE model yielded AUC 0.57, 0.56, 0.53 and 0.55 for AMI, HF, PN and All Cause readmission prediction, respectively, while the proposed model yielded 0.66, 0.65, 0.63, 0.74 for the corresponding conditions, all significantly better than the LACE counterpart. The proposed models that leverage all features at discharge time is more accurate than the models that only leverage features at admission time (0.66 vs. 0.61 for AMI, 0.65 vs. 0.61 for HF, 0.63 vs. 0.56 for PN, 0.74 vs. 0.60 for All Cause). Furthermore, the proposed admission-time models already outperform the performance of LACE, which is a discharge-time model (0.61 vs. 0.57 for AMI, 0.61 vs. 0.56 for HF, 0.56 vs. 0.53 for PN, 0.60 vs. 0.55 for All Cause). Similar conclusions can be drawn from other hospitals as well. The same performance comparison also holds for precision and recall at top-decile predictions. Most of the performance improvements are statistically significant. The institution-specific readmission risk prediction framework is more flexible and more effective than the one-size-fit-all models like the LACE, sometimes twice and three-time more effective. The admission-time models are able to give early warning signs compared to the discharge-time models, and may be able to help hospital staff intervene early while the patient is still in the hospital. Copyright © 2015 Elsevier B.V. All rights reserved.

Absolute fracture risk assessment using lumbar spine and femoral neck bone density measurements: derivation and validation of a hybrid system.

PubMed

Leslie, William D; Lix, Lisa M

2011-03-01

The World Health Organization (WHO) Fracture Risk Assessment Tool (FRAX) computes 10-year probability of major osteoporotic fracture from multiple risk factors, including femoral neck (FN) T-scores. Lumbar spine (LS) measurements are not currently part of the FRAX formulation but are used widely in clinical practice, and this creates confusion when there is spine-hip discordance. Our objective was to develop a hybrid 10-year absolute fracture risk assessment system in which nonvertebral (NV) fracture risk was assessed from the FN and clinical vertebral (V) fracture risk was assessed from the LS. We identified 37,032 women age 45 years and older undergoing baseline FN and LS dual-energy X-ray absorptiometry (DXA; 1990-2005) from a population database that contains all clinical DXA results for the Province of Manitoba, Canada. Results were linked to longitudinal health service records for physician billings and hospitalizations to identify nontrauma vertebral and nonvertebral fracture codes after bone mineral density (BMD) testing. The population was randomly divided into equal-sized derivation and validation cohorts. Using the derivation cohort, three fracture risk prediction systems were created from Cox proportional hazards models (adjusted for age and multiple FRAX risk factors): FN to predict combined all fractures, FN to predict nonvertebral fractures, and LS to predict vertebral (without nonvertebral) fractures. The hybrid system was the sum of nonvertebral risk from the FN model and vertebral risk from the LS model. The FN and hybrid systems were both strongly predictive of overall fracture risk (p < .001). In the validation cohort, ROC analysis showed marginally better performance of the hybrid system versus the FN system for overall fracture prediction (p = .24) and significantly better performance for vertebral fracture prediction (p < .001). In a discordance subgroup with FN and LS T-score differences greater than 1 SD, there was a significant improvement in overall fracture prediction with the hybrid method (p = .025). Risk reclassification under the hybrid system showed better alignment with observed fracture risk, with 6.4% of the women reclassified to a different risk category. In conclusion, a hybrid 10-year absolute fracture risk assessment system based on combining FN and LS information is feasible. The improvement in fracture risk prediction is small but supports clinical interest in a system that integrates LS in fracture risk assessment. Copyright © 2011 American Society for Bone and Mineral Research.

Development and Validation of a Practical Two-Step Prediction Model and Clinical Risk Score for Post-Thrombotic Syndrome.

PubMed

Amin, Elham E; van Kuijk, Sander M J; Joore, Manuela A; Prandoni, Paolo; Cate, Hugo Ten; Cate-Hoek, Arina J Ten

2018-06-04

 Post-thrombotic syndrome (PTS) is a common chronic consequence of deep vein thrombosis that affects the quality of life and is associated with substantial costs. In clinical practice, it is not possible to predict the individual patient risk. We develop and validate a practical two-step prediction tool for PTS in the acute and sub-acute phase of deep vein thrombosis.  Multivariable regression modelling with data from two prospective cohorts in which 479 (derivation) and 1,107 (validation) consecutive patients with objectively confirmed deep vein thrombosis of the leg, from thrombosis outpatient clinic of Maastricht University Medical Centre, the Netherlands (derivation) and Padua University hospital in Italy (validation), were included. PTS was defined as a Villalta score of ≥ 5 at least 6 months after acute thrombosis.  Variables in the baseline model in the acute phase were: age, body mass index, sex, varicose veins, history of venous thrombosis, smoking status, provoked thrombosis and thrombus location. For the secondary model, the additional variable was residual vein obstruction. Optimism-corrected area under the receiver operating characteristic curves (AUCs) were 0.71 for the baseline model and 0.60 for the secondary model. Calibration plots showed well-calibrated predictions. External validation of the derived clinical risk scores was successful: AUC, 0.66 (95% confidence interval [CI], 0.63-0.70) and 0.64 (95% CI, 0.60-0.69).  Individual risk for PTS in the acute phase of deep vein thrombosis can be predicted based on readily accessible baseline clinical and demographic characteristics. The individual risk in the sub-acute phase can be predicted with limited additional clinical characteristics. Schattauer GmbH Stuttgart.

Object-oriented regression for building predictive models with high dimensional omics data from translational studies.

PubMed

Zhao, Lue Ping; Bolouri, Hamid

2016-04-01

Maturing omics technologies enable researchers to generate high dimension omics data (HDOD) routinely in translational clinical studies. In the field of oncology, The Cancer Genome Atlas (TCGA) provided funding support to researchers to generate different types of omics data on a common set of biospecimens with accompanying clinical data and has made the data available for the research community to mine. One important application, and the focus of this manuscript, is to build predictive models for prognostic outcomes based on HDOD. To complement prevailing regression-based approaches, we propose to use an object-oriented regression (OOR) methodology to identify exemplars specified by HDOD patterns and to assess their associations with prognostic outcome. Through computing patient's similarities to these exemplars, the OOR-based predictive model produces a risk estimate using a patient's HDOD. The primary advantages of OOR are twofold: reducing the penalty of high dimensionality and retaining the interpretability to clinical practitioners. To illustrate its utility, we apply OOR to gene expression data from non-small cell lung cancer patients in TCGA and build a predictive model for prognostic survivorship among stage I patients, i.e., we stratify these patients by their prognostic survival risks beyond histological classifications. Identification of these high-risk patients helps oncologists to develop effective treatment protocols and post-treatment disease management plans. Using the TCGA data, the total sample is divided into training and validation data sets. After building up a predictive model in the training set, we compute risk scores from the predictive model, and validate associations of risk scores with prognostic outcome in the validation data (P-value=0.015). Copyright © 2016 Elsevier Inc. All rights reserved.

Object-Oriented Regression for Building Predictive Models with High Dimensional Omics Data from Translational Studies

PubMed Central

Zhao, Lue Ping; Bolouri, Hamid

2016-01-01

Maturing omics technologies enable researchers to generate high dimension omics data (HDOD) routinely in translational clinical studies. In the field of oncology, The Cancer Genome Atlas (TCGA) provided funding support to researchers to generate different types of omics data on a common set of biospecimens with accompanying clinical data and to make the data available for the research community to mine. One important application, and the focus of this manuscript, is to build predictive models for prognostic outcomes based on HDOD. To complement prevailing regression-based approaches, we propose to use an object-oriented regression (OOR) methodology to identify exemplars specified by HDOD patterns and to assess their associations with prognostic outcome. Through computing patient’s similarities to these exemplars, the OOR-based predictive model produces a risk estimate using a patient’s HDOD. The primary advantages of OOR are twofold: reducing the penalty of high dimensionality and retaining the interpretability to clinical practitioners. To illustrate its utility, we apply OOR to gene expression data from non-small cell lung cancer patients in TCGA and build a predictive model for prognostic survivorship among stage I patients, i.e., we stratify these patients by their prognostic survival risks beyond histological classifications. Identification of these high-risk patients helps oncologists to develop effective treatment protocols and post-treatment disease management plans. Using the TCGA data, the total sample is divided into training and validation data sets. After building up a predictive model in the training set, we compute risk scores from the predictive model, and validate associations of risk scores with prognostic outcome in the validation data (p=0.015). PMID:26972839

Evaluating Predictive Models of Software Quality

NASA Astrophysics Data System (ADS)

Ciaschini, V.; Canaparo, M.; Ronchieri, E.; Salomoni, D.

2014-06-01

Applications from High Energy Physics scientific community are constantly growing and implemented by a large number of developers. This implies a strong churn on the code and an associated risk of faults, which is unavoidable as long as the software undergoes active evolution. However, the necessities of production systems run counter to this. Stability and predictability are of paramount importance; in addition, a short turn-around time for the defect discovery-correction-deployment cycle is required. A way to reconcile these opposite foci is to use a software quality model to obtain an approximation of the risk before releasing a program to only deliver software with a risk lower than an agreed threshold. In this article we evaluated two quality predictive models to identify the operational risk and the quality of some software products. We applied these models to the development history of several EMI packages with intent to discover the risk factor of each product and compare it with its real history. We attempted to determine if the models reasonably maps reality for the applications under evaluation, and finally we concluded suggesting directions for further studies.

Prediction of five-year all-cause mortality in Chinese patients with type 2 diabetes mellitus - A population-based retrospective cohort study.

PubMed

Wan, Eric Yuk Fai; Fong, Daniel Yee Tak; Fung, Colman Siu Cheung; Yu, Esther Yee Tak; Chin, Weng Yee; Chan, Anca Ka Chun; Lam, Cindy Lo Kuen

2017-06-01

This study aimed to develop and validate an all-cause mortality risk prediction model for Chinese primary care patients with type 2 diabetes mellitus(T2DM) in Hong Kong. A population-based retrospective cohort study was conducted on 132,462 Chinese patients who had received public primary care services during 2010. Each gender sample was randomly split on a 2:1 basis into derivation and validation cohorts and was followed-up for a median period of 5years. Gender-specific mortality risk prediction models showing the interaction effect between predictors and age were derived using Cox proportional hazards regression with forward stepwise approach. Developed models were compared with pre-existing models by Harrell's C-statistic and calibration plot using validation cohort. Common predictors of increased mortality risk in both genders included: age; smoking habit; diabetes duration; use of anti-hypertensive agents, insulin and lipid-lowering drugs; body mass index; hemoglobin A1c; systolic blood pressure(BP); total cholesterol to high-density lipoprotein-cholesterol ratio; urine albumin to creatinine ratio(urine ACR); and estimated glomerular filtration rate(eGFR). Prediction models showed better discrimination with Harrell"'s C-statistics of 0.768(males) and 0.782(females) and calibration power from the plots than previously established models. Our newly developed gender-specific models provide a more accurate predicted 5-year mortality risk for Chinese diabetic patients than other established models. Copyright © 2017 Elsevier Inc. All rights reserved.

Prediction of acute kidney injury within 30 days of cardiac surgery.

PubMed

Ng, Shu Yi; Sanagou, Masoumeh; Wolfe, Rory; Cochrane, Andrew; Smith, Julian A; Reid, Christopher Michael

2014-06-01

To predict acute kidney injury after cardiac surgery. The study included 28,422 cardiac surgery patients who had had no preoperative renal dialysis from June 2001 to June 2009 in 18 hospitals. Logistic regression analyses were undertaken to identify the best combination of risk factors for predicting acute kidney injury. Two models were developed, one including the preoperative risk factors and another including the pre-, peri-, and early postoperative risk factors. The area under the receiver operating characteristic curve was calculated, using split-sample internal validation, to assess model discrimination. The incidence of acute kidney injury was 5.8% (1642 patients). The mortality for patients who experienced acute kidney injury was 17.4% versus 1.6% for patients who did not. On validation, the area under the curve for the preoperative model was 0.77, and the Hosmer-Lemeshow goodness-of-fit P value was .06. For the postoperative model area under the curve was 0.81 and the Hosmer-Lemeshow P value was .6. Both models had good discrimination and acceptable calibration. Acute kidney injury after cardiac surgery can be predicted using preoperative risk factors alone or, with greater accuracy, using pre-, peri-, and early postoperative risk factors. The ability to identify high-risk individuals can be useful in preoperative patient management and for recruitment of appropriate patients to clinical trials. Prediction in the early stages of postoperative care can guide subsequent intensive care of patients and could also be the basis of a retrospective performance audit tool. Copyright © 2014 The American Association for Thoracic Surgery. Published by Mosby, Inc. All rights reserved.

Development of Risk Score for Predicting 3-Year Incidence of Type 2 Diabetes: Japan Epidemiology Collaboration on Occupational Health Study

PubMed Central

Nanri, Akiko; Nakagawa, Tohru; Kuwahara, Keisuke; Yamamoto, Shuichiro; Honda, Toru; Okazaki, Hiroko; Uehara, Akihiko; Yamamoto, Makoto; Miyamoto, Toshiaki; Kochi, Takeshi; Eguchi, Masafumi; Murakami, Taizo; Shimizu, Chii; Shimizu, Makiko; Tomita, Kentaro; Nagahama, Satsue; Imai, Teppei; Nishihara, Akiko; Sasaki, Naoko; Hori, Ai; Sakamoto, Nobuaki; Nishiura, Chihiro; Totsuzaki, Takafumi; Kato, Noritada; Fukasawa, Kenji; Huanhuan, Hu; Akter, Shamima; Kurotani, Kayo; Kabe, Isamu; Mizoue, Tetsuya; Sone, Tomofumi; Dohi, Seitaro

2015-01-01

Objective Risk models and scores have been developed to predict incidence of type 2 diabetes in Western populations, but their performance may differ when applied to non-Western populations. We developed and validated a risk score for predicting 3-year incidence of type 2 diabetes in a Japanese population. Methods Participants were 37,416 men and women, aged 30 or older, who received periodic health checkup in 2008–2009 in eight companies. Diabetes was defined as fasting plasma glucose (FPG) ≥126 mg/dl, random plasma glucose ≥200 mg/dl, glycated hemoglobin (HbA1c) ≥6.5%, or receiving medical treatment for diabetes. Risk scores on non-invasive and invasive models including FPG and HbA1c were developed using logistic regression in a derivation cohort and validated in the remaining cohort. Results The area under the curve (AUC) for the non-invasive model including age, sex, body mass index, waist circumference, hypertension, and smoking status was 0.717 (95% CI, 0.703–0.731). In the invasive model in which both FPG and HbA1c were added to the non-invasive model, AUC was increased to 0.893 (95% CI, 0.883–0.902). When the risk scores were applied to the validation cohort, AUCs (95% CI) for the non-invasive and invasive model were 0.734 (0.715–0.753) and 0.882 (0.868–0.895), respectively. Participants with a non-invasive score of ≥15 and invasive score of ≥19 were projected to have >20% and >50% risk, respectively, of developing type 2 diabetes within 3 years. Conclusions The simple risk score of the non-invasive model might be useful for predicting incident type 2 diabetes, and its predictive performance may be markedly improved by incorporating FPG and HbA1c. PMID:26558900

Development of Risk Score for Predicting 3-Year Incidence of Type 2 Diabetes: Japan Epidemiology Collaboration on Occupational Health Study.

PubMed

Nanri, Akiko; Nakagawa, Tohru; Kuwahara, Keisuke; Yamamoto, Shuichiro; Honda, Toru; Okazaki, Hiroko; Uehara, Akihiko; Yamamoto, Makoto; Miyamoto, Toshiaki; Kochi, Takeshi; Eguchi, Masafumi; Murakami, Taizo; Shimizu, Chii; Shimizu, Makiko; Tomita, Kentaro; Nagahama, Satsue; Imai, Teppei; Nishihara, Akiko; Sasaki, Naoko; Hori, Ai; Sakamoto, Nobuaki; Nishiura, Chihiro; Totsuzaki, Takafumi; Kato, Noritada; Fukasawa, Kenji; Huanhuan, Hu; Akter, Shamima; Kurotani, Kayo; Kabe, Isamu; Mizoue, Tetsuya; Sone, Tomofumi; Dohi, Seitaro

2015-01-01

Risk models and scores have been developed to predict incidence of type 2 diabetes in Western populations, but their performance may differ when applied to non-Western populations. We developed and validated a risk score for predicting 3-year incidence of type 2 diabetes in a Japanese population. Participants were 37,416 men and women, aged 30 or older, who received periodic health checkup in 2008-2009 in eight companies. Diabetes was defined as fasting plasma glucose (FPG) ≥ 126 mg/dl, random plasma glucose ≥ 200 mg/dl, glycated hemoglobin (HbA1c) ≥ 6.5%, or receiving medical treatment for diabetes. Risk scores on non-invasive and invasive models including FPG and HbA1c were developed using logistic regression in a derivation cohort and validated in the remaining cohort. The area under the curve (AUC) for the non-invasive model including age, sex, body mass index, waist circumference, hypertension, and smoking status was 0.717 (95% CI, 0.703-0.731). In the invasive model in which both FPG and HbA1c were added to the non-invasive model, AUC was increased to 0.893 (95% CI, 0.883-0.902). When the risk scores were applied to the validation cohort, AUCs (95% CI) for the non-invasive and invasive model were 0.734 (0.715-0.753) and 0.882 (0.868-0.895), respectively. Participants with a non-invasive score of ≥ 15 and invasive score of ≥ 19 were projected to have >20% and >50% risk, respectively, of developing type 2 diabetes within 3 years. The simple risk score of the non-invasive model might be useful for predicting incident type 2 diabetes, and its predictive performance may be markedly improved by incorporating FPG and HbA1c.

Predicting the risk for hospital-onset Clostridium difficile infection (HO-CDI) at the time of inpatient admission: HO-CDI risk score.

PubMed

Tabak, Ying P; Johannes, Richard S; Sun, Xiaowu; Nunez, Carlos M; McDonald, L Clifford

2015-06-01

To predict the likelihood of hospital-onset Clostridium difficile infection (HO-CDI) based on patient clinical presentations at admission Retrospective data analysis Six US acute care hospitals Adult inpatients We used clinical data collected at the time of admission in electronic health record (EHR) systems to develop and validate a HO-CDI predictive model. The outcome measure was HO-CDI cases identified by a nonduplicate positive C. difficile toxin assay result with stool specimens collected >48 hours after inpatient admission. We fit a logistic regression model to predict the risk of HO-CDI. We validated the model using 1,000 bootstrap simulations. Among 78,080 adult admissions, 323 HO-CDI cases were identified (ie, a rate of 4.1 per 1,000 admissions). The logistic regression model yielded 14 independent predictors, including hospital community onset CDI pressure, patient age ≥65, previous healthcare exposures, CDI in previous admission, admission to the intensive care unit, albumin ≤3 g/dL, creatinine >2.0 mg/dL, bands >32%, platelets ≤150 or >420 109/L, and white blood cell count >11,000 mm3. The model had a c-statistic of 0.78 (95% confidence interval [CI], 0.76-0.81) with good calibration. Among 79% of patients with risk scores of 0-7, 19 HO-CDIs occurred per 10,000 admissions; for patients with risk scores >20, 623 HO-CDIs occurred per 10,000 admissions (P<.0001). Using clinical parameters available at the time of admission, this HO-CDI model demonstrated good predictive ability, and it may have utility as an early risk identification tool for HO-CDI preventive interventions and outcome comparisons.

Conservation Risks: When Will Rhinos be Extinct?

PubMed

Haas, Timothy C; Ferreira, Sam M

2016-08-01

We develop a risk intelligence system for biodiversity enterprises. Such enterprises depend on a supply of endangered species for their revenue. Many of these enterprises, however, cannot purchase a supply of this resource and are largely unable to secure the resource against theft in the form of poaching. Because replacements are not available once a species becomes extinct, insurance products are not available to reduce the risk exposure of these enterprises to an extinction event. For many species, the dynamics of anthropogenic impacts driven by economic as well as noneconomic values of associated wildlife products along with their ecological stressors can help meaningfully predict extinction risks. We develop an agent/individual-based economic-ecological model that captures these effects and apply it to the case of South African rhinos. Our model uses observed rhino dynamics and poaching statistics. It seeks to predict rhino extinction under the present scenario. This scenario has no legal horn trade, but allows live African rhino trade and legal hunting. Present rhino populations are small and threatened by a rising onslaught of poaching. This present scenario and associated dynamics predicts continued decline in rhino population size with accelerated extinction risks of rhinos by 2036. Our model supports the computation of extinction risks at any future time point. This capability can be used to evaluate the effectiveness of proposed conservation strategies at reducing a species' extinction risk. Models used to compute risk predictions, however, need to be statistically estimated. We point out that statistically fitting such models to observations will involve massive numbers of observations on consumer behavior and time-stamped location observations on thousands of animals. Finally, we propose Big Data algorithms to perform such estimates and to interpret the fitted model's output.

Performance of comorbidity, risk adjustment, and functional status measures in expenditure prediction for patients with diabetes.

PubMed

Maciejewski, Matthew L; Liu, Chuan-Fen; Fihn, Stephan D

2009-01-01

To compare the ability of generic comorbidity and risk adjustment measures, a diabetes-specific measure, and a self-reported functional status measure to explain variation in health care expenditures for individuals with diabetes. This study included a retrospective cohort of 3,092 diabetic veterans participating in a multisite trial. Two comorbidity measures, four risk adjusters, a functional status measure, a diabetes complication count, and baseline expenditures were constructed from administrative and survey data. Outpatient, inpatient, and total expenditure models were estimated using ordinary least squares regression. Adjusted R(2) statistics and predictive ratios were compared across measures to assess overall explanatory power and explanatory power of low- and high-cost subgroups. Administrative data-based risk adjusters performed better than the comorbidity, functional status, and diabetes-specific measures in all expenditure models. The diagnostic cost groups (DCGs) measure had the greatest predictive power overall and for the low- and high-cost subgroups, while the diabetes-specific measure had the lowest predictive power. A model with DCGs and the diabetes-specific measure modestly improved predictive power. Existing generic measures can be useful for diabetes-specific research and policy applications, but more predictive diabetes-specific measures are needed.

Comparing Mammography Abnormality Features and Genetic Variants in the Prediction of Breast Cancer in Women Recommended for Breast Biopsy

PubMed Central

Burnside, Elizabeth S.; Liu, Jie; Wu, Yirong; Onitilo, Adedayo A.; McCarty, Catherine; Page, C. David; Peissig, Peggy; Trentham-Dietz, Amy; Kitchner, Terrie; Fan, Jun; Yuan, Ming

2015-01-01

Rationale and Objectives The discovery of germline genetic variants associated with breast cancer has engendered interest in risk stratification for improved, targeted detection and diagnosis. However, there has yet to be a comparison of the predictive ability of these genetic variants with mammography abnormality descriptors. Materials and Methods Our IRB-approved, HIPAA-compliant study utilized a personalized medicine registry in which participants consented to provide a DNA sample and participate in longitudinal follow-up. In our retrospective, age-matched, case-controlled study of 373 cases and 395 controls who underwent breast biopsy, we collected risk factors selected a priori based on the literature including: demographic variables based on the Gail model, common germline genetic variants, and diagnostic mammography findings according to BI-RADS. We developed predictive models using logistic regression to determine the predictive ability of: 1) demographic variables, 2) 10 selected genetic variants, or 3) mammography BI-RADS features. We evaluated each model in turn by calculating a risk score for each patient using 10-fold cross validation; used this risk estimate to construct ROC curves; and compared the AUC of each using the DeLong method. Results The performance of the regression model using demographic risk factors was not statistically different from the model using genetic variants (p=0.9). The model using mammography features (AUC = 0.689) was superior to both the demographic model (AUC = .598; p<0.001) and the genetic model (AUC = .601; p<0.001). Conclusion BI-RADS features exceeded the ability of demographic and 10 selected germline genetic variants to predict breast cancer in women recommended for biopsy. PMID:26514439

A Risk Prediction Model for Sporadic CRC Based on Routine Lab Results.

PubMed

Boursi, Ben; Mamtani, Ronac; Hwang, Wei-Ting; Haynes, Kevin; Yang, Yu-Xiao

2016-07-01

Current risk scores for colorectal cancer (CRC) are based on demographic and behavioral factors and have limited predictive values. To develop a novel risk prediction model for sporadic CRC using clinical and laboratory data in electronic medical records. We conducted a nested case-control study in a UK primary care database. Cases included those with a diagnostic code of CRC, aged 50-85. Each case was matched with four controls using incidence density sampling. CRC predictors were examined using univariate conditional logistic regression. Variables with p value <0.25 in the univariate analysis were further evaluated in multivariate models using backward elimination. Discrimination was assessed using receiver operating curve. Calibration was evaluated using the McFadden's R2. Net reclassification index (NRI) associated with incorporation of laboratory results was calculated. Results were internally validated. A model similar to existing CRC prediction models which included age, sex, height, obesity, ever smoking, alcohol dependence, and previous screening colonoscopy had an AUC of 0.58 (0.57-0.59) with poor goodness of fit. A laboratory-based model including hematocrit, MCV, lymphocytes, and neutrophil-lymphocyte ratio (NLR) had an AUC of 0.76 (0.76-0.77) and a McFadden's R2 of 0.21 with a NRI of 47.6 %. A combined model including sex, hemoglobin, MCV, white blood cells, platelets, NLR, and oral hypoglycemic use had an AUC of 0.80 (0.79-0.81) with a McFadden's R2 of 0.27 and a NRI of 60.7 %. Similar results were shown in an internal validation set. A laboratory-based risk model had good predictive power for sporadic CRC risk.

Non-Targeted Effects Models Predict Significantly Higher Mars Mission Cancer Risk than Targeted Effects Models

DOE PAGES

Cucinotta, Francis A.; Cacao, Eliedonna

2017-05-12

Cancer risk is an important concern for galactic cosmic ray (GCR) exposures, which consist of a wide-energy range of protons, heavy ions and secondary radiation produced in shielding and tissues. Relative biological effectiveness (RBE) factors for surrogate cancer endpoints in cell culture models and tumor induction in mice vary considerable, including significant variations for different tissues and mouse strains. Many studies suggest non-targeted effects (NTE) occur for low doses of high linear energy transfer (LET) radiation, leading to deviation from the linear dose response model used in radiation protection. Using the mouse Harderian gland tumor experiment, the only extensive data-setmore » for dose response modelling with a variety of particle types (>4), for the first-time a particle track structure model of tumor prevalence is used to investigate the effects of NTEs in predictions of chronic GCR exposure risk. The NTE model led to a predicted risk 2-fold higher compared to a targeted effects model. The scarcity of data with animal models for tissues that dominate human radiation cancer risk, including lung, colon, breast, liver, and stomach, suggest that studies of NTEs in other tissues are urgently needed prior to long-term space missions outside the protection of the Earth’s geomagnetic sphere.« less

Non-Targeted Effects Models Predict Significantly Higher Mars Mission Cancer Risk than Targeted Effects Models

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cucinotta, Francis A.; Cacao, Eliedonna

Cancer risk is an important concern for galactic cosmic ray (GCR) exposures, which consist of a wide-energy range of protons, heavy ions and secondary radiation produced in shielding and tissues. Relative biological effectiveness (RBE) factors for surrogate cancer endpoints in cell culture models and tumor induction in mice vary considerable, including significant variations for different tissues and mouse strains. Many studies suggest non-targeted effects (NTE) occur for low doses of high linear energy transfer (LET) radiation, leading to deviation from the linear dose response model used in radiation protection. Using the mouse Harderian gland tumor experiment, the only extensive data-setmore » for dose response modelling with a variety of particle types (>4), for the first-time a particle track structure model of tumor prevalence is used to investigate the effects of NTEs in predictions of chronic GCR exposure risk. The NTE model led to a predicted risk 2-fold higher compared to a targeted effects model. The scarcity of data with animal models for tissues that dominate human radiation cancer risk, including lung, colon, breast, liver, and stomach, suggest that studies of NTEs in other tissues are urgently needed prior to long-term space missions outside the protection of the Earth’s geomagnetic sphere.« less

A Review on Automatic Mammographic Density and Parenchymal Segmentation

PubMed Central

He, Wenda; Juette, Arne; Denton, Erika R. E.; Oliver, Arnau

2015-01-01

Breast cancer is the most frequently diagnosed cancer in women. However, the exact cause(s) of breast cancer still remains unknown. Early detection, precise identification of women at risk, and application of appropriate disease prevention measures are by far the most effective way to tackle breast cancer. There are more than 70 common genetic susceptibility factors included in the current non-image-based risk prediction models (e.g., the Gail and the Tyrer-Cuzick models). Image-based risk factors, such as mammographic densities and parenchymal patterns, have been established as biomarkers but have not been fully incorporated in the risk prediction models used for risk stratification in screening and/or measuring responsiveness to preventive approaches. Within computer aided mammography, automatic mammographic tissue segmentation methods have been developed for estimation of breast tissue composition to facilitate mammographic risk assessment. This paper presents a comprehensive review of automatic mammographic tissue segmentation methodologies developed over the past two decades and the evidence for risk assessment/density classification using segmentation. The aim of this review is to analyse how engineering advances have progressed and the impact automatic mammographic tissue segmentation has in a clinical environment, as well as to understand the current research gaps with respect to the incorporation of image-based risk factors in non-image-based risk prediction models. PMID:26171249

Validation of Fatigue Modeling Predictions in Aviation Operations

NASA Technical Reports Server (NTRS)

Gregory, Kevin; Martinez, Siera; Flynn-Evans, Erin

2017-01-01

Bio-mathematical fatigue models that predict levels of alertness and performance are one potential tool for use within integrated fatigue risk management approaches. A number of models have been developed that provide predictions based on acute and chronic sleep loss, circadian desynchronization, and sleep inertia. Some are publicly available and gaining traction in settings such as commercial aviation as a means of evaluating flight crew schedules for potential fatigue-related risks. Yet, most models have not been rigorously evaluated and independently validated for the operations to which they are being applied and many users are not fully aware of the limitations in which model results should be interpreted and applied.

A risk factor-based predictive model of outcomes in carotid endarterectomy: the National Surgical Quality Improvement Program 2005-2010.

PubMed

Bekelis, Kimon; Bakhoum, Samuel F; Desai, Atman; Mackenzie, Todd A; Goodney, Philip; Labropoulos, Nicos

2013-04-01

Accurate knowledge of individualized risks and benefits is crucial to the surgical management of patients undergoing carotid endarterectomy (CEA). Although large randomized trials have determined specific cutoffs for the degree of stenosis, precise delineation of patient-level risks remains a topic of debate, especially in real world practice. We attempted to create a risk factor-based predictive model of outcomes in CEA. We performed a retrospective cohort study involving patients who underwent CEAs from 2005 to 2010 and were registered in the American College of Surgeons National Quality Improvement Project database. Of the 35 698 patients, 20 015 were asymptomatic (56.1%) and 15 683 were symptomatic (43.9%). These patients demonstrated a 1.64% risk of stroke, 0.69% risk of myocardial infarction, and 0.75% risk of death within 30 days after CEA. Multivariate analysis demonstrated that increasing age, male sex, history of chronic obstructive pulmonary disease, myocardial infarction, angina, congestive heart failure, peripheral vascular disease, previous stroke or transient ischemic attack, and dialysis were independent risk factors associated with an increased risk of the combined outcome of postoperative stroke, myocardial infarction, or death. A validated model for outcome prediction based on individual patient characteristics was developed. There was a steep effect of age on the risk of myocardial infarction and death. This national study confirms that that risks of CEA vary dramatically based on patient-level characteristics. Because of limited discrimination, it cannot be used for individual patient risk assessment. However, it can be used as a baseline for improvement and development of more accurate predictive models based on other databases or prospective studies.

Predicting neutropenia risk in patients with cancer using electronic data.

PubMed

Pawloski, Pamala A; Thomas, Avis J; Kane, Sheryl; Vazquez-Benitez, Gabriela; Shapiro, Gary R; Lyman, Gary H

2017-04-01

Clinical guidelines recommending the use of myeloid growth factors are largely based on the prescribed chemotherapy regimen. The guidelines suggest that oncologists consider patient-specific characteristics when prescribing granulocyte-colony stimulating factor (G-CSF) prophylaxis; however, a mechanism to quantify individual patient risk is lacking. Readily available electronic health record (EHR) data can provide patient-specific information needed for individualized neutropenia risk estimation. An evidence-based, individualized neutropenia risk estimation algorithm has been developed. This study evaluated the automated extraction of EHR chemotherapy treatment data and externally validated the neutropenia risk prediction model. A retrospective cohort of adult patients with newly diagnosed breast, colorectal, lung, lymphoid, or ovarian cancer who received the first cycle of a cytotoxic chemotherapy regimen from 2008 to 2013 were recruited from a single cancer clinic. Electronically extracted EHR chemotherapy treatment data were validated by chart review. Neutropenia risk stratification was conducted and risk model performance was assessed using calibration and discrimination. Chemotherapy treatment data electronically extracted from the EHR were verified by chart review. The neutropenia risk prediction tool classified 126 patients (57%) as being low risk for febrile neutropenia, 44 (20%) as intermediate risk, and 51 (23%) as high risk. The model was well calibrated (Hosmer-Lemeshow goodness-of-fit test = 0.24). Discrimination was adequate and slightly less than in the original internal validation (c-statistic 0.75 vs 0.81). Chemotherapy treatment data were electronically extracted from the EHR successfully. The individualized neutropenia risk prediction model performed well in our retrospective external cohort. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Job stress models for predicting burnout syndrome: a review.

PubMed

Chirico, Francesco

2016-01-01

In Europe, the Council Directive 89/391 for improvement of workers' safety and health has emphasized the importance of addressing all occupational risk factors, and hence also psychosocial and organizational risk factors. Nevertheless, the construct of "work-related stress" elaborated from EU-OSHA is not totally corresponding with the "psychosocial" risk, that is a broader category of risk, comprising various and different psychosocial risk factors. The term "burnout", without any binding definition, tries to integrate symptoms as well as cause of the burnout process. In Europe, the most important methods developed for the work related stress risk assessment are based on the Cox's transactional model of job stress. Nevertheless, there are more specific models for predicting burnout syndrome. This literature review provides an overview of job burnout, highlighting the most important models of job burnout, such as the Job Strain, the Effort/Reward Imbalance and the Job Demands-Resources models. The difference between these models and the Cox's model of job stress is explored.

Iowa radon leukaemia study: a hierarchical population risk model for spatially correlated exposure measured with error.

PubMed

Smith, Brian J; Zhang, Lixun; Field, R William

2007-11-10

This paper presents a Bayesian model that allows for the joint prediction of county-average radon levels and estimation of the associated leukaemia risk. The methods are motivated by radon data from an epidemiologic study of residential radon in Iowa that include 2726 outdoor and indoor measurements. Prediction of county-average radon is based on a geostatistical model for the radon data which assumes an underlying continuous spatial process. In the radon model, we account for uncertainties due to incomplete spatial coverage, spatial variability, characteristic differences between homes, and detector measurement error. The predicted radon averages are, in turn, included as a covariate in Poisson models for incident cases of acute lymphocytic (ALL), acute myelogenous (AML), chronic lymphocytic (CLL), and chronic myelogenous (CML) leukaemias reported to the Iowa cancer registry from 1973 to 2002. Since radon and leukaemia risk are modelled simultaneously in our approach, the resulting risk estimates accurately reflect uncertainties in the predicted radon exposure covariate. Posterior mean (95 per cent Bayesian credible interval) estimates of the relative risk associated with a 1 pCi/L increase in radon for ALL, AML, CLL, and CML are 0.91 (0.78-1.03), 1.01 (0.92-1.12), 1.06 (0.96-1.16), and 1.12 (0.98-1.27), respectively. Copyright 2007 John Wiley & Sons, Ltd.

Endometrial cancer risk prediction including serum-based biomarkers: results from the EPIC cohort.

PubMed

Fortner, Renée T; Hüsing, Anika; Kühn, Tilman; Konar, Meric; Overvad, Kim; Tjønneland, Anne; Hansen, Louise; Boutron-Ruault, Marie-Christine; Severi, Gianluca; Fournier, Agnès; Boeing, Heiner; Trichopoulou, Antonia; Benetou, Vasiliki; Orfanos, Philippos; Masala, Giovanna; Agnoli, Claudia; Mattiello, Amalia; Tumino, Rosario; Sacerdote, Carlotta; Bueno-de-Mesquita, H B As; Peeters, Petra H M; Weiderpass, Elisabete; Gram, Inger T; Gavrilyuk, Oxana; Quirós, J Ramón; Maria Huerta, José; Ardanaz, Eva; Larrañaga, Nerea; Lujan-Barroso, Leila; Sánchez-Cantalejo, Emilio; Butt, Salma Tunå; Borgquist, Signe; Idahl, Annika; Lundin, Eva; Khaw, Kay-Tee; Allen, Naomi E; Rinaldi, Sabina; Dossus, Laure; Gunter, Marc; Merritt, Melissa A; Tzoulaki, Ioanna; Riboli, Elio; Kaaks, Rudolf

2017-03-15

Endometrial cancer risk prediction models including lifestyle, anthropometric and reproductive factors have limited discrimination. Adding biomarker data to these models may improve predictive capacity; to our knowledge, this has not been investigated for endometrial cancer. Using a nested case-control study within the European Prospective Investigation into Cancer and Nutrition (EPIC) cohort, we investigated the improvement in discrimination gained by adding serum biomarker concentrations to risk estimates derived from an existing risk prediction model based on epidemiologic factors. Serum concentrations of sex steroid hormones, metabolic markers, growth factors, adipokines and cytokines were evaluated in a step-wise backward selection process; biomarkers were retained at p < 0.157 indicating improvement in the Akaike information criterion (AIC). Improvement in discrimination was assessed using the C-statistic for all biomarkers alone, and change in C-statistic from addition of biomarkers to preexisting absolute risk estimates. We used internal validation with bootstrapping (1000-fold) to adjust for over-fitting. Adiponectin, estrone, interleukin-1 receptor antagonist, tumor necrosis factor-alpha and triglycerides were selected into the model. After accounting for over-fitting, discrimination was improved by 2.0 percentage points when all evaluated biomarkers were included and 1.7 percentage points in the model including the selected biomarkers. Models including etiologic markers on independent pathways and genetic markers may further improve discrimination. © 2016 UICC.

A Matter of Classes: Stratifying Health Care Populations to Produce Better Estimates of Inpatient Costs

PubMed Central

Rein, David B

2005-01-01

Objective To stratify traditional risk-adjustment models by health severity classes in a way that is empirically based, is accessible to policy makers, and improves predictions of inpatient costs. Data Sources Secondary data created from the administrative claims from all 829,356 children aged 21 years and under enrolled in Georgia Medicaid in 1999. Study Design A finite mixture model was used to assign child Medicaid patients to health severity classes. These class assignments were then used to stratify both portions of a traditional two-part risk-adjustment model predicting inpatient Medicaid expenditures. Traditional model results were compared with the stratified model using actuarial statistics. Principal Findings The finite mixture model identified four classes of children: a majority healthy class and three illness classes with increasing levels of severity. Stratifying the traditional two-part risk-adjustment model by health severity classes improved its R2 from 0.17 to 0.25. The majority of additional predictive power resulted from stratifying the second part of the two-part model. Further, the preference for the stratified model was unaffected by months of patient enrollment time. Conclusions Stratifying health care populations based on measures of health severity is a powerful method to achieve more accurate cost predictions. Insurers who ignore the predictive advances of sample stratification in setting risk-adjusted premiums may create strong financial incentives for adverse selection. Finite mixture models provide an empirically based, replicable methodology for stratification that should be accessible to most health care financial managers. PMID:16033501

Personalized dynamic prediction of death according to tumour progression and high-dimensional genetic factors: Meta-analysis with a joint model.

PubMed

Emura, Takeshi; Nakatochi, Masahiro; Matsui, Shigeyuki; Michimae, Hirofumi; Rondeau, Virginie

2017-01-01

Developing a personalized risk prediction model of death is fundamental for improving patient care and touches on the realm of personalized medicine. The increasing availability of genomic information and large-scale meta-analytic data sets for clinicians has motivated the extension of traditional survival prediction based on the Cox proportional hazards model. The aim of our paper is to develop a personalized risk prediction formula for death according to genetic factors and dynamic tumour progression status based on meta-analytic data. To this end, we extend the existing joint frailty-copula model to a model allowing for high-dimensional genetic factors. In addition, we propose a dynamic prediction formula to predict death given tumour progression events possibly occurring after treatment or surgery. For clinical use, we implement the computation software of the prediction formula in the joint.Cox R package. We also develop a tool to validate the performance of the prediction formula by assessing the prediction error. We illustrate the method with the meta-analysis of individual patient data on ovarian cancer patients.

Inter-model comparison of the landscape determinants of vector-borne disease: implications for epidemiological and entomological risk modeling.

PubMed

Lorenz, Alyson; Dhingra, Radhika; Chang, Howard H; Bisanzio, Donal; Liu, Yang; Remais, Justin V

2014-01-01

Extrapolating landscape regression models for use in assessing vector-borne disease risk and other applications requires thoughtful evaluation of fundamental model choice issues. To examine implications of such choices, an analysis was conducted to explore the extent to which disparate landscape models agree in their epidemiological and entomological risk predictions when extrapolated to new regions. Agreement between six literature-drawn landscape models was examined by comparing predicted county-level distributions of either Lyme disease or Ixodes scapularis vector using Spearman ranked correlation. AUC analyses and multinomial logistic regression were used to assess the ability of these extrapolated landscape models to predict observed national data. Three models based on measures of vegetation, habitat patch characteristics, and herbaceous landcover emerged as effective predictors of observed disease and vector distribution. An ensemble model containing these three models improved precision and predictive ability over individual models. A priori assessment of qualitative model characteristics effectively identified models that subsequently emerged as better predictors in quantitative analysis. Both a methodology for quantitative model comparison and a checklist for qualitative assessment of candidate models for extrapolation are provided; both tools aim to improve collaboration between those producing models and those interested in applying them to new areas and research questions.

Prediction of high-risk areas for visceral leishmaniasis using socioeconomic indicators and remote sensing data

PubMed Central

2014-01-01

Spatial heterogeneity in the incidence of visceral leishmaniasis (VL) is an important aspect to be considered in planning control actions for the disease. The objective of this study was to predict areas at high risk for visceral leishmaniasis (VL) based on socioeconomic indicators and remote sensing data. We applied classification and regression trees to develop and validate prediction models. Performance of the models was assessed by means of sensitivity, specificity and area under the ROC curve. The model developed was able to discriminate 15 subsets of census tracts (CT) with different probabilities of containing CT with high risk of VL occurrence. The model presented, respectively, in the validation and learning samples, sensitivity of 79% and 52%, specificity of 75% and 66%, and area under the ROC curve of 83% and 66%. Considering the complex network of factors involved in the occurrence of VL in urban areas, the results of this study showed that the development of a predictive model for VL might be feasible and useful for guiding interventions against the disease, but it is still a challenge as demonstrated by the unsatisfactory predictive performance of the model developed. PMID:24885128

Using risk-adjustment models to identify high-cost risks.

PubMed

Meenan, Richard T; Goodman, Michael J; Fishman, Paul A; Hornbrook, Mark C; O'Keeffe-Rosetti, Maureen C; Bachman, Donald J

2003-11-01

We examine the ability of various publicly available risk models to identify high-cost individuals and enrollee groups using multi-HMO administrative data. Five risk-adjustment models (the Global Risk-Adjustment Model [GRAM], Diagnostic Cost Groups [DCGs], Adjusted Clinical Groups [ACGs], RxRisk, and Prior-expense) were estimated on a multi-HMO administrative data set of 1.5 million individual-level observations for 1995-1996. Models produced distributions of individual-level annual expense forecasts for comparison to actual values. Prespecified "high-cost" thresholds were set within each distribution. The area under the receiver operating characteristic curve (AUC) for "high-cost" prevalences of 1% and 0.5% was calculated, as was the proportion of "high-cost" dollars correctly identified. Results are based on a separate 106,000-observation validation dataset. For "high-cost" prevalence targets of 1% and 0.5%, ACGs, DCGs, GRAM, and Prior-expense are very comparable in overall discrimination (AUCs, 0.83-0.86). Given a 0.5% prevalence target and a 0.5% prediction threshold, DCGs, GRAM, and Prior-expense captured $963,000 (approximately 3%) more "high-cost" sample dollars than other models. DCGs captured the most "high-cost" dollars among enrollees with asthma, diabetes, and depression; predictive performance among demographic groups (Medicaid members, members over 64, and children under 13) varied across models. Risk models can efficiently identify enrollees who are likely to generate future high costs and who could benefit from case management. The dollar value of improved prediction performance of the most accurate risk models should be meaningful to decision-makers and encourage their broader use for identifying high costs.

Development of a Risk Assessment Tool to Predict Fall-Related Severe Injuries Occurring in a Hospital

PubMed Central

Toyabe, Shin-ichi

2014-01-01

Inpatient falls are the most common adverse events that occur in a hospital, and about 3 to 10% of falls result in serious injuries such as bone fractures and intracranial haemorrhages. We previously reported that bone fractures and intracranial haemorrhages were two major fall-related injuries and that risk assessment score for osteoporotic bone fracture was significantly associated not only with bone fractures after falls but also with intracranial haemorrhage after falls. Based on the results, we tried to establish a risk assessment tool for predicting fall-related severe injuries in a hospital. Possible risk factors related to fall-related serious injuries were extracted from data on inpatients that were admitted to a tertiary-care university hospital by using multivariate Cox’ s regression analysis and multiple logistic regression analysis. We found that fall risk score and fracture risk score were the two significant factors, and we constructed models to predict fall-related severe injuries incorporating these factors. When the prediction model was applied to another independent dataset, the constructed model could detect patients with fall-related severe injuries efficiently. The new assessment system could identify patients prone to severe injuries after falls in a reproducible fashion. PMID:25168984

Persistent hemifacial spasm after microvascular decompression: a risk assessment model.

PubMed

Shah, Aalap; Horowitz, Michael

2017-06-01

Microvascular decompression (MVD) for hemifacial spasm (HFS) provides resolution of disabling symptoms such as eyelid twitching and muscle contractions of the entire hemiface. The primary aim of this study was to evaluate the predictive value of patient demographics and spasm characteristics on long-term outcomes, with or without intraoperative lateral spread response (LSR) as an additional variable in a risk assessment model. A retrospective study was undertaken to evaluate the associations of pre-operative patient characteristics, as well as intraoperative LSR and need for a staged procedure on the presence of persistent or recurrent HFS at the time of hospital discharge and at follow-up. A risk assessment model was constructed with the inclusion of six clinically or statistically significant variables from the univariate analyses. A receiving operator characteristic curve was generated, and area under the curve was calculated to determine the strength of the predictive model. A risk assessment model was first created consisting of significant pre-operative variables (Model 1) (age >50, female gender, history of botulinum toxin use, platysma muscle involvement). This model demonstrated borderline predictive value for persistent spasm at discharge (AUC .60; p=.045) and fair predictive value at follow-up (AUC .75; p=.001). Intraoperative variables (e.g. LSR persistence) demonstrated little additive value (Model 2) (AUC .67). Patients with a higher risk score (three or greater) demonstrated greater odds of persistent HFS at the time of discharge (OR 1.5 [95%CI 1.16-1.97]; p=.035), as well as greater odds of persistent or recurrent spasm at the time of follow-up (OR 3.0 [95%CI 1.52-5.95]; p=.002) Conclusions: A risk assessment model consisting of pre-operative clinical characteristics is useful in prognosticating HFS persistence at follow-up.

Predicting Progression from Mild Cognitive Impairment to Alzheimer's Dementia Using Clinical, MRI, and Plasma Biomarkers via Probabilistic Pattern Classification

PubMed Central

Korolev, Igor O.; Symonds, Laura L.; Bozoki, Andrea C.

2016-01-01

Background Individuals with mild cognitive impairment (MCI) have a substantially increased risk of developing dementia due to Alzheimer's disease (AD). In this study, we developed a multivariate prognostic model for predicting MCI-to-dementia progression at the individual patient level. Methods Using baseline data from 259 MCI patients and a probabilistic, kernel-based pattern classification approach, we trained a classifier to distinguish between patients who progressed to AD-type dementia (n = 139) and those who did not (n = 120) during a three-year follow-up period. More than 750 variables across four data sources were considered as potential predictors of progression. These data sources included risk factors, cognitive and functional assessments, structural magnetic resonance imaging (MRI) data, and plasma proteomic data. Predictive utility was assessed using a rigorous cross-validation framework. Results Cognitive and functional markers were most predictive of progression, while plasma proteomic markers had limited predictive utility. The best performing model incorporated a combination of cognitive/functional markers and morphometric MRI measures and predicted progression with 80% accuracy (83% sensitivity, 76% specificity, AUC = 0.87). Predictors of progression included scores on the Alzheimer's Disease Assessment Scale, Rey Auditory Verbal Learning Test, and Functional Activities Questionnaire, as well as volume/cortical thickness of three brain regions (left hippocampus, middle temporal gyrus, and inferior parietal cortex). Calibration analysis revealed that the model is capable of generating probabilistic predictions that reliably reflect the actual risk of progression. Finally, we found that the predictive accuracy of the model varied with patient demographic, genetic, and clinical characteristics and could be further improved by taking into account the confidence of the predictions. Conclusions We developed an accurate prognostic model for predicting MCI-to-dementia progression over a three-year period. The model utilizes widely available, cost-effective, non-invasive markers and can be used to improve patient selection in clinical trials and identify high-risk MCI patients for early treatment. PMID:26901338

Do repeated assessments of performance status improve predictions for risk of death among patients with cancer? A population-based cohort study.

PubMed

Su, Jiandong; Barbera, Lisa; Sutradhar, Rinku

2015-06-01

Prior work has utilized longitudinal information on performance status to demonstrate its association with risk of death among cancer patients; however, no study has assessed whether such longitudinal information improves the predictions for risk of death. To examine whether the use of repeated performance status assessments improve predictions for risk of death compared to using only performance status assessment at the time of cancer diagnosis. This was a population-based longitudinal study of adult outpatients who had a cancer diagnosis and had at least one assessment of performance status. To account for each patient's changing performance status over time, we implemented a Cox model with a time-varying covariate for performance status. This model was compared to a Cox model using only a time-fixed (baseline) covariate for performance status. The regression coefficients of each model were derived based on a randomly selected 60% of patients, and then, the predictive ability of each model was assessed via concordance probabilities when applied to the remaining 40% of patients. Our study consisted of 15,487 cancer patients with over 53,000 performance status assessments. The utilization of repeated performance status assessments improved predictions for risk of death compared to using only the performance status assessment taken at diagnosis. When studying the hazard of death among patients with cancer, if available, researchers should incorporate changing information on performance status scores, instead of simply baseline information on performance status. © The Author(s) 2015.

Improving Global Vascular Risk Prediction with Behavioral and Anthropometric Factors: The Multi-ethnic Northern Manhattan Cohort Study

PubMed Central

Sacco, Ralph L.; Khatri, Minesh; Rundek, Tatjana; Xu, Qiang; Gardener, Hannah; Boden-Albala, Bernadette; Di Tullio, Marco R.; Homma, Shunichi; Elkind, Mitchell SV; Paik, Myunghee C

2010-01-01

Objective To improve global vascular risk prediction with behavioral and anthropometric factors. Background Few cardiovascular risk models are designed to predict the global vascular risk of MI, stroke, or vascular death in multi-ethnic individuals, and existing schemes do not fully include behavioral risk factors. Methods A randomly-derived, population-based, prospective cohort of 2737 community participants free of stroke and coronary artery disease were followed annually for a median of 9.0 years in the Northern Manhattan Study (mean age 69 years; 63.2% women; 52.7% Hispanic, 24.9% African-American, 19.9% white). A global vascular risk score (GVRS) predictive of stroke, myocardial infarction, or vascular death was developed by adding variables to the traditional Framingham cardiovascular variables based on the likelihood ratio criterion. Model utility was assessed through receiver operating characteristics, calibration, and effect on reclassification of subjects. Results Variables which significantly added to the traditional Framingham profile included waist circumference, alcohol consumption, and physical activity. Continuous measures for blood pressure and fasting blood sugar were used instead of hypertension and diabetes. Ten -year event-free probabilities were 0.95 for the first quartile of GVRS, 0.89 for the second quartile, 0.79 for the third quartile, and 0.56 for the fourth quartile. The addition of behavioral factors in our model improved prediction of 10 -year event rates compared to a model restricted to the traditional variables. Conclusion A global vascular risk score that combines both traditional, behavioral, and anthropometric risk factors, uses continuous variables for physiological parameters, and is applicable to non-white subjects could improve primary prevention strategies. PMID:19958966

Prediction of cardiovascular disease risk among low-income urban dwellers in metropolitan Kuala Lumpur, Malaysia.

PubMed

Su, Tin Tin; Amiri, Mohammadreza; Mohd Hairi, Farizah; Thangiah, Nithiah; Bulgiba, Awang; Majid, Hazreen Abdul

2015-01-01

We aimed to predict the ten-year cardiovascular disease (CVD) risk among low-income urban dwellers of metropolitan Malaysia. Participants were selected from a cross-sectional survey conducted in Kuala Lumpur. To assess the 10-year CVD risk, we employed the Framingham risk scoring (FRS) models. Significant determinants of the ten-year CVD risk were identified using General Linear Model (GLM). Altogether 882 adults (≥30 years old with no CVD history) were randomly selected. The classic FRS model (figures in parentheses are from the modified model) revealed that 20.5% (21.8%) and 38.46% (38.9%) of respondents were at high and moderate risk of CVD. The GLM models identified the importance of education, occupation, and marital status in predicting the future CVD risk. Our study indicated that one out of five low-income urban dwellers has high chance of having CVD within ten years. Health care expenditure, other illness related costs and loss of productivity due to CVD would worsen the current situation of low-income urban population. As such, the public health professionals and policy makers should establish substantial effort to formulate the public health policy and community-based intervention to minimize the upcoming possible high mortality and morbidity due to CVD among the low-income urban dwellers.

Prediction of Cardiovascular Disease Risk among Low-Income Urban Dwellers in Metropolitan Kuala Lumpur, Malaysia

PubMed Central

Su, Tin Tin; Amiri, Mohammadreza; Mohd Hairi, Farizah; Thangiah, Nithiah; Majid, Hazreen Abdul

2015-01-01

We aimed to predict the ten-year cardiovascular disease (CVD) risk among low-income urban dwellers of metropolitan Malaysia. Participants were selected from a cross-sectional survey conducted in Kuala Lumpur. To assess the 10-year CVD risk, we employed the Framingham risk scoring (FRS) models. Significant determinants of the ten-year CVD risk were identified using General Linear Model (GLM). Altogether 882 adults (≥30 years old with no CVD history) were randomly selected. The classic FRS model (figures in parentheses are from the modified model) revealed that 20.5% (21.8%) and 38.46% (38.9%) of respondents were at high and moderate risk of CVD. The GLM models identified the importance of education, occupation, and marital status in predicting the future CVD risk. Our study indicated that one out of five low-income urban dwellers has high chance of having CVD within ten years. Health care expenditure, other illness related costs and loss of productivity due to CVD would worsen the current situation of low-income urban population. As such, the public health professionals and policy makers should establish substantial effort to formulate the public health policy and community-based intervention to minimize the upcoming possible high mortality and morbidity due to CVD among the low-income urban dwellers. PMID:25821810

The New York risk score for in-hospital and 30-day mortality for coronary artery bypass graft surgery.

PubMed

Hannan, Edward L; Farrell, Louise Szypulski; Wechsler, Andrew; Jordan, Desmond; Lahey, Stephen J; Culliford, Alfred T; Gold, Jeffrey P; Higgins, Robert S D; Smith, Craig R

2013-01-01

Simplified risk scores for coronary artery bypass graft surgery are frequently in lieu of more complicated statistical models and are valuable for informed consent and choice of intervention. Previous risk scores have been based on in-hospital mortality, but a substantial number of patients die within 30 days of the procedure. These deaths should also be accounted for, so we have developed a risk score based on in-hospital and 30-day mortality. New York's Cardiac Surgery Reporting System was used to develop an in-hospital and 30-day logistic regression model for patients undergoing coronary artery bypass graft surgery in 2009, and this model was converted into a simple linear risk score that provides estimated in-hospital and 30-day mortality rates for different values of the score. The accuracy of the risk score in predicting mortality was tested. This score was also validated by applying it to 2008 New York coronary artery bypass graft data. Subsequent analyses evaluated the ability of the risk score to predict complications and length of stay. The overall in-hospital and 30-day mortality rate for the 10,148 patients in the study was 1.79%. There are seven risk factors comprising the score, with risk factor scores ranging from 1 to 5, and the highest possible total score is 23. The score accurately predicted mortality in 2009 as well as in 2008, and was strongly correlated with complications and length of stay. The risk score is a simple way of estimating short-term mortality that accurately predicts mortality in the year the model was developed as well as in the previous year. Perioperative complications and length of stay are also well predicted by the risk score. Copyright © 2013 The Society of Thoracic Surgeons. Published by Elsevier Inc. All rights reserved.

Data mining model using simple and readily available factors could identify patients at high risk for hepatocellular carcinoma in chronic hepatitis C.

PubMed

Kurosaki, Masayuki; Hiramatsu, Naoki; Sakamoto, Minoru; Suzuki, Yoshiyuki; Iwasaki, Manabu; Tamori, Akihiro; Matsuura, Kentaro; Kakinuma, Sei; Sugauchi, Fuminaka; Sakamoto, Naoya; Nakagawa, Mina; Izumi, Namiki

2012-03-01

Assessment of the risk of hepatocellular carcinoma (HCC) development is essential for formulating personalized surveillance or antiviral treatment plan for chronic hepatitis C. We aimed to build a simple model for the identification of patients at high risk of developing HCC. Chronic hepatitis C patients followed for at least 5 years (n=1003) were analyzed by data mining to build a predictive model for HCC development. The model was externally validated using a cohort of 1072 patients (472 with sustained virological response (SVR) and 600 with nonSVR to PEG-interferon plus ribavirin therapy). On the basis of factors such as age, platelet, albumin, and aspartate aminotransferase, the HCC risk prediction model identified subgroups with high-, intermediate-, and low-risk of HCC with a 5-year HCC development rate of 20.9%, 6.3-7.3%, and 0-1.5%, respectively. The reproducibility of the model was confirmed through external validation (r(2)=0.981). The 10-year HCC development rate was also significantly higher in the high-and intermediate-risk group than in the low-risk group (24.5% vs. 4.8%; p<0.0001). In the high-and intermediate-risk group, the incidence of HCC development was significantly reduced in patients with SVR compared to those with nonSVR (5-year rate, 9.5% vs. 4.5%; p=0.040). The HCC risk prediction model uses simple and readily available factors and identifies patients at a high risk of HCC development. The model allows physicians to identify patients requiring HCC surveillance and those who benefit from IFN therapy to prevent HCC. Copyright © 2011 European Association for the Study of the Liver. Published by Elsevier B.V. All rights reserved.

Utility of different cardiovascular disease prediction models in rheumatoid arthritis.

PubMed

Purcarea, A; Sovaila, S; Udrea, G; Rezus, E; Gheorghe, A; Tiu, C; Stoica, V

2014-01-01

Rheumatoid arthritis comes with a 30% higher probability for cardiovascular disease than the general population. Current guidelines advocate for early and aggressive primary prevention and treatment of risk factors in high-risk populations but this excess risk is under-addressed in RA in real life. This is mainly due to difficulties met in the correct risk evaluation. This study aims to underline the differences in results of the main cardiovascular risk screening models in the real life rheumatoid arthritis population. In a cross-sectional study, patients addressed to a tertiary care center in Romania for an biannual follow-up of rheumatoid arthritis and the ones who were considered free of any cardiovascular disease were assessed for subclinical atherosclerosis. Clinical, biological and carotidal ultrasound evaluations were performed. A number of cardiovascular disease prediction scores were performed and differences between tests were noted in regard to subclinical atherosclerosis as defined by the existence of carotid intima media thickness over 0,9 mm or carotid plaque. In a population of 29 Romanian rheumatoid arthritis patients free of cardiovascular disease, the performance of Framingham Risk Score, HeartSCORE, ARIC cardiovascular disease prediction score, Reynolds Risk Score, PROCAM risk score and Qrisk2 score were compared. All the scores under-diagnosed subclinical atherosclerosis. With an AUROC of 0,792, the SCORE model was the only one that could partially stratify patients in low, intermediate and high-risk categories. The use of the EULAR recommended modifier did not help to reclassify patients. The only score that showed a statistically significant prediction capacity for subclinical atherosclerosis in a Romanian rheumatoid arthritis population was SCORE. The additional calibration or the use of imaging techniques in CVD risk prediction for the intermediate risk category might be warranted.

Utility of different cardiovascular disease prediction models in rheumatoid arthritis

PubMed Central

Purcarea, A; Sovaila, S; Udrea, G; Rezus, E; Gheorghe, A; Tiu, C; Stoica, V

2014-01-01

Background. Rheumatoid arthritis comes with a 30% higher probability for cardiovascular disease than the general population. Current guidelines advocate for early and aggressive primary prevention and treatment of risk factors in high-risk populations but this excess risk is under-addressed in RA in real life. This is mainly due to difficulties met in the correct risk evaluation. This study aims to underline the differences in results of the main cardiovascular risk screening models in the real life rheumatoid arthritis population. Methods. In a cross-sectional study, patients addressed to a tertiary care center in Romania for an biannual follow-up of rheumatoid arthritis and the ones who were considered free of any cardiovascular disease were assessed for subclinical atherosclerosis. Clinical, biological and carotidal ultrasound evaluations were performed. A number of cardiovascular disease prediction scores were performed and differences between tests were noted in regard to subclinical atherosclerosis as defined by the existence of carotid intima media thickness over 0,9 mm or carotid plaque. Results. In a population of 29 Romanian rheumatoid arthritis patients free of cardiovascular disease, the performance of Framingham Risk Score, HeartSCORE, ARIC cardiovascular disease prediction score, Reynolds Risk Score, PROCAM risk score and Qrisk2 score were compared. All the scores under-diagnosed subclinical atherosclerosis. With an AUROC of 0,792, the SCORE model was the only one that could partially stratify patients in low, intermediate and high-risk categories. The use of the EULAR recommended modifier did not help to reclassify patients. Conclusion. The only score that showed a statistically significant prediction capacity for subclinical atherosclerosis in a Romanian rheumatoid arthritis population was SCORE. The additional calibration or the use of imaging techniques in CVD risk prediction for the intermediate risk category might be warranted. PMID:25713628

Evaluating diagnosis-based risk-adjustment methods in a population with spinal cord dysfunction.

PubMed

Warner, Grace; Hoenig, Helen; Montez, Maria; Wang, Fei; Rosen, Amy

2004-02-01

To examine performance of models in predicting health care utilization for individuals with spinal cord dysfunction. Regression models compared 2 diagnosis-based risk-adjustment methods, the adjusted clinical groups (ACGs) and diagnostic cost groups (DCGs). To improve prediction, we added to our model: (1) spinal cord dysfunction-specific diagnostic information, (2) limitations in self-care function, and (3) both 1 and 2. Models were replicated in 3 populations. Samples from 3 populations: (1) 40% of veterans using Veterans Health Administration services in fiscal year 1997 (FY97) (N=1,046,803), (2) veteran sample with spinal cord dysfunction identified by codes from the International Statistical Classification of Diseases, 9th Revision, Clinical Modifications (N=7666), and (3) veteran sample identified in Veterans Affairs Spinal Cord Dysfunction Registry (N=5888). Not applicable. Inpatient, outpatient, and total days of care in FY97. The DCG models (R(2) range,.22-.38) performed better than ACG models (R(2) range,.04-.34) for all outcomes. Spinal cord dysfunction-specific diagnostic information improved prediction more in the ACG model than in the DCG model (R(2) range for ACG,.14-.34; R(2) range for DCG,.24-.38). Information on self-care function slightly improved performance (R(2) range increased from 0 to.04). The DCG risk-adjustment models predicted health care utilization better than ACG models. ACG model prediction was improved by adding information.

Predicting risk for childhood asthma by pre-pregnancy, perinatal, and postnatal factors.

PubMed

Wen, Hui-Ju; Chiang, Tung-Liang; Lin, Shio-Jean; Guo, Yue Leon

2015-05-01

Symptoms of atopic disease start early in human life. Predicting risk for childhood asthma by early-life exposure would contribute to disease prevention. A birth cohort study was conducted to investigate early-life risk factors for childhood asthma and to develop a predictive model for the development of asthma. National representative samples of newborn babies were obtained by multistage stratified systematic sampling from the 2005 Taiwan Birth Registry. Information on potential risk factors and children's health was collected by home interview when babies were 6 months old and 5 yr old, respectively. Backward stepwise regression analysis was used to identify the risk factors of childhood asthma for predictive models that were used to calculate the probability of childhood asthma. A total of 19,192 children completed the study satisfactorily. Physician-diagnosed asthma was reported in 6.6% of 5-yr-old children. Pre-pregnancy factors (parental atopy and socioeconomic status), perinatal factors (place of residence, exposure to indoor mold and painting/renovations during pregnancy), and postnatal factors (maternal postpartum depression and the presence of atopic dermatitis before 6 months of age) were chosen for the predictive models, and the highest predicted probability of asthma in 5-yr-old children was 68.1% in boys and 78.1% in girls; the lowest probability in boys and girls was 4.1% and 3.2%, respectively. This investigation provides a technique for predicting risk of childhood asthma that can be used to developing a preventive strategy against asthma. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Development and validation of a predictive model for excessive postpartum blood loss: A retrospective, cohort study.

PubMed

Rubio-Álvarez, Ana; Molina-Alarcón, Milagros; Arias-Arias, Ángel; Hernández-Martínez, Antonio

2018-03-01

postpartum haemorrhage is one of the leading causes of maternal morbidity and mortality worldwide. Despite the use of uterotonics agents as preventive measure, it remains a challenge to identify those women who are at increased risk of postpartum bleeding. to develop and to validate a predictive model to assess the risk of excessive bleeding in women with vaginal birth. retrospective cohorts study. "Mancha-Centro Hospital" (Spain). the elaboration of the predictive model was based on a derivation cohort consisting of 2336 women between 2009 and 2011. For validation purposes, a prospective cohort of 953 women between 2013 and 2014 were employed. Women with antenatal fetal demise, multiple pregnancies and gestations under 35 weeks were excluded METHODS: we used a multivariate analysis with binary logistic regression, Ridge Regression and areas under the Receiver Operating Characteristic curves to determine the predictive ability of the proposed model. there was 197 (8.43%) women with excessive bleeding in the derivation cohort and 63 (6.61%) women in the validation cohort. Predictive factors in the final model were: maternal age, primiparity, duration of the first and second stages of labour, neonatal birth weight and antepartum haemoglobin levels. Accordingly, the predictive ability of this model in the derivation cohort was 0.90 (95% CI: 0.85-0.93), while it remained 0.83 (95% CI: 0.74-0.92) in the validation cohort. this predictive model is proved to have an excellent predictive ability in the derivation cohort, and its validation in a latter population equally shows a good ability for prediction. This model can be employed to identify women with a higher risk of postpartum haemorrhage. Copyright © 2017 Elsevier Ltd. All rights reserved.

Inability to predict postpartum hemorrhage: insights from Egyptian intervention data

PubMed Central

2011-01-01

Background Knowledge on how well we can predict primary postpartum hemorrhage (PPH) can help policy makers and health providers design current delivery protocols and PPH case management. The purpose of this paper is to identify risk factors and determine predictive probabilities of those risk factors for primary PPH among women expecting singleton vaginal deliveries in Egypt. Methods From a prospective cohort study, 2510 pregnant women were recruited over a six-month period in Egypt in 2004. PPH was defined as blood loss ≥ 500 ml. Measures of blood loss were made every 20 minutes for the first 4 hours after delivery using a calibrated under the buttocks drape. Using all variables available in the patients' charts, we divided them in ante-partum and intra-partum factors. We employed logistic regression to analyze socio-demographic, medical and past obstetric history, and labor and delivery outcomes as potential PPH risk factors. Post-model predicted probabilities were estimated using the identified risk factors. Results We found a total of 93 cases of primary PPH. In multivariate models, ante-partum hemoglobin, history of previous PPH, labor augmentation and prolonged labor were significantly associated with PPH. Post model probability estimates showed that even among women with three or more risk factors, PPH could only be predicted in 10% of the cases. Conclusions The predictive probability of ante-partum and intra-partum risk factors for PPH is very low. Prevention of PPH to all women is highly recommended. PMID:22123123

A model to predict the onset of non-alcoholic fatty liver disease within 2 years in elderly adults.

PubMed

Lin, Ya-Jie; Gao, Xi-Mei; Pan, Wei-Wei; Gao, Shuai; Yu, Zhen-Zhen; Xu, Ping; Fan, Xiao-Peng

2017-10-01

Non-alcoholic fatty liver disease (NAFLD) is a common cause of chronic hepatitis, which leads to cirrhosis and hepatocellular carcinoma. However, it is difficult to identify subjects at high risk for NAFLD onset. This study aims to construct a model to predict the onset of NAFLD within 2 years in elderly adults. This study included and followed 3378 initial NAFLD-free subjects aged 60 years or over for 2 years, which were randomly divided into a training set and a validation set. NAFLD was diagnosed on ultrasound. Clinical and laboratory data were recorded at baseline. A model was constructed in the training set to predict the onset of NAFLD and validated in the validation set. Body mass index, hemoglobin, fasting blood glucose, and triglycerides were identified as predictors for the onset of NAFLD. A risk score (R) was calculated by them. It classified the subjects into low-risk group (R ≤ -2.88), moderate-risk group (-2.88 < R ≤ -1.26), and high-risk group (R > -1.26). In the training set, 4.68% of the participants in the low-risk group, 11.59% of the participants in the moderate-risk group, and 31.02% of the participants in the high-risk group developed NAFLD. In the validation set, 5.84% of the participants in the low-risk group, 10.57% of the participants in the moderate-risk group, and 29.44% of the participants in the high-risk group developed NAFLD. This study developed a model to predict the onset of NAFLD in elderly adults, which might provide indications for intervention to these subjects. © 2017 Journal of Gastroenterology and Hepatology Foundation and John Wiley & Sons Australia, Ltd.

Risk factors for the treatment outcome of retreated pulmonary tuberculosis patients in China: an optimized prediction model.

PubMed

Wang, X-M; Yin, S-H; Du, J; Du, M-L; Wang, P-Y; Wu, J; Horbinski, C M; Wu, M-J; Zheng, H-Q; Xu, X-Q; Shu, W; Zhang, Y-J

2017-07-01

Retreatment of tuberculosis (TB) often fails in China, yet the risk factors associated with the failure remain unclear. To identify risk factors for the treatment failure of retreated pulmonary tuberculosis (PTB) patients, we analyzed the data of 395 retreated PTB patients who received retreatment between July 2009 and July 2011 in China. PTB patients were categorized into 'success' and 'failure' groups by their treatment outcome. Univariable and multivariable logistic regression were used to evaluate the association between treatment outcome and socio-demographic as well as clinical factors. We also created an optimized risk score model to evaluate the predictive values of these risk factors on treatment failure. Of 395 patients, 99 (25·1%) were diagnosed as retreatment failure. Our results showed that risk factors associated with treatment failure included drug resistance, low education level, low body mass index (6 months), standard treatment regimen, retreatment type, positive culture result after 2 months of treatment, and the place where the first medicine was taken. An Optimized Framingham risk model was then used to calculate the risk scores of these factors. Place where first medicine was taken (temporary living places) received a score of 6, which was highest among all the factors. The predicted probability of treatment failure increases as risk score increases. Ten out of 359 patients had a risk score >9, which corresponded to an estimated probability of treatment failure >70%. In conclusion, we have identified multiple clinical and socio-demographic factors that are associated with treatment failure of retreated PTB patients. We also created an optimized risk score model that was effective in predicting the retreatment failure. These results provide novel insights for the prognosis and improvement of treatment for retreated PTB patients.

Alternative research funding to improve clinical outcomes: model of prediction and prevention of sudden cardiac death.

PubMed

Myerburg, Robert J; Ullmann, Steven G

2015-04-01

Although identification and management of cardiovascular risk markers have provided important population risk insights and public health benefits, individual risk prediction remains challenging. Using sudden cardiac death risk as a base case, the complex epidemiology of sudden cardiac death risk and the substantial new funding required to study individual risk are explored. Complex epidemiology derives from the multiple subgroups having different denominators and risk profiles, while funding limitations emerge from saturation of conventional sources of research funding without foreseeable opportunities for increases. A resolution to this problem would have to emerge from new sources of funding targeted to individual risk prediction. In this analysis, we explore the possibility of a research funding strategy that would offer business incentives to the insurance industries, while providing support for unresolved research goals. The model is developed for the case of sudden cardiac death risk, but the concept is applicable to other areas of the medical enterprise. © 2015 American Heart Association, Inc.

SMALL POPULATIONS REQUIRE SPECIFIC MODELING APPROACHES FOR ASSESSING RISK

EPA Science Inventory

All populations face non-zero risks of extinction. However, the risks for small populations, and therefore the modeling approaches necessary to predict them, are different from those of large populations. These differences are currently hindering assessment of risk to small pop...

A prediction tool incorporating the biomarker S-100B for patient selection for completion lymph node dissection in stage III melanoma.

PubMed

Damude, S; Wevers, K P; Murali, R; Kruijff, S; Hoekstra, H J; Bastiaannet, E

2017-09-01

Completion lymph node dissection (CLND) in sentinel node (SN)-positive melanoma patients is accompanied with morbidity, while about 80% yield no additional metastases in non-sentinel nodes (NSNs). A prediction tool for NSN involvement could be of assistance in patient selection for CLND. This study investigated which parameters predict NSN-positivity, and whether the biomarker S-100B improves the accuracy of a prediction model. Recorded clinicopathologic factors were tested for their association with NSN-positivity in 110 SN-positive patients who underwent CLND. A prediction model was developed with multivariable logistic regression, incorporating all predictive factors. Five models were compared for their predictive power by calculating the Area Under the Curve (AUC). A weighted risk score, 'S-100B Non-Sentinel Node Risk Score' (SN-SNORS), was derived for the model with the highest AUC. Besides, a nomogram was developed as visual representation. NSN-positivity was present in 24 (21.8%) patients. Sex, ulceration, number of harvested SNs, number of positive SNs, and S-100B value were independently associated with NSN-positivity. The AUC for the model including all these factors was 0.78 (95%CI 0.69-0.88). SN-SNORS was the sum of scores for the five parameters. Scores of ≤9.5, 10-11.5, and ≥12 were associated with low (0%), intermediate (21.0%) and high (43.2%) risk of NSN involvement. A prediction tool based on five parameters, including the biomarker S-100B, showed accurate risk stratification for NSN-involvement in SN-positive melanoma patients. If validated in future studies, this tool could help to identify patients with low risk for NSN-involvement. Copyright © 2017 Elsevier Ltd, BASO ~ The Association for Cancer Surgery, and the European Society of Surgical Oncology. All rights reserved.

Development and validation of a predictive risk model for all-cause mortality in type 2 diabetes.

PubMed

Robinson, Tom E; Elley, C Raina; Kenealy, Tim; Drury, Paul L

2015-06-01

Type 2 diabetes is common and is associated with an approximate 80% increase in the rate of mortality. Management decisions may be assisted by an estimate of the patient's absolute risk of adverse outcomes, including death. This study aimed to derive a predictive risk model for all-cause mortality in type 2 diabetes. We used primary care data from a large national multi-ethnic cohort of patients with type 2 diabetes in New Zealand and linked mortality records to develop a predictive risk model for 5-year risk of mortality. We then validated this model using information from a separate cohort of patients with type 2 diabetes. 26,864 people were included in the development cohort with a median follow up time of 9.1 years. We developed three models initially using demographic information and then progressively more clinical detail. The final model, which also included markers of renal disease, proved to give best prediction of all-cause mortality with a C-statistic of 0.80 in the development cohort and 0.79 in the validation cohort (7610 people) and was well calibrated. Ethnicity was a major factor with hazard ratios of 1.37 for indigenous Maori, 0.41 for East Asian and 0.55 for Indo Asian compared with European (P<0.001). We have developed a model using information usually available in primary care that provides good assessment of patient's risk of death. Results are similar to models previously published from smaller cohorts in other countries and apply to a wider range of patient ethnic groups. Copyright © 2015. Published by Elsevier Ireland Ltd.

Evaluating critical uncertainty thresholds in a spatial model of forest pest invasion risk

Treesearch

Frank H. Koch; Denys Yemshanov; Daniel W. McKenney; William D. Smith

2009-01-01

Pest risk maps can provide useful decision support in invasive species management, but most do not adequately consider the uncertainty associated with predicted risk values. This study explores how increased uncertainty in a risk model’s numeric assumptions might affect the resultant risk map. We used a spatial stochastic model, integrating components for...

Combining PubMed knowledge and EHR data to develop a weighted bayesian network for pancreatic cancer prediction.

PubMed

Zhao, Di; Weng, Chunhua

2011-10-01

In this paper, we propose a novel method that combines PubMed knowledge and Electronic Health Records to develop a weighted Bayesian Network Inference (BNI) model for pancreatic cancer prediction. We selected 20 common risk factors associated with pancreatic cancer and used PubMed knowledge to weigh the risk factors. A keyword-based algorithm was developed to extract and classify PubMed abstracts into three categories that represented positive, negative, or neutral associations between each risk factor and pancreatic cancer. Then we designed a weighted BNI model by adding the normalized weights into a conventional BNI model. We used this model to extract the EHR values for patients with or without pancreatic cancer, which then enabled us to calculate the prior probabilities for the 20 risk factors in the BNI. The software iDiagnosis was designed to use this weighted BNI model for predicting pancreatic cancer. In an evaluation using a case-control dataset, the weighted BNI model significantly outperformed the conventional BNI and two other classifiers (k-Nearest Neighbor and Support Vector Machine). We conclude that the weighted BNI using PubMed knowledge and EHR data shows remarkable accuracy improvement over existing representative methods for pancreatic cancer prediction. Copyright © 2011 Elsevier Inc. All rights reserved.

Combining PubMed Knowledge and EHR Data to Develop a Weighted Bayesian Network for Pancreatic Cancer Prediction

PubMed Central

Zhao, Di; Weng, Chunhua

2011-01-01

In this paper, we propose a novel method that combines PubMed knowledge and Electronic Health Records to develop a weighted Bayesian Network Inference (BNI) model for pancreatic cancer prediction. We selected 20 common risk factors associated with pancreatic cancer and used PubMed knowledge to weigh the risk factors. A keyword-based algorithm was developed to extract and classify PubMed abstracts into three categories that represented positive, negative, or neutral associations between each risk factor and pancreatic cancer. Then we designed a weighted BNI model by adding the normalized weights into a conventional BNI model. We used this model to extract the EHR values for patients with or without pancreatic cancer, which then enabled us to calculate the prior probabilities for the 20 risk factors in the BNI. The software iDiagnosis was designed to use this weighted BNI model for predicting pancreatic cancer. In an evaluation using a case-control dataset, the weighted BNI model significantly outperformed the conventional BNI and two other classifiers (k-Nearest Neighbor and Support Vector Machine). We conclude that the weighted BNI using PubMed knowledge and EHR data shows remarkable accuracy improvement over existing representative methods for pancreatic cancer prediction. PMID:21642013

INTEGRATING EARTH OBSERVATION AND FIELD DATA INTO A LYME DISEASE MODEL TO MAP AND PREDICT RISKS TO BIODIVERSITY AND HUMAN HEALTH

EPA Science Inventory

DW-75-92243901
Title: Integrating Earth Observation and Field Data into a Lyme Disease Model to Map and Predict Risks to Biodiversity and Human HealthDurland Fish, Maria Diuk-Wasser, Joe Roman, Yongtao Guan, Brad Lobitz, Rama Nemani, Joe Piesman, Montira J. Pongsiri, F...

Validation of a probabilistic post-fire erosion model

Treesearch

Pete Robichaud; William J. Elliot; Sarah A. Lewis; Mary Ellen Miller

2016-01-01

Post-fire increases of runoff and erosion often occur and land managers need tools to be able to project the increased risk. The Erosion Risk Management Tool (ERMiT) uses the Water Erosion Prediction Project (WEPP) model as the underlying processor. ERMiT predicts the probability of a given amount of hillslope sediment delivery from a single rainfall or...

A test of the vulnerability model: temperament and temperament change as predictors of future mental disorders - the TRAILS study.

PubMed

Laceulle, Odilia M; Ormel, Johan; Vollebergh, Wilma A M; van Aken, Marcel A G; Nederhof, Esther

2014-03-01

This study aimed to test the vulnerability model of the relationship between temperament and mental disorders using a large sample of adolescents from the TRacking Adolescents Individual Lives' Survey (TRAILS). The vulnerability model argues that particular temperaments can place individuals at risk for the development of mental health problems. Importantly, the model may imply that not only baseline temperament predicts mental health problems prospectively, but additionally, that changes in temperament predict corresponding changes in risk for mental health problems. Data were used from 1195 TRAILS participants. Adolescent temperament was assessed both at age 11 and at age 16. Onset of mental disorders between age 16 and 19 was assessed at age 19, by means of the World Health Organization Composite International Diagnostic Interview (WHO CIDI). Results showed that temperament at age 11 predicted future mental disorders, thereby providing support for the vulnerability model. Moreover, temperament change predicted future mental disorders above and beyond the effect of basal temperament. For example, an increase in frustration increased the risk of mental disorders proportionally. This study confirms, and extends, the vulnerability model. Consequences of both temperament and temperament change were general (e.g., changes in frustration predicted both internalizing and externalizing disorders) as well as dimension specific (e.g., changes in fear predicted internalizing but not externalizing disorders). These findings confirm previous studies, which showed that mental disorders have both unique and shared underlying temperamental risk factors. © 2013 The Authors. Journal of Child Psychology and Psychiatry © 2013 Association for Child and Adolescent Mental Health.

Conditional Toxicity Value (CTV) Predictor: An In Silico Approach for Generating Quantitative Risk Estimates for Chemicals.

PubMed

Wignall, Jessica A; Muratov, Eugene; Sedykh, Alexander; Guyton, Kathryn Z; Tropsha, Alexander; Rusyn, Ivan; Chiu, Weihsueh A

2018-05-01

Human health assessments synthesize human, animal, and mechanistic data to produce toxicity values that are key inputs to risk-based decision making. Traditional assessments are data-, time-, and resource-intensive, and they cannot be developed for most environmental chemicals owing to a lack of appropriate data. As recommended by the National Research Council, we propose a solution for predicting toxicity values for data-poor chemicals through development of quantitative structure-activity relationship (QSAR) models. We used a comprehensive database of chemicals with existing regulatory toxicity values from U.S. federal and state agencies to develop quantitative QSAR models. We compared QSAR-based model predictions to those based on high-throughput screening (HTS) assays. QSAR models for noncancer threshold-based values and cancer slope factors had cross-validation-based Q 2 of 0.25-0.45, mean model errors of 0.70-1.11 log 10 units, and applicability domains covering >80% of environmental chemicals. Toxicity values predicted from QSAR models developed in this study were more accurate and precise than those based on HTS assays or mean-based predictions. A publicly accessible web interface to make predictions for any chemical of interest is available at http://toxvalue.org. An in silico tool that can predict toxicity values with an uncertainty of an order of magnitude or less can be used to quickly and quantitatively assess risks of environmental chemicals when traditional toxicity data or human health assessments are unavailable. This tool can fill a critical gap in the risk assessment and management of data-poor chemicals. https://doi.org/10.1289/EHP2998.

A risk score for in-hospital death in patients admitted with ischemic or hemorrhagic stroke.

PubMed

Smith, Eric E; Shobha, Nandavar; Dai, David; Olson, DaiWai M; Reeves, Mathew J; Saver, Jeffrey L; Hernandez, Adrian F; Peterson, Eric D; Fonarow, Gregg C; Schwamm, Lee H

2013-01-28

We aimed to derive and validate a single risk score for predicting death from ischemic stroke (IS), intracerebral hemorrhage (ICH), and subarachnoid hemorrhage (SAH). Data from 333 865 stroke patients (IS, 82.4%; ICH, 11.2%; SAH, 2.6%; uncertain type, 3.8%) in the Get With The Guidelines-Stroke database were used. In-hospital mortality varied greatly according to stroke type (IS, 5.5%; ICH, 27.2%; SAH, 25.1%; unknown type, 6.0%; P<0.001). The patients were randomly divided into derivation (60%) and validation (40%) samples. Logistic regression was used to determine the independent predictors of mortality and to assign point scores for a prediction model in the overall population and in the subset with the National Institutes of Health Stroke Scale (NIHSS) recorded (37.1%). The c statistic, a measure of how well the models discriminate the risk of death, was 0.78 in the overall validation sample and 0.86 in the model including NIHSS. The model with NIHSS performed nearly as well in each stroke type as in the overall model including all types (c statistics for IS alone, 0.85; for ICH alone, 0.83; for SAH alone, 0.83; uncertain type alone, 0.86). The calibration of the model was excellent, as demonstrated by plots of observed versus predicted mortality. A single prediction score for all stroke types can be used to predict risk of in-hospital death following stroke admission. Incorporation of NIHSS information substantially improves this predictive accuracy.

Assessment of uncertainties in radiation-induced cancer risk predictions at clinically relevant doses

DOE Office of Scientific and Technical Information (OSTI.GOV)

Nguyen, J.; Moteabbed, M.; Paganetti, H., E-mail: hpaganetti@mgh.harvard.edu

2015-01-15

Purpose: Theoretical dose–response models offer the possibility to assess second cancer induction risks after external beam therapy. The parameters used in these models are determined with limited data from epidemiological studies. Risk estimations are thus associated with considerable uncertainties. This study aims at illustrating uncertainties when predicting the risk for organ-specific second cancers in the primary radiation field illustrated by choosing selected treatment plans for brain cancer patients. Methods: A widely used risk model was considered in this study. The uncertainties of the model parameters were estimated with reported data of second cancer incidences for various organs. Standard error propagationmore » was then subsequently applied to assess the uncertainty in the risk model. Next, second cancer risks of five pediatric patients treated for cancer in the head and neck regions were calculated. For each case, treatment plans for proton and photon therapy were designed to estimate the uncertainties (a) in the lifetime attributable risk (LAR) for a given treatment modality and (b) when comparing risks of two different treatment modalities. Results: Uncertainties in excess of 100% of the risk were found for almost all organs considered. When applied to treatment plans, the calculated LAR values have uncertainties of the same magnitude. A comparison between cancer risks of different treatment modalities, however, does allow statistically significant conclusions. In the studied cases, the patient averaged LAR ratio of proton and photon treatments was 0.35, 0.56, and 0.59 for brain carcinoma, brain sarcoma, and bone sarcoma, respectively. Their corresponding uncertainties were estimated to be potentially below 5%, depending on uncertainties in dosimetry. Conclusions: The uncertainty in the dose–response curve in cancer risk models makes it currently impractical to predict the risk for an individual external beam treatment. On the other hand, the ratio of absolute risks between two modalities is less sensitive to the uncertainties in the risk model and can provide statistically significant estimates.« less

Prediction of liver disease in patients whose liver function tests have been checked in primary care: model development and validation using population-based observational cohorts.

PubMed

McLernon, David J; Donnan, Peter T; Sullivan, Frank M; Roderick, Paul; Rosenberg, William M; Ryder, Steve D; Dillon, John F

2014-06-02

To derive and validate a clinical prediction model to estimate the risk of liver disease diagnosis following liver function tests (LFTs) and to convert the model to a simplified scoring tool for use in primary care. Population-based observational cohort study of patients in Tayside Scotland identified as having their LFTs performed in primary care and followed for 2 years. Biochemistry data were linked to secondary care, prescriptions and mortality data to ascertain baseline characteristics of the derivation cohort. A separate validation cohort was obtained from 19 general practices across the rest of Scotland to externally validate the final model. Primary care, Tayside, Scotland. Derivation cohort: LFT results from 310 511 patients. After exclusions (including: patients under 16 years, patients having initial LFTs measured in secondary care, bilirubin >35 μmol/L, liver complications within 6 weeks and history of a liver condition), the derivation cohort contained 95 977 patients with no clinically apparent liver condition. Validation cohort: after exclusions, this cohort contained 11 653 patients. Diagnosis of a liver condition within 2 years. From the derivation cohort (n=95 977), 481 (0.5%) were diagnosed with a liver disease. The model showed good discrimination (C-statistic=0.78). Given the low prevalence of liver disease, the negative predictive values were high. Positive predictive values were low but rose to 20-30% for high-risk patients. This study successfully developed and validated a clinical prediction model and subsequent scoring tool, the Algorithm for Liver Function Investigations (ALFI), which can predict liver disease risk in patients with no clinically obvious liver disease who had their initial LFTs taken in primary care. ALFI can help general practitioners focus referral on a small subset of patients with higher predicted risk while continuing to address modifiable liver disease risk factors in those at lower risk. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

An emission-weighted proximity model for air pollution exposure assessment.

PubMed

Zou, Bin; Wilson, J Gaines; Zhan, F Benjamin; Zeng, Yongnian

2009-08-15

Among the most common spatial models for estimating personal exposure are Traditional Proximity Models (TPMs). Though TPMs are straightforward to configure and interpret, they are prone to extensive errors in exposure estimates and do not provide prospective estimates. To resolve these inherent problems with TPMs, we introduce here a novel Emission Weighted Proximity Model (EWPM) to improve the TPM, which takes into consideration the emissions from all sources potentially influencing the receptors. EWPM performance was evaluated by comparing the normalized exposure risk values of sulfur dioxide (SO(2)) calculated by EWPM with those calculated by TPM and monitored observations over a one-year period in two large Texas counties. In order to investigate whether the limitations of TPM in potential exposure risk prediction without recorded incidence can be overcome, we also introduce a hybrid framework, a 'Geo-statistical EWPM'. Geo-statistical EWPM is a synthesis of Ordinary Kriging Geo-statistical interpolation and EWPM. The prediction results are presented as two potential exposure risk prediction maps. The performance of these two exposure maps in predicting individual SO(2) exposure risk was validated with 10 virtual cases in prospective exposure scenarios. Risk values for EWPM were clearly more agreeable with the observed concentrations than those from TPM. Over the entire study area, the mean SO(2) exposure risk from EWPM was higher relative to TPM (1.00 vs. 0.91). The mean bias of the exposure risk values of 10 virtual cases between EWPM and 'Geo-statistical EWPM' are much smaller than those between TPM and 'Geo-statistical TPM' (5.12 vs. 24.63). EWPM appears to more accurately portray individual exposure relative to TPM. The 'Geo-statistical EWPM' effectively augments the role of the standard proximity model and makes it possible to predict individual risk in future exposure scenarios resulting in adverse health effects from environmental pollution.

Pretreatment data is highly predictive of liver chemistry signals in clinical trials

PubMed Central

Cai, Zhaohui; Bresell, Anders; Steinberg, Mark H; Silberg, Debra G; Furlong, Stephen T

2012-01-01

Purpose The goal of this retrospective analysis was to assess how well predictive models could determine which patients would develop liver chemistry signals during clinical trials based on their pretreatment (baseline) information. Patients and methods Based on data from 24 late-stage clinical trials, classification models were developed to predict liver chemistry outcomes using baseline information, which included demographics, medical history, concomitant medications, and baseline laboratory results. Results Predictive models using baseline data predicted which patients would develop liver signals during the trials with average validation accuracy around 80%. Baseline levels of individual liver chemistry tests were most important for predicting their own elevations during the trials. High bilirubin levels at baseline were not uncommon and were associated with a high risk of developing biochemical Hy’s law cases. Baseline γ-glutamyltransferase (GGT) level appeared to have some predictive value, but did not increase predictability beyond using established liver chemistry tests. Conclusion It is possible to predict which patients are at a higher risk of developing liver chemistry signals using pretreatment (baseline) data. Derived knowledge from such predictions may allow proactive and targeted risk management, and the type of analysis described here could help determine whether new biomarkers offer improved performance over established ones. PMID:23226004

Assessing Risk Prediction Models Using Individual Participant Data From Multiple Studies

PubMed Central

Pennells, Lisa; Kaptoge, Stephen; White, Ian R.; Thompson, Simon G.; Wood, Angela M.; Tipping, Robert W.; Folsom, Aaron R.; Couper, David J.; Ballantyne, Christie M.; Coresh, Josef; Goya Wannamethee, S.; Morris, Richard W.; Kiechl, Stefan; Willeit, Johann; Willeit, Peter; Schett, Georg; Ebrahim, Shah; Lawlor, Debbie A.; Yarnell, John W.; Gallacher, John; Cushman, Mary; Psaty, Bruce M.; Tracy, Russ; Tybjærg-Hansen, Anne; Price, Jackie F.; Lee, Amanda J.; McLachlan, Stela; Khaw, Kay-Tee; Wareham, Nicholas J.; Brenner, Hermann; Schöttker, Ben; Müller, Heiko; Jansson, Jan-Håkan; Wennberg, Patrik; Salomaa, Veikko; Harald, Kennet; Jousilahti, Pekka; Vartiainen, Erkki; Woodward, Mark; D'Agostino, Ralph B.; Bladbjerg, Else-Marie; Jørgensen, Torben; Kiyohara, Yutaka; Arima, Hisatomi; Doi, Yasufumi; Ninomiya, Toshiharu; Dekker, Jacqueline M.; Nijpels, Giel; Stehouwer, Coen D. A.; Kauhanen, Jussi; Salonen, Jukka T.; Meade, Tom W.; Cooper, Jackie A.; Cushman, Mary; Folsom, Aaron R.; Psaty, Bruce M.; Shea, Steven; Döring, Angela; Kuller, Lewis H.; Grandits, Greg; Gillum, Richard F.; Mussolino, Michael; Rimm, Eric B.; Hankinson, Sue E.; Manson, JoAnn E.; Pai, Jennifer K.; Kirkland, Susan; Shaffer, Jonathan A.; Shimbo, Daichi; Bakker, Stephan J. L.; Gansevoort, Ron T.; Hillege, Hans L.; Amouyel, Philippe; Arveiler, Dominique; Evans, Alun; Ferrières, Jean; Sattar, Naveed; Westendorp, Rudi G.; Buckley, Brendan M.; Cantin, Bernard; Lamarche, Benoît; Barrett-Connor, Elizabeth; Wingard, Deborah L.; Bettencourt, Richele; Gudnason, Vilmundur; Aspelund, Thor; Sigurdsson, Gunnar; Thorsson, Bolli; Kavousi, Maryam; Witteman, Jacqueline C.; Hofman, Albert; Franco, Oscar H.; Howard, Barbara V.; Zhang, Ying; Best, Lyle; Umans, Jason G.; Onat, Altan; Sundström, Johan; Michael Gaziano, J.; Stampfer, Meir; Ridker, Paul M.; Michael Gaziano, J.; Ridker, Paul M.; Marmot, Michael; Clarke, Robert; Collins, Rory; Fletcher, Astrid; Brunner, Eric; Shipley, Martin; Kivimäki, Mika; Ridker, Paul M.; Buring, Julie; Cook, Nancy; Ford, Ian; Shepherd, James; Cobbe, Stuart M.; Robertson, Michele; Walker, Matthew; Watson, Sarah; Alexander, Myriam; Butterworth, Adam S.; Angelantonio, Emanuele Di; Gao, Pei; Haycock, Philip; Kaptoge, Stephen; Pennells, Lisa; Thompson, Simon G.; Walker, Matthew; Watson, Sarah; White, Ian R.; Wood, Angela M.; Wormser, David; Danesh, John

2014-01-01

Individual participant time-to-event data from multiple prospective epidemiologic studies enable detailed investigation into the predictive ability of risk models. Here we address the challenges in appropriately combining such information across studies. Methods are exemplified by analyses of log C-reactive protein and conventional risk factors for coronary heart disease in the Emerging Risk Factors Collaboration, a collation of individual data from multiple prospective studies with an average follow-up duration of 9.8 years (dates varied). We derive risk prediction models using Cox proportional hazards regression analysis stratified by study and obtain estimates of risk discrimination, Harrell's concordance index, and Royston's discrimination measure within each study; we then combine the estimates across studies using a weighted meta-analysis. Various weighting approaches are compared and lead us to recommend using the number of events in each study. We also discuss the calculation of measures of reclassification for multiple studies. We further show that comparison of differences in predictive ability across subgroups should be based only on within-study information and that combining measures of risk discrimination from case-control studies and prospective studies is problematic. The concordance index and discrimination measure gave qualitatively similar results throughout. While the concordance index was very heterogeneous between studies, principally because of differing age ranges, the increments in the concordance index from adding log C-reactive protein to conventional risk factors were more homogeneous. PMID:24366051

Assessing risk prediction models using individual participant data from multiple studies.

PubMed

Pennells, Lisa; Kaptoge, Stephen; White, Ian R; Thompson, Simon G; Wood, Angela M

2014-03-01

Individual participant time-to-event data from multiple prospective epidemiologic studies enable detailed investigation into the predictive ability of risk models. Here we address the challenges in appropriately combining such information across studies. Methods are exemplified by analyses of log C-reactive protein and conventional risk factors for coronary heart disease in the Emerging Risk Factors Collaboration, a collation of individual data from multiple prospective studies with an average follow-up duration of 9.8 years (dates varied). We derive risk prediction models using Cox proportional hazards regression analysis stratified by study and obtain estimates of risk discrimination, Harrell's concordance index, and Royston's discrimination measure within each study; we then combine the estimates across studies using a weighted meta-analysis. Various weighting approaches are compared and lead us to recommend using the number of events in each study. We also discuss the calculation of measures of reclassification for multiple studies. We further show that comparison of differences in predictive ability across subgroups should be based only on within-study information and that combining measures of risk discrimination from case-control studies and prospective studies is problematic. The concordance index and discrimination measure gave qualitatively similar results throughout. While the concordance index was very heterogeneous between studies, principally because of differing age ranges, the increments in the concordance index from adding log C-reactive protein to conventional risk factors were more homogeneous.

Lung cancer risk prediction to select smokers for screening CT--a model based on the Italian COSMOS trial.

PubMed

Maisonneuve, Patrick; Bagnardi, Vincenzo; Bellomi, Massimo; Spaggiari, Lorenzo; Pelosi, Giuseppe; Rampinelli, Cristiano; Bertolotti, Raffaella; Rotmensz, Nicole; Field, John K; Decensi, Andrea; Veronesi, Giulia

2011-11-01

Screening with low-dose helical computed tomography (CT) has been shown to significantly reduce lung cancer mortality but the optimal target population and time interval to subsequent screening are yet to be defined. We developed two models to stratify individual smokers according to risk of developing lung cancer. We first used the number of lung cancers detected at baseline screening CT in the 5,203 asymptomatic participants of the COSMOS trial to recalibrate the Bach model, which we propose using to select smokers for screening. Next, we incorporated lung nodule characteristics and presence of emphysema identified at baseline CT into the Bach model and proposed the resulting multivariable model to predict lung cancer risk in screened smokers after baseline CT. Age and smoking exposure were the main determinants of lung cancer risk. The recalibrated Bach model accurately predicted lung cancers detected during the first year of screening. Presence of nonsolid nodules (RR = 10.1, 95% CI = 5.57-18.5), nodule size more than 8 mm (RR = 9.89, 95% CI = 5.84-16.8), and emphysema (RR = 2.36, 95% CI = 1.59-3.49) at baseline CT were all significant predictors of subsequent lung cancers. Incorporation of these variables into the Bach model increased the predictive value of the multivariable model (c-index = 0.759, internal validation). The recalibrated Bach model seems suitable for selecting the higher risk population for recruitment for large-scale CT screening. The Bach model incorporating CT findings at baseline screening could help defining the time interval to subsequent screening in individual participants. Further studies are necessary to validate these models.

Risk adjustment for health care financing in chronic disease: what are we missing by failing to account for disease severity?

PubMed

Omachi, Theodore A; Gregorich, Steven E; Eisner, Mark D; Penaloza, Renee A; Tolstykh, Irina V; Yelin, Edward H; Iribarren, Carlos; Dudley, R Adams; Blanc, Paul D

2013-08-01

Adjustment for differing risks among patients is usually incorporated into newer payment approaches, and current risk models rely on age, sex, and diagnosis codes. It is unknown the extent to which controlling additionally for disease severity improves cost prediction. Failure to adjust for within-disease variation may create incentives to avoid sicker patients. We address this issue among patients with chronic obstructive pulmonary disease (COPD). Cost and clinical data were collected prospectively from 1202 COPD patients at Kaiser Permanente. Baseline analysis included age, sex, and diagnosis codes (using the Diagnostic Cost Group Relative Risk Score) in a general linear model predicting total medical costs in the following year. We determined whether adding COPD severity measures-forced expiratory volume in 1 second, 6-Minute Walk Test, dyspnea score, body mass index, and BODE Index (composite of the other 4 measures)-improved predictions. Separately, we examined household income as a cost predictor. Mean costs were $12,334/y. Controlling for Relative Risk Score, each ½ SD worsening in COPD severity factor was associated with $629 to $1135 in increased annual costs (all P<0.01). The lowest stratum of forced expiratory volume in 1 second (<30% normal) predicted $4098 (95% confidence interval, $576-$8773) additional costs. Household income predicted excess costs when added to the baseline model (P=0.038), but this became nonsignificant when also incorporating the BODE Index. Disease severity measures explain significant cost variations beyond current risk models, and adding them to such models appears important to fairly compensate organizations that accept responsibility for sicker COPD patients. Appropriately controlling for disease severity also accounts for costs otherwise associated with lower socioeconomic status.

Novel biomarker-based model for the prediction of sorafenib response and overall survival in advanced hepatocellular carcinoma: a prospective cohort study.

PubMed

Kim, Hwi Young; Lee, Dong Hyeon; Lee, Jeong-Hoon; Cho, Young Youn; Cho, Eun Ju; Yu, Su Jong; Kim, Yoon Jun; Yoon, Jung-Hwan

2018-03-20

Prediction of the outcome of sorafenib therapy using biomarkers is an unmet clinical need in patients with advanced hepatocellular carcinoma (HCC). The aim was to develop and validate a biomarker-based model for predicting sorafenib response and overall survival (OS). This prospective cohort study included 124 consecutive HCC patients (44 with disease control, 80 with progression) with Child-Pugh class A liver function, who received sorafenib. Potential serum biomarkers (namely, hepatocyte growth factor [HGF], fibroblast growth factor [FGF], vascular endothelial growth factor receptor-1, CD117, and angiopoietin-2) were tested. After identifying independent predictors of tumor response, a risk scoring system for predicting OS was developed and 3-fold internal validation was conducted. A risk scoring system was developed with six covariates: etiology, platelet count, Barcelona Clinic Liver Cancer stage, protein induced by vitamin K absence-II, HGF, and FGF. When patients were stratified into low-risk (score ≤ 5), intermediate-risk (score 6), and high-risk (score ≥ 7) groups, the model provided good discriminant functions on tumor response (concordance [c]-index, 0.884) and 12-month survival (area under the curve [AUC], 0.825). The median OS was 19.0, 11.2, and 6.1 months in the low-, intermediate-, and high-risk group, respectively (P < 0.001). In internal validation, the model maintained good discriminant functions on tumor response (c-index, 0.825) and 12-month survival (AUC, 0.803), and good calibration functions (all P > 0.05 between expected and observed values). This new model including serum FGF and HGF showed good performance in predicting the response to sorafenib and survival in patients with advanced HCC.

External model validation of binary clinical risk prediction models in cardiovascular and thoracic surgery.

PubMed

Hickey, Graeme L; Blackstone, Eugene H

2016-08-01

Clinical risk-prediction models serve an important role in healthcare. They are used for clinical decision-making and measuring the performance of healthcare providers. To establish confidence in a model, external model validation is imperative. When designing such an external model validation study, thought must be given to patient selection, risk factor and outcome definitions, missing data, and the transparent reporting of the analysis. In addition, there are a number of statistical methods available for external model validation. Execution of a rigorous external validation study rests in proper study design, application of suitable statistical methods, and transparent reporting. Copyright © 2016 The American Association for Thoracic Surgery. Published by Elsevier Inc. All rights reserved.

Evaluating predictive modeling's potential to improve teleretinal screening participation in urban safety net clinics.

PubMed

Ogunyemi, Omolola; Teklehaimanot, Senait; Patty, Lauren; Moran, Erin; George, Sheba

2013-01-01

Screening guidelines for diabetic patients recommend yearly eye examinations to detect diabetic retinopathy and other forms of diabetic eye disease. However, annual screening rates for retinopathy in US urban safety net settings remain low. Using data gathered from a study of teleretinal screening in six urban safety net clinics, we assessed whether predictive modeling could be of value in identifying patients at risk of developing retinopathy. We developed and examined the accuracy of two predictive modeling approaches for diabetic retinopathy in a sample of 513 diabetic individuals, using routinely available clinical variables from retrospective medical record reviews. Bayesian networks and radial basis function (neural) networks were learned using ten-fold cross-validation. The predictive models were modestly predictive with the best model having an AUC of 0.71. Using routinely available clinical variables to predict patients at risk of developing retinopathy and to target them for annual eye screenings may be of some usefulness to safety net clinics.

Evaluation of a Genetic Risk Score to Improve Risk Prediction for Alzheimer's Disease.

PubMed

Chouraki, Vincent; Reitz, Christiane; Maury, Fleur; Bis, Joshua C; Bellenguez, Celine; Yu, Lei; Jakobsdottir, Johanna; Mukherjee, Shubhabrata; Adams, Hieab H; Choi, Seung Hoan; Larson, Eric B; Fitzpatrick, Annette; Uitterlinden, Andre G; de Jager, Philip L; Hofman, Albert; Gudnason, Vilmundur; Vardarajan, Badri; Ibrahim-Verbaas, Carla; van der Lee, Sven J; Lopez, Oscar; Dartigues, Jean-François; Berr, Claudine; Amouyel, Philippe; Bennett, David A; van Duijn, Cornelia; DeStefano, Anita L; Launer, Lenore J; Ikram, M Arfan; Crane, Paul K; Lambert, Jean-Charles; Mayeux, Richard; Seshadri, Sudha

2016-06-18

Effective prevention of Alzheimer's disease (AD) requires the development of risk prediction tools permitting preclinical intervention. We constructed a genetic risk score (GRS) comprising common genetic variants associated with AD, evaluated its association with incident AD and assessed its capacity to improve risk prediction over traditional models based on age, sex, education, and APOEɛ4. In eight prospective cohorts included in the International Genomics of Alzheimer's Project (IGAP), we derived weighted sum of risk alleles from the 19 top SNPs reported by the IGAP GWAS in participants aged 65 and older without prevalent dementia. Hazard ratios (HR) of incident AD were estimated in Cox models. Improvement in risk prediction was measured by the difference in C-index (Δ-C), the integrated discrimination improvement (IDI) and continuous net reclassification improvement (NRI>0). Overall, 19,687 participants at risk were included, of whom 2,782 developed AD. The GRS was associated with a 17% increase in AD risk (pooled HR = 1.17; 95% CI =   [1.13-1.21] per standard deviation increase in GRS; p-value =  2.86×10-16). This association was stronger among persons with at least one APOEɛ4 allele (HRGRS = 1.24; 95% CI =   [1.15-1.34]) than in others (HRGRS = 1.13; 95% CI =   [1.08-1.18]; pinteraction = 3.45×10-2). Risk prediction after seven years of follow-up showed a small improvement when adding the GRS to age, sex, APOEɛ4, and education (Δ-Cindex =  0.0043 [0.0019-0.0067]). Similar patterns were observed for IDI and NRI>0. In conclusion, a risk score incorporating common genetic variation outside the APOEɛ4 locus improved AD risk prediction and may facilitate risk stratification for prevention trials.

Methods and Techniques for Risk Prediction of Space Shuttle Upgrades

NASA Technical Reports Server (NTRS)

Hoffman, Chad R.; Pugh, Rich; Safie, Fayssal

1998-01-01

Since the Space Shuttle Accident in 1986, NASA has been trying to incorporate probabilistic risk assessment (PRA) in decisions concerning the Space Shuttle and other NASA projects. One major study NASA is currently conducting is in the PRA area in establishing an overall risk model for the Space Shuttle System. The model is intended to provide a tool to predict the Shuttle risk and to perform sensitivity analyses and trade studies including evaluation of upgrades. Marshall Space Flight Center (MSFC) and its prime contractors including Pratt and Whitney (P&W) are part of the NASA team conducting the PRA study. MSFC responsibility involves modeling the External Tank (ET), the Solid Rocket Booster (SRB), the Reusable Solid Rocket Motor (RSRM), and the Space Shuttle Main Engine (SSME). A major challenge that faced the PRA team is modeling the shuttle upgrades. This mainly includes the P&W High Pressure Fuel Turbopump (HPFTP) and the High Pressure Oxidizer Turbopump (HPOTP). The purpose of this paper is to discuss the various methods and techniques used for predicting the risk of the P&W redesigned HPFTP and HPOTP.

The Acquired Preparedness Model of Risk for Bulimic Symptom Development

PubMed Central

Combs, Jessica L.; Smith, Gregory T.; Flory, Kate; Simmons, Jean R.; Hill, Kelly K.

2010-01-01

The authors applied person-environment transaction theory to test the acquired preparedness model of eating disorder risk. The model holds that (a) middle school girls high in the trait of ineffectiveness are differentially prepared to acquire high risk expectancies for reinforcement from dieting/thinness; (b) those expectancies predict subsequent binge eating and purging; and (c) the influence of the disposition of ineffectiveness on binge eating and purging is mediated by dieting/thinness expectancies. In a three-wave longitudinal study of 394 middle school girls, they found support for the model. Seventh grade girls’ scores on ineffectiveness predicted their subsequent endorsement of high risk dieting/thinness expectancies, which in turn predicted subsequent increases in binge eating and purging. Statistical tests of mediation supported the hypothesis that the prospective relation between ineffectiveness and binge eating was mediated by dieting/thinness expectancies, as was the prospective relation between ineffectiveness and purging. This application of a basic science theory to eating disorder risk appears fruitful, and the findings suggest the importance of early interventions that address both disposition and learning. PMID:20853933

Diagnosis-Based Risk Adjustment for Medicare Capitation Payments

PubMed Central

Ellis, Randall P.; Pope, Gregory C.; Iezzoni, Lisa I.; Ayanian, John Z.; Bates, David W.; Burstin, Helen; Ash, Arlene S.

1996-01-01

Using 1991-92 data for a 5-percent Medicare sample, we develop, estimate, and evaluate risk-adjustment models that utilize diagnostic information from both inpatient and ambulatory claims to adjust payments for aged and disabled Medicare enrollees. Hierarchical coexisting conditions (HCC) models achieve greater explanatory power than diagnostic cost group (DCG) models by taking account of multiple coexisting medical conditions. Prospective models predict average costs of individuals with chronic conditions nearly as well as concurrent models. All models predict medical costs far more accurately than the current health maintenance organization (HMO) payment formula. PMID:10172666

Development and validation of multivariable predictive model for thromboembolic events in lymphoma patients.

PubMed

Antic, Darko; Milic, Natasa; Nikolovski, Srdjan; Todorovic, Milena; Bila, Jelena; Djurdjevic, Predrag; Andjelic, Bosko; Djurasinovic, Vladislava; Sretenovic, Aleksandra; Vukovic, Vojin; Jelicic, Jelena; Hayman, Suzanne; Mihaljevic, Biljana

2016-10-01

Lymphoma patients are at increased risk of thromboembolic events but thromboprophylaxis in these patients is largely underused. We sought to develop and validate a simple model, based on individual clinical and laboratory patient characteristics that would designate lymphoma patients at risk for thromboembolic event. The study population included 1,820 lymphoma patients who were treated in the Lymphoma Departments at the Clinics of Hematology, Clinical Center of Serbia and Clinical Center Kragujevac. The model was developed using data from a derivation cohort (n = 1,236), and further assessed in the validation cohort (n = 584). Sixty-five patients (5.3%) in the derivation cohort and 34 (5.8%) patients in the validation cohort developed thromboembolic events. The variables independently associated with risk for thromboembolism were: previous venous and/or arterial events, mediastinal involvement, BMI>30 kg/m(2) , reduced mobility, extranodal localization, development of neutropenia and hemoglobin level < 100g/L. Based on the risk model score, the population was divided into the following risk categories: low (score 0-1), intermediate (score 2-3), and high (score >3). For patients classified at risk (intermediate and high-risk scores), the model produced negative predictive value of 98.5%, positive predictive value of 25.1%, sensitivity of 75.4%, and specificity of 87.5%. A high-risk score had positive predictive value of 65.2%. The diagnostic performance measures retained similar values in the validation cohort. Developed prognostic Thrombosis Lymphoma - ThroLy score is more specific for lymphoma patients than any other available score targeting thrombosis in cancer patients. Am. J. Hematol. 91:1014-1019, 2016. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges.

PubMed

Goldstein, Benjamin A; Navar, Ann Marie; Carter, Rickey E

2017-06-14

Risk prediction plays an important role in clinical cardiology research. Traditionally, most risk models have been based on regression models. While useful and robust, these statistical methods are limited to using a small number of predictors which operate in the same way on everyone, and uniformly throughout their range. The purpose of this review is to illustrate the use of machine-learning methods for development of risk prediction models. Typically presented as black box approaches, most machine-learning methods are aimed at solving particular challenges that arise in data analysis that are not well addressed by typical regression approaches. To illustrate these challenges, as well as how different methods can address them, we consider trying to predicting mortality after diagnosis of acute myocardial infarction. We use data derived from our institution's electronic health record and abstract data on 13 regularly measured laboratory markers. We walk through different challenges that arise in modelling these data and then introduce different machine-learning approaches. Finally, we discuss general issues in the application of machine-learning methods including tuning parameters, loss functions, variable importance, and missing data. Overall, this review serves as an introduction for those working on risk modelling to approach the diffuse field of machine learning. © The Author 2016. Published by Oxford University Press on behalf of the European Society of Cardiology.

A comparison of imputation techniques for handling missing predictor values in a risk model with a binary outcome.

PubMed

Ambler, Gareth; Omar, Rumana Z; Royston, Patrick

2007-06-01

Risk models that aim to predict the future course and outcome of disease processes are increasingly used in health research, and it is important that they are accurate and reliable. Most of these risk models are fitted using routinely collected data in hospitals or general practices. Clinical outcomes such as short-term mortality will be near-complete, but many of the predictors may have missing values. A common approach to dealing with this is to perform a complete-case analysis. However, this may lead to overfitted models and biased estimates if entire patient subgroups are excluded. The aim of this paper is to investigate a number of methods for imputing missing data to evaluate their effect on risk model estimation and the reliability of the predictions. Multiple imputation methods, including hotdecking and multiple imputation by chained equations (MICE), were investigated along with several single imputation methods. A large national cardiac surgery database was used to create simulated yet realistic datasets. The results suggest that complete case analysis may produce unreliable risk predictions and should be avoided. Conditional mean imputation performed well in our scenario, but may not be appropriate if using variable selection methods. MICE was amongst the best performing multiple imputation methods with regards to the quality of the predictions. Additionally, it produced the least biased estimates, with good coverage, and hence is recommended for use in practice.

Predicting all-cause risk of 30-day hospital readmission using artificial neural networks.

PubMed

Jamei, Mehdi; Nisnevich, Aleksandr; Wetchler, Everett; Sudat, Sylvia; Liu, Eric

2017-01-01

Avoidable hospital readmissions not only contribute to the high costs of healthcare in the US, but also have an impact on the quality of care for patients. Large scale adoption of Electronic Health Records (EHR) has created the opportunity to proactively identify patients with high risk of hospital readmission, and apply effective interventions to mitigate that risk. To that end, in the past, numerous machine-learning models have been employed to predict the risk of 30-day hospital readmission. However, the need for an accurate and real-time predictive model, suitable for hospital setting applications still exists. Here, using data from more than 300,000 hospital stays in California from Sutter Health's EHR system, we built and tested an artificial neural network (NN) model based on Google's TensorFlow library. Through comparison with other traditional and non-traditional models, we demonstrated that neural networks are great candidates to capture the complexity and interdependency of various data fields in EHRs. LACE, the current industry standard, showed a precision (PPV) of 0.20 in identifying high-risk patients in our database. In contrast, our NN model yielded a PPV of 0.24, which is a 20% improvement over LACE. Additionally, we discussed the predictive power of Social Determinants of Health (SDoH) data, and presented a simple cost analysis to assist hospitalists in implementing helpful and cost-effective post-discharge interventions.

Predicting all-cause risk of 30-day hospital readmission using artificial neural networks

PubMed Central

2017-01-01

Avoidable hospital readmissions not only contribute to the high costs of healthcare in the US, but also have an impact on the quality of care for patients. Large scale adoption of Electronic Health Records (EHR) has created the opportunity to proactively identify patients with high risk of hospital readmission, and apply effective interventions to mitigate that risk. To that end, in the past, numerous machine-learning models have been employed to predict the risk of 30-day hospital readmission. However, the need for an accurate and real-time predictive model, suitable for hospital setting applications still exists. Here, using data from more than 300,000 hospital stays in California from Sutter Health’s EHR system, we built and tested an artificial neural network (NN) model based on Google’s TensorFlow library. Through comparison with other traditional and non-traditional models, we demonstrated that neural networks are great candidates to capture the complexity and interdependency of various data fields in EHRs. LACE, the current industry standard, showed a precision (PPV) of 0.20 in identifying high-risk patients in our database. In contrast, our NN model yielded a PPV of 0.24, which is a 20% improvement over LACE. Additionally, we discussed the predictive power of Social Determinants of Health (SDoH) data, and presented a simple cost analysis to assist hospitalists in implementing helpful and cost-effective post-discharge interventions. PMID:28708848

A Naive Bayes machine learning approach to risk prediction using censored, time-to-event data.

PubMed

Wolfson, Julian; Bandyopadhyay, Sunayan; Elidrisi, Mohamed; Vazquez-Benitez, Gabriela; Vock, David M; Musgrove, Donald; Adomavicius, Gediminas; Johnson, Paul E; O'Connor, Patrick J

2015-09-20

Predicting an individual's risk of experiencing a future clinical outcome is a statistical task with important consequences for both practicing clinicians and public health experts. Modern observational databases such as electronic health records provide an alternative to the longitudinal cohort studies traditionally used to construct risk models, bringing with them both opportunities and challenges. Large sample sizes and detailed covariate histories enable the use of sophisticated machine learning techniques to uncover complex associations and interactions, but observational databases are often 'messy', with high levels of missing data and incomplete patient follow-up. In this paper, we propose an adaptation of the well-known Naive Bayes machine learning approach to time-to-event outcomes subject to censoring. We compare the predictive performance of our method with the Cox proportional hazards model which is commonly used for risk prediction in healthcare populations, and illustrate its application to prediction of cardiovascular risk using an electronic health record dataset from a large Midwest integrated healthcare system. Copyright © 2015 John Wiley & Sons, Ltd.

Predicting Readmission at Early Hospitalization Using Electronic Clinical Data: An Early Readmission Risk Score.

PubMed

Tabak, Ying P; Sun, Xiaowu; Nunez, Carlos M; Gupta, Vikas; Johannes, Richard S

2017-03-01

Identifying patients at high risk for readmission early during hospitalization may aid efforts in reducing readmissions. We sought to develop an early readmission risk predictive model using automated clinical data available at hospital admission. We developed an early readmission risk model using a derivation cohort and validated the model with a validation cohort. We used a published Acute Laboratory Risk of Mortality Score as an aggregated measure of clinical severity at admission and the number of hospital discharges in the previous 90 days as a measure of disease progression. We then evaluated the administrative data-enhanced model by adding principal and secondary diagnoses and other variables. We examined the c-statistic change when additional variables were added to the model. There were 1,195,640 adult discharges from 70 hospitals with 39.8% male and the median age of 63 years (first and third quartile: 43, 78). The 30-day readmission rate was 11.9% (n=142,211). The early readmission model yielded a graded relationship of readmission and the Acute Laboratory Risk of Mortality Score and the number of previous discharges within 90 days. The model c-statistic was 0.697 with good calibration. When administrative variables were added to the model, the c-statistic increased to 0.722. Automated clinical data can generate a readmission risk score early at hospitalization with fair discrimination. It may have applied value to aid early care transition. Adding administrative data increases predictive accuracy. The administrative data-enhanced model may be used for hospital comparison and outcome research.

Prediction of morbidity and mortality in patients with type 2 diabetes.

PubMed

Wells, Brian J; Roth, Rachel; Nowacki, Amy S; Arrigain, Susana; Yu, Changhong; Rosenkrans, Wayne A; Kattan, Michael W

2013-01-01

Introduction. The objective of this study was to create a tool that accurately predicts the risk of morbidity and mortality in patients with type 2 diabetes according to an oral hypoglycemic agent. Materials and Methods. The model was based on a cohort of 33,067 patients with type 2 diabetes who were prescribed a single oral hypoglycemic agent at the Cleveland Clinic between 1998 and 2006. Competing risk regression models were created for coronary heart disease (CHD), heart failure, and stroke, while a Cox regression model was created for mortality. Propensity scores were used to account for possible treatment bias. A prediction tool was created and internally validated using tenfold cross-validation. The results were compared to a Framingham model and a model based on the United Kingdom Prospective Diabetes Study (UKPDS) for CHD and stroke, respectively. Results and Discussion. Median follow-up for the mortality outcome was 769 days. The numbers of patients experiencing events were as follows: CHD (3062), heart failure (1408), stroke (1451), and mortality (3661). The prediction tools demonstrated the following concordance indices (c-statistics) for the specific outcomes: CHD (0.730), heart failure (0.753), stroke (0.688), and mortality (0.719). The prediction tool was superior to the Framingham model at predicting CHD and was at least as accurate as the UKPDS model at predicting stroke. Conclusions. We created an accurate tool for predicting the risk of stroke, coronary heart disease, heart failure, and death in patients with type 2 diabetes. The calculator is available online at http://rcalc.ccf.org under the heading "Type 2 Diabetes" and entitled, "Predicting 5-Year Morbidity and Mortality." This may be a valuable tool to aid the clinician's choice of an oral hypoglycemic, to better inform patients, and to motivate dialogue between physician and patient.

Dependence regulation in newlywed couples: A prospective examination.

PubMed

Derrick, Jaye L; Leonard, Kenneth E; Homish, Gregory G

2012-12-01

According to the Risk Regulation Model (Murray, S. L., Holmes, J. G., & Collins, N. L. (2006). Optimizing assurance: The risk regulation system in relationships. Psychological Bulletin, 132 , 641-666), people need to trust in their partner's regard before they risk interdependence. The current study prospectively examines the association between perceived regard and levels of dependence in newlywed couples over nine years of marriage. Analyses demonstrate that changes in perceived regard predict levels of dependence, changes in dependence do not predict perceived regard, and alternative explanations cannot account for these effects. Further, changes in perceived regard prospectively predict divorce, and levels of dependence mediate this association. Results are discussed in terms of the dependence regulation component of the Risk Regulation Model.

Predicting the Risk of Breakthrough Urinary Tract Infections: Primary Vesicoureteral Reflux.

PubMed

Hidas, Guy; Billimek, John; Nam, Alexander; Soltani, Tandis; Kelly, Maryellen S; Selby, Blake; Dorgalli, Crystal; Wehbi, Elias; McAleer, Irene; McLorie, Gordon; Greenfield, Sheldon; Kaplan, Sherrie H; Khoury, Antoine E

2015-11-01

We constructed a risk prediction instrument stratifying patients with primary vesicoureteral reflux into groups according to their 2-year probability of breakthrough urinary tract infection. Demographic and clinical information was retrospectively collected in children diagnosed with primary vesicoureteral reflux and followed for 2 years. Bivariate and binary logistic regression analyses were performed to identify factors associated with breakthrough urinary tract infection. The final regression model was used to compute an estimation of the 2-year probability of breakthrough urinary tract infection for each subject. Accuracy of the binary classifier for breakthrough urinary tract infection was evaluated using receiver operator curve analysis. Three distinct risk groups were identified. The model was then validated in a prospective cohort. A total of 252 bivariate analyses showed that high grade (IV or V) vesicoureteral reflux (OR 9.4, 95% CI 3.8-23.5, p <0.001), presentation after urinary tract infection (OR 5.3, 95% CI 1.1-24.7, p = 0.034) and female gender (OR 2.6, 95% CI 0.097-7.11, p <0.054) were important risk factors for breakthrough urinary tract infection. Subgroup analysis revealed bladder and bowel dysfunction was a significant risk factor more pronounced in low grade (I to III) vesicoureteral reflux (OR 2.8, p = 0.018). The estimation model was applied for prospective validation, which demonstrated predicted vs actual 2-year breakthrough urinary tract infection rates of 19% vs 21%. Stratifying the patients into 3 risk groups based on parameters in the risk model showed 2-year risk for breakthrough urinary tract infection was 8.6%, 26.0% and 62.5% in the low, intermediate and high risk groups, respectively. This proposed risk stratification and probability model allows prediction of 2-year risk of patient breakthrough urinary tract infection to better inform parents of possible outcomes and treatment strategies. Copyright © 2015 American Urological Association Education and Research, Inc. Published by Elsevier Inc. All rights reserved.

Prediction of skull fracture risk for children 0-9 months old through validated parametric finite element model and cadaver test reconstruction.

PubMed

Li, Zhigang; Liu, Weiguo; Zhang, Jinhuan; Hu, Jingwen

2015-09-01

Skull fracture is one of the most common pediatric traumas. However, injury assessment tools for predicting pediatric skull fracture risk is not well established mainly due to the lack of cadaver tests. Weber conducted 50 pediatric cadaver drop tests for forensic research on child abuse in the mid-1980s (Experimental studies of skull fractures in infants, Z Rechtsmed. 92: 87-94, 1984; Biomechanical fragility of the infant skull, Z Rechtsmed. 94: 93-101, 1985). To our knowledge, these studies contained the largest sample size among pediatric cadaver tests in the literature. However, the lack of injury measurements limited their direct application in investigating pediatric skull fracture risks. In this study, 50 pediatric cadaver tests from Weber's studies were reconstructed using a parametric pediatric head finite element (FE) model which were morphed into subjects with ages, head sizes/shapes, and skull thickness values that reported in the tests. The skull fracture risk curves for infants from 0 to 9 months old were developed based on the model-predicted head injury measures through logistic regression analysis. It was found that the model-predicted stress responses in the skull (maximal von Mises stress, maximal shear stress, and maximal first principal stress) were better predictors than global kinematic-based injury measures (peak head acceleration and head injury criterion (HIC)) in predicting pediatric skull fracture. This study demonstrated the feasibility of using age- and size/shape-appropriate head FE models to predict pediatric head injuries. Such models can account for the morphological variations among the subjects, which cannot be considered by a single FE human model.

Countervailing social network influences on problem behaviors among homeless youth.

PubMed

Rice, Eric; Stein, Judith A; Milburn, Norweeta

2008-10-01

The impact of countervailing social network influences (i.e., pro-social, anti-social or HIV risk peers) on problem behaviors (i.e., HIV drug risk, HIV sex risk or anti-social behaviors) among 696 homeless youth was assessed using structural equation modeling. Results revealed that older youth were less likely to report having pro-social peers and were more likely to have HIV risk and anti-social peers. A longer time homeless predicted fewer pro-social peers, more anti-social peers, and more HIV risk peers. Heterosexual youth reported fewer HIV risk peers and more pro-social peers. Youth recruited at agencies were more likely to report pro-social peers. Having pro-social peers predicted less HIV sex risk behavior and less anti-social behavior. Having HIV risk peers predicted all problem behavior outcomes. Anti-social peers predicted more anti-social behavior. Once the association between anti-social and HIV risk peers was accounted for independently, having anti-social peers did not independently predict sex or drug risk behaviors.

Development of a flood-induced health risk prediction model for Africa

NASA Astrophysics Data System (ADS)

Lee, D.; Block, P. J.

2017-12-01

Globally, many floods occur in developing or tropical regions where the impact on public health is substantial, including death and injury, drinking water, endemic disease, and so on. Although these flood impacts on public health have been investigated, integrated management of floods and flood-induced health risks is technically and institutionally limited. Specifically, while the use of climatic and hydrologic forecasts for disaster management has been highlighted, analogous predictions for forecasting the magnitude and impact of health risks are lacking, as is the infrastructure for health early warning systems, particularly in developing countries. In this study, we develop flood-induced health risk prediction model for African regions using season-ahead flood predictions with climate drivers and a variety of physical and socio-economic information, such as local hazard, exposure, resilience, and health vulnerability indicators. Skillful prediction of flood and flood-induced health risks can contribute to practical pre- and post-disaster responses in both local- and global-scales, and may eventually be integrated into multi-hazard early warning systems for informed advanced planning and management. This is especially attractive for areas with limited observations and/or little capacity to develop flood-induced health risk warning systems.

Cancer survival analysis using semi-supervised learning method based on Cox and AFT models with L1/2 regularization.

PubMed

Liang, Yong; Chai, Hua; Liu, Xiao-Ying; Xu, Zong-Ben; Zhang, Hai; Leung, Kwong-Sak

2016-03-01

One of the most important objectives of the clinical cancer research is to diagnose cancer more accurately based on the patients' gene expression profiles. Both Cox proportional hazards model (Cox) and accelerated failure time model (AFT) have been widely adopted to the high risk and low risk classification or survival time prediction for the patients' clinical treatment. Nevertheless, two main dilemmas limit the accuracy of these prediction methods. One is that the small sample size and censored data remain a bottleneck for training robust and accurate Cox classification model. In addition to that, similar phenotype tumours and prognoses are actually completely different diseases at the genotype and molecular level. Thus, the utility of the AFT model for the survival time prediction is limited when such biological differences of the diseases have not been previously identified. To try to overcome these two main dilemmas, we proposed a novel semi-supervised learning method based on the Cox and AFT models to accurately predict the treatment risk and the survival time of the patients. Moreover, we adopted the efficient L1/2 regularization approach in the semi-supervised learning method to select the relevant genes, which are significantly associated with the disease. The results of the simulation experiments show that the semi-supervised learning model can significant improve the predictive performance of Cox and AFT models in survival analysis. The proposed procedures have been successfully applied to four real microarray gene expression and artificial evaluation datasets. The advantages of our proposed semi-supervised learning method include: 1) significantly increase the available training samples from censored data; 2) high capability for identifying the survival risk classes of patient in Cox model; 3) high predictive accuracy for patients' survival time in AFT model; 4) strong capability of the relevant biomarker selection. Consequently, our proposed semi-supervised learning model is one more appropriate tool for survival analysis in clinical cancer research.

Supervised Risk Predictor of Breast Cancer Based on Intrinsic Subtypes

PubMed Central

Parker, Joel S.; Mullins, Michael; Cheang, Maggie C.U.; Leung, Samuel; Voduc, David; Vickery, Tammi; Davies, Sherri; Fauron, Christiane; He, Xiaping; Hu, Zhiyuan; Quackenbush, John F.; Stijleman, Inge J.; Palazzo, Juan; Marron, J.S.; Nobel, Andrew B.; Mardis, Elaine; Nielsen, Torsten O.; Ellis, Matthew J.; Perou, Charles M.; Bernard, Philip S.

2009-01-01

Purpose To improve on current standards for breast cancer prognosis and prediction of chemotherapy benefit by developing a risk model that incorporates the gene expression–based “intrinsic” subtypes luminal A, luminal B, HER2-enriched, and basal-like. Methods A 50-gene subtype predictor was developed using microarray and quantitative reverse transcriptase polymerase chain reaction data from 189 prototype samples. Test sets from 761 patients (no systemic therapy) were evaluated for prognosis, and 133 patients were evaluated for prediction of pathologic complete response (pCR) to a taxane and anthracycline regimen. Results The intrinsic subtypes as discrete entities showed prognostic significance (P = 2.26E-12) and remained significant in multivariable analyses that incorporated standard parameters (estrogen receptor status, histologic grade, tumor size, and node status). A prognostic model for node-negative breast cancer was built using intrinsic subtype and clinical information. The C-index estimate for the combined model (subtype and tumor size) was a significant improvement on either the clinicopathologic model or subtype model alone. The intrinsic subtype model predicted neoadjuvant chemotherapy efficacy with a negative predictive value for pCR of 97%. Conclusion Diagnosis by intrinsic subtype adds significant prognostic and predictive information to standard parameters for patients with breast cancer. The prognostic properties of the continuous risk score will be of value for the management of node-negative breast cancers. The subtypes and risk score can also be used to assess the likelihood of efficacy from neoadjuvant chemotherapy. PMID:19204204

Failure of Colorectal Surgical Site Infection Predictive Models Applied to an Independent Dataset: Do They Add Value or Just Confusion?

PubMed

Bergquist, John R; Thiels, Cornelius A; Etzioni, David A; Habermann, Elizabeth B; Cima, Robert R

2016-04-01

Colorectal surgical site infections (C-SSIs) are a major source of postoperative morbidity. Institutional C-SSI rates are modeled and scrutinized, and there is increasing movement in the direction of public reporting. External validation of C-SSI risk prediction models is lacking. Factors governing C-SSI occurrence are complicated and multifactorial. We hypothesized that existing C-SSI prediction models have limited ability to accurately predict C-SSI in independent data. Colorectal resections identified from our institutional ACS-NSQIP dataset (2006 to 2014) were reviewed. The primary outcome was any C-SSI according to the ACS-NSQIP definition. Emergency cases were excluded. Published C-SSI risk scores: the National Nosocomial Infection Surveillance (NNIS), Contamination, Obesity, Laparotomy, and American Society of Anesthesiologists (ASA) class (COLA), Preventie Ziekenhuisinfecties door Surveillance (PREZIES), and NSQIP-based models were compared with receiver operating characteristic (ROC) analysis to evaluate discriminatory quality. There were 2,376 cases included, with an overall C-SSI rate of 9% (213 cases). None of the models produced reliable and high quality C-SSI predictions. For any C-SSI, the NNIS c-index was 0.57 vs 0.61 for COLA, 0.58 for PREZIES, and 0.62 for NSQIP: all well below the minimum "reasonably" predictive c-index of 0.7. Predictions for superficial, deep, and organ space SSI were similarly poor. Published C-SSI risk prediction models do not accurately predict C-SSI in our independent institutional dataset. Application of externally developed prediction models to any individual practice must be validated or modified to account for institution and case-mix specific factors. This questions the validity of using externally or nationally developed models for "expected" outcomes and interhospital comparisons. Copyright © 2016 American College of Surgeons. Published by Elsevier Inc. All rights reserved.

Prediction of Incident Hypertension Within the Next Year: Prospective Study Using Statewide Electronic Health Records and Machine Learning

PubMed Central

Zhang, Yan; Wang, Oliver; Jin, Bo; Xia, Minjie; Liu, Modi; Zhou, Xin; Wu, Qian; Guo, Yanting; Zhu, Chunqing; Li, Yu-Ming; Culver, Devore S; Alfreds, Shaun T; Stearns, Frank; Sylvester, Karl G; Widen, Eric

2018-01-01

Background As a high-prevalence health condition, hypertension is clinically costly, difficult to manage, and often leads to severe and life-threatening diseases such as cardiovascular disease (CVD) and stroke. Objective The aim of this study was to develop and validate prospectively a risk prediction model of incident essential hypertension within the following year. Methods Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. Retrospective (N=823,627, calendar year 2013) and prospective (N=680,810, calendar year 2014) cohorts were formed. A machine learning algorithm, XGBoost, was adopted in the process of feature selection and model building. It generated an ensemble of classification trees and assigned a final predictive risk score to each individual. Results The 1-year incident hypertension risk model attained areas under the curve (AUCs) of 0.917 and 0.870 in the retrospective and prospective cohorts, respectively. Risk scores were calculated and stratified into five risk categories, with 4526 out of 381,544 patients (1.19%) in the lowest risk category (score 0-0.05) and 21,050 out of 41,329 patients (50.93%) in the highest risk category (score 0.4-1) receiving a diagnosis of incident hypertension in the following 1 year. Type 2 diabetes, lipid disorders, CVDs, mental illness, clinical utilization indicators, and socioeconomic determinants were recognized as driving or associated features of incident essential hypertension. The very high risk population mainly comprised elderly (age>50 years) individuals with multiple chronic conditions, especially those receiving medications for mental disorders. Disparities were also found in social determinants, including some community-level factors associated with higher risk and others that were protective against hypertension. Conclusions With statewide EHR datasets, our study prospectively validated an accurate 1-year risk prediction model for incident essential hypertension. Our real-time predictive analytic model has been deployed in the state of Maine, providing implications in interventions for hypertension and related diseases and hopefully enhancing hypertension care. PMID:29382633

Predicting Substance Use in Emerging Adulthood: A Genetically Informed Study of Developmental Transactions between Impulsivity and Family Conflict

PubMed Central

Elam, Kit K.; Wang, Frances L.; Bountress, Kaitlin; Chassin, Laurie; Pandika, Danielle; Lemery-Chalfant, Kathryn

2016-01-01

Deviance proneness models propose a multi-level interplay in which transactions among genetic, individual, and family risk factors place children at increased risk for substance use. We examined bidirectional transactions between impulsivity and family conflict from middle childhood to adolescence and their contributions to substance use in adolescence and emerging adulthood (n = 380). Moreover, we examined children’s, mothers’ and fathers’ polygenic risk scores for behavioral undercontrol, and mothers’ and fathers’ interparental conflict and substance disorder diagnoses as predictors of these transactions. Results support a developmental cascade model in which children’s polygenic risk scores predicted greater impulsivity in middle childhood. Impulsivity in middle childhood predicted greater family conflict in late childhood, which in turn predicted greater impulsivity in late adolescence. Adolescent impulsivity subsequently predicted greater substance use in emerging adulthood. Results are discussed with respect to evocative genotype-environment correlations within developmental cascades and applications to prevention efforts. PMID:27427799

A MELD-based model to determine risk of mortality among patients with acute variceal bleeding.

PubMed

Reverter, Enric; Tandon, Puneeta; Augustin, Salvador; Turon, Fanny; Casu, Stefania; Bastiampillai, Ravin; Keough, Adam; Llop, Elba; González, Antonio; Seijo, Susana; Berzigotti, Annalisa; Ma, Mang; Genescà, Joan; Bosch, Jaume; García-Pagán, Joan Carles; Abraldes, Juan G

2014-02-01

Patients with cirrhosis with acute variceal bleeding (AVB) have high mortality rates (15%-20%). Previously described models are seldom used to determine prognoses of these patients, partially because they have not been validated externally and because they include subjective variables, such as bleeding during endoscopy and Child-Pugh score, which are evaluated inconsistently. We aimed to improve determination of risk for patients with AVB. We analyzed data collected from 178 patients with cirrhosis (Child-Pugh scores of A, B, and C: 15%, 57%, and 28%, respectively) and esophageal AVB who received standard therapy from 2007 through 2010. We tested the performance (discrimination and calibration) of previously described models, including the model for end-stage liver disease (MELD), and developed a new MELD calibration to predict the mortality of patients within 6 weeks of presentation with AVB. MELD-based predictions were validated in cohorts of patients from Canada (n = 240) and Spain (n = 221). Among study subjects, the 6-week mortality rate was 16%. MELD was the best model in terms of discrimination; it was recalibrated to predict the 6-week mortality rate with logistic regression (logit, -5.312 + 0.207 • MELD; bootstrapped R(2), 0.3295). MELD values of 19 or greater predicted 20% or greater mortality, whereas MELD scores less than 11 predicted less than 5% mortality. The model performed well for patients from Canada at all risk levels. In the Spanish validation set, in which all patients were treated with banding ligation, MELD predictions were accurate up to the 20% risk threshold. We developed a MELD-based model that accurately predicts mortality among patients with AVB, based on objective variables available at admission. This model could be useful to evaluate the efficacy of new therapies and stratify patients in randomized trials. Copyright © 2014 AGA Institute. Published by Elsevier Inc. All rights reserved.

A Novel Model for Predicting Rehospitalization Risk Incorporating Physical Function, Cognitive Status, and Psychosocial Support Using Natural Language Processing.

PubMed

Greenwald, Jeffrey L; Cronin, Patrick R; Carballo, Victoria; Danaei, Goodarz; Choy, Garry

2017-03-01

With the increasing focus on reducing hospital readmissions in the United States, numerous readmissions risk prediction models have been proposed, mostly developed through analyses of structured data fields in electronic medical records and administrative databases. Three areas that may have an impact on readmission but are poorly captured using structured data sources are patients' physical function, cognitive status, and psychosocial environment and support. The objective of the study was to build a discriminative model using information germane to these 3 areas to identify hospitalized patients' risk for 30-day all cause readmissions. We conducted clinician focus groups to identify language used in the clinical record regarding these 3 areas. We then created a dataset including 30,000 inpatients, 10,000 from each of 3 hospitals, and searched those records for the focus group-derived language using natural language processing. A 30-day readmission prediction model was developed on 75% of the dataset and validated on the other 25% and also on hospital specific subsets. Focus group language was aggregated into 35 variables. The final model had 16 variables, a validated C-statistic of 0.74, and was well calibrated. Subset validation of the model by hospital yielded C-statistics of 0.70-0.75. Deriving a 30-day readmission risk prediction model through identification of physical, cognitive, and psychosocial issues using natural language processing yielded a model that performs similarly to the better performing models previously published with the added advantage of being based on clinically relevant factors and also automated and scalable. Because of the clinical relevance of the variables in the model, future research may be able to test if targeting interventions to identified risks results in reductions in readmissions.

Climate Change Could Increase the Geographic Extent of Hendra Virus Spillover Risk.

PubMed

Martin, Gerardo; Yanez-Arenas, Carlos; Chen, Carla; Plowright, Raina K; Webb, Rebecca J; Skerratt, Lee F

2018-03-19

Disease risk mapping is important for predicting and mitigating impacts of bat-borne viruses, including Hendra virus (Paramyxoviridae:Henipavirus), that can spillover to domestic animals and thence to humans. We produced two models to estimate areas at potential risk of HeV spillover explained by the climatic suitability for its flying fox reservoir hosts, Pteropus alecto and P. conspicillatus. We included additional climatic variables that might affect spillover risk through other biological processes (such as bat or horse behaviour, plant phenology and bat foraging habitat). Models were fit with a Poisson point process model and a log-Gaussian Cox process. In response to climate change, risk expanded southwards due to an expansion of P. alecto suitable habitat, which increased the number of horses at risk by 175-260% (110,000-165,000). In the northern limits of the current distribution, spillover risk was highly uncertain because of model extrapolation to novel climatic conditions. The extent of areas at risk of spillover from P. conspicillatus was predicted shrink. Due to a likely expansion of P. alecto into these areas, it could replace P. conspicillatus as the main HeV reservoir. We recommend: (1) HeV monitoring in bats, (2) enhancing HeV prevention in horses in areas predicted to be at risk, (3) investigate and develop mitigation strategies for areas that could experience reservoir host replacements.

Lung cancer in never smokers Epidemiology and risk prediction models

PubMed Central

McCarthy, William J.; Meza, Rafael; Jeon, Jihyoun; Moolgavkar, Suresh

2012-01-01

In this chapter we review the epidemiology of lung cancer incidence and mortality among never smokers/ nonsmokers and describe the never smoker lung cancer risk models used by CISNET modelers. Our review focuses on those influences likely to have measurable population impact on never smoker risk, such as secondhand smoke, even though the individual-level impact may be small. Occupational exposures may also contribute importantly to the population attributable risk of lung cancer. We examine the following risk factors in this chapter: age, environmental tobacco smoke, cooking fumes, ionizing radiation including radon gas, inherited genetic susceptibility, selected occupational exposures, preexisting lung disease, and oncogenic viruses. We also compare the prevalence of never smokers between the three CISNET smoking scenarios and present the corresponding lung cancer mortality estimates among never smokers as predicted by a typical CISNET model. PMID:22882894

Validity of cardiovascular risk prediction models in Latin America and among Hispanics in the United States of America: a systematic review.

PubMed

Cortes-Bergoderi, Mery; Thomas, Randal J; Albuquerque, Felipe N; Batsis, John A; Burdiat, Gerard; Perez-Terzic, Carmen; Trejo-Gutierrez, Jorge; Lopez-Jimenez, Francisco

2012-08-01

To assess the use and validity of prediction models to estimate the risk of cardiovascular disease (CVD) in Latin America and among Hispanic populations in the United States of America. This was a systematic review of three databases: Ovid MEDLINE (1 January 1950-15 April 2010), LILACS (1 January 1988-15 April 2010), and EMBASE (1 January 1988-15 April 2010). MeSH search terms and domains were related to CVD, prediction rules, Latin America (including the Caribbean), and Hispanics in the United States. Database searches were supplemented by correspondence with experts in the field. A total of 1 655 abstracts were identified, of which five cohorts with a total of 13 142 subjects met inclusion criteria. A Mexican cohort showed that the predicted/observed event-rate ratio for coronary heart disease (CHD) according to the Framingham risk score (FRS) was 1.68 (95% CI, 1.26-2.11); incident myocardial infarction, 1.36 (95% CI, 0.90-1.83); and CHD death, 1.21 (95% CI, 0.43-2.00). In Ecuador, a prediction model for CVD and total deaths in hypertensive patients had an area under the curve (AUC) of 0.79 (95% CI, 0.72-0.86), while the World Health Organization method had an AUC of 0.74 (95% CI, 0.67-0.82). A study predicting mortality risk in people with Chagas' disease had an AUC of 0.81 (95% CI, 0.72-0.90). Among a United State s cohort that included Hispanics, FRS overestimated CVD risk for Hispanics with an AUC of 0.69. Another study in the United States that assessed FRS factors predicting CVD death among Mexican-Americans had an AUC of 0.78. The evidence regarding CVD risk prediction rules in Latin America or among Hispanics in the United States is modest at best. It is likely that the FRS overestimates CVD risk in Hispanics when not properly recalibrated.

Prognostic and Prediction Tools in Bladder Cancer: A Comprehensive Review of the Literature.

PubMed

Kluth, Luis A; Black, Peter C; Bochner, Bernard H; Catto, James; Lerner, Seth P; Stenzl, Arnulf; Sylvester, Richard; Vickers, Andrew J; Xylinas, Evanguelos; Shariat, Shahrokh F

2015-08-01

This review focuses on risk assessment and prediction tools for bladder cancer (BCa). To review the current knowledge on risk assessment and prediction tools to enhance clinical decision making and counseling of patients with BCa. A literature search in English was performed using PubMed in July 2013. Relevant risk assessment and prediction tools for BCa were selected. More than 1600 publications were retrieved. Special attention was given to studies that investigated the clinical benefit of a prediction tool. Most prediction tools for BCa focus on the prediction of disease recurrence and progression in non-muscle-invasive bladder cancer or disease recurrence and survival after radical cystectomy. Although these tools are helpful, recent prediction tools aim to address a specific clinical problem, such as the prediction of organ-confined disease and lymph node metastasis to help identify patients who might benefit from neoadjuvant chemotherapy. Although a large number of prediction tools have been reported in recent years, many of them lack external validation. Few studies have investigated the clinical utility of any given model as measured by its ability to improve clinical decision making. There is a need for novel biomarkers to improve the accuracy and utility of prediction tools for BCa. Decision tools hold the promise of facilitating the shared decision process, potentially improving clinical outcomes for BCa patients. Prediction models need external validation and assessment of clinical utility before they can be incorporated into routine clinical care. We looked at models that aim to predict outcomes for patients with bladder cancer (BCa). We found a large number of prediction models that hold the promise of facilitating treatment decisions for patients with BCa. However, many models are missing confirmation in a different patient cohort, and only a few studies have tested the clinical utility of any given model as measured by its ability to improve clinical decision making. Copyright © 2015 European Association of Urology. Published by Elsevier B.V. All rights reserved.

Performance of Comorbidity, Risk Adjustment, and Functional Status Measures in Expenditure Prediction for Patients With Diabetes

PubMed Central

Maciejewski, Matthew L.; Liu, Chuan-Fen; Fihn, Stephan D.

2009-01-01

OBJECTIVE—To compare the ability of generic comorbidity and risk adjustment measures, a diabetes-specific measure, and a self-reported functional status measure to explain variation in health care expenditures for individuals with diabetes. RESEARCH DESIGN AND METHODS—This study included a retrospective cohort of 3,092 diabetic veterans participating in a multisite trial. Two comorbidity measures, four risk adjusters, a functional status measure, a diabetes complication count, and baseline expenditures were constructed from administrative and survey data. Outpatient, inpatient, and total expenditure models were estimated using ordinary least squares regression. Adjusted R2 statistics and predictive ratios were compared across measures to assess overall explanatory power and explanatory power of low- and high-cost subgroups. RESULTS—Administrative data–based risk adjusters performed better than the comorbidity, functional status, and diabetes-specific measures in all expenditure models. The diagnostic cost groups (DCGs) measure had the greatest predictive power overall and for the low- and high-cost subgroups, while the diabetes-specific measure had the lowest predictive power. A model with DCGs and the diabetes-specific measure modestly improved predictive power. CONCLUSIONS—Existing generic measures can be useful for diabetes-specific research and policy applications, but more predictive diabetes-specific measures are needed. PMID:18945927

Uncertainty and Variability in Physiologically-Based ...

EPA Pesticide Factsheets

EPA announced the availability of the final report, Uncertainty and Variability in Physiologically-Based Pharmacokinetic (PBPK) Models: Key Issues and Case Studies. This report summarizes some of the recent progress in characterizing uncertainty and variability in physiologically-based pharmacokinetic models and their predictions for use in risk assessment. This report summarizes some of the recent progress in characterizing uncertainty and variability in physiologically-based pharmacokinetic models and their predictions for use in risk assessment.

Using Computational Approaches to Improve Risk-Stratified Patient Management: Rationale and Methods

PubMed Central

Stone, Bryan L; Sakaguchi, Farrant; Sheng, Xiaoming; Murtaugh, Maureen A

2015-01-01

Background Chronic diseases affect 52% of Americans and consume 86% of health care costs. A small portion of patients consume most health care resources and costs. More intensive patient management strategies, such as case management, are usually more effective at improving health outcomes, but are also more expensive. To use limited resources efficiently, risk stratification is commonly used in managing patients with chronic diseases, such as asthma, chronic obstructive pulmonary disease, diabetes, and heart disease. Patients are stratified based on predicted risk with patients at higher risk given more intensive care. The current risk-stratified patient management approach has 3 limitations resulting in many patients not receiving the most appropriate care, unnecessarily increased costs, and suboptimal health outcomes. First, using predictive models for health outcomes and costs is currently the best method for forecasting individual patient’s risk. Yet, accuracy of predictive models remains poor causing many patients to be misstratified. If an existing model were used to identify candidate patients for case management, enrollment would miss more than half of those who would benefit most, but include others unlikely to benefit, wasting limited resources. Existing models have been developed under the assumption that patient characteristics primarily influence outcomes and costs, leaving physician characteristics out of the models. In reality, both characteristics have an impact. Second, existing models usually give neither an explanation why a particular patient is predicted to be at high risk nor suggestions on interventions tailored to the patient’s specific case. As a result, many high-risk patients miss some suitable interventions. Third, thresholds for risk strata are suboptimal and determined heuristically with no quality guarantee. Objective The purpose of this study is to improve risk-stratified patient management so that more patients will receive the most appropriate care. Methods This study will (1) combine patient, physician profile, and environmental variable features to improve prediction accuracy of individual patient health outcomes and costs; (2) develop the first algorithm to explain prediction results and suggest tailored interventions; (3) develop the first algorithm to compute optimal thresholds for risk strata; and (4) conduct simulations to estimate outcomes of risk-stratified patient management for various configurations. The proposed techniques will be demonstrated on a test case of asthma patients. Results We are currently in the process of extracting clinical and administrative data from an integrated health care system’s enterprise data warehouse. We plan to complete this study in approximately 5 years. Conclusions Methods developed in this study will help transform risk-stratified patient management for better clinical outcomes, higher patient satisfaction and quality of life, reduced health care use, and lower costs. PMID:26503357

Online Prediction of Health Care Utilization in the Next Six Months Based on Electronic Health Record Information: A Cohort and Validation Study.

PubMed

Hu, Zhongkai; Hao, Shiying; Jin, Bo; Shin, Andrew Young; Zhu, Chunqing; Huang, Min; Wang, Yue; Zheng, Le; Dai, Dorothy; Culver, Devore S; Alfreds, Shaun T; Rogow, Todd; Stearns, Frank; Sylvester, Karl G; Widen, Eric; Ling, Xuefeng

2015-09-22

The increasing rate of health care expenditures in the United States has placed a significant burden on the nation's economy. Predicting future health care utilization of patients can provide useful information to better understand and manage overall health care deliveries and clinical resource allocation. This study developed an electronic medical record (EMR)-based online risk model predictive of resource utilization for patients in Maine in the next 6 months across all payers, all diseases, and all demographic groups. In the HealthInfoNet, Maine's health information exchange (HIE), a retrospective cohort of 1,273,114 patients was constructed with the preceding 12-month EMR. Each patient's next 6-month (between January 1, 2013 and June 30, 2013) health care resource utilization was retrospectively scored ranging from 0 to 100 and a decision tree-based predictive model was developed. Our model was later integrated in the Maine HIE population exploration system to allow a prospective validation analysis of 1,358,153 patients by forecasting their next 6-month risk of resource utilization between July 1, 2013 and December 31, 2013. Prospectively predicted risks, on either an individual level or a population (per 1000 patients) level, were consistent with the next 6-month resource utilization distributions and the clinical patterns at the population level. Results demonstrated the strong correlation between its care resource utilization and our risk scores, supporting the effectiveness of our model. With the online population risk monitoring enterprise dashboards, the effectiveness of the predictive algorithm has been validated by clinicians and caregivers in the State of Maine. The model and associated online applications were designed for tracking the evolving nature of total population risk, in a longitudinal manner, for health care resource utilization. It will enable more effective care management strategies driving improved patient outcomes.

Online Prediction of Health Care Utilization in the Next Six Months Based on Electronic Health Record Information: A Cohort and Validation Study

PubMed Central

Hu, Zhongkai; Hao, Shiying; Jin, Bo; Shin, Andrew Young; Zhu, Chunqing; Huang, Min; Wang, Yue; Zheng, Le; Dai, Dorothy; Culver, Devore S; Alfreds, Shaun T; Rogow, Todd; Stearns, Frank

2015-01-01

Background The increasing rate of health care expenditures in the United States has placed a significant burden on the nation’s economy. Predicting future health care utilization of patients can provide useful information to better understand and manage overall health care deliveries and clinical resource allocation. Objective This study developed an electronic medical record (EMR)-based online risk model predictive of resource utilization for patients in Maine in the next 6 months across all payers, all diseases, and all demographic groups. Methods In the HealthInfoNet, Maine’s health information exchange (HIE), a retrospective cohort of 1,273,114 patients was constructed with the preceding 12-month EMR. Each patient’s next 6-month (between January 1, 2013 and June 30, 2013) health care resource utilization was retrospectively scored ranging from 0 to 100 and a decision tree–based predictive model was developed. Our model was later integrated in the Maine HIE population exploration system to allow a prospective validation analysis of 1,358,153 patients by forecasting their next 6-month risk of resource utilization between July 1, 2013 and December 31, 2013. Results Prospectively predicted risks, on either an individual level or a population (per 1000 patients) level, were consistent with the next 6-month resource utilization distributions and the clinical patterns at the population level. Results demonstrated the strong correlation between its care resource utilization and our risk scores, supporting the effectiveness of our model. With the online population risk monitoring enterprise dashboards, the effectiveness of the predictive algorithm has been validated by clinicians and caregivers in the State of Maine. Conclusions The model and associated online applications were designed for tracking the evolving nature of total population risk, in a longitudinal manner, for health care resource utilization. It will enable more effective care management strategies driving improved patient outcomes. PMID:26395541

Scalar utility theory and proportional processing: what does it actually imply?

PubMed Central

Rosenström, Tom; Wiesner, Karoline; Houston, Alasdair I

2017-01-01

Scalar Utility Theory (SUT) is a model used to predict animal and human choice behaviour in the context of reward amount, delay to reward, and variability in these quantities (risk preferences). This article reviews and extends SUT, deriving novel predictions. We show that, contrary to what has been implied in the literature, (1) SUT can predict both risk averse and risk prone behaviour for both reward amounts and delays to reward depending on experimental parameters, (2) SUT implies violations of several concepts of rational behaviour (e.g. it violates strong stochastic transitivity and its equivalents, and leads to probability matching) and (3) SUT can predict, but does not always predict, a linear relationship between risk sensitivity in choices and coefficient of variation in the decision-making experiment. SUT derives from Scalar Expectancy Theory which models uncertainty in behavioural timing using a normal distribution. We show that the above conclusions also hold for other distributions, such as the inverse Gaussian distribution derived from drift-diffusion models. A straightforward way to test the key assumptions of SUT is suggested and possible extensions, future prospects and mechanistic underpinnings are discussed. PMID:27288541

Scalar utility theory and proportional processing: What does it actually imply?

PubMed

Rosenström, Tom; Wiesner, Karoline; Houston, Alasdair I

2016-09-07

Scalar Utility Theory (SUT) is a model used to predict animal and human choice behaviour in the context of reward amount, delay to reward, and variability in these quantities (risk preferences). This article reviews and extends SUT, deriving novel predictions. We show that, contrary to what has been implied in the literature, (1) SUT can predict both risk averse and risk prone behaviour for both reward amounts and delays to reward depending on experimental parameters, (2) SUT implies violations of several concepts of rational behaviour (e.g. it violates strong stochastic transitivity and its equivalents, and leads to probability matching) and (3) SUT can predict, but does not always predict, a linear relationship between risk sensitivity in choices and coefficient of variation in the decision-making experiment. SUT derives from Scalar Expectancy Theory which models uncertainty in behavioural timing using a normal distribution. We show that the above conclusions also hold for other distributions, such as the inverse Gaussian distribution derived from drift-diffusion models. A straightforward way to test the key assumptions of SUT is suggested and possible extensions, future prospects and mechanistic underpinnings are discussed. Copyright © 2016 Elsevier Ltd. All rights reserved.

Melanoma Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing melanoma cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Genetic markers enhance coronary risk prediction in men: the MORGAM prospective cohorts.

PubMed

Hughes, Maria F; Saarela, Olli; Stritzke, Jan; Kee, Frank; Silander, Kaisa; Klopp, Norman; Kontto, Jukka; Karvanen, Juha; Willenborg, Christina; Salomaa, Veikko; Virtamo, Jarmo; Amouyel, Phillippe; Arveiler, Dominique; Ferrières, Jean; Wiklund, Per-Gunner; Baumert, Jens; Thorand, Barbara; Diemert, Patrick; Trégouët, David-Alexandre; Hengstenberg, Christian; Peters, Annette; Evans, Alun; Koenig, Wolfgang; Erdmann, Jeanette; Samani, Nilesh J; Kuulasmaa, Kari; Schunkert, Heribert

2012-01-01

More accurate coronary heart disease (CHD) prediction, specifically in middle-aged men, is needed to reduce the burden of disease more effectively. We hypothesised that a multilocus genetic risk score could refine CHD prediction beyond classic risk scores and obtain more precise risk estimates using a prospective cohort design. Using data from nine prospective European cohorts, including 26,221 men, we selected in a case-cohort setting 4,818 healthy men at baseline, and used Cox proportional hazards models to examine associations between CHD and risk scores based on genetic variants representing 13 genomic regions. Over follow-up (range: 5-18 years), 1,736 incident CHD events occurred. Genetic risk scores were validated in men with at least 10 years of follow-up (632 cases, 1361 non-cases). Genetic risk score 1 (GRS1) combined 11 SNPs and two haplotypes, with effect estimates from previous genome-wide association studies. GRS2 combined 11 SNPs plus 4 SNPs from the haplotypes with coefficients estimated from these prospective cohorts using 10-fold cross-validation. Scores were added to a model adjusted for classic risk factors comprising the Framingham risk score and 10-year risks were derived. Both scores improved net reclassification (NRI) over the Framingham score (7.5%, p = 0.017 for GRS1, 6.5%, p = 0.044 for GRS2) but GRS2 also improved discrimination (c-index improvement 1.11%, p = 0.048). Subgroup analysis on men aged 50-59 (436 cases, 603 non-cases) improved net reclassification for GRS1 (13.8%) and GRS2 (12.5%). Net reclassification improvement remained significant for both scores when family history of CHD was added to the baseline model for this male subgroup improving prediction of early onset CHD events. Genetic risk scores add precision to risk estimates for CHD and improve prediction beyond classic risk factors, particularly for middle aged men.

The Theory of Planned Behavior as a Predictor of HIV Testing Intention.

PubMed

Ayodele, Olabode

2017-03-01

This investigation tests the theory of planned behavior (TPB) as a predictor of HIV testing intention among Nigerian university undergraduate students. A cross-sectional study of 392 students was conducted using a self-administered structured questionnaire that measured socio-demographics, perceived risk of human immunodeficiency virus (HIV) infection, and TPB constructs. Analysis was based on 273 students who had never been tested for HIV. Hierarchical multiple regression analysis assessed the applicability of the TPB in predicting HIV testing intention and additional predictive value of perceived risk of HIV infection. The prediction model containing TPB constructs explained 35% of the variance in HIV testing intention, with attitude and perceived behavioral control making significant and unique contributions to intention. Perceived risk of HIV infection contributed marginally (2%) but significantly to the final prediction model. Findings supported the TPB in predicting HIV testing intention. Although future studies must determine the generalizability of these results, the findings highlight the importance of perceived behavioral control, attitude, and perceived risk of HIV infection in the prediction of HIV testing intention among students who have not previously tested for HIV.

SU-E-T-628: Predicted Risk of Post-Irradiation Cerebral Necrosis in Pediatric Brain Cancer Patients: A Treatment Planning Comparison of Proton Vs. Photon Therapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Freund, D; Zhang, R; Sanders, M

Purpose: Post-irradiation cerebral necrosis (PICN) is a severe late effect that can Result from brain cancers treatment using radiation therapy. The purpose of this study was to compare the treatment plans and predicted risk of PICN after volumetric modulated arc therapy (VMAT) to the risk after passively scattered proton therapy (PSPT) and intensity modulated proton therapy (IMPT) in a cohort of pediatric patients. Methods: Thirteen pediatric patients with varying age and sex were selected for this study. A clinical treatment volume (CTV) was constructed for 8 glioma patients and 5 ependymoma patients. Prescribed dose was 54 Gy over 30 fractionsmore » to the planning volume. Dosimetric endpoints were compared between VMAT and proton plans. The normal tissue complication probability (NTCP) following VMAT and proton therapy planning was also calculated using PICN as the biological endpoint. Sensitivity tests were performed to determine if predicted risk of PICN was sensitive to positional errors, proton range errors and selection of risk models. Results: Both PSPT and IMPT plans resulted in a significant increase in the maximum dose and reduction in the total brain volume irradiated to low doses compared with the VMAT plans. The average ratios of NTCP between PSPT and VMAT were 0.56 and 0.38 for glioma and ependymoma patients respectively and the average ratios of NTCP between IMPT and VMAT were 0.67 and 0.68 for glioma and ependymoma plans respectively. Sensitivity test revealed that predicted ratios of risk were insensitive to range and positional errors but varied with risk model selection. Conclusion: Both PSPT and IMPT plans resulted in a decrease in the predictive risk of necrosis for the pediatric plans studied in this work. Sensitivity analysis upheld the qualitative findings of the risk models used in this study, however more accurate models that take into account dose and volume are needed.« less

Leptospirosis in American Samoa – Estimating and Mapping Risk Using Environmental Data

PubMed Central

Lau, Colleen L.; Clements, Archie C. A.; Skelly, Chris; Dobson, Annette J.; Smythe, Lee D.; Weinstein, Philip

2012-01-01

Background The recent emergence of leptospirosis has been linked to many environmental drivers of disease transmission. Accurate epidemiological data are lacking because of under-diagnosis, poor laboratory capacity, and inadequate surveillance. Predictive risk maps have been produced for many diseases to identify high-risk areas for infection and guide allocation of public health resources, and are particularly useful where disease surveillance is poor. To date, no predictive risk maps have been produced for leptospirosis. The objectives of this study were to estimate leptospirosis seroprevalence at geographic locations based on environmental factors, produce a predictive disease risk map for American Samoa, and assess the accuracy of the maps in predicting infection risk. Methodology and Principal Findings Data on seroprevalence and risk factors were obtained from a recent study of leptospirosis in American Samoa. Data on environmental variables were obtained from local sources, and included rainfall, altitude, vegetation, soil type, and location of backyard piggeries. Multivariable logistic regression was performed to investigate associations between seropositivity and risk factors. Using the multivariable models, seroprevalence at geographic locations was predicted based on environmental variables. Goodness of fit of models was measured using area under the curve of the receiver operating characteristic, and the percentage of cases correctly classified as seropositive. Environmental predictors of seroprevalence included living below median altitude of a village, in agricultural areas, on clay soil, and higher density of piggeries above the house. Models had acceptable goodness of fit, and correctly classified ∼84% of cases. Conclusions and Significance Environmental variables could be used to identify high-risk areas for leptospirosis. Environmental monitoring could potentially be a valuable strategy for leptospirosis control, and allow us to move from disease surveillance to environmental health hazard surveillance as a more cost-effective tool for directing public health interventions. PMID:22666516

Developing a Risk Model to Target High-risk Preventive Interventions for Sexual Assault Victimization among Female U.S. Army Soldiers

PubMed Central

Street, Amy E.; Rosellini, Anthony J.; Ursano, Robert J.; Heeringa, Steven G.; Hill, Eric D.; Monahan, John; Naifeh, James A.; Petukhova, Maria V.; Reis, Ben Y.; Sampson, Nancy A.; Bliese, Paul D.; Stein, Murray B.; Zaslavsky, Alan M.; Kessler, Ronald C.

2016-01-01

Sexual violence victimization is a significant problem among female U.S. military personnel. Preventive interventions for high-risk individuals might reduce prevalence, but would require accurate targeting. We attempted to develop a targeting model for female Regular U.S. Army soldiers based on theoretically-guided predictors abstracted from administrative data records. As administrative reports of sexual assault victimization are known to be incomplete, parallel machine learning models were developed to predict administratively-recorded (in the population) and self-reported (in a representative survey) victimization. Capture-recapture methods were used to combine predictions across models. Key predictors included low status, crime involvement, and treated mental disorders. Area under the Receiver Operating Characteristic curve was .83−.88. 33.7-63.2% of victimizations occurred among soldiers in the highest-risk ventile (5%). This high concentration of risk suggests that the models could be useful in targeting preventive interventions, although final determination would require careful weighing of intervention costs, effectiveness, and competing risks. PMID:28154788

Evaluation of potential risks from ash disposal site leachate

DOE Office of Scientific and Technical Information (OSTI.GOV)

Mills, W.B.; Loh, J.Y.; Bate, M.C.

1999-04-01

A risk-based approach is used to evaluate potential human health risks associated with a discharge from an ash disposal site into a small stream. The RIVRISK model was used to estimate downstream concentrations and corresponding risks. The modeling and risk analyses focus on boron, the constituent of greatest potential concern to public health at the site investigated, in Riddle Run, Pennsylvania. Prior to performing the risk assessment, the model is validated by comparing observed and predicted results. The comparison is good and an uncertainty analysis is provided to explain the comparison. The hazard quotient (HQ) for boron is predicted tomore » be greater than 1 at presently regulated compliance points over a range of flow rates. The reference dose (RfD) currently recommended by the United States Environmental Protection Agency (US EPA) was used for the analyses. However, the toxicity of boron as expressed by the RfD is now under review by both the U.S. EPA and the World Health Organization. Alternative reference doses being examined would produce predicted boron hazard quotients of less than 1 at nearly all flow conditions.« less

Quantitative prediction of oral cancer risk in patients with oral leukoplakia.

PubMed

Liu, Yao; Li, Yicheng; Fu, Yue; Liu, Tong; Liu, Xiaoyong; Zhang, Xinyan; Fu, Jie; Guan, Xiaobing; Chen, Tong; Chen, Xiaoxin; Sun, Zheng

2017-07-11

Exfoliative cytology has been widely used for early diagnosis of oral squamous cell carcinoma. We have developed an oral cancer risk index using DNA index value to quantitatively assess cancer risk in patients with oral leukoplakia, but with limited success. In order to improve the performance of the risk index, we collected exfoliative cytology, histopathology, and clinical follow-up data from two independent cohorts of normal, leukoplakia and cancer subjects (training set and validation set). Peaks were defined on the basis of first derivatives with positives, and modern machine learning techniques were utilized to build statistical prediction models on the reconstructed data. Random forest was found to be the best model with high sensitivity (100%) and specificity (99.2%). Using the Peaks-Random Forest model, we constructed an index (OCRI2) as a quantitative measurement of cancer risk. Among 11 leukoplakia patients with an OCRI2 over 0.5, 4 (36.4%) developed cancer during follow-up (23 ± 20 months), whereas 3 (5.3%) of 57 leukoplakia patients with an OCRI2 less than 0.5 developed cancer (32 ± 31 months). OCRI2 is better than other methods in predicting oral squamous cell carcinoma during follow-up. In conclusion, we have developed an exfoliative cytology-based method for quantitative prediction of cancer risk in patients with oral leukoplakia.

Applying artificial neural networks to predict communication risks in the emergency department.

PubMed

Bagnasco, Annamaria; Siri, Anna; Aleo, Giuseppe; Rocco, Gennaro; Sasso, Loredana

2015-10-01

To describe the utility of artificial neural networks in predicting communication risks. In health care, effective communication reduces the risk of error. Therefore, it is important to identify the predictive factors of effective communication. Non-technical skills are needed to achieve effective communication. This study explores how artificial neural networks can be applied to predict the risk of communication failures in emergency departments. A multicentre observational study. Data were collected between March-May 2011 by observing the communication interactions of 840 nurses with their patients during their routine activities in emergency departments. The tools used for our observation were a questionnaire to collect personal and descriptive data, level of training and experience and Guilbert's observation grid, applying the Situation-Background-Assessment-Recommendation technique to communication in emergency departments. A total of 840 observations were made on the nurses working in the emergency departments. Based on Guilbert's observation grid, the output variables is likely to influence the risk of communication failure were 'terminology'; 'listening'; 'attention' and 'clarity', whereas nurses' personal characteristics were used as input variables in the artificial neural network model. A model based on the multilayer perceptron topology was developed and trained. The receiver operator characteristic analysis confirmed that the artificial neural network model correctly predicted the performance of more than 80% of the communication failures. The application of the artificial neural network model could offer a valid tool to forecast and prevent harmful communication errors in the emergency department. © 2015 John Wiley & Sons Ltd.

The mortality risk score and the ADG score: two points-based scoring systems for the Johns Hopkins aggregated diagnosis groups to predict mortality in a general adult population cohort in Ontario, Canada.

PubMed

Austin, Peter C; Walraven, Carl van

2011-10-01

Logistic regression models that incorporated age, sex, and indicator variables for the Johns Hopkins' Aggregated Diagnosis Groups (ADGs) categories have been shown to accurately predict all-cause mortality in adults. To develop 2 different point-scoring systems using the ADGs. The Mortality Risk Score (MRS) collapses age, sex, and the ADGs to a single summary score that predicts the annual risk of all-cause death in adults. The ADG Score derives weights for the individual ADG diagnosis groups. : Retrospective cohort constructed using population-based administrative data. All 10,498,413 residents of Ontario, Canada, between the age of 20 and 100 years who were alive on their birthday in 2007, participated in this study. Participants were randomly divided into derivation and validation samples. : Death within 1 year. In the derivation cohort, the MRS ranged from -21 to 139 (median value 29, IQR 17 to 44). In the validation group, a logistic regression model with the MRS as the sole predictor significantly predicted the risk of 1-year mortality with a c-statistic of 0.917. A regression model with age, sex, and the ADG Score has similar performance. Both methods accurately predicted the risk of 1-year mortality across the 20 vigintiles of risk. The MRS combined values for a person's age, sex, and the John Hopkins ADGs to accurately predict 1-year mortality in adults. The ADG Score is a weighted score representing the presence or absence of the 32 ADG diagnosis groups. These scores will facilitate health services researchers conducting risk adjustment using administrative health care databases.

Do psychosocial work conditions predict risk of disability pensioning? An analysis of register-based outcomes using pooled data on 40,554 observations.

PubMed

Clausen, Thomas; Burr, Hermann; Borg, Vilhelm

2014-06-01

To investigate whether high psychosocial job demands (quantitative demands and work pace) and low psychosocial job resources (influence at work and quality of leadership) predicted risk of disability pensioning among employees in four occupational groups--employees working with customers, employees working with clients, office workers and manual workers--in line with the propositions of the Job Demands-Resources (JD-R) model. Survey data from 40,554 individuals were fitted to the DREAM register containing information on payments of disability pension. Using multi-adjusted Cox regression, observations were followed in the DREAM-register to assess risk of disability pensioning. Average follow-up time was 5.9 years (SD=3.0). Low levels of influence at work predicted an increased risk of disability pensioning and medium levels of quantitative demands predicted a decreased risk of disability pensioning in the study population. We found significant interaction effects between job demands and job resources as combinations low quality of leadership and high job demands predicted the highest rate of disability pensioning. Further analyses showed some, but no statistically significant, differences between the four occupational groups in the associations between job demands, job resources and risk of disability pensioning. The study showed that psychosocial job demands and job resources predicted risk of disability pensioning. The direction of some of the observed associations countered the expectations of the JD-R model and the findings of the present study therefore imply that associations between job demands, job resources and adverse labour market outcomes are more complex than conceptualised in the JD-R model. © 2014 the Nordic Societies of Public Health.

A climate-based prediction model in the high-risk clusters of the Mekong Delta region, Vietnam: towards improving dengue prevention and control.

PubMed

Phung, Dung; Talukder, Mohammad Radwanur Rahman; Rutherford, Shannon; Chu, Cordia

2016-10-01

To develop a prediction score scheme useful for prevention practitioners and authorities to implement dengue preparedness and controls in the Mekong Delta region (MDR). We applied a spatial scan statistic to identify high-risk dengue clusters in the MDR and used generalised linear-distributed lag models to examine climate-dengue associations using dengue case records and meteorological data from 2003 to 2013. The significant predictors were collapsed into categorical scales, and the β-coefficients of predictors were converted to prediction scores. The score scheme was validated for predicting dengue outbreaks using ROC analysis. The north-eastern MDR was identified as the high-risk cluster. A 1 °C increase in temperature at lag 1-4 and 5-8 weeks increased the dengue risk 11% (95% CI, 9-13) and 7% (95% CI, 6-8), respectively. A 1% rise in humidity increased dengue risk 0.9% (95% CI, 0.2-1.4) at lag 1-4 and 0.8% (95% CI, 0.2-1.4) at lag 5-8 weeks. Similarly, a 1-mm increase in rainfall increased dengue risk 0.1% (95% CI, 0.05-0.16) at lag 1-4 and 0.11% (95% CI, 0.07-0.16) at lag 5-8 weeks. The predicted scores performed with high accuracy in diagnosing the dengue outbreaks (96.3%). This study demonstrates the potential usefulness of a dengue prediction score scheme derived from complex statistical models for high-risk dengue clusters. We recommend a further study to examine the possibility of incorporating such a score scheme into the dengue early warning system in similar climate settings. © 2016 John Wiley & Sons Ltd.

Comparison of different risk stratification systems in predicting short-term serious outcome of syncope patients.

PubMed

Safari, Saeed; Baratloo, Alireza; Hashemi, Behrooz; Rahmati, Farhad; Forouzanfar, Mohammad Mehdi; Motamedi, Maryam; Mirmohseni, Ladan

2016-01-01

Determining etiologic causes and prognosis can significantly improve management of syncope patients. The present study aimed to compare the values of San Francisco, Osservatorio Epidemiologico sulla Sincope nel Lazio (OESIL), Boston, and Risk Stratification of Syncope in the Emergency Department (ROSE) score clinical decision rules in predicting the short-term serious outcome of syncope patients. The present diagnostic accuracy study with 1-week follow-up was designed to evaluate the predictive values of the four mentioned clinical decision rules. Screening performance characteristics of each model in predicting mortality, myocardial infarction (MI), and cerebrovascular accidents (CVAs) were calculated and compared. To evaluate the value of each aforementioned model in predicting the outcome, sensitivity, specificity, positive likelihood ratio, and negative likelihood ratio were calculated and receiver-operating curve (ROC) curve analysis was done. A total of 187 patients (mean age: 64.2 ± 17.2 years) were enrolled in the study. Mortality, MI, and CVA were seen in 19 (10.2%), 12 (6.4%), and 36 (19.2%) patients, respectively. Area under the ROC curve for OESIL, San Francisco, Boston, and ROSE models in prediction the risk of 1-week mortality, MI, and CVA was in the 30-70% range, with no significant difference among models ( P > 0.05). The pooled model did not show higher accuracy in prediction of mortality, MI, and CVA compared to others ( P > 0.05). This study revealed the weakness of all four evaluated models in predicting short-term serious outcome of syncope patients referred to the emergency department without any significant advantage for one among others.

Modeling Individual Patient Preferences for Colorectal Cancer Screening Based on Their Tolerance for Complications Risk.

PubMed

Taksler, Glen B; Perzynski, Adam T; Kattan, Michael W

2017-04-01

Recommendations for colorectal cancer screening encourage patients to choose among various screening methods based on individual preferences for benefits, risks, screening frequency, and discomfort. We devised a model to illustrate how individuals with varying tolerance for screening complications risk might decide on their preferred screening strategy. We developed a discrete-time Markov mathematical model that allowed hypothetical individuals to maximize expected lifetime utility by selecting screening method, start age, stop age, and frequency. Individuals could choose from stool-based testing every 1 to 3 years, flexible sigmoidoscopy every 1 to 20 years with annual stool-based testing, colonoscopy every 1 to 20 years, or no screening. We compared the life expectancy gained from the chosen strategy with the life expectancy available from a benchmark strategy of decennial colonoscopy. For an individual at average risk of colorectal cancer who was risk neutral with respect to screening complications (and therefore was willing to undergo screening if it would actuarially increase life expectancy), the model predicted that he or she would choose colonoscopy every 10 years, from age 53 to 73 years, consistent with national guidelines. For a similar individual who was moderately averse to screening complications risk (and therefore required a greater increase in life expectancy to accept potential risks of colonoscopy), the model predicted that he or she would prefer flexible sigmoidoscopy every 12 years with annual stool-based testing, with 93% of the life expectancy benefit of decennial colonoscopy. For an individual with higher risk aversion, the model predicted that he or she would prefer 2 lifetime flexible sigmoidoscopies, 20 years apart, with 70% of the life expectancy benefit of decennial colonoscopy. Mathematical models may formalize how individuals with different risk attitudes choose between various guideline-recommended colorectal cancer screening strategies.

Evaluation of Non-Laboratory and Laboratory Prediction Models for Current and Future Diabetes Mellitus: A Cross-Sectional and Retrospective Cohort Study

PubMed Central

Hahn, Seokyung; Moon, Min Kyong; Park, Kyong Soo; Cho, Young Min

2016-01-01

Background Various diabetes risk scores composed of non-laboratory parameters have been developed, but only a few studies performed cross-validation of these scores and a comparison with laboratory parameters. We evaluated the performance of diabetes risk scores composed of non-laboratory parameters, including a recently published Korean risk score (KRS), and compared them with laboratory parameters. Methods The data of 26,675 individuals who visited the Seoul National University Hospital Healthcare System Gangnam Center for a health screening program were reviewed for cross-sectional validation. The data of 3,029 individuals with a mean of 6.2 years of follow-up were reviewed for longitudinal validation. The KRS and 16 other risk scores were evaluated and compared with a laboratory prediction model developed by logistic regression analysis. Results For the screening of undiagnosed diabetes, the KRS exhibited a sensitivity of 81%, a specificity of 58%, and an area under the receiver operating characteristic curve (AROC) of 0.754. Other scores showed AROCs that ranged from 0.697 to 0.782. For the prediction of future diabetes, the KRS exhibited a sensitivity of 74%, a specificity of 54%, and an AROC of 0.696. Other scores had AROCs ranging from 0.630 to 0.721. The laboratory prediction model composed of fasting plasma glucose and hemoglobin A1c levels showed a significantly higher AROC (0.838, P < 0.001) than the KRS. The addition of the KRS to the laboratory prediction model increased the AROC (0.849, P = 0.016) without a significant improvement in the risk classification (net reclassification index: 4.6%, P = 0.264). Conclusions The non-laboratory risk scores, including KRS, are useful to estimate the risk of undiagnosed diabetes but are inferior to the laboratory parameters for predicting future diabetes. PMID:27214034

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention.

PubMed

Attallah, Omneya; Karthikesalingam, Alan; Holt, Peter J E; Thompson, Matthew M; Sayers, Rob; Bown, Matthew J; Choke, Eddie C; Ma, Xianghong

2017-08-03

Feature selection (FS) process is essential in the medical area as it reduces the effort and time needed for physicians to measure unnecessary features. Choosing useful variables is a difficult task with the presence of censoring which is the unique characteristic in survival analysis. Most survival FS methods depend on Cox's proportional hazard model; however, machine learning techniques (MLT) are preferred but not commonly used due to censoring. Techniques that have been proposed to adopt MLT to perform FS with survival data cannot be used with the high level of censoring. The researcher's previous publications proposed a technique to deal with the high level of censoring. It also used existing FS techniques to reduce dataset dimension. However, in this paper a new FS technique was proposed and combined with feature transformation and the proposed uncensoring approaches to select a reduced set of features and produce a stable predictive model. In this paper, a FS technique based on artificial neural network (ANN) MLT is proposed to deal with highly censored Endovascular Aortic Repair (EVAR). Survival data EVAR datasets were collected during 2004 to 2010 from two vascular centers in order to produce a final stable model. They contain almost 91% of censored patients. The proposed approach used a wrapper FS method with ANN to select a reduced subset of features that predict the risk of EVAR re-intervention after 5 years to patients from two different centers located in the United Kingdom, to allow it to be potentially applied to cross-centers predictions. The proposed model is compared with the two popular FS techniques; Akaike and Bayesian information criteria (AIC, BIC) that are used with Cox's model. The final model outperforms other methods in distinguishing the high and low risk groups; as they both have concordance index and estimated AUC better than the Cox's model based on AIC, BIC, Lasso, and SCAD approaches. These models have p-values lower than 0.05, meaning that patients with different risk groups can be separated significantly and those who would need re-intervention can be correctly predicted. The proposed approach will save time and effort made by physicians to collect unnecessary variables. The final reduced model was able to predict the long-term risk of aortic complications after EVAR. This predictive model can help clinicians decide patients' future observation plan.

Cryptosporidiosis susceptibility and risk: a case study.

PubMed

Makri, Anna; Modarres, Reza; Parkin, Rebecca

2004-02-01

Regional estimates of cryptosporidiosis risks from drinking water exposure were developed and validated, accounting for AIDS status and age. We constructed a model with probability distributions and point estimates representing Cryptosporidium in tap water, tap water consumed per day (exposure characterization); dose response, illness given infection, prolonged illness given illness; and three conditional probabilities describing the likelihood of case detection by active surveillance (health effects characterization). The model predictions were combined with population data to derive expected case numbers and incidence rates per 100,000 population, by age and AIDS status, borough specific and for New York City overall in 2000 (risk characterization). They were compared with same-year surveillance data to evaluate predictive ability, assumed to represent true incidence of waterborne cryptosporidiosis. The predicted mean risks, similar to previously published estimates for this region, overpredicted observed incidence-most extensively when accounting for AIDS status. The results suggest that overprediction may be due to conservative parameters applied to both non-AIDS and AIDS populations, and that biological differences for children need to be incorporated. Interpretations are limited by the unknown accuracy of available surveillance data, in addition to variability and uncertainty of model predictions. The model appears sensitive to geographical differences in AIDS prevalence. The use of surveillance data for validation and model parameters pertinent to susceptibility are discussed.

Prediction of Ischemic Heart Disease and Stroke in Survivors of Childhood Cancer.

PubMed

Chow, Eric J; Chen, Yan; Hudson, Melissa M; Feijen, Elizabeth A M; Kremer, Leontien C; Border, William L; Green, Daniel M; Meacham, Lillian R; Mulrooney, Daniel A; Ness, Kirsten K; Oeffinger, Kevin C; Ronckers, Cécile M; Sklar, Charles A; Stovall, Marilyn; van der Pal, Helena J; van Dijk, Irma W E M; van Leeuwen, Flora E; Weathers, Rita E; Robison, Leslie L; Armstrong, Gregory T; Yasui, Yutaka

2018-01-01

Purpose We aimed to predict individual risk of ischemic heart disease and stroke in 5-year survivors of childhood cancer. Patients and Methods Participants in the Childhood Cancer Survivor Study (CCSS; n = 13,060) were observed through age 50 years for the development of ischemic heart disease and stroke. Siblings (n = 4,023) established the baseline population risk. Piecewise exponential models with backward selection estimated the relationships between potential predictors and each outcome. The St Jude Lifetime Cohort Study (n = 1,842) and the Emma Children's Hospital cohort (n = 1,362) were used to validate the CCSS models. Results Ischemic heart disease and stroke occurred in 265 and 295 CCSS participants, respectively. Risk scores based on a standard prediction model that included sex, chemotherapy, and radiotherapy (cranial, neck, and chest) exposures achieved an area under the curve and concordance statistic of 0.70 and 0.70 for ischemic heart disease and 0.63 and 0.66 for stroke, respectively. Validation cohort area under the curve and concordance statistics ranged from 0.66 to 0.67 for ischemic heart disease and 0.68 to 0.72 for stroke. Risk scores were collapsed to form statistically distinct low-, moderate-, and high-risk groups. The cumulative incidences at age 50 years among CCSS low-risk groups were < 5%, compared with approximately 20% for high-risk groups ( P < .001); cumulative incidence was only 1% for siblings ( P < .001 v low-risk survivors). Conclusion Information available to clinicians soon after completion of childhood cancer therapy can predict individual risk for subsequent ischemic heart disease and stroke with reasonable accuracy and discrimination through age 50 years. These models provide a framework on which to base future screening strategies and interventions.

Development and applications of the Veterans Health Administration's Stratification Tool for Opioid Risk Mitigation (STORM) to improve opioid safety and prevent overdose and suicide.

PubMed

Oliva, Elizabeth M; Bowe, Thomas; Tavakoli, Sara; Martins, Susana; Lewis, Eleanor T; Paik, Meenah; Wiechers, Ilse; Henderson, Patricia; Harvey, Michael; Avoundjian, Tigran; Medhanie, Amanuel; Trafton, Jodie A

2017-02-01

Concerns about opioid-related adverse events, including overdose, prompted the Veterans Health Administration (VHA) to launch an Opioid Safety Initiative and Overdose Education and Naloxone Distribution program. To mitigate risks associated with opioid prescribing, a holistic approach that takes into consideration both risk factors (e.g., dose, substance use disorders) and risk mitigation interventions (e.g., urine drug screening, psychosocial treatment) is needed. This article describes the Stratification Tool for Opioid Risk Mitigation (STORM), a tool developed in VHA that reflects this holistic approach and facilitates patient identification and monitoring. STORM prioritizes patients for review and intervention according to their modeled risk for overdose/suicide-related events and displays risk factors and risk mitigation interventions obtained from VHA electronic medical record (EMR)-data extracts. Patients' estimated risk is based on a predictive risk model developed using fiscal year 2010 (FY2010: 10/1/2009-9/30/2010) EMR-data extracts and mortality data among 1,135,601 VHA patients prescribed opioid analgesics to predict risk for an overdose/suicide-related event in FY2011 (2.1% experienced an event). Cross-validation was used to validate the model, with receiver operating characteristic curves for the training and test data sets performing well (>.80 area under the curve). The predictive risk model distinguished patients based on risk for overdose/suicide-related adverse events, allowing for identification of high-risk patients and enrichment of target populations of patients with greater safety concerns for proactive monitoring and application of risk mitigation interventions. Results suggest that clinical informatics can leverage EMR-extracted data to identify patients at-risk for overdose/suicide-related events and provide clinicians with actionable information to mitigate risk. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

Validation of the Registry to Evaluate Early and Long-Term Pulmonary Arterial Hypertension Disease Management (REVEAL) pulmonary hypertension prediction model in a unique population and utility in the prediction of long-term survival.

PubMed

Cogswell, Rebecca; Kobashigawa, Erin; McGlothlin, Dana; Shaw, Robin; De Marco, Teresa

2012-11-01

The Registry to Evaluate Early and Long-Term Pulmonary Arterial (PAH) Hypertension Disease Management (REVEAL) model was designed to predict 1-year survival in patients with PAH. Multivariate prediction models need to be evaluated in cohorts distinct from the derivation set to determine external validity. In addition, limited data exist on the utility of this model in the prediction of long-term survival. REVEAL model performance was assessed to predict 1-year and 5-year outcomes, defined as survival or composite survival or freedom from lung transplant, in 140 patients with PAH. The validation cohort had a higher proportion of human immunodeficiency virus (7.9% vs 1.9%, p < 0.0001), methamphetamine use (19.3% vs 4.9%, p < 0.0001), and portal hypertension PAH (16.4% vs 5.1%, p < 0.0001) compared with the development cohort. The C-index of the model to predict survival was 0.765 at 1 year and 0.712 at 5 years of follow-up. The C-index of the model to predict composite survival or freedom from lung transplant was 0.805 and 0.724 at 1 and 5 years of follow-up, respectively. Prediction by the model, however, was weakest among patients with intermediate-risk predicted survival. The REVEAL model had adequate discrimination to predict 1-year survival in this small but clinically distinct validation cohort. Although the model also had predictive ability out to 5 years, prediction was limited among patients of intermediate risk, suggesting our prediction methods can still be improved. Copyright © 2012. Published by Elsevier Inc.

Quantitative assessment of the microbial risk of leafy greens from farm to consumption: preliminary framework, data, and risk estimates.

PubMed

Danyluk, Michelle D; Schaffner, Donald W

2011-05-01

This project was undertaken to relate what is known about the behavior of Escherichia coli O157:H7 under laboratory conditions and integrate this information to what is known regarding the 2006 E. coli O157:H7 spinach outbreak in the context of a quantitative microbial risk assessment. The risk model explicitly assumes that all contamination arises from exposure in the field. Extracted data, models, and user inputs were entered into an Excel spreadsheet, and the modeling software @RISK was used to perform Monte Carlo simulations. The model predicts that cut leafy greens that are temperature abused will support the growth of E. coli O157:H7, and populations of the organism may increase by as much a 1 log CFU/day under optimal temperature conditions. When the risk model used a starting level of -1 log CFU/g, with 0.1% of incoming servings contaminated, the predicted numbers of cells per serving were within the range of best available estimates of pathogen levels during the outbreak. The model predicts that levels in the field of -1 log CFU/g and 0.1% prevalence could have resulted in an outbreak approximately the size of the 2006 E. coli O157:H7 outbreak. This quantitative microbial risk assessment model represents a preliminary framework that identifies available data and provides initial risk estimates for pathogenic E. coli in leafy greens. Data gaps include retail storage times, correlations between storage time and temperature, determining the importance of E. coli O157:H7 in leafy greens lag time models, and validation of the importance of cross-contamination during the washing process.

Ecological covariates based predictive model of malaria risk in the state of Chhattisgarh, India.

PubMed

Kumar, Rajesh; Dash, Chinmaya; Rani, Khushbu

2017-09-01

Malaria being an endemic disease in the state of Chhattisgarh and ecologically dependent mosquito-borne disease, the study is intended to identify the ecological covariates of malaria risk in districts of the state and to build a suitable predictive model based on those predictors which could assist developing a weather based early warning system. This secondary data based analysis used one month lagged district level malaria positive cases as response variable and ecological covariates as independent variables which were tested with fixed effect panelled negative binomial regression models. Interactions among the covariates were explored using two way factorial interaction in the model. Although malaria risk in the state possesses perennial characteristics, higher parasitic incidence was observed during the rainy and winter seasons. The univariate analysis indicated that the malaria incidence risk was statistically significant associated with rainfall, maximum humidity, minimum temperature, wind speed, and forest cover ( p  < 0.05). The efficient predictive model include the forest cover [IRR-1.033 (1.024-1.042)], maximum humidity [IRR-1.016 (1.013-1.018)], and two-way factorial interactions between district specific averaged monthly minimum temperature and monthly minimum temperature, monthly minimum temperature was statistically significant [IRR-1.44 (1.231-1.695)] whereas the interaction term has a protective effect [IRR-0.982 (0.974-0.990)] against malaria infections. Forest cover, maximum humidity, minimum temperature and wind speed emerged as potential covariates to be used in predictive models for modelling the malaria risk in the state which could be efficiently used for early warning systems in the state.

Using ensemble rainfall predictions in a countrywide flood forecasting model in Scotland

NASA Astrophysics Data System (ADS)

Cranston, M. D.; Maxey, R.; Tavendale, A. C. W.; Buchanan, P.

2012-04-01

Improving flood predictions for all sources of flooding is at the centre of flood risk management policy in Scotland. With the introduction of the Flood Risk Management (Scotland) Act providing a new statutory basis for SEPA's flood warning responsibilities, the pressures on delivering hydrological science developments in support of this legislation has increased. Specifically, flood forecasting capabilities need to develop in support of the need to reduce the impact of flooding through the provision of actively disseminated, reliable and timely flood warnings. Flood forecasting in Scotland has developed significantly in recent years (Cranston and Tavendale, 2012). The development of hydrological models to predict flooding at a catchment scale has relied upon the application of rainfall runoff models utilising raingauge, radar and quantitative precipitation forecasts in the short lead time (less than 6 hours). Single or deterministic forecasts based on highly uncertain rainfall predictions have led to the greatest operational difficulties when communicating flood risk with emergency responders, therefore the emergence of probability-based estimates offers the greatest opportunity for managing uncertain predictions. This paper presents operational application of a physical-conceptual distributed hydrological model on a countrywide basis across Scotland. Developed by CEH Wallingford for SEPA in 2011, Grid-to-Grid (G2G) principally runs in deterministic mode and employs radar and raingauge estimates of rainfall together with weather model predictions to produce forecast river flows, as gridded time-series at a resolution of 1km and for up to 5 days ahead (Cranston, et al., 2012). However the G2G model is now being run operationally using ensemble predictions of rainfall from the MOGREPS-R system to provide probabilistic flood forecasts. By presenting a range of flood predictions on a national scale through this approach, hydrologists are now able to consider an objective measure of the likelihood of flooding impacts to help with risk based emergency communication.

Divorce as Risky Behavior

PubMed Central

LIGHT, AUDREY; AHN, TAEHYUN

2010-01-01

Given that divorce often represents a high-stakes income gamble, we ask how individual levels of risk tolerance affect the decision to divorce. We extend the orthodox divorce model by assuming that individuals are risk averse, that marriage is risky, and that divorce is even riskier. The model predicts that conditional on the expected gains to marriage and divorce, the probability of divorce increases with relative risk tolerance because risk averse individuals require compensation for the additional risk that is inherent in divorce. To implement the model empirically, we use data for first-married women and men from the 1979 National Longitudinal Survey of Youth to estimate a probit model of divorce in which a measure of risk tolerance is among the covariates. The estimates reveal that a 1-point increase in risk tolerance raises the predicted probability of divorce by 4.3% for a representative man and by 11.4% for a representative woman. These findings are consistent with the notion that divorce entails a greater income gamble for women than for men. PMID:21308563

Divorce as risky behavior.

PubMed

Light, Audrey; Ahn, Taehyun

2010-11-01

Given that divorce often represents a high-stakes income gamble, we ask how individual levels of risk tolerance affect the decision to divorce. We extend the orthodox divorce model by assuming that individuals are risk averse, that marriage is risky, and that divorce is even riskier. The model predicts that conditional on the expected gains to marriage and divorce, the probability of divorce increases with relative risk tolerance because risk averse individuals require compensation for the additional risk that is inherent in divorce. To implement the model empirically, we use data for first-married women and men from the 1979 National Longitudinal Survey of Youth to estimate a probit model of divorce in which a measure of risk tolerance is among the covariates. The estimates reveal that a 1-point increase in risk tolerance raises the predicted probability of divorce by 4.3% for a representative man and by 11.4% for a representative woman. These findings are consistent with the notion that divorce entails a greater income gamble for women than for men.

A First Step towards a Clinical Decision Support System for Post-traumatic Stress Disorders.

PubMed

Ma, Sisi; Galatzer-Levy, Isaac R; Wang, Xuya; Fenyö, David; Shalev, Arieh Y

2016-01-01

PTSD is distressful and debilitating, following a non-remitting course in about 10% to 20% of trauma survivors. Numerous risk indicators of PTSD have been identified, but individual level prediction remains elusive. As an effort to bridge the gap between scientific discovery and practical application, we designed and implemented a clinical decision support pipeline to provide clinically relevant recommendation for trauma survivors. To meet the specific challenge of early prediction, this work uses data obtained within ten days of a traumatic event. The pipeline creates personalized predictive model for each individual, and computes quality metrics for each predictive model. Clinical recommendations are made based on both the prediction of the model and its quality, thus avoiding making potentially detrimental recommendations based on insufficient information or suboptimal model. The current pipeline outperforms the acute stress disorder, a commonly used clinical risk factor for PTSD development, both in terms of sensitivity and specificity.

Application of the Rosner-Wei Risk-Prediction Model to Estimate Sexual Orientation Patterns in Colon Cancer Risk in a Prospective Cohort of U.S. Women

PubMed Central

Austin, S. Bryn; Pazaris, Mathew J.; Wei, Esther K.; Rosner, Bernard; Kennedy, Grace A.; Bowen, Deborah; Spiegelman, Donna

2014-01-01

Purpose We examined whether lesbian and bisexual women may be at greater risk of colon cancer (CC) than heterosexual women. Methods Working with a large cohort of U.S. women ages 25-64 years, we analyzed 20 years of prospective data to estimate CC incidence, based on known risk factors by applying the Rosner-Wei CC risk-prediction model. Comparing to heterosexual women, we calculated for lesbian and bisexual women the predicted one-year incidence rate (IR) per 100,000 person-years and estimated incidence rate ratios (IRR) and 95% confidence intervals (CI), based on each woman’s comprehensive risk factor profile. Results Analyses included 1,373,817 person-years of data from 66,257 women. For each sexual orientation group, mean predicted one-year CC IR per 100,000 person-years was slightly over 12 cases for each of the sexual orientation groups. After controlling for confounders in fully adjusted models and compared to heterosexuals, no significant differences in IRR were observed for lesbians (IRR 1.01; 95% CI 0.99, 1.04) or bisexuals (IRR 1.01; 95% CI 0.98, 1.04). Conclusions CC risk is similar across all sexual orientation subgroups, with all groups comparably affected. Health professionals must ensure that prevention, screening, and treatment programs are adequately reaching each of these communities. PMID:24852207

Probabilistic framework for product design optimization and risk management

NASA Astrophysics Data System (ADS)

Keski-Rahkonen, J. K.

2018-05-01

Probabilistic methods have gradually gained ground within engineering practices but currently it is still the industry standard to use deterministic safety margin approaches to dimensioning components and qualitative methods to manage product risks. These methods are suitable for baseline design work but quantitative risk management and product reliability optimization require more advanced predictive approaches. Ample research has been published on how to predict failure probabilities for mechanical components and furthermore to optimize reliability through life cycle cost analysis. This paper reviews the literature for existing methods and tries to harness their best features and simplify the process to be applicable in practical engineering work. Recommended process applies Monte Carlo method on top of load-resistance models to estimate failure probabilities. Furthermore, it adds on existing literature by introducing a practical framework to use probabilistic models in quantitative risk management and product life cycle costs optimization. The main focus is on mechanical failure modes due to the well-developed methods used to predict these types of failures. However, the same framework can be applied on any type of failure mode as long as predictive models can be developed.

Predicting acute contact toxicity of pesticides in honeybees (Apis mellifera) through a k-nearest neighbor model.

PubMed

Como, F; Carnesecchi, E; Volani, S; Dorne, J L; Richardson, J; Bassan, A; Pavan, M; Benfenati, E

2017-01-01

Ecological risk assessment of plant protection products (PPPs) requires an understanding of both the toxicity and the extent of exposure to assess risks for a range of taxa of ecological importance including target and non-target species. Non-target species such as honey bees (Apis mellifera), solitary bees and bumble bees are of utmost importance because of their vital ecological services as pollinators of wild plants and crops. To improve risk assessment of PPPs in bee species, computational models predicting the acute and chronic toxicity of a range of PPPs and contaminants can play a major role in providing structural and physico-chemical properties for the prioritisation of compounds of concern and future risk assessments. Over the last three decades, scientific advisory bodies and the research community have developed toxicological databases and quantitative structure-activity relationship (QSAR) models that are proving invaluable to predict toxicity using historical data and reduce animal testing. This paper describes the development and validation of a k-Nearest Neighbor (k-NN) model using in-house software for the prediction of acute contact toxicity of pesticides on honey bees. Acute contact toxicity data were collected from different sources for 256 pesticides, which were divided into training and test sets. The k-NN models were validated with good prediction, with an accuracy of 70% for all compounds and of 65% for highly toxic compounds, suggesting that they might reliably predict the toxicity of structurally diverse pesticides and could be used to screen and prioritise new pesticides. Copyright © 2016 Elsevier Ltd. All rights reserved.

Do causal concentration-response functions exist? A critical review of associational and causal relations between fine particulate matter and mortality.

PubMed

Cox, Louis Anthony Tony

2017-08-01

Concentration-response (C-R) functions relating concentrations of pollutants in ambient air to mortality risks or other adverse health effects provide the basis for many public health risk assessments, benefits estimates for clean air regulations, and recommendations for revisions to existing air quality standards. The assumption that C-R functions relating levels of exposure and levels of response estimated from historical data usefully predict how future changes in concentrations would change risks has seldom been carefully tested. This paper critically reviews literature on C-R functions for fine particulate matter (PM2.5) and mortality risks. We find that most of them describe historical associations rather than valid causal models for predicting effects of interventions that change concentrations. The few papers that explicitly attempt to model causality rely on unverified modeling assumptions, casting doubt on their predictions about effects of interventions. A large literature on modern causal inference algorithms for observational data has been little used in C-R modeling. Applying these methods to publicly available data from Boston and the South Coast Air Quality Management District around Los Angeles shows that C-R functions estimated for one do not hold for the other. Changes in month-specific PM2.5 concentrations from one year to the next do not help to predict corresponding changes in average elderly mortality rates in either location. Thus, the assumption that estimated C-R relations predict effects of pollution-reducing interventions may not be true. Better causal modeling methods are needed to better predict how reducing air pollution would affect public health.

Prostate Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing prostate cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Bladder Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing bladder cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Ovarian Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing ovarian cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Pancreatic Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing pancreatic cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Testicular Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of testicular cervical cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Breast Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing breast cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Esophageal Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing esophageal cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Cervical Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing cervical cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Liver Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing liver cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Lung Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing lung cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Colorectal Cancer Risk Prediction Models

Cancer.gov

Developing statistical models that estimate the probability of developing colorectal cancer over a defined period of time will help clinicians identify individuals at higher risk of specific cancers, allowing for earlier or more frequent screening and counseling of behavioral changes to decrease risk.

Genetic Predisposition to Ischemic Stroke

PubMed Central

Kamatani, Yoichiro; Takahashi, Atsushi; Hata, Jun; Furukawa, Ryohei; Shiwa, Yuh; Yamaji, Taiki; Hara, Megumi; Tanno, Kozo; Ohmomo, Hideki; Ono, Kanako; Takashima, Naoyuki; Matsuda, Koichi; Wakai, Kenji; Sawada, Norie; Iwasaki, Motoki; Yamagishi, Kazumasa; Ago, Tetsuro; Ninomiya, Toshiharu; Fukushima, Akimune; Hozawa, Atsushi; Minegishi, Naoko; Satoh, Mamoru; Endo, Ryujin; Sasaki, Makoto; Sakata, Kiyomi; Kobayashi, Seiichiro; Ogasawara, Kuniaki; Nakamura, Motoyuki; Hitomi, Jiro; Kita, Yoshikuni; Tanaka, Keitaro; Iso, Hiroyasu; Kitazono, Takanari; Kubo, Michiaki; Tanaka, Hideo; Tsugane, Shoichiro; Kiyohara, Yutaka; Yamamoto, Masayuki; Sobue, Kenji; Shimizu, Atsushi

2017-01-01

Background and Purpose— The prediction of genetic predispositions to ischemic stroke (IS) may allow the identification of individuals at elevated risk and thereby prevent IS in clinical practice. Previously developed weighted multilocus genetic risk scores showed limited predictive ability for IS. Here, we investigated the predictive ability of a newer method, polygenic risk score (polyGRS), based on the idea that a few strong signals, as well as several weaker signals, can be collectively informative to determine IS risk. Methods— We genotyped 13 214 Japanese individuals with IS and 26 470 controls (derivation samples) and generated both multilocus genetic risk scores and polyGRS, using the same derivation data set. The predictive abilities of each scoring system were then assessed using 2 independent sets of Japanese samples (KyushuU and JPJM data sets). Results— In both validation data sets, polyGRS was shown to be significantly associated with IS, but weighted multilocus genetic risk scores was not. Comparing the highest with the lowest polyGRS quintile, the odds ratios for IS were 1.75 (95% confidence interval, 1.33–2.31) and 1.99 (95% confidence interval, 1.19–3.33) in the KyushuU and JPJM samples, respectively. Using the KyushuU samples, the addition of polyGRS to a nongenetic risk model resulted in a significant improvement of the predictive ability (net reclassification improvement=0.151; P<0.001). Conclusions— The polyGRS was shown to be superior to weighted multilocus genetic risk scores as an IS prediction model. Thus, together with the nongenetic risk factors, polyGRS will provide valuable information for individual risk assessment and management of modifiable risk factors. PMID:28034966

Preoperative predictive model for acute kidney injury after elective cardiac surgery: a prospective multicentre cohort study.

PubMed

Callejas, Raquel; Panadero, Alfredo; Vives, Marc; Duque, Paula; Echarri, Gemma; Monedero, Pablo

2018-05-11

Predictive models of CS-AKI include emergency surgery and patients with haemodynamic instability. Our objective was to evaluate the performance of validated predictive models (Thakar and Demirjian) in elective cardiac surgery and to propose a better score in the case of poor performance. A prospective, multicentre, observational study was designed. Data were collected from 942 patients undergoing cardiac surgery, after excluding emergency surgery and patients with an intraaortic balloon pump. The main outcome measure was CS-AKI defined by the composite of requiring dialysis or doubling baseline creatinine values. Both models showed poor discrimination in elective surgery (Thakar's model, AUROC = 0.57, 95% CI = 0.50-0.64 and Demirjian's model, AUROC= 0.64, 95% CI = 0.58-0.71). We generated a new model whose significant independent predictors were: anaemia, age, hypertension, obesity, congestive heart failure, previous cardiac surgery and type of surgery. It classifies patients with scores 0-3 as low risk (< 5%), scores 4-7 as medium risk (up to 15%) and scores > 8 as high risk (>30%) of developing CS-AKI with a statistically significant correlation (p <0.001). Our model reflects acceptable discriminatory ability (AUC = 0.72, 95% CI = 0.66-0.78) which is significantly better than Thakar and Demirjian's models (p<0.01). We developed a new simple predictive model of CS-AKI in elective surgery based on available preoperative information. Our new model is easy to calculate and can be an effective tool for communicating risk to patients and guiding decision-making in the perioperative period. The study requires external validation.

Launch Vehicle Debris Models and Crew Vehicle Ascent Abort Risk

NASA Technical Reports Server (NTRS)

Gee, Ken; Lawrence, Scott

2013-01-01

For manned space launch systems, a reliable abort system is required to reduce the risks associated with a launch vehicle failure during ascent. Understanding the risks associated with failure environments can be achieved through the use of physics-based models of these environments. Debris fields due to destruction of the launch vehicle is one such environment. To better analyze the risk posed by debris, a physics-based model for generating launch vehicle debris catalogs has been developed. The model predicts the mass distribution of the debris field based on formulae developed from analysis of explosions. Imparted velocity distributions are computed using a shock-physics code to model the explosions within the launch vehicle. A comparison of the debris catalog with an existing catalog for the Shuttle external tank show good comparison in the debris characteristics and the predicted debris strike probability. The model is used to analyze the effects of number of debris pieces and velocity distributions on the strike probability and risk.

Cheese Microbial Risk Assessments — A Review

PubMed Central

Choi, Kyoung-Hee; Lee, Heeyoung; Lee, Soomin; Kim, Sejeong; Yoon, Yohan

2016-01-01

Cheese is generally considered a safe and nutritious food, but foodborne illnesses linked to cheese consumption have occurred in many countries. Several microbial risk assessments related to Listeria monocytogenes, Staphylococcus aureus, and Escherichia coli infections, causing cheese-related foodborne illnesses, have been conducted. Although the assessments of microbial risk in soft and low moisture cheeses such as semi-hard and hard cheeses have been accomplished, it has been more focused on the correlations between pathogenic bacteria and soft cheese, because cheese-associated foodborne illnesses have been attributed to the consumption of soft cheeses. As a part of this microbial risk assessment, predictive models have been developed to describe the relationship between several factors (pH, Aw, starter culture, and time) and the fates of foodborne pathogens in cheese. Predictions from these studies have been used for microbial risk assessment as a part of exposure assessment. These microbial risk assessments have identified that risk increased in cheese with high moisture content, especially for raw milk cheese, but the risk can be reduced by preharvest and postharvest preventions. For accurate quantitative microbial risk assessment, more data including interventions such as curd cooking conditions (temperature and time) and ripening period should be available for predictive models developed with cheese, cheese consumption amounts and cheese intake frequency data as well as more dose-response models. PMID:26950859

Toward a cumulative ecological risk model for the etiology of child maltreatment

PubMed Central

MacKenzie, Michael J.; Kotch, Jonathan B.; Lee, Li-Ching

2011-01-01

The purpose of the current study was to further the integration of cumulative risk models with empirical research on the etiology of child maltreatment. Despite the well-established literature supporting the importance of the accumulation of ecological risk, this perspective has had difficulty infiltrating empirical maltreatment research and its tendency to focus on more limited risk factors. Utilizing a sample of 842 mother-infant dyads, we compared the capacity of individual risk factors and a cumulative index to predict maltreatment reports in a prospective longitudinal investigation over the first sixteen years of life. The total load of risk in early infancy was found to be related to maternal cognitions surrounding her new role, measures of social support and well-being, and indicators of child cognitive functioning. After controlling for total level of cumulative risk, most single factors failed to predict later maltreatment reports and no single variable provided odd-ratios as powerful as the predictive power of a cumulative index. Continuing the shift away from simplistic causal models toward an appreciation for the cumulative nature of risk would be an important step forward in the way we conceptualize intervention and support programs, concentrating them squarely on alleviating the substantial risk facing so many of society’s families. PMID:24817777

Adaptation of clinical prediction models for application in local settings.

PubMed

Kappen, Teus H; Vergouwe, Yvonne; van Klei, Wilton A; van Wolfswinkel, Leo; Kalkman, Cor J; Moons, Karel G M

2012-01-01

When planning to use a validated prediction model in new patients, adequate performance is not guaranteed. For example, changes in clinical practice over time or a different case mix than the original validation population may result in inaccurate risk predictions. To demonstrate how clinical information can direct updating a prediction model and development of a strategy for handling missing predictor values in clinical practice. A previously derived and validated prediction model for postoperative nausea and vomiting was updated using a data set of 1847 patients. The update consisted of 1) changing the definition of an existing predictor, 2) reestimating the regression coefficient of a predictor, and 3) adding a new predictor to the model. The updated model was then validated in a new series of 3822 patients. Furthermore, several imputation models were considered to handle real-time missing values, so that possible missing predictor values could be anticipated during actual model use. Differences in clinical practice between our local population and the original derivation population guided the update strategy of the prediction model. The predictive accuracy of the updated model was better (c statistic, 0.68; calibration slope, 1.0) than the original model (c statistic, 0.62; calibration slope, 0.57). Inclusion of logistical variables in the imputation models, besides observed patient characteristics, contributed to a strategy to deal with missing predictor values at the time of risk calculation. Extensive knowledge of local, clinical processes provides crucial information to guide the process of adapting a prediction model to new clinical practices.

[How exactly can we predict the prognosis of COPD].

PubMed

Atiş, Sibel; Kanik, Arzu; Ozgür, Eylem Sercan; Eker, Suzan; Tümkaya, Münir; Ozge, Cengiz

2009-01-01

Predictive models play a pivotal role in the provision of accurate and useful probabilistic assessments of clinical outcomes in chronic diseases. This study was aimed to develop a dedicated prognostic index for quantifying progression risk in chronic obstructive pulmonary disease (COPD). Data were collected prospectively from 75 COPD patients during a three years period. A predictive model of progression risk of COPD was developed using Bayesian logistic regression analysis by Markov chain Monte Carlo method. One-year cycles were used for the disease progression in this model. Primary end points for progression were impairment in basal dyspne index (BDI) score, FEV(1) decline, and exacerbation frequency in last three years. Time-varying covariates age, smoking, body mass index (BMI), severity of disease according to GOLD, PaO2, PaCO(2), IC, RV/TLC, DLCO were used under the study. The mean age was 57.1 + or - 8.1. BDI were strongly correlated with exacerbation frequency (p= 0.001) but not with FEV(1) decline. BMI was found to be a predictor factor for impairment in BDI (p= 0.03). The following independent risk factors were significant to predict exacerbation frequency: GOLD staging (OR for GOLD I vs. II and III = 2.3 and 4.0), hypoxemia (OR for mild vs moderate and severe = 2.1 and 5.1) and hyperinflation (OR= 1.6). PaO2 (p= 0.026), IC (p= 0.02) and RV/TLC (p= 0.03) were found to be predictive factors for FEV(1) decline. The model estimated BDI, lung function and exacerbation frequency at the last time point by testing initial data of three years with 95% reliability (p< 0.001). Accordingly, this model was evaluated as confident of 95% for assessing the future status of COPD patients. Using Bayesian predictive models, it was possible to develop a risk-stratification index that accurately predicted progression of COPD. This model can provide decision-making about future in COPD patients with high reliability looking clinical data of beginning.

Development and validation of Prediction models for Risks of complications in Early-onset Pre-eclampsia (PREP): a prospective cohort study.

PubMed

Thangaratinam, Shakila; Allotey, John; Marlin, Nadine; Mol, Ben W; Von Dadelszen, Peter; Ganzevoort, Wessel; Akkermans, Joost; Ahmed, Asif; Daniels, Jane; Deeks, Jon; Ismail, Khaled; Barnard, Ann Marie; Dodds, Julie; Kerry, Sally; Moons, Carl; Riley, Richard D; Khan, Khalid S

2017-04-01

The prognosis of early-onset pre-eclampsia (before 34 weeks' gestation) is variable. Accurate prediction of complications is required to plan appropriate management in high-risk women. To develop and validate prediction models for outcomes in early-onset pre-eclampsia. Prospective cohort for model development, with validation in two external data sets. Model development: 53 obstetric units in the UK. Model transportability: PIERS (Pre-eclampsia Integrated Estimate of RiSk for mothers) and PETRA (Pre-Eclampsia TRial Amsterdam) studies. Pregnant women with early-onset pre-eclampsia. Nine hundred and forty-six women in the model development data set and 850 women (634 in PIERS, 216 in PETRA) in the transportability (external validation) data sets. The predictors were identified from systematic reviews of tests to predict complications in pre-eclampsia and were prioritised by Delphi survey. The primary outcome was the composite of adverse maternal outcomes established using Delphi surveys. The secondary outcome was the composite of fetal and neonatal complications. We developed two prediction models: a logistic regression model (PREP-L) to assess the overall risk of any maternal outcome until postnatal discharge and a survival analysis model (PREP-S) to obtain individual risk estimates at daily intervals from diagnosis until 34 weeks. Shrinkage was used to adjust for overoptimism of predictor effects. For internal validation (of the full models in the development data) and external validation (of the reduced models in the transportability data), we computed the ability of the models to discriminate between those with and without poor outcomes ( c -statistic), and the agreement between predicted and observed risk (calibration slope). The PREP-L model included maternal age, gestational age at diagnosis, medical history, systolic blood pressure, urine protein-to-creatinine ratio, platelet count, serum urea concentration, oxygen saturation, baseline treatment with antihypertensive drugs and administration of magnesium sulphate. The PREP-S model additionally included exaggerated tendon reflexes and serum alanine aminotransaminase and creatinine concentration. Both models showed good discrimination for maternal complications, with anoptimism-adjusted c -statistic of 0.82 [95% confidence interval (CI) 0.80 to 0.84] for PREP-L and 0.75 (95% CI 0.73 to 0.78) for the PREP-S model in the internal validation. External validation of the reduced PREP-L model showed good performance with a c -statistic of 0.81 (95% CI 0.77 to 0.85) in PIERS and 0.75 (95% CI 0.64 to 0.86) in PETRA cohorts for maternal complications, and calibrated well with slopes of 0.93 (95% CI 0.72 to 1.10) and 0.90 (95% CI 0.48 to 1.32), respectively. In the PIERS data set, the reduced PREP-S model had a c -statistic of 0.71 (95% CI 0.67 to 0.75) and a calibration slope of 0.67 (95% CI 0.56 to 0.79). Low gestational age at diagnosis, high urine protein-to-creatinine ratio, increased serum urea concentration, treatment with antihypertensive drugs, magnesium sulphate, abnormal uterine artery Doppler scan findings and estimated fetal weight below the 10th centile were associated with fetal complications. The PREP-L model provided individualised risk estimates in early-onset pre-eclampsia to plan management of high- or low-risk individuals. The PREP-S model has the potential to be used as a triage tool for risk assessment. The impacts of the model use on outcomes need further evaluation. Current Controlled Trials ISRCTN40384046. The National Institute for Health Research Health Technology Assessment programme.

Predictors of non-vertebral fracture in older Chinese males and females: Mr. OS and Ms. OS (Hong Kong).

PubMed

Kwok, Timothy Chi Yui; Su, Yi; Khoo, Chyi Chyi; Leung, Jason; Kwok, Anthony; Orwoll, Eric; Woo, Jean; Leung, Ping Chung

2017-05-01

Clinical risk factors to predict fracture are useful in guiding management of patients with osteoporosis or falls. Clinical predictors may however be population specific because of differences in lifestyle, environment and ethnicity. Four thousand community-dwelling Chinese males and females with average ages of 72.4 and 72.6 years were followed up for incident fractures, with an average of 6.5 and 8.8 years, respectively. Clinical information was collected, and bone mineral density (BMD) measurements were carried out at baseline. Stepwise Cox regression models were used to identify risk factors of nonvertebral fractures, with BMD as covariate. Areas under the receiver-operating characteristic (ROC) curve (AUC) were compared among different risk models. The incidence rates of nonvertebral fractures were 10.3 and 20.5 per 1000 person years in males and females, respectively. In males, age ≥80, history of a fall in the past year, fracture history, chronic obstructive pulmonary disease, impaired visual depth perception and low physical health-related quality of life were significant fracture risk factors, independent of BMD. In females, the significant factors were fracture history, low visual acuity and slow narrow walking speed. The clinical risk factors had a significant influence on fracture risk irrespective of osteoporosis status, even having a better risk discrimination than BMD alone, especially in males. The best risk prediction model consisted both BMD and clinical risk factors. Clinical risk factors have additive value to hip BMD in predicting nonvertebral fractures in older Chinese people and may predict them better than BMD alone in older Chinese males.

Validation of the Saskatoon Falls Prevention Consortium's Falls Screening and Referral Algorithm

PubMed Central

Lawson, Sara Nicole; Zaluski, Neal; Petrie, Amanda; Arnold, Cathy; Basran, Jenny

2013-01-01

ABSTRACT Purpose: To investigate the concurrent validity of the Saskatoon Falls Prevention Consortium's Falls Screening and Referral Algorithm (FSRA). Method: A total of 29 older adults (mean age 77.7 [SD 4.0] y) residing in an independent-living senior's complex who met inclusion criteria completed a demographic questionnaire and the components of the FSRA and Berg Balance Scale (BBS). The FSRA consists of the Elderly Fall Screening Test (EFST) and the Multi-factor Falls Questionnaire (MFQ); it is designed to categorize individuals into low, moderate, or high fall-risk categories to determine appropriate management pathways. A predictive model for probability of fall risk, based on previous research, was used to determine concurrent validity of the FSRI. Results: The FSRA placed 79% of participants into the low-risk category, whereas the predictive model found the probability of fall risk to range from 0.04 to 0.74, with a mean of 0.35 (SD 0.25). No statistically significant correlation was found between the FSRA and the predictive model for probability of fall risk (Spearman's ρ=0.35, p=0.06). Conclusion: The FSRA lacks concurrent validity relative to to a previously established model of fall risk and appears to over-categorize individuals into the low-risk group. Further research on the FSRA as an adequate tool to screen community-dwelling older adults for fall risk is recommended. PMID:24381379

Melanoma-specific mortality and competing mortality in patients with non-metastatic malignant melanoma: a population-based analysis.

PubMed

Shen, Weidong; Sakamoto, Naoko; Yang, Limin

2016-07-07

The objectives of this study were to evaluate and model the probability of melanoma-specific death and competing causes of death for patients with melanoma by competing risk analysis, and to build competing risk nomograms to provide individualized and accurate predictive tools. Melanoma data were obtained from the Surveillance Epidemiology and End Results program. All patients diagnosed with primary non-metastatic melanoma during the years 2004-2007 were potentially eligible for inclusion. The cumulative incidence function (CIF) was used to describe the probability of melanoma mortality and competing risk mortality. We used Gray's test to compare differences in CIF between groups. The proportional subdistribution hazard approach by Fine and Gray was used to model CIF. We built competing risk nomograms based on the models that we developed. The 5-year cumulative incidence of melanoma death was 7.1 %, and the cumulative incidence of other causes of death was 7.4 %. We identified that variables associated with an elevated probability of melanoma-specific mortality included older age, male sex, thick melanoma, ulcerated cancer, and positive lymph nodes. The nomograms were well calibrated. C-indexes were 0.85 and 0.83 for nomograms predicting the probability of melanoma mortality and competing risk mortality, which suggests good discriminative ability. This large study cohort enabled us to build a reliable competing risk model and nomogram for predicting melanoma prognosis. Model performance proved to be good. This individualized predictive tool can be used in clinical practice to help treatment-related decision making.

Interrelationship of Cytokines, Hypothalamic-Pituitary-Adrenal Axis Hormones, and Psychosocial Variables in the Prediction of Preterm Birth

PubMed Central

Pearce, B.D.; Grove, J.; Bonney, E.A.; Bliwise, N.; Dudley, D.J.; Schendel, D.E.; Thorsen, P.

2010-01-01

Background/Aims To examine the relationship of biological mediators (cytokines, stress hormones), psychosocial, obstetric history, and demographic factors in the early prediction of preterm birth (PTB) using a comprehensive logistic regression model incorporating diverse risk factors. Methods In this prospective case-control study, maternal serum biomarkers were quantified at 9–23 weeks’ gestation in 60 women delivering at <37 weeks compared to 123 women delivering at term. Biomarker data were combined with maternal sociodemographic factors and stress data into regression models encompassing 22 preterm risk factors and 1st-order interactions. Results Among individual biomarkers, we found that macrophage migration inhibitory factor (MIF), interleukin-10, C-reactive protein (CRP), and tumor necrosis factor-α were statistically significant predictors of PTB at all cutoff levels tested (75th, 85th, and 90th percentiles). We fit multifactor models for PTB prediction at each biomarker cutoff. Our best models revealed that MIF, CRP, risk-taking behavior, and low educational attainment were consistent predictors of PTB at all biomarker cutoffs. The 75th percentile cutoff yielded the best predicting model with an area under the ROC curve of 0.808 (95% CI 0.743–0.874). Conclusion Our comprehensive models highlight the prominence of behavioral risk factors for PTB and point to MIF as a possible psychobiological mediator. PMID:20160447

Simulated effect of pneumococcal vaccination in the Netherlands on existing rules constructed in a non-vaccinated cohort predicting sequelae after bacterial meningitis

PubMed Central

2010-01-01

Background Previously two prediction rules identifying children at risk of hearing loss and academic or behavioral limitations after bacterial meningitis were developed. Streptococcus pneumoniae as causative pathogen was an important risk factor in both. Since 2006 Dutch children receive seven-valent conjugate vaccination against S. pneumoniae. The presumed effect of vaccination was simulated by excluding all children infected by S. pneumoniae with the serotypes included in the vaccine, from both previous collected cohorts (between 1990-1995). Methods Children infected by one of the vaccine serotypes were excluded from both original cohorts (hearing loss: 70 of 628 children; academic or behavioral limitations: 26 of 182 children). All identified risk factors were included in multivariate logistic regression models. The discriminative ability of both new models was calculated. Results The same risk factors as in the original models were significant. The discriminative ability of the original hearing loss model was 0.84 and of the new model 0.87. In the academic or behavioral limitations model it was 0.83 and 0.84 respectively. Conclusion It can be assumed that the prediction rules will also be applicable on a vaccinated population. However, vaccination does not provide 100% coverage and evidence is available that serotype replacement will occur. The impact of vaccination on serotype replacement needs to be investigated, and the prediction rules must be validated externally. PMID:20815866

Interrelationship of cytokines, hypothalamic-pituitary-adrenal axis hormones, and psychosocial variables in the prediction of preterm birth.

PubMed

Pearce, B D; Grove, J; Bonney, E A; Bliwise, N; Dudley, D J; Schendel, D E; Thorsen, P

2010-01-01

To examine the relationship of biological mediators (cytokines, stress hormones), psychosocial, obstetric history, and demographic factors in the early prediction of preterm birth (PTB) using a comprehensive logistic regression model incorporating diverse risk factors. In this prospective case-control study, maternal serum biomarkers were quantified at 9-23 weeks' gestation in 60 women delivering at <37 weeks compared to 123 women delivering at term. Biomarker data were combined with maternal sociodemographic factors and stress data into regression models encompassing 22 preterm risk factors and 1st-order interactions. Among individual biomarkers, we found that macrophage migration inhibitory factor (MIF), interleukin-10, C-reactive protein (CRP), and tumor necrosis factor-alpha were statistically significant predictors of PTB at all cutoff levels tested (75th, 85th, and 90th percentiles). We fit multifactor models for PTB prediction at each biomarker cutoff. Our best models revealed that MIF, CRP, risk-taking behavior, and low educational attainment were consistent predictors of PTB at all biomarker cutoffs. The 75th percentile cutoff yielded the best predicting model with an area under the ROC curve of 0.808 (95% CI 0.743-0.874). Our comprehensive models highlight the prominence of behavioral risk factors for PTB and point to MIF as a possible psychobiological mediator. Copyright (c) 2010 S. Karger AG, Basel.

Risk of fire occurrence in arid and semi-arid ecosystems of Iran: an investigation using Bayesian belief networks.

PubMed

Bashari, Hossein; Naghipour, Ali Asghar; Khajeddin, Seyed Jamaleddin; Sangoony, Hamed; Tahmasebi, Pejman

2016-09-01

Identifying areas that have a high risk of burning is a main component of fire management planning. Although the available tools can predict the fire risks, these are poor in accommodating uncertainties in their predictions. In this study, we accommodated uncertainty in wildfire prediction using Bayesian belief networks (BBNs). An influence diagram was developed to identify the factors influencing wildfire in arid and semi-arid areas of Iran, and it was populated with probabilities to produce a BBNs model. The behavior of the model was tested using scenario and sensitivity analysis. Land cover/use, mean annual rainfall, mean annual temperature, elevation, and livestock density were recognized as the main variables determining wildfire occurrence. The produced model had good accuracy as its ROC area under the curve was 0.986. The model could be applied in both predictive and diagnostic analysis for answering "what if" and "how" questions. The probabilistic relationships within the model can be updated over time using observation and monitoring data. The wildfire BBN model may be updated as new knowledge emerges; hence, it can be used to support the process of adaptive management.

Validation of risk stratification for children with febrile neutropenia in a pediatric oncology unit in India.

PubMed

Das, Anirban; Trehan, Amita; Oberoi, Sapna; Bansal, Deepak

2017-06-01

The study aims to validate a score predicting risk of complications in pediatric patients with chemotherapy-related febrile neutropenia (FN) and evaluate the performance of previously published models for risk stratification. Children diagnosed with cancer and presenting with FN were evaluated in a prospective single-center study. A score predicting the risk of complications, previously derived in the unit, was validated on a prospective cohort. Performance of six predictive models published from geographically distinct settings was assessed on the same cohort. Complications were observed in 109 (26.3%) of 414 episodes of FN over 15 months. A risk score based on undernutrition (two points), time from last chemotherapy (<7 days = two points), presence of a nonupper respiratory focus of infection (two points), C-reactive protein (>60 mg/l = five points), and absolute neutrophil count (<100 per μl = two points) was used to stratify patients into "low risk" (score <7, n = 208) and assessed using the following parameters: overall performance (Nagelkerke R 2 = 34.4%), calibration (calibration slope = 0.39; P = 0.25 in Hosmer-Lemeshow test), discrimination (c-statistic = 0.81), overall sensitivity (86%), negative predictive value (93%), and clinical net benefit (0.43). Six previously published rules demonstrated inferior performance in this cohort. An indigenous decision rule using five simple predefined variables was successful in identifying children at risk for complications. Prediction models derived in developed nations may not be appropriate for low-middle-income settings and need to be validated before use. © 2016 Wiley Periodicals, Inc.

Usefulness of the addition of beta-2-microglobulin, cystatin C and C-reactive protein to an established risk factors model to improve mortality risk prediction in patients undergoing coronary angiography.

PubMed

Nead, Kevin T; Zhou, Margaret J; Caceres, Roxanne Diaz; Sharp, Stephen J; Wehner, Mackenzie R; Olin, Jeffrey W; Cooke, John P; Leeper, Nicholas J

2013-03-15

Evidence-based therapies are available to reduce the risk for death from cardiovascular disease, yet many patients go untreated. Novel methods are needed to identify those at highest risk for cardiovascular death. In this study, the biomarkers β2-microglobulin, cystatin C, and C-reactive protein were measured at baseline in a cohort of participants who underwent coronary angiography. Adjusted Cox proportional-hazards models were used to determine whether the biomarkers predicted all-cause and cardiovascular mortality. Additionally, improvements in risk reclassification and discrimination were evaluated by calculating the net reclassification improvement, C-index, and integrated discrimination improvement with the addition of the biomarkers to a baseline model of risk factors for cardiovascular disease and death. During a median follow-up period of 5.6 years, there were 78 deaths among 470 participants. All biomarkers independently predicted future all-cause and cardiovascular mortality. A significant improvement in risk reclassification was observed for all-cause (net reclassification improvement 35.8%, p = 0.004) and cardiovascular (net reclassification improvement 61.9%, p = 0.008) mortality compared to the baseline risk factors model. Additionally, there was significantly increased risk discrimination with C-indexes of 0.777 (change in C-index 0.057, 95% confidence interval 0.016 to 0.097) and 0.826 (change in C-index 0.071, 95% confidence interval 0.010 to 0.133) for all-cause and cardiovascular mortality, respectively. Improvements in risk discrimination were further supported using the integrated discrimination improvement index. In conclusion, this study provides evidence that β2-microglobulin, cystatin C, and C-reactive protein predict mortality and improve risk reclassification and discrimination for a high-risk cohort of patients who undergo coronary angiography. Copyright © 2013 Elsevier Inc. All rights reserved.

Epithelial–mesenchymal transition biomarkers and support vector machine guided model in preoperatively predicting regional lymph node metastasis for rectal cancer

PubMed Central

Fan, X-J; Wan, X-B; Huang, Y; Cai, H-M; Fu, X-H; Yang, Z-L; Chen, D-K; Song, S-X; Wu, P-H; Liu, Q; Wang, L; Wang, J-P

2012-01-01

Background: Current imaging modalities are inadequate in preoperatively predicting regional lymph node metastasis (RLNM) status in rectal cancer (RC). Here, we designed support vector machine (SVM) model to address this issue by integrating epithelial–mesenchymal-transition (EMT)-related biomarkers along with clinicopathological variables. Methods: Using tissue microarrays and immunohistochemistry, the EMT-related biomarkers expression was measured in 193 RC patients. Of which, 74 patients were assigned to the training set to select the robust variables for designing SVM model. The SVM model predictive value was validated in the testing set (119 patients). Results: In training set, eight variables, including six EMT-related biomarkers and two clinicopathological variables, were selected to devise SVM model. In testing set, we identified 63 patients with high risk to RLNM and 56 patients with low risk. The sensitivity, specificity and overall accuracy of SVM in predicting RLNM were 68.3%, 81.1% and 72.3%, respectively. Importantly, multivariate logistic regression analysis showed that SVM model was indeed an independent predictor of RLNM status (odds ratio, 11.536; 95% confidence interval, 4.113–32.361; P<0.0001). Conclusion: Our SVM-based model displayed moderately strong predictive power in defining the RLNM status in RC patients, providing an important approach to select RLNM high-risk subgroup for neoadjuvant chemoradiotherapy. PMID:22538975

Predictive risk mapping of West Nile virus (WNV) infection in Saskatchewan horses.

PubMed

Epp, Tasha Y; Waldner, Cheryl; Berke, Olaf

2011-07-01

The objective of this study was to develop a model using equine data from geographically limited surveillance locations to predict risk categories for West Nile virus (WNV) infection in horses in all geographic locations across the province of Saskatchewan. The province was divided geographically into low-, medium-, or high-risk categories for WNV, based on available serology information from 923 horses obtained through 4 studies of WNV infection in horse populations in Saskatchewan. Discriminant analysis was used to build models using the observed risk of WNV in horses and geographic division-specific environmental data as well as to predict the risk category for all areas, including those beyond the surveillance zones. High-risk areas were indicated by relatively lower rainfall, higher temperatures, and a lower percentage of area covered in trees, water, and wetland. These conditions were most often identified in the southwest corner of the province. Environmental conditions can be used to identify those areas that are at highest risk for WNV. Public health managers could use prediction maps, which are based on animal or human information and developed from annual early season meteorological information, to guide ongoing decisions about when and where to focus intervention strategies for WNV.

Risk Factors Analysis and Death Prediction in Some Life-Threatening Ailments Using Chi-Square Case-Based Reasoning (χ2 CBR) Model.

PubMed

Adeniyi, D A; Wei, Z; Yang, Y

2018-01-30

A wealth of data are available within the health care system, however, effective analysis tools for exploring the hidden patterns in these datasets are lacking. To alleviate this limitation, this paper proposes a simple but promising hybrid predictive model by suitably combining the Chi-square distance measurement with case-based reasoning technique. The study presents the realization of an automated risk calculator and death prediction in some life-threatening ailments using Chi-square case-based reasoning (χ 2 CBR) model. The proposed predictive engine is capable of reducing runtime and speeds up execution process through the use of critical χ 2 distribution value. This work also showcases the development of a novel feature selection method referred to as frequent item based rule (FIBR) method. This FIBR method is used for selecting the best feature for the proposed χ 2 CBR model at the preprocessing stage of the predictive procedures. The implementation of the proposed risk calculator is achieved through the use of an in-house developed PHP program experimented with XAMP/Apache HTTP server as hosting server. The process of data acquisition and case-based development is implemented using the MySQL application. Performance comparison between our system, the NBY, the ED-KNN, the ANN, the SVM, the Random Forest and the traditional CBR techniques shows that the quality of predictions produced by our system outperformed the baseline methods studied. The result of our experiment shows that the precision rate and predictive quality of our system in most cases are equal to or greater than 70%. Our result also shows that the proposed system executes faster than the baseline methods studied. Therefore, the proposed risk calculator is capable of providing useful, consistent, faster, accurate and efficient risk level prediction to both the patients and the physicians at any time, online and on a real-time basis.

Validation of variants in SLC28A3 and UGT1A6 as genetic markers predictive of anthracycline-induced cardiotoxicity in children.

PubMed

Visscher, H; Ross, C J D; Rassekh, S R; Sandor, G S S; Caron, H N; van Dalen, E C; Kremer, L C; van der Pal, H J; Rogers, P C; Rieder, M J; Carleton, B C; Hayden, M R

2013-08-01

The use of anthracyclines as effective antineoplastic drugs is limited by the occurrence of cardiotoxicity. Multiple genetic variants predictive of anthracycline-induced cardiotoxicity (ACT) in children were recently identified. The current study was aimed to assess replication of these findings in an independent cohort of children. . Twenty-three variants were tested for association with ACT in an independent cohort of 218 patients. Predictive models including genetic and clinical risk factors were constructed in the original cohort and assessed in the current replication cohort. . We confirmed the association of rs17863783 in UGT1A6 and ACT in the replication cohort (P = 0.0062, odds ratio (OR) 7.98). Additional evidence for association of rs7853758 (P = 0.058, OR 0.46) and rs885004 (P = 0.058, OR 0.42) in SLC28A3 was found (combined P = 1.6 × 10(-5) and P = 3.0 × 10(-5), respectively). A previously constructed prediction model did not significantly improve risk prediction in the replication cohort over clinical factors alone. However, an improved prediction model constructed using replicated genetic variants as well as clinical factors discriminated significantly better between cases and controls than clinical factors alone in both original (AUC 0.77 vs. 0.68, P = 0.0031) and replication cohort (AUC 0.77 vs. 0.69, P = 0.060). . We validated genetic variants in two genes predictive of ACT in an independent cohort. A prediction model combining replicated genetic variants as well as clinical risk factors might be able to identify high- and low-risk patients who could benefit from alternative treatment options. Copyright © 2013 Wiley Periodicals, Inc.

Common polygenic variation enhances risk prediction for Alzheimer’s disease

PubMed Central

Sims, Rebecca; Bannister, Christian; Harold, Denise; Vronskaya, Maria; Majounie, Elisa; Badarinarayan, Nandini; Morgan, Kevin; Passmore, Peter; Holmes, Clive; Powell, John; Brayne, Carol; Gill, Michael; Mead, Simon; Goate, Alison; Cruchaga, Carlos; Lambert, Jean-Charles; van Duijn, Cornelia; Maier, Wolfgang; Ramirez, Alfredo; Holmans, Peter; Jones, Lesley; Hardy, John; Seshadri, Sudha; Schellenberg, Gerard D.; Amouyel, Philippe

2015-01-01

The identification of subjects at high risk for Alzheimer’s disease is important for prognosis and early intervention. We investigated the polygenic architecture of Alzheimer’s disease and the accuracy of Alzheimer’s disease prediction models, including and excluding the polygenic component in the model. This study used genotype data from the powerful dataset comprising 17 008 cases and 37 154 controls obtained from the International Genomics of Alzheimer’s Project (IGAP). Polygenic score analysis tested whether the alleles identified to associate with disease in one sample set were significantly enriched in the cases relative to the controls in an independent sample. The disease prediction accuracy was investigated in a subset of the IGAP data, a sample of 3049 cases and 1554 controls (for whom APOE genotype data were available) by means of sensitivity, specificity, area under the receiver operating characteristic curve (AUC) and positive and negative predictive values. We observed significant evidence for a polygenic component enriched in Alzheimer’s disease (P = 4.9 × 10−26). This enrichment remained significant after APOE and other genome-wide associated regions were excluded (P = 3.4 × 10−19). The best prediction accuracy AUC = 78.2% (95% confidence interval 77–80%) was achieved by a logistic regression model with APOE, the polygenic score, sex and age as predictors. In conclusion, Alzheimer’s disease has a significant polygenic component, which has predictive utility for Alzheimer’s disease risk and could be a valuable research tool complementing experimental designs, including preventative clinical trials, stem cell selection and high/low risk clinical studies. In modelling a range of sample disease prevalences, we found that polygenic scores almost doubles case prediction from chance with increased prediction at polygenic extremes. PMID:26490334

Evaluating predictive modeling’s potential to improve teleretinal screening participation in urban safety net clinics

PubMed Central

Ogunyemi, Omolola; Teklehaimanot, Senait; Patty, Lauren; Moran, Erin; George, Sheba

2013-01-01

Introduction Screening guidelines for diabetic patients recommend yearly eye examinations to detect diabetic retinopathy and other forms of diabetic eye disease. However, annual screening rates for retinopathy in US urban safety net settings remain low. Methods Using data gathered from a study of teleretinal screening in six urban safety net clinics, we assessed whether predictive modeling could be of value in identifying patients at risk of developing retinopathy. We developed and examined the accuracy of two predictive modeling approaches for diabetic retinopathy in a sample of 513 diabetic individuals, using routinely available clinical variables from retrospective medical record reviews. Bayesian networks and radial basis function (neural) networks were learned using ten-fold cross-validation. Results The predictive models were modestly predictive with the best model having an AUC of 0.71. Discussion Using routinely available clinical variables to predict patients at risk of developing retinopathy and to target them for annual eye screenings may be of some usefulness to safety net clinics. PMID:23920536

Geographic Profiling to Assess the Risk of Rare Plant Poaching in Natural Areas

NASA Astrophysics Data System (ADS)

Young, John A.; van Manen, Frank T.; Thatcher, Cindy A.

2011-09-01

We demonstrate the use of an expert-assisted spatial model to examine geographic factors influencing the poaching risk of a rare plant (American ginseng, Panax quinquefolius L.) in Shenandoah National Park, Virginia, USA. Following principles of the analytic hierarchy process (AHP), we identified a hierarchy of 11 geographic factors deemed important to poaching risk and requested law enforcement personnel of the National Park Service to rank those factors in a series of pair-wise comparisons. We used those comparisons to determine statistical weightings of each factor and combined them into a spatial model predicting poaching risk. We tested the model using 69 locations of previous poaching incidents recorded by law enforcement personnel. These locations occurred more frequently in areas predicted by the model to have a higher risk of poaching than random locations. The results of our study can be used to evaluate resource protection strategies and to target law enforcement activities.

Modeling Success: Using Preenrollment Data to Identify Academically At-Risk Students

ERIC Educational Resources Information Center

Gansemer-Topf, Ann M.; Compton, Jonathan; Wohlgemuth, Darin; Forbes, Greg; Ralston, Ekaterina

2015-01-01

Improving student success and degree completion is one of the core principles of strategic enrollment management. To address this principle, institutional data were used to develop a statistical model to identify academically at-risk students. The model employs multiple linear regression techniques to predict students at risk of earning below a…

Spatial model for risk prediction and sub-national prioritization to aid poliovirus eradication in Pakistan.

PubMed

Mercer, Laina D; Safdar, Rana M; Ahmed, Jamal; Mahamud, Abdirahman; Khan, M Muzaffar; Gerber, Sue; O'Leary, Aiden; Ryan, Mike; Salet, Frank; Kroiss, Steve J; Lyons, Hil; Upfill-Brown, Alexander; Chabot-Couture, Guillaume

2017-10-11

Pakistan is one of only three countries where poliovirus circulation remains endemic. For the Pakistan Polio Eradication Program, identifying high risk districts is essential to target interventions and allocate limited resources. Using a hierarchical Bayesian framework we developed a spatial Poisson hurdle model to jointly model the probability of one or more paralytic polio cases, and the number of cases that would be detected in the event of an outbreak. Rates of underimmunization, routine immunization, and population immunity, as well as seasonality and a history of cases were used to project future risk of cases. The expected number of cases in each district in a 6-month period was predicted using indicators from the previous 6-months and the estimated coefficients from the model. The model achieves an average of 90% predictive accuracy as measured by area under the receiver operating characteristic (ROC) curve, for the past 3 years of cases. The risk of poliovirus has decreased dramatically in many of the key reservoir areas in Pakistan. The results of this model have been used to prioritize sub-national areas in Pakistan to receive additional immunization activities, additional monitoring, or other special interventions.

Surrogate modeling of joint flood risk across coastal watersheds

NASA Astrophysics Data System (ADS)

Bass, Benjamin; Bedient, Philip

2018-03-01

This study discusses the development and performance of a rapid prediction system capable of representing the joint rainfall-runoff and storm surge flood response of tropical cyclones (TCs) for probabilistic risk analysis. Due to the computational demand required for accurately representing storm surge with the high-fidelity ADvanced CIRCulation (ADCIRC) hydrodynamic model and its coupling with additional numerical models to represent rainfall-runoff, a surrogate or statistical model was trained to represent the relationship between hurricane wind- and pressure-field characteristics and their peak joint flood response typically determined from physics based numerical models. This builds upon past studies that have only evaluated surrogate models for predicting peak surge, and provides the first system capable of probabilistically representing joint flood levels from TCs. The utility of this joint flood prediction system is then demonstrated by improving upon probabilistic TC flood risk products, which currently account for storm surge but do not take into account TC associated rainfall-runoff. Results demonstrate the source apportionment of rainfall-runoff versus storm surge and highlight that slight increases in flood risk levels may occur due to the interaction between rainfall-runoff and storm surge as compared to the Federal Emergency Management Association's (FEMAs) current practices.

Can shoulder dystocia be reliably predicted?

PubMed

Dodd, Jodie M; Catcheside, Britt; Scheil, Wendy

2012-06-01

To evaluate factors reported to increase the risk of shoulder dystocia, and to evaluate their predictive value at a population level. The South Australian Pregnancy Outcome Unit's population database from 2005 to 2010 was accessed to determine the occurrence of shoulder dystocia in addition to reported risk factors, including age, parity, self-reported ethnicity, presence of diabetes and infant birth weight. Odds ratios (and 95% confidence interval) of shoulder dystocia was calculated for each risk factor, which were then incorporated into a logistic regression model. Test characteristics for each variable in predicting shoulder dystocia were calculated. As a proportion of all births, the reported rate of shoulder dystocia increased significantly from 0.95% in 2005 to 1.38% in 2010 (P = 0.0002). Using a logistic regression model, induction of labour and infant birth weight greater than both 4000 and 4500 g were identified as significant independent predictors of shoulder dystocia. The value of risk factors alone and when incorporated into the logistic regression model was poorly predictive of the occurrence of shoulder dystocia. While there are a number of factors associated with an increased risk of shoulder dystocia, none are of sufficient sensitivity or positive predictive value to allow their use clinically to reliably and accurately identify the occurrence of shoulder dystocia. © 2012 The Authors ANZJOG © 2012 The Royal Australian and New Zealand College of Obstetricians and Gynaecologists.

Applying the Seattle Heart Failure Model in the Office Setting in the Era of Electronic Medical Records.

PubMed

Williams, Brent A; Agarwal, Shikhar

2018-02-23

Prediction models such as the Seattle Heart Failure Model (SHFM) can help guide management of heart failure (HF) patients, but the SHFM has not been validated in the office environment. This retrospective cohort study assessed the predictive performance of the SHFM among patients with new or pre-existing HF in the context of an office visit.Methods and Results:SHFM elements were ascertained through electronic medical records at an office visit. The primary outcome was all-cause mortality. A "warranty period" for the baseline SHFM risk estimate was sought by examining predictive performance over time through a series of landmark analyses. Discrimination and calibration were estimated according to the proposed warranty period. Low- and high-risk thresholds were proposed based on the distribution of SHFM estimates. Among 26,851 HF patients, 14,380 (54%) died over a mean 4.7-year follow-up period. The SHFM lost predictive performance over time, with C=0.69 and C<0.65 within 3 and beyond 12 months from baseline respectively. The diminishing predictive value was attributed to modifiable SHFM elements. Discrimination (C=0.66) and calibration for 12-month mortality were acceptable. A low-risk threshold of ∼5% mortality risk within 12 months reflects the 10% of HF patients in the office setting with the lowest risk. The SHFM has utility in the office environment.

Does consideration of either psychological or material disadvantage improve coronary risk prediction? Prospective observational study of Scottish men.

PubMed

Macleod, John; Metcalfe, Chris; Smith, George Davey; Hart, Carole

2007-09-01

To assess the value of psychosocial risk factors in discriminating between individuals at higher and lower risk of coronary heart disease, using risk prediction equations. Prospective observational study. Scotland. 5191 employed men aged 35 to 64 years and free of coronary heart disease at study enrollment Area under receiver operating characteristic (ROC) curves for risk prediction equations including different risk factors for coronary heart disease. During the first 10 years of follow up, 203 men died of coronary heart disease and a further 200 were admitted to hospital with this diagnosis. Area under the ROC curve for the standard Framingham coronary risk factors was 74.5%. Addition of "vital exhaustion" and psychological stress led to areas under the ROC curve of 74.5% and 74.6%, respectively. Addition of current social class and lifetime social class to the standard Framingham equation gave areas under the ROC curve of 74.6% and 74.9%, respectively. In no case was there strong evidence for improved discrimination of the model containing the novel risk factor over the standard model. Consideration of psychosocial risk factors, including those that are strong independent predictors of heart disease, does not substantially influence the ability of risk prediction tools to discriminate between individuals at higher and lower risk of coronary heart disease.

Predicting preterm birth among participants of North Carolina’s Pregnancy Medical Home Program

PubMed Central

Tucker, Christine M.; Berrien, Kate; Menard, M. Kathryn; Herring, Amy H.; Daniels, Julie; Rowley, Diane L.; Halpern, Carolyn Tucker

2016-01-01

Objective To determine which combination of risk factors from Community Care of North Carolina’s (CCNC) Pregnancy Medical Home (PMH) risk screening form was most predictive of preterm birth (PTB) by parity and race/ethnicity. Methods This retrospective cohort included pregnant Medicaid patients screened by the PMH program before 24 weeks gestation who delivered a live birth in North Carolina between September 2011-September 2012 (N=15,428). Data came from CCNC’s Case Management Information System, Medicaid claims, and birth certificates. Logistic regression with backward stepwise elimination was used to arrive at the final models. To internally validate the predictive model, we used bootstrapping techniques. Results The prevalence of PTB was 11%. Multifetal gestation, a previous PTB, cervical insufficiency, diabetes, renal disease, and hypertension were the strongest risk factors with odds ratios ranging from 2.34 to 10.78. Non-Hispanic black race, underweight, smoking during pregnancy, asthma, other chronic conditions, nulliparity, and a history of a low birth weight infant or fetal death/second trimester loss were additional predictors in the final predictive model. About half of the risk factors prioritized by the PMH program remained in our final model (ROC=0.66). The odds of PTB associated with food insecurity and obesity differed by parity. The influence of unsafe or unstable housing and short interpregnancy interval on PTB differed by race/ethnicity. Conclusions Evaluation of the PMH risk screen provides insight to ensure women at highest risk are prioritized for care management. Using multiple data sources, salient risk factors for PTB were identified, allowing for better-targeted approaches for PTB prevention. PMID:26112751

Empirically Based Composite Fracture Prediction Model From the Global Longitudinal Study of Osteoporosis in Postmenopausal Women (GLOW)

PubMed Central

Compston, Juliet E.; Chapurlat, Roland D.; Pfeilschifter, Johannes; Cooper, Cyrus; Hosmer, David W.; Adachi, Jonathan D.; Anderson, Frederick A.; Díez-Pérez, Adolfo; Greenspan, Susan L.; Netelenbos, J. Coen; Nieves, Jeri W.; Rossini, Maurizio; Watts, Nelson B.; Hooven, Frederick H.; LaCroix, Andrea Z.; March, Lyn; Roux, Christian; Saag, Kenneth G.; Siris, Ethel S.; Silverman, Stuart; Gehlbach, Stephen H.

2014-01-01

Context: Several fracture prediction models that combine fractures at different sites into a composite outcome are in current use. However, to the extent individual fracture sites have differing risk factor profiles, model discrimination is impaired. Objective: The objective of the study was to improve model discrimination by developing a 5-year composite fracture prediction model for fracture sites that display similar risk profiles. Design: This was a prospective, observational cohort study. Setting: The study was conducted at primary care practices in 10 countries. Patients: Women aged 55 years or older participated in the study. Intervention: Self-administered questionnaires collected data on patient characteristics, fracture risk factors, and previous fractures. Main Outcome Measure: The main outcome is time to first clinical fracture of hip, pelvis, upper leg, clavicle, or spine, each of which exhibits a strong association with advanced age. Results: Of four composite fracture models considered, model discrimination (c index) is highest for an age-related fracture model (c index of 0.75, 47 066 women), and lowest for Fracture Risk Assessment Tool (FRAX) major fracture and a 10-site model (c indices of 0.67 and 0.65). The unadjusted increase in fracture risk for an additional 10 years of age ranges from 80% to 180% for the individual bones in the age-associated model. Five other fracture sites not considered for the age-associated model (upper arm/shoulder, rib, wrist, lower leg, and ankle) have age associations for an additional 10 years of age from a 10% decrease to a 60% increase. Conclusions: After examining results for 10 different bone fracture sites, advanced age appeared the single best possibility for uniting several different sites, resulting in an empirically based composite fracture risk model. PMID:24423345

Gastro-esophageal reflux disease symptoms and demographic factors as a pre-screening tool for Barrett's esophagus.

PubMed

Liu, Xinxue; Wong, Angela; Kadri, Sudarshan R; Corovic, Andrej; O'Donovan, Maria; Lao-Sirieix, Pierre; Lovat, Laurence B; Burnham, Rodney W; Fitzgerald, Rebecca C

2014-01-01

Barrett's esophagus (BE) occurs as consequence of reflux and is a risk factor for esophageal adenocarcinoma. The current "gold-standard" for diagnosing BE is endoscopy which remains prohibitively expensive and impractical as a population screening tool. We aimed to develop a pre-screening tool to aid decision making for diagnostic referrals. A prospective (training) cohort of 1603 patients attending for endoscopy was used for identification of risk factors to develop a risk prediction model. Factors associated with BE in the univariate analysis were selected to develop prediction models that were validated in an independent, external cohort of 477 non-BE patients referred for endoscopy with symptoms of reflux or dyspepsia. Two prediction models were developed separately for columnar lined epithelium (CLE) of any length and using a stricter definition of intestinal metaplasia (IM) with segments ≥ 2 cm with areas under the ROC curves (AUC) of 0.72 (95%CI: 0.67-0.77) and 0.81 (95%CI: 0.76-0.86), respectively. The two prediction models included demographics (age, sex), symptoms (heartburn, acid reflux, chest pain, abdominal pain) and medication for "stomach" symptoms. These two models were validated in the independent cohort with AUCs of 0.61 (95%CI: 0.54-0.68) and 0.64 (95%CI: 0.52-0.77) for CLE and IM ≥ 2 cm, respectively. We have identified and validated two prediction models for CLE and IM ≥ 2 cm. Both models have fair prediction accuracies and can select out around 20% of individuals unlikely to benefit from investigation for Barrett's esophagus. Such prediction models have the potential to generate useful cost-savings for BE screening among the symptomatic population.

A risk tertiles model for predicting mortality in patients with acute respiratory distress syndrome: age, plateau pressure, and P(aO(2))/F(IO(2)) at ARDS onset can predict mortality.

PubMed

Villar, Jesús; Pérez-Méndez, Lina; Basaldúa, Santiago; Blanco, Jesús; Aguilar, Gerardo; Toral, Darío; Zavala, Elizabeth; Romera, Miguel A; González-Díaz, Gumersindo; Nogal, Frutos Del; Santos-Bouza, Antonio; Ramos, Luís; Macías, Santiago; Kacmarek, Robert M

2011-04-01

Predicting mortality has become a necessary step for selecting patients for clinical trials and defining outcomes. We examined whether stratification by tertiles of respiratory and ventilatory variables at the onset of acute respiratory distress syndrome (ARDS) identifies patients with different risks of death in the intensive care unit. We performed a secondary analysis of data from 220 patients included in 2 multicenter prospective independent trials of ARDS patients mechanically ventilated with a lung-protective strategy. Using demographic, pulmonary, and ventilation data collected at ARDS onset, we derived and validated a simple prediction model based on a population-based stratification of variable values into low, middle, and high tertiles. The derivation cohort included 170 patients (all from one trial) and the validation cohort included 50 patients (all from a second trial). Tertile distribution for age, plateau airway pressure (P(plat)), and P(aO(2))/F(IO(2)) at ARDS onset identified subgroups with different mortalities, particularly for the highest-risk tertiles: age (> 62 years), P(plat) (> 29 cm H(2)O), and P(aO(2))/F(IO(2)) (< 112 mm Hg). Risk was defined by the number of coexisting high-risk tertiles: patients with no high-risk tertiles had a mortality of 12%, whereas patients with 3 high-risk tertiles had 90% mortality (P < .001). A prediction model based on tertiles of patient age, P(plat), and P(aO(2))/F(IO(2)) at the time the patient meets ARDS criteria identifies patients with the lowest and highest risk of intensive care unit death.

External validation of risk prediction models for incident colorectal cancer using UK Biobank

PubMed Central

Usher-Smith, J A; Harshfield, A; Saunders, C L; Sharp, S J; Emery, J; Walter, F M; Muir, K; Griffin, S J

2018-01-01

Background: This study aimed to compare and externally validate risk scores developed to predict incident colorectal cancer (CRC) that include variables routinely available or easily obtainable via self-completed questionnaire. Methods: External validation of fourteen risk models from a previous systematic review in 373 112 men and women within the UK Biobank cohort with 5-year follow-up, no prior history of CRC and data for incidence of CRC through linkage to national cancer registries. Results: There were 1719 (0.46%) cases of incident CRC. The performance of the risk models varied substantially. In men, the QCancer10 model and models by Tao, Driver and Ma all had an area under the receiver operating characteristic curve (AUC) between 0.67 and 0.70. Discrimination was lower in women: the QCancer10, Wells, Tao, Guesmi and Ma models were the best performing with AUCs between 0.63 and 0.66. Assessment of calibration was possible for six models in men and women. All would require country-specific recalibration if estimates of absolute risks were to be given to individuals. Conclusions: Several risk models based on easily obtainable data have relatively good discrimination in a UK population. Modelling studies are now required to estimate the potential health benefits and cost-effectiveness of implementing stratified risk-based CRC screening. PMID:29381683

A mathematical prediction model incorporating molecular subtype for risk of non-sentinel lymph node metastasis in sentinel lymph node-positive breast cancer patients: a retrospective analysis and nomogram development.

PubMed

Wang, Na-Na; Yang, Zheng-Jun; Wang, Xue; Chen, Li-Xuan; Zhao, Hong-Meng; Cao, Wen-Feng; Zhang, Bin

2018-04-25

Molecular subtype of breast cancer is associated with sentinel lymph node status. We sought to establish a mathematical prediction model that included breast cancer molecular subtype for risk of positive non-sentinel lymph nodes in breast cancer patients with sentinel lymph node metastasis and further validate the model in a separate validation cohort. We reviewed the clinicopathologic data of breast cancer patients with sentinel lymph node metastasis who underwent axillary lymph node dissection between June 16, 2014 and November 16, 2017 at our hospital. Sentinel lymph node biopsy was performed and patients with pathologically proven sentinel lymph node metastasis underwent axillary lymph node dissection. Independent risks for non-sentinel lymph node metastasis were assessed in a training cohort by multivariate analysis and incorporated into a mathematical prediction model. The model was further validated in a separate validation cohort, and a nomogram was developed and evaluated for diagnostic performance in predicting the risk of non-sentinel lymph node metastasis. Moreover, we assessed the performance of five different models in predicting non-sentinel lymph node metastasis in training cohort. Totally, 495 cases were eligible for the study, including 291 patients in the training cohort and 204 in the validation cohort. Non-sentinel lymph node metastasis was observed in 33.3% (97/291) patients in the training cohort. The AUC of MSKCC, Tenon, MDA, Ljubljana, and Louisville models in training cohort were 0.7613, 0.7142, 0.7076, 0.7483, and 0.671, respectively. Multivariate regression analysis indicated that tumor size (OR = 1.439; 95% CI 1.025-2.021; P = 0.036), sentinel lymph node macro-metastasis versus micro-metastasis (OR = 5.063; 95% CI 1.111-23.074; P = 0.036), the number of positive sentinel lymph nodes (OR = 2.583, 95% CI 1.714-3.892; P < 0.001), and the number of negative sentinel lymph nodes (OR = 0.686, 95% CI 0.575-0.817; P < 0.001) were independent statistically significant predictors of non-sentinel lymph node metastasis. Furthermore, luminal B (OR = 3.311, 95% CI 1.593-6.884; P = 0.001) and HER2 overexpression (OR = 4.308, 95% CI 1.097-16.912; P = 0.036) were independent and statistically significant predictor of non-sentinel lymph node metastasis versus luminal A. A regression model based on the results of multivariate analysis was established to predict the risk of non-sentinel lymph node metastasis, which had an AUC of 0.8188. The model was validated in the validation cohort and showed excellent diagnostic performance. The mathematical prediction model that incorporates five variables including breast cancer molecular subtype demonstrates excellent diagnostic performance in assessing the risk of non-sentinel lymph node metastasis in sentinel lymph node-positive patients. The prediction model could be of help surgeons in evaluating the risk of non-sentinel lymph node involvement for breast cancer patients; however, the model requires further validation in prospective studies.

Comparison of risk scores for the prediction of stroke in African Americans: Findings from the Jackson Heart Study.

PubMed

Foraker, Randi E; Greiner, Melissa; Sims, Mario; Tucker, Katherine L; Towfighi, Amytis; Bidulescu, Aurelian; Shoben, Abigail B; Smith, Sakima; Talegawkar, Sameera; Blackshear, Chad; Wang, Wei; Hardy, Natalie Chantelle; O'Brien, Emily

2016-07-01

Evidence from existing cohort studies supports the prediction of incident coronary heart disease and stroke using 10-year cardiovascular disease (CVD) risk scores and the American Heart Association/American Stroke Association's cardiovascular health (CVH) metric. We included all Jackson Heart Study participants with complete scoring information at the baseline study visit (2000-2004) who had no history of stroke (n = 4,140). We used Kaplan-Meier methods to calculate the cumulative incidence of stroke and used Cox models to estimate hazard ratios and 95% CIs for stroke according to CVD risk and CVH score. We compared the discrimination of the 2 models according to the Harrell c index and plotted predicted vs observed stroke risk calibration plots for each of the 2 models. The median age of the African American participants was 54.5 years, and 65% were female. The cumulative incidence of stroke increased across worsening categories of CVD risk and CVH. A 1-unit increase in CVD risk increased the hazard of stroke (1.07, 1.06-1.08), whereas each 1-unit increase in CVH corresponded to a decreased hazard of stroke (0.76, 0.69-0.83). As evidenced by the c statistics, the CVH model was less discriminating than the CVD risk model (0.59 [0.55-0.64] vs 0.79 [0.76-0.83]). Both scores were associated with incident stroke in a dose-response fashion; however, the CVD risk model was more discriminating than the CVH model. The CVH score may still be preferable for its simplicity in application to broad patient populations and public health efforts. Copyright © 2016 Elsevier Inc. All rights reserved.

Development, Validation and Deployment of a Real Time 30 Day Hospital Readmission Risk Assessment Tool in the Maine Healthcare Information Exchange.

PubMed

Hao, Shiying; Wang, Yue; Jin, Bo; Shin, Andrew Young; Zhu, Chunqing; Huang, Min; Zheng, Le; Luo, Jin; Hu, Zhongkai; Fu, Changlin; Dai, Dorothy; Wang, Yicheng; Culver, Devore S; Alfreds, Shaun T; Rogow, Todd; Stearns, Frank; Sylvester, Karl G; Widen, Eric; Ling, Xuefeng B

2015-01-01

Identifying patients at risk of a 30-day readmission can help providers design interventions, and provide targeted care to improve clinical effectiveness. This study developed a risk model to predict a 30-day inpatient hospital readmission for patients in Maine, across all payers, all diseases and all demographic groups. Our objective was to develop a model to determine the risk for inpatient hospital readmission within 30 days post discharge. All patients within the Maine Health Information Exchange (HIE) system were included. The model was retrospectively developed on inpatient encounters between January 1, 2012 to December 31, 2012 from 24 randomly chosen hospitals, and then prospectively validated on inpatient encounters from January 1, 2013 to December 31, 2013 using all HIE patients. A risk assessment tool partitioned the entire HIE population into subgroups that corresponded to probability of hospital readmission as determined by a corresponding positive predictive value (PPV). An overall model c-statistic of 0.72 was achieved. The total 30-day readmission rates in low (score of 0-30), intermediate (score of 30-70) and high (score of 70-100) risk groupings were 8.67%, 24.10% and 74.10%, respectively. A time to event analysis revealed the higher risk groups readmitted to a hospital earlier than the lower risk groups. Six high-risk patient subgroup patterns were revealed through unsupervised clustering. Our model was successfully integrated into the statewide HIE to identify patient readmission risk upon admission and daily during hospitalization or for 30 days subsequently, providing daily risk score updates. The risk model was validated as an effective tool for predicting 30-day readmissions for patients across all payer, disease and demographic groups within the Maine HIE. Exposing the key clinical, demographic and utilization profiles driving each patient's risk of readmission score may be useful to providers in developing individualized post discharge care plans.

Validation of the 2014 European Society of Cardiology guidelines risk prediction model for the primary prevention of sudden cardiac death in hypertrophic cardiomyopathy.

PubMed

Vriesendorp, Pieter A; Schinkel, Arend F L; Liebregts, Max; Theuns, Dominic A M J; van Cleemput, Johan; Ten Cate, Folkert J; Willems, Rik; Michels, Michelle

2015-08-01

The recently released 2014 European Society of Cardiology guidelines of hypertrophic cardiomyopathy (HCM) use a new clinical risk prediction model for sudden cardiac death (SCD), based on the HCM Risk-SCD study. Our study is the first external and independent validation of this new risk prediction model. The study population consisted of a consecutive cohort of 706 patients with HCM without prior SCD event, from 2 tertiary referral centers. The primary end point was a composite of SCD and appropriate implantable cardioverter-defibrillator therapy, identical to the HCM Risk-SCD end point. The 5-year SCD risk was calculated using the HCM Risk-SCD formula. Receiver operating characteristic curves and C-statistics were calculated for the 2014 European Society of Cardiology guidelines, and risk stratification methods of the 2003 American College of Cardiology/European Society of Cardiology guidelines and 2011 American College of Cardiology Foundation/American Heart Association guidelines. During follow-up of 7.7±5.3 years, SCD occurred in 42 (5.9%) of 706 patients (ages 49±16 years; 34% women). The C-statistic of the new model was 0.69 (95% CI, 0.57-0.82; P=0.008), which performed significantly better than the conventional risk factor models based on the 2003 guidelines (C-statistic of 0.55: 95% CI, 0.47-0.63; P=0.3), and 2011 guidelines (C-statistic of 0.60: 95% CI, 0.50-0.70; P=0.07). The HCM Risk-SCD model improves the risk stratification of patients with HCM for primary prevention of SCD, and calculating an individual risk estimate contributes to the clinical decision-making process. Improved risk stratification is important for the decision making before implantable cardioverter-defibrillator implantation for the primary prevention of SCD. © 2015 American Heart Association, Inc.

J Waves for Predicting Cardiac Events in Hypertrophic Cardiomyopathy.

PubMed

Tsuda, Toyonobu; Hayashi, Kenshi; Konno, Tetsuo; Sakata, Kenji; Fujita, Takashi; Hodatsu, Akihiko; Nagata, Yoji; Teramoto, Ryota; Nomura, Akihiro; Tanaka, Yoshihiro; Furusho, Hiroshi; Takamura, Masayuki; Kawashiri, Masa-Aki; Fujino, Noboru; Yamagishi, Masakazu

2017-10-01

This study sought to investigate whether the presence of J waves was associated with cardiac events in patients with hypertrophic cardiomyopathy (HCM). It has been uncertain whether the presence of J waves predicts life-threatening cardiac events in patients with HCM. This study evaluated consecutive 338 patients with HCM (207 men; age 61 ± 17 years of age). A J-wave was defined as J-point elevation >0.1 mV in at least 2 contiguous inferior and/or lateral leads. Cardiac events were defined as sudden cardiac death, ventricular fibrillation or sustained ventricular tachycardia, or appropriate implantable cardiac defibrillator therapy. The study also investigated whether adding the J-wave in a conventional risk model improved a prediction of cardiac events. J waves were seen in 46 (13.6%) patients at registration. Cardiac events occurred in 31 patients (9.2%) during median follow-up of 4.9 years (interquartile range: 2.6 to 7.1 years). In a Cox proportional hazards model, the presence of J waves was significantly associated with cardiac events (adjusted hazard ratio: 4.01; 95% confidence interval [CI]: 1.78 to 9.05; p = 0.001). Compared with the conventional risk model, the model using J waves in addition to conventional risks better predicted cardiac events (net reclassification improvement, 0.55; 95% CI: 0.20 to 0.90; p = 0.002). The presence of J waves was significantly associated with cardiac events in HCM. Adding J waves to conventional cardiac risk factors improved prediction of cardiac events. Further confirmatory studies are needed before considering J-point elevation as a marker of risk for use in making management decisions regarding risk in patients with HCM. Copyright © 2017 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.

California Community College Administrators' Use of Predictive Modeling to Improve Student Course Completions

ERIC Educational Resources Information Center

Grogan, Rita D.

2017-01-01

Purpose: The purpose of this case study was to determine the impact of utilizing predictive modeling to improve successful course completion rates for at-risk students at California community colleges. A secondary purpose of the study was to identify factors of predictive modeling that have the most importance for improving successful course…

Prognostic Value of the Thrombolysis in Myocardial Infarction Risk Score in ST-Elevation Myocardial Infarction Patients With Left Ventricular Dysfunction (from the EPHESUS Trial).

PubMed

Popovic, Batric; Girerd, Nicolas; Rossignol, Patrick; Agrinier, Nelly; Camenzind, Edoardo; Fay, Renaud; Pitt, Bertram; Zannad, Faiez

2016-11-15

The Thrombolysis in Myocardial Infarction (TIMI) risk score remains a robust prediction tool for short-term and midterm outcome in the patients with ST-elevation myocardial infarction (STEMI). However, the validity of this risk score in patients with STEMI with reduced left ventricular ejection fraction (LVEF) remains unclear. A total of 2,854 patients with STEMI with early coronary revascularization participating in the randomized EPHESUS (Epleronone Post-Acute Myocardial Infarction Heart Failure Efficacy and Survival Study) trial were analyzed. TIMI risk score was calculated at baseline, and its predictive value was evaluated using C-indexes from Cox models. The increase in reclassification of other variables in addition to TIMI score was assessed using the net reclassification index. TIMI risk score had a poor predictive accuracy for all-cause mortality (C-index values at 30 days and 1 year ≤0.67) and recurrent myocardial infarction (MI; C-index values ≤0.60). Among TIMI score items, diabetes/hypertension/angina, heart rate >100 beats/min, and systolic blood pressure <100 mm Hg were inconsistently associated with survival, whereas none of the TIMI score items, aside from age, were significantly associated with MI recurrence. Using a constructed predictive model, lower LVEF, lower estimated glomerular filtration rate (eGFR), and previous MI were significantly associated with all-cause mortality. The predictive accuracy of this model, which included LVEF and eGFR, was fair for both 30-day and 1-year all-cause mortality (C-index values ranging from 0.71 to 0.75). In conclusion, TIMI risk score demonstrates poor discrimination in predicting mortality or recurrent MI in patients with STEMI with reduced LVEF. LVEF and eGFR are major factors that should not be ignored by predictive risk scores in this population. Copyright © 2016 Elsevier Inc. All rights reserved.

Comparative and Predictive Multimedia Assessments Using Monte Carlo Uncertainty Analyses

NASA Astrophysics Data System (ADS)

Whelan, G.

2002-05-01

Multiple-pathway frameworks (sometimes referred to as multimedia models) provide a platform for combining medium-specific environmental models and databases, such that they can be utilized in a more holistic assessment of contaminant fate and transport in the environment. These frameworks provide a relatively seamless transfer of information from one model to the next and from databases to models. Within these frameworks, multiple models are linked, resulting in models that consume information from upstream models and produce information to be consumed by downstream models. The Framework for Risk Analysis in Multimedia Environmental Systems (FRAMES) is an example, which allows users to link their models to other models and databases. FRAMES is an icon-driven, site-layout platform that is an open-architecture, object-oriented system that interacts with environmental databases; helps the user construct a Conceptual Site Model that is real-world based; allows the user to choose the most appropriate models to solve simulation requirements; solves the standard risk paradigm of release transport and fate; and exposure/risk assessments to people and ecology; and presents graphical packages for analyzing results. FRAMES is specifically designed allow users to link their own models into a system, which contains models developed by others. This paper will present the use of FRAMES to evaluate potential human health exposures using real site data and realistic assumptions from sources, through the vadose and saturated zones, to exposure and risk assessment at three real-world sites, using the Multimedia Environmental Pollutant Assessment System (MEPAS), which is a multimedia model contained within FRAMES. These real-world examples use predictive and comparative approaches coupled with a Monte Carlo analysis. A predictive analysis is where models are calibrated to monitored site data, prior to the assessment, and a comparative analysis is where models are not calibrated but based solely on literature or judgement and is usually used to compare alternatives. In many cases, a combination is employed where the model is calibrated to a portion of the data (e.g., to determine hydrodynamics), then used to compare alternatives. Three subsurface-based multimedia examples are presented, increasing in complexity. The first presents the application of a predictive, deterministic assessment; the second presents a predictive and comparative, Monte Carlo analysis; and the third presents a comparative, multi-dimensional Monte Carlo analysis. Endpoints are typically presented in terms of concentration, hazard, risk, and dose, and because the vadose zone model typically represents a connection between a source and the aquifer, it does not generally represent the final medium in a multimedia risk assessment.

Extensions of criteria for evaluating risk prediction models for public health applications.

PubMed

Pfeiffer, Ruth M

2013-04-01

We recently proposed two novel criteria to assess the usefulness of risk prediction models for public health applications. The proportion of cases followed, PCF(p), is the proportion of individuals who will develop disease who are included in the proportion p of individuals in the population at highest risk. The proportion needed to follow-up, PNF(q), is the proportion of the general population at highest risk that one needs to follow in order that a proportion q of those destined to become cases will be followed (Pfeiffer, R.M. and Gail, M.H., 2011. Two criteria for evaluating risk prediction models. Biometrics 67, 1057-1065). Here, we extend these criteria in two ways. First, we introduce two new criteria by integrating PCF and PNF over a range of values of q or p to obtain iPCF, the integrated PCF, and iPNF, the integrated PNF. A key assumption in the previous work was that the risk model is well calibrated. This assumption also underlies novel estimates of iPCF and iPNF based on observed risks in a population alone. The second extension is to propose and study estimates of PCF, PNF, iPCF, and iPNF that are consistent even if the risk models are not well calibrated. These new estimates are obtained from case-control data when the outcome prevalence in the population is known, and from cohort data, with baseline covariates and observed health outcomes. We study the efficiency of the various estimates and propose and compare tests for comparing two risk models, both of which were evaluated in the same validation data.

Livestock Helminths in a Changing Climate: Approaches and Restrictions to Meaningful Predictions.

PubMed

Fox, Naomi J; Marion, Glenn; Davidson, Ross S; White, Piran C L; Hutchings, Michael R

2012-03-06

Climate change is a driving force for livestock parasite risk. This is especially true for helminths including the nematodes Haemonchus contortus, Teladorsagia circumcincta, Nematodirus battus, and the trematode Fasciola hepatica, since survival and development of free-living stages is chiefly affected by temperature and moisture. The paucity of long term predictions of helminth risk under climate change has driven us to explore optimal modelling approaches and identify current bottlenecks to generating meaningful predictions. We classify approaches as correlative or mechanistic, exploring their strengths and limitations. Climate is one aspect of a complex system and, at the farm level, husbandry has a dominant influence on helminth transmission. Continuing environmental change will necessitate the adoption of mitigation and adaptation strategies in husbandry. Long term predictive models need to have the architecture to incorporate these changes. Ultimately, an optimal modelling approach is likely to combine mechanistic processes and physiological thresholds with correlative bioclimatic modelling, incorporating changes in livestock husbandry and disease control. Irrespective of approach, the principal limitation to parasite predictions is the availability of active surveillance data and empirical data on physiological responses to climate variables. By combining improved empirical data and refined models with a broad view of the livestock system, robust projections of helminth risk can be developed.