Prediction models for clustered data: comparison of a random intercept and standard regression model

PubMed Central

2013-01-01

Background When study data are clustered, standard regression analysis is considered inappropriate and analytical techniques for clustered data need to be used. For prediction research in which the interest of predictor effects is on the patient level, random effect regression models are probably preferred over standard regression analysis. It is well known that the random effect parameter estimates and the standard logistic regression parameter estimates are different. Here, we compared random effect and standard logistic regression models for their ability to provide accurate predictions. Methods Using an empirical study on 1642 surgical patients at risk of postoperative nausea and vomiting, who were treated by one of 19 anesthesiologists (clusters), we developed prognostic models either with standard or random intercept logistic regression. External validity of these models was assessed in new patients from other anesthesiologists. We supported our results with simulation studies using intra-class correlation coefficients (ICC) of 5%, 15%, or 30%. Standard performance measures and measures adapted for the clustered data structure were estimated. Results The model developed with random effect analysis showed better discrimination than the standard approach, if the cluster effects were used for risk prediction (standard c-index of 0.69 versus 0.66). In the external validation set, both models showed similar discrimination (standard c-index 0.68 versus 0.67). The simulation study confirmed these results. For datasets with a high ICC (≥15%), model calibration was only adequate in external subjects, if the used performance measure assumed the same data structure as the model development method: standard calibration measures showed good calibration for the standard developed model, calibration measures adapting the clustered data structure showed good calibration for the prediction model with random intercept. Conclusion The models with random intercept discriminate better than the standard model only if the cluster effect is used for predictions. The prediction model with random intercept had good calibration within clusters. PMID:23414436

Prediction models for clustered data: comparison of a random intercept and standard regression model.

PubMed

Bouwmeester, Walter; Twisk, Jos W R; Kappen, Teus H; van Klei, Wilton A; Moons, Karel G M; Vergouwe, Yvonne

2013-02-15

When study data are clustered, standard regression analysis is considered inappropriate and analytical techniques for clustered data need to be used. For prediction research in which the interest of predictor effects is on the patient level, random effect regression models are probably preferred over standard regression analysis. It is well known that the random effect parameter estimates and the standard logistic regression parameter estimates are different. Here, we compared random effect and standard logistic regression models for their ability to provide accurate predictions. Using an empirical study on 1642 surgical patients at risk of postoperative nausea and vomiting, who were treated by one of 19 anesthesiologists (clusters), we developed prognostic models either with standard or random intercept logistic regression. External validity of these models was assessed in new patients from other anesthesiologists. We supported our results with simulation studies using intra-class correlation coefficients (ICC) of 5%, 15%, or 30%. Standard performance measures and measures adapted for the clustered data structure were estimated. The model developed with random effect analysis showed better discrimination than the standard approach, if the cluster effects were used for risk prediction (standard c-index of 0.69 versus 0.66). In the external validation set, both models showed similar discrimination (standard c-index 0.68 versus 0.67). The simulation study confirmed these results. For datasets with a high ICC (≥15%), model calibration was only adequate in external subjects, if the used performance measure assumed the same data structure as the model development method: standard calibration measures showed good calibration for the standard developed model, calibration measures adapting the clustered data structure showed good calibration for the prediction model with random intercept. The models with random intercept discriminate better than the standard model only if the cluster effect is used for predictions. The prediction model with random intercept had good calibration within clusters.

Prediction models for CO2 emission in Malaysia using best subsets regression and multi-linear regression

NASA Astrophysics Data System (ADS)

Tan, C. H.; Matjafri, M. Z.; Lim, H. S.

2015-10-01

This paper presents the prediction models which analyze and compute the CO2 emission in Malaysia. Each prediction model for CO2 emission will be analyzed based on three main groups which is transportation, electricity and heat production as well as residential buildings and commercial and public services. The prediction models were generated using data obtained from World Bank Open Data. Best subset method will be used to remove irrelevant data and followed by multi linear regression to produce the prediction models. From the results, high R-square (prediction) value was obtained and this implies that the models are reliable to predict the CO2 emission by using specific data. In addition, the CO2 emissions from these three groups are forecasted using trend analysis plots for observation purpose.

The prediction of intelligence in preschool children using alternative models to regression.

PubMed

Finch, W Holmes; Chang, Mei; Davis, Andrew S; Holden, Jocelyn E; Rothlisberg, Barbara A; McIntosh, David E

2011-12-01

Statistical prediction of an outcome variable using multiple independent variables is a common practice in the social and behavioral sciences. For example, neuropsychologists are sometimes called upon to provide predictions of preinjury cognitive functioning for individuals who have suffered a traumatic brain injury. Typically, these predictions are made using standard multiple linear regression models with several demographic variables (e.g., gender, ethnicity, education level) as predictors. Prior research has shown conflicting evidence regarding the ability of such models to provide accurate predictions of outcome variables such as full-scale intelligence (FSIQ) test scores. The present study had two goals: (1) to demonstrate the utility of a set of alternative prediction methods that have been applied extensively in the natural sciences and business but have not been frequently explored in the social sciences and (2) to develop models that can be used to predict premorbid cognitive functioning in preschool children. Predictions of Stanford-Binet 5 FSIQ scores for preschool-aged children is used to compare the performance of a multiple regression model with several of these alternative methods. Results demonstrate that classification and regression trees provided more accurate predictions of FSIQ scores than does the more traditional regression approach. Implications of these results are discussed.

An adaptive two-stage analog/regression model for probabilistic prediction of small-scale precipitation in France

NASA Astrophysics Data System (ADS)

Chardon, Jérémy; Hingray, Benoit; Favre, Anne-Catherine

2018-01-01

Statistical downscaling models (SDMs) are often used to produce local weather scenarios from large-scale atmospheric information. SDMs include transfer functions which are based on a statistical link identified from observations between local weather and a set of large-scale predictors. As physical processes driving surface weather vary in time, the most relevant predictors and the regression link are likely to vary in time too. This is well known for precipitation for instance and the link is thus often estimated after some seasonal stratification of the data. In this study, we present a two-stage analog/regression model where the regression link is estimated from atmospheric analogs of the current prediction day. Atmospheric analogs are identified from fields of geopotential heights at 1000 and 500 hPa. For the regression stage, two generalized linear models are further used to model the probability of precipitation occurrence and the distribution of non-zero precipitation amounts, respectively. The two-stage model is evaluated for the probabilistic prediction of small-scale precipitation over France. It noticeably improves the skill of the prediction for both precipitation occurrence and amount. As the analog days vary from one prediction day to another, the atmospheric predictors selected in the regression stage and the value of the corresponding regression coefficients can vary from one prediction day to another. The model allows thus for a day-to-day adaptive and tailored downscaling. It can also reveal specific predictors for peculiar and non-frequent weather configurations.

A gentle introduction to quantile regression for ecologists

USGS Publications Warehouse

Cade, B.S.; Noon, B.R.

2003-01-01

Quantile regression is a way to estimate the conditional quantiles of a response variable distribution in the linear model that provides a more complete view of possible causal relationships between variables in ecological processes. Typically, all the factors that affect ecological processes are not measured and included in the statistical models used to investigate relationships between variables associated with those processes. As a consequence, there may be a weak or no predictive relationship between the mean of the response variable (y) distribution and the measured predictive factors (X). Yet there may be stronger, useful predictive relationships with other parts of the response variable distribution. This primer relates quantile regression estimates to prediction intervals in parametric error distribution regression models (eg least squares), and discusses the ordering characteristics, interval nature, sampling variation, weighting, and interpretation of the estimates for homogeneous and heterogeneous regression models.

Prediction of dynamical systems by symbolic regression

NASA Astrophysics Data System (ADS)

Quade, Markus; Abel, Markus; Shafi, Kamran; Niven, Robert K.; Noack, Bernd R.

2016-07-01

We study the modeling and prediction of dynamical systems based on conventional models derived from measurements. Such algorithms are highly desirable in situations where the underlying dynamics are hard to model from physical principles or simplified models need to be found. We focus on symbolic regression methods as a part of machine learning. These algorithms are capable of learning an analytically tractable model from data, a highly valuable property. Symbolic regression methods can be considered as generalized regression methods. We investigate two particular algorithms, the so-called fast function extraction which is a generalized linear regression algorithm, and genetic programming which is a very general method. Both are able to combine functions in a certain way such that a good model for the prediction of the temporal evolution of a dynamical system can be identified. We illustrate the algorithms by finding a prediction for the evolution of a harmonic oscillator based on measurements, by detecting an arriving front in an excitable system, and as a real-world application, the prediction of solar power production based on energy production observations at a given site together with the weather forecast.

Comparison of Neural Network and Linear Regression Models in Statistically Predicting Mental and Physical Health Status of Breast Cancer Survivors

DTIC Science & Technology

2015-07-15

Long-term effects on cancer survivors’ quality of life of physical training versus physical training combined with cognitive-behavioral therapy ...COMPARISON OF NEURAL NETWORK AND LINEAR REGRESSION MODELS IN STATISTICALLY PREDICTING MENTAL AND PHYSICAL HEALTH STATUS OF BREAST...34Comparison of Neural Network and Linear Regression Models in Statistically Predicting Mental and Physical Health Status of Breast Cancer Survivors

Comprehensive ripeness-index for prediction of ripening level in mangoes by multivariate modelling of ripening behaviour

NASA Astrophysics Data System (ADS)

Eyarkai Nambi, Vijayaram; Thangavel, Kuladaisamy; Manickavasagan, Annamalai; Shahir, Sultan

2017-01-01

Prediction of ripeness level in climacteric fruits is essential for post-harvest handling. An index capable of predicting ripening level with minimum inputs would be highly beneficial to the handlers, processors and researchers in fruit industry. A study was conducted with Indian mango cultivars to develop a ripeness index and associated model. Changes in physicochemical, colour and textural properties were measured throughout the ripening period and the period was classified into five stages (unripe, early ripe, partially ripe, ripe and over ripe). Multivariate regression techniques like partial least square regression, principal component regression and multi linear regression were compared and evaluated for its prediction. Multi linear regression model with 12 parameters was found more suitable in ripening prediction. Scientific variable reduction method was adopted to simplify the developed model. Better prediction was achieved with either 2 or 3 variables (total soluble solids, colour and acidity). Cross validation was done to increase the robustness and it was found that proposed ripening index was more effective in prediction of ripening stages. Three-variable model would be suitable for commercial applications where reasonable accuracies are sufficient. However, 12-variable model can be used to obtain more precise results in research and development applications.

Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.

PubMed

Stylianou, Neophytos; Akbarov, Artur; Kontopantelis, Evangelos; Buchan, Iain; Dunn, Ken W

2015-08-01

Predicting mortality from burn injury has traditionally employed logistic regression models. Alternative machine learning methods have been introduced in some areas of clinical prediction as the necessary software and computational facilities have become accessible. Here we compare logistic regression and machine learning predictions of mortality from burn. An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts. Copyright © 2015 Elsevier Ltd and ISBI. All rights reserved.

Individualized Prediction of Heat Stress in Firefighters: A Data-Driven Approach Using Classification and Regression Trees.

PubMed

Mani, Ashutosh; Rao, Marepalli; James, Kelley; Bhattacharya, Amit

2015-01-01

The purpose of this study was to explore data-driven models, based on decision trees, to develop practical and easy to use predictive models for early identification of firefighters who are likely to cross the threshold of hyperthermia during live-fire training. Predictive models were created for three consecutive live-fire training scenarios. The final predicted outcome was a categorical variable: will a firefighter cross the upper threshold of hyperthermia - Yes/No. Two tiers of models were built, one with and one without taking into account the outcome (whether a firefighter crossed hyperthermia or not) from the previous training scenario. First tier of models included age, baseline heart rate and core body temperature, body mass index, and duration of training scenario as predictors. The second tier of models included the outcome of the previous scenario in the prediction space, in addition to all the predictors from the first tier of models. Classification and regression trees were used independently for prediction. The response variable for the regression tree was the quantitative variable: core body temperature at the end of each scenario. The predicted quantitative variable from regression trees was compared to the upper threshold of hyperthermia (38°C) to predict whether a firefighter would enter hyperthermia. The performance of classification and regression tree models was satisfactory for the second (success rate = 79%) and third (success rate = 89%) training scenarios but not for the first (success rate = 43%). Data-driven models based on decision trees can be a useful tool for predicting physiological response without modeling the underlying physiological systems. Early prediction of heat stress coupled with proactive interventions, such as pre-cooling, can help reduce heat stress in firefighters.

Predicting recycling behaviour: Comparison of a linear regression model and a fuzzy logic model.

PubMed

Vesely, Stepan; Klöckner, Christian A; Dohnal, Mirko

2016-03-01

In this paper we demonstrate that fuzzy logic can provide a better tool for predicting recycling behaviour than the customarily used linear regression. To show this, we take a set of empirical data on recycling behaviour (N=664), which we randomly divide into two halves. The first half is used to estimate a linear regression model of recycling behaviour, and to develop a fuzzy logic model of recycling behaviour. As the first comparison, the fit of both models to the data included in estimation of the models (N=332) is evaluated. As the second comparison, predictive accuracy of both models for "new" cases (hold-out data not included in building the models, N=332) is assessed. In both cases, the fuzzy logic model significantly outperforms the regression model in terms of fit. To conclude, when accurate predictions of recycling and possibly other environmental behaviours are needed, fuzzy logic modelling seems to be a promising technique. Copyright © 2015 Elsevier Ltd. All rights reserved.

Newer classification and regression tree techniques: Bagging and Random Forests for ecological prediction

Treesearch

Anantha M. Prasad; Louis R. Iverson; Andy Liaw; Andy Liaw

2006-01-01

We evaluated four statistical models - Regression Tree Analysis (RTA), Bagging Trees (BT), Random Forests (RF), and Multivariate Adaptive Regression Splines (MARS) - for predictive vegetation mapping under current and future climate scenarios according to the Canadian Climate Centre global circulation model.

Fire spread in chaparral – a comparison of laboratory data and model predictions in burning live fuels

Treesearch

David R. Weise; Eunmo Koo; Xiangyang Zhou; Shankar Mahalingam; Frédéric Morandini; Jacques-Henri Balbi

2016-01-01

Fire behaviour data from 240 laboratory fires in high-density live chaparral fuel beds were compared with model predictions. Logistic regression was used to develop a model to predict fire spread success in the fuel beds and linear regression was used to predict rate of spread. Predictions from the Rothermel equation and three proposed changes as well as two physically...

Linear Multivariable Regression Models for Prediction of Eddy Dissipation Rate from Available Meteorological Data

NASA Technical Reports Server (NTRS)

MCKissick, Burnell T. (Technical Monitor); Plassman, Gerald E.; Mall, Gerald H.; Quagliano, John R.

2005-01-01

Linear multivariable regression models for predicting day and night Eddy Dissipation Rate (EDR) from available meteorological data sources are defined and validated. Model definition is based on a combination of 1997-2000 Dallas/Fort Worth (DFW) data sources, EDR from Aircraft Vortex Spacing System (AVOSS) deployment data, and regression variables primarily from corresponding Automated Surface Observation System (ASOS) data. Model validation is accomplished through EDR predictions on a similar combination of 1994-1995 Memphis (MEM) AVOSS and ASOS data. Model forms include an intercept plus a single term of fixed optimal power for each of these regression variables; 30-minute forward averaged mean and variance of near-surface wind speed and temperature, variance of wind direction, and a discrete cloud cover metric. Distinct day and night models, regressing on EDR and the natural log of EDR respectively, yield best performance and avoid model discontinuity over day/night data boundaries.

Modified Regression Correlation Coefficient for Poisson Regression Model

NASA Astrophysics Data System (ADS)

Kaengthong, Nattacha; Domthong, Uthumporn

2017-09-01

This study gives attention to indicators in predictive power of the Generalized Linear Model (GLM) which are widely used; however, often having some restrictions. We are interested in regression correlation coefficient for a Poisson regression model. This is a measure of predictive power, and defined by the relationship between the dependent variable (Y) and the expected value of the dependent variable given the independent variables [E(Y|X)] for the Poisson regression model. The dependent variable is distributed as Poisson. The purpose of this research was modifying regression correlation coefficient for Poisson regression model. We also compare the proposed modified regression correlation coefficient with the traditional regression correlation coefficient in the case of two or more independent variables, and having multicollinearity in independent variables. The result shows that the proposed regression correlation coefficient is better than the traditional regression correlation coefficient based on Bias and the Root Mean Square Error (RMSE).

Predicting School Enrollments Using the Modified Regression Technique.

ERIC Educational Resources Information Center

Grip, Richard S.; Young, John W.

This report is based on a study in which a regression model was constructed to increase accuracy in enrollment predictions. A model, known as the Modified Regression Technique (MRT), was used to examine K-12 enrollment over the past 20 years in 2 New Jersey school districts of similar size and ethnicity. To test the model's accuracy, MRT was…

Prediction of unwanted pregnancies using logistic regression, probit regression and discriminant analysis

PubMed Central

Ebrahimzadeh, Farzad; Hajizadeh, Ebrahim; Vahabi, Nasim; Almasian, Mohammad; Bakhteyar, Katayoon

2015-01-01

Background: Unwanted pregnancy not intended by at least one of the parents has undesirable consequences for the family and the society. In the present study, three classification models were used and compared to predict unwanted pregnancies in an urban population. Methods: In this cross-sectional study, 887 pregnant mothers referring to health centers in Khorramabad, Iran, in 2012 were selected by the stratified and cluster sampling; relevant variables were measured and for prediction of unwanted pregnancy, logistic regression, discriminant analysis, and probit regression models and SPSS software version 21 were used. To compare these models, indicators such as sensitivity, specificity, the area under the ROC curve, and the percentage of correct predictions were used. Results: The prevalence of unwanted pregnancies was 25.3%. The logistic and probit regression models indicated that parity and pregnancy spacing, contraceptive methods, household income and number of living male children were related to unwanted pregnancy. The performance of the models based on the area under the ROC curve was 0.735, 0.733, and 0.680 for logistic regression, probit regression, and linear discriminant analysis, respectively. Conclusion: Given the relatively high prevalence of unwanted pregnancies in Khorramabad, it seems necessary to revise family planning programs. Despite the similar accuracy of the models, if the researcher is interested in the interpretability of the results, the use of the logistic regression model is recommended. PMID:26793655

Prediction of unwanted pregnancies using logistic regression, probit regression and discriminant analysis.

PubMed

Ebrahimzadeh, Farzad; Hajizadeh, Ebrahim; Vahabi, Nasim; Almasian, Mohammad; Bakhteyar, Katayoon

2015-01-01

Unwanted pregnancy not intended by at least one of the parents has undesirable consequences for the family and the society. In the present study, three classification models were used and compared to predict unwanted pregnancies in an urban population. In this cross-sectional study, 887 pregnant mothers referring to health centers in Khorramabad, Iran, in 2012 were selected by the stratified and cluster sampling; relevant variables were measured and for prediction of unwanted pregnancy, logistic regression, discriminant analysis, and probit regression models and SPSS software version 21 were used. To compare these models, indicators such as sensitivity, specificity, the area under the ROC curve, and the percentage of correct predictions were used. The prevalence of unwanted pregnancies was 25.3%. The logistic and probit regression models indicated that parity and pregnancy spacing, contraceptive methods, household income and number of living male children were related to unwanted pregnancy. The performance of the models based on the area under the ROC curve was 0.735, 0.733, and 0.680 for logistic regression, probit regression, and linear discriminant analysis, respectively. Given the relatively high prevalence of unwanted pregnancies in Khorramabad, it seems necessary to revise family planning programs. Despite the similar accuracy of the models, if the researcher is interested in the interpretability of the results, the use of the logistic regression model is recommended.

Predicting 30-day Hospital Readmission with Publicly Available Administrative Database. A Conditional Logistic Regression Modeling Approach.

PubMed

Zhu, K; Lou, Z; Zhou, J; Ballester, N; Kong, N; Parikh, P

2015-01-01

This article is part of the Focus Theme of Methods of Information in Medicine on "Big Data and Analytics in Healthcare". Hospital readmissions raise healthcare costs and cause significant distress to providers and patients. It is, therefore, of great interest to healthcare organizations to predict what patients are at risk to be readmitted to their hospitals. However, current logistic regression based risk prediction models have limited prediction power when applied to hospital administrative data. Meanwhile, although decision trees and random forests have been applied, they tend to be too complex to understand among the hospital practitioners. Explore the use of conditional logistic regression to increase the prediction accuracy. We analyzed an HCUP statewide inpatient discharge record dataset, which includes patient demographics, clinical and care utilization data from California. We extracted records of heart failure Medicare beneficiaries who had inpatient experience during an 11-month period. We corrected the data imbalance issue with under-sampling. In our study, we first applied standard logistic regression and decision tree to obtain influential variables and derive practically meaning decision rules. We then stratified the original data set accordingly and applied logistic regression on each data stratum. We further explored the effect of interacting variables in the logistic regression modeling. We conducted cross validation to assess the overall prediction performance of conditional logistic regression (CLR) and compared it with standard classification models. The developed CLR models outperformed several standard classification models (e.g., straightforward logistic regression, stepwise logistic regression, random forest, support vector machine). For example, the best CLR model improved the classification accuracy by nearly 20% over the straightforward logistic regression model. Furthermore, the developed CLR models tend to achieve better sensitivity of more than 10% over the standard classification models, which can be translated to correct labeling of additional 400 - 500 readmissions for heart failure patients in the state of California over a year. Lastly, several key predictor identified from the HCUP data include the disposition location from discharge, the number of chronic conditions, and the number of acute procedures. It would be beneficial to apply simple decision rules obtained from the decision tree in an ad-hoc manner to guide the cohort stratification. It could be potentially beneficial to explore the effect of pairwise interactions between influential predictors when building the logistic regression models for different data strata. Judicious use of the ad-hoc CLR models developed offers insights into future development of prediction models for hospital readmissions, which can lead to better intuition in identifying high-risk patients and developing effective post-discharge care strategies. Lastly, this paper is expected to raise the awareness of collecting data on additional markers and developing necessary database infrastructure for larger-scale exploratory studies on readmission risk prediction.

Applicability of Monte Carlo cross validation technique for model development and validation using generalised least squares regression

NASA Astrophysics Data System (ADS)

Haddad, Khaled; Rahman, Ataur; A Zaman, Mohammad; Shrestha, Surendra

2013-03-01

SummaryIn regional hydrologic regression analysis, model selection and validation are regarded as important steps. Here, the model selection is usually based on some measurements of goodness-of-fit between the model prediction and observed data. In Regional Flood Frequency Analysis (RFFA), leave-one-out (LOO) validation or a fixed percentage leave out validation (e.g., 10%) is commonly adopted to assess the predictive ability of regression-based prediction equations. This paper develops a Monte Carlo Cross Validation (MCCV) technique (which has widely been adopted in Chemometrics and Econometrics) in RFFA using Generalised Least Squares Regression (GLSR) and compares it with the most commonly adopted LOO validation approach. The study uses simulated and regional flood data from the state of New South Wales in Australia. It is found that when developing hydrologic regression models, application of the MCCV is likely to result in a more parsimonious model than the LOO. It has also been found that the MCCV can provide a more realistic estimate of a model's predictive ability when compared with the LOO.

Can Predictive Modeling Identify Head and Neck Oncology Patients at Risk for Readmission?

PubMed

Manning, Amy M; Casper, Keith A; Peter, Kay St; Wilson, Keith M; Mark, Jonathan R; Collar, Ryan M

2018-05-01

Objective Unplanned readmission within 30 days is a contributor to health care costs in the United States. The use of predictive modeling during hospitalization to identify patients at risk for readmission offers a novel approach to quality improvement and cost reduction. Study Design Two-phase study including retrospective analysis of prospectively collected data followed by prospective longitudinal study. Setting Tertiary academic medical center. Subjects and Methods Prospectively collected data for patients undergoing surgical treatment for head and neck cancer from January 2013 to January 2015 were used to build predictive models for readmission within 30 days of discharge using logistic regression, classification and regression tree (CART) analysis, and random forests. One model (logistic regression) was then placed prospectively into the discharge workflow from March 2016 to May 2016 to determine the model's ability to predict which patients would be readmitted within 30 days. Results In total, 174 admissions had descriptive data. Thirty-two were excluded due to incomplete data. Logistic regression, CART, and random forest predictive models were constructed using the remaining 142 admissions. When applied to 106 consecutive prospective head and neck oncology patients at the time of discharge, the logistic regression model predicted readmissions with a specificity of 94%, a sensitivity of 47%, a negative predictive value of 90%, and a positive predictive value of 62% (odds ratio, 14.9; 95% confidence interval, 4.02-55.45). Conclusion Prospectively collected head and neck cancer databases can be used to develop predictive models that can accurately predict which patients will be readmitted. This offers valuable support for quality improvement initiatives and readmission-related cost reduction in head and neck cancer care.

Precision Efficacy Analysis for Regression.

ERIC Educational Resources Information Center

Brooks, Gordon P.

When multiple linear regression is used to develop a prediction model, sample size must be large enough to ensure stable coefficients. If the derivation sample size is inadequate, the model may not predict well for future subjects. The precision efficacy analysis for regression (PEAR) method uses a cross- validity approach to select sample sizes…

Predicting Depression among Patients with Diabetes Using Longitudinal Data. A Multilevel Regression Model.

PubMed

Jin, H; Wu, S; Vidyanti, I; Di Capua, P; Wu, B

2015-01-01

This article is part of the Focus Theme of Methods of Information in Medicine on "Big Data and Analytics in Healthcare". Depression is a common and often undiagnosed condition for patients with diabetes. It is also a condition that significantly impacts healthcare outcomes, use, and cost as well as elevating suicide risk. Therefore, a model to predict depression among diabetes patients is a promising and valuable tool for providers to proactively assess depressive symptoms and identify those with depression. This study seeks to develop a generalized multilevel regression model, using a longitudinal data set from a recent large-scale clinical trial, to predict depression severity and presence of major depression among patients with diabetes. Severity of depression was measured by the Patient Health Questionnaire PHQ-9 score. Predictors were selected from 29 candidate factors to develop a 2-level Poisson regression model that can make population-average predictions for all patients and subject-specific predictions for individual patients with historical records. Newly obtained patient records can be incorporated with historical records to update the prediction model. Root-mean-square errors (RMSE) were used to evaluate predictive accuracy of PHQ-9 scores. The study also evaluated the classification ability of using the predicted PHQ-9 scores to classify patients as having major depression. Two time-invariant and 10 time-varying predictors were selected for the model. Incorporating historical records and using them to update the model may improve both predictive accuracy of PHQ-9 scores and classification ability of the predicted scores. Subject-specific predictions (for individual patients with historical records) achieved RMSE about 4 and areas under the receiver operating characteristic (ROC) curve about 0.9 and are better than population-average predictions. The study developed a generalized multilevel regression model to predict depression and demonstrated that using generalized multilevel regression based on longitudinal patient records can achieve high predictive ability.

Predicting Air Permeability of Handloom Fabrics: A Comparative Analysis of Regression and Artificial Neural Network Models

NASA Astrophysics Data System (ADS)

Mitra, Ashis; Majumdar, Prabal Kumar; Bannerjee, Debamalya

2013-03-01

This paper presents a comparative analysis of two modeling methodologies for the prediction of air permeability of plain woven handloom cotton fabrics. Four basic fabric constructional parameters namely ends per inch, picks per inch, warp count and weft count have been used as inputs for artificial neural network (ANN) and regression models. Out of the four regression models tried, interaction model showed very good prediction performance with a meager mean absolute error of 2.017 %. However, ANN models demonstrated superiority over the regression models both in terms of correlation coefficient and mean absolute error. The ANN model with 10 nodes in the single hidden layer showed very good correlation coefficient of 0.982 and 0.929 and mean absolute error of only 0.923 and 2.043 % for training and testing data respectively.

Comparison of modeling methods to predict the spatial distribution of deep-sea coral and sponge in the Gulf of Alaska

NASA Astrophysics Data System (ADS)

Rooper, Christopher N.; Zimmermann, Mark; Prescott, Megan M.

2017-08-01

Deep-sea coral and sponge ecosystems are widespread throughout most of Alaska's marine waters, and are associated with many different species of fishes and invertebrates. These ecosystems are vulnerable to the effects of commercial fishing activities and climate change. We compared four commonly used species distribution models (general linear models, generalized additive models, boosted regression trees and random forest models) and an ensemble model to predict the presence or absence and abundance of six groups of benthic invertebrate taxa in the Gulf of Alaska. All four model types performed adequately on training data for predicting presence and absence, with regression forest models having the best overall performance measured by the area under the receiver-operating-curve (AUC). The models also performed well on the test data for presence and absence with average AUCs ranging from 0.66 to 0.82. For the test data, ensemble models performed the best. For abundance data, there was an obvious demarcation in performance between the two regression-based methods (general linear models and generalized additive models), and the tree-based models. The boosted regression tree and random forest models out-performed the other models by a wide margin on both the training and testing data. However, there was a significant drop-off in performance for all models of invertebrate abundance ( 50%) when moving from the training data to the testing data. Ensemble model performance was between the tree-based and regression-based methods. The maps of predictions from the models for both presence and abundance agreed very well across model types, with an increase in variability in predictions for the abundance data. We conclude that where data conforms well to the modeled distribution (such as the presence-absence data and binomial distribution in this study), the four types of models will provide similar results, although the regression-type models may be more consistent with biological theory. For data with highly zero-inflated distributions and non-normal distributions such as the abundance data from this study, the tree-based methods performed better. Ensemble models that averaged predictions across the four model types, performed better than the GLM or GAM models but slightly poorer than the tree-based methods, suggesting ensemble models might be more robust to overfitting than tree methods, while mitigating some of the disadvantages in predictive performance of regression methods.

Regression Simulation Model. Appendix X. Users Manual,

DTIC Science & Technology

1981-03-01

change as the prediction equations become refined. Whereas no notice will be provided when the changes are made, the programs will be modified such that...NATIONAL BUREAU Of STANDARDS 1963 A ___,_ __ _ __ _ . APPENDIX X ( R4/ EGRESSION IMULATION ’jDEL. Ape’A ’) 7 USERS MANUA submitted to The Great River...regression analysis and to establish a prediction equation (model). The prediction equation contains the partial regression coefficients (B-weights) which

Partial least squares for efficient models of fecal indicator bacteria on Great Lakes beaches

USGS Publications Warehouse

Brooks, Wesley R.; Fienen, Michael N.; Corsi, Steven R.

2013-01-01

At public beaches, it is now common to mitigate the impact of water-borne pathogens by posting a swimmer's advisory when the concentration of fecal indicator bacteria (FIB) exceeds an action threshold. Since culturing the bacteria delays public notification when dangerous conditions exist, regression models are sometimes used to predict the FIB concentration based on readily-available environmental measurements. It is hard to know which environmental parameters are relevant to predicting FIB concentration, and the parameters are usually correlated, which can hurt the predictive power of a regression model. Here the method of partial least squares (PLS) is introduced to automate the regression modeling process. Model selection is reduced to the process of setting a tuning parameter to control the decision threshold that separates predicted exceedances of the standard from predicted non-exceedances. The method is validated by application to four Great Lakes beaches during the summer of 2010. Performance of the PLS models compares favorably to that of the existing state-of-the-art regression models at these four sites.

Predicting Quantitative Traits With Regression Models for Dense Molecular Markers and Pedigree

PubMed Central

de los Campos, Gustavo; Naya, Hugo; Gianola, Daniel; Crossa, José; Legarra, Andrés; Manfredi, Eduardo; Weigel, Kent; Cotes, José Miguel

2009-01-01

The availability of genomewide dense markers brings opportunities and challenges to breeding programs. An important question concerns the ways in which dense markers and pedigrees, together with phenotypic records, should be used to arrive at predictions of genetic values for complex traits. If a large number of markers are included in a regression model, marker-specific shrinkage of regression coefficients may be needed. For this reason, the Bayesian least absolute shrinkage and selection operator (LASSO) (BL) appears to be an interesting approach for fitting marker effects in a regression model. This article adapts the BL to arrive at a regression model where markers, pedigrees, and covariates other than markers are considered jointly. Connections between BL and other marker-based regression models are discussed, and the sensitivity of BL with respect to the choice of prior distributions assigned to key parameters is evaluated using simulation. The proposed model was fitted to two data sets from wheat and mouse populations, and evaluated using cross-validation methods. Results indicate that inclusion of markers in the regression further improved the predictive ability of models. An R program that implements the proposed model is freely available. PMID:19293140

On the interest of combining an analog model to a regression model for the adaptation of the downscaling link. Application to probabilistic prediction of precipitation over France.

NASA Astrophysics Data System (ADS)

Chardon, Jérémy; Hingray, Benoit; Favre, Anne-Catherine

2016-04-01

Scenarios of surface weather required for the impact studies have to be unbiased and adapted to the space and time scales of the considered hydro-systems. Hence, surface weather scenarios obtained from global climate models and/or numerical weather prediction models are not really appropriated. Outputs of these models have to be post-processed, which is often carried out thanks to Statistical Downscaling Methods (SDMs). Among those SDMs, approaches based on regression are often applied. For a given station, a regression link can be established between a set of large scale atmospheric predictors and the surface weather variable. These links are then used for the prediction of the latter. However, physical processes generating surface weather vary in time. This is well known for precipitation for instance. The most relevant predictors and the regression link are also likely to vary in time. A better prediction skill is thus classically obtained with a seasonal stratification of the data. Another strategy is to identify the most relevant predictor set and establish the regression link from dates that are similar - or analog - to the target date. In practice, these dates can be selected thanks to an analog model. In this study, we explore the possibility of improving the local performance of an analog model - where the analogy is applied to the geopotential heights 1000 and 500 hPa - using additional local scale predictors for the probabilistic prediction of the Safran precipitation over France. For each prediction day, the prediction is obtained from two GLM regression models - for both the occurrence and the quantity of precipitation - for which predictors and parameters are estimated from the analog dates. Firstly, the resulting combined model noticeably allows increasing the prediction performance by adapting the downscaling link for each prediction day. Secondly, the selected predictors for a given prediction depend on the large scale situation and on the considered region. Finally, even with such an adaptive predictor identification, the downscaling link appears to be robust: for a same prediction day, predictors selected for different locations of a given region are similar and the regression parameters are consistent within the region of interest.

Artificial neural networks predict the incidence of portosplenomesenteric venous thrombosis in patients with acute pancreatitis.

PubMed

Fei, Y; Hu, J; Li, W-Q; Wang, W; Zong, G-Q

2017-03-01

Essentials Predicting the occurrence of portosplenomesenteric vein thrombosis (PSMVT) is difficult. We studied 72 patients with acute pancreatitis. Artificial neural networks modeling was more accurate than logistic regression in predicting PSMVT. Additional predictive factors may be incorporated into artificial neural networks. Objective To construct and validate artificial neural networks (ANNs) for predicting the occurrence of portosplenomesenteric venous thrombosis (PSMVT) and compare the predictive ability of the ANNs with that of logistic regression. Methods The ANNs and logistic regression modeling were constructed using simple clinical and laboratory data of 72 acute pancreatitis (AP) patients. The ANNs and logistic modeling were first trained on 48 randomly chosen patients and validated on the remaining 24 patients. The accuracy and the performance characteristics were compared between these two approaches by SPSS17.0 software. Results The training set and validation set did not differ on any of the 11 variables. After training, the back propagation network training error converged to 1 × 10 -20 , and it retained excellent pattern recognition ability. When the ANNs model was applied to the validation set, it revealed a sensitivity of 80%, specificity of 85.7%, a positive predictive value of 77.6% and negative predictive value of 90.7%. The accuracy was 83.3%. Differences could be found between ANNs modeling and logistic regression modeling in these parameters (10.0% [95% CI, -14.3 to 34.3%], 14.3% [95% CI, -8.6 to 37.2%], 15.7% [95% CI, -9.9 to 41.3%], 11.8% [95% CI, -8.2 to 31.8%], 22.6% [95% CI, -1.9 to 47.1%], respectively). When ANNs modeling was used to identify PSMVT, the area under receiver operating characteristic curve was 0.849 (95% CI, 0.807-0.901), which demonstrated better overall properties than logistic regression modeling (AUC = 0.716) (95% CI, 0.679-0.761). Conclusions ANNs modeling was a more accurate tool than logistic regression in predicting the occurrence of PSMVT following AP. More clinical factors or biomarkers may be incorporated into ANNs modeling to improve its predictive ability. © 2016 International Society on Thrombosis and Haemostasis.

Multinomial Logistic Regression Predicted Probability Map To Visualize The Influence Of Socio-Economic Factors On Breast Cancer Occurrence in Southern Karnataka

NASA Astrophysics Data System (ADS)

Madhu, B.; Ashok, N. C.; Balasubramanian, S.

2014-11-01

Multinomial logistic regression analysis was used to develop statistical model that can predict the probability of breast cancer in Southern Karnataka using the breast cancer occurrence data during 2007-2011. Independent socio-economic variables describing the breast cancer occurrence like age, education, occupation, parity, type of family, health insurance coverage, residential locality and socioeconomic status of each case was obtained. The models were developed as follows: i) Spatial visualization of the Urban- rural distribution of breast cancer cases that were obtained from the Bharat Hospital and Institute of Oncology. ii) Socio-economic risk factors describing the breast cancer occurrences were complied for each case. These data were then analysed using multinomial logistic regression analysis in a SPSS statistical software and relations between the occurrence of breast cancer across the socio-economic status and the influence of other socio-economic variables were evaluated and multinomial logistic regression models were constructed. iii) the model that best predicted the occurrence of breast cancer were identified. This multivariate logistic regression model has been entered into a geographic information system and maps showing the predicted probability of breast cancer occurrence in Southern Karnataka was created. This study demonstrates that Multinomial logistic regression is a valuable tool for developing models that predict the probability of breast cancer Occurrence in Southern Karnataka.

Predicting ecological flow regime at ungaged sites: A comparison of methods

USGS Publications Warehouse

Murphy, Jennifer C.; Knight, Rodney R.; Wolfe, William J.; Gain, W. Scott

2012-01-01

Nineteen ecologically relevant streamflow characteristics were estimated using published rainfall–runoff and regional regression models for six sites with observed daily streamflow records in Kentucky. The regional regression model produced median estimates closer to the observed median for all but two characteristics. The variability of predictions from both models was generally less than the observed variability. The variability of the predictions from the rainfall–runoff model was greater than that from the regional regression model for all but three characteristics. Eight characteristics predicted by the rainfall–runoff model display positive or negative bias across all six sites; biases are not as pronounced for the regional regression model. Results suggest that a rainfall–runoff model calibrated on a single characteristic is less likely to perform well as a predictor of a range of other characteristics (flow regime) when compared with a regional regression model calibrated individually on multiple characteristics used to represent the flow regime. Poor model performance may misrepresent hydrologic conditions, potentially distorting the perceived risk of ecological degradation. Without prior selection of streamflow characteristics, targeted calibration, and error quantification, the widespread application of general hydrologic models to ecological flow studies is problematic. Published 2012. This article is a U.S. Government work and is in the public domain in the USA.

Approximating prediction uncertainty for random forest regression models

Treesearch

John W. Coulston; Christine E. Blinn; Valerie A. Thomas; Randolph H. Wynne

2016-01-01

Machine learning approaches such as random forest have increased for the spatial modeling and mapping of continuous variables. Random forest is a non-parametric ensemble approach, and unlike traditional regression approaches there is no direct quantification of prediction error. Understanding prediction uncertainty is important when using model-based continuous maps as...

Predicting Jakarta composite index using hybrid of fuzzy time series and support vector regression models

NASA Astrophysics Data System (ADS)

Febrian Umbara, Rian; Tarwidi, Dede; Budi Setiawan, Erwin

2018-03-01

The paper discusses the prediction of Jakarta Composite Index (JCI) in Indonesia Stock Exchange. The study is based on JCI historical data for 1286 days to predict the value of JCI one day ahead. This paper proposes predictions done in two stages., The first stage using Fuzzy Time Series (FTS) to predict values of ten technical indicators, and the second stage using Support Vector Regression (SVR) to predict the value of JCI one day ahead, resulting in a hybrid prediction model FTS-SVR. The performance of this combined prediction model is compared with the performance of the single stage prediction model using SVR only. Ten technical indicators are used as input for each model.

The microcomputer scientific software series 2: general linear model--regression.

Treesearch

Harold M. Rauscher

1983-01-01

The general linear model regression (GLMR) program provides the microcomputer user with a sophisticated regression analysis capability. The output provides a regression ANOVA table, estimators of the regression model coefficients, their confidence intervals, confidence intervals around the predicted Y-values, residuals for plotting, a check for multicollinearity, a...

Comparative study of biodegradability prediction of chemicals using decision trees, functional trees, and logistic regression.

PubMed

Chen, Guangchao; Li, Xuehua; Chen, Jingwen; Zhang, Ya-Nan; Peijnenburg, Willie J G M

2014-12-01

Biodegradation is the principal environmental dissipation process of chemicals. As such, it is a dominant factor determining the persistence and fate of organic chemicals in the environment, and is therefore of critical importance to chemical management and regulation. In the present study, the authors developed in silico methods assessing biodegradability based on a large heterogeneous set of 825 organic compounds, using the techniques of the C4.5 decision tree, the functional inner regression tree, and logistic regression. External validation was subsequently carried out by 2 independent test sets of 777 and 27 chemicals. As a result, the functional inner regression tree exhibited the best predictability with predictive accuracies of 81.5% and 81.0%, respectively, on the training set (825 chemicals) and test set I (777 chemicals). Performance of the developed models on the 2 test sets was subsequently compared with that of the Estimation Program Interface (EPI) Suite Biowin 5 and Biowin 6 models, which also showed a better predictability of the functional inner regression tree model. The model built in the present study exhibits a reasonable predictability compared with existing models while possessing a transparent algorithm. Interpretation of the mechanisms of biodegradation was also carried out based on the models developed. © 2014 SETAC.

Random forest models to predict aqueous solubility.

PubMed

Palmer, David S; O'Boyle, Noel M; Glen, Robert C; Mitchell, John B O

2007-01-01

Random Forest regression (RF), Partial-Least-Squares (PLS) regression, Support Vector Machines (SVM), and Artificial Neural Networks (ANN) were used to develop QSPR models for the prediction of aqueous solubility, based on experimental data for 988 organic molecules. The Random Forest regression model predicted aqueous solubility more accurately than those created by PLS, SVM, and ANN and offered methods for automatic descriptor selection, an assessment of descriptor importance, and an in-parallel measure of predictive ability, all of which serve to recommend its use. The prediction of log molar solubility for an external test set of 330 molecules that are solid at 25 degrees C gave an r2 = 0.89 and RMSE = 0.69 log S units. For a standard data set selected from the literature, the model performed well with respect to other documented methods. Finally, the diversity of the training and test sets are compared to the chemical space occupied by molecules in the MDL drug data report, on the basis of molecular descriptors selected by the regression analysis.

Latin hypercube approach to estimate uncertainty in ground water vulnerability

USGS Publications Warehouse

Gurdak, J.J.; McCray, J.E.; Thyne, G.; Qi, S.L.

2007-01-01

A methodology is proposed to quantify prediction uncertainty associated with ground water vulnerability models that were developed through an approach that coupled multivariate logistic regression with a geographic information system (GIS). This method uses Latin hypercube sampling (LHS) to illustrate the propagation of input error and estimate uncertainty associated with the logistic regression predictions of ground water vulnerability. Central to the proposed method is the assumption that prediction uncertainty in ground water vulnerability models is a function of input error propagation from uncertainty in the estimated logistic regression model coefficients (model error) and the values of explanatory variables represented in the GIS (data error). Input probability distributions that represent both model and data error sources of uncertainty were simultaneously sampled using a Latin hypercube approach with logistic regression calculations of probability of elevated nonpoint source contaminants in ground water. The resulting probability distribution represents the prediction intervals and associated uncertainty of the ground water vulnerability predictions. The method is illustrated through a ground water vulnerability assessment of the High Plains regional aquifer. Results of the LHS simulations reveal significant prediction uncertainties that vary spatially across the regional aquifer. Additionally, the proposed method enables a spatial deconstruction of the prediction uncertainty that can lead to improved prediction of ground water vulnerability. ?? 2007 National Ground Water Association.

Modeling the frequency of opposing left-turn conflicts at signalized intersections using generalized linear regression models.

PubMed

Zhang, Xin; Liu, Pan; Chen, Yuguang; Bai, Lu; Wang, Wei

2014-01-01

The primary objective of this study was to identify whether the frequency of traffic conflicts at signalized intersections can be modeled. The opposing left-turn conflicts were selected for the development of conflict predictive models. Using data collected at 30 approaches at 20 signalized intersections, the underlying distributions of the conflicts under different traffic conditions were examined. Different conflict-predictive models were developed to relate the frequency of opposing left-turn conflicts to various explanatory variables. The models considered include a linear regression model, a negative binomial model, and separate models developed for four traffic scenarios. The prediction performance of different models was compared. The frequency of traffic conflicts follows a negative binominal distribution. The linear regression model is not appropriate for the conflict frequency data. In addition, drivers behaved differently under different traffic conditions. Accordingly, the effects of conflicting traffic volumes on conflict frequency vary across different traffic conditions. The occurrences of traffic conflicts at signalized intersections can be modeled using generalized linear regression models. The use of conflict predictive models has potential to expand the uses of surrogate safety measures in safety estimation and evaluation.

Linear regression models for solvent accessibility prediction in proteins.

PubMed

Wagner, Michael; Adamczak, Rafał; Porollo, Aleksey; Meller, Jarosław

2005-04-01

The relative solvent accessibility (RSA) of an amino acid residue in a protein structure is a real number that represents the solvent exposed surface area of this residue in relative terms. The problem of predicting the RSA from the primary amino acid sequence can therefore be cast as a regression problem. Nevertheless, RSA prediction has so far typically been cast as a classification problem. Consequently, various machine learning techniques have been used within the classification framework to predict whether a given amino acid exceeds some (arbitrary) RSA threshold and would thus be predicted to be "exposed," as opposed to "buried." We have recently developed novel methods for RSA prediction using nonlinear regression techniques which provide accurate estimates of the real-valued RSA and outperform classification-based approaches with respect to commonly used two-class projections. However, while their performance seems to provide a significant improvement over previously published approaches, these Neural Network (NN) based methods are computationally expensive to train and involve several thousand parameters. In this work, we develop alternative regression models for RSA prediction which are computationally much less expensive, involve orders-of-magnitude fewer parameters, and are still competitive in terms of prediction quality. In particular, we investigate several regression models for RSA prediction using linear L1-support vector regression (SVR) approaches as well as standard linear least squares (LS) regression. Using rigorously derived validation sets of protein structures and extensive cross-validation analysis, we compare the performance of the SVR with that of LS regression and NN-based methods. In particular, we show that the flexibility of the SVR (as encoded by metaparameters such as the error insensitivity and the error penalization terms) can be very beneficial to optimize the prediction accuracy for buried residues. We conclude that the simple and computationally much more efficient linear SVR performs comparably to nonlinear models and thus can be used in order to facilitate further attempts to design more accurate RSA prediction methods, with applications to fold recognition and de novo protein structure prediction methods.

LiDAR based prediction of forest biomass using hierarchical models with spatially varying coefficients

USGS Publications Warehouse

Babcock, Chad; Finley, Andrew O.; Bradford, John B.; Kolka, Randall K.; Birdsey, Richard A.; Ryan, Michael G.

2015-01-01

Many studies and production inventory systems have shown the utility of coupling covariates derived from Light Detection and Ranging (LiDAR) data with forest variables measured on georeferenced inventory plots through regression models. The objective of this study was to propose and assess the use of a Bayesian hierarchical modeling framework that accommodates both residual spatial dependence and non-stationarity of model covariates through the introduction of spatial random effects. We explored this objective using four forest inventory datasets that are part of the North American Carbon Program, each comprising point-referenced measures of above-ground forest biomass and discrete LiDAR. For each dataset, we considered at least five regression model specifications of varying complexity. Models were assessed based on goodness of fit criteria and predictive performance using a 10-fold cross-validation procedure. Results showed that the addition of spatial random effects to the regression model intercept improved fit and predictive performance in the presence of substantial residual spatial dependence. Additionally, in some cases, allowing either some or all regression slope parameters to vary spatially, via the addition of spatial random effects, further improved model fit and predictive performance. In other instances, models showed improved fit but decreased predictive performance—indicating over-fitting and underscoring the need for cross-validation to assess predictive ability. The proposed Bayesian modeling framework provided access to pixel-level posterior predictive distributions that were useful for uncertainty mapping, diagnosing spatial extrapolation issues, revealing missing model covariates, and discovering locally significant parameters.

Application of Machine-Learning Models to Predict Tacrolimus Stable Dose in Renal Transplant Recipients

NASA Astrophysics Data System (ADS)

Tang, Jie; Liu, Rong; Zhang, Yue-Li; Liu, Mou-Ze; Hu, Yong-Fang; Shao, Ming-Jie; Zhu, Li-Jun; Xin, Hua-Wen; Feng, Gui-Wen; Shang, Wen-Jun; Meng, Xiang-Guang; Zhang, Li-Rong; Ming, Ying-Zi; Zhang, Wei

2017-02-01

Tacrolimus has a narrow therapeutic window and considerable variability in clinical use. Our goal was to compare the performance of multiple linear regression (MLR) and eight machine learning techniques in pharmacogenetic algorithm-based prediction of tacrolimus stable dose (TSD) in a large Chinese cohort. A total of 1,045 renal transplant patients were recruited, 80% of which were randomly selected as the “derivation cohort” to develop dose-prediction algorithm, while the remaining 20% constituted the “validation cohort” to test the final selected algorithm. MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied and their performances were compared in this work. Among all the machine learning models, RT performed best in both derivation [0.71 (0.67-0.76)] and validation cohorts [0.73 (0.63-0.82)]. In addition, the ideal rate of RT was 4% higher than that of MLR. To our knowledge, this is the first study to use machine learning models to predict TSD, which will further facilitate personalized medicine in tacrolimus administration in the future.

A Demonstration of Regression False Positive Selection in Data Mining

ERIC Educational Resources Information Center

Pinder, Jonathan P.

2014-01-01

Business analytics courses, such as marketing research, data mining, forecasting, and advanced financial modeling, have substantial predictive modeling components. The predictive modeling in these courses requires students to estimate and test many linear regressions. As a result, false positive variable selection ("type I errors") is…

Watershed Regressions for Pesticides (WARP) for Predicting Annual Maximum and Annual Maximum Moving-Average Concentrations of Atrazine in Streams

USGS Publications Warehouse

Stone, Wesley W.; Gilliom, Robert J.; Crawford, Charles G.

2008-01-01

Regression models were developed for predicting annual maximum and selected annual maximum moving-average concentrations of atrazine in streams using the Watershed Regressions for Pesticides (WARP) methodology developed by the National Water-Quality Assessment Program (NAWQA) of the U.S. Geological Survey (USGS). The current effort builds on the original WARP models, which were based on the annual mean and selected percentiles of the annual frequency distribution of atrazine concentrations. Estimates of annual maximum and annual maximum moving-average concentrations for selected durations are needed to characterize the levels of atrazine and other pesticides for comparison to specific water-quality benchmarks for evaluation of potential concerns regarding human health or aquatic life. Separate regression models were derived for the annual maximum and annual maximum 21-day, 60-day, and 90-day moving-average concentrations. Development of the regression models used the same explanatory variables, transformations, model development data, model validation data, and regression methods as those used in the original development of WARP. The models accounted for 72 to 75 percent of the variability in the concentration statistics among the 112 sampling sites used for model development. Predicted concentration statistics from the four models were within a factor of 10 of the observed concentration statistics for most of the model development and validation sites. Overall, performance of the models for the development and validation sites supports the application of the WARP models for predicting annual maximum and selected annual maximum moving-average atrazine concentration in streams and provides a framework to interpret the predictions in terms of uncertainty. For streams with inadequate direct measurements of atrazine concentrations, the WARP model predictions for the annual maximum and the annual maximum moving-average atrazine concentrations can be used to characterize the probable levels of atrazine for comparison to specific water-quality benchmarks. Sites with a high probability of exceeding a benchmark for human health or aquatic life can be prioritized for monitoring.

Developing global regression models for metabolite concentration prediction regardless of cell line.

PubMed

André, Silvère; Lagresle, Sylvain; Da Sliva, Anthony; Heimendinger, Pierre; Hannas, Zahia; Calvosa, Éric; Duponchel, Ludovic

2017-11-01

Following the Process Analytical Technology (PAT) of the Food and Drug Administration (FDA), drug manufacturers are encouraged to develop innovative techniques in order to monitor and understand their processes in a better way. Within this framework, it has been demonstrated that Raman spectroscopy coupled with chemometric tools allow to predict critical parameters of mammalian cell cultures in-line and in real time. However, the development of robust and predictive regression models clearly requires many batches in order to take into account inter-batch variability and enhance models accuracy. Nevertheless, this heavy procedure has to be repeated for every new line of cell culture involving many resources. This is why we propose in this paper to develop global regression models taking into account different cell lines. Such models are finally transferred to any culture of the cells involved. This article first demonstrates the feasibility of developing regression models, not only for mammalian cell lines (CHO and HeLa cell cultures), but also for insect cell lines (Sf9 cell cultures). Then global regression models are generated, based on CHO cells, HeLa cells, and Sf9 cells. Finally, these models are evaluated considering a fourth cell line(HEK cells). In addition to suitable predictions of glucose and lactate concentration of HEK cell cultures, we expose that by adding a single HEK-cell culture to the calibration set, the predictive ability of the regression models are substantially increased. In this way, we demonstrate that using global models, it is not necessary to consider many cultures of a new cell line in order to obtain accurate models. Biotechnol. Bioeng. 2017;114: 2550-2559. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Building and verifying a severity prediction model of acute pancreatitis (AP) based on BISAP, MEWS and routine test indexes.

PubMed

Ye, Jiang-Feng; Zhao, Yu-Xin; Ju, Jian; Wang, Wei

2017-10-01

To discuss the value of the Bedside Index for Severity in Acute Pancreatitis (BISAP), Modified Early Warning Score (MEWS), serum Ca2+, similarly hereinafter, and red cell distribution width (RDW) for predicting the severity grade of acute pancreatitis and to develop and verify a more accurate scoring system to predict the severity of AP. In 302 patients with AP, we calculated BISAP and MEWS scores and conducted regression analyses on the relationships of BISAP scoring, RDW, MEWS, and serum Ca2+ with the severity of AP using single-factor logistics. The variables with statistical significance in the single-factor logistic regression were used in a multi-factor logistic regression model; forward stepwise regression was used to screen variables and build a multi-factor prediction model. A receiver operating characteristic curve (ROC curve) was constructed, and the significance of multi- and single-factor prediction models in predicting the severity of AP using the area under the ROC curve (AUC) was evaluated. The internal validity of the model was verified through bootstrapping. Among 302 patients with AP, 209 had mild acute pancreatitis (MAP) and 93 had severe acute pancreatitis (SAP). According to single-factor logistic regression analysis, we found that BISAP, MEWS and serum Ca2+ are prediction indexes of the severity of AP (P-value<0.001), whereas RDW is not a prediction index of AP severity (P-value>0.05). The multi-factor logistic regression analysis showed that BISAP and serum Ca2+ are independent prediction indexes of AP severity (P-value<0.001), and MEWS is not an independent prediction index of AP severity (P-value>0.05); BISAP is negatively related to serum Ca2+ (r=-0.330, P-value<0.001). The constructed model is as follows: ln()=7.306+1.151*BISAP-4.516*serum Ca2+. The predictive ability of each model for SAP follows the order of the combined BISAP and serum Ca2+ prediction model>Ca2+>BISAP. There is no statistical significance for the predictive ability of BISAP and serum Ca2+ (P-value>0.05); however, there is remarkable statistical significance for the predictive ability using the newly built prediction model as well as BISAP and serum Ca2+ individually (P-value<0.01). Verification of the internal validity of the models by bootstrapping is favorable. BISAP and serum Ca2+ have high predictive value for the severity of AP. However, the model built by combining BISAP and serum Ca2+ is remarkably superior to those of BISAP and serum Ca2+ individually. Furthermore, this model is simple, practical and appropriate for clinical use. Copyright © 2016. Published by Elsevier Masson SAS.

The Application of the Cumulative Logistic Regression Model to Automated Essay Scoring

ERIC Educational Resources Information Center

Haberman, Shelby J.; Sinharay, Sandip

2010-01-01

Most automated essay scoring programs use a linear regression model to predict an essay score from several essay features. This article applied a cumulative logit model instead of the linear regression model to automated essay scoring. Comparison of the performances of the linear regression model and the cumulative logit model was performed on a…

RRegrs: an R package for computer-aided model selection with multiple regression models.

PubMed

Tsiliki, Georgia; Munteanu, Cristian R; Seoane, Jose A; Fernandez-Lozano, Carlos; Sarimveis, Haralambos; Willighagen, Egon L

2015-01-01

Predictive regression models can be created with many different modelling approaches. Choices need to be made for data set splitting, cross-validation methods, specific regression parameters and best model criteria, as they all affect the accuracy and efficiency of the produced predictive models, and therefore, raising model reproducibility and comparison issues. Cheminformatics and bioinformatics are extensively using predictive modelling and exhibit a need for standardization of these methodologies in order to assist model selection and speed up the process of predictive model development. A tool accessible to all users, irrespectively of their statistical knowledge, would be valuable if it tests several simple and complex regression models and validation schemes, produce unified reports, and offer the option to be integrated into more extensive studies. Additionally, such methodology should be implemented as a free programming package, in order to be continuously adapted and redistributed by others. We propose an integrated framework for creating multiple regression models, called RRegrs. The tool offers the option of ten simple and complex regression methods combined with repeated 10-fold and leave-one-out cross-validation. Methods include Multiple Linear regression, Generalized Linear Model with Stepwise Feature Selection, Partial Least Squares regression, Lasso regression, and Support Vector Machines Recursive Feature Elimination. The new framework is an automated fully validated procedure which produces standardized reports to quickly oversee the impact of choices in modelling algorithms and assess the model and cross-validation results. The methodology was implemented as an open source R package, available at https://www.github.com/enanomapper/RRegrs, by reusing and extending on the caret package. The universality of the new methodology is demonstrated using five standard data sets from different scientific fields. Its efficiency in cheminformatics and QSAR modelling is shown with three use cases: proteomics data for surface-modified gold nanoparticles, nano-metal oxides descriptor data, and molecular descriptors for acute aquatic toxicity data. The results show that for all data sets RRegrs reports models with equal or better performance for both training and test sets than those reported in the original publications. Its good performance as well as its adaptability in terms of parameter optimization could make RRegrs a popular framework to assist the initial exploration of predictive models, and with that, the design of more comprehensive in silico screening applications.Graphical abstractRRegrs is a computer-aided model selection framework for R multiple regression models; this is a fully validated procedure with application to QSAR modelling.

Ridge regression for predicting elastic moduli and hardness of calcium aluminosilicate glasses

NASA Astrophysics Data System (ADS)

Deng, Yifan; Zeng, Huidan; Jiang, Yejia; Chen, Guorong; Chen, Jianding; Sun, Luyi

2018-03-01

It is of great significance to design glasses with satisfactory mechanical properties predictively through modeling. Among various modeling methods, data-driven modeling is such a reliable approach that can dramatically shorten research duration, cut research cost and accelerate the development of glass materials. In this work, the ridge regression (RR) analysis was used to construct regression models for predicting the compositional dependence of CaO-Al2O3-SiO2 glass elastic moduli (Shear, Bulk, and Young’s moduli) and hardness based on the ternary diagram of the compositions. The property prediction over a large glass composition space was accomplished with known experimental data of various compositions in the literature, and the simulated results are in good agreement with the measured ones. This regression model can serve as a facile and effective tool for studying the relationship between the compositions and the property, enabling high-efficient design of glasses to meet the requirements for specific elasticity and hardness.

Application of General Regression Neural Network to the Prediction of LOD Change

NASA Astrophysics Data System (ADS)

Zhang, Xiao-Hong; Wang, Qi-Jie; Zhu, Jian-Jun; Zhang, Hao

2012-01-01

Traditional methods for predicting the change in length of day (LOD change) are mainly based on some linear models, such as the least square model and autoregression model, etc. However, the LOD change comprises complicated non-linear factors and the prediction effect of the linear models is always not so ideal. Thus, a kind of non-linear neural network — general regression neural network (GRNN) model is tried to make the prediction of the LOD change and the result is compared with the predicted results obtained by taking advantage of the BP (back propagation) neural network model and other models. The comparison result shows that the application of the GRNN to the prediction of the LOD change is highly effective and feasible.

An analysis of input errors in precipitation-runoff models using regression with errors in the independent variables

USGS Publications Warehouse

Troutman, Brent M.

1982-01-01

Errors in runoff prediction caused by input data errors are analyzed by treating precipitation-runoff models as regression (conditional expectation) models. Independent variables of the regression consist of precipitation and other input measurements; the dependent variable is runoff. In models using erroneous input data, prediction errors are inflated and estimates of expected storm runoff for given observed input variables are biased. This bias in expected runoff estimation results in biased parameter estimates if these parameter estimates are obtained by a least squares fit of predicted to observed runoff values. The problems of error inflation and bias are examined in detail for a simple linear regression of runoff on rainfall and for a nonlinear U.S. Geological Survey precipitation-runoff model. Some implications for flood frequency analysis are considered. A case study using a set of data from Turtle Creek near Dallas, Texas illustrates the problems of model input errors.

A model for prediction of color change after tooth bleaching based on CIELAB color space

NASA Astrophysics Data System (ADS)

Herrera, Luis J.; Santana, Janiley; Yebra, Ana; Rivas, María. José; Pulgar, Rosa; Pérez, María. M.

2017-08-01

An experimental study aiming to develop a model based on CIELAB color space for prediction of color change after a tooth bleaching procedure is presented. Multivariate linear regression models were obtained to predict the L*, a*, b* and W* post-bleaching values using the pre-bleaching L*, a*and b*values. Moreover, univariate linear regression models were obtained to predict the variation in chroma (C*), hue angle (h°) and W*. The results demonstrated that is possible to estimate color change when using a carbamide peroxide tooth-bleaching system. The models obtained can be applied in clinic to predict the colour change after bleaching.

ℓ(p)-Norm multikernel learning approach for stock market price forecasting.

PubMed

Shao, Xigao; Wu, Kun; Liao, Bifeng

2012-01-01

Linear multiple kernel learning model has been used for predicting financial time series. However, ℓ(1)-norm multiple support vector regression is rarely observed to outperform trivial baselines in practical applications. To allow for robust kernel mixtures that generalize well, we adopt ℓ(p)-norm multiple kernel support vector regression (1 ≤ p < ∞) as a stock price prediction model. The optimization problem is decomposed into smaller subproblems, and the interleaved optimization strategy is employed to solve the regression model. The model is evaluated on forecasting the daily stock closing prices of Shanghai Stock Index in China. Experimental results show that our proposed model performs better than ℓ(1)-norm multiple support vector regression model.

Estimating current and future streamflow characteristics at ungaged sites, central and eastern Montana, with application to evaluating effects of climate change on fish populations

USGS Publications Warehouse

Sando, Roy; Chase, Katherine J.

2017-03-23

A common statistical procedure for estimating streamflow statistics at ungaged locations is to develop a relational model between streamflow and drainage basin characteristics at gaged locations using least squares regression analysis; however, least squares regression methods are parametric and make constraining assumptions about the data distribution. The random forest regression method provides an alternative nonparametric method for estimating streamflow characteristics at ungaged sites and requires that the data meet fewer statistical conditions than least squares regression methods.Random forest regression analysis was used to develop predictive models for 89 streamflow characteristics using Precipitation-Runoff Modeling System simulated streamflow data and drainage basin characteristics at 179 sites in central and eastern Montana. The predictive models were developed from streamflow data simulated for current (baseline, water years 1982–99) conditions and three future periods (water years 2021–38, 2046–63, and 2071–88) under three different climate-change scenarios. These predictive models were then used to predict streamflow characteristics for baseline conditions and three future periods at 1,707 fish sampling sites in central and eastern Montana. The average root mean square error for all predictive models was about 50 percent. When streamflow predictions at 23 fish sampling sites were compared to nearby locations with simulated data, the mean relative percent difference was about 43 percent. When predictions were compared to streamflow data recorded at 21 U.S. Geological Survey streamflow-gaging stations outside of the calibration basins, the average mean absolute percent error was about 73 percent.

Genetic improvement in mastitis resistance: comparison of selection criteria from cross-sectional and random regression sire models for somatic cell score.

PubMed

Odegård, J; Klemetsdal, G; Heringstad, B

2005-04-01

Several selection criteria for reducing incidence of mastitis were developed from a random regression sire model for test-day somatic cell score (SCS). For comparison, sire transmitting abilities were also predicted based on a cross-sectional model for lactation mean SCS. Only first-crop daughters were used in genetic evaluation of SCS, and the different selection criteria were compared based on their correlation with incidence of clinical mastitis in second-crop daughters (measured as mean daughter deviations). Selection criteria were predicted based on both complete and reduced first-crop daughter groups (261 or 65 daughters per sire, respectively). For complete daughter groups, predicted transmitting abilities at around 30 d in milk showed the best predictive ability for incidence of clinical mastitis, closely followed by average predicted transmitting abilities over the entire lactation. Both of these criteria were derived from the random regression model. These selection criteria improved accuracy of selection by approximately 2% relative to a cross-sectional model. However, for reduced daughter groups, the cross-sectional model yielded increased predictive ability compared with the selection criteria based on the random regression model. This result may be explained by the cross-sectional model being more robust, i.e., less sensitive to precision of (co)variance components estimates and effects of data structure.

Can We Use Regression Modeling to Quantify Mean Annual Streamflow at a Global-Scale?

NASA Astrophysics Data System (ADS)

Barbarossa, V.; Huijbregts, M. A. J.; Hendriks, J. A.; Beusen, A.; Clavreul, J.; King, H.; Schipper, A.

2016-12-01

Quantifying mean annual flow of rivers (MAF) at ungauged sites is essential for a number of applications, including assessments of global water supply, ecosystem integrity and water footprints. MAF can be quantified with spatially explicit process-based models, which might be overly time-consuming and data-intensive for this purpose, or with empirical regression models that predict MAF based on climate and catchment characteristics. Yet, regression models have mostly been developed at a regional scale and the extent to which they can be extrapolated to other regions is not known. In this study, we developed a global-scale regression model for MAF using observations of discharge and catchment characteristics from 1,885 catchments worldwide, ranging from 2 to 106 km2 in size. In addition, we compared the performance of the regression model with the predictive ability of the spatially explicit global hydrological model PCR-GLOBWB [van Beek et al., 2011] by comparing results from both models to independent measurements. We obtained a regression model explaining 89% of the variance in MAF based on catchment area, mean annual precipitation and air temperature, average slope and elevation. The regression model performed better than PCR-GLOBWB for the prediction of MAF, as root-mean-square error values were lower (0.29 - 0.38 compared to 0.49 - 0.57) and the modified index of agreement was higher (0.80 - 0.83 compared to 0.72 - 0.75). Our regression model can be applied globally at any point of the river network, provided that the input parameters are within the range of values employed in the calibration of the model. The performance is reduced for water scarce regions and further research should focus on improving such an aspect for regression-based global hydrological models.

Bootstrap Prediction Intervals in Non-Parametric Regression with Applications to Anomaly Detection

NASA Technical Reports Server (NTRS)

Kumar, Sricharan; Srivistava, Ashok N.

2012-01-01

Prediction intervals provide a measure of the probable interval in which the outputs of a regression model can be expected to occur. Subsequently, these prediction intervals can be used to determine if the observed output is anomalous or not, conditioned on the input. In this paper, a procedure for determining prediction intervals for outputs of nonparametric regression models using bootstrap methods is proposed. Bootstrap methods allow for a non-parametric approach to computing prediction intervals with no specific assumptions about the sampling distribution of the noise or the data. The asymptotic fidelity of the proposed prediction intervals is theoretically proved. Subsequently, the validity of the bootstrap based prediction intervals is illustrated via simulations. Finally, the bootstrap prediction intervals are applied to the problem of anomaly detection on aviation data.

Nonlinear-regression flow model of the Gulf Coast aquifer systems in the south-central United States

USGS Publications Warehouse

Kuiper, L.K.

1994-01-01

A multiple-regression methodology was used to help answer questions concerning model reliability, and to calibrate a time-dependent variable-density ground-water flow model of the gulf coast aquifer systems in the south-central United States. More than 40 regression models with 2 to 31 regressions parameters are used and detailed results are presented for 12 of the models. More than 3,000 values for grid-element volume-averaged head and hydraulic conductivity are used for the regression model observations. Calculated prediction interval half widths, though perhaps inaccurate due to a lack of normality of the residuals, are the smallest for models with only four regression parameters. In addition, the root-mean weighted residual decreases very little with an increase in the number of regression parameters. The various models showed considerable overlap between the prediction inter- vals for shallow head and hydraulic conductivity. Approximate 95-percent prediction interval half widths for volume-averaged freshwater head exceed 108 feet; for volume-averaged base 10 logarithm hydraulic conductivity, they exceed 0.89. All of the models are unreliable for the prediction of head and ground-water flow in the deeper parts of the aquifer systems, including the amount of flow coming from the underlying geopressured zone. Truncating the domain of solution of one model to exclude that part of the system having a ground-water density greater than 1.005 grams per cubic centimeter or to exclude that part of the systems below a depth of 3,000 feet, and setting the density to that of freshwater does not appreciably change the results for head and ground-water flow, except for locations close to the truncation surface.

Bayesian Unimodal Density Regression for Causal Inference

ERIC Educational Resources Information Center

Karabatsos, George; Walker, Stephen G.

2011-01-01

Karabatsos and Walker (2011) introduced a new Bayesian nonparametric (BNP) regression model. Through analyses of real and simulated data, they showed that the BNP regression model outperforms other parametric and nonparametric regression models of common use, in terms of predictive accuracy of the outcome (dependent) variable. The other,…

Developing and testing a global-scale regression model to quantify mean annual streamflow

NASA Astrophysics Data System (ADS)

Barbarossa, Valerio; Huijbregts, Mark A. J.; Hendriks, A. Jan; Beusen, Arthur H. W.; Clavreul, Julie; King, Henry; Schipper, Aafke M.

2017-01-01

Quantifying mean annual flow of rivers (MAF) at ungauged sites is essential for assessments of global water supply, ecosystem integrity and water footprints. MAF can be quantified with spatially explicit process-based models, which might be overly time-consuming and data-intensive for this purpose, or with empirical regression models that predict MAF based on climate and catchment characteristics. Yet, regression models have mostly been developed at a regional scale and the extent to which they can be extrapolated to other regions is not known. In this study, we developed a global-scale regression model for MAF based on a dataset unprecedented in size, using observations of discharge and catchment characteristics from 1885 catchments worldwide, measuring between 2 and 106 km2. In addition, we compared the performance of the regression model with the predictive ability of the spatially explicit global hydrological model PCR-GLOBWB by comparing results from both models to independent measurements. We obtained a regression model explaining 89% of the variance in MAF based on catchment area and catchment averaged mean annual precipitation and air temperature, slope and elevation. The regression model performed better than PCR-GLOBWB for the prediction of MAF, as root-mean-square error (RMSE) values were lower (0.29-0.38 compared to 0.49-0.57) and the modified index of agreement (d) was higher (0.80-0.83 compared to 0.72-0.75). Our regression model can be applied globally to estimate MAF at any point of the river network, thus providing a feasible alternative to spatially explicit process-based global hydrological models.

Markovian prediction of future values for food grains in the economic survey

NASA Astrophysics Data System (ADS)

Sathish, S.; Khadar Babu, S. K.

2017-11-01

Now-a-days prediction and forecasting are plays a vital role in research. For prediction, regression is useful to predict the future value and current value on production process. In this paper, we assume food grain production exhibit Markov chain dependency and time homogeneity. The economic generative performance evaluation the balance time artificial fertilization different level in Estrusdetection using a daily Markov chain model. Finally, Markov process prediction gives better performance compare with Regression model.

Regression model estimation of early season crop proportions: North Dakota, some preliminary results

NASA Technical Reports Server (NTRS)

Lin, K. K. (Principal Investigator)

1982-01-01

To estimate crop proportions early in the season, an approach is proposed based on: use of a regression-based prediction equation to obtain an a priori estimate for specific major crop groups; modification of this estimate using current-year LANDSAT and weather data; and a breakdown of the major crop groups into specific crops by regression models. Results from the development and evaluation of appropriate regression models for the first portion of the proposed approach are presented. The results show that the model predicts 1980 crop proportions very well at both county and crop reporting district levels. In terms of planted acreage, the model underpredicted 9.1 percent of the 1980 published data on planted acreage at the county level. It predicted almost exactly the 1980 published data on planted acreage at the crop reporting district level and overpredicted the planted acreage by just 0.92 percent.

Conformal Regression for Quantitative Structure-Activity Relationship Modeling-Quantifying Prediction Uncertainty.

PubMed

Svensson, Fredrik; Aniceto, Natalia; Norinder, Ulf; Cortes-Ciriano, Isidro; Spjuth, Ola; Carlsson, Lars; Bender, Andreas

2018-05-29

Making predictions with an associated confidence is highly desirable as it facilitates decision making and resource prioritization. Conformal regression is a machine learning framework that allows the user to define the required confidence and delivers predictions that are guaranteed to be correct to the selected extent. In this study, we apply conformal regression to model molecular properties and bioactivity values and investigate different ways to scale the resultant prediction intervals to create as efficient (i.e., narrow) regressors as possible. Different algorithms to estimate the prediction uncertainty were used to normalize the prediction ranges, and the different approaches were evaluated on 29 publicly available data sets. Our results show that the most efficient conformal regressors are obtained when using the natural exponential of the ensemble standard deviation from the underlying random forest to scale the prediction intervals, but other approaches were almost as efficient. This approach afforded an average prediction range of 1.65 pIC50 units at the 80% confidence level when applied to bioactivity modeling. The choice of nonconformity function has a pronounced impact on the average prediction range with a difference of close to one log unit in bioactivity between the tightest and widest prediction range. Overall, conformal regression is a robust approach to generate bioactivity predictions with associated confidence.

Genomic Bayesian functional regression models with interactions for predicting wheat grain yield using hyper-spectral image data.

PubMed

Montesinos-López, Abelardo; Montesinos-López, Osval A; Cuevas, Jaime; Mata-López, Walter A; Burgueño, Juan; Mondal, Sushismita; Huerta, Julio; Singh, Ravi; Autrique, Enrique; González-Pérez, Lorena; Crossa, José

2017-01-01

Modern agriculture uses hyperspectral cameras that provide hundreds of reflectance data at discrete narrow bands in many environments. These bands often cover the whole visible light spectrum and part of the infrared and ultraviolet light spectra. With the bands, vegetation indices are constructed for predicting agronomically important traits such as grain yield and biomass. However, since vegetation indices only use some wavelengths (referred to as bands), we propose using all bands simultaneously as predictor variables for the primary trait grain yield; results of several multi-environment maize (Aguate et al. in Crop Sci 57(5):1-8, 2017) and wheat (Montesinos-López et al. in Plant Methods 13(4):1-23, 2017) breeding trials indicated that using all bands produced better prediction accuracy than vegetation indices. However, until now, these prediction models have not accounted for the effects of genotype × environment (G × E) and band × environment (B × E) interactions incorporating genomic or pedigree information. In this study, we propose Bayesian functional regression models that take into account all available bands, genomic or pedigree information, the main effects of lines and environments, as well as G × E and B × E interaction effects. The data set used is comprised of 976 wheat lines evaluated for grain yield in three environments (Drought, Irrigated and Reduced Irrigation). The reflectance data were measured in 250 discrete narrow bands ranging from 392 to 851 nm (nm). The proposed Bayesian functional regression models were implemented using two types of basis: B-splines and Fourier. Results of the proposed Bayesian functional regression models, including all the wavelengths for predicting grain yield, were compared with results from conventional models with and without bands. We observed that the models with B × E interaction terms were the most accurate models, whereas the functional regression models (with B-splines and Fourier basis) and the conventional models performed similarly in terms of prediction accuracy. However, the functional regression models are more parsimonious and computationally more efficient because the number of beta coefficients to be estimated is 21 (number of basis), rather than estimating the 250 regression coefficients for all bands. In this study adding pedigree or genomic information did not increase prediction accuracy.

Dynamic prediction in functional concurrent regression with an application to child growth.

PubMed

Leroux, Andrew; Xiao, Luo; Crainiceanu, Ciprian; Checkley, William

2018-04-15

In many studies, it is of interest to predict the future trajectory of subjects based on their historical data, referred to as dynamic prediction. Mixed effects models have traditionally been used for dynamic prediction. However, the commonly used random intercept and slope model is often not sufficiently flexible for modeling subject-specific trajectories. In addition, there may be useful exposures/predictors of interest that are measured concurrently with the outcome, complicating dynamic prediction. To address these problems, we propose a dynamic functional concurrent regression model to handle the case where both the functional response and the functional predictors are irregularly measured. Currently, such a model cannot be fit by existing software. We apply the model to dynamically predict children's length conditional on prior length, weight, and baseline covariates. Inference on model parameters and subject-specific trajectories is conducted using the mixed effects representation of the proposed model. An extensive simulation study shows that the dynamic functional regression model provides more accurate estimation and inference than existing methods. Methods are supported by fast, flexible, open source software that uses heavily tested smoothing techniques. © 2017 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.

Adjustment of regional regression models of urban-runoff quality using data for Chattanooga, Knoxville, and Nashville, Tennessee

USGS Publications Warehouse

Hoos, Anne B.; Patel, Anant R.

1996-01-01

Model-adjustment procedures were applied to the combined data bases of storm-runoff quality for Chattanooga, Knoxville, and Nashville, Tennessee, to improve predictive accuracy for storm-runoff quality for urban watersheds in these three cities and throughout Middle and East Tennessee. Data for 45 storms at 15 different sites (five sites in each city) constitute the data base. Comparison of observed values of storm-runoff load and event-mean concentration to the predicted values from the regional regression models for 10 constituents shows prediction errors, as large as 806,000 percent. Model-adjustment procedures, which combine the regional model predictions with local data, are applied to improve predictive accuracy. Standard error of estimate after model adjustment ranges from 67 to 322 percent. Calibration results may be biased due to sampling error in the Tennessee data base. The relatively large values of standard error of estimate for some of the constituent models, although representing significant reduction (at least 50 percent) in prediction error compared to estimation with unadjusted regional models, may be unacceptable for some applications. The user may wish to collect additional local data for these constituents and repeat the analysis, or calibrate an independent local regression model.

Genomic-Enabled Prediction of Ordinal Data with Bayesian Logistic Ordinal Regression.

PubMed

Montesinos-López, Osval A; Montesinos-López, Abelardo; Crossa, José; Burgueño, Juan; Eskridge, Kent

2015-08-18

Most genomic-enabled prediction models developed so far assume that the response variable is continuous and normally distributed. The exception is the probit model, developed for ordered categorical phenotypes. In statistical applications, because of the easy implementation of the Bayesian probit ordinal regression (BPOR) model, Bayesian logistic ordinal regression (BLOR) is implemented rarely in the context of genomic-enabled prediction [sample size (n) is much smaller than the number of parameters (p)]. For this reason, in this paper we propose a BLOR model using the Pólya-Gamma data augmentation approach that produces a Gibbs sampler with similar full conditional distributions of the BPOR model and with the advantage that the BPOR model is a particular case of the BLOR model. We evaluated the proposed model by using simulation and two real data sets. Results indicate that our BLOR model is a good alternative for analyzing ordinal data in the context of genomic-enabled prediction with the probit or logit link. Copyright © 2015 Montesinos-López et al.

Multivariate regression model for predicting lumber grade volumes of northern red oak sawlogs

Treesearch

Daniel A. Yaussy; Robert L. Brisbin

1983-01-01

A multivariate regression model was developed to predict green board-foot yields for the seven common factory lumber grades processed from northern red oak (Quercus rubra L.) factory grade logs. The model uses the standard log measurements of grade, scaling diameter, length, and percent defect. It was validated with an independent data set. The model...

Predictive and mechanistic multivariate linear regression models for reaction development

PubMed Central

Santiago, Celine B.; Guo, Jing-Yao

2018-01-01

Multivariate Linear Regression (MLR) models utilizing computationally-derived and empirically-derived physical organic molecular descriptors are described in this review. Several reports demonstrating the effectiveness of this methodological approach towards reaction optimization and mechanistic interrogation are discussed. A detailed protocol to access quantitative and predictive MLR models is provided as a guide for model development and parameter analysis. PMID:29719711

Three methods to construct predictive models using logistic regression and likelihood ratios to facilitate adjustment for pretest probability give similar results.

PubMed

Chan, Siew Foong; Deeks, Jonathan J; Macaskill, Petra; Irwig, Les

2008-01-01

To compare three predictive models based on logistic regression to estimate adjusted likelihood ratios allowing for interdependency between diagnostic variables (tests). This study was a review of the theoretical basis, assumptions, and limitations of published models; and a statistical extension of methods and application to a case study of the diagnosis of obstructive airways disease based on history and clinical examination. Albert's method includes an offset term to estimate an adjusted likelihood ratio for combinations of tests. Spiegelhalter and Knill-Jones method uses the unadjusted likelihood ratio for each test as a predictor and computes shrinkage factors to allow for interdependence. Knottnerus' method differs from the other methods because it requires sequencing of tests, which limits its application to situations where there are few tests and substantial data. Although parameter estimates differed between the models, predicted "posttest" probabilities were generally similar. Construction of predictive models using logistic regression is preferred to the independence Bayes' approach when it is important to adjust for dependency of tests errors. Methods to estimate adjusted likelihood ratios from predictive models should be considered in preference to a standard logistic regression model to facilitate ease of interpretation and application. Albert's method provides the most straightforward approach.

A novel strategy for forensic age prediction by DNA methylation and support vector regression model

PubMed Central

Xu, Cheng; Qu, Hongzhu; Wang, Guangyu; Xie, Bingbing; Shi, Yi; Yang, Yaran; Zhao, Zhao; Hu, Lan; Fang, Xiangdong; Yan, Jiangwei; Feng, Lei

2015-01-01

High deviations resulting from prediction model, gender and population difference have limited age estimation application of DNA methylation markers. Here we identified 2,957 novel age-associated DNA methylation sites (P < 0.01 and R2 > 0.5) in blood of eight pairs of Chinese Han female monozygotic twins. Among them, nine novel sites (false discovery rate < 0.01), along with three other reported sites, were further validated in 49 unrelated female volunteers with ages of 20–80 years by Sequenom Massarray. A total of 95 CpGs were covered in the PCR products and 11 of them were built the age prediction models. After comparing four different models including, multivariate linear regression, multivariate nonlinear regression, back propagation neural network and support vector regression, SVR was identified as the most robust model with the least mean absolute deviation from real chronological age (2.8 years) and an average accuracy of 4.7 years predicted by only six loci from the 11 loci, as well as an less cross-validated error compared with linear regression model. Our novel strategy provides an accurate measurement that is highly useful in estimating the individual age in forensic practice as well as in tracking the aging process in other related applications. PMID:26635134

ℓ p-Norm Multikernel Learning Approach for Stock Market Price Forecasting

PubMed Central

Shao, Xigao; Wu, Kun; Liao, Bifeng

2012-01-01

Linear multiple kernel learning model has been used for predicting financial time series. However, ℓ 1-norm multiple support vector regression is rarely observed to outperform trivial baselines in practical applications. To allow for robust kernel mixtures that generalize well, we adopt ℓ p-norm multiple kernel support vector regression (1 ≤ p < ∞) as a stock price prediction model. The optimization problem is decomposed into smaller subproblems, and the interleaved optimization strategy is employed to solve the regression model. The model is evaluated on forecasting the daily stock closing prices of Shanghai Stock Index in China. Experimental results show that our proposed model performs better than ℓ 1-norm multiple support vector regression model. PMID:23365561

Novel applications of multitask learning and multiple output regression to multiple genetic trait prediction.

PubMed

He, Dan; Kuhn, David; Parida, Laxmi

2016-06-15

Given a set of biallelic molecular markers, such as SNPs, with genotype values encoded numerically on a collection of plant, animal or human samples, the goal of genetic trait prediction is to predict the quantitative trait values by simultaneously modeling all marker effects. Genetic trait prediction is usually represented as linear regression models. In many cases, for the same set of samples and markers, multiple traits are observed. Some of these traits might be correlated with each other. Therefore, modeling all the multiple traits together may improve the prediction accuracy. In this work, we view the multitrait prediction problem from a machine learning angle: as either a multitask learning problem or a multiple output regression problem, depending on whether different traits share the same genotype matrix or not. We then adapted multitask learning algorithms and multiple output regression algorithms to solve the multitrait prediction problem. We proposed a few strategies to improve the least square error of the prediction from these algorithms. Our experiments show that modeling multiple traits together could improve the prediction accuracy for correlated traits. The programs we used are either public or directly from the referred authors, such as MALSAR (http://www.public.asu.edu/~jye02/Software/MALSAR/) package. The Avocado data set has not been published yet and is available upon request. dhe@us.ibm.com. © The Author 2016. Published by Oxford University Press.

Comparison and validation of statistical methods for predicting power outage durations in the event of hurricanes.

PubMed

Nateghi, Roshanak; Guikema, Seth D; Quiring, Steven M

2011-12-01

This article compares statistical methods for modeling power outage durations during hurricanes and examines the predictive accuracy of these methods. Being able to make accurate predictions of power outage durations is valuable because the information can be used by utility companies to plan their restoration efforts more efficiently. This information can also help inform customers and public agencies of the expected outage times, enabling better collective response planning, and coordination of restoration efforts for other critical infrastructures that depend on electricity. In the long run, outage duration estimates for future storm scenarios may help utilities and public agencies better allocate risk management resources to balance the disruption from hurricanes with the cost of hardening power systems. We compare the out-of-sample predictive accuracy of five distinct statistical models for estimating power outage duration times caused by Hurricane Ivan in 2004. The methods compared include both regression models (accelerated failure time (AFT) and Cox proportional hazard models (Cox PH)) and data mining techniques (regression trees, Bayesian additive regression trees (BART), and multivariate additive regression splines). We then validate our models against two other hurricanes. Our results indicate that BART yields the best prediction accuracy and that it is possible to predict outage durations with reasonable accuracy. © 2011 Society for Risk Analysis.

Comparison of integrated clustering methods for accurate and stable prediction of building energy consumption data

DOE PAGES

Hsu, David

2015-09-27

Clustering methods are often used to model energy consumption for two reasons. First, clustering is often used to process data and to improve the predictive accuracy of subsequent energy models. Second, stable clusters that are reproducible with respect to non-essential changes can be used to group, target, and interpret observed subjects. However, it is well known that clustering methods are highly sensitive to the choice of algorithms and variables. This can lead to misleading assessments of predictive accuracy and mis-interpretation of clusters in policymaking. This paper therefore introduces two methods to the modeling of energy consumption in buildings: clusterwise regression,more » also known as latent class regression, which integrates clustering and regression simultaneously; and cluster validation methods to measure stability. Using a large dataset of multifamily buildings in New York City, clusterwise regression is compared to common two-stage algorithms that use K-means and model-based clustering with linear regression. Predictive accuracy is evaluated using 20-fold cross validation, and the stability of the perturbed clusters is measured using the Jaccard coefficient. These results show that there seems to be an inherent tradeoff between prediction accuracy and cluster stability. This paper concludes by discussing which clustering methods may be appropriate for different analytical purposes.« less

Multivariate Analysis of Seismic Field Data

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

Alam, M. Kathleen

1999-06-01

This report includes the details of the model building procedure and prediction of seismic field data. Principal Components Regression, a multivariate analysis technique, was used to model seismic data collected as two pieces of equipment were cycled on and off. Models built that included only the two pieces of equipment of interest had trouble predicting data containing signals not included in the model. Evidence for poor predictions came from the prediction curves as well as spectral F-ratio plots. Once the extraneous signals were included in the model, predictions improved dramatically. While Principal Components Regression performed well for the present datamore » sets, the present data analysis suggests further work will be needed to develop more robust modeling methods as the data become more complex.« less

Modeling time-to-event (survival) data using classification tree analysis.

PubMed

Linden, Ariel; Yarnold, Paul R

2017-12-01

Time to the occurrence of an event is often studied in health research. Survival analysis differs from other designs in that follow-up times for individuals who do not experience the event by the end of the study (called censored) are accounted for in the analysis. Cox regression is the standard method for analysing censored data, but the assumptions required of these models are easily violated. In this paper, we introduce classification tree analysis (CTA) as a flexible alternative for modelling censored data. Classification tree analysis is a "decision-tree"-like classification model that provides parsimonious, transparent (ie, easy to visually display and interpret) decision rules that maximize predictive accuracy, derives exact P values via permutation tests, and evaluates model cross-generalizability. Using empirical data, we identify all statistically valid, reproducible, longitudinally consistent, and cross-generalizable CTA survival models and then compare their predictive accuracy to estimates derived via Cox regression and an unadjusted naïve model. Model performance is assessed using integrated Brier scores and a comparison between estimated survival curves. The Cox regression model best predicts average incidence of the outcome over time, whereas CTA survival models best predict either relatively high, or low, incidence of the outcome over time. Classification tree analysis survival models offer many advantages over Cox regression, such as explicit maximization of predictive accuracy, parsimony, statistical robustness, and transparency. Therefore, researchers interested in accurate prognoses and clear decision rules should consider developing models using the CTA-survival framework. © 2017 John Wiley & Sons, Ltd.

Consequences of kriging and land use regression for PM2.5 predictions in epidemiologic analyses: Insights into spatial variability using high-resolution satellite data

PubMed Central

Alexeeff, Stacey E.; Schwartz, Joel; Kloog, Itai; Chudnovsky, Alexandra; Koutrakis, Petros; Coull, Brent A.

2016-01-01

Many epidemiological studies use predicted air pollution exposures as surrogates for true air pollution levels. These predicted exposures contain exposure measurement error, yet simulation studies have typically found negligible bias in resulting health effect estimates. However, previous studies typically assumed a statistical spatial model for air pollution exposure, which may be oversimplified. We address this shortcoming by assuming a realistic, complex exposure surface derived from fine-scale (1km x 1km) remote-sensing satellite data. Using simulation, we evaluate the accuracy of epidemiological health effect estimates in linear and logistic regression when using spatial air pollution predictions from kriging and land use regression models. We examined chronic (long-term) and acute (short-term) exposure to air pollution. Results varied substantially across different scenarios. Exposure models with low out-of-sample R2 yielded severe biases in the health effect estimates of some models, ranging from 60% upward bias to 70% downward bias. One land use regression exposure model with greater than 0.9 out-of-sample R2 yielded upward biases up to 13% for acute health effect estimates. Almost all models drastically underestimated the standard errors. Land use regression models performed better in chronic effects simulations. These results can help researchers when interpreting health effect estimates in these types of studies. PMID:24896768

An empirical model for estimating annual consumption by freshwater fish populations

USGS Publications Warehouse

Liao, H.; Pierce, C.L.; Larscheid, J.G.

2005-01-01

Population consumption is an important process linking predator populations to their prey resources. Simple tools are needed to enable fisheries managers to estimate population consumption. We assembled 74 individual estimates of annual consumption by freshwater fish populations and their mean annual population size, 41 of which also included estimates of mean annual biomass. The data set included 14 freshwater fish species from 10 different bodies of water. From this data set we developed two simple linear regression models predicting annual population consumption. Log-transformed population size explained 94% of the variation in log-transformed annual population consumption. Log-transformed biomass explained 98% of the variation in log-transformed annual population consumption. We quantified the accuracy of our regressions and three alternative consumption models as the mean percent difference from observed (bioenergetics-derived) estimates in a test data set. Predictions from our population-size regression matched observed consumption estimates poorly (mean percent difference = 222%). Predictions from our biomass regression matched observed consumption reasonably well (mean percent difference = 24%). The biomass regression was superior to an alternative model, similar in complexity, and comparable to two alternative models that were more complex and difficult to apply. Our biomass regression model, log10(consumption) = 0.5442 + 0.9962??log10(biomass), will be a useful tool for fishery managers, enabling them to make reasonably accurate annual population consumption predictions from mean annual biomass estimates. ?? Copyright by the American Fisheries Society 2005.

Prediction of bovine milk technological traits from mid-infrared spectroscopy analysis in dairy cows.

PubMed

Visentin, G; McDermott, A; McParland, S; Berry, D P; Kenny, O A; Brodkorb, A; Fenelon, M A; De Marchi, M

2015-09-01

Rapid, cost-effective monitoring of milk technological traits is a significant challenge for dairy industries specialized in cheese manufacturing. The objective of the present study was to investigate the ability of mid-infrared spectroscopy to predict rennet coagulation time, curd-firming time, curd firmness at 30 and 60min after rennet addition, heat coagulation time, casein micelle size, and pH in cow milk samples, and to quantify associations between these milk technological traits and conventional milk quality traits. Samples (n=713) were collected from 605 cows from multiple herds; the samples represented multiple breeds, stages of lactation, parities, and milking times. Reference analyses were undertaken in accordance with standardized methods, and mid-infrared spectra in the range of 900 to 5,000cm(-1) were available for all samples. Prediction models were developed using partial least squares regression, and prediction accuracy was based on both cross and external validation. The proportion of variance explained by the prediction models in external validation was greatest for pH (71%), followed by rennet coagulation time (55%) and milk heat coagulation time (46%). Models to predict curd firmness 60min from rennet addition and casein micelle size, however, were poor, explaining only 25 and 13%, respectively, of the total variance in each trait within external validation. On average, all prediction models tended to be unbiased. The linear regression coefficient of the reference value on the predicted value varied from 0.17 (casein micelle size regression model) to 0.83 (pH regression model) but all differed from 1. The ratio performance deviation of 1.07 (casein micelle size prediction model) to 1.79 (pH prediction model) for all prediction models in the external validation was <2, suggesting that none of the prediction models could be used for analytical purposes. With the exception of casein micelle size and curd firmness at 60min after rennet addition, the developed prediction models may be useful as a screening method, because the concordance correlation coefficient ranged from 0.63 (heat coagulation time prediction model) to 0.84 (pH prediction model) in the external validation. Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

[From clinical judgment to linear regression model.

PubMed

Palacios-Cruz, Lino; Pérez, Marcela; Rivas-Ruiz, Rodolfo; Talavera, Juan O

2013-01-01

When we think about mathematical models, such as linear regression model, we think that these terms are only used by those engaged in research, a notion that is far from the truth. Legendre described the first mathematical model in 1805, and Galton introduced the formal term in 1886. Linear regression is one of the most commonly used regression models in clinical practice. It is useful to predict or show the relationship between two or more variables as long as the dependent variable is quantitative and has normal distribution. Stated in another way, the regression is used to predict a measure based on the knowledge of at least one other variable. Linear regression has as it's first objective to determine the slope or inclination of the regression line: Y = a + bx, where "a" is the intercept or regression constant and it is equivalent to "Y" value when "X" equals 0 and "b" (also called slope) indicates the increase or decrease that occurs when the variable "x" increases or decreases in one unit. In the regression line, "b" is called regression coefficient. The coefficient of determination (R 2 ) indicates the importance of independent variables in the outcome.

Multivariate regression model for predicting yields of grade lumber from yellow birch sawlogs

Treesearch

Andrew F. Howard; Daniel A. Yaussy

1986-01-01

A multivariate regression model was developed to predict green board-foot yields for the common grades of factory lumber processed from yellow birch factory-grade logs. The model incorporates the standard log measurements of scaling diameter, length, proportion of scalable defects, and the assigned USDA Forest Service log grade. Differences in yields between band and...

Stock price forecasting for companies listed on Tehran stock exchange using multivariate adaptive regression splines model and semi-parametric splines technique

NASA Astrophysics Data System (ADS)

Rounaghi, Mohammad Mahdi; Abbaszadeh, Mohammad Reza; Arashi, Mohammad

2015-11-01

One of the most important topics of interest to investors is stock price changes. Investors whose goals are long term are sensitive to stock price and its changes and react to them. In this regard, we used multivariate adaptive regression splines (MARS) model and semi-parametric splines technique for predicting stock price in this study. The MARS model as a nonparametric method is an adaptive method for regression and it fits for problems with high dimensions and several variables. semi-parametric splines technique was used in this study. Smoothing splines is a nonparametric regression method. In this study, we used 40 variables (30 accounting variables and 10 economic variables) for predicting stock price using the MARS model and using semi-parametric splines technique. After investigating the models, we select 4 accounting variables (book value per share, predicted earnings per share, P/E ratio and risk) as influencing variables on predicting stock price using the MARS model. After fitting the semi-parametric splines technique, only 4 accounting variables (dividends, net EPS, EPS Forecast and P/E Ratio) were selected as variables effective in forecasting stock prices.

Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection.

PubMed

Muhlestein, Whitney E; Akagi, Dallin S; Kallos, Justiss A; Morone, Peter J; Weaver, Kyle D; Thompson, Reid C; Chambless, Lola B

2018-04-01

Objective  Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods  A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results  Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p  = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion  Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Crop status evaluations and yield predictions

NASA Technical Reports Server (NTRS)

Haun, J. R.

1975-01-01

A model was developed for predicting the day 50 percent of the wheat crop is planted in North Dakota. This model incorporates location as an independent variable. The Julian date when 50 percent of the crop was planted for the nine divisions of North Dakota for seven years was regressed on the 49 variables through the step-down multiple regression procedure. This procedure begins with all of the independent variables and sequentially removes variables that are below a predetermined level of significance after each step. The prediction equation was tested on daily data. The accuracy of the model is considered satisfactory for finding the historic dates on which to initiate yield prediction model. Growth prediction models were also developed for spring wheat.

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.

Application of linear regression analysis in accuracy assessment of rolling force calculations

NASA Astrophysics Data System (ADS)

Poliak, E. I.; Shim, M. K.; Kim, G. S.; Choo, W. Y.

1998-10-01

Efficient operation of the computational models employed in process control systems require periodical assessment of the accuracy of their predictions. Linear regression is proposed as a tool which allows separate systematic and random prediction errors from those related to measurements. A quantitative characteristic of the model predictive ability is introduced in addition to standard statistical tests for model adequacy. Rolling force calculations are considered as an example for the application. However, the outlined approach can be used to assess the performance of any computational model.

Predicting birth weight with conditionally linear transformation models.

PubMed

Möst, Lisa; Schmid, Matthias; Faschingbauer, Florian; Hothorn, Torsten

2016-12-01

Low and high birth weight (BW) are important risk factors for neonatal morbidity and mortality. Gynecologists must therefore accurately predict BW before delivery. Most prediction formulas for BW are based on prenatal ultrasound measurements carried out within one week prior to birth. Although successfully used in clinical practice, these formulas focus on point predictions of BW but do not systematically quantify uncertainty of the predictions, i.e. they result in estimates of the conditional mean of BW but do not deliver prediction intervals. To overcome this problem, we introduce conditionally linear transformation models (CLTMs) to predict BW. Instead of focusing only on the conditional mean, CLTMs model the whole conditional distribution function of BW given prenatal ultrasound parameters. Consequently, the CLTM approach delivers both point predictions of BW and fetus-specific prediction intervals. Prediction intervals constitute an easy-to-interpret measure of prediction accuracy and allow identification of fetuses subject to high prediction uncertainty. Using a data set of 8712 deliveries at the Perinatal Centre at the University Clinic Erlangen (Germany), we analyzed variants of CLTMs and compared them to standard linear regression estimation techniques used in the past and to quantile regression approaches. The best-performing CLTM variant was competitive with quantile regression and linear regression approaches in terms of conditional coverage and average length of the prediction intervals. We propose that CLTMs be used because they are able to account for possible heteroscedasticity, kurtosis, and skewness of the distribution of BWs. © The Author(s) 2014.

CUSUM-Logistic Regression analysis for the rapid detection of errors in clinical laboratory test results.

PubMed

Sampson, Maureen L; Gounden, Verena; van Deventer, Hendrik E; Remaley, Alan T

2016-02-01

The main drawback of the periodic analysis of quality control (QC) material is that test performance is not monitored in time periods between QC analyses, potentially leading to the reporting of faulty test results. The objective of this study was to develop a patient based QC procedure for the more timely detection of test errors. Results from a Chem-14 panel measured on the Beckman LX20 analyzer were used to develop the model. Each test result was predicted from the other 13 members of the panel by multiple regression, which resulted in correlation coefficients between the predicted and measured result of >0.7 for 8 of the 14 tests. A logistic regression model, which utilized the measured test result, the predicted test result, the day of the week and time of day, was then developed for predicting test errors. The output of the logistic regression was tallied by a daily CUSUM approach and used to predict test errors, with a fixed specificity of 90%. The mean average run length (ARL) before error detection by CUSUM-Logistic Regression (CSLR) was 20 with a mean sensitivity of 97%, which was considerably shorter than the mean ARL of 53 (sensitivity 87.5%) for a simple prediction model that only used the measured result for error detection. A CUSUM-Logistic Regression analysis of patient laboratory data can be an effective approach for the rapid and sensitive detection of clinical laboratory errors. Published by Elsevier Inc.

A Predictive Model for Microbial Counts on Beaches where Intertidal Sand is the Primary Source

PubMed Central

Feng, Zhixuan; Reniers, Ad; Haus, Brian K.; Solo-Gabriele, Helena M.; Wang, John D.; Fleming, Lora E.

2015-01-01

Human health protection at recreational beaches requires accurate and timely information on microbiological conditions to issue advisories. The objective of this study was to develop a new numerical mass balance model for enterococci levels on nonpoint source beaches. The significant advantage of this model is its easy implementation, and it provides a detailed description of the cross-shore distribution of enterococci that is useful for beach management purposes. The performance of the balance model was evaluated by comparing predicted exceedances of a beach advisory threshold value to field data, and to a traditional regression model. Both the balance model and regression equation predicted approximately 70% the advisories correctly at the knee depth and over 90% at the waist depth. The balance model has the advantage over the regression equation in its ability to simulate spatiotemporal variations of microbial levels, and it is recommended for making more informed management decisions. PMID:25840869

Fuzzy regression modeling for tool performance prediction and degradation detection.

PubMed

Li, X; Er, M J; Lim, B S; Zhou, J H; Gan, O P; Rutkowski, L

2010-10-01

In this paper, the viability of using Fuzzy-Rule-Based Regression Modeling (FRM) algorithm for tool performance and degradation detection is investigated. The FRM is developed based on a multi-layered fuzzy-rule-based hybrid system with Multiple Regression Models (MRM) embedded into a fuzzy logic inference engine that employs Self Organizing Maps (SOM) for clustering. The FRM converts a complex nonlinear problem to a simplified linear format in order to further increase the accuracy in prediction and rate of convergence. The efficacy of the proposed FRM is tested through a case study - namely to predict the remaining useful life of a ball nose milling cutter during a dry machining process of hardened tool steel with a hardness of 52-54 HRc. A comparative study is further made between four predictive models using the same set of experimental data. It is shown that the FRM is superior as compared with conventional MRM, Back Propagation Neural Networks (BPNN) and Radial Basis Function Networks (RBFN) in terms of prediction accuracy and learning speed.

Predicting exposure-response associations of ambient particulate matter with mortality in 73 Chinese cities.

PubMed

Madaniyazi, Lina; Guo, Yuming; Chen, Renjie; Kan, Haidong; Tong, Shilu

2016-01-01

Estimating the burden of mortality associated with particulates requires knowledge of exposure-response associations. However, the evidence on exposure-response associations is limited in many cities, especially in developing countries. In this study, we predicted associations of particulates smaller than 10 μm in aerodynamic diameter (PM10) with mortality in 73 Chinese cities. The meta-regression model was used to test and quantify which city-specific characteristics contributed significantly to the heterogeneity of PM10-mortality associations for 16 Chinese cities. Then, those city-specific characteristics with statistically significant regression coefficients were treated as independent variables to build multivariate meta-regression models. The model with the best fitness was used to predict PM10-mortality associations in 73 Chinese cities in 2010. Mean temperature, PM10 concentration and green space per capita could best explain the heterogeneity in PM10-mortality associations. Based on city-specific characteristics, we were able to develop multivariate meta-regression models to predict associations between air pollutants and health outcomes reasonably well. Copyright © 2015 Elsevier Ltd. All rights reserved.

Vesicular stomatitis forecasting based on Google Trends

PubMed Central

Lu, Yi; Zhou, GuangYa; Chen, Qin

2018-01-01

Background Vesicular stomatitis (VS) is an important viral disease of livestock. The main feature of VS is irregular blisters that occur on the lips, tongue, oral mucosa, hoof crown and nipple. Humans can also be infected with vesicular stomatitis and develop meningitis. This study analyses 2014 American VS outbreaks in order to accurately predict vesicular stomatitis outbreak trends. Methods American VS outbreaks data were collected from OIE. The data for VS keywords were obtained by inputting 24 disease-related keywords into Google Trends. After calculating the Pearson and Spearman correlation coefficients, it was found that there was a relationship between outbreaks and keywords derived from Google Trends. Finally, the predicted model was constructed based on qualitative classification and quantitative regression. Results For the regression model, the Pearson correlation coefficients between the predicted outbreaks and actual outbreaks are 0.953 and 0.948, respectively. For the qualitative classification model, we constructed five classification predictive models and chose the best classification predictive model as the result. The results showed, SN (sensitivity), SP (specificity) and ACC (prediction accuracy) values of the best classification predictive model are 78.52%,72.5% and 77.14%, respectively. Conclusion This study applied Google search data to construct a qualitative classification model and a quantitative regression model. The results show that the method is effective and that these two models obtain more accurate forecast. PMID:29385198

Developing a dengue forecast model using machine learning: A case study in China.

PubMed

Guo, Pi; Liu, Tao; Zhang, Qin; Wang, Li; Xiao, Jianpeng; Zhang, Qingying; Luo, Ganfeng; Li, Zhihao; He, Jianfeng; Zhang, Yonghui; Ma, Wenjun

2017-10-01

In China, dengue remains an important public health issue with expanded areas and increased incidence recently. Accurate and timely forecasts of dengue incidence in China are still lacking. We aimed to use the state-of-the-art machine learning algorithms to develop an accurate predictive model of dengue. Weekly dengue cases, Baidu search queries and climate factors (mean temperature, relative humidity and rainfall) during 2011-2014 in Guangdong were gathered. A dengue search index was constructed for developing the predictive models in combination with climate factors. The observed year and week were also included in the models to control for the long-term trend and seasonality. Several machine learning algorithms, including the support vector regression (SVR) algorithm, step-down linear regression model, gradient boosted regression tree algorithm (GBM), negative binomial regression model (NBM), least absolute shrinkage and selection operator (LASSO) linear regression model and generalized additive model (GAM), were used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed using the root-mean-square error (RMSE) and R-squared measures. The residuals of the models were examined using the autocorrelation and partial autocorrelation function analyses to check the validity of the models. The models were further validated using dengue surveillance data from five other provinces. The epidemics during the last 12 weeks and the peak of the 2014 large outbreak were accurately forecasted by the SVR model selected by a cross-validation technique. Moreover, the SVR model had the consistently smallest prediction error rates for tracking the dynamics of dengue and forecasting the outbreaks in other areas in China. The proposed SVR model achieved a superior performance in comparison with other forecasting techniques assessed in this study. The findings can help the government and community respond early to dengue epidemics.

Building interpretable predictive models for pediatric hospital readmission using Tree-Lasso logistic regression.

PubMed

Jovanovic, Milos; Radovanovic, Sandro; Vukicevic, Milan; Van Poucke, Sven; Delibasic, Boris

2016-09-01

Quantification and early identification of unplanned readmission risk have the potential to improve the quality of care during hospitalization and after discharge. However, high dimensionality, sparsity, and class imbalance of electronic health data and the complexity of risk quantification, challenge the development of accurate predictive models. Predictive models require a certain level of interpretability in order to be applicable in real settings and create actionable insights. This paper aims to develop accurate and interpretable predictive models for readmission in a general pediatric patient population, by integrating a data-driven model (sparse logistic regression) and domain knowledge based on the international classification of diseases 9th-revision clinical modification (ICD-9-CM) hierarchy of diseases. Additionally, we propose a way to quantify the interpretability of a model and inspect the stability of alternative solutions. The analysis was conducted on >66,000 pediatric hospital discharge records from California, State Inpatient Databases, Healthcare Cost and Utilization Project between 2009 and 2011. We incorporated domain knowledge based on the ICD-9-CM hierarchy in a data driven, Tree-Lasso regularized logistic regression model, providing the framework for model interpretation. This approach was compared with traditional Lasso logistic regression resulting in models that are easier to interpret by fewer high-level diagnoses, with comparable prediction accuracy. The results revealed that the use of a Tree-Lasso model was as competitive in terms of accuracy (measured by area under the receiver operating characteristic curve-AUC) as the traditional Lasso logistic regression, but integration with the ICD-9-CM hierarchy of diseases provided more interpretable models in terms of high-level diagnoses. Additionally, interpretations of models are in accordance with existing medical understanding of pediatric readmission. Best performing models have similar performances reaching AUC values 0.783 and 0.779 for traditional Lasso and Tree-Lasso, respectfully. However, information loss of Lasso models is 0.35 bits higher compared to Tree-Lasso model. We propose a method for building predictive models applicable for the detection of readmission risk based on Electronic Health records. Integration of domain knowledge (in the form of ICD-9-CM taxonomy) and a data-driven, sparse predictive algorithm (Tree-Lasso Logistic Regression) resulted in an increase of interpretability of the resulting model. The models are interpreted for the readmission prediction problem in general pediatric population in California, as well as several important subpopulations, and the interpretations of models comply with existing medical understanding of pediatric readmission. Finally, quantitative assessment of the interpretability of the models is given, that is beyond simple counts of selected low-level features. Copyright © 2016 Elsevier B.V. All rights reserved.

Regression Models and Fuzzy Logic Prediction of TBM Penetration Rate

NASA Astrophysics Data System (ADS)

Minh, Vu Trieu; Katushin, Dmitri; Antonov, Maksim; Veinthal, Renno

2017-03-01

This paper presents statistical analyses of rock engineering properties and the measured penetration rate of tunnel boring machine (TBM) based on the data of an actual project. The aim of this study is to analyze the influence of rock engineering properties including uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), rock brittleness index (BI), the distance between planes of weakness (DPW), and the alpha angle (Alpha) between the tunnel axis and the planes of weakness on the TBM rate of penetration (ROP). Four (4) statistical regression models (two linear and two nonlinear) are built to predict the ROP of TBM. Finally a fuzzy logic model is developed as an alternative method and compared to the four statistical regression models. Results show that the fuzzy logic model provides better estimations and can be applied to predict the TBM performance. The R-squared value (R2) of the fuzzy logic model scores the highest value of 0.714 over the second runner-up of 0.667 from the multiple variables nonlinear regression model.

Predicting seasonal influenza transmission using functional regression models with temporal dependence.

PubMed

Oviedo de la Fuente, Manuel; Febrero-Bande, Manuel; Muñoz, María Pilar; Domínguez, Àngela

2018-01-01

This paper proposes a novel approach that uses meteorological information to predict the incidence of influenza in Galicia (Spain). It extends the Generalized Least Squares (GLS) methods in the multivariate framework to functional regression models with dependent errors. These kinds of models are useful when the recent history of the incidence of influenza are readily unavailable (for instance, by delays on the communication with health informants) and the prediction must be constructed by correcting the temporal dependence of the residuals and using more accessible variables. A simulation study shows that the GLS estimators render better estimations of the parameters associated with the regression model than they do with the classical models. They obtain extremely good results from the predictive point of view and are competitive with the classical time series approach for the incidence of influenza. An iterative version of the GLS estimator (called iGLS) was also proposed that can help to model complicated dependence structures. For constructing the model, the distance correlation measure [Formula: see text] was employed to select relevant information to predict influenza rate mixing multivariate and functional variables. These kinds of models are extremely useful to health managers in allocating resources in advance to manage influenza epidemics.

Product unit neural network models for predicting the growth limits of Listeria monocytogenes.

PubMed

Valero, A; Hervás, C; García-Gimeno, R M; Zurera, G

2007-08-01

A new approach to predict the growth/no growth interface of Listeria monocytogenes as a function of storage temperature, pH, citric acid (CA) and ascorbic acid (AA) is presented. A linear logistic regression procedure was performed and a non-linear model was obtained by adding new variables by means of a Neural Network model based on Product Units (PUNN). The classification efficiency of the training data set and the generalization data of the new Logistic Regression PUNN model (LRPU) were compared with Linear Logistic Regression (LLR) and Polynomial Logistic Regression (PLR) models. 92% of the total cases from the LRPU model were correctly classified, an improvement on the percentage obtained using the PLR model (90%) and significantly higher than the results obtained with the LLR model, 80%. On the other hand predictions of LRPU were closer to data observed which permits to design proper formulations in minimally processed foods. This novel methodology can be applied to predictive microbiology for describing growth/no growth interface of food-borne microorganisms such as L. monocytogenes. The optimal balance is trying to find models with an acceptable interpretation capacity and with good ability to fit the data on the boundaries of variable range. The results obtained conclude that these kinds of models might well be very a valuable tool for mathematical modeling.

Predictors of course in obsessive-compulsive disorder: logistic regression versus Cox regression for recurrent events.

PubMed

Kempe, P T; van Oppen, P; de Haan, E; Twisk, J W R; Sluis, A; Smit, J H; van Dyck, R; van Balkom, A J L M

2007-09-01

Two methods for predicting remissions in obsessive-compulsive disorder (OCD) treatment are evaluated. Y-BOCS measurements of 88 patients with a primary OCD (DSM-III-R) diagnosis were performed over a 16-week treatment period, and during three follow-ups. Remission at any measurement was defined as a Y-BOCS score lower than thirteen combined with a reduction of seven points when compared with baseline. Logistic regression models were compared with a Cox regression for recurrent events model. Logistic regression yielded different models at different evaluation times. The recurrent events model remained stable when fewer measurements were used. Higher baseline levels of neuroticism and more severe OCD symptoms were associated with a lower chance of remission, early age of onset and more depressive symptoms with a higher chance. Choice of outcome time affects logistic regression prediction models. Recurrent events analysis uses all information on remissions and relapses. Short- and long-term predictors for OCD remission show overlap.

Cox regression analysis with missing covariates via nonparametric multiple imputation.

PubMed

Hsu, Chiu-Hsieh; Yu, Mandi

2018-01-01

We consider the situation of estimating Cox regression in which some covariates are subject to missing, and there exists additional information (including observed event time, censoring indicator and fully observed covariates) which may be predictive of the missing covariates. We propose to use two working regression models: one for predicting the missing covariates and the other for predicting the missing probabilities. For each missing covariate observation, these two working models are used to define a nearest neighbor imputing set. This set is then used to non-parametrically impute covariate values for the missing observation. Upon the completion of imputation, Cox regression is performed on the multiply imputed datasets to estimate the regression coefficients. In a simulation study, we compare the nonparametric multiple imputation approach with the augmented inverse probability weighted (AIPW) method, which directly incorporates the two working models into estimation of Cox regression, and the predictive mean matching imputation (PMM) method. We show that all approaches can reduce bias due to non-ignorable missing mechanism. The proposed nonparametric imputation method is robust to mis-specification of either one of the two working models and robust to mis-specification of the link function of the two working models. In contrast, the PMM method is sensitive to misspecification of the covariates included in imputation. The AIPW method is sensitive to the selection probability. We apply the approaches to a breast cancer dataset from Surveillance, Epidemiology and End Results (SEER) Program.

The creation and evaluation of a model to simulate the probability of conception in seasonal-calving pasture-based dairy heifers.

PubMed

Fenlon, Caroline; O'Grady, Luke; Butler, Stephen; Doherty, Michael L; Dunnion, John

2017-01-01

Herd fertility in pasture-based dairy farms is a key driver of farm economics. Models for predicting nulliparous reproductive outcomes are rare, but age, genetics, weight, and BCS have been identified as factors influencing heifer conception. The aim of this study was to create a simulation model of heifer conception to service with thorough evaluation. Artificial Insemination service records from two research herds and ten commercial herds were provided to build and evaluate the models. All were managed as spring-calving pasture-based systems. The factors studied were related to age, genetics, and time of service. The data were split into training and testing sets and bootstrapping was used to train the models. Logistic regression (with and without random effects) and generalised additive modelling were selected as the model-building techniques. Two types of evaluation were used to test the predictive ability of the models: discrimination and calibration. Discrimination, which includes sensitivity, specificity, accuracy and ROC analysis, measures a model's ability to distinguish between positive and negative outcomes. Calibration measures the accuracy of the predicted probabilities with the Hosmer-Lemeshow goodness-of-fit, calibration plot and calibration error. After data cleaning and the removal of services with missing values, 1396 services remained to train the models and 597 were left for testing. Age, breed, genetic predicted transmitting ability for calving interval, month and year were significant in the multivariate models. The regression models also included an interaction between age and month. Year within herd was a random effect in the mixed regression model. Overall prediction accuracy was between 77.1% and 78.9%. All three models had very high sensitivity, but low specificity. The two regression models were very well-calibrated. The mean absolute calibration errors were all below 4%. Because the models were not adept at identifying unsuccessful services, they are not suggested for use in predicting the outcome of individual heifer services. Instead, they are useful for the comparison of services with different covariate values or as sub-models in whole-farm simulations. The mixed regression model was identified as the best model for prediction, as the random effects can be ignored and the other variables can be easily obtained or simulated.

Building factorial regression models to explain and predict nitrate concentrations in groundwater under agricultural land

NASA Astrophysics Data System (ADS)

Stigter, T. Y.; Ribeiro, L.; Dill, A. M. M. Carvalho

2008-07-01

SummaryFactorial regression models, based on correspondence analysis, are built to explain the high nitrate concentrations in groundwater beneath an agricultural area in the south of Portugal, exceeding 300 mg/l, as a function of chemical variables, electrical conductivity (EC), land use and hydrogeological setting. Two important advantages of the proposed methodology are that qualitative parameters can be involved in the regression analysis and that multicollinearity is avoided. Regression is performed on eigenvectors extracted from the data similarity matrix, the first of which clearly reveals the impact of agricultural practices and hydrogeological setting on the groundwater chemistry of the study area. Significant correlation exists between response variable NO3- and explanatory variables Ca 2+, Cl -, SO42-, depth to water, aquifer media and land use. Substituting Cl - by the EC results in the most accurate regression model for nitrate, when disregarding the four largest outliers (model A). When built solely on land use and hydrogeological setting, the regression model (model B) is less accurate but more interesting from a practical viewpoint, as it is based on easily obtainable data and can be used to predict nitrate concentrations in groundwater in other areas with similar conditions. This is particularly useful for conservative contaminants, where risk and vulnerability assessment methods, based on assumed rather than established correlations, generally produce erroneous results. Another purpose of the models can be to predict the future evolution of nitrate concentrations under influence of changes in land use or fertilization practices, which occur in compliance with policies such as the Nitrates Directive. Model B predicts a 40% decrease in nitrate concentrations in groundwater of the study area, when horticulture is replaced by other land use with much lower fertilization and irrigation rates.

Using automated texture features to determine the probability for masking of a tumor on mammography, but not ultrasound.

PubMed

Häberle, Lothar; Hack, Carolin C; Heusinger, Katharina; Wagner, Florian; Jud, Sebastian M; Uder, Michael; Beckmann, Matthias W; Schulz-Wendtland, Rüdiger; Wittenberg, Thomas; Fasching, Peter A

2017-08-30

Tumors in radiologically dense breast were overlooked on mammograms more often than tumors in low-density breasts. A fast reproducible and automated method of assessing percentage mammographic density (PMD) would be desirable to support decisions whether ultrasonography should be provided for women in addition to mammography in diagnostic mammography units. PMD assessment has still not been included in clinical routine work, as there are issues of interobserver variability and the procedure is quite time consuming. This study investigated whether fully automatically generated texture features of mammograms can replace time-consuming semi-automatic PMD assessment to predict a patient's risk of having an invasive breast tumor that is visible on ultrasound but masked on mammography (mammography failure). This observational study included 1334 women with invasive breast cancer treated at a hospital-based diagnostic mammography unit. Ultrasound was available for the entire cohort as part of routine diagnosis. Computer-based threshold PMD assessments ("observed PMD") were carried out and 363 texture features were obtained from each mammogram. Several variable selection and regression techniques (univariate selection, lasso, boosting, random forest) were applied to predict PMD from the texture features. The predicted PMD values were each used as new predictor for masking in logistic regression models together with clinical predictors. These four logistic regression models with predicted PMD were compared among themselves and with a logistic regression model with observed PMD. The most accurate masking prediction was determined by cross-validation. About 120 of the 363 texture features were selected for predicting PMD. Density predictions with boosting were the best substitute for observed PMD to predict masking. Overall, the corresponding logistic regression model performed better (cross-validated AUC, 0.747) than one without mammographic density (0.734), but less well than the one with the observed PMD (0.753). However, in patients with an assigned mammography failure risk >10%, covering about half of all masked tumors, the boosting-based model performed at least as accurately as the original PMD model. Automatically generated texture features can replace semi-automatically determined PMD in a prediction model for mammography failure, such that more than 50% of masked tumors could be discovered.

A computational approach to compare regression modelling strategies in prediction research.

PubMed

Pajouheshnia, Romin; Pestman, Wiebe R; Teerenstra, Steven; Groenwold, Rolf H H

2016-08-25

It is often unclear which approach to fit, assess and adjust a model will yield the most accurate prediction model. We present an extension of an approach for comparing modelling strategies in linear regression to the setting of logistic regression and demonstrate its application in clinical prediction research. A framework for comparing logistic regression modelling strategies by their likelihoods was formulated using a wrapper approach. Five different strategies for modelling, including simple shrinkage methods, were compared in four empirical data sets to illustrate the concept of a priori strategy comparison. Simulations were performed in both randomly generated data and empirical data to investigate the influence of data characteristics on strategy performance. We applied the comparison framework in a case study setting. Optimal strategies were selected based on the results of a priori comparisons in a clinical data set and the performance of models built according to each strategy was assessed using the Brier score and calibration plots. The performance of modelling strategies was highly dependent on the characteristics of the development data in both linear and logistic regression settings. A priori comparisons in four empirical data sets found that no strategy consistently outperformed the others. The percentage of times that a model adjustment strategy outperformed a logistic model ranged from 3.9 to 94.9 %, depending on the strategy and data set. However, in our case study setting the a priori selection of optimal methods did not result in detectable improvement in model performance when assessed in an external data set. The performance of prediction modelling strategies is a data-dependent process and can be highly variable between data sets within the same clinical domain. A priori strategy comparison can be used to determine an optimal logistic regression modelling strategy for a given data set before selecting a final modelling approach.

Widen NomoGram for multinomial logistic regression: an application to staging liver fibrosis in chronic hepatitis C patients.

PubMed

Ardoino, Ilaria; Lanzoni, Monica; Marano, Giuseppe; Boracchi, Patrizia; Sagrini, Elisabetta; Gianstefani, Alice; Piscaglia, Fabio; Biganzoli, Elia M

2017-04-01

The interpretation of regression models results can often benefit from the generation of nomograms, 'user friendly' graphical devices especially useful for assisting the decision-making processes. However, in the case of multinomial regression models, whenever categorical responses with more than two classes are involved, nomograms cannot be drawn in the conventional way. Such a difficulty in managing and interpreting the outcome could often result in a limitation of the use of multinomial regression in decision-making support. In the present paper, we illustrate the derivation of a non-conventional nomogram for multinomial regression models, intended to overcome this issue. Although it may appear less straightforward at first sight, the proposed methodology allows an easy interpretation of the results of multinomial regression models and makes them more accessible for clinicians and general practitioners too. Development of prediction model based on multinomial logistic regression and of the pertinent graphical tool is illustrated by means of an example involving the prediction of the extent of liver fibrosis in hepatitis C patients by routinely available markers.

Predicting clicks of PubMed articles.

PubMed

Mao, Yuqing; Lu, Zhiyong

2013-01-01

Predicting the popularity or access usage of an article has the potential to improve the quality of PubMed searches. We can model the click trend of each article as its access changes over time by mining the PubMed query logs, which contain the previous access history for all articles. In this article, we examine the access patterns produced by PubMed users in two years (July 2009 to July 2011). We explore the time series of accesses for each article in the query logs, model the trends with regression approaches, and subsequently use the models for prediction. We show that the click trends of PubMed articles are best fitted with a log-normal regression model. This model allows the number of accesses an article receives and the time since it first becomes available in PubMed to be related via quadratic and logistic functions, with the model parameters to be estimated via maximum likelihood. Our experiments predicting the number of accesses for an article based on its past usage demonstrate that the mean absolute error and mean absolute percentage error of our model are 4.0% and 8.1% lower than the power-law regression model, respectively. The log-normal distribution is also shown to perform significantly better than a previous prediction method based on a human memory theory in cognitive science. This work warrants further investigation on the utility of such a log-normal regression approach towards improving information access in PubMed.

Predicting clicks of PubMed articles

PubMed Central

Mao, Yuqing; Lu, Zhiyong

2013-01-01

Predicting the popularity or access usage of an article has the potential to improve the quality of PubMed searches. We can model the click trend of each article as its access changes over time by mining the PubMed query logs, which contain the previous access history for all articles. In this article, we examine the access patterns produced by PubMed users in two years (July 2009 to July 2011). We explore the time series of accesses for each article in the query logs, model the trends with regression approaches, and subsequently use the models for prediction. We show that the click trends of PubMed articles are best fitted with a log-normal regression model. This model allows the number of accesses an article receives and the time since it first becomes available in PubMed to be related via quadratic and logistic functions, with the model parameters to be estimated via maximum likelihood. Our experiments predicting the number of accesses for an article based on its past usage demonstrate that the mean absolute error and mean absolute percentage error of our model are 4.0% and 8.1% lower than the power-law regression model, respectively. The log-normal distribution is also shown to perform significantly better than a previous prediction method based on a human memory theory in cognitive science. This work warrants further investigation on the utility of such a log-normal regression approach towards improving information access in PubMed. PMID:24551386

Machine learning in updating predictive models of planning and scheduling transportation projects

DOT National Transportation Integrated Search

1997-01-01

A method combining machine learning and regression analysis to automatically and intelligently update predictive models used in the Kansas Department of Transportations (KDOTs) internal management system is presented. The predictive models used...

Predicting the aquatic toxicity mode of action using logistic regression and linear discriminant analysis.

PubMed

Ren, Y Y; Zhou, L C; Yang, L; Liu, P Y; Zhao, B W; Liu, H X

2016-09-01

The paper highlights the use of the logistic regression (LR) method in the construction of acceptable statistically significant, robust and predictive models for the classification of chemicals according to their aquatic toxic modes of action. Essentials accounting for a reliable model were all considered carefully. The model predictors were selected by stepwise forward discriminant analysis (LDA) from a combined pool of experimental data and chemical structure-based descriptors calculated by the CODESSA and DRAGON software packages. Model predictive ability was validated both internally and externally. The applicability domain was checked by the leverage approach to verify prediction reliability. The obtained models are simple and easy to interpret. In general, LR performs much better than LDA and seems to be more attractive for the prediction of the more toxic compounds, i.e. compounds that exhibit excess toxicity versus non-polar narcotic compounds and more reactive compounds versus less reactive compounds. In addition, model fit and regression diagnostics was done through the influence plot which reflects the hat-values, studentized residuals, and Cook's distance statistics of each sample. Overdispersion was also checked for the LR model. The relationships between the descriptors and the aquatic toxic behaviour of compounds are also discussed.

Egg production forecasting: Determining efficient modeling approaches.

PubMed

Ahmad, H A

2011-12-01

Several mathematical or statistical and artificial intelligence models were developed to compare egg production forecasts in commercial layers. Initial data for these models were collected from a comparative layer trial on commercial strains conducted at the Poultry Research Farms, Auburn University. Simulated data were produced to represent new scenarios by using means and SD of egg production of the 22 commercial strains. From the simulated data, random examples were generated for neural network training and testing for the weekly egg production prediction from wk 22 to 36. Three neural network architectures-back-propagation-3, Ward-5, and the general regression neural network-were compared for their efficiency to forecast egg production, along with other traditional models. The general regression neural network gave the best-fitting line, which almost overlapped with the commercial egg production data, with an R(2) of 0.71. The general regression neural network-predicted curve was compared with original egg production data, the average curves of white-shelled and brown-shelled strains, linear regression predictions, and the Gompertz nonlinear model. The general regression neural network was superior in all these comparisons and may be the model of choice if the initial overprediction is managed efficiently. In general, neural network models are efficient, are easy to use, require fewer data, and are practical under farm management conditions to forecast egg production.

Population heterogeneity in the salience of multiple risk factors for adolescent delinquency.

PubMed

Lanza, Stephanie T; Cooper, Brittany R; Bray, Bethany C

2014-03-01

To present mixture regression analysis as an alternative to more standard regression analysis for predicting adolescent delinquency. We demonstrate how mixture regression analysis allows for the identification of population subgroups defined by the salience of multiple risk factors. We identified population subgroups (i.e., latent classes) of individuals based on their coefficients in a regression model predicting adolescent delinquency from eight previously established risk indices drawn from the community, school, family, peer, and individual levels. The study included N = 37,763 10th-grade adolescents who participated in the Communities That Care Youth Survey. Standard, zero-inflated, and mixture Poisson and negative binomial regression models were considered. Standard and mixture negative binomial regression models were selected as optimal. The five-class regression model was interpreted based on the class-specific regression coefficients, indicating that risk factors had varying salience across classes of adolescents. Standard regression showed that all risk factors were significantly associated with delinquency. Mixture regression provided more nuanced information, suggesting a unique set of risk factors that were salient for different subgroups of adolescents. Implications for the design of subgroup-specific interventions are discussed. Copyright © 2014 Society for Adolescent Health and Medicine. Published by Elsevier Inc. All rights reserved.

Data mining of tree-based models to analyze freeway accident frequency.

PubMed

Chang, Li-Yen; Chen, Wen-Chieh

2005-01-01

Statistical models, such as Poisson or negative binomial regression models, have been employed to analyze vehicle accident frequency for many years. However, these models have their own model assumptions and pre-defined underlying relationship between dependent and independent variables. If these assumptions are violated, the model could lead to erroneous estimation of accident likelihood. Classification and Regression Tree (CART), one of the most widely applied data mining techniques, has been commonly employed in business administration, industry, and engineering. CART does not require any pre-defined underlying relationship between target (dependent) variable and predictors (independent variables) and has been shown to be a powerful tool, particularly for dealing with prediction and classification problems. This study collected the 2001-2002 accident data of National Freeway 1 in Taiwan. A CART model and a negative binomial regression model were developed to establish the empirical relationship between traffic accidents and highway geometric variables, traffic characteristics, and environmental factors. The CART findings indicated that the average daily traffic volume and precipitation variables were the key determinants for freeway accident frequencies. By comparing the prediction performance between the CART and the negative binomial regression models, this study demonstrates that CART is a good alternative method for analyzing freeway accident frequencies. By comparing the prediction performance between the CART and the negative binomial regression models, this study demonstrates that CART is a good alternative method for analyzing freeway accident frequencies.

4D-Fingerprint Categorical QSAR Models for Skin Sensitization Based on Classification Local Lymph Node Assay Measures

PubMed Central

Li, Yi; Tseng, Yufeng J.; Pan, Dahua; Liu, Jianzhong; Kern, Petra S.; Gerberick, G. Frank; Hopfinger, Anton J.

2008-01-01

Currently, the only validated methods to identify skin sensitization effects are in vivo models, such as the Local Lymph Node Assay (LLNA) and guinea pig studies. There is a tremendous need, in particular due to novel legislation, to develop animal alternatives, eg. Quantitative Structure-Activity Relationship (QSAR) models. Here, QSAR models for skin sensitization using LLNA data have been constructed. The descriptors used to generate these models are derived from the 4D-molecular similarity paradigm and are referred to as universal 4D-fingerprints. A training set of 132 structurally diverse compounds and a test set of 15 structurally diverse compounds were used in this study. The statistical methodologies used to build the models are logistic regression (LR), and partial least square coupled logistic regression (PLS-LR), which prove to be effective tools for studying skin sensitization measures expressed in the two categorical terms of sensitizer and non-sensitizer. QSAR models with low values of the Hosmer-Lemeshow goodness-of-fit statistic, χHL2, are significant and predictive. For the training set, the cross-validated prediction accuracy of the logistic regression models ranges from 77.3% to 78.0%, while that of PLS-logistic regression models ranges from 87.1% to 89.4%. For the test set, the prediction accuracy of logistic regression models ranges from 80.0%-86.7%, while that of PLS-logistic regression models ranges from 73.3%-80.0%. The QSAR models are made up of 4D-fingerprints related to aromatic atoms, hydrogen bond acceptors and negatively partially charged atoms. PMID:17226934

Generalized regression neural network (GRNN)-based approach for colored dissolved organic matter (CDOM) retrieval: case study of Connecticut River at Middle Haddam Station, USA.

PubMed

Heddam, Salim

2014-11-01

The prediction of colored dissolved organic matter (CDOM) using artificial neural network approaches has received little attention in the past few decades. In this study, colored dissolved organic matter (CDOM) was modeled using generalized regression neural network (GRNN) and multiple linear regression (MLR) models as a function of Water temperature (TE), pH, specific conductance (SC), and turbidity (TU). Evaluation of the prediction accuracy of the models is based on the root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (CC), and Willmott's index of agreement (d). The results indicated that GRNN can be applied successfully for prediction of colored dissolved organic matter (CDOM).

A novel simple QSAR model for the prediction of anti-HIV activity using multiple linear regression analysis.

PubMed

Afantitis, Antreas; Melagraki, Georgia; Sarimveis, Haralambos; Koutentis, Panayiotis A; Markopoulos, John; Igglessi-Markopoulou, Olga

2006-08-01

A quantitative-structure activity relationship was obtained by applying Multiple Linear Regression Analysis to a series of 80 1-[2-hydroxyethoxy-methyl]-6-(phenylthio) thymine (HEPT) derivatives with significant anti-HIV activity. For the selection of the best among 37 different descriptors, the Elimination Selection Stepwise Regression Method (ES-SWR) was utilized. The resulting QSAR model (R (2) (CV) = 0.8160; S (PRESS) = 0.5680) proved to be very accurate both in training and predictive stages.

Analysis and prediction of flow from local source in a river basin using a Neuro-fuzzy modeling tool.

PubMed

Aqil, Muhammad; Kita, Ichiro; Yano, Akira; Nishiyama, Soichi

2007-10-01

Traditionally, the multiple linear regression technique has been one of the most widely used models in simulating hydrological time series. However, when the nonlinear phenomenon is significant, the multiple linear will fail to develop an appropriate predictive model. Recently, neuro-fuzzy systems have gained much popularity for calibrating the nonlinear relationships. This study evaluated the potential of a neuro-fuzzy system as an alternative to the traditional statistical regression technique for the purpose of predicting flow from a local source in a river basin. The effectiveness of the proposed identification technique was demonstrated through a simulation study of the river flow time series of the Citarum River in Indonesia. Furthermore, in order to provide the uncertainty associated with the estimation of river flow, a Monte Carlo simulation was performed. As a comparison, a multiple linear regression analysis that was being used by the Citarum River Authority was also examined using various statistical indices. The simulation results using 95% confidence intervals indicated that the neuro-fuzzy model consistently underestimated the magnitude of high flow while the low and medium flow magnitudes were estimated closer to the observed data. The comparison of the prediction accuracy of the neuro-fuzzy and linear regression methods indicated that the neuro-fuzzy approach was more accurate in predicting river flow dynamics. The neuro-fuzzy model was able to improve the root mean square error (RMSE) and mean absolute percentage error (MAPE) values of the multiple linear regression forecasts by about 13.52% and 10.73%, respectively. Considering its simplicity and efficiency, the neuro-fuzzy model is recommended as an alternative tool for modeling of flow dynamics in the study area.

New strategy for determination of anthocyanins, polyphenols and antioxidant capacity of Brassica oleracea liquid extract using infrared spectroscopies and multivariate regression

NASA Astrophysics Data System (ADS)

de Oliveira, Isadora R. N.; Roque, Jussara V.; Maia, Mariza P.; Stringheta, Paulo C.; Teófilo, Reinaldo F.

2018-04-01

A new method was developed to determine the antioxidant properties of red cabbage extract (Brassica oleracea) by mid (MID) and near (NIR) infrared spectroscopies and partial least squares (PLS) regression. A 70% (v/v) ethanolic extract of red cabbage was concentrated to 9° Brix and further diluted (12 to 100%) in water. The dilutions were used as external standards for the building of PLS models. For the first time, this strategy was applied for building multivariate regression models. Reference analyses and spectral data were obtained from diluted extracts. The determinate properties were total and monomeric anthocyanins, total polyphenols and antioxidant capacity by ABTS (2,2-azino-bis(3-ethyl-benzothiazoline-6-sulfonate)) and DPPH (2,2-diphenyl-1-picrylhydrazyl) methods. Ordered predictors selection (OPS) and genetic algorithm (GA) were used for feature selection before PLS regression (PLS-1). In addition, a PLS-2 regression was applied to all properties simultaneously. PLS-1 models provided more predictive models than did PLS-2 regression. PLS-OPS and PLS-GA models presented excellent prediction results with a correlation coefficient higher than 0.98. However, the best models were obtained using PLS and variable selection with the OPS algorithm and the models based on NIR spectra were considered more predictive for all properties. Then, these models provided a simple, rapid and accurate method for determination of red cabbage extract antioxidant properties and its suitability for use in the food industry.

Connectome-based predictive modeling of attention: Comparing different functional connectivity features and prediction methods across datasets.

PubMed

Yoo, Kwangsun; Rosenberg, Monica D; Hsu, Wei-Ting; Zhang, Sheng; Li, Chiang-Shan R; Scheinost, Dustin; Constable, R Todd; Chun, Marvin M

2018-02-15

Connectome-based predictive modeling (CPM; Finn et al., 2015; Shen et al., 2017) was recently developed to predict individual differences in traits and behaviors, including fluid intelligence (Finn et al., 2015) and sustained attention (Rosenberg et al., 2016a), from functional brain connectivity (FC) measured with fMRI. Here, using the CPM framework, we compared the predictive power of three different measures of FC (Pearson's correlation, accordance, and discordance) and two different prediction algorithms (linear and partial least square [PLS] regression) for attention function. Accordance and discordance are recently proposed FC measures that respectively track in-phase synchronization and out-of-phase anti-correlation (Meskaldji et al., 2015). We defined connectome-based models using task-based or resting-state FC data, and tested the effects of (1) functional connectivity measure and (2) feature-selection/prediction algorithm on individualized attention predictions. Models were internally validated in a training dataset using leave-one-subject-out cross-validation, and externally validated with three independent datasets. The training dataset included fMRI data collected while participants performed a sustained attention task and rested (N = 25; Rosenberg et al., 2016a). The validation datasets included: 1) data collected during performance of a stop-signal task and at rest (N = 83, including 19 participants who were administered methylphenidate prior to scanning; Farr et al., 2014a; Rosenberg et al., 2016b), 2) data collected during Attention Network Task performance and rest (N = 41, Rosenberg et al., in press), and 3) resting-state data and ADHD symptom severity from the ADHD-200 Consortium (N = 113; Rosenberg et al., 2016a). Models defined using all combinations of functional connectivity measure (Pearson's correlation, accordance, and discordance) and prediction algorithm (linear and PLS regression) predicted attentional abilities, with correlations between predicted and observed measures of attention as high as 0.9 for internal validation, and 0.6 for external validation (all p's < 0.05). Models trained on task data outperformed models trained on rest data. Pearson's correlation and accordance features generally showed a small numerical advantage over discordance features, while PLS regression models were usually better than linear regression models. Overall, in addition to correlation features combined with linear models (Rosenberg et al., 2016a), it is useful to consider accordance features and PLS regression for CPM. Copyright © 2017 Elsevier Inc. All rights reserved.

Computational intelligence models to predict porosity of tablets using minimum features

PubMed Central

Khalid, Mohammad Hassan; Kazemi, Pezhman; Perez-Gandarillas, Lucia; Michrafy, Abderrahim; Szlęk, Jakub; Jachowicz, Renata; Mendyk, Aleksander

2017-01-01

The effects of different formulations and manufacturing process conditions on the physical properties of a solid dosage form are of importance to the pharmaceutical industry. It is vital to have in-depth understanding of the material properties and governing parameters of its processes in response to different formulations. Understanding the mentioned aspects will allow tighter control of the process, leading to implementation of quality-by-design (QbD) practices. Computational intelligence (CI) offers an opportunity to create empirical models that can be used to describe the system and predict future outcomes in silico. CI models can help explore the behavior of input parameters, unlocking deeper understanding of the system. This research endeavor presents CI models to predict the porosity of tablets created by roll-compacted binary mixtures, which were milled and compacted under systematically varying conditions. CI models were created using tree-based methods, artificial neural networks (ANNs), and symbolic regression trained on an experimental data set and screened using root-mean-square error (RMSE) scores. The experimental data were composed of proportion of microcrystalline cellulose (MCC) (in percentage), granule size fraction (in micrometers), and die compaction force (in kilonewtons) as inputs and porosity as an output. The resulting models show impressive generalization ability, with ANNs (normalized root-mean-square error [NRMSE] =1%) and symbolic regression (NRMSE =4%) as the best-performing methods, also exhibiting reliable predictive behavior when presented with a challenging external validation data set (best achieved symbolic regression: NRMSE =3%). Symbolic regression demonstrates the transition from the black box modeling paradigm to more transparent predictive models. Predictive performance and feature selection behavior of CI models hints at the most important variables within this factor space. PMID:28138223

Computational intelligence models to predict porosity of tablets using minimum features.

PubMed

Khalid, Mohammad Hassan; Kazemi, Pezhman; Perez-Gandarillas, Lucia; Michrafy, Abderrahim; Szlęk, Jakub; Jachowicz, Renata; Mendyk, Aleksander

2017-01-01

The effects of different formulations and manufacturing process conditions on the physical properties of a solid dosage form are of importance to the pharmaceutical industry. It is vital to have in-depth understanding of the material properties and governing parameters of its processes in response to different formulations. Understanding the mentioned aspects will allow tighter control of the process, leading to implementation of quality-by-design (QbD) practices. Computational intelligence (CI) offers an opportunity to create empirical models that can be used to describe the system and predict future outcomes in silico. CI models can help explore the behavior of input parameters, unlocking deeper understanding of the system. This research endeavor presents CI models to predict the porosity of tablets created by roll-compacted binary mixtures, which were milled and compacted under systematically varying conditions. CI models were created using tree-based methods, artificial neural networks (ANNs), and symbolic regression trained on an experimental data set and screened using root-mean-square error (RMSE) scores. The experimental data were composed of proportion of microcrystalline cellulose (MCC) (in percentage), granule size fraction (in micrometers), and die compaction force (in kilonewtons) as inputs and porosity as an output. The resulting models show impressive generalization ability, with ANNs (normalized root-mean-square error [NRMSE] =1%) and symbolic regression (NRMSE =4%) as the best-performing methods, also exhibiting reliable predictive behavior when presented with a challenging external validation data set (best achieved symbolic regression: NRMSE =3%). Symbolic regression demonstrates the transition from the black box modeling paradigm to more transparent predictive models. Predictive performance and feature selection behavior of CI models hints at the most important variables within this factor space.

Gaussian Process Regression Model in Spatial Logistic Regression

NASA Astrophysics Data System (ADS)

Sofro, A.; Oktaviarina, A.

2018-01-01

Spatial analysis has developed very quickly in the last decade. One of the favorite approaches is based on the neighbourhood of the region. Unfortunately, there are some limitations such as difficulty in prediction. Therefore, we offer Gaussian process regression (GPR) to accommodate the issue. In this paper, we will focus on spatial modeling with GPR for binomial data with logit link function. The performance of the model will be investigated. We will discuss the inference of how to estimate the parameters and hyper-parameters and to predict as well. Furthermore, simulation studies will be explained in the last section.

Development and implementation of a regression model for predicting recreational water quality in the Cuyahoga River, Cuyahoga Valley National Park, Ohio 2009-11

USGS Publications Warehouse

Brady, Amie M.G.; Plona, Meg B.

2012-01-01

The Cuyahoga River within Cuyahoga Valley National Park (CVNP) is at times impaired for recreational use due to elevated concentrations of Escherichia coli (E. coli), a fecal-indicator bacterium. During the recreational seasons of mid-May through September during 2009–11, samples were collected 4 days per week and analyzed for E. coli concentrations at two sites within CVNP. Other water-quality and environ-mental data, including turbidity, rainfall, and streamflow, were measured and (or) tabulated for analysis. Regression models developed to predict recreational water quality in the river were implemented during the recreational seasons of 2009–11 for one site within CVNP–Jaite. For the 2009 and 2010 seasons, the regression models were better at predicting exceedances of Ohio's single-sample standard for primary-contact recreation compared to the traditional method of using the previous day's E. coli concentration. During 2009, the regression model was based on data collected during 2005 through 2008, excluding available 2004 data. The resulting model for 2009 did not perform as well as expected (based on the calibration data set) and tended to overestimate concentrations (correct responses at 69 percent). During 2010, the regression model was based on data collected during 2004 through 2009, including all of the available data. The 2010 model performed well, correctly predicting 89 percent of the samples above or below the single-sample standard, even though the predictions tended to be lower than actual sample concentrations. During 2011, the regression model was based on data collected during 2004 through 2010 and tended to overestimate concentrations. The 2011 model did not perform as well as the traditional method or as expected, based on the calibration dataset (correct responses at 56 percent). At a second site—Lock 29, approximately 5 river miles upstream from Jaite, a regression model based on data collected at the site during the recreational seasons of 2008–10 also did not perform as well as the traditional method or as well as expected (correct responses at 60 percent). Above normal precipitation in the region and a delayed start to the 2011 sampling season (sampling began mid-June) may have affected how well the 2011 models performed. With these new data, however, updated regression models may be better able to predict recreational water quality conditions due to the increased amount of diverse water quality conditions included in the calibration data. Daily recreational water-quality predictions for Jaite were made available on the Ohio Nowcast Web site at www.ohionowcast.info. Other public outreach included signage at trailheads in the park, articles in the park's quarterly-published schedule of events and volunteer newsletters. A U.S. Geological Survey Fact Sheet was also published to bring attention to water-quality issues in the park.

Predicting No-Shows in Radiology Using Regression Modeling of Data Available in the Electronic Medical Record.

PubMed

Harvey, H Benjamin; Liu, Catherine; Ai, Jing; Jaworsky, Cristina; Guerrier, Claude Emmanuel; Flores, Efren; Pianykh, Oleg

2017-10-01

To test whether data elements available in the electronic medical record (EMR) can be effectively leveraged to predict failure to attend a scheduled radiology examination. Using data from a large academic medical center, we identified all patients with a diagnostic imaging examination scheduled from January 1, 2016, to April 1, 2016, and determined whether the patient successfully attended the examination. Demographic, clinical, and health services utilization variables available in the EMR potentially relevant to examination attendance were recorded for each patient. We used descriptive statistics and logistic regression models to test whether these data elements could predict failure to attend a scheduled radiology examination. The predictive accuracy of the regression models were determined by calculating the area under the receiver operator curve. Among the 54,652 patient appointments with radiology examinations scheduled during the study period, 6.5% were no-shows. No-show rates were highest for the modalities of mammography and CT and lowest for PET and MRI. Logistic regression indicated that 16 of the 27 demographic, clinical, and health services utilization factors were significantly associated with failure to attend a scheduled radiology examination (P ≤ .05). Stepwise logistic regression analysis demonstrated that previous no-shows, days between scheduling and appointments, modality type, and insurance type were most strongly predictive of no-show. A model considering all 16 data elements had good ability to predict radiology no-shows (area under the receiver operator curve = 0.753). The predictive ability was similar or improved when these models were analyzed by modality. Patient and examination information readily available in the EMR can be successfully used to predict radiology no-shows. Moving forward, this information can be proactively leveraged to identify patients who might benefit from additional patient engagement through appointment reminders or other targeted interventions to avoid no-shows. Copyright © 2017 American College of Radiology. Published by Elsevier Inc. All rights reserved.

Monthly streamflow forecasting in the Rhine basin

NASA Astrophysics Data System (ADS)

Schick, Simon; Rössler, Ole; Weingartner, Rolf

2017-04-01

Forecasting seasonal streamflow of the Rhine river is of societal relevance as the Rhine is an important water way and water resource in Western Europe. The present study investigates the predictability of monthly mean streamflow at lead times of zero, one, and two months with the focus on potential benefits by the integration of seasonal climate predictions. Specifically, we use seasonal predictions of precipitation and surface air temperature released by the European Centre for Medium-Range Weather Forecasts (ECMWF) for a regression analysis. In order to disentangle forecast uncertainty, the 'Reverse Ensemble Streamflow Prediction' framework is adapted here to the context of regression: By using appropriate subsets of predictors the regression model is constrained to either the initial conditions, the meteorological forcing, or both. An operational application is mimicked by equipping the model with the seasonal climate predictions provided by ECMWF. Finally, to mitigate the spatial aggregation of the meteorological fields the model is also applied at the subcatchment scale, and the resulting predictions are combined afterwards. The hindcast experiment is carried out for the period 1982-2011 in cross validation mode at two gauging stations, namely the Rhine at Lobith and Basel. The results show that monthly forecasts are skillful with respect to climatology only at zero lead time. In addition, at zero lead time the integration of seasonal climate predictions decreases the mean absolute error by 5 to 10 percentage compared to forecasts which are solely based on initial conditions. This reduction most likely is induced by the seasonal prediction of precipitation and not air temperature. The study is completed by bench marking the regression model with runoff simulations from ECMWFs seasonal forecast system. By simply using basin averages followed by a linear bias correction, these runoff simulations translate well to monthly streamflow. Though the regression model is only slightly outperformed, we argue that runoff out of the land surface component of seasonal climate forecasting systems is an interesting option when it comes to seasonal streamflow forecasting in large river basins.

Predicting Energy Performance of a Net-Zero Energy Building: A Statistical Approach

PubMed Central

Kneifel, Joshua; Webb, David

2016-01-01

Performance-based building requirements have become more prevalent because it gives freedom in building design while still maintaining or exceeding the energy performance required by prescriptive-based requirements. In order to determine if building designs reach target energy efficiency improvements, it is necessary to estimate the energy performance of a building using predictive models and different weather conditions. Physics-based whole building energy simulation modeling is the most common approach. However, these physics-based models include underlying assumptions and require significant amounts of information in order to specify the input parameter values. An alternative approach to test the performance of a building is to develop a statistically derived predictive regression model using post-occupancy data that can accurately predict energy consumption and production based on a few common weather-based factors, thus requiring less information than simulation models. A regression model based on measured data should be able to predict energy performance of a building for a given day as long as the weather conditions are similar to those during the data collection time frame. This article uses data from the National Institute of Standards and Technology (NIST) Net-Zero Energy Residential Test Facility (NZERTF) to develop and validate a regression model to predict the energy performance of the NZERTF using two weather variables aggregated to the daily level, applies the model to estimate the energy performance of hypothetical NZERTFs located in different cities in the Mixed-Humid climate zone, and compares these estimates to the results from already existing EnergyPlus whole building energy simulations. This regression model exhibits agreement with EnergyPlus predictive trends in energy production and net consumption, but differs greatly in energy consumption. The model can be used as a framework for alternative and more complex models based on the experimental data collected from the NZERTF. PMID:27956756

Predicting Energy Performance of a Net-Zero Energy Building: A Statistical Approach.

PubMed

Kneifel, Joshua; Webb, David

2016-09-01

Performance-based building requirements have become more prevalent because it gives freedom in building design while still maintaining or exceeding the energy performance required by prescriptive-based requirements. In order to determine if building designs reach target energy efficiency improvements, it is necessary to estimate the energy performance of a building using predictive models and different weather conditions. Physics-based whole building energy simulation modeling is the most common approach. However, these physics-based models include underlying assumptions and require significant amounts of information in order to specify the input parameter values. An alternative approach to test the performance of a building is to develop a statistically derived predictive regression model using post-occupancy data that can accurately predict energy consumption and production based on a few common weather-based factors, thus requiring less information than simulation models. A regression model based on measured data should be able to predict energy performance of a building for a given day as long as the weather conditions are similar to those during the data collection time frame. This article uses data from the National Institute of Standards and Technology (NIST) Net-Zero Energy Residential Test Facility (NZERTF) to develop and validate a regression model to predict the energy performance of the NZERTF using two weather variables aggregated to the daily level, applies the model to estimate the energy performance of hypothetical NZERTFs located in different cities in the Mixed-Humid climate zone, and compares these estimates to the results from already existing EnergyPlus whole building energy simulations. This regression model exhibits agreement with EnergyPlus predictive trends in energy production and net consumption, but differs greatly in energy consumption. The model can be used as a framework for alternative and more complex models based on the experimental data collected from the NZERTF.

Prediction by regression and intrarange data scatter in surface-process studies

USGS Publications Warehouse

Toy, T.J.; Osterkamp, W.R.; Renard, K.G.

1993-01-01

Modeling is a major component of contemporary earth science, and regression analysis occupies a central position in the parameterization, calibration, and validation of geomorphic and hydrologic models. Although this methodology can be used in many ways, we are primarily concerned with the prediction of values for one variable from another variable. Examination of the literature reveals considerable inconsistency in the presentation of the results of regression analysis and the occurrence of patterns in the scatter of data points about the regression line. Both circumstances confound utilization and evaluation of the models. Statisticians are well aware of various problems associated with the use of regression analysis and offer improved practices; often, however, their guidelines are not followed. After a review of the aforementioned circumstances and until standard criteria for model evaluation become established, we recommend, as a minimum, inclusion of scatter diagrams, the standard error of the estimate, and sample size in reporting the results of regression analyses for most surface-process studies. ?? 1993 Springer-Verlag.

Using Logistic Regression To Predict the Probability of Debris Flows Occurring in Areas Recently Burned By Wildland Fires

USGS Publications Warehouse

Rupert, Michael G.; Cannon, Susan H.; Gartner, Joseph E.

2003-01-01

Logistic regression was used to predict the probability of debris flows occurring in areas recently burned by wildland fires. Multiple logistic regression is conceptually similar to multiple linear regression because statistical relations between one dependent variable and several independent variables are evaluated. In logistic regression, however, the dependent variable is transformed to a binary variable (debris flow did or did not occur), and the actual probability of the debris flow occurring is statistically modeled. Data from 399 basins located within 15 wildland fires that burned during 2000-2002 in Colorado, Idaho, Montana, and New Mexico were evaluated. More than 35 independent variables describing the burn severity, geology, land surface gradient, rainfall, and soil properties were evaluated. The models were developed as follows: (1) Basins that did and did not produce debris flows were delineated from National Elevation Data using a Geographic Information System (GIS). (2) Data describing the burn severity, geology, land surface gradient, rainfall, and soil properties were determined for each basin. These data were then downloaded to a statistics software package for analysis using logistic regression. (3) Relations between the occurrence/non-occurrence of debris flows and burn severity, geology, land surface gradient, rainfall, and soil properties were evaluated and several preliminary multivariate logistic regression models were constructed. All possible combinations of independent variables were evaluated to determine which combination produced the most effective model. The multivariate model that best predicted the occurrence of debris flows was selected. (4) The multivariate logistic regression model was entered into a GIS, and a map showing the probability of debris flows was constructed. The most effective model incorporates the percentage of each basin with slope greater than 30 percent, percentage of land burned at medium and high burn severity in each basin, particle size sorting, average storm intensity (millimeters per hour), soil organic matter content, soil permeability, and soil drainage. The results of this study demonstrate that logistic regression is a valuable tool for predicting the probability of debris flows occurring in recently-burned landscapes.

Whole-genome regression and prediction methods applied to plant and animal breeding.

PubMed

de Los Campos, Gustavo; Hickey, John M; Pong-Wong, Ricardo; Daetwyler, Hans D; Calus, Mario P L

2013-02-01

Genomic-enabled prediction is becoming increasingly important in animal and plant breeding and is also receiving attention in human genetics. Deriving accurate predictions of complex traits requires implementing whole-genome regression (WGR) models where phenotypes are regressed on thousands of markers concurrently. Methods exist that allow implementing these large-p with small-n regressions, and genome-enabled selection (GS) is being implemented in several plant and animal breeding programs. The list of available methods is long, and the relationships between them have not been fully addressed. In this article we provide an overview of available methods for implementing parametric WGR models, discuss selected topics that emerge in applications, and present a general discussion of lessons learned from simulation and empirical data analysis in the last decade.

Whole-Genome Regression and Prediction Methods Applied to Plant and Animal Breeding

PubMed Central

de los Campos, Gustavo; Hickey, John M.; Pong-Wong, Ricardo; Daetwyler, Hans D.; Calus, Mario P. L.

2013-01-01

Genomic-enabled prediction is becoming increasingly important in animal and plant breeding and is also receiving attention in human genetics. Deriving accurate predictions of complex traits requires implementing whole-genome regression (WGR) models where phenotypes are regressed on thousands of markers concurrently. Methods exist that allow implementing these large-p with small-n regressions, and genome-enabled selection (GS) is being implemented in several plant and animal breeding programs. The list of available methods is long, and the relationships between them have not been fully addressed. In this article we provide an overview of available methods for implementing parametric WGR models, discuss selected topics that emerge in applications, and present a general discussion of lessons learned from simulation and empirical data analysis in the last decade. PMID:22745228

Deep learning architecture for air quality predictions.

PubMed

Li, Xiang; Peng, Ling; Hu, Yuan; Shao, Jing; Chi, Tianhe

2016-11-01

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.

Four Major South Korea's Rivers Using Deep Learning Models.

PubMed

Lee, Sangmok; Lee, Donghyun

2018-06-24

Harmful algal blooms are an annual phenomenon that cause environmental damage, economic losses, and disease outbreaks. A fundamental solution to this problem is still lacking, thus, the best option for counteracting the effects of algal blooms is to improve advance warnings (predictions). However, existing physical prediction models have difficulties setting a clear coefficient indicating the relationship between each factor when predicting algal blooms, and many variable data sources are required for the analysis. These limitations are accompanied by high time and economic costs. Meanwhile, artificial intelligence and deep learning methods have become increasingly common in scientific research; attempts to apply the long short-term memory (LSTM) model to environmental research problems are increasing because the LSTM model exhibits good performance for time-series data prediction. However, few studies have applied deep learning models or LSTM to algal bloom prediction, especially in South Korea, where algal blooms occur annually. Therefore, we employed the LSTM model for algal bloom prediction in four major rivers of South Korea. We conducted short-term (one week) predictions by employing regression analysis and deep learning techniques on a newly constructed water quality and quantity dataset drawn from 16 dammed pools on the rivers. Three deep learning models (multilayer perceptron, MLP; recurrent neural network, RNN; and long short-term memory, LSTM) were used to predict chlorophyll-a, a recognized proxy for algal activity. The results were compared to those from OLS (ordinary least square) regression analysis and actual data based on the root mean square error (RSME). The LSTM model showed the highest prediction rate for harmful algal blooms and all deep learning models out-performed the OLS regression analysis. Our results reveal the potential for predicting algal blooms using LSTM and deep learning.

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

Singh, Kunwar P., E-mail: kpsingh_52@yahoo.com; Gupta, Shikha

Ensemble learning approach based decision treeboost (DTB) and decision tree forest (DTF) models are introduced in order to establish quantitative structure–toxicity relationship (QSTR) for the prediction of toxicity of 1450 diverse chemicals. Eight non-quantum mechanical molecular descriptors were derived. Structural diversity of the chemicals was evaluated using Tanimoto similarity index. Stochastic gradient boosting and bagging algorithms supplemented DTB and DTF models were constructed for classification and function optimization problems using the toxicity end-point in T. pyriformis. Special attention was drawn to prediction ability and robustness of the models, investigated both in external and 10-fold cross validation processes. In complete data,more » optimal DTB and DTF models rendered accuracies of 98.90%, 98.83% in two-category and 98.14%, 98.14% in four-category toxicity classifications. Both the models further yielded classification accuracies of 100% in external toxicity data of T. pyriformis. The constructed regression models (DTB and DTF) using five descriptors yielded correlation coefficients (R{sup 2}) of 0.945, 0.944 between the measured and predicted toxicities with mean squared errors (MSEs) of 0.059, and 0.064 in complete T. pyriformis data. The T. pyriformis regression models (DTB and DTF) applied to the external toxicity data sets yielded R{sup 2} and MSE values of 0.637, 0.655; 0.534, 0.507 (marine bacteria) and 0.741, 0.691; 0.155, 0.173 (algae). The results suggest for wide applicability of the inter-species models in predicting toxicity of new chemicals for regulatory purposes. These approaches provide useful strategy and robust tools in the screening of ecotoxicological risk or environmental hazard potential of chemicals. - Graphical abstract: Importance of input variables in DTB and DTF classification models for (a) two-category, and (b) four-category toxicity intervals in T. pyriformis data. Generalization and predictive abilities of the constructed (c) DTB and (d) DTF regression models to predict the T. pyriformis toxicity of diverse chemicals. - Highlights: • Ensemble learning (EL) based models constructed for toxicity prediction of chemicals • Predictive models used a few simple non-quantum mechanical molecular descriptors. • EL-based DTB/DTF models successfully discriminated toxic and non-toxic chemicals. • DTB/DTF regression models precisely predicted toxicity of chemicals in multi-species. • Proposed EL based models can be used as tool to predict toxicity of new chemicals.« less

Regression: The Apple Does Not Fall Far From the Tree.

PubMed

Vetter, Thomas R; Schober, Patrick

2018-05-15

Researchers and clinicians are frequently interested in either: (1) assessing whether there is a relationship or association between 2 or more variables and quantifying this association; or (2) determining whether 1 or more variables can predict another variable. The strength of such an association is mainly described by the correlation. However, regression analysis and regression models can be used not only to identify whether there is a significant relationship or association between variables but also to generate estimations of such a predictive relationship between variables. This basic statistical tutorial discusses the fundamental concepts and techniques related to the most common types of regression analysis and modeling, including simple linear regression, multiple regression, logistic regression, ordinal regression, and Poisson regression, as well as the common yet often underrecognized phenomenon of regression toward the mean. The various types of regression analysis are powerful statistical techniques, which when appropriately applied, can allow for the valid interpretation of complex, multifactorial data. Regression analysis and models can assess whether there is a relationship or association between 2 or more observed variables and estimate the strength of this association, as well as determine whether 1 or more variables can predict another variable. Regression is thus being applied more commonly in anesthesia, perioperative, critical care, and pain research. However, it is crucial to note that regression can identify plausible risk factors; it does not prove causation (a definitive cause and effect relationship). The results of a regression analysis instead identify independent (predictor) variable(s) associated with the dependent (outcome) variable. As with other statistical methods, applying regression requires that certain assumptions be met, which can be tested with specific diagnostics.

Regional regression models of watershed suspended-sediment discharge for the eastern United States

NASA Astrophysics Data System (ADS)

Roman, David C.; Vogel, Richard M.; Schwarz, Gregory E.

2012-11-01

SummaryEstimates of mean annual watershed sediment discharge, derived from long-term measurements of suspended-sediment concentration and streamflow, often are not available at locations of interest. The goal of this study was to develop multivariate regression models to enable prediction of mean annual suspended-sediment discharge from available basin characteristics useful for most ungaged river locations in the eastern United States. The models are based on long-term mean sediment discharge estimates and explanatory variables obtained from a combined dataset of 1201 US Geological Survey (USGS) stations derived from a SPAtially Referenced Regression on Watershed attributes (SPARROW) study and the Geospatial Attributes of Gages for Evaluating Streamflow (GAGES) database. The resulting regional regression models summarized for major US water resources regions 1-8, exhibited prediction R2 values ranging from 76.9% to 92.7% and corresponding average model prediction errors ranging from 56.5% to 124.3%. Results from cross-validation experiments suggest that a majority of the models will perform similarly to calibration runs. The 36-parameter regional regression models also outperformed a 16-parameter national SPARROW model of suspended-sediment discharge and indicate that mean annual sediment loads in the eastern United States generally correlates with a combination of basin area, land use patterns, seasonal precipitation, soil composition, hydrologic modification, and to a lesser extent, topography.

Regional regression models of watershed suspended-sediment discharge for the eastern United States

USGS Publications Warehouse

Roman, David C.; Vogel, Richard M.; Schwarz, Gregory E.

2012-01-01

Estimates of mean annual watershed sediment discharge, derived from long-term measurements of suspended-sediment concentration and streamflow, often are not available at locations of interest. The goal of this study was to develop multivariate regression models to enable prediction of mean annual suspended-sediment discharge from available basin characteristics useful for most ungaged river locations in the eastern United States. The models are based on long-term mean sediment discharge estimates and explanatory variables obtained from a combined dataset of 1201 US Geological Survey (USGS) stations derived from a SPAtially Referenced Regression on Watershed attributes (SPARROW) study and the Geospatial Attributes of Gages for Evaluating Streamflow (GAGES) database. The resulting regional regression models summarized for major US water resources regions 1–8, exhibited prediction R2 values ranging from 76.9% to 92.7% and corresponding average model prediction errors ranging from 56.5% to 124.3%. Results from cross-validation experiments suggest that a majority of the models will perform similarly to calibration runs. The 36-parameter regional regression models also outperformed a 16-parameter national SPARROW model of suspended-sediment discharge and indicate that mean annual sediment loads in the eastern United States generally correlates with a combination of basin area, land use patterns, seasonal precipitation, soil composition, hydrologic modification, and to a lesser extent, topography.

Stata Modules for Calculating Novel Predictive Performance Indices for Logistic Models

PubMed Central

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

2016-01-01

Background 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. Objectives 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. Materials and Methods 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. Results The command is addpred for logistic regression models. Conclusions The Stata package provided herein can encourage the use of novel methods in examining predictive capacity of ever-emerging plethora of novel biomarkers. PMID:27279830

Predicting surface fuel models and fuel metrics using lidar and CIR imagery in a dense mixed conifer forest

Treesearch

Marek K. Jakubowksi; Qinghua Guo; Brandon Collins; Scott Stephens; Maggi Kelly

2013-01-01

We compared the ability of several classification and regression algorithms to predict forest stand structure metrics and standard surface fuel models. Our study area spans a dense, topographically complex Sierra Nevada mixed-conifer forest. We used clustering, regression trees, and support vector machine algorithms to analyze high density (average 9 pulses/m

Prediction of hearing outcomes by multiple regression analysis in patients with idiopathic sudden sensorineural hearing loss.

PubMed

Suzuki, Hideaki; Tabata, Takahisa; Koizumi, Hiroki; Hohchi, Nobusuke; Takeuchi, Shoko; Kitamura, Takuro; Fujino, Yoshihisa; Ohbuchi, Toyoaki

2014-12-01

This study aimed to create a multiple regression model for predicting hearing outcomes of idiopathic sudden sensorineural hearing loss (ISSNHL). The participants were 205 consecutive patients (205 ears) with ISSNHL (hearing level ≥ 40 dB, interval between onset and treatment ≤ 30 days). They received systemic steroid administration combined with intratympanic steroid injection. Data were examined by simple and multiple regression analyses. Three hearing indices (percentage hearing improvement, hearing gain, and posttreatment hearing level [HLpost]) and 7 prognostic factors (age, days from onset to treatment, initial hearing level, initial hearing level at low frequencies, initial hearing level at high frequencies, presence of vertigo, and contralateral hearing level) were included in the multiple regression analysis as dependent and explanatory variables, respectively. In the simple regression analysis, the percentage hearing improvement, hearing gain, and HLpost showed significant correlation with 2, 5, and 6 of the 7 prognostic factors, respectively. The multiple correlation coefficients were 0.396, 0.503, and 0.714 for the percentage hearing improvement, hearing gain, and HLpost, respectively. Predicted values of HLpost calculated by the multiple regression equation were reliable with 70% probability with a 40-dB-width prediction interval. Prediction of HLpost by the multiple regression model may be useful to estimate the hearing prognosis of ISSNHL. © The Author(s) 2014.

Prediction of sweetness and amino acid content in soybean crops from hyperspectral imagery

NASA Astrophysics Data System (ADS)

Monteiro, Sildomar Takahashi; Minekawa, Yohei; Kosugi, Yukio; Akazawa, Tsuneya; Oda, Kunio

Hyperspectral image data provides a powerful tool for non-destructive crop analysis. This paper investigates a hyperspectral image data-processing method to predict the sweetness and amino acid content of soybean crops. Regression models based on artificial neural networks were developed in order to calculate the level of sucrose, glucose, fructose, and nitrogen concentrations, which can be related to the sweetness and amino acid content of vegetables. A performance analysis was conducted comparing regression models obtained using different preprocessing methods, namely, raw reflectance, second derivative, and principal components analysis. This method is demonstrated using high-resolution hyperspectral data of wavelengths ranging from the visible to the near infrared acquired from an experimental field of green vegetable soybeans. The best predictions were achieved using a nonlinear regression model of the second derivative transformed dataset. Glucose could be predicted with greater accuracy, followed by sucrose, fructose and nitrogen. The proposed method provides the possibility to provide relatively accurate maps predicting the chemical content of soybean crop fields.

Regression modeling and prediction of road sweeping brush load characteristics from finite element analysis and experimental results.

PubMed

Wang, Chong; Sun, Qun; Wahab, Magd Abdel; Zhang, Xingyu; Xu, Limin

2015-09-01

Rotary cup brushes mounted on each side of a road sweeper undertake heavy debris removal tasks but the characteristics have not been well known until recently. A Finite Element (FE) model that can analyze brush deformation and predict brush characteristics have been developed to investigate the sweeping efficiency and to assist the controller design. However, the FE model requires large amount of CPU time to simulate each brush design and operating scenario, which may affect its applications in a real-time system. This study develops a mathematical regression model to summarize the FE modeled results. The complex brush load characteristic curves were statistically analyzed to quantify the effects of cross-section, length, mounting angle, displacement and rotational speed etc. The data were then fitted by a multiple variable regression model using the maximum likelihood method. The fitted results showed good agreement with the FE analysis results and experimental results, suggesting that the mathematical regression model may be directly used in a real-time system to predict characteristics of different brushes under varying operating conditions. The methodology may also be used in the design and optimization of rotary brush tools. Copyright © 2015 Elsevier Ltd. All rights reserved.

An Application to the Prediction of LOD Change Based on General Regression Neural Network

NASA Astrophysics Data System (ADS)

Zhang, X. H.; Wang, Q. J.; Zhu, J. J.; Zhang, H.

2011-07-01

Traditional prediction of the LOD (length of day) change was based on linear models, such as the least square model and the autoregressive technique, etc. Due to the complex non-linear features of the LOD variation, the performances of the linear model predictors are not fully satisfactory. This paper applies a non-linear neural network - general regression neural network (GRNN) model to forecast the LOD change, and the results are analyzed and compared with those obtained with the back propagation neural network and other models. The comparison shows that the performance of the GRNN model in the prediction of the LOD change is efficient and feasible.

Verifying the performance of artificial neural network and multiple linear regression in predicting the mean seasonal municipal solid waste generation rate: A case study of Fars province, Iran.

PubMed

Azadi, Sama; Karimi-Jashni, Ayoub

2016-02-01

Predicting the mass of solid waste generation plays an important role in integrated solid waste management plans. In this study, the performance of two predictive models, Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) was verified to predict mean Seasonal Municipal Solid Waste Generation (SMSWG) rate. The accuracy of the proposed models is illustrated through a case study of 20 cities located in Fars Province, Iran. Four performance measures, MAE, MAPE, RMSE and R were used to evaluate the performance of these models. The MLR, as a conventional model, showed poor prediction performance. On the other hand, the results indicated that the ANN model, as a non-linear model, has a higher predictive accuracy when it comes to prediction of the mean SMSWG rate. As a result, in order to develop a more cost-effective strategy for waste management in the future, the ANN model could be used to predict the mean SMSWG rate. Copyright © 2015 Elsevier Ltd. All rights reserved.

Use of multivariate linear regression and support vector regression to predict functional outcome after surgery for cervical spondylotic myelopathy.

PubMed

Hoffman, Haydn; Lee, Sunghoon I; Garst, Jordan H; Lu, Derek S; Li, Charles H; Nagasawa, Daniel T; Ghalehsari, Nima; Jahanforouz, Nima; Razaghy, Mehrdad; Espinal, Marie; Ghavamrezaii, Amir; Paak, Brian H; Wu, Irene; Sarrafzadeh, Majid; Lu, Daniel C

2015-09-01

This study introduces the use of multivariate linear regression (MLR) and support vector regression (SVR) models to predict postoperative outcomes in a cohort of patients who underwent surgery for cervical spondylotic myelopathy (CSM). Currently, predicting outcomes after surgery for CSM remains a challenge. We recruited patients who had a diagnosis of CSM and required decompressive surgery with or without fusion. Fine motor function was tested preoperatively and postoperatively with a handgrip-based tracking device that has been previously validated, yielding mean absolute accuracy (MAA) results for two tracking tasks (sinusoidal and step). All patients completed Oswestry disability index (ODI) and modified Japanese Orthopaedic Association questionnaires preoperatively and postoperatively. Preoperative data was utilized in MLR and SVR models to predict postoperative ODI. Predictions were compared to the actual ODI scores with the coefficient of determination (R(2)) and mean absolute difference (MAD). From this, 20 patients met the inclusion criteria and completed follow-up at least 3 months after surgery. With the MLR model, a combination of the preoperative ODI score, preoperative MAA (step function), and symptom duration yielded the best prediction of postoperative ODI (R(2)=0.452; MAD=0.0887; p=1.17 × 10(-3)). With the SVR model, a combination of preoperative ODI score, preoperative MAA (sinusoidal function), and symptom duration yielded the best prediction of postoperative ODI (R(2)=0.932; MAD=0.0283; p=5.73 × 10(-12)). The SVR model was more accurate than the MLR model. The SVR can be used preoperatively in risk/benefit analysis and the decision to operate. Copyright © 2015 Elsevier Ltd. All rights reserved.

Performance characterization of complex fuel port geometries for hybrid rocket fuel grains

NASA Astrophysics Data System (ADS)

Bath, Andrew

This research investigated the 3D printing and burning of fuel grains with complex geometry and the development of software capable of modeling and predicting the regression of a cross-section of these complex fuel grains. The software developed did predict the geometry to a fair degree of accuracy, especially when enhanced corner rounding was turned on. The model does have some drawbacks, notably being relatively slow, and does not perfectly predict the regression. If corner rounding is turned off, however, the model does become much faster; although less accurate, this method does still predict a relatively accurate resulting burn geometry, and is fast enough to be used for performance-tuning or genetic algorithms. In addition to the modeling method, preliminary investigations into the burning behavior of fuel grains with a helical flow path were performed. The helix fuel grains have a regression rate of nearly 3 times that of any other fuel grain geometry, primarily due to the enhancement of the friction coefficient between the flow and flow path.

Accelerated Changes in Cortical Thickness Measurements with Age in Military Service Members with Traumatic Brain Injury.

PubMed

Savjani, Ricky R; Taylor, Brian A; Acion, Laura; Wilde, Elisabeth A; Jorge, Ricardo E

2017-11-15

Finding objective and quantifiable imaging markers of mild traumatic brain injury (TBI) has proven challenging, especially in the military population. Changes in cortical thickness after injury have been reported in animals and in humans, but it is unclear how these alterations manifest in the chronic phase, and it is difficult to characterize accurately with imaging. We used cortical thickness measures derived from Advanced Normalization Tools (ANTs) to predict a continuous demographic variable: age. We trained four different regression models (linear regression, support vector regression, Gaussian process regression, and random forests) to predict age from healthy control brains from publicly available datasets (n = 762). We then used these models to predict brain age in military Service Members with TBI (n = 92) and military Service Members without TBI (n = 34). Our results show that all four models overpredicted age in Service Members with TBI, and the predicted age difference was significantly greater compared with military controls. These data extend previous civilian findings and show that cortical thickness measures may reveal an association of accelerated changes over time with military TBI.

Improving near-infrared prediction model robustness with support vector machine regression: a pharmaceutical tablet assay example.

PubMed

Igne, Benoît; Drennen, James K; Anderson, Carl A

2014-01-01

Changes in raw materials and process wear and tear can have significant effects on the prediction error of near-infrared calibration models. When the variability that is present during routine manufacturing is not included in the calibration, test, and validation sets, the long-term performance and robustness of the model will be limited. Nonlinearity is a major source of interference. In near-infrared spectroscopy, nonlinearity can arise from light path-length differences that can come from differences in particle size or density. The usefulness of support vector machine (SVM) regression to handle nonlinearity and improve the robustness of calibration models in scenarios where the calibration set did not include all the variability present in test was evaluated. Compared to partial least squares (PLS) regression, SVM regression was less affected by physical (particle size) and chemical (moisture) differences. The linearity of the SVM predicted values was also improved. Nevertheless, although visualization and interpretation tools have been developed to enhance the usability of SVM-based methods, work is yet to be done to provide chemometricians in the pharmaceutical industry with a regression method that can supplement PLS-based methods.

Logistic regression analysis of conventional ultrasonography, strain elastosonography, and contrast-enhanced ultrasound characteristics for the differentiation of benign and malignant thyroid nodules

PubMed Central

Deng, Yingyuan; Wang, Tianfu; Chen, Siping; Liu, Weixiang

2017-01-01

The aim of the study is to screen the significant sonographic features by logistic regression analysis and fit a model to diagnose thyroid nodules. A total of 525 pathological thyroid nodules were retrospectively analyzed. All the nodules underwent conventional ultrasonography (US), strain elastosonography (SE), and contrast -enhanced ultrasound (CEUS). Those nodules’ 12 suspicious sonographic features were used to assess thyroid nodules. The significant features of diagnosing thyroid nodules were picked out by logistic regression analysis. All variables that were statistically related to diagnosis of thyroid nodules, at a level of p < 0.05 were embodied in a logistic regression analysis model. The significant features in the logistic regression model of diagnosing thyroid nodules were calcification, suspected cervical lymph node metastasis, hypoenhancement pattern, margin, shape, vascularity, posterior acoustic, echogenicity, and elastography score. According to the results of logistic regression analysis, the formula that could predict whether or not thyroid nodules are malignant was established. The area under the receiver operating curve (ROC) was 0.930 and the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 83.77%, 89.56%, 87.05%, 86.04%, and 87.79% respectively. PMID:29228030

Logistic regression analysis of conventional ultrasonography, strain elastosonography, and contrast-enhanced ultrasound characteristics for the differentiation of benign and malignant thyroid nodules.

PubMed

Pang, Tiantian; Huang, Leidan; Deng, Yingyuan; Wang, Tianfu; Chen, Siping; Gong, Xuehao; Liu, Weixiang

2017-01-01

The aim of the study is to screen the significant sonographic features by logistic regression analysis and fit a model to diagnose thyroid nodules. A total of 525 pathological thyroid nodules were retrospectively analyzed. All the nodules underwent conventional ultrasonography (US), strain elastosonography (SE), and contrast -enhanced ultrasound (CEUS). Those nodules' 12 suspicious sonographic features were used to assess thyroid nodules. The significant features of diagnosing thyroid nodules were picked out by logistic regression analysis. All variables that were statistically related to diagnosis of thyroid nodules, at a level of p < 0.05 were embodied in a logistic regression analysis model. The significant features in the logistic regression model of diagnosing thyroid nodules were calcification, suspected cervical lymph node metastasis, hypoenhancement pattern, margin, shape, vascularity, posterior acoustic, echogenicity, and elastography score. According to the results of logistic regression analysis, the formula that could predict whether or not thyroid nodules are malignant was established. The area under the receiver operating curve (ROC) was 0.930 and the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 83.77%, 89.56%, 87.05%, 86.04%, and 87.79% respectively.

Blood glucose level prediction based on support vector regression using mobile platforms.

PubMed

Reymann, Maximilian P; Dorschky, Eva; Groh, Benjamin H; Martindale, Christine; Blank, Peter; Eskofier, Bjoern M

2016-08-01

The correct treatment of diabetes is vital to a patient's health: Staying within defined blood glucose levels prevents dangerous short- and long-term effects on the body. Mobile devices informing patients about their future blood glucose levels could enable them to take counter-measures to prevent hypo or hyper periods. Previous work addressed this challenge by predicting the blood glucose levels using regression models. However, these approaches required a physiological model, representing the human body's response to insulin and glucose intake, or are not directly applicable to mobile platforms (smart phones, tablets). In this paper, we propose an algorithm for mobile platforms to predict blood glucose levels without the need for a physiological model. Using an online software simulator program, we trained a Support Vector Regression (SVR) model and exported the parameter settings to our mobile platform. The prediction accuracy of our mobile platform was evaluated with pre-recorded data of a type 1 diabetes patient. The blood glucose level was predicted with an error of 19 % compared to the true value. Considering the permitted error of commercially used devices of 15 %, our algorithm is the basis for further development of mobile prediction algorithms.

Multiple regression analysis in modelling of carbon dioxide emissions by energy consumption use in Malaysia

NASA Astrophysics Data System (ADS)

Keat, Sim Chong; Chun, Beh Boon; San, Lim Hwee; Jafri, Mohd Zubir Mat

2015-04-01

Climate change due to carbon dioxide (CO2) emissions is one of the most complex challenges threatening our planet. This issue considered as a great and international concern that primary attributed from different fossil fuels. In this paper, regression model is used for analyzing the causal relationship among CO2 emissions based on the energy consumption in Malaysia using time series data for the period of 1980-2010. The equations were developed using regression model based on the eight major sources that contribute to the CO2 emissions such as non energy, Liquefied Petroleum Gas (LPG), diesel, kerosene, refinery gas, Aviation Turbine Fuel (ATF) and Aviation Gasoline (AV Gas), fuel oil and motor petrol. The related data partly used for predict the regression model (1980-2000) and partly used for validate the regression model (2001-2010). The results of the prediction model with the measured data showed a high correlation coefficient (R2=0.9544), indicating the model's accuracy and efficiency. These results are accurate and can be used in early warning of the population to comply with air quality standards.

Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters

PubMed Central

2014-01-01

This paper examined the efficiency of multivariate linear regression (MLR) and artificial neural network (ANN) models in prediction of two major water quality parameters in a wastewater treatment plant. Biochemical oxygen demand (BOD) and chemical oxygen demand (COD) as well as indirect indicators of organic matters are representative parameters for sewer water quality. Performance of the ANN models was evaluated using coefficient of correlation (r), root mean square error (RMSE) and bias values. The computed values of BOD and COD by model, ANN method and regression analysis were in close agreement with their respective measured values. Results showed that the ANN performance model was better than the MLR model. Comparative indices of the optimized ANN with input values of temperature (T), pH, total suspended solid (TSS) and total suspended (TS) for prediction of BOD was RMSE = 25.1 mg/L, r = 0.83 and for prediction of COD was RMSE = 49.4 mg/L, r = 0.81. It was found that the ANN model could be employed successfully in estimating the BOD and COD in the inlet of wastewater biochemical treatment plants. Moreover, sensitive examination results showed that pH parameter have more effect on BOD and COD predicting to another parameters. Also, both implemented models have predicted BOD better than COD. PMID:24456676

Survival Regression Modeling Strategies in CVD Prediction.

PubMed

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

2016-04-01

A fundamental part of prevention is prediction. Potential predictors are the sine qua non of prediction models. However, whether incorporating novel predictors to prediction models could be directly translated to added predictive value remains an area of dispute. The difference between the predictive power of a predictive model with (enhanced model) and without (baseline model) a certain predictor is generally regarded as an indicator of the predictive value added by that predictor. Indices such as discrimination and calibration have long been used in this regard. Recently, the use of added predictive value has been suggested while comparing the predictive performances of the predictive models with and without novel biomarkers. User-friendly statistical software capable of implementing novel statistical procedures is conspicuously lacking. This shortcoming has restricted implementation of such novel model assessment methods. We aimed to construct Stata commands to help researchers obtain the aforementioned statistical indices. We have written Stata commands that are intended to help researchers obtain the following. 1, Nam-D'Agostino X 2 goodness of fit test; 2, Cut point-free and cut point-based net reclassification improvement index (NRI), relative absolute integrated discriminatory improvement index (IDI), and survival-based regression analyses. We applied the commands to real data on women participating in the Tehran lipid and glucose study (TLGS) to examine if information relating to a family history of premature cardiovascular disease (CVD), waist circumference, and fasting plasma glucose can improve predictive performance of Framingham's general CVD risk algorithm. The command is adpredsurv for survival models. Herein we have described the Stata package "adpredsurv" for calculation of the Nam-D'Agostino X 2 goodness of fit test as well as cut point-free and cut point-based NRI, relative and absolute IDI, and survival-based regression analyses. We hope this work encourages the use of novel methods in examining predictive capacity of the emerging plethora of novel biomarkers.

[Prediction model of health workforce and beds in county hospitals of Hunan by multiple linear regression].

PubMed

Ling, Ru; Liu, Jiawang

2011-12-01

To construct prediction model for health workforce and hospital beds in county hospitals of Hunan by multiple linear regression. We surveyed 16 counties in Hunan with stratified random sampling according to uniform questionnaires,and multiple linear regression analysis with 20 quotas selected by literature view was done. Independent variables in the multiple linear regression model on medical personnels in county hospitals included the counties' urban residents' income, crude death rate, medical beds, business occupancy, professional equipment value, the number of devices valued above 10 000 yuan, fixed assets, long-term debt, medical income, medical expenses, outpatient and emergency visits, hospital visits, actual available bed days, and utilization rate of hospital beds. Independent variables in the multiple linear regression model on county hospital beds included the the population of aged 65 and above in the counties, disposable income of urban residents, medical personnel of medical institutions in county area, business occupancy, the total value of professional equipment, fixed assets, long-term debt, medical income, medical expenses, outpatient and emergency visits, hospital visits, actual available bed days, utilization rate of hospital beds, and length of hospitalization. The prediction model shows good explanatory and fitting, and may be used for short- and mid-term forecasting.

Developing a dengue forecast model using machine learning: A case study in China

PubMed Central

Zhang, Qin; Wang, Li; Xiao, Jianpeng; Zhang, Qingying; Luo, Ganfeng; Li, Zhihao; He, Jianfeng; Zhang, Yonghui; Ma, Wenjun

2017-01-01

Background In China, dengue remains an important public health issue with expanded areas and increased incidence recently. Accurate and timely forecasts of dengue incidence in China are still lacking. We aimed to use the state-of-the-art machine learning algorithms to develop an accurate predictive model of dengue. Methodology/Principal findings Weekly dengue cases, Baidu search queries and climate factors (mean temperature, relative humidity and rainfall) during 2011–2014 in Guangdong were gathered. A dengue search index was constructed for developing the predictive models in combination with climate factors. The observed year and week were also included in the models to control for the long-term trend and seasonality. Several machine learning algorithms, including the support vector regression (SVR) algorithm, step-down linear regression model, gradient boosted regression tree algorithm (GBM), negative binomial regression model (NBM), least absolute shrinkage and selection operator (LASSO) linear regression model and generalized additive model (GAM), were used as candidate models to predict dengue incidence. Performance and goodness of fit of the models were assessed using the root-mean-square error (RMSE) and R-squared measures. The residuals of the models were examined using the autocorrelation and partial autocorrelation function analyses to check the validity of the models. The models were further validated using dengue surveillance data from five other provinces. The epidemics during the last 12 weeks and the peak of the 2014 large outbreak were accurately forecasted by the SVR model selected by a cross-validation technique. Moreover, the SVR model had the consistently smallest prediction error rates for tracking the dynamics of dengue and forecasting the outbreaks in other areas in China. Conclusion and significance The proposed SVR model achieved a superior performance in comparison with other forecasting techniques assessed in this study. The findings can help the government and community respond early to dengue epidemics. PMID:29036169

Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days

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

Bramer, Lisa M.; Rounds, J.; Burleyson, C. D.

Understanding the conditions associated with stress on the electricity grid is important in the development of contingency plans for maintaining reliability during periods when the grid is stressed. In this paper, heat-related grid stress and the relationship with weather conditions were examined using data from the eastern United States. Penalized logistic regression models were developed and applied to predict stress on the electric grid using weather data. The inclusion of other weather variables, such as precipitation, in addition to temperature improved model performance. Several candidate models and combinations of predictive variables were examined. A penalized logistic regression model which wasmore » fit at the operation-zone level was found to provide predictive value and interpretability. Additionally, the importance of different weather variables observed at various time scales were examined. Maximum temperature and precipitation were identified as important across all zones while the importance of other weather variables was zone specific. In conclusion, the methods presented in this work are extensible to other regions and can be used to aid in planning and development of the electrical grid.« less

Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days

DOE PAGES

Bramer, Lisa M.; Rounds, J.; Burleyson, C. D.; ...

2017-09-22

Understanding the conditions associated with stress on the electricity grid is important in the development of contingency plans for maintaining reliability during periods when the grid is stressed. In this paper, heat-related grid stress and the relationship with weather conditions were examined using data from the eastern United States. Penalized logistic regression models were developed and applied to predict stress on the electric grid using weather data. The inclusion of other weather variables, such as precipitation, in addition to temperature improved model performance. Several candidate models and combinations of predictive variables were examined. A penalized logistic regression model which wasmore » fit at the operation-zone level was found to provide predictive value and interpretability. Additionally, the importance of different weather variables observed at various time scales were examined. Maximum temperature and precipitation were identified as important across all zones while the importance of other weather variables was zone specific. In conclusion, the methods presented in this work are extensible to other regions and can be used to aid in planning and development of the electrical grid.« less

Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach

NASA Astrophysics Data System (ADS)

Bagirov, Adil M.; Mahmood, Arshad; Barton, Andrew

2017-05-01

This paper develops the Clusterwise Linear Regression (CLR) technique for prediction of monthly rainfall. The CLR is a combination of clustering and regression techniques. It is formulated as an optimization problem and an incremental algorithm is designed to solve it. The algorithm is applied to predict monthly rainfall in Victoria, Australia using rainfall data with five input meteorological variables over the period of 1889-2014 from eight geographically diverse weather stations. The prediction performance of the CLR method is evaluated by comparing observed and predicted rainfall values using four measures of forecast accuracy. The proposed method is also compared with the CLR using the maximum likelihood framework by the expectation-maximization algorithm, multiple linear regression, artificial neural networks and the support vector machines for regression models using computational results. The results demonstrate that the proposed algorithm outperforms other methods in most locations.

Non-destructive and rapid prediction of moisture content in red pepper (Capsicum annuum L.) powder using near-infrared spectroscopy and a partial least squares regression model

USDA-ARS?s Scientific Manuscript database

Purpose: The aim of this study was to develop a technique for the non-destructive and rapid prediction of the moisture content in red pepper powder using near-infrared (NIR) spectroscopy and a partial least squares regression (PLSR) model. Methods: Three red pepper powder products were separated in...

Third molar development: measurements versus scores as age predictor.

PubMed

Thevissen, P W; Fieuws, S; Willems, G

2011-10-01

Human third molar development is widely used to predict chronological age of sub adult individuals with unknown or doubted age. For these predictions, classically, the radiologically observed third molar growth and maturation is registered using a staging and related scoring technique. Measures of lengths and widths of the developing wisdom tooth and its adjacent second molar can be considered as an alternative registration. The aim of this study was to verify relations between mandibular third molar developmental stages or measurements of mandibular second molar and third molars and age. Age related performance of stages and measurements were compared to assess if measurements added information to age predictions from third molar formation stage. The sample was 340 orthopantomograms (170 females, 170 males) of individuals homogenously distributed in age between 7 and 24 years. Mandibular lower right, third and second molars, were staged following Gleiser and Hunt, length and width measurements were registered, and various ratios of these measurements were calculated. Univariable regression models with age as response and third molar stage, measurements and ratios of second and third molars as predictors, were considered. Multivariable regression models assessed if measurements or ratios added information to age prediction from third molar stage. Coefficients of determination (R(2)) and root mean squared errors (RMSE) obtained from all regression models were compared. The univariable regression model using stages as predictor yielded most accurate age predictions (males: R(2) 0.85, RMSE between 0.85 and 1.22 year; females: R(2) 0.77, RMSE between 1.19 and 2.11 year) compared to all models including measurements and ratios. The multivariable regression models indicated that measurements and ratios added no clinical relevant information to the age prediction from third molar stage. Ratios and measurements of second and third molars are less accurate age predictors than stages of developing third molars. Copyright © 2011 Elsevier Ltd. All rights reserved.

Application of XGBoost algorithm in hourly PM2.5 concentration prediction

NASA Astrophysics Data System (ADS)

Pan, Bingyue

2018-02-01

In view of prediction techniques of hourly PM2.5 concentration in China, this paper applied the XGBoost(Extreme Gradient Boosting) algorithm to predict hourly PM2.5 concentration. The monitoring data of air quality in Tianjin city was analyzed by using XGBoost algorithm. The prediction performance of the XGBoost method is evaluated by comparing observed and predicted PM2.5 concentration using three measures of forecast accuracy. The XGBoost method is also compared with the random forest algorithm, multiple linear regression, decision tree regression and support vector machines for regression models using computational results. The results demonstrate that the XGBoost algorithm outperforms other data mining methods.

The extension of total gain (TG) statistic in survival models: properties and applications.

PubMed

Choodari-Oskooei, Babak; Royston, Patrick; Parmar, Mahesh K B

2015-07-01

The results of multivariable regression models are usually summarized in the form of parameter estimates for the covariates, goodness-of-fit statistics, and the relevant p-values. These statistics do not inform us about whether covariate information will lead to any substantial improvement in prediction. Predictive ability measures can be used for this purpose since they provide important information about the practical significance of prognostic factors. R (2)-type indices are the most familiar forms of such measures in survival models, but they all have limitations and none is widely used. In this paper, we extend the total gain (TG) measure, proposed for a logistic regression model, to survival models and explore its properties using simulations and real data. TG is based on the binary regression quantile plot, otherwise known as the predictiveness curve. Standardised TG ranges from 0 (no explanatory power) to 1 ('perfect' explanatory power). The results of our simulations show that unlike many of the other R (2)-type predictive ability measures, TG is independent of random censoring. It increases as the effect of a covariate increases and can be applied to different types of survival models, including models with time-dependent covariate effects. We also apply TG to quantify the predictive ability of multivariable prognostic models developed in several disease areas. Overall, TG performs well in our simulation studies and can be recommended as a measure to quantify the predictive ability in survival models.

Prediction of Patient-Controlled Analgesic Consumption: A Multimodel Regression Tree Approach.

PubMed

Hu, Yuh-Jyh; Ku, Tien-Hsiung; Yang, Yu-Hung; Shen, Jia-Ying

2018-01-01

Several factors contribute to individual variability in postoperative pain, therefore, individuals consume postoperative analgesics at different rates. Although many statistical studies have analyzed postoperative pain and analgesic consumption, most have identified only the correlation and have not subjected the statistical model to further tests in order to evaluate its predictive accuracy. In this study involving 3052 patients, a multistrategy computational approach was developed for analgesic consumption prediction. This approach uses data on patient-controlled analgesia demand behavior over time and combines clustering, classification, and regression to mitigate the limitations of current statistical models. Cross-validation results indicated that the proposed approach significantly outperforms various existing regression methods. Moreover, a comparison between the predictions by anesthesiologists and medical specialists and those of the computational approach for an independent test data set of 60 patients further evidenced the superiority of the computational approach in predicting analgesic consumption because it produced markedly lower root mean squared errors.

A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating

NASA Astrophysics Data System (ADS)

Zhan, Liwei; Li, Chengwei

2017-02-01

A hybrid PSO-SVM-based model is proposed to predict the friction coefficient between aircraft tire and coating. The presented hybrid model combines a support vector machine (SVM) with particle swarm optimization (PSO) technique. SVM has been adopted to solve regression problems successfully. Its regression accuracy is greatly related to optimizing parameters such as the regularization constant C , the parameter gamma γ corresponding to RBF kernel and the epsilon parameter \\varepsilon in the SVM training procedure. However, the friction coefficient which is predicted based on SVM has yet to be explored between aircraft tire and coating. The experiment reveals that drop height and tire rotational speed are the factors affecting friction coefficient. Bearing in mind, the friction coefficient can been predicted using the hybrid PSO-SVM-based model by the measured friction coefficient between aircraft tire and coating. To compare regression accuracy, a grid search (GS) method and a genetic algorithm (GA) are used to optimize the relevant parameters (C , γ and \\varepsilon ), respectively. The regression accuracy could be reflected by the coefficient of determination ({{R}2} ). The result shows that the hybrid PSO-RBF-SVM-based model has better accuracy compared with the GS-RBF-SVM- and GA-RBF-SVM-based models. The agreement of this model (PSO-RBF-SVM) with experiment data confirms its good performance.

[Logistic regression model of noninvasive prediction for portal hypertensive gastropathy in patients with hepatitis B associated cirrhosis].

PubMed

Wang, Qingliang; Li, Xiaojie; Hu, Kunpeng; Zhao, Kun; Yang, Peisheng; Liu, Bo

2015-05-12

To explore the risk factors of portal hypertensive gastropathy (PHG) in patients with hepatitis B associated cirrhosis and establish a Logistic regression model of noninvasive prediction. The clinical data of 234 hospitalized patients with hepatitis B associated cirrhosis from March 2012 to March 2014 were analyzed retrospectively. The dependent variable was the occurrence of PHG while the independent variables were screened by binary Logistic analysis. Multivariate Logistic regression was used for further analysis of significant noninvasive independent variables. Logistic regression model was established and odds ratio was calculated for each factor. The accuracy, sensitivity and specificity of model were evaluated by the curve of receiver operating characteristic (ROC). According to univariate Logistic regression, the risk factors included hepatic dysfunction, albumin (ALB), bilirubin (TB), prothrombin time (PT), platelet (PLT), white blood cell (WBC), portal vein diameter, spleen index, splenic vein diameter, diameter ratio, PLT to spleen volume ratio, esophageal varices (EV) and gastric varices (GV). Multivariate analysis showed that hepatic dysfunction (X1), TB (X2), PLT (X3) and splenic vein diameter (X4) were the major occurring factors for PHG. The established regression model was Logit P=-2.667+2.186X1-2.167X2+0.725X3+0.976X4. The accuracy of model for PHG was 79.1% with a sensitivity of 77.2% and a specificity of 80.8%. Hepatic dysfunction, TB, PLT and splenic vein diameter are risk factors for PHG and the noninvasive predicted Logistic regression model was Logit P=-2.667+2.186X1-2.167X2+0.725X3+0.976X4.

Use of genetic programming, logistic regression, and artificial neural nets to predict readmission after coronary artery bypass surgery.

PubMed

Engoren, Milo; Habib, Robert H; Dooner, John J; Schwann, Thomas A

2013-08-01

As many as 14 % of patients undergoing coronary artery bypass surgery are readmitted within 30 days. Readmission is usually the result of morbidity and may lead to death. The purpose of this study is to develop and compare statistical and genetic programming models to predict readmission. Patients were divided into separate Construction and Validation populations. Using 88 variables, logistic regression, genetic programs, and artificial neural nets were used to develop predictive models. Models were first constructed and tested on the Construction populations, then validated on the Validation population. Areas under the receiver operator characteristic curves (AU ROC) were used to compare the models. Two hundred and two patients (7.6 %) in the 2,644 patient Construction group and 216 (8.0 %) of the 2,711 patient Validation group were re-admitted within 30 days of CABG surgery. Logistic regression predicted readmission with AU ROC = .675 ± .021 in the Construction group. Genetic programs significantly improved the accuracy, AU ROC = .767 ± .001, p < .001). Artificial neural nets were less accurate with AU ROC = 0.597 ± .001 in the Construction group. Predictive accuracy of all three techniques fell in the Validation group. However, the accuracy of genetic programming (AU ROC = .654 ± .001) was still trivially but statistically non-significantly better than that of the logistic regression (AU ROC = .644 ± .020, p = .61). Genetic programming and logistic regression provide alternative methods to predict readmission that are similarly accurate.

FPGA implementation of predictive degradation model for engine oil lifetime

NASA Astrophysics Data System (ADS)

Idros, M. F. M.; Razak, A. H. A.; Junid, S. A. M. Al; Suliman, S. I.; Halim, A. K.

2018-03-01

This paper presents the implementation of linear regression model for degradation prediction on Register Transfer Logic (RTL) using QuartusII. A stationary model had been identified in the degradation trend for the engine oil in a vehicle in time series method. As for RTL implementation, the degradation model is written in Verilog HDL and the data input are taken at a certain time. Clock divider had been designed to support the timing sequence of input data. At every five data, a regression analysis is adapted for slope variation determination and prediction calculation. Here, only the negative value are taken as the consideration for the prediction purposes for less number of logic gate. Least Square Method is adapted to get the best linear model based on the mean values of time series data. The coded algorithm has been implemented on FPGA for validation purposes. The result shows the prediction time to change the engine oil.

Neuropsychological tests for predicting cognitive decline in older adults

PubMed Central

Baerresen, Kimberly M; Miller, Karen J; Hanson, Eric R; Miller, Justin S; Dye, Richelin V; Hartman, Richard E; Vermeersch, David; Small, Gary W

2015-01-01

Summary Aim To determine neuropsychological tests likely to predict cognitive decline. Methods A sample of nonconverters (n = 106) was compared with those who declined in cognitive status (n = 24). Significant univariate logistic regression prediction models were used to create multivariate logistic regression models to predict decline based on initial neuropsychological testing. Results Rey–Osterrieth Complex Figure Test (RCFT) Retention predicted conversion to mild cognitive impairment (MCI) while baseline Buschke Delay predicted conversion to Alzheimer’s disease (AD). Due to group sample size differences, additional analyses were conducted using a subsample of demographically matched nonconverters. Analyses indicated RCFT Retention predicted conversion to MCI and AD, and Buschke Delay predicted conversion to AD. Conclusion Results suggest RCFT Retention and Buschke Delay may be useful in predicting cognitive decline. PMID:26107318

Classification and regression tree analysis of acute-on-chronic hepatitis B liver failure: Seeing the forest for the trees.

PubMed

Shi, K-Q; Zhou, Y-Y; Yan, H-D; Li, H; Wu, F-L; Xie, Y-Y; Braddock, M; Lin, X-Y; Zheng, M-H

2017-02-01

At present, there is no ideal model for predicting the short-term outcome of patients with acute-on-chronic hepatitis B liver failure (ACHBLF). This study aimed to establish and validate a prognostic model by using the classification and regression tree (CART) analysis. A total of 1047 patients from two separate medical centres with suspected ACHBLF were screened in the study, which were recognized as derivation cohort and validation cohort, respectively. CART analysis was applied to predict the 3-month mortality of patients with ACHBLF. The accuracy of the CART model was tested using the area under the receiver operating characteristic curve, which was compared with the model for end-stage liver disease (MELD) score and a new logistic regression model. CART analysis identified four variables as prognostic factors of ACHBLF: total bilirubin, age, serum sodium and INR, and three distinct risk groups: low risk (4.2%), intermediate risk (30.2%-53.2%) and high risk (81.4%-96.9%). The new logistic regression model was constructed with four independent factors, including age, total bilirubin, serum sodium and prothrombin activity by multivariate logistic regression analysis. The performances of the CART model (0.896), similar to the logistic regression model (0.914, P=.382), exceeded that of MELD score (0.667, P<.001). The results were confirmed in the validation cohort. We have developed and validated a novel CART model superior to MELD for predicting three-month mortality of patients with ACHBLF. Thus, the CART model could facilitate medical decision-making and provide clinicians with a validated practical bedside tool for ACHBLF risk stratification. © 2016 John Wiley & Sons Ltd.

Using Logistic Regression to Predict the Probability of Debris Flows in Areas Burned by Wildfires, Southern California, 2003-2006

USGS Publications Warehouse

Rupert, Michael G.; Cannon, Susan H.; Gartner, Joseph E.; Michael, John A.; Helsel, Dennis R.

2008-01-01

Logistic regression was used to develop statistical models that can be used to predict the probability of debris flows in areas recently burned by wildfires by using data from 14 wildfires that burned in southern California during 2003-2006. Twenty-eight independent variables describing the basin morphology, burn severity, rainfall, and soil properties of 306 drainage basins located within those burned areas were evaluated. The models were developed as follows: (1) Basins that did and did not produce debris flows soon after the 2003 to 2006 fires were delineated from data in the National Elevation Dataset using a geographic information system; (2) Data describing the basin morphology, burn severity, rainfall, and soil properties were compiled for each basin. These data were then input to a statistics software package for analysis using logistic regression; and (3) Relations between the occurrence or absence of debris flows and the basin morphology, burn severity, rainfall, and soil properties were evaluated, and five multivariate logistic regression models were constructed. All possible combinations of independent variables were evaluated to determine which combinations produced the most effective models, and the multivariate models that best predicted the occurrence of debris flows were identified. Percentage of high burn severity and 3-hour peak rainfall intensity were significant variables in all models. Soil organic matter content and soil clay content were significant variables in all models except Model 5. Soil slope was a significant variable in all models except Model 4. The most suitable model can be selected from these five models on the basis of the availability of independent variables in the particular area of interest and field checking of probability maps. The multivariate logistic regression models can be entered into a geographic information system, and maps showing the probability of debris flows can be constructed in recently burned areas of southern California. This study demonstrates that logistic regression is a valuable tool for developing models that predict the probability of debris flows occurring in recently burned landscapes.

A Comparison between Multiple Regression Models and CUN-BAE Equation to Predict Body Fat in Adults

PubMed Central

Fuster-Parra, Pilar; Bennasar-Veny, Miquel; Tauler, Pedro; Yañez, Aina; López-González, Angel A.; Aguiló, Antoni

2015-01-01

Background Because the accurate measure of body fat (BF) is difficult, several prediction equations have been proposed. The aim of this study was to compare different multiple regression models to predict BF, including the recently reported CUN-BAE equation. Methods Multi regression models using body mass index (BMI) and body adiposity index (BAI) as predictors of BF will be compared. These models will be also compared with the CUN-BAE equation. For all the analysis a sample including all the participants and another one including only the overweight and obese subjects will be considered. The BF reference measure was made using Bioelectrical Impedance Analysis. Results The simplest models including only BMI or BAI as independent variables showed that BAI is a better predictor of BF. However, adding the variable sex to both models made BMI a better predictor than the BAI. For both the whole group of participants and the group of overweight and obese participants, using simple models (BMI, age and sex as variables) allowed obtaining similar correlations with BF as when the more complex CUN-BAE was used (ρ = 0:87 vs. ρ = 0:86 for the whole sample and ρ = 0:88 vs. ρ = 0:89 for overweight and obese subjects, being the second value the one for CUN-BAE). Conclusions There are simpler models than CUN-BAE equation that fits BF as well as CUN-BAE does. Therefore, it could be considered that CUN-BAE overfits. Using a simple linear regression model, the BAI, as the only variable, predicts BF better than BMI. However, when the sex variable is introduced, BMI becomes the indicator of choice to predict BF. PMID:25821960

A comparison between multiple regression models and CUN-BAE equation to predict body fat in adults.

PubMed

Fuster-Parra, Pilar; Bennasar-Veny, Miquel; Tauler, Pedro; Yañez, Aina; López-González, Angel A; Aguiló, Antoni

2015-01-01

Because the accurate measure of body fat (BF) is difficult, several prediction equations have been proposed. The aim of this study was to compare different multiple regression models to predict BF, including the recently reported CUN-BAE equation. Multi regression models using body mass index (BMI) and body adiposity index (BAI) as predictors of BF will be compared. These models will be also compared with the CUN-BAE equation. For all the analysis a sample including all the participants and another one including only the overweight and obese subjects will be considered. The BF reference measure was made using Bioelectrical Impedance Analysis. The simplest models including only BMI or BAI as independent variables showed that BAI is a better predictor of BF. However, adding the variable sex to both models made BMI a better predictor than the BAI. For both the whole group of participants and the group of overweight and obese participants, using simple models (BMI, age and sex as variables) allowed obtaining similar correlations with BF as when the more complex CUN-BAE was used (ρ = 0:87 vs. ρ = 0:86 for the whole sample and ρ = 0:88 vs. ρ = 0:89 for overweight and obese subjects, being the second value the one for CUN-BAE). There are simpler models than CUN-BAE equation that fits BF as well as CUN-BAE does. Therefore, it could be considered that CUN-BAE overfits. Using a simple linear regression model, the BAI, as the only variable, predicts BF better than BMI. However, when the sex variable is introduced, BMI becomes the indicator of choice to predict BF.

Estimating suspended sediment load with multivariate adaptive regression spline, teaching-learning based optimization, and artificial bee colony models.

PubMed

Yilmaz, Banu; Aras, Egemen; Nacar, Sinan; Kankal, Murat

2018-05-23

The functional life of a dam is often determined by the rate of sediment delivery to its reservoir. Therefore, an accurate estimate of the sediment load in rivers with dams is essential for designing and predicting a dam's useful lifespan. The most credible method is direct measurements of sediment input, but this can be very costly and it cannot always be implemented at all gauging stations. In this study, we tested various regression models to estimate suspended sediment load (SSL) at two gauging stations on the Çoruh River in Turkey, including artificial bee colony (ABC), teaching-learning-based optimization algorithm (TLBO), and multivariate adaptive regression splines (MARS). These models were also compared with one another and with classical regression analyses (CRA). Streamflow values and previously collected data of SSL were used as model inputs with predicted SSL data as output. Two different training and testing dataset configurations were used to reinforce the model accuracy. For the MARS method, the root mean square error value was found to range between 35% and 39% for the test two gauging stations, which was lower than errors for other models. Error values were even lower (7% to 15%) using another dataset. Our results indicate that simultaneous measurements of streamflow with SSL provide the most effective parameter for obtaining accurate predictive models and that MARS is the most accurate model for predicting SSL. Copyright © 2017 Elsevier B.V. All rights reserved.

Genetic prediction of type 2 diabetes using deep neural network.

PubMed

Kim, J; Kim, J; Kwak, M J; Bajaj, M

2018-04-01

Type 2 diabetes (T2DM) has strong heritability but genetic models to explain heritability have been challenging. We tested deep neural network (DNN) to predict T2DM using the nested case-control study of Nurses' Health Study (3326 females, 45.6% T2DM) and Health Professionals Follow-up Study (2502 males, 46.5% T2DM). We selected 96, 214, 399, and 678 single-nucleotide polymorphism (SNPs) through Fisher's exact test and L1-penalized logistic regression. We split each dataset randomly in 4:1 to train prediction models and test their performance. DNN and logistic regressions showed better area under the curve (AUC) of ROC curves than the clinical model when 399 or more SNPs included. DNN was superior than logistic regressions in AUC with 399 or more SNPs in male and 678 SNPs in female. Addition of clinical factors consistently increased AUC of DNN but failed to improve logistic regressions with 214 or more SNPs. In conclusion, we show that DNN can be a versatile tool to predict T2DM incorporating large numbers of SNPs and clinical information. Limitations include a relatively small number of the subjects mostly of European ethnicity. Further studies are warranted to confirm and improve performance of genetic prediction models using DNN in different ethnic groups. © 2017 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Assessment of wastewater treatment facility compliance with decreasing ammonia discharge limits using a regression tree model.

PubMed

Suchetana, Bihu; Rajagopalan, Balaji; Silverstein, JoAnn

2017-11-15

A regression tree-based diagnostic approach is developed to evaluate factors affecting US wastewater treatment plant compliance with ammonia discharge permit limits using Discharge Monthly Report (DMR) data from a sample of 106 municipal treatment plants for the period of 2004-2008. Predictor variables used to fit the regression tree are selected using random forests, and consist of the previous month's effluent ammonia, influent flow rates and plant capacity utilization. The tree models are first used to evaluate compliance with existing ammonia discharge standards at each facility and then applied assuming more stringent discharge limits, under consideration in many states. The model predicts that the ability to meet both current and future limits depends primarily on the previous month's treatment performance. With more stringent discharge limits predicted ammonia concentration relative to the discharge limit, increases. In-sample validation shows that the regression trees can provide a median classification accuracy of >70%. The regression tree model is validated using ammonia discharge data from an operating wastewater treatment plant and is able to accurately predict the observed ammonia discharge category approximately 80% of the time, indicating that the regression tree model can be applied to predict compliance for individual treatment plants providing practical guidance for utilities and regulators with an interest in controlling ammonia discharges. The proposed methodology is also used to demonstrate how to delineate reliable sources of demand and supply in a point source-to-point source nutrient credit trading scheme, as well as how planners and decision makers can set reasonable discharge limits in future. Copyright © 2017 Elsevier B.V. All rights reserved.

Forecasting peak asthma admissions in London: an application of quantile regression models.

PubMed

Soyiri, Ireneous N; Reidpath, Daniel D; Sarran, Christophe

2013-07-01

Asthma is a chronic condition of great public health concern globally. The associated morbidity, mortality and healthcare utilisation place an enormous burden on healthcare infrastructure and services. This study demonstrates a multistage quantile regression approach to predicting excess demand for health care services in the form of asthma daily admissions in London, using retrospective data from the Hospital Episode Statistics, weather and air quality. Trivariate quantile regression models (QRM) of asthma daily admissions were fitted to a 14-day range of lags of environmental factors, accounting for seasonality in a hold-in sample of the data. Representative lags were pooled to form multivariate predictive models, selected through a systematic backward stepwise reduction approach. Models were cross-validated using a hold-out sample of the data, and their respective root mean square error measures, sensitivity, specificity and predictive values compared. Two of the predictive models were able to detect extreme number of daily asthma admissions at sensitivity levels of 76 % and 62 %, as well as specificities of 66 % and 76 %. Their positive predictive values were slightly higher for the hold-out sample (29 % and 28 %) than for the hold-in model development sample (16 % and 18 %). QRMs can be used in multistage to select suitable variables to forecast extreme asthma events. The associations between asthma and environmental factors, including temperature, ozone and carbon monoxide can be exploited in predicting future events using QRMs.

Forecasting peak asthma admissions in London: an application of quantile regression models

NASA Astrophysics Data System (ADS)

Soyiri, Ireneous N.; Reidpath, Daniel D.; Sarran, Christophe

2013-07-01

Asthma is a chronic condition of great public health concern globally. The associated morbidity, mortality and healthcare utilisation place an enormous burden on healthcare infrastructure and services. This study demonstrates a multistage quantile regression approach to predicting excess demand for health care services in the form of asthma daily admissions in London, using retrospective data from the Hospital Episode Statistics, weather and air quality. Trivariate quantile regression models (QRM) of asthma daily admissions were fitted to a 14-day range of lags of environmental factors, accounting for seasonality in a hold-in sample of the data. Representative lags were pooled to form multivariate predictive models, selected through a systematic backward stepwise reduction approach. Models were cross-validated using a hold-out sample of the data, and their respective root mean square error measures, sensitivity, specificity and predictive values compared. Two of the predictive models were able to detect extreme number of daily asthma admissions at sensitivity levels of 76 % and 62 %, as well as specificities of 66 % and 76 %. Their positive predictive values were slightly higher for the hold-out sample (29 % and 28 %) than for the hold-in model development sample (16 % and 18 %). QRMs can be used in multistage to select suitable variables to forecast extreme asthma events. The associations between asthma and environmental factors, including temperature, ozone and carbon monoxide can be exploited in predicting future events using QRMs.

Hyperspectral Imaging for Predicting the Internal Quality of Kiwifruits Based on Variable Selection Algorithms and Chemometric Models.

PubMed

Zhu, Hongyan; Chu, Bingquan; Fan, Yangyang; Tao, Xiaoya; Yin, Wenxin; He, Yong

2017-08-10

We investigated the feasibility and potentiality of determining firmness, soluble solids content (SSC), and pH in kiwifruits using hyperspectral imaging, combined with variable selection methods and calibration models. The images were acquired by a push-broom hyperspectral reflectance imaging system covering two spectral ranges. Weighted regression coefficients (BW), successive projections algorithm (SPA) and genetic algorithm-partial least square (GAPLS) were compared and evaluated for the selection of effective wavelengths. Moreover, multiple linear regression (MLR), partial least squares regression and least squares support vector machine (LS-SVM) were developed to predict quality attributes quantitatively using effective wavelengths. The established models, particularly SPA-MLR, SPA-LS-SVM and GAPLS-LS-SVM, performed well. The SPA-MLR models for firmness (R pre  = 0.9812, RPD = 5.17) and SSC (R pre  = 0.9523, RPD = 3.26) at 380-1023 nm showed excellent performance, whereas GAPLS-LS-SVM was the optimal model at 874-1734 nm for predicting pH (R pre  = 0.9070, RPD = 2.60). Image processing algorithms were developed to transfer the predictive model in every pixel to generate prediction maps that visualize the spatial distribution of firmness and SSC. Hence, the results clearly demonstrated that hyperspectral imaging has the potential as a fast and non-invasive method to predict the quality attributes of kiwifruits.

Analysis of Multivariate Experimental Data Using A Simplified Regression Model Search Algorithm

NASA Technical Reports Server (NTRS)

Ulbrich, Norbert M.

2013-01-01

A new regression model search algorithm was developed that may be applied to both general multivariate experimental data sets and wind tunnel strain-gage balance calibration data. The algorithm is a simplified version of a more complex algorithm that was originally developed for the NASA Ames Balance Calibration Laboratory. The new algorithm performs regression model term reduction to prevent overfitting of data. It has the advantage that it needs only about one tenth of the original algorithm's CPU time for the completion of a regression model search. In addition, extensive testing showed that the prediction accuracy of math models obtained from the simplified algorithm is similar to the prediction accuracy of math models obtained from the original algorithm. The simplified algorithm, however, cannot guarantee that search constraints related to a set of statistical quality requirements are always satisfied in the optimized regression model. Therefore, the simplified algorithm is not intended to replace the original algorithm. Instead, it may be used to generate an alternate optimized regression model of experimental data whenever the application of the original search algorithm fails or requires too much CPU time. Data from a machine calibration of NASA's MK40 force balance is used to illustrate the application of the new search algorithm.

Habitat features and predictive habitat modeling for the Colorado chipmunk in southern New Mexico

USGS Publications Warehouse

Rivieccio, M.; Thompson, B.C.; Gould, W.R.; Boykin, K.G.

2003-01-01

Two subspecies of Colorado chipmunk (state threatened and federal species of concern) occur in southern New Mexico: Tamias quadrivittatus australis in the Organ Mountains and T. q. oscuraensis in the Oscura Mountains. We developed a GIS model of potentially suitable habitat based on vegetation and elevation features, evaluated site classifications of the GIS model, and determined vegetation and terrain features associated with chipmunk occurrence. We compared GIS model classifications with actual vegetation and elevation features measured at 37 sites. At 60 sites we measured 18 habitat variables regarding slope, aspect, tree species, shrub species, and ground cover. We used logistic regression to analyze habitat variables associated with chipmunk presence/absence. All (100%) 37 sample sites (28 predicted suitable, 9 predicted unsuitable) were classified correctly by the GIS model regarding elevation and vegetation. For 28 sites predicted suitable by the GIS model, 18 sites (64%) appeared visually suitable based on habitat variables selected from logistic regression analyses, of which 10 sites (36%) were specifically predicted as suitable habitat via logistic regression. We detected chipmunks at 70% of sites deemed suitable via the logistic regression models. Shrub cover, tree density, plant proximity, presence of logs, and presence of rock outcrop were retained in the logistic model for the Oscura Mountains; litter, shrub cover, and grass cover were retained in the logistic model for the Organ Mountains. Evaluation of predictive models illustrates the need for multi-stage analyses to best judge performance. Microhabitat analyses indicate prospective needs for different management strategies between the subspecies. Sensitivities of each population of the Colorado chipmunk to natural and prescribed fire suggest that partial burnings of areas inhabited by Colorado chipmunks in southern New Mexico may be beneficial. These partial burnings may later help avoid a fire that could substantially reduce habitat of chipmunks over a mountain range.

Predicting lettuce canopy photosynthesis with statistical and neural network models

NASA Technical Reports Server (NTRS)

Frick, J.; Precetti, C.; Mitchell, C. A.

1998-01-01

An artificial neural network (NN) and a statistical regression model were developed to predict canopy photosynthetic rates (Pn) for 'Waldman's Green' leaf lettuce (Latuca sativa L.). All data used to develop and test the models were collected for crop stands grown hydroponically and under controlled-environment conditions. In the NN and regression models, canopy Pn was predicted as a function of three independent variables: shootzone CO2 concentration (600 to 1500 micromoles mol-1), photosynthetic photon flux (PPF) (600 to 1100 micromoles m-2 s-1), and canopy age (10 to 20 days after planting). The models were used to determine the combinations of CO2 and PPF setpoints required each day to maintain maximum canopy Pn. The statistical model (a third-order polynomial) predicted Pn more accurately than the simple NN (a three-layer, fully connected net). Over an 11-day validation period, average percent difference between predicted and actual Pn was 12.3% and 24.6% for the statistical and NN models, respectively. Both models lost considerable accuracy when used to determine relatively long-range Pn predictions (> or = 6 days into the future).

A Comparative Study of Classification and Regression Algorithms for Modelling Students' Academic Performance

ERIC Educational Resources Information Center

Strecht, Pedro; Cruz, Luís; Soares, Carlos; Mendes-Moreira, João; Abreu, Rui

2015-01-01

Predicting the success or failure of a student in a course or program is a problem that has recently been addressed using data mining techniques. In this paper we evaluate some of the most popular classification and regression algorithms on this problem. We address two problems: prediction of approval/failure and prediction of grade. The former is…

Can air temperature be used to project influences of climate change on stream temperature?

USGS Publications Warehouse

Arismendi, Ivan; Safeeq, Mohammad; Dunham, Jason B.; Johnson, Sherri L.

2014-01-01

Worldwide, lack of data on stream temperature has motivated the use of regression-based statistical models to predict stream temperatures based on more widely available data on air temperatures. Such models have been widely applied to project responses of stream temperatures under climate change, but the performance of these models has not been fully evaluated. To address this knowledge gap, we examined the performance of two widely used linear and nonlinear regression models that predict stream temperatures based on air temperatures. We evaluated model performance and temporal stability of model parameters in a suite of regulated and unregulated streams with 11–44 years of stream temperature data. Although such models may have validity when predicting stream temperatures within the span of time that corresponds to the data used to develop them, model predictions did not transfer well to other time periods. Validation of model predictions of most recent stream temperatures, based on air temperature–stream temperature relationships from previous time periods often showed poor performance when compared with observed stream temperatures. Overall, model predictions were less robust in regulated streams and they frequently failed in detecting the coldest and warmest temperatures within all sites. In many cases, the magnitude of errors in these predictions falls within a range that equals or exceeds the magnitude of future projections of climate-related changes in stream temperatures reported for the region we studied (between 0.5 and 3.0 °C by 2080). The limited ability of regression-based statistical models to accurately project stream temperatures over time likely stems from the fact that underlying processes at play, namely the heat budgets of air and water, are distinctive in each medium and vary among localities and through time.

Using Time Series Analysis to Predict Cardiac Arrest in a PICU.

PubMed

Kennedy, Curtis E; Aoki, Noriaki; Mariscalco, Michele; Turley, James P

2015-11-01

To build and test cardiac arrest prediction models in a PICU, using time series analysis as input, and to measure changes in prediction accuracy attributable to different classes of time series data. Retrospective cohort study. Thirty-one bed academic PICU that provides care for medical and general surgical (not congenital heart surgery) patients. Patients experiencing a cardiac arrest in the PICU and requiring external cardiac massage for at least 2 minutes. None. One hundred three cases of cardiac arrest and 109 control cases were used to prepare a baseline dataset that consisted of 1,025 variables in four data classes: multivariate, raw time series, clinical calculations, and time series trend analysis. We trained 20 arrest prediction models using a matrix of five feature sets (combinations of data classes) with four modeling algorithms: linear regression, decision tree, neural network, and support vector machine. The reference model (multivariate data with regression algorithm) had an accuracy of 78% and 87% area under the receiver operating characteristic curve. The best model (multivariate + trend analysis data with support vector machine algorithm) had an accuracy of 94% and 98% area under the receiver operating characteristic curve. Cardiac arrest predictions based on a traditional model built with multivariate data and a regression algorithm misclassified cases 3.7 times more frequently than predictions that included time series trend analysis and built with a support vector machine algorithm. Although the final model lacks the specificity necessary for clinical application, we have demonstrated how information from time series data can be used to increase the accuracy of clinical prediction models.

Sentinel node status prediction by four statistical models: results from a large bi-institutional series (n = 1132).

PubMed

Mocellin, Simone; Thompson, John F; Pasquali, Sandro; Montesco, Maria C; Pilati, Pierluigi; Nitti, Donato; Saw, Robyn P; Scolyer, Richard A; Stretch, Jonathan R; Rossi, Carlo R

2009-12-01

To improve selection for sentinel node (SN) biopsy (SNB) in patients with cutaneous melanoma using statistical models predicting SN status. About 80% of patients currently undergoing SNB are node negative. In the absence of conclusive evidence of a SNBassociated survival benefit, these patients may be over-treated. Here, we tested the efficiency of 4 different models in predicting SN status. The clinicopathologic data (age, gender, tumor thickness, Clark level, regression, ulceration, histologic subtype, and mitotic index) of 1132 melanoma patients who had undergone SNB at institutions in Italy and Australia were analyzed. Logistic regression, classification tree, random forest, and support vector machine models were fitted to the data. The predictive models were built with the aim of maximizing the negative predictive value (NPV) and reducing the rate of SNB procedures though minimizing the error rate. After cross-validation logistic regression, classification tree, random forest, and support vector machine predictive models obtained clinically relevant NPV (93.6%, 94.0%, 97.1%, and 93.0%, respectively), SNB reduction (27.5%, 29.8%, 18.2%, and 30.1%, respectively), and error rates (1.8%, 1.8%, 0.5%, and 2.1%, respectively). Using commonly available clinicopathologic variables, predictive models can preoperatively identify a proportion of patients ( approximately 25%) who might be spared SNB, with an acceptable (1%-2%) error. If validated in large prospective series, these models might be implemented in the clinical setting for improved patient selection, which ultimately would lead to better quality of life for patients and optimization of resource allocation for the health care system.

Multivariate Regression Analysis and Slaughter Livestock,

DTIC Science & Technology

AGRICULTURE, *ECONOMICS), (*MEAT, PRODUCTION), MULTIVARIATE ANALYSIS, REGRESSION ANALYSIS , ANIMALS, WEIGHT, COSTS, PREDICTIONS, STABILITY, MATHEMATICAL MODELS, STORAGE, BEEF, PORK, FOOD, STATISTICAL DATA, ACCURACY

Prediction of Emergency Department Hospital Admission Based on Natural Language Processing and Neural Networks.

PubMed

Zhang, Xingyu; Kim, Joyce; Patzer, Rachel E; Pitts, Stephen R; Patzer, Aaron; Schrager, Justin D

2017-10-26

To describe and compare logistic regression and neural network modeling strategies to predict hospital admission or transfer following initial presentation to Emergency Department (ED) triage with and without the addition of natural language processing elements. Using data from the National Hospital Ambulatory Medical Care Survey (NHAMCS), a cross-sectional probability sample of United States EDs from 2012 and 2013 survey years, we developed several predictive models with the outcome being admission to the hospital or transfer vs. discharge home. We included patient characteristics immediately available after the patient has presented to the ED and undergone a triage process. We used this information to construct logistic regression (LR) and multilayer neural network models (MLNN) which included natural language processing (NLP) and principal component analysis from the patient's reason for visit. Ten-fold cross validation was used to test the predictive capacity of each model and receiver operating curves (AUC) were then calculated for each model. Of the 47,200 ED visits from 642 hospitals, 6,335 (13.42%) resulted in hospital admission (or transfer). A total of 48 principal components were extracted by NLP from the reason for visit fields, which explained 75% of the overall variance for hospitalization. In the model including only structured variables, the AUC was 0.824 (95% CI 0.818-0.830) for logistic regression and 0.823 (95% CI 0.817-0.829) for MLNN. Models including only free-text information generated AUC of 0.742 (95% CI 0.731- 0.753) for logistic regression and 0.753 (95% CI 0.742-0.764) for MLNN. When both structured variables and free text variables were included, the AUC reached 0.846 (95% CI 0.839-0.853) for logistic regression and 0.844 (95% CI 0.836-0.852) for MLNN. The predictive accuracy of hospital admission or transfer for patients who presented to ED triage overall was good, and was improved with the inclusion of free text data from a patient's reason for visit regardless of modeling approach. Natural language processing and neural networks that incorporate patient-reported outcome free text may increase predictive accuracy for hospital admission.

Predicting flight delay based on multiple linear regression

NASA Astrophysics Data System (ADS)

Ding, Yi

2017-08-01

Delay of flight has been regarded as one of the toughest difficulties in aviation control. How to establish an effective model to handle the delay prediction problem is a significant work. To solve the problem that the flight delay is difficult to predict, this study proposes a method to model the arriving flights and a multiple linear regression algorithm to predict delay, comparing with Naive-Bayes and C4.5 approach. Experiments based on a realistic dataset of domestic airports show that the accuracy of the proposed model approximates 80%, which is further improved than the Naive-Bayes and C4.5 approach approaches. The result testing shows that this method is convenient for calculation, and also can predict the flight delays effectively. It can provide decision basis for airport authorities.

Predicting chemical bioavailability using microarray gene expression data and regression modeling: A tale of three explosive compounds.

PubMed

Gong, Ping; Nan, Xiaofei; Barker, Natalie D; Boyd, Robert E; Chen, Yixin; Wilkins, Dawn E; Johnson, David R; Suedel, Burton C; Perkins, Edward J

2016-03-08

Chemical bioavailability is an important dose metric in environmental risk assessment. Although many approaches have been used to evaluate bioavailability, not a single approach is free from limitations. Previously, we developed a new genomics-based approach that integrated microarray technology and regression modeling for predicting bioavailability (tissue residue) of explosives compounds in exposed earthworms. In the present study, we further compared 18 different regression models and performed variable selection simultaneously with parameter estimation. This refined approach was applied to both previously collected and newly acquired earthworm microarray gene expression datasets for three explosive compounds. Our results demonstrate that a prediction accuracy of R(2) = 0.71-0.82 was achievable at a relatively low model complexity with as few as 3-10 predictor genes per model. These results are much more encouraging than our previous ones. This study has demonstrated that our approach is promising for bioavailability measurement, which warrants further studies of mixed contamination scenarios in field settings.

Applicability of linear regression equation for prediction of chlorophyll content in rice leaves

NASA Astrophysics Data System (ADS)

Li, Yunmei

2005-09-01

A modeling approach is used to assess the applicability of the derived equations which are capable to predict chlorophyll content of rice leaves at a given view direction. Two radiative transfer models, including PROSPECT model operated at leaf level and FCR model operated at canopy level, are used in the study. The study is consisted of three steps: (1) Simulation of bidirectional reflectance from canopy with different leaf chlorophyll contents, leaf-area-index (LAI) and under storey configurations; (2) Establishment of prediction relations of chlorophyll content by stepwise regression; and (3) Assessment of the applicability of these relations. The result shows that the accuracy of prediction is affected by different under storey configurations and, however, the accuracy tends to be greatly improved with increase of LAI.

Pragmatic estimation of a spatio-temporal air quality model with irregular monitoring data

NASA Astrophysics Data System (ADS)

Sampson, Paul D.; Szpiro, Adam A.; Sheppard, Lianne; Lindström, Johan; Kaufman, Joel D.

2011-11-01

Statistical analyses of health effects of air pollution have increasingly used GIS-based covariates for prediction of ambient air quality in "land use" regression models. More recently these spatial regression models have accounted for spatial correlation structure in combining monitoring data with land use covariates. We present a flexible spatio-temporal modeling framework and pragmatic, multi-step estimation procedure that accommodates essentially arbitrary patterns of missing data with respect to an ideally complete space by time matrix of observations on a network of monitoring sites. The methodology incorporates a model for smooth temporal trends with coefficients varying in space according to Partial Least Squares regressions on a large set of geographic covariates and nonstationary modeling of spatio-temporal residuals from these regressions. This work was developed to provide spatial point predictions of PM 2.5 concentrations for the Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air) using irregular monitoring data derived from the AQS regulatory monitoring network and supplemental short-time scale monitoring campaigns conducted to better predict intra-urban variation in air quality. We demonstrate the interpretation and accuracy of this methodology in modeling data from 2000 through 2006 in six U.S. metropolitan areas and establish a basis for likelihood-based estimation.

Fire frequency in the Interior Columbia River Basin: Building regional models from fire history data

USGS Publications Warehouse

McKenzie, D.; Peterson, D.L.; Agee, James K.

2000-01-01

Fire frequency affects vegetation composition and successional pathways; thus it is essential to understand fire regimes in order to manage natural resources at broad spatial scales. Fire history data are lacking for many regions for which fire management decisions are being made, so models are needed to estimate past fire frequency where local data are not yet available. We developed multiple regression models and tree-based (classification and regression tree, or CART) models to predict fire return intervals across the interior Columbia River basin at 1-km resolution, using georeferenced fire history, potential vegetation, cover type, and precipitation databases. The models combined semiqualitative methods and rigorous statistics. The fire history data are of uneven quality; some estimates are based on only one tree, and many are not cross-dated. Therefore, we weighted the models based on data quality and performed a sensitivity analysis of the effects on the models of estimation errors that are due to lack of cross-dating. The regression models predict fire return intervals from 1 to 375 yr for forested areas, whereas the tree-based models predict a range of 8 to 150 yr. Both types of models predict latitudinal and elevational gradients of increasing fire return intervals. Examination of regional-scale output suggests that, although the tree-based models explain more of the variation in the original data, the regression models are less likely to produce extrapolation errors. Thus, the models serve complementary purposes in elucidating the relationships among fire frequency, the predictor variables, and spatial scale. The models can provide local managers with quantitative information and provide data to initialize coarse-scale fire-effects models, although predictions for individual sites should be treated with caution because of the varying quality and uneven spatial coverage of the fire history database. The models also demonstrate the integration of qualitative and quantitative methods when requisite data for fully quantitative models are unavailable. They can be tested by comparing new, independent fire history reconstructions against their predictions and can be continually updated, as better fire history data become available.

An Excel Solver Exercise to Introduce Nonlinear Regression

ERIC Educational Resources Information Center

Pinder, Jonathan P.

2013-01-01

Business students taking business analytics courses that have significant predictive modeling components, such as marketing research, data mining, forecasting, and advanced financial modeling, are introduced to nonlinear regression using application software that is a "black box" to the students. Thus, although correct models are…

Gaussian functional regression for output prediction: Model assimilation and experimental design

NASA Astrophysics Data System (ADS)

Nguyen, N. C.; Peraire, J.

2016-03-01

In this paper, we introduce a Gaussian functional regression (GFR) technique that integrates multi-fidelity models with model reduction to efficiently predict the input-output relationship of a high-fidelity model. The GFR method combines the high-fidelity model with a low-fidelity model to provide an estimate of the output of the high-fidelity model in the form of a posterior distribution that can characterize uncertainty in the prediction. A reduced basis approximation is constructed upon the low-fidelity model and incorporated into the GFR method to yield an inexpensive posterior distribution of the output estimate. As this posterior distribution depends crucially on a set of training inputs at which the high-fidelity models are simulated, we develop a greedy sampling algorithm to select the training inputs. Our approach results in an output prediction model that inherits the fidelity of the high-fidelity model and has the computational complexity of the reduced basis approximation. Numerical results are presented to demonstrate the proposed approach.

Modeling the prediction of business intelligence system effectiveness.

PubMed

Weng, Sung-Shun; Yang, Ming-Hsien; Koo, Tian-Lih; Hsiao, Pei-I

2016-01-01

Although business intelligence (BI) technologies are continually evolving, the capability to apply BI technologies has become an indispensable resource for enterprises running in today's complex, uncertain and dynamic business environment. This study performed pioneering work by constructing models and rules for the prediction of business intelligence system effectiveness (BISE) in relation to the implementation of BI solutions. For enterprises, effectively managing critical attributes that determine BISE to develop prediction models with a set of rules for self-evaluation of the effectiveness of BI solutions is necessary to improve BI implementation and ensure its success. The main study findings identified the critical prediction indicators of BISE that are important to forecasting BI performance and highlighted five classification and prediction rules of BISE derived from decision tree structures, as well as a refined regression prediction model with four critical prediction indicators constructed by logistic regression analysis that can enable enterprises to improve BISE while effectively managing BI solution implementation and catering to academics to whom theory is important.

Mobile Phone-Based Unobtrusive Ecological Momentary Assessment of Day-to-Day Mood: An Explorative Study.

PubMed

Asselbergs, Joost; Ruwaard, Jeroen; Ejdys, Michal; Schrader, Niels; Sijbrandij, Marit; Riper, Heleen

2016-03-29

Ecological momentary assessment (EMA) is a useful method to tap the dynamics of psychological and behavioral phenomena in real-world contexts. However, the response burden of (self-report) EMA limits its clinical utility. The aim was to explore mobile phone-based unobtrusive EMA, in which mobile phone usage logs are considered as proxy measures of clinically relevant user states and contexts. This was an uncontrolled explorative pilot study. Our study consisted of 6 weeks of EMA/unobtrusive EMA data collection in a Dutch student population (N=33), followed by a regression modeling analysis. Participants self-monitored their mood on their mobile phone (EMA) with a one-dimensional mood measure (1 to 10) and a two-dimensional circumplex measure (arousal/valence, -2 to 2). Meanwhile, with participants' consent, a mobile phone app unobtrusively collected (meta) data from six smartphone sensor logs (unobtrusive EMA: calls/short message service (SMS) text messages, screen time, application usage, accelerometer, and phone camera events). Through forward stepwise regression (FSR), we built personalized regression models from the unobtrusive EMA variables to predict day-to-day variation in EMA mood ratings. The predictive performance of these models (ie, cross-validated mean squared error and percentage of correct predictions) was compared to naive benchmark regression models (the mean model and a lag-2 history model). A total of 27 participants (81%) provided a mean 35.5 days (SD 3.8) of valid EMA/unobtrusive EMA data. The FSR models accurately predicted 55% to 76% of EMA mood scores. However, the predictive performance of these models was significantly inferior to that of naive benchmark models. Mobile phone-based unobtrusive EMA is a technically feasible and potentially powerful EMA variant. The method is young and positive findings may not replicate. At present, we do not recommend the application of FSR-based mood prediction in real-world clinical settings. Further psychometric studies and more advanced data mining techniques are needed to unlock unobtrusive EMA's true potential.

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.

Variable Selection for Regression Models of Percentile Flows

NASA Astrophysics Data System (ADS)

Fouad, G.

2017-12-01

Percentile flows describe the flow magnitude equaled or exceeded for a given percent of time, and are widely used in water resource management. However, these statistics are normally unavailable since most basins are ungauged. Percentile flows of ungauged basins are often predicted using regression models based on readily observable basin characteristics, such as mean elevation. The number of these independent variables is too large to evaluate all possible models. A subset of models is typically evaluated using automatic procedures, like stepwise regression. This ignores a large variety of methods from the field of feature (variable) selection and physical understanding of percentile flows. A study of 918 basins in the United States was conducted to compare an automatic regression procedure to the following variable selection methods: (1) principal component analysis, (2) correlation analysis, (3) random forests, (4) genetic programming, (5) Bayesian networks, and (6) physical understanding. The automatic regression procedure only performed better than principal component analysis. Poor performance of the regression procedure was due to a commonly used filter for multicollinearity, which rejected the strongest models because they had cross-correlated independent variables. Multicollinearity did not decrease model performance in validation because of a representative set of calibration basins. Variable selection methods based strictly on predictive power (numbers 2-5 from above) performed similarly, likely indicating a limit to the predictive power of the variables. Similar performance was also reached using variables selected based on physical understanding, a finding that substantiates recent calls to emphasize physical understanding in modeling for predictions in ungauged basins. The strongest variables highlighted the importance of geology and land cover, whereas widely used topographic variables were the weakest predictors. Variables suffered from a high degree of multicollinearity, possibly illustrating the co-evolution of climatic and physiographic conditions. Given the ineffectiveness of many variables used here, future work should develop new variables that target specific processes associated with percentile flows.

Calibration of remotely sensed, coarse resolution NDVI to CO2 fluxes in a sagebrush–steppe ecosystem

USGS Publications Warehouse

Wylie, Bruce K.; Johnson, Douglas A.; Laca, Emilio; Saliendra, Nicanor Z.; Gilmanov, Tagir G.; Reed, Bradley C.; Tieszen, Larry L.; Worstell, Bruce B.

2003-01-01

The net ecosystem exchange (NEE) of carbon flux can be partitioned into gross primary productivity (GPP) and respiration (R). The contribution of remote sensing and modeling holds the potential to predict these components and map them spatially and temporally. This has obvious utility to quantify carbon sink and source relationships and to identify improved land management strategies for optimizing carbon sequestration. The objective of our study was to evaluate prediction of 14-day average daytime CO2 fluxes (Fday) and nighttime CO2 fluxes (Rn) using remote sensing and other data. Fday and Rnwere measured with a Bowen ratio–energy balance (BREB) technique in a sagebrush (Artemisia spp.)–steppe ecosystem in northeast Idaho, USA, during 1996–1999. Micrometeorological variables aggregated across 14-day periods and time-integrated Advanced Very High Resolution Radiometer (AVHRR) Normalized Difference Vegetation Index (iNDVI) were determined during four growing seasons (1996–1999) and used to predict Fday and Rn. We found that iNDVI was a strong predictor of Fday(R2=0.79, n=66, P<0.0001). Inclusion of evapotranspiration in the predictive equation led to improved predictions of Fday (R2=0.82, n=66, P<0.0001). Crossvalidation indicated that regression tree predictions of Fday were prone to overfitting and that linear regression models were more robust. Multiple regression and regression tree models predicted Rn quite well (R2=0.75–0.77, n=66) with the regression tree model being slightly more robust in crossvalidation. Temporal mapping of Fday and Rn is possible with these techniques and would allow the assessment of NEE in sagebrush–steppe ecosystems. Simulations of periodic Fday measurements, as might be provided by a mobile flux tower, indicated that such measurements could be used in combination with iNDVI to accurately predict Fday. These periodic measurements could maximize the utility of expensive flux towers for evaluating various carbon management strategies, carbon certification, and validation and calibration of carbon flux models.

Calibration of remotely sensed, coarse resolution NDVI to CO2 fluxes in a sagebrush-steppe ecosystem

USGS Publications Warehouse

Wylie, B.K.; Johnson, D.A.; Laca, Emilio; Saliendra, Nicanor Z.; Gilmanov, T.G.; Reed, B.C.; Tieszen, L.L.; Worstell, B.B.

2003-01-01

The net ecosystem exchange (NEE) of carbon flux can be partitioned into gross primary productivity (GPP) and respiration (R). The contribution of remote sensing and modeling holds the potential to predict these components and map them spatially and temporally. This has obvious utility to quantify carbon sink and source relationships and to identify improved land management strategies for optimizing carbon sequestration. The objective of our study was to evaluate prediction of 14-day average daytime CO2 fluxes (Fday) and nighttime CO2 fluxes (Rn) using remote sensing and other data. Fday and Rn were measured with a Bowen ratio-energy balance (BREB) technique in a sagebrush (Artemisia spp.)-steppe ecosystem in northeast Idaho, USA, during 1996-1999. Micrometeorological variables aggregated across 14-day periods and time-integrated Advanced Very High Resolution Radiometer (AVHRR) Normalized Difference Vegetation Index (iNDVI) were determined during four growing seasons (1996-1999) and used to predict Fday and Rn. We found that iNDVI was a strong predictor of Fday (R2 = 0.79, n = 66, P < 0.0001). Inclusion of evapotranspiration in the predictive equation led to improved predictions of Fday (R2= 0.82, n = 66, P < 0.0001). Crossvalidation indicated that regression tree predictions of Fday were prone to overfitting and that linear regression models were more robust. Multiple regression and regression tree models predicted Rn quite well (R2 = 0.75-0.77, n = 66) with the regression tree model being slightly more robust in crossvalidation. Temporal mapping of Fday and Rn is possible with these techniques and would allow the assessment of NEE in sagebrush-steppe ecosystems. Simulations of periodic Fday measurements, as might be provided by a mobile flux tower, indicated that such measurements could be used in combination with iNDVI to accurately predict Fday. These periodic measurements could maximize the utility of expensive flux towers for evaluating various carbon management strategies, carbon certification, and validation and calibration of carbon flux models. ?? 2003 Elsevier Science Inc. All rights reserved.

[Research of prevalence of schistosomiasis in Hunan province, 1984-2015].

PubMed

Li, F Y; Tan, H Z; Ren, G H; Jiang, Q; Wang, H L

2017-03-10

Objective: To analyze the prevalence of schistosomiasis in Hunan province, and provide scientific evidence for the control and elimination of schistosomiasis. Methods: The changes of infection rates of Schistosoma ( S .) japonicum among residents and cattle in Hunan from 1984 to 2015 were analyzed by using dynamic trend diagram; and the time regression model was used to fit the infection rates of S. japonicum , and predict the recent infection rate. Results: The overall infection rates of S. japonicum in Hunan from 1984 to 2015 showed downward trend (95.29% in residents and 95.16% in cattle). By using the linear regression model, the actual values of infection rates in residents and cattle were all in the 95% confidence intervals of the value predicted; and the prediction showed that the infection rates in the residents and cattle would continue to decrease from 2016 to 2020. Conclusion: The prevalence of schistosomiasis was in decline in Hunan. The regression model has a good effect in the short-term prediction of schistosomiasis prevalence.

Dual Incorporation of the in vitro Data (IC50) and in vivo (Cmax) Data for the Prediction of Area Under the Curve (AUC) for Statins using Regression Models Developed for Either Pravastatin or Simvastatin.

PubMed

Srinivas, N R

2016-08-01

Linear regression models utilizing a single time point (Cmax) has been reported for pravastatin and simvastatin. A new model was developed for the prediction of AUC of statins that utilized the slopes of the above 2 models, with pharmacokinetic (Cmax) and a pharmacodynamic (IC50 value) components for the statins. The prediction of AUCs for various statins (pravastatin, atorvastatin, simvastatin and rosuvastatin) was carried out using the newly developed dual pharmacokinetic and pharmacodynamic model. Generally, the AUC predictions were contained within 0.5 to 2-fold difference of the observed AUC suggesting utility of the new models. The root mean square error predictions were<45% for the 2 models. On the basis of the present work, it is feasible to utilize both pharmacokinetic (Cmax) and pharmacodynamic (IC50) data for effectively predicting the AUC for statins. Such a new concept as described in the work may have utility in both drug discovery and development stages. © Georg Thieme Verlag KG Stuttgart · New York.

Prediction of pulmonary hypertension in idiopathic pulmonary fibrosis☆

PubMed Central

Zisman, David A.; Ross, David J.; Belperio, John A.; Saggar, Rajan; Lynch, Joseph P.; Ardehali, Abbas; Karlamangla, Arun S.

2007-01-01

Summary Background Reliable, noninvasive approaches to the diagnosis of pulmonary hypertension in idiopathic pulmonary fibrosis are needed. We tested the hypothesis that the forced vital capacity to diffusing capacity ratio and room air resting pulse oximetry may be combined to predict mean pulmonary artery pressure (MPAP) in idiopathic pulmonary fibrosis. Methods Sixty-one idiopathic pulmonary fibrosis patients with available right-heart catheterization were studied. We regressed measured MPAP as a continuous variable on pulse oximetry (SpO2) and percent predicted forced vital capacity (FVC) to percent-predicted diffusing capacity ratio (% FVC/% DLco) in a multivariable linear regression model. Results Linear regression generated the following equation: MPAP = −11.9+0.272 × SpO2+0.0659 × (100−SpO2)2+3.06 × (% FVC/% DLco); adjusted R2 = 0.55, p<0.0001. The sensitivity, specificity, positive predictive and negative predictive value of model-predicted pulmonary hypertension were 71% (95% confidence interval (CI): 50–89%), 81% (95% CI: 68–92%), 71% (95% CI: 51–87%) and 81% (95% CI: 68–94%). Conclusions A pulmonary hypertension predictor based on room air resting pulse oximetry and FVC to diffusing capacity ratio has a relatively high negative predictive value. However, this model will require external validation before it can be used in clinical practice. PMID:17604151

Harvest-time prediction of apple physiological indices using fiber optic Fourier transform near-infrared spectrometer

NASA Astrophysics Data System (ADS)

Liu, Yande; Ying, Yibin; Lu, Huishan; Fu, Xiaping

2004-12-01

This work evaluates the feasibility of Fourier transform near infrared (FT-NIR) spectrometry for rapid determining the total soluble solids content and acidity of apple fruit. Intact apple fruit were measured by reflectance FT-NIR in 800-2500 nm range. FT-NIR models were developed based on partial least square (PLS) regression and principal component regress (PCR) with respect to the reflectance and its first derivative, the logarithms of the reflectance reciprocal and its second derivative. The above regression models, related the FT-NIR spectra to soluble solids content (SSC), titratable acidity (TA) and available acidity (pH). The best combination, based on the prediction results, was PLS models with respect to the logarithms of the reflectance reciprocal. Predictions with PLS models resulted standard errors of prediction (SEP) of 0.455, 0.044 and 0.068, and correlation coefficients of 0.968, 0.728 and 0.831 for SSC, TA and pH, respectively. It was concluded that by using the FT-NIR spectrometry measurement system, in the appropriate spectral range, it is possible to nondestructively assess the maturity factors of apple fruit.

Prediction of hourly PM2.5 using a space-time support vector regression model

NASA Astrophysics Data System (ADS)

Yang, Wentao; Deng, Min; Xu, Feng; Wang, Hang

2018-05-01

Real-time air quality prediction has been an active field of research in atmospheric environmental science. The existing methods of machine learning are widely used to predict pollutant concentrations because of their enhanced ability to handle complex non-linear relationships. However, because pollutant concentration data, as typical geospatial data, also exhibit spatial heterogeneity and spatial dependence, they may violate the assumptions of independent and identically distributed random variables in most of the machine learning methods. As a result, a space-time support vector regression model is proposed to predict hourly PM2.5 concentrations. First, to address spatial heterogeneity, spatial clustering is executed to divide the study area into several homogeneous or quasi-homogeneous subareas. To handle spatial dependence, a Gauss vector weight function is then developed to determine spatial autocorrelation variables as part of the input features. Finally, a local support vector regression model with spatial autocorrelation variables is established for each subarea. Experimental data on PM2.5 concentrations in Beijing are used to verify whether the results of the proposed model are superior to those of other methods.

Comparison of random regression models with Legendre polynomials and linear splines for production traits and somatic cell score of Canadian Holstein cows.

PubMed

Bohmanova, J; Miglior, F; Jamrozik, J; Misztal, I; Sullivan, P G

2008-09-01

A random regression model with both random and fixed regressions fitted by Legendre polynomials of order 4 was compared with 3 alternative models fitting linear splines with 4, 5, or 6 knots. The effects common for all models were a herd-test-date effect, fixed regressions on days in milk (DIM) nested within region-age-season of calving class, and random regressions for additive genetic and permanent environmental effects. Data were test-day milk, fat and protein yields, and SCS recorded from 5 to 365 DIM during the first 3 lactations of Canadian Holstein cows. A random sample of 50 herds consisting of 96,756 test-day records was generated to estimate variance components within a Bayesian framework via Gibbs sampling. Two sets of genetic evaluations were subsequently carried out to investigate performance of the 4 models. Models were compared by graphical inspection of variance functions, goodness of fit, error of prediction of breeding values, and stability of estimated breeding values. Models with splines gave lower estimates of variances at extremes of lactations than the model with Legendre polynomials. Differences among models in goodness of fit measured by percentages of squared bias, correlations between predicted and observed records, and residual variances were small. The deviance information criterion favored the spline model with 6 knots. Smaller error of prediction and higher stability of estimated breeding values were achieved by using spline models with 5 and 6 knots compared with the model with Legendre polynomials. In general, the spline model with 6 knots had the best overall performance based upon the considered model comparison criteria.

Comparison of Prediction Model for Cardiovascular Autonomic Dysfunction Using Artificial Neural Network and Logistic Regression Analysis

PubMed Central

Zeng, Fangfang; Li, Zhongtao; Yu, Xiaoling; Zhou, Linuo

2013-01-01

Background This study aimed to develop the artificial neural network (ANN) and multivariable logistic regression (LR) analyses for prediction modeling of cardiovascular autonomic (CA) dysfunction in the general population, and compare the prediction models using the two approaches. Methods and Materials We analyzed a previous dataset based on a Chinese population sample consisting of 2,092 individuals aged 30–80 years. The prediction models were derived from an exploratory set using ANN and LR analysis, and were tested in the validation set. Performances of these prediction models were then compared. Results Univariate analysis indicated that 14 risk factors showed statistically significant association with the prevalence of CA dysfunction (P<0.05). The mean area under the receiver-operating curve was 0.758 (95% CI 0.724–0.793) for LR and 0.762 (95% CI 0.732–0.793) for ANN analysis, but noninferiority result was found (P<0.001). The similar results were found in comparisons of sensitivity, specificity, and predictive values in the prediction models between the LR and ANN analyses. Conclusion The prediction models for CA dysfunction were developed using ANN and LR. ANN and LR are two effective tools for developing prediction models based on our dataset. PMID:23940593

Development of a noise prediction model based on advanced fuzzy approaches in typical industrial workrooms.

PubMed

Aliabadi, Mohsen; Golmohammadi, Rostam; Khotanlou, Hassan; Mansoorizadeh, Muharram; Salarpour, Amir

2014-01-01

Noise prediction is considered to be the best method for evaluating cost-preventative noise controls in industrial workrooms. One of the most important issues is the development of accurate models for analysis of the complex relationships among acoustic features affecting noise level in workrooms. In this study, advanced fuzzy approaches were employed to develop relatively accurate models for predicting noise in noisy industrial workrooms. The data were collected from 60 industrial embroidery workrooms in the Khorasan Province, East of Iran. The main acoustic and embroidery process features that influence the noise were used to develop prediction models using MATLAB software. Multiple regression technique was also employed and its results were compared with those of fuzzy approaches. Prediction errors of all prediction models based on fuzzy approaches were within the acceptable level (lower than one dB). However, Neuro-fuzzy model (RMSE=0.53dB and R2=0.88) could slightly improve the accuracy of noise prediction compared with generate fuzzy model. Moreover, fuzzy approaches provided more accurate predictions than did regression technique. The developed models based on fuzzy approaches as useful prediction tools give professionals the opportunity to have an optimum decision about the effectiveness of acoustic treatment scenarios in embroidery workrooms.

Groundwater depth prediction in a shallow aquifer in north China by a quantile regression model

NASA Astrophysics Data System (ADS)

Li, Fawen; Wei, Wan; Zhao, Yong; Qiao, Jiale

2017-01-01

There is a close relationship between groundwater level in a shallow aquifer and the surface ecological environment; hence, it is important to accurately simulate and predict the groundwater level in eco-environmental construction projects. The multiple linear regression (MLR) model is one of the most useful methods to predict groundwater level (depth); however, the predicted values by this model only reflect the mean distribution of the observations and cannot effectively fit the extreme distribution data (outliers). The study reported here builds a prediction model of groundwater-depth dynamics in a shallow aquifer using the quantile regression (QR) method on the basis of the observed data of groundwater depth and related factors. The proposed approach was applied to five sites in Tianjin city, north China, and the groundwater depth was calculated in different quantiles, from which the optimal quantile was screened out according to the box plot method and compared to the values predicted by the MLR model. The results showed that the related factors in the five sites did not follow the standard normal distribution and that there were outliers in the precipitation and last-month (initial state) groundwater-depth factors because the basic assumptions of the MLR model could not be achieved, thereby causing errors. Nevertheless, these conditions had no effect on the QR model, as it could more effectively describe the distribution of original data and had a higher precision in fitting the outliers.

Influence of landscape-scale factors in limiting brook trout populations in Pennsylvania streams

USGS Publications Warehouse

Kocovsky, P.M.; Carline, R.F.

2006-01-01

Landscapes influence the capacity of streams to produce trout through their effect on water chemistry and other factors at the reach scale. Trout abundance also fluctuates over time; thus, to thoroughly understand how spatial factors at landscape scales affect trout populations, one must assess the changes in populations over time to provide a context for interpreting the importance of spatial factors. We used data from the Pennsylvania Fish and Boat Commission's fisheries management database to investigate spatial factors that affect the capacity of streams to support brook trout Salvelinus fontinalis and to provide models useful for their management. We assessed the relative importance of spatial and temporal variation by calculating variance components and comparing relative standard errors for spatial and temporal variation. We used binary logistic regression to predict the presence of harvestable-length brook trout and multiple linear regression to assess the mechanistic links between landscapes and trout populations and to predict population density. The variance in trout density among streams was equal to or greater than the temporal variation for several streams, indicating that differences among sites affect population density. Logistic regression models correctly predicted the absence of harvestable-length brook trout in 60% of validation samples. The r 2-value for the linear regression model predicting density was 0.3, indicating low predictive ability. Both logistic and linear regression models supported buffering capacity against acid episodes as an important mechanistic link between landscapes and trout populations. Although our models fail to predict trout densities precisely, their success at elucidating the mechanistic links between landscapes and trout populations, in concert with the importance of spatial variation, increases our understanding of factors affecting brook trout abundance and will help managers and private groups to protect and enhance populations of wild brook trout. ?? Copyright by the American Fisheries Society 2006.

Age- and sex-dependent regression models for predicting the live weight of West African Dwarf goat from body measurements.

PubMed

Sowande, O S; Oyewale, B F; Iyasere, O S

2010-06-01

The relationships between live weight and eight body measurements of West African Dwarf (WAD) goats were studied using 211 animals under farm condition. The animals were categorized based on age and sex. Data obtained on height at withers (HW), heart girth (HG), body length (BL), head length (HL), and length of hindquarter (LHQ) were fitted into simple linear, allometric, and multiple-regression models to predict live weight from the body measurements according to age group and sex. Results showed that live weight, HG, BL, LHQ, HL, and HW increased with the age of the animals. In multiple-regression model, HG and HL best fit the model for goat kids; HG, HW, and HL for goat aged 13-24 months; while HG, LHQ, HW, and HL best fit the model for goats aged 25-36 months. Coefficients of determination (R(2)) values for linear and allometric models for predicting the live weight of WAD goat increased with age in all the body measurements, with HG being the most satisfactory single measurement in predicting the live weight of WAD goat. Sex had significant influence on the model with R(2) values consistently higher in females except the models for LHQ and HW.

The novel application of artificial neural network on bioelectrical impedance analysis to assess the body composition in elderly

PubMed Central

2013-01-01

Background This study aims to improve accuracy of Bioelectrical Impedance Analysis (BIA) prediction equations for estimating fat free mass (FFM) of the elderly by using non-linear Back Propagation Artificial Neural Network (BP-ANN) model and to compare the predictive accuracy with the linear regression model by using energy dual X-ray absorptiometry (DXA) as reference method. Methods A total of 88 Taiwanese elderly adults were recruited in this study as subjects. Linear regression equations and BP-ANN prediction equation were developed using impedances and other anthropometrics for predicting the reference FFM measured by DXA (FFMDXA) in 36 male and 26 female Taiwanese elderly adults. The FFM estimated by BIA prediction equations using traditional linear regression model (FFMLR) and BP-ANN model (FFMANN) were compared to the FFMDXA. The measuring results of an additional 26 elderly adults were used to validate than accuracy of the predictive models. Results The results showed the significant predictors were impedance, gender, age, height and weight in developed FFMLR linear model (LR) for predicting FFM (coefficient of determination, r2 = 0.940; standard error of estimate (SEE) = 2.729 kg; root mean square error (RMSE) = 2.571kg, P < 0.001). The above predictors were set as the variables of the input layer by using five neurons in the BP-ANN model (r2 = 0.987 with a SD = 1.192 kg and relatively lower RMSE = 1.183 kg), which had greater (improved) accuracy for estimating FFM when compared with linear model. The results showed a better agreement existed between FFMANN and FFMDXA than that between FFMLR and FFMDXA. Conclusion When compared the performance of developed prediction equations for estimating reference FFMDXA, the linear model has lower r2 with a larger SD in predictive results than that of BP-ANN model, which indicated ANN model is more suitable for estimating FFM. PMID:23388042

Prediction of silicon oxynitride plasma etching using a generalized regression neural network

NASA Astrophysics Data System (ADS)

Kim, Byungwhan; Lee, Byung Teak

2005-08-01

A prediction model of silicon oxynitride (SiON) etching was constructed using a neural network. Model prediction performance was improved by means of genetic algorithm. The etching was conducted in a C2F6 inductively coupled plasma. A 24 full factorial experiment was employed to systematically characterize parameter effects on SiON etching. The process parameters include radio frequency source power, bias power, pressure, and C2F6 flow rate. To test the appropriateness of the trained model, additional 16 experiments were conducted. For comparison, four types of statistical regression models were built. Compared to the best regression model, the optimized neural network model demonstrated an improvement of about 52%. The optimized model was used to infer etch mechanisms as a function of parameters. The pressure effect was noticeably large only as relatively large ion bombardment was maintained in the process chamber. Ion-bombardment-activated polymer deposition played the most significant role in interpreting the complex effect of bias power or C2F6 flow rate. Moreover, [CF2] was expected to be the predominant precursor to polymer deposition.

Modeling Stationary Lithium-Ion Batteries for Optimization and Predictive Control

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

Baker, Kyri A; Shi, Ying; Christensen, Dane T

Accurately modeling stationary battery storage behavior is crucial to understand and predict its limitations in demand-side management scenarios. In this paper, a lithium-ion battery model was derived to estimate lifetime and state-of-charge for building-integrated use cases. The proposed battery model aims to balance speed and accuracy when modeling battery behavior for real-time predictive control and optimization. In order to achieve these goals, a mixed modeling approach was taken, which incorporates regression fits to experimental data and an equivalent circuit to model battery behavior. A comparison of the proposed battery model output to actual data from the manufacturer validates the modelingmore » approach taken in the paper. Additionally, a dynamic test case demonstrates the effects of using regression models to represent internal resistance and capacity fading.« less

Modeling Stationary Lithium-Ion Batteries for Optimization and Predictive Control: Preprint

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

Raszmann, Emma; Baker, Kyri; Shi, Ying

Accurately modeling stationary battery storage behavior is crucial to understand and predict its limitations in demand-side management scenarios. In this paper, a lithium-ion battery model was derived to estimate lifetime and state-of-charge for building-integrated use cases. The proposed battery model aims to balance speed and accuracy when modeling battery behavior for real-time predictive control and optimization. In order to achieve these goals, a mixed modeling approach was taken, which incorporates regression fits to experimental data and an equivalent circuit to model battery behavior. A comparison of the proposed battery model output to actual data from the manufacturer validates the modelingmore » approach taken in the paper. Additionally, a dynamic test case demonstrates the effects of using regression models to represent internal resistance and capacity fading.« less

Regression models to predict hip joint centers in pathological hip population.

PubMed

Mantovani, Giulia; Ng, K C Geoffrey; Lamontagne, Mario

2016-02-01

The purpose was to investigate the validity of Harrington's and Davis's hip joint center (HJC) regression equations on a population affected by a hip deformity, (i.e., femoroacetabular impingement). Sixty-seven participants (21 healthy controls, 46 with a cam-type deformity) underwent pelvic CT imaging. Relevant bony landmarks and geometric HJCs were digitized from the images, and skin thickness was measured for the anterior and posterior superior iliac spines. Non-parametric statistical and Bland-Altman tests analyzed differences between the predicted HJC (from regression equations) and the actual HJC (from CT images). The error from Davis's model (25.0 ± 6.7 mm) was larger than Harrington's (12.3 ± 5.9 mm, p<0.001). There were no differences between groups, thus, studies on femoroacetabular impingement can implement conventional regression models. Measured skin thickness was 9.7 ± 7.0mm and 19.6 ± 10.9 mm for the anterior and posterior bony landmarks, respectively, and correlated with body mass index. Skin thickness estimates can be considered to reduce the systematic error introduced by surface markers. New adult-specific regression equations were developed from the CT dataset, with the hypothesis that they could provide better estimates when tuned to a larger adult-specific dataset. The linear models were validated on external datasets and using leave-one-out cross-validation techniques; Prediction errors were comparable to those of Harrington's model, despite the adult-specific population and the larger sample size, thus, prediction accuracy obtained from these parameters could not be improved. Copyright © 2015 Elsevier B.V. All rights reserved.

Modeling energy expenditure in children and adolescents using quantile regression

PubMed Central

Yang, Yunwen; Adolph, Anne L.; Puyau, Maurice R.; Vohra, Firoz A.; Zakeri, Issa F.

2013-01-01

Advanced mathematical models have the potential to capture the complex metabolic and physiological processes that result in energy expenditure (EE). Study objective is to apply quantile regression (QR) to predict EE and determine quantile-dependent variation in covariate effects in nonobese and obese children. First, QR models will be developed to predict minute-by-minute awake EE at different quantile levels based on heart rate (HR) and physical activity (PA) accelerometry counts, and child characteristics of age, sex, weight, and height. Second, the QR models will be used to evaluate the covariate effects of weight, PA, and HR across the conditional EE distribution. QR and ordinary least squares (OLS) regressions are estimated in 109 children, aged 5–18 yr. QR modeling of EE outperformed OLS regression for both nonobese and obese populations. Average prediction errors for QR compared with OLS were not only smaller at the median τ = 0.5 (18.6 vs. 21.4%), but also substantially smaller at the tails of the distribution (10.2 vs. 39.2% at τ = 0.1 and 8.7 vs. 19.8% at τ = 0.9). Covariate effects of weight, PA, and HR on EE for the nonobese and obese children differed across quantiles (P < 0.05). The associations (linear and quadratic) between PA and HR with EE were stronger for the obese than nonobese population (P < 0.05). In conclusion, QR provided more accurate predictions of EE compared with conventional OLS regression, especially at the tails of the distribution, and revealed substantially different covariate effects of weight, PA, and HR on EE in nonobese and obese children. PMID:23640591

A Predictive Model for Readmissions Among Medicare Patients in a California Hospital.

PubMed

Duncan, Ian; Huynh, Nhan

2017-11-17

Predictive models for hospital readmission rates are in high demand because of the Centers for Medicare & Medicaid Services (CMS) Hospital Readmission Reduction Program (HRRP). The LACE index is one of the most popular predictive tools among hospitals in the United States. The LACE index is a simple tool with 4 parameters: Length of stay, Acuity of admission, Comorbidity, and Emergency visits in the previous 6 months. The authors applied logistic regression to develop a predictive model for a medium-sized not-for-profit community hospital in California using patient-level data with more specific patient information (including 13 explanatory variables). Specifically, the logistic regression is applied to 2 populations: a general population including all patients and the specific group of patients targeted by the CMS penalty (characterized as ages 65 or older with select conditions). The 2 resulting logistic regression models have a higher sensitivity rate compared to the sensitivity of the LACE index. The C statistic values of the model applied to both populations demonstrate moderate levels of predictive power. The authors also build an economic model to demonstrate the potential financial impact of the use of the model for targeting high-risk patients in a sample hospital and demonstrate that, on balance, whether the hospital gains or loses from reducing readmissions depends on its margin and the extent of its readmission penalties.

Prediction of biomechanical parameters of the proximal femur using statistical appearance models and support vector regression.

PubMed

Fritscher, Karl; Schuler, Benedikt; Link, Thomas; Eckstein, Felix; Suhm, Norbert; Hänni, Markus; Hengg, Clemens; Schubert, Rainer

2008-01-01

Fractures of the proximal femur are one of the principal causes of mortality among elderly persons. Traditional methods for the determination of femoral fracture risk use methods for measuring bone mineral density. However, BMD alone is not sufficient to predict bone failure load for an individual patient and additional parameters have to be determined for this purpose. In this work an approach that uses statistical models of appearance to identify relevant regions and parameters for the prediction of biomechanical properties of the proximal femur will be presented. By using Support Vector Regression the proposed model based approach is capable of predicting two different biomechanical parameters accurately and fully automatically in two different testing scenarios.

Pan evaporation modeling using six different heuristic computing methods in different climates of China

NASA Astrophysics Data System (ADS)

Wang, Lunche; Kisi, Ozgur; Zounemat-Kermani, Mohammad; Li, Hui

2017-01-01

Pan evaporation (Ep) plays important roles in agricultural water resources management. One of the basic challenges is modeling Ep using limited climatic parameters because there are a number of factors affecting the evaporation rate. This study investigated the abilities of six different soft computing methods, multi-layer perceptron (MLP), generalized regression neural network (GRNN), fuzzy genetic (FG), least square support vector machine (LSSVM), multivariate adaptive regression spline (MARS), adaptive neuro-fuzzy inference systems with grid partition (ANFIS-GP), and two regression methods, multiple linear regression (MLR) and Stephens and Stewart model (SS) in predicting monthly Ep. Long-term climatic data at various sites crossing a wide range of climates during 1961-2000 are used for model development and validation. The results showed that the models have different accuracies in different climates and the MLP model performed superior to the other models in predicting monthly Ep at most stations using local input combinations (for example, the MAE (mean absolute errors), RMSE (root mean square errors), and determination coefficient (R2) are 0.314 mm/day, 0.405 mm/day and 0.988, respectively for HEB station), while GRNN model performed better in Tibetan Plateau (MAE, RMSE and R2 are 0.459 mm/day, 0.592 mm/day and 0.932, respectively). The accuracies of above models ranked as: MLP, GRNN, LSSVM, FG, ANFIS-GP, MARS and MLR. The overall results indicated that the soft computing techniques generally performed better than the regression methods, but MLR and SS models can be more preferred at some climatic zones instead of complex nonlinear models, for example, the BJ (Beijing), CQ (Chongqing) and HK (Haikou) stations. Therefore, it can be concluded that Ep could be successfully predicted using above models in hydrological modeling studies.

Predicting outcome on admission and post-admission for acetaminophen-induced acute liver failure using classification and regression tree models.

PubMed

Speiser, Jaime Lynn; Lee, William M; Karvellas, Constantine J

2015-01-01

Assessing prognosis for acetaminophen-induced acute liver failure (APAP-ALF) patients often presents significant challenges. King's College (KCC) has been validated on hospital admission, but little has been published on later phases of illness. We aimed to improve determinations of prognosis both at the time of and following admission for APAP-ALF using Classification and Regression Tree (CART) models. CART models were applied to US ALFSG registry data to predict 21-day death or liver transplant early (on admission) and post-admission (days 3-7) for 803 APAP-ALF patients enrolled 01/1998-09/2013. Accuracy in prediction of outcome (AC), sensitivity (SN), specificity (SP), and area under receiver-operating curve (AUROC) were compared between 3 models: KCC (INR, creatinine, coma grade, pH), CART analysis using only KCC variables (KCC-CART) and a CART model using new variables (NEW-CART). Traditional KCC yielded 69% AC, 90% SP, 27% SN, and 0.58 AUROC on admission, with similar performance post-admission. KCC-CART at admission offered predictive 66% AC, 65% SP, 67% SN, and 0.74 AUROC. Post-admission, KCC-CART had predictive 82% AC, 86% SP, 46% SN and 0.81 AUROC. NEW-CART models using MELD (Model for end stage liver disease), lactate and mechanical ventilation on admission yielded predictive 72% AC, 71% SP, 77% SN and AUROC 0.79. For later stages, NEW-CART (MELD, lactate, coma grade) offered predictive AC 86%, SP 91%, SN 46%, AUROC 0.73. CARTs offer simple prognostic models for APAP-ALF patients, which have higher AUROC and SN than KCC, with similar AC and negligibly worse SP. Admission and post-admission predictions were developed. • Prognostication in acetaminophen-induced acute liver failure (APAP-ALF) is challenging beyond admission • Little has been published regarding the use of King's College Criteria (KCC) beyond admission and KCC has shown limited sensitivity in subsequent studies • Classification and Regression Tree (CART) methodology allows the development of predictive models using binary splits and offers an intuitive method for predicting outcome, using processes familiar to clinicians • Data from the ALFSG registry suggested that CART prognosis models for the APAP population offer improved sensitivity and model performance over traditional regression-based KCC, while maintaining similar accuracy and negligibly worse specificity • KCC-CART models offered modest improvement over traditional KCC, with NEW-CART models performing better than KCC-CART particularly at late time points.

Assessing the accuracy of ANFIS, EEMD-GRNN, PCR, and MLR models in predicting PM2.5

NASA Astrophysics Data System (ADS)

Ausati, Shadi; Amanollahi, Jamil

2016-10-01

Since Sanandaj is considered one of polluted cities of Iran, prediction of any type of pollution especially prediction of suspended particles of PM2.5, which are the cause of many diseases, could contribute to health of society by timely announcements and prior to increase of PM2.5. In order to predict PM2.5 concentration in the Sanandaj air the hybrid models consisting of an ensemble empirical mode decomposition and general regression neural network (EEMD-GRNN), Adaptive Neuro-Fuzzy Inference System (ANFIS), principal component regression (PCR), and linear model such as multiple liner regression (MLR) model were used. In these models the data of suspended particles of PM2.5 were the dependent variable and the data related to air quality including PM2.5, PM10, SO2, NO2, CO, O3 and meteorological data including average minimum temperature (Min T), average maximum temperature (Max T), average atmospheric pressure (AP), daily total precipitation (TP), daily relative humidity level of the air (RH) and daily wind speed (WS) for the year 2014 in Sanandaj were the independent variables. Among the used models, EEMD-GRNN model with values of R2 = 0.90, root mean square error (RMSE) = 4.9218 and mean absolute error (MAE) = 3.4644 in the training phase and with values of R2 = 0.79, RMSE = 5.0324 and MAE = 3.2565 in the testing phase, exhibited the best function in predicting this phenomenon. It can be concluded that hybrid models have accurate results to predict PM2.5 concentration compared with linear model.

The role of shoe design on the prediction of free torque at the shoe-surface interface using pressure insole technology.

PubMed

Weaver, Brian Thomas; Fitzsimons, Kathleen; Braman, Jerrod; Haut, Roger

2016-09-01

The goal of the current study was to expand on previous work to validate the use of pressure insole technology in conjunction with linear regression models to predict the free torque at the shoe-surface interface that is generated while wearing different athletic shoes. Three distinctly different shoe designs were utilised. The stiffness of each shoe was determined with a material's testing machine. Six participants wore each shoe that was fitted with an insole pressure measurement device and performed rotation trials on an embedded force plate. A pressure sensor mask was constructed from those sensors having a high linear correlation with free torque values. Linear regression models were developed to predict free torques from these pressure sensor data. The models were able to accurately predict their own free torque well (RMS error 3.72 ± 0.74 Nm), but not that of the other shoes (RMS error 10.43 ± 3.79 Nm). Models performing self-prediction were also able to measure differences in shoe stiffness. The results of the current study showed the need for participant-shoe specific linear regression models to insure high prediction accuracy of free torques from pressure sensor data during isolated internal and external rotations of the body with respect to a planted foot.

New regression model for predicting hand-arm vibration (HAV) of Malaysian Army (MA) three-tonne truck steering wheels.

PubMed

Aziz, Shamsul Akmar Ab; Nuawi, Mohd Zaki; Nor, Mohd Jailani Mohd

2015-01-01

The objective of this study was to present a new method for determination of hand-arm vibration (HAV) in Malaysian Army (MA) three-tonne truck steering wheels based on changes in vehicle speed using regression model and the statistical analysis method known as Integrated Kurtosis-Based Algorithm for Z-Notch Filter Technique Vibro (I-kaz Vibro). The test was conducted for two different road conditions, tarmac and dirt roads. HAV exposure was measured using a Brüel & Kjær Type 3649 vibration analyzer, which is capable of recording HAV exposures from steering wheels. The data was analyzed using I-kaz Vibro to determine the HAV values in relation to varying speeds of a truck and to determine the degree of data scattering for HAV data signals. Based on the results obtained, HAV experienced by drivers can be determined using the daily vibration exposure A(8), I-kaz Vibro coefficient (Ƶ(v)(∞)), and the I-kaz Vibro display. The I-kaz Vibro displays also showed greater scatterings, indicating that the values of Ƶ(v)(∞) and A(8) were increasing. Prediction of HAV exposure was done using the developed regression model and graphical representations of Ƶ(v)(∞). The results of the regression model showed that Ƶ(v)(∞) increased when the vehicle speed and HAV exposure increased. For model validation, predicted and measured noise exposures were compared, and high coefficient of correlation (R(2)) values were obtained, indicating that good agreement was obtained between them. By using the developed regression model, we can easily predict HAV exposure from steering wheels for HAV exposure monitoring.

A nonparametric multiple imputation approach for missing categorical data.

PubMed

Zhou, Muhan; He, Yulei; Yu, Mandi; Hsu, Chiu-Hsieh

2017-06-06

Incomplete categorical variables with more than two categories are common in public health data. However, most of the existing missing-data methods do not use the information from nonresponse (missingness) probabilities. We propose a nearest-neighbour multiple imputation approach to impute a missing at random categorical outcome and to estimate the proportion of each category. The donor set for imputation is formed by measuring distances between each missing value with other non-missing values. The distance function is calculated based on a predictive score, which is derived from two working models: one fits a multinomial logistic regression for predicting the missing categorical outcome (the outcome model) and the other fits a logistic regression for predicting missingness probabilities (the missingness model). A weighting scheme is used to accommodate contributions from two working models when generating the predictive score. A missing value is imputed by randomly selecting one of the non-missing values with the smallest distances. We conduct a simulation to evaluate the performance of the proposed method and compare it with several alternative methods. A real-data application is also presented. The simulation study suggests that the proposed method performs well when missingness probabilities are not extreme under some misspecifications of the working models. However, the calibration estimator, which is also based on two working models, can be highly unstable when missingness probabilities for some observations are extremely high. In this scenario, the proposed method produces more stable and better estimates. In addition, proper weights need to be chosen to balance the contributions from the two working models and achieve optimal results for the proposed method. We conclude that the proposed multiple imputation method is a reasonable approach to dealing with missing categorical outcome data with more than two levels for assessing the distribution of the outcome. In terms of the choices for the working models, we suggest a multinomial logistic regression for predicting the missing outcome and a binary logistic regression for predicting the missingness probability.

A consensus least squares support vector regression (LS-SVR) for analysis of near-infrared spectra of plant samples.

PubMed

Li, Yankun; Shao, Xueguang; Cai, Wensheng

2007-04-15

Consensus modeling of combining the results of multiple independent models to produce a single prediction avoids the instability of single model. Based on the principle of consensus modeling, a consensus least squares support vector regression (LS-SVR) method for calibrating the near-infrared (NIR) spectra was proposed. In the proposed approach, NIR spectra of plant samples were firstly preprocessed using discrete wavelet transform (DWT) for filtering the spectral background and noise, then, consensus LS-SVR technique was used for building the calibration model. With an optimization of the parameters involved in the modeling, a satisfied model was achieved for predicting the content of reducing sugar in plant samples. The predicted results show that consensus LS-SVR model is more robust and reliable than the conventional partial least squares (PLS) and LS-SVR methods.

ATLS Hypovolemic Shock Classification by Prediction of Blood Loss in Rats Using Regression Models.

PubMed

Choi, Soo Beom; Choi, Joon Yul; Park, Jee Soo; Kim, Deok Won

2016-07-01

In our previous study, our input data set consisted of 78 rats, the blood loss in percent as a dependent variable, and 11 independent variables (heart rate, systolic blood pressure, diastolic blood pressure, mean arterial pressure, pulse pressure, respiration rate, temperature, perfusion index, lactate concentration, shock index, and new index (lactate concentration/perfusion)). The machine learning methods for multicategory classification were applied to a rat model in acute hemorrhage to predict the four Advanced Trauma Life Support (ATLS) hypovolemic shock classes for triage in our previous study. However, multicategory classification is much more difficult and complicated than binary classification. We introduce a simple approach for classifying ATLS hypovolaemic shock class by predicting blood loss in percent using support vector regression and multivariate linear regression (MLR). We also compared the performance of the classification models using absolute and relative vital signs. The accuracies of support vector regression and MLR models with relative values by predicting blood loss in percent were 88.5% and 84.6%, respectively. These were better than the best accuracy of 80.8% of the direct multicategory classification using the support vector machine one-versus-one model in our previous study for the same validation data set. Moreover, the simple MLR models with both absolute and relative values could provide possibility of the future clinical decision support system for ATLS classification. The perfusion index and new index were more appropriate with relative changes than absolute values.

Forecasting municipal solid waste generation using prognostic tools and regression analysis.

PubMed

Ghinea, Cristina; Drăgoi, Elena Niculina; Comăniţă, Elena-Diana; Gavrilescu, Marius; Câmpean, Teofil; Curteanu, Silvia; Gavrilescu, Maria

2016-11-01

For an adequate planning of waste management systems the accurate forecast of waste generation is an essential step, since various factors can affect waste trends. The application of predictive and prognosis models are useful tools, as reliable support for decision making processes. In this paper some indicators such as: number of residents, population age, urban life expectancy, total municipal solid waste were used as input variables in prognostic models in order to predict the amount of solid waste fractions. We applied Waste Prognostic Tool, regression analysis and time series analysis to forecast municipal solid waste generation and composition by considering the Iasi Romania case study. Regression equations were determined for six solid waste fractions (paper, plastic, metal, glass, biodegradable and other waste). Accuracy Measures were calculated and the results showed that S-curve trend model is the most suitable for municipal solid waste (MSW) prediction. Copyright © 2016 Elsevier Ltd. All rights reserved.

Model parameter uncertainty analysis for an annual field-scale P loss model

NASA Astrophysics Data System (ADS)

Bolster, Carl H.; Vadas, Peter A.; Boykin, Debbie

2016-08-01

Phosphorous (P) fate and transport models are important tools for developing and evaluating conservation practices aimed at reducing P losses from agricultural fields. Because all models are simplifications of complex systems, there will exist an inherent amount of uncertainty associated with their predictions. It is therefore important that efforts be directed at identifying, quantifying, and communicating the different sources of model uncertainties. In this study, we conducted an uncertainty analysis with the Annual P Loss Estimator (APLE) model. Our analysis included calculating parameter uncertainties and confidence and prediction intervals for five internal regression equations in APLE. We also estimated uncertainties of the model input variables based on values reported in the literature. We then predicted P loss for a suite of fields under different management and climatic conditions while accounting for uncertainties in the model parameters and inputs and compared the relative contributions of these two sources of uncertainty to the overall uncertainty associated with predictions of P loss. Both the overall magnitude of the prediction uncertainties and the relative contributions of the two sources of uncertainty varied depending on management practices and field characteristics. This was due to differences in the number of model input variables and the uncertainties in the regression equations associated with each P loss pathway. Inspection of the uncertainties in the five regression equations brought attention to a previously unrecognized limitation with the equation used to partition surface-applied fertilizer P between leaching and runoff losses. As a result, an alternate equation was identified that provided similar predictions with much less uncertainty. Our results demonstrate how a thorough uncertainty and model residual analysis can be used to identify limitations with a model. Such insight can then be used to guide future data collection and model development and evaluation efforts.

Modeling urban coastal flood severity from crowd-sourced flood reports using Poisson regression and Random Forest

NASA Astrophysics Data System (ADS)

Sadler, J. M.; Goodall, J. L.; Morsy, M. M.; Spencer, K.

2018-04-01

Sea level rise has already caused more frequent and severe coastal flooding and this trend will likely continue. Flood prediction is an essential part of a coastal city's capacity to adapt to and mitigate this growing problem. Complex coastal urban hydrological systems however, do not always lend themselves easily to physically-based flood prediction approaches. This paper presents a method for using a data-driven approach to estimate flood severity in an urban coastal setting using crowd-sourced data, a non-traditional but growing data source, along with environmental observation data. Two data-driven models, Poisson regression and Random Forest regression, are trained to predict the number of flood reports per storm event as a proxy for flood severity, given extensive environmental data (i.e., rainfall, tide, groundwater table level, and wind conditions) as input. The method is demonstrated using data from Norfolk, Virginia USA from September 2010 to October 2016. Quality-controlled, crowd-sourced street flooding reports ranging from 1 to 159 per storm event for 45 storm events are used to train and evaluate the models. Random Forest performed better than Poisson regression at predicting the number of flood reports and had a lower false negative rate. From the Random Forest model, total cumulative rainfall was by far the most dominant input variable in predicting flood severity, followed by low tide and lower low tide. These methods serve as a first step toward using data-driven methods for spatially and temporally detailed coastal urban flood prediction.

Development of non-linear models predicting daily fine particle concentrations using aerosol optical depth retrievals and ground-based measurements at a municipality in the Brazilian Amazon region

NASA Astrophysics Data System (ADS)

Gonçalves, Karen dos Santos; Winkler, Mirko S.; Benchimol-Barbosa, Paulo Roberto; de Hoogh, Kees; Artaxo, Paulo Eduardo; de Souza Hacon, Sandra; Schindler, Christian; Künzli, Nino

2018-07-01

Epidemiological studies generally use particulate matter measurements with diameter less 2.5 μm (PM2.5) from monitoring networks. Satellite aerosol optical depth (AOD) data has considerable potential in predicting PM2.5 concentrations, and thus provides an alternative method for producing knowledge regarding the level of pollution and its health impact in areas where no ground PM2.5 measurements are available. This is the case in the Brazilian Amazon rainforest region where forest fires are frequent sources of high pollution. In this study, we applied a non-linear model for predicting PM2.5 concentration from AOD retrievals using interaction terms between average temperature, relative humidity, sine, cosine of date in a period of 365,25 days and the square of the lagged relative residual. Regression performance statistics were tested comparing the goodness of fit and R2 based on results from linear regression and non-linear regression for six different models. The regression results for non-linear prediction showed the best performance, explaining on average 82% of the daily PM2.5 concentrations when considering the whole period studied. In the context of Amazonia, it was the first study predicting PM2.5 concentrations using the latest high-resolution AOD products also in combination with the testing of a non-linear model performance. Our results permitted a reliable prediction considering the AOD-PM2.5 relationship and set the basis for further investigations on air pollution impacts in the complex context of Brazilian Amazon Region.

Body Fat Percentage Prediction Using Intelligent Hybrid Approaches

PubMed Central

Shao, Yuehjen E.

2014-01-01

Excess of body fat often leads to obesity. Obesity is typically associated with serious medical diseases, such as cancer, heart disease, and diabetes. Accordingly, knowing the body fat is an extremely important issue since it affects everyone's health. Although there are several ways to measure the body fat percentage (BFP), the accurate methods are often associated with hassle and/or high costs. Traditional single-stage approaches may use certain body measurements or explanatory variables to predict the BFP. Diverging from existing approaches, this study proposes new intelligent hybrid approaches to obtain fewer explanatory variables, and the proposed forecasting models are able to effectively predict the BFP. The proposed hybrid models consist of multiple regression (MR), artificial neural network (ANN), multivariate adaptive regression splines (MARS), and support vector regression (SVR) techniques. The first stage of the modeling includes the use of MR and MARS to obtain fewer but more important sets of explanatory variables. In the second stage, the remaining important variables are served as inputs for the other forecasting methods. A real dataset was used to demonstrate the development of the proposed hybrid models. The prediction results revealed that the proposed hybrid schemes outperformed the typical, single-stage forecasting models. PMID:24723804

Modeling maximum daily temperature using a varying coefficient regression model

Treesearch

Han Li; Xinwei Deng; Dong-Yum Kim; Eric P. Smith

2014-01-01

Relationships between stream water and air temperatures are often modeled using linear or nonlinear regression methods. Despite a strong relationship between water and air temperatures and a variety of models that are effective for data summarized on a weekly basis, such models did not yield consistently good predictions for summaries such as daily maximum temperature...

An Investigation of the Fit of Linear Regression Models to Data from an SAT[R] Validity Study. Research Report 2011-3

ERIC Educational Resources Information Center

Kobrin, Jennifer L.; Sinharay, Sandip; Haberman, Shelby J.; Chajewski, Michael

2011-01-01

This study examined the adequacy of a multiple linear regression model for predicting first-year college grade point average (FYGPA) using SAT[R] scores and high school grade point average (HSGPA). A variety of techniques, both graphical and statistical, were used to examine if it is possible to improve on the linear regression model. The results…

Calibration transfer of a Raman spectroscopic quantification method for the assessment of liquid detergent compositions from at-line laboratory to in-line industrial scale.

PubMed

Brouckaert, D; Uyttersprot, J-S; Broeckx, W; De Beer, T

2018-03-01

Calibration transfer or standardisation aims at creating a uniform spectral response on different spectroscopic instruments or under varying conditions, without requiring a full recalibration for each situation. In the current study, this strategy is applied to construct at-line multivariate calibration models and consequently employ them in-line in a continuous industrial production line, using the same spectrometer. Firstly, quantitative multivariate models are constructed at-line at laboratory scale for predicting the concentration of two main ingredients in hard surface cleaners. By regressing the Raman spectra of a set of small-scale calibration samples against their reference concentration values, partial least squares (PLS) models are developed to quantify the surfactant levels in the liquid detergent compositions under investigation. After evaluating the models performance with a set of independent validation samples, a univariate slope/bias correction is applied in view of transporting these at-line calibration models to an in-line manufacturing set-up. This standardisation technique allows a fast and easy transfer of the PLS regression models, by simply correcting the model predictions on the in-line set-up, without adjusting anything to the original multivariate calibration models. An extensive statistical analysis is performed in order to assess the predictive quality of the transferred regression models. Before and after transfer, the R 2 and RMSEP of both models is compared for evaluating if their magnitude is similar. T-tests are then performed to investigate whether the slope and intercept of the transferred regression line are not statistically different from 1 and 0, respectively. Furthermore, it is inspected whether no significant bias can be noted. F-tests are executed as well, for assessing the linearity of the transfer regression line and for investigating the statistical coincidence of the transfer and validation regression line. Finally, a paired t-test is performed to compare the original at-line model to the slope/bias corrected in-line model, using interval hypotheses. It is shown that the calibration models of Surfactant 1 and Surfactant 2 yield satisfactory in-line predictions after slope/bias correction. While Surfactant 1 passes seven out of eight statistical tests, the recommended validation parameters are 100% successful for Surfactant 2. It is hence concluded that the proposed strategy for transferring at-line calibration models to an in-line industrial environment via a univariate slope/bias correction of the predicted values offers a successful standardisation approach. Copyright © 2017 Elsevier B.V. All rights reserved.

INTRODUCTION TO A COMBINED MULTIPLE LINEAR REGRESSION AND ARMA MODELING APPROACH FOR BEACH BACTERIA PREDICTION

EPA Science Inventory

Due to the complexity of the processes contributing to beach bacteria concentrations, many researchers rely on statistical modeling, among which multiple linear regression (MLR) modeling is most widely used. Despite its ease of use and interpretation, there may be time dependence...

Predicting Plywood Properties with Wood-based Composite Models

Treesearch

Christopher Adam Senalik; Robert J. Ross

2015-01-01

Previous research revealed that stress wave nondestructive testing techniques could be used to evaluate the tensile and flexural properties of wood-based composite materials. Regression models were developed that related stress wave transmission characteristics (velocity and attenuation) to modulus of elasticity and strength. The developed regression models accounted...

Linear and nonlinear models for predicting fish bioconcentration factors for pesticides.

PubMed

Yuan, Jintao; Xie, Chun; Zhang, Ting; Sun, Jinfang; Yuan, Xuejie; Yu, Shuling; Zhang, Yingbiao; Cao, Yunyuan; Yu, Xingchen; Yang, Xuan; Yao, Wu

2016-08-01

This work is devoted to the applications of the multiple linear regression (MLR), multilayer perceptron neural network (MLP NN) and projection pursuit regression (PPR) to quantitative structure-property relationship analysis of bioconcentration factors (BCFs) of pesticides tested on Bluegill (Lepomis macrochirus). Molecular descriptors of a total of 107 pesticides were calculated with the DRAGON Software and selected by inverse enhanced replacement method. Based on the selected DRAGON descriptors, a linear model was built by MLR, nonlinear models were developed using MLP NN and PPR. The robustness of the obtained models was assessed by cross-validation and external validation using test set. Outliers were also examined and deleted to improve predictive power. Comparative results revealed that PPR achieved the most accurate predictions. This study offers useful models and information for BCF prediction, risk assessment, and pesticide formulation. Copyright © 2016 Elsevier Ltd. All rights reserved.

Area under the curve predictions of dalbavancin, a new lipoglycopeptide agent, using the end of intravenous infusion concentration data point by regression analyses such as linear, log-linear and power models.

PubMed

Bhamidipati, Ravi Kanth; Syed, Muzeeb; Mullangi, Ramesh; Srinivas, Nuggehally

2018-02-01

1. Dalbavancin, a lipoglycopeptide, is approved for treating gram-positive bacterial infections. Area under plasma concentration versus time curve (AUC inf ) of dalbavancin is a key parameter and AUC inf /MIC ratio is a critical pharmacodynamic marker. 2. Using end of intravenous infusion concentration (i.e. C max ) C max versus AUC inf relationship for dalbavancin was established by regression analyses (i.e. linear, log-log, log-linear and power models) using 21 pairs of subject data. 3. The predictions of the AUC inf were performed using published C max data by application of regression equations. The quotient of observed/predicted values rendered fold difference. The mean absolute error (MAE)/root mean square error (RMSE) and correlation coefficient (r) were used in the assessment. 4. MAE and RMSE values for the various models were comparable. The C max versus AUC inf exhibited excellent correlation (r > 0.9488). The internal data evaluation showed narrow confinement (0.84-1.14-fold difference) with a RMSE < 10.3%. The external data evaluation showed that the models predicted AUC inf with a RMSE of 3.02-27.46% with fold difference largely contained within 0.64-1.48. 5. Regardless of the regression models, a single time point strategy of using C max (i.e. end of 30-min infusion) is amenable as a prospective tool for predicting AUC inf of dalbavancin in patients.

Role of subdural electrocorticography in prediction of long-term seizure outcome in epilepsy surgery

PubMed Central

Juhász, Csaba; Shah, Aashit; Sood, Sandeep; Chugani, Harry T.

2009-01-01

Since prediction of long-term seizure outcome using preoperative diagnostic modalities remains suboptimal in epilepsy surgery, we evaluated whether interictal spike frequency measures obtained from extraoperative subdural electrocorticography (ECoG) recording could predict long-term seizure outcome. This study included 61 young patients (age 0.4–23.0 years), who underwent extraoperative ECoG recording prior to cortical resection for alleviation of uncontrolled focal seizures. Patient age, frequency of preoperative seizures, neuroimaging findings, ictal and interictal ECoG measures were preoperatively obtained. The seizure outcome was prospectively measured [follow-up period: 2.5–6.4 years (mean 4.6 years)]. Univariate and multivariate logistic regression analyses determined how well preoperative demographic and diagnostic measures predicted long-term seizure outcome. Following the initial cortical resection, Engel Class I, II, III and IV outcomes were noted in 35, 6, 12 and 7 patients, respectively. One child died due to disseminated intravascular coagulation associated with pseudomonas sepsis 2 days after surgery. Univariate regression analyses revealed that incomplete removal of seizure onset zone, higher interictal spike-frequency in the preserved cortex and incomplete removal of cortical abnormalities on neuroimaging were associated with a greater risk of failing to obtain Class I outcome. Multivariate logistic regression analysis revealed that incomplete removal of seizure onset zone was the only independent predictor of failure to obtain Class I outcome. The goodness of regression model fit and the predictive ability of regression model were greatest in the full regression model incorporating both ictal and interictal measures [R2 0.44; Area under the receiver operating characteristic (ROC) curve: 0.81], slightly smaller in the reduced model incorporating ictal but not interictal measures (R2 0.40; Area under the ROC curve: 0.79) and slightly smaller again in the reduced model incorporating interictal but not ictal measures (R2 0.27; Area under the ROC curve: 0.77). Seizure onset zone and interictal spike frequency measures on subdural ECoG recording may both be useful in predicting the long-term seizure outcome of epilepsy surgery. Yet, the additive clinical impact of interictal spike frequency measures to predict long-term surgical outcome may be modest in the presence of ictal ECoG and neuroimaging data. PMID:19286694

Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

PubMed

Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

2003-01-01

Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

Macrocell path loss prediction using artificial intelligence techniques

NASA Astrophysics Data System (ADS)

Usman, Abraham U.; Okereke, Okpo U.; Omizegba, Elijah E.

2014-04-01

The prediction of propagation loss is a practical non-linear function approximation problem which linear regression or auto-regression models are limited in their ability to handle. However, some computational Intelligence techniques such as artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFISs) have been shown to have great ability to handle non-linear function approximation and prediction problems. In this study, the multiple layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN) and an ANFIS network were trained using actual signal strength measurement taken at certain suburban areas of Bauchi metropolis, Nigeria. The trained networks were then used to predict propagation losses at the stated areas under differing conditions. The predictions were compared with the prediction accuracy of the popular Hata model. It was observed that ANFIS model gave a better fit in all cases having higher R2 values in each case and on average is more robust than MLP and RBF models as it generalises better to a different data.

Analysis of the Influence of Quantile Regression Model on Mainland Tourists' Service Satisfaction Performance

PubMed Central

Wang, Wen-Cheng; Cho, Wen-Chien; Chen, Yin-Jen

2014-01-01

It is estimated that mainland Chinese tourists travelling to Taiwan can bring annual revenues of 400 billion NTD to the Taiwan economy. Thus, how the Taiwanese Government formulates relevant measures to satisfy both sides is the focus of most concern. Taiwan must improve the facilities and service quality of its tourism industry so as to attract more mainland tourists. This paper conducted a questionnaire survey of mainland tourists and used grey relational analysis in grey mathematics to analyze the satisfaction performance of all satisfaction question items. The first eight satisfaction items were used as independent variables, and the overall satisfaction performance was used as a dependent variable for quantile regression model analysis to discuss the relationship between the dependent variable under different quantiles and independent variables. Finally, this study further discussed the predictive accuracy of the least mean regression model and each quantile regression model, as a reference for research personnel. The analysis results showed that other variables could also affect the overall satisfaction performance of mainland tourists, in addition to occupation and age. The overall predictive accuracy of quantile regression model Q0.25 was higher than that of the other three models. PMID:24574916

Analysis of the influence of quantile regression model on mainland tourists' service satisfaction performance.

PubMed

Wang, Wen-Cheng; Cho, Wen-Chien; Chen, Yin-Jen

2014-01-01

It is estimated that mainland Chinese tourists travelling to Taiwan can bring annual revenues of 400 billion NTD to the Taiwan economy. Thus, how the Taiwanese Government formulates relevant measures to satisfy both sides is the focus of most concern. Taiwan must improve the facilities and service quality of its tourism industry so as to attract more mainland tourists. This paper conducted a questionnaire survey of mainland tourists and used grey relational analysis in grey mathematics to analyze the satisfaction performance of all satisfaction question items. The first eight satisfaction items were used as independent variables, and the overall satisfaction performance was used as a dependent variable for quantile regression model analysis to discuss the relationship between the dependent variable under different quantiles and independent variables. Finally, this study further discussed the predictive accuracy of the least mean regression model and each quantile regression model, as a reference for research personnel. The analysis results showed that other variables could also affect the overall satisfaction performance of mainland tourists, in addition to occupation and age. The overall predictive accuracy of quantile regression model Q0.25 was higher than that of the other three models.

Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards.

PubMed

Churpek, Matthew M; Yuen, Trevor C; Winslow, Christopher; Meltzer, David O; Kattan, Michael W; Edelson, Dana P

2016-02-01

Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. Observational cohort study. Five hospitals, from November 2008 until January 2013. Hospitalized ward patients None Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]). In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.

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.

Intranasal Pharmacokinetic Data for Triptans Such as Sumatriptan and Zolmitriptan Can Render Area Under the Curve (AUC) Predictions for the Oral Route: Strategy Development and Application.

PubMed

Srinivas, Nuggehally R; Syed, Muzeeb

2016-01-01

Limited pharmacokinetic sampling strategy may be useful for predicting the area under the curve (AUC) for triptans and may have clinical utility as a prospective tool for prediction. Using appropriate intranasal pharmacokinetic data, a Cmax vs. AUC relationship was established by linear regression models for sumatriptan and zolmitriptan. The predictions of the AUC values were performed using published mean/median Cmax data and appropriate regression lines. The quotient of observed and predicted values rendered fold-difference calculation. The mean absolute error (MAE), mean positive error (MPE), mean negative error (MNE), root mean square error (RMSE), correlation coefficient (r), and the goodness of the AUC fold prediction were used to evaluate the two triptans. Also, data from the mean concentration profiles at time points of 1 hour (sumatriptan) and 3 hours (zolmitriptan) were used for the AUC prediction. The Cmax vs. AUC models displayed excellent correlation for both sumatriptan (r = .9997; P < .001) and zolmitriptan (r = .9999; P < .001). Irrespective of the two triptans, the majority of the predicted AUCs (83%-85%) were within 0.76-1.25-fold difference using the regression model. The prediction of AUC values for sumatriptan or zolmitriptan using the concentration data that reflected the Tmax occurrence were in the proximity of the reported values. In summary, the Cmax vs. AUC models exhibited strong correlations for sumatriptan and zolmitriptan. The usefulness of the prediction of the AUC values was established by a rigorous statistical approach.

Independent variable complexity for regional regression of the flow duration curve in ungauged basins

NASA Astrophysics Data System (ADS)

Fouad, Geoffrey; Skupin, André; Hope, Allen

2016-04-01

The flow duration curve (FDC) is one of the most widely used tools to quantify streamflow. Its percentile flows are often required for water resource applications, but these values must be predicted for ungauged basins with insufficient or no streamflow data. Regional regression is a commonly used approach for predicting percentile flows that involves identifying hydrologic regions and calibrating regression models to each region. The independent variables used to describe the physiographic and climatic setting of the basins are a critical component of regional regression, yet few studies have investigated their effect on resulting predictions. In this study, the complexity of the independent variables needed for regional regression is investigated. Different levels of variable complexity are applied for a regional regression consisting of 918 basins in the US. Both the hydrologic regions and regression models are determined according to the different sets of variables, and the accuracy of resulting predictions is assessed. The different sets of variables include (1) a simple set of three variables strongly tied to the FDC (mean annual precipitation, potential evapotranspiration, and baseflow index), (2) a traditional set of variables describing the average physiographic and climatic conditions of the basins, and (3) a more complex set of variables extending the traditional variables to include statistics describing the distribution of physiographic data and temporal components of climatic data. The latter set of variables is not typically used in regional regression, and is evaluated for its potential to predict percentile flows. The simplest set of only three variables performed similarly to the other more complex sets of variables. Traditional variables used to describe climate, topography, and soil offered little more to the predictions, and the experimental set of variables describing the distribution of basin data in more detail did not improve predictions. These results are largely reflective of cross-correlation existing in hydrologic datasets, and highlight the limited predictive power of many traditionally used variables for regional regression. A parsimonious approach including fewer variables chosen based on their connection to streamflow may be more efficient than a data mining approach including many different variables. Future regional regression studies may benefit from having a hydrologic rationale for including different variables and attempting to create new variables related to streamflow.

Statistical Power for a Simultaneous Test of Factorial and Predictive Invariance

ERIC Educational Resources Information Center

Olivera-Aguilar, Margarita; Millsap, Roger E.

2013-01-01

A common finding in studies of differential prediction across groups is that although regression slopes are the same or similar across groups, group differences exist in regression intercepts. Building on earlier work by Birnbaum (1979), Millsap (1998) presented an invariant factor model that would explain such intercept differences as arising due…

Predicting heavy metal concentrations in soils and plants using field spectrophotometry

NASA Astrophysics Data System (ADS)

Muradyan, V.; Tepanosyan, G.; Asmaryan, Sh.; Sahakyan, L.; Saghatelyan, A.; Warner, T. A.

2017-09-01

Aim of this study is to predict heavy metal (HM) concentrations in soils and plants using field remote sensing methods. The studied sites were an industrial town of Kajaran and city of Yerevan. The research also included sampling of soils and leaves of two tree species exposed to different pollution levels and determination of contents of HM in lab conditions. The obtained spectral values were then collated with contents of HM in Kajaran soils and the tree leaves sampled in Yerevan, and statistical analysis was done. Consequently, Zn and Pb have a negative correlation coefficient (p <0.01) in a 2498 nm spectral range for soils. Pb has a significantly higher correlation at red edge for plants. A regression models and artificial neural network (ANN) for HM prediction were developed. Good results were obtained for the best stress sensitive spectral band ANN (R2 0.9, RPD 2.0), Simple Linear Regression (SLR) and Partial Least Squares Regression (PLSR) (R2 0.7, RPD 1.4) models. Multiple Linear Regression (MLR) model was not applicable to predict Pb and Zn concentrations in soils in this research. Almost all full spectrum PLS models provide good calibration and validation results (RPD>1.4). Full spectrum ANN models are characterized by excellent calibration R2, rRMSE and RPD (0.9; 0.1 and >2.5 respectively). For prediction of Pb and Ni contents in plants SLR and PLS models were used. The latter provide almost the same results. Our findings indicate that it is possible to make coarse direct estimation of HM content in soils and plants using rapid and economic reflectance spectroscopy.

Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

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

Yahya, Noorazrul, E-mail: noorazrul.yahya@research.uwa.edu.au; Ebert, Martin A.; Bulsara, Max

Purpose: Given the paucity of available data concerning radiotherapy-induced urinary toxicity, it is important to ensure derivation of the most robust models with superior predictive performance. This work explores multiple statistical-learning strategies for prediction of urinary symptoms following external beam radiotherapy of the prostate. Methods: The performance of logistic regression, elastic-net, support-vector machine, random forest, neural network, and multivariate adaptive regression splines (MARS) to predict urinary symptoms was analyzed using data from 754 participants accrued by TROG03.04-RADAR. Predictive features included dose-surface data, comorbidities, and medication-intake. Four symptoms were analyzed: dysuria, haematuria, incontinence, and frequency, each with three definitions (grade ≥more » 1, grade ≥ 2 and longitudinal) with event rate between 2.3% and 76.1%. Repeated cross-validations producing matched models were implemented. A synthetic minority oversampling technique was utilized in endpoints with rare events. Parameter optimization was performed on the training data. Area under the receiver operating characteristic curve (AUROC) was used to compare performance using sample size to detect differences of ≥0.05 at the 95% confidence level. Results: Logistic regression, elastic-net, random forest, MARS, and support-vector machine were the highest-performing statistical-learning strategies in 3, 3, 3, 2, and 1 endpoints, respectively. Logistic regression, MARS, elastic-net, random forest, neural network, and support-vector machine were the best, or were not significantly worse than the best, in 7, 7, 5, 5, 3, and 1 endpoints. The best-performing statistical model was for dysuria grade ≥ 1 with AUROC ± standard deviation of 0.649 ± 0.074 using MARS. For longitudinal frequency and dysuria grade ≥ 1, all strategies produced AUROC>0.6 while all haematuria endpoints and longitudinal incontinence models produced AUROC<0.6. Conclusions: Logistic regression and MARS were most likely to be the best-performing strategy for the prediction of urinary symptoms with elastic-net and random forest producing competitive results. The predictive power of the models was modest and endpoint-dependent. New features, including spatial dose maps, may be necessary to achieve better models.« less

Weather variability and the incidence of cryptosporidiosis: comparison of time series poisson regression and SARIMA models.

PubMed

Hu, Wenbiao; Tong, Shilu; Mengersen, Kerrie; Connell, Des

2007-09-01

Few studies have examined the relationship between weather variables and cryptosporidiosis in Australia. This paper examines the potential impact of weather variability on the transmission of cryptosporidiosis and explores the possibility of developing an empirical forecast system. Data on weather variables, notified cryptosporidiosis cases, and population size in Brisbane were supplied by the Australian Bureau of Meteorology, Queensland Department of Health, and Australian Bureau of Statistics for the period of January 1, 1996-December 31, 2004, respectively. Time series Poisson regression and seasonal auto-regression integrated moving average (SARIMA) models were performed to examine the potential impact of weather variability on the transmission of cryptosporidiosis. Both the time series Poisson regression and SARIMA models show that seasonal and monthly maximum temperature at a prior moving average of 1 and 3 months were significantly associated with cryptosporidiosis disease. It suggests that there may be 50 more cases a year for an increase of 1 degrees C maximum temperature on average in Brisbane. Model assessments indicated that the SARIMA model had better predictive ability than the Poisson regression model (SARIMA: root mean square error (RMSE): 0.40, Akaike information criterion (AIC): -12.53; Poisson regression: RMSE: 0.54, AIC: -2.84). Furthermore, the analysis of residuals shows that the time series Poisson regression appeared to violate a modeling assumption, in that residual autocorrelation persisted. The results of this study suggest that weather variability (particularly maximum temperature) may have played a significant role in the transmission of cryptosporidiosis. A SARIMA model may be a better predictive model than a Poisson regression model in the assessment of the relationship between weather variability and the incidence of cryptosporidiosis.

Gaussian Process Regression (GPR) Representation in Predictive Model Markup Language (PMML)

PubMed Central

Lechevalier, D.; Ak, R.; Ferguson, M.; Law, K. H.; Lee, Y.-T. T.; Rachuri, S.

2017-01-01

This paper describes Gaussian process regression (GPR) models presented in predictive model markup language (PMML). PMML is an extensible-markup-language (XML) -based standard language used to represent data-mining and predictive analytic models, as well as pre- and post-processed data. The previous PMML version, PMML 4.2, did not provide capabilities for representing probabilistic (stochastic) machine-learning algorithms that are widely used for constructing predictive models taking the associated uncertainties into consideration. The newly released PMML version 4.3, which includes the GPR model, provides new features: confidence bounds and distribution for the predictive estimations. Both features are needed to establish the foundation for uncertainty quantification analysis. Among various probabilistic machine-learning algorithms, GPR has been widely used for approximating a target function because of its capability of representing complex input and output relationships without predefining a set of basis functions, and predicting a target output with uncertainty quantification. GPR is being employed to various manufacturing data-analytics applications, which necessitates representing this model in a standardized form for easy and rapid employment. In this paper, we present a GPR model and its representation in PMML. Furthermore, we demonstrate a prototype using a real data set in the manufacturing domain. PMID:29202125

Gaussian Process Regression (GPR) Representation in Predictive Model Markup Language (PMML).

PubMed

Park, J; Lechevalier, D; Ak, R; Ferguson, M; Law, K H; Lee, Y-T T; Rachuri, S

2017-01-01

This paper describes Gaussian process regression (GPR) models presented in predictive model markup language (PMML). PMML is an extensible-markup-language (XML) -based standard language used to represent data-mining and predictive analytic models, as well as pre- and post-processed data. The previous PMML version, PMML 4.2, did not provide capabilities for representing probabilistic (stochastic) machine-learning algorithms that are widely used for constructing predictive models taking the associated uncertainties into consideration. The newly released PMML version 4.3, which includes the GPR model, provides new features: confidence bounds and distribution for the predictive estimations. Both features are needed to establish the foundation for uncertainty quantification analysis. Among various probabilistic machine-learning algorithms, GPR has been widely used for approximating a target function because of its capability of representing complex input and output relationships without predefining a set of basis functions, and predicting a target output with uncertainty quantification. GPR is being employed to various manufacturing data-analytics applications, which necessitates representing this model in a standardized form for easy and rapid employment. In this paper, we present a GPR model and its representation in PMML. Furthermore, we demonstrate a prototype using a real data set in the manufacturing domain.

The use of quantile regression to forecast higher than expected respiratory deaths in a daily time series: a study of New York City data 1987-2000.

PubMed

Soyiri, Ireneous N; Reidpath, Daniel D

2013-01-01

Forecasting higher than expected numbers of health events provides potentially valuable insights in its own right, and may contribute to health services management and syndromic surveillance. This study investigates the use of quantile regression to predict higher than expected respiratory deaths. Data taken from 70,830 deaths occurring in New York were used. Temporal, weather and air quality measures were fitted using quantile regression at the 90th-percentile with half the data (in-sample). Four QR models were fitted: an unconditional model predicting the 90th-percentile of deaths (Model 1), a seasonal/temporal (Model 2), a seasonal, temporal plus lags of weather and air quality (Model 3), and a seasonal, temporal model with 7-day moving averages of weather and air quality. Models were cross-validated with the out of sample data. Performance was measured as proportionate reduction in weighted sum of absolute deviations by a conditional, over unconditional models; i.e., the coefficient of determination (R1). The coefficient of determination showed an improvement over the unconditional model between 0.16 and 0.19. The greatest improvement in predictive and forecasting accuracy of daily mortality was associated with the inclusion of seasonal and temporal predictors (Model 2). No gains were made in the predictive models with the addition of weather and air quality predictors (Models 3 and 4). However, forecasting models that included weather and air quality predictors performed slightly better than the seasonal and temporal model alone (i.e., Model 3 > Model 4 > Model 2) This study provided a new approach to predict higher than expected numbers of respiratory related-deaths. The approach, while promising, has limitations and should be treated at this stage as a proof of concept.

The Use of Quantile Regression to Forecast Higher Than Expected Respiratory Deaths in a Daily Time Series: A Study of New York City Data 1987-2000

PubMed Central

Soyiri, Ireneous N.; Reidpath, Daniel D.

2013-01-01

Forecasting higher than expected numbers of health events provides potentially valuable insights in its own right, and may contribute to health services management and syndromic surveillance. This study investigates the use of quantile regression to predict higher than expected respiratory deaths. Data taken from 70,830 deaths occurring in New York were used. Temporal, weather and air quality measures were fitted using quantile regression at the 90th-percentile with half the data (in-sample). Four QR models were fitted: an unconditional model predicting the 90th-percentile of deaths (Model 1), a seasonal / temporal (Model 2), a seasonal, temporal plus lags of weather and air quality (Model 3), and a seasonal, temporal model with 7-day moving averages of weather and air quality. Models were cross-validated with the out of sample data. Performance was measured as proportionate reduction in weighted sum of absolute deviations by a conditional, over unconditional models; i.e., the coefficient of determination (R1). The coefficient of determination showed an improvement over the unconditional model between 0.16 and 0.19. The greatest improvement in predictive and forecasting accuracy of daily mortality was associated with the inclusion of seasonal and temporal predictors (Model 2). No gains were made in the predictive models with the addition of weather and air quality predictors (Models 3 and 4). However, forecasting models that included weather and air quality predictors performed slightly better than the seasonal and temporal model alone (i.e., Model 3 > Model 4 > Model 2) This study provided a new approach to predict higher than expected numbers of respiratory related-deaths. The approach, while promising, has limitations and should be treated at this stage as a proof of concept. PMID:24147122

Improvement of Storm Forecasts Using Gridded Bayesian Linear Regression for Northeast United States

NASA Astrophysics Data System (ADS)

Yang, J.; Astitha, M.; Schwartz, C. S.

2017-12-01

Bayesian linear regression (BLR) is a post-processing technique in which regression coefficients are derived and used to correct raw forecasts based on pairs of observation-model values. This study presents the development and application of a gridded Bayesian linear regression (GBLR) as a new post-processing technique to improve numerical weather prediction (NWP) of rain and wind storm forecasts over northeast United States. Ten controlled variables produced from ten ensemble members of the National Center for Atmospheric Research (NCAR) real-time prediction system are used for a GBLR model. In the GBLR framework, leave-one-storm-out cross-validation is utilized to study the performances of the post-processing technique in a database composed of 92 storms. To estimate the regression coefficients of the GBLR, optimization procedures that minimize the systematic and random error of predicted atmospheric variables (wind speed, precipitation, etc.) are implemented for the modeled-observed pairs of training storms. The regression coefficients calculated for meteorological stations of the National Weather Service are interpolated back to the model domain. An analysis of forecast improvements based on error reductions during the storms will demonstrate the value of GBLR approach. This presentation will also illustrate how the variances are optimized for the training partition in GBLR and discuss the verification strategy for grid points where no observations are available. The new post-processing technique is successful in improving wind speed and precipitation storm forecasts using past event-based data and has the potential to be implemented in real-time.

A multimodel approach to interannual and seasonal prediction of Danube discharge anomalies

NASA Astrophysics Data System (ADS)

Rimbu, Norel; Ionita, Monica; Patrut, Simona; Dima, Mihai

2010-05-01

Interannual and seasonal predictability of Danube river discharge is investigated using three model types: 1) time series models 2) linear regression models of discharge with large-scale climate mode indices and 3) models based on stable teleconnections. All models are calibrated using discharge and climatic data for the period 1901-1977 and validated for the period 1978-2008 . Various time series models, like autoregressive (AR), moving average (MA), autoregressive and moving average (ARMA) or singular spectrum analysis and autoregressive moving average (SSA+ARMA) models have been calibrated and their skills evaluated. The best results were obtained using SSA+ARMA models. SSA+ARMA models proved to have the highest forecast skill also for other European rivers (Gamiz-Fortis et al. 2008). Multiple linear regression models using large-scale climatic mode indices as predictors have a higher forecast skill than the time series models. The best predictors for Danube discharge are the North Atlantic Oscillation (NAO) and the East Atlantic/Western Russia patterns during winter and spring. Other patterns, like Polar/Eurasian or Tropical Northern Hemisphere (TNH) are good predictors for summer and autumn discharge. Based on stable teleconnection approach (Ionita et al. 2008) we construct prediction models through a combination of sea surface temperature (SST), temperature (T) and precipitation (PP) from the regions where discharge and SST, T and PP variations are stable correlated. Forecast skills of these models are higher than forecast skills of the time series and multiple regression models. The models calibrated and validated in our study can be used for operational prediction of interannual and seasonal Danube discharge anomalies. References Gamiz-Fortis, S., D. Pozo-Vazquez, R.M. Trigo, and Y. Castro-Diez, Quantifying the predictability of winter river flow in Iberia. Part I: intearannual predictability. J. Climate, 2484-2501, 2008. Gamiz-Fortis, S., D. Pozo-Vazquez, R.M. Trigo, and Y. Castro-Diez, Quantifying the predictability of winter river flow in Iberia. Part II: seasonal predictability. J. Climate, 2503-2518, 2008. Ionita, M., G. Lohmann, and N. Rimbu, Prediction of spring Elbe river discharge based on stable teleconnections with global temperature and precipitation. J. Climate. 6215-6226, 2008.

Identification of the prediction model for dengue incidence in Can Tho city, a Mekong Delta area in Vietnam.

PubMed

Phung, Dung; Huang, Cunrui; Rutherford, Shannon; Chu, Cordia; Wang, Xiaoming; Nguyen, Minh; Nguyen, Nga Huy; Manh, Cuong Do

2015-01-01

The Mekong Delta is highly vulnerable to climate change and a dengue endemic area in Vietnam. This study aims to examine the association between climate factors and dengue incidence and to identify the best climate prediction model for dengue incidence in Can Tho city, the Mekong Delta area in Vietnam. We used three different regression models comprising: standard multiple regression model (SMR), seasonal autoregressive integrated moving average model (SARIMA), and Poisson distributed lag model (PDLM) to examine the association between climate factors and dengue incidence over the period 2003-2010. We validated the models by forecasting dengue cases for the period of January-December, 2011 using the mean absolute percentage error (MAPE). Receiver operating characteristics curves were used to analyze the sensitivity of the forecast of a dengue outbreak. The results indicate that temperature and relative humidity are significantly associated with changes in dengue incidence consistently across the model methods used, but not cumulative rainfall. The Poisson distributed lag model (PDLM) performs the best prediction of dengue incidence for a 6, 9, and 12-month period and diagnosis of an outbreak however the SARIMA model performs a better prediction of dengue incidence for a 3-month period. The simple or standard multiple regression performed highly imprecise prediction of dengue incidence. We recommend a follow-up study to validate the model on a larger scale in the Mekong Delta region and to analyze the possibility of incorporating a climate-based dengue early warning method into the national dengue surveillance system. Copyright © 2014 Elsevier B.V. All rights reserved.

Comparing machine learning and logistic regression methods for predicting hypertension using a combination of gene expression and next-generation sequencing data.

PubMed

Held, Elizabeth; Cape, Joshua; Tintle, Nathan

2016-01-01

Machine learning methods continue to show promise in the analysis of data from genetic association studies because of the high number of variables relative to the number of observations. However, few best practices exist for the application of these methods. We extend a recently proposed supervised machine learning approach for predicting disease risk by genotypes to be able to incorporate gene expression data and rare variants. We then apply 2 different versions of the approach (radial and linear support vector machines) to simulated data from Genetic Analysis Workshop 19 and compare performance to logistic regression. Method performance was not radically different across the 3 methods, although the linear support vector machine tended to show small gains in predictive ability relative to a radial support vector machine and logistic regression. Importantly, as the number of genes in the models was increased, even when those genes contained causal rare variants, model predictive ability showed a statistically significant decrease in performance for both the radial support vector machine and logistic regression. The linear support vector machine showed more robust performance to the inclusion of additional genes. Further work is needed to evaluate machine learning approaches on larger samples and to evaluate the relative improvement in model prediction from the incorporation of gene expression data.

Determination of riverbank erosion probability using Locally Weighted Logistic Regression

NASA Astrophysics Data System (ADS)

Ioannidou, Elena; Flori, Aikaterini; Varouchakis, Emmanouil A.; Giannakis, Georgios; Vozinaki, Anthi Eirini K.; Karatzas, George P.; Nikolaidis, Nikolaos

2015-04-01

Riverbank erosion is a natural geomorphologic process that affects the fluvial environment. The most important issue concerning riverbank erosion is the identification of the vulnerable locations. An alternative to the usual hydrodynamic models to predict vulnerable locations is to quantify the probability of erosion occurrence. This can be achieved by identifying the underlying relations between riverbank erosion and the geomorphological or hydrological variables that prevent or stimulate erosion. Thus, riverbank erosion can be determined by a regression model using independent variables that are considered to affect the erosion process. The impact of such variables may vary spatially, therefore, a non-stationary regression model is preferred instead of a stationary equivalent. Locally Weighted Regression (LWR) is proposed as a suitable choice. This method can be extended to predict the binary presence or absence of erosion based on a series of independent local variables by using the logistic regression model. It is referred to as Locally Weighted Logistic Regression (LWLR). Logistic regression is a type of regression analysis used for predicting the outcome of a categorical dependent variable (e.g. binary response) based on one or more predictor variables. The method can be combined with LWR to assign weights to local independent variables of the dependent one. LWR allows model parameters to vary over space in order to reflect spatial heterogeneity. The probabilities of the possible outcomes are modelled as a function of the independent variables using a logistic function. Logistic regression measures the relationship between a categorical dependent variable and, usually, one or several continuous independent variables by converting the dependent variable to probability scores. Then, a logistic regression is formed, which predicts success or failure of a given binary variable (e.g. erosion presence or absence) for any value of the independent variables. The erosion occurrence probability can be calculated in conjunction with the model deviance regarding the independent variables tested. The most straightforward measure for goodness of fit is the G statistic. It is a simple and effective way to study and evaluate the Logistic Regression model efficiency and the reliability of each independent variable. The developed statistical model is applied to the Koiliaris River Basin on the island of Crete, Greece. Two datasets of river bank slope, river cross-section width and indications of erosion were available for the analysis (12 and 8 locations). Two different types of spatial dependence functions, exponential and tricubic, were examined to determine the local spatial dependence of the independent variables at the measurement locations. The results show a significant improvement when the tricubic function is applied as the erosion probability is accurately predicted at all eight validation locations. Results for the model deviance show that cross-section width is more important than bank slope in the estimation of erosion probability along the Koiliaris riverbanks. The proposed statistical model is a useful tool that quantifies the erosion probability along the riverbanks and can be used to assist managing erosion and flooding events. Acknowledgements This work is part of an on-going THALES project (CYBERSENSORS - High Frequency Monitoring System for Integrated Water Resources Management of Rivers). The project has been co-financed by the European Union (European Social Fund - ESF) and Greek national funds through the Operational Program "Education and Lifelong Learning" of the National Strategic Reference Framework (NSRF) - Research Funding Program: THALES. Investing in knowledge society through the European Social Fund.

Robust functional regression model for marginal mean and subject-specific inferences.

PubMed

Cao, Chunzheng; Shi, Jian Qing; Lee, Youngjo

2017-01-01

We introduce flexible robust functional regression models, using various heavy-tailed processes, including a Student t-process. We propose efficient algorithms in estimating parameters for the marginal mean inferences and in predicting conditional means as well as interpolation and extrapolation for the subject-specific inferences. We develop bootstrap prediction intervals (PIs) for conditional mean curves. Numerical studies show that the proposed model provides a robust approach against data contamination or distribution misspecification, and the proposed PIs maintain the nominal confidence levels. A real data application is presented as an illustrative example.

Modern modeling techniques had limited external validity in predicting mortality from traumatic brain injury.

PubMed

van der Ploeg, Tjeerd; Nieboer, Daan; Steyerberg, Ewout W

2016-10-01

Prediction of medical outcomes may potentially benefit from using modern statistical modeling techniques. We aimed to externally validate modeling strategies for prediction of 6-month mortality of patients suffering from traumatic brain injury (TBI) with predictor sets of increasing complexity. We analyzed individual patient data from 15 different studies including 11,026 TBI patients. We consecutively considered a core set of predictors (age, motor score, and pupillary reactivity), an extended set with computed tomography scan characteristics, and a further extension with two laboratory measurements (glucose and hemoglobin). With each of these sets, we predicted 6-month mortality using default settings with five statistical modeling techniques: logistic regression (LR), classification and regression trees, random forests (RFs), support vector machines (SVM) and neural nets. For external validation, a model developed on one of the 15 data sets was applied to each of the 14 remaining sets. This process was repeated 15 times for a total of 630 validations. The area under the receiver operating characteristic curve (AUC) was used to assess the discriminative ability of the models. For the most complex predictor set, the LR models performed best (median validated AUC value, 0.757), followed by RF and support vector machine models (median validated AUC value, 0.735 and 0.732, respectively). With each predictor set, the classification and regression trees models showed poor performance (median validated AUC value, <0.7). The variability in performance across the studies was smallest for the RF- and LR-based models (inter quartile range for validated AUC values from 0.07 to 0.10). In the area of predicting mortality from TBI, nonlinear and nonadditive effects are not pronounced enough to make modern prediction methods beneficial. Copyright © 2016 Elsevier Inc. All rights reserved.

[Prediction of total nitrogen and alkali hydrolysable nitrogen content in loess using hyperspectral data based on correlation analysis and partial least squares regression].

PubMed

Liu, Xiu-ying; Wang, Li; Chang, Qing-rui; Wang, Xiao-xing; Shang, Yan

2015-07-01

Wuqi County of Shaanxi Province, where the vegetation recovering measures have been carried out for years, was taken as the study area. A total of 100 loess samples from 24 different profiles were collected. Total nitrogen (TN) and alkali hydrolysable nitrogen (AHN) contents of the soil samples were analyzed, and the soil samples were scanned in the visible/near-infrared (VNIR) region of 350-2500 nm in the laboratory. The calibration models were developed between TN and AHN contents and VNIR values based on correlation analysis (CA) and partial least squares regression (PLS). Independent samples validated the calibration models. The results indicated that the optimum model for predicting TN of loess was established by using first derivative of reflectance. The best model for predicting AHN of loess was established by using normal derivative spectra. The optimum TN model could effectively predict TN in loess from 0 to 40 cm, but the optimum AHN model could only roughly predict AHN at the same depth. This study provided a good method for rapidly predicting TN of loess where vegetation recovering measures have been adopted, but prediction of AHN needs to be further studied.

A combined M5P tree and hazard-based duration model for predicting urban freeway traffic accident durations.

PubMed

Lin, Lei; Wang, Qian; Sadek, Adel W

2016-06-01

The duration of freeway traffic accidents duration is an important factor, which affects traffic congestion, environmental pollution, and secondary accidents. Among previous studies, the M5P algorithm has been shown to be an effective tool for predicting incident duration. M5P builds a tree-based model, like the traditional classification and regression tree (CART) method, but with multiple linear regression models as its leaves. The problem with M5P for accident duration prediction, however, is that whereas linear regression assumes that the conditional distribution of accident durations is normally distributed, the distribution for a "time-to-an-event" is almost certainly nonsymmetrical. A hazard-based duration model (HBDM) is a better choice for this kind of a "time-to-event" modeling scenario, and given this, HBDMs have been previously applied to analyze and predict traffic accidents duration. Previous research, however, has not yet applied HBDMs for accident duration prediction, in association with clustering or classification of the dataset to minimize data heterogeneity. The current paper proposes a novel approach for accident duration prediction, which improves on the original M5P tree algorithm through the construction of a M5P-HBDM model, in which the leaves of the M5P tree model are HBDMs instead of linear regression models. Such a model offers the advantage of minimizing data heterogeneity through dataset classification, and avoids the need for the incorrect assumption of normality for traffic accident durations. The proposed model was then tested on two freeway accident datasets. For each dataset, the first 500 records were used to train the following three models: (1) an M5P tree; (2) a HBDM; and (3) the proposed M5P-HBDM, and the remainder of data were used for testing. The results show that the proposed M5P-HBDM managed to identify more significant and meaningful variables than either M5P or HBDMs. Moreover, the M5P-HBDM had the lowest overall mean absolute percentage error (MAPE). Copyright © 2016 Elsevier Ltd. All rights reserved.

Modeling the probability of giving birth at health institutions among pregnant women attending antenatal care in West Shewa Zone, Oromia, Ethiopia: a cross sectional study.

PubMed

Dida, Nagasa; Birhanu, Zewdie; Gerbaba, Mulusew; Tilahun, Dejen; Morankar, Sudhakar

2014-06-01

Although ante natal care and institutional delivery is effective means for reducing maternal morbidity and mortality, the probability of giving birth at health institutions among ante natal care attendants has not been modeled in Ethiopia. Therefore, the objective of this study was to model predictors of giving birth at health institutions among expectant mothers following antenatal care. Facility based cross sectional study design was conducted among 322 consecutively selected mothers who were following ante natal care in two districts of West Shewa Zone, Oromia Regional State, Ethiopia. Participants were proportionally recruited from six health institutions. The data were analyzed using SPSS version 17.0. Multivariable logistic regression was employed to develop the prediction model. The final regression model had good discrimination power (89.2%), optimum sensitivity (89.0%) and specificity (80.0%) to predict the probability of giving birth at health institutions. Accordingly, self efficacy (beta=0.41), perceived barrier (beta=-0.31) and perceived susceptibility (beta=0.29) were significantly predicted the probability of giving birth at health institutions. The present study showed that logistic regression model has predicted the probability of giving birth at health institutions and identified significant predictors which health care providers should take into account in promotion of institutional delivery.

A New Approach of Juvenile Age Estimation using Measurements of the Ilium and Multivariate Adaptive Regression Splines (MARS) Models for Better Age Prediction.

PubMed

Corron, Louise; Marchal, François; Condemi, Silvana; Chaumoître, Kathia; Adalian, Pascal

2017-01-01

Juvenile age estimation methods used in forensic anthropology generally lack methodological consistency and/or statistical validity. Considering this, a standard approach using nonparametric Multivariate Adaptive Regression Splines (MARS) models were tested to predict age from iliac biometric variables of male and female juveniles from Marseilles, France, aged 0-12 years. Models using unidimensional (length and width) and bidimensional iliac data (module and surface) were constructed on a training sample of 176 individuals and validated on an independent test sample of 68 individuals. Results show that MARS prediction models using iliac width, module and area give overall better and statistically valid age estimates. These models integrate punctual nonlinearities of the relationship between age and osteometric variables. By constructing valid prediction intervals whose size increases with age, MARS models take into account the normal increase of individual variability. MARS models can qualify as a practical and standardized approach for juvenile age estimation. © 2016 American Academy of Forensic Sciences.

Prediction model for the return to work of workers with injuries in Hong Kong.

PubMed

Xu, Yanwen; Chan, Chetwyn C H; Lo, Karen Hui Yu-Ling; Tang, Dan

2008-01-01

This study attempts to formulate a prediction model of return to work for a group of workers who have been suffering from chronic pain and physical injury while also being out of work in Hong Kong. The study used Case-based Reasoning (CBR) method, and compared the result with the statistical method of logistic regression model. The database of the algorithm of CBR was composed of 67 cases who were also used in the logistic regression model. The testing cases were 32 participants who had a similar background and characteristics to those in the database. The methods of setting constraints and Euclidean distance metric were used in CBR to search the closest cases to the trial case based on the matrix. The usefulness of the algorithm was tested on 32 new participants, and the accuracy of predicting return to work outcomes was 62.5%, which was no better than the 71.2% accuracy derived from the logistic regression model. The results of the study would enable us to have a better understanding of the CBR applied in the field of occupational rehabilitation by comparing with the conventional regression analysis. The findings would also shed light on the development of relevant interventions for the return-to-work process of these workers.

[Establishment of the prediction model for ischemic cardiovascular disease of elderly male population under current health care program].

PubMed

Chen, Jin-hong; Wu, Hai-yun; He, Kun-lun; He, Yao; Qin, Yin-he

2010-10-01

To establish and verify the prediction model for ischemic cardiovascular disease (ICVD) among the elderly population who were under the current health care programs. Statistical analysis on data from physical examination, hospitalization of the past years, from questionnaire and telephone interview was carried out in May, 2003. Data was from a hospital which implementing a health care program. Baseline population with a proportion of 4:1 was randomly selected to generate both module group and verification group. Baseline data was induced to make the verification group into regression model of module group and to generate the predictive value. Distinguished ability with area under ROC curve and the predictive veracity were verified through comparing the predictive incidence rate and actual incidence rate of every deciles group by Hosmer-Lemeshow test. Predictive veracity of the prediction model at population level was verified through comparing the predictive 6-year incidence rates of ICVD with actual 6-year accumulative incidence rates of ICVD with error rate calculated. The samples included 2271 males over the age of 65 with 1817 people for modeling population and 454 for verified population. All of the samples were stratified into two layers to establish hierarchical Cox proportional hazard regression model, including one advanced age group (greater than or equal to 75 years old), and another elderly group (less than 75 years old). Data from the statically analysis showed that the risk factors in aged group were age, systolic blood pressure, serum creatinine level, fasting blood glucose level, while protective factor was high density lipoprotein;in advanced age group, the risk factors were body weight index, systolic blood pressure, serum total cholesterol level, serum creatinine level, fasting blood glucose level, while protective factor was HDL-C. The area under the ROC curve (AUC) and 95%CI were 0.723 and 0.687 - 0.759 respectively. Discriminating power was good. All individual predictive ICVD cumulative incidence and actual incidence were analyzed using Hosmer-Lemeshow test, χ(2) = 1.43, P = 0.786, showing that the predictive veracity was good. The stratified Cox Hazards Regression model was used to establish prediction model of the aged male population under a certain health care program. The common prediction factor of the two age groups were: systolic blood pressure, serum creatinine level, fasting blood glucose level and HDL-C. The area under the ROC curve of the verification group was 0.723, showing that the distinguished ability was good and the predict ability at the individual level and at the group level were also satisfactory. It was feasible to using Cox Proportional Hazards Regression Model for predicting the population groups.

A Prediction Model for Community Colleges Using Graduation Rate as the Performance Indicator

ERIC Educational Resources Information Center

Moosai, Susan

2010-01-01

In this thesis a prediction model using graduation rate as the performance indicator is obtained for community colleges for three cohort years, 2003, 2004, and 2005 in the states of California, Florida, and Michigan. Multiple Regression analysis, using an aggregate of seven predictor variables, was employed in determining this prediction model.…

A way forward for fire-caused tree mortality prediction: Modeling a physiological consequence of fire

Treesearch

Kathleen L. Kavanaugh; Matthew B. Dickinson; Anthony S. Bova

2010-01-01

Current operational methods for predicting tree mortality from fire injury are regression-based models that only indirectly consider underlying causes and, thus, have limited generality. A better understanding of the physiological consequences of tree heating and injury are needed to develop biophysical process models that can make predictions under changing or novel...

Linearity versus Nonlinearity of Offspring-Parent Regression: An Experimental Study of Drosophila Melanogaster

PubMed Central

Gimelfarb, A.; Willis, J. H.

1994-01-01

An experiment was conducted to investigate the offspring-parent regression for three quantitative traits (weight, abdominal bristles and wing length) in Drosophila melanogaster. Linear and polynomial models were fitted for the regressions of a character in offspring on both parents. It is demonstrated that responses by the characters to selection predicted by the nonlinear regressions may differ substantially from those predicted by the linear regressions. This is true even, and especially, if selection is weak. The realized heritability for a character under selection is shown to be determined not only by the offspring-parent regression but also by the distribution of the character and by the form and strength of selection. PMID:7828818

A new computational strategy for predicting essential genes.

PubMed

Cheng, Jian; Wu, Wenwu; Zhang, Yinwen; Li, Xiangchen; Jiang, Xiaoqian; Wei, Gehong; Tao, Shiheng

2013-12-21

Determination of the minimum gene set for cellular life is one of the central goals in biology. Genome-wide essential gene identification has progressed rapidly in certain bacterial species; however, it remains difficult to achieve in most eukaryotic species. Several computational models have recently been developed to integrate gene features and used as alternatives to transfer gene essentiality annotations between organisms. We first collected features that were widely used by previous predictive models and assessed the relationships between gene features and gene essentiality using a stepwise regression model. We found two issues that could significantly reduce model accuracy: (i) the effect of multicollinearity among gene features and (ii) the diverse and even contrasting correlations between gene features and gene essentiality existing within and among different species. To address these issues, we developed a novel model called feature-based weighted Naïve Bayes model (FWM), which is based on Naïve Bayes classifiers, logistic regression, and genetic algorithm. The proposed model assesses features and filters out the effects of multicollinearity and diversity. The performance of FWM was compared with other popular models, such as support vector machine, Naïve Bayes model, and logistic regression model, by applying FWM to reciprocally predict essential genes among and within 21 species. Our results showed that FWM significantly improves the accuracy and robustness of essential gene prediction. FWM can remarkably improve the accuracy of essential gene prediction and may be used as an alternative method for other classification work. This method can contribute substantially to the knowledge of the minimum gene sets required for living organisms and the discovery of new drug targets.

Modelling Nitrogen Oxides in Los Angeles Using a Hybrid Dispersion/Land Use Regression Model

NASA Astrophysics Data System (ADS)

Wilton, Darren C.

The goal of this dissertation is to develop models capable of predicting long term annual average NOx concentrations in urban areas. Predictions from simple meteorological dispersion models and seasonal proxies for NO2 oxidation were included as covariates in a land use regression (LUR) model for NOx in Los Angeles, CA. The NO x measurements were obtained from a comprehensive measurement campaign that is part of the Multi-Ethnic Study of Atherosclerosis Air Pollution Study (MESA Air). Simple land use regression models were initially developed using a suite of GIS-derived land use variables developed from various buffer sizes (R²=0.15). Caline3, a simple steady-state Gaussian line source model, was initially incorporated into the land-use regression framework. The addition of this spatio-temporally varying Caline3 covariate improved the simple LUR model predictions. The extent of improvement was much more pronounced for models based solely on the summer measurements (simple LUR: R²=0.45; Caline3/LUR: R²=0.70), than it was for models based on all seasons (R²=0.20). We then used a Lagrangian dispersion model to convert static land use covariates for population density, commercial/industrial area into spatially and temporally varying covariates. The inclusion of these covariates resulted in significant improvement in model prediction (R²=0.57). In addition to the dispersion model covariates described above, a two-week average value of daily peak-hour ozone was included as a surrogate of the oxidation of NO2 during the different sampling periods. This additional covariate further improved overall model performance for all models. The best model by 10-fold cross validation (R²=0.73) contained the Caline3 prediction, a static covariate for length of A3 roads within 50 meters, the Calpuff-adjusted covariates derived from both population density and industrial/commercial land area, and the ozone covariate. This model was tested against annual average NOx concentrations from an independent data set from the EPA's Air Quality System (AQS) and MESA Air fixed site monitors, and performed very well (R²=0.82).

Comparison of Logistic Regression and Artificial Neural Network in Low Back Pain Prediction: Second National Health Survey

PubMed Central

Parsaeian, M; Mohammad, K; Mahmoudi, M; Zeraati, H

2012-01-01

Background: The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Methods: Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. Results: The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Conclusions: Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant. PMID:23113198

Comparison of logistic regression and artificial neural network in low back pain prediction: second national health survey.

PubMed

Parsaeian, M; Mohammad, K; Mahmoudi, M; Zeraati, H

2012-01-01

The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant.

A statistical method for predicting seizure onset zones from human single-neuron recordings

NASA Astrophysics Data System (ADS)

Valdez, André B.; Hickman, Erin N.; Treiman, David M.; Smith, Kris A.; Steinmetz, Peter N.

2013-02-01

Objective. Clinicians often use depth-electrode recordings to localize human epileptogenic foci. To advance the diagnostic value of these recordings, we applied logistic regression models to single-neuron recordings from depth-electrode microwires to predict seizure onset zones (SOZs). Approach. We collected data from 17 epilepsy patients at the Barrow Neurological Institute and developed logistic regression models to calculate the odds of observing SOZs in the hippocampus, amygdala and ventromedial prefrontal cortex, based on statistics such as the burst interspike interval (ISI). Main results. Analysis of these models showed that, for a single-unit increase in burst ISI ratio, the left hippocampus was approximately 12 times more likely to contain a SOZ; and the right amygdala, 14.5 times more likely. Our models were most accurate for the hippocampus bilaterally (at 85% average sensitivity), and performance was comparable with current diagnostics such as electroencephalography. Significance. Logistic regression models can be combined with single-neuron recording to predict likely SOZs in epilepsy patients being evaluated for resective surgery, providing an automated source of clinically useful information.

Evaluating penalized logistic regression models to predict Heat-Related Electric grid stress days

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

Bramer, L. M.; Rounds, J.; Burleyson, C. D.

Understanding the conditions associated with stress on the electricity grid is important in the development of contingency plans for maintaining reliability during periods when the grid is stressed. In this paper, heat-related grid stress and the relationship with weather conditions is examined using data from the eastern United States. Penalized logistic regression models were developed and applied to predict stress on the electric grid using weather data. The inclusion of other weather variables, such as precipitation, in addition to temperature improved model performance. Several candidate models and datasets were examined. A penalized logistic regression model fit at the operation-zone levelmore » was found to provide predictive value and interpretability. Additionally, the importance of different weather variables observed at different time scales were examined. Maximum temperature and precipitation were identified as important across all zones while the importance of other weather variables was zone specific. The methods presented in this work are extensible to other regions and can be used to aid in planning and development of the electrical grid.« less

Comparing spatial regression to random forests for large ...

EPA Pesticide Factsheets

Environmental data may be “large” due to number of records, number of covariates, or both. Random forests has a reputation for good predictive performance when using many covariates, whereas spatial regression, when using reduced rank methods, has a reputation for good predictive performance when using many records. In this study, we compare these two techniques using a data set containing the macroinvertebrate multimetric index (MMI) at 1859 stream sites with over 200 landscape covariates. Our primary goal is predicting MMI at over 1.1 million perennial stream reaches across the USA. For spatial regression modeling, we develop two new methods to accommodate large data: (1) a procedure that estimates optimal Box-Cox transformations to linearize covariate relationships; and (2) a computationally efficient covariate selection routine that takes into account spatial autocorrelation. We show that our new methods lead to cross-validated performance similar to random forests, but that there is an advantage for spatial regression when quantifying the uncertainty of the predictions. Simulations are used to clarify advantages for each method. This research investigates different approaches for modeling and mapping national stream condition. We use MMI data from the EPA's National Rivers and Streams Assessment and predictors from StreamCat (Hill et al., 2015). Previous studies have focused on modeling the MMI condition classes (i.e., good, fair, and po

Predicting location of recurrence using FDG, FLT, and Cu-ATSM PET in canine sinonasal tumors treated with radiotherapy

NASA Astrophysics Data System (ADS)

Bradshaw, Tyler; Fu, Rau; Bowen, Stephen; Zhu, Jun; Forrest, Lisa; Jeraj, Robert

2015-07-01

Dose painting relies on the ability of functional imaging to identify resistant tumor subvolumes to be targeted for additional boosting. This work assessed the ability of FDG, FLT, and Cu-ATSM PET imaging to predict the locations of residual FDG PET in canine tumors following radiotherapy. Nineteen canines with spontaneous sinonasal tumors underwent PET/CT imaging with radiotracers FDG, FLT, and Cu-ATSM prior to hypofractionated radiotherapy. Therapy consisted of 10 fractions of 4.2 Gy to the sinonasal cavity with or without an integrated boost of 0.8 Gy to the GTV. Patients had an additional FLT PET/CT scan after fraction 2, a Cu-ATSM PET/CT scan after fraction 3, and follow-up FDG PET/CT scans after radiotherapy. Following image registration, simple and multiple linear and logistic voxel regressions were performed to assess how well pre- and mid-treatment PET imaging predicted post-treatment FDG uptake. R2 and pseudo R2 were used to assess the goodness of fits. For simple linear regression models, regression coefficients for all pre- and mid-treatment PET images were significantly positive across the population (P < 0.05). However, there was large variability among patients in goodness of fits: R2 ranged from 0.00 to 0.85, with a median of 0.12. Results for logistic regression models were similar. Multiple linear regression models resulted in better fits (median R2 = 0.31), but there was still large variability between patients in R2. The R2 from regression models for different predictor variables were highly correlated across patients (R ≈ 0.8), indicating tumors that were poorly predicted with one tracer were also poorly predicted by other tracers. In conclusion, the high inter-patient variability in goodness of fits indicates that PET was able to predict locations of residual tumor in some patients, but not others. This suggests not all patients would be good candidates for dose painting based on a single biological target.

Predicting location of recurrence using FDG, FLT, and Cu-ATSM PET in canine sinonasal tumors treated with radiotherapy.

PubMed

Bradshaw, Tyler; Fu, Rau; Bowen, Stephen; Zhu, Jun; Forrest, Lisa; Jeraj, Robert

2015-07-07

Dose painting relies on the ability of functional imaging to identify resistant tumor subvolumes to be targeted for additional boosting. This work assessed the ability of FDG, FLT, and Cu-ATSM PET imaging to predict the locations of residual FDG PET in canine tumors following radiotherapy. Nineteen canines with spontaneous sinonasal tumors underwent PET/CT imaging with radiotracers FDG, FLT, and Cu-ATSM prior to hypofractionated radiotherapy. Therapy consisted of 10 fractions of 4.2 Gy to the sinonasal cavity with or without an integrated boost of 0.8 Gy to the GTV. Patients had an additional FLT PET/CT scan after fraction 2, a Cu-ATSM PET/CT scan after fraction 3, and follow-up FDG PET/CT scans after radiotherapy. Following image registration, simple and multiple linear and logistic voxel regressions were performed to assess how well pre- and mid-treatment PET imaging predicted post-treatment FDG uptake. R(2) and pseudo R(2) were used to assess the goodness of fits. For simple linear regression models, regression coefficients for all pre- and mid-treatment PET images were significantly positive across the population (P < 0.05). However, there was large variability among patients in goodness of fits: R(2) ranged from 0.00 to 0.85, with a median of 0.12. Results for logistic regression models were similar. Multiple linear regression models resulted in better fits (median R(2) = 0.31), but there was still large variability between patients in R(2). The R(2) from regression models for different predictor variables were highly correlated across patients (R ≈ 0.8), indicating tumors that were poorly predicted with one tracer were also poorly predicted by other tracers. In conclusion, the high inter-patient variability in goodness of fits indicates that PET was able to predict locations of residual tumor in some patients, but not others. This suggests not all patients would be good candidates for dose painting based on a single biological target.

A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy

NASA Astrophysics Data System (ADS)

Boucher, Thomas F.; Ozanne, Marie V.; Carmosino, Marco L.; Dyar, M. Darby; Mahadevan, Sridhar; Breves, Elly A.; Lepore, Kate H.; Clegg, Samuel M.

2015-05-01

The ChemCam instrument on the Mars Curiosity rover is generating thousands of LIBS spectra and bringing interest in this technique to public attention. The key to interpreting Mars or any other types of LIBS data are calibrations that relate laboratory standards to unknowns examined in other settings and enable predictions of chemical composition. Here, LIBS spectral data are analyzed using linear regression methods including partial least squares (PLS-1 and PLS-2), principal component regression (PCR), least absolute shrinkage and selection operator (lasso), elastic net, and linear support vector regression (SVR-Lin). These were compared against results from nonlinear regression methods including kernel principal component regression (K-PCR), polynomial kernel support vector regression (SVR-Py) and k-nearest neighbor (kNN) regression to discern the most effective models for interpreting chemical abundances from LIBS spectra of geological samples. The results were evaluated for 100 samples analyzed with 50 laser pulses at each of five locations averaged together. Wilcoxon signed-rank tests were employed to evaluate the statistical significance of differences among the nine models using their predicted residual sum of squares (PRESS) to make comparisons. For MgO, SiO2, Fe2O3, CaO, and MnO, the sparse models outperform all the others except for linear SVR, while for Na2O, K2O, TiO2, and P2O5, the sparse methods produce inferior results, likely because their emission lines in this energy range have lower transition probabilities. The strong performance of the sparse methods in this study suggests that use of dimensionality-reduction techniques as a preprocessing step may improve the performance of the linear models. Nonlinear methods tend to overfit the data and predict less accurately, while the linear methods proved to be more generalizable with better predictive performance. These results are attributed to the high dimensionality of the data (6144 channels) relative to the small number of samples studied. The best-performing models were SVR-Lin for SiO2, MgO, Fe2O3, and Na2O, lasso for Al2O3, elastic net for MnO, and PLS-1 for CaO, TiO2, and K2O. Although these differences in model performance between methods were identified, most of the models produce comparable results when p ≤ 0.05 and all techniques except kNN produced statistically-indistinguishable results. It is likely that a combination of models could be used together to yield a lower total error of prediction, depending on the requirements of the user.

Correlation of sensory bitterness in dairy protein hydrolysates: Comparison of prediction models built using sensory, chromatographic and electronic tongue data.

PubMed

Newman, J; Egan, T; Harbourne, N; O'Riordan, D; Jacquier, J C; O'Sullivan, M

2014-08-01

Sensory evaluation can be problematic for ingredients with a bitter taste during research and development phase of new food products. In this study, 19 dairy protein hydrolysates (DPH) were analysed by an electronic tongue and their physicochemical characteristics, the data obtained from these methods were correlated with their bitterness intensity as scored by a trained sensory panel and each model was also assessed by its predictive capabilities. The physiochemical characteristics of the DPHs investigated were degree of hydrolysis (DH%), and data relating to peptide size and relative hydrophobicity from size exclusion chromatography (SEC) and reverse phase (RP) HPLC. Partial least square regression (PLS) was used to construct the prediction models. All PLS regressions had good correlations (0.78 to 0.93) with the strongest being the combination of data obtained from SEC and RP HPLC. However, the PLS with the strongest predictive power was based on the e-tongue which had the PLS regression with the lowest root mean predicted residual error sum of squares (PRESS) in the study. The results show that the PLS models constructed with the e-tongue and the combination of SEC and RP-HPLC has potential to be used for prediction of bitterness and thus reducing the reliance on sensory analysis in DPHs for future food research. Copyright © 2014 Elsevier B.V. All rights reserved.

The implementation of rare events logistic regression to predict the distribution of mesophotic hard corals across the main Hawaiian Islands.

PubMed

Veazey, Lindsay M; Franklin, Erik C; Kelley, Christopher; Rooney, John; Frazer, L Neil; Toonen, Robert J

2016-01-01

Predictive habitat suitability models are powerful tools for cost-effective, statistically robust assessment of the environmental drivers of species distributions. The aim of this study was to develop predictive habitat suitability models for two genera of scleractinian corals (Leptoserisand Montipora) found within the mesophotic zone across the main Hawaiian Islands. The mesophotic zone (30-180 m) is challenging to reach, and therefore historically understudied, because it falls between the maximum limit of SCUBA divers and the minimum typical working depth of submersible vehicles. Here, we implement a logistic regression with rare events corrections to account for the scarcity of presence observations within the dataset. These corrections reduced the coefficient error and improved overall prediction success (73.6% and 74.3%) for both original regression models. The final models included depth, rugosity, slope, mean current velocity, and wave height as the best environmental covariates for predicting the occurrence of the two genera in the mesophotic zone. Using an objectively selected theta ("presence") threshold, the predicted presence probability values (average of 0.051 for Leptoseris and 0.040 for Montipora) were translated to spatially-explicit habitat suitability maps of the main Hawaiian Islands at 25 m grid cell resolution. Our maps are the first of their kind to use extant presence and absence data to examine the habitat preferences of these two dominant mesophotic coral genera across Hawai'i.

Predicting outcome in severe traumatic brain injury using a simple prognostic model.

PubMed

Sobuwa, Simpiwe; Hartzenberg, Henry Benjamin; Geduld, Heike; Uys, Corrie

2014-06-17

Several studies have made it possible to predict outcome in severe traumatic brain injury (TBI) making it beneficial as an aid for clinical decision-making in the emergency setting. However, reliable predictive models are lacking for resource-limited prehospital settings such as those in developing countries like South Africa. To develop a simple predictive model for severe TBI using clinical variables in a South African prehospital setting. All consecutive patients admitted at two level-one centres in Cape Town, South Africa, for severe TBI were included. A binary logistic regression model was used, which included three predictor variables: oxygen saturation (SpO₂), Glasgow Coma Scale (GCS) and pupil reactivity. The Glasgow Outcome Scale was used to assess outcome on hospital discharge. A total of 74.4% of the outcomes were correctly predicted by the logistic regression model. The model demonstrated SpO₂ (p=0.019), GCS (p=0.001) and pupil reactivity (p=0.002) as independently significant predictors of outcome in severe TBI. Odds ratios of a good outcome were 3.148 (SpO₂ ≥ 90%), 5.108 (GCS 6 - 8) and 4.405 (pupils bilaterally reactive). This model is potentially useful for effective predictions of outcome in severe TBI.

Potential habitat distribution for the freshwater diatom Didymosphenia geminata in the continental US

USGS Publications Warehouse

Kumar, S.; Spaulding, S.A.; Stohlgren, T.J.; Hermann, K.A.; Schmidt, T.S.; Bahls, L.L.

2009-01-01

The diatom Didymosphenia geminata is a single-celled alga found in lakes, streams, and rivers. Nuisance blooms of D geminata affect the diversity, abundance, and productivity of other aquatic organisms. Because D geminata can be transported by humans on waders and other gear, accurate spatial prediction of habitat suitability is urgently needed for early detection and rapid response, as well as for evaluation of monitoring and control programs. We compared four modeling methods to predict D geminata's habitat distribution; two methods use presence-absence data (logistic regression and classification and regression tree [CART]), and two involve presence data (maximum entropy model [Maxent] and genetic algorithm for rule-set production [GARP]). Using these methods, we evaluated spatially explicit, bioclimatic and environmental variables as predictors of diatom distribution. The Maxent model provided the most accurate predictions, followed by logistic regression, CART, and GARP. The most suitable habitats were predicted to occur in the western US, in relatively cool sites, and at high elevations with a high base-flow index. The results provide insights into the factors that affect the distribution of D geminata and a spatial basis for the prediction of nuisance blooms. ?? The Ecological Society of America.

A Model for Predicting Student Performance on High-Stakes Assessment

ERIC Educational Resources Information Center

Dammann, Matthew Walter

2010-01-01

This research study examined the use of student achievement on reading and math state assessments to predict success on the science state assessment. Multiple regression analysis was utilized to test the prediction for all students in grades 5 and 8 in a mid-Atlantic state. The prediction model developed from the analysis explored the combined…

Artificial Neural Networks: A New Approach to Predicting Application Behavior.

ERIC Educational Resources Information Center

Gonzalez, Julie M. Byers; DesJardins, Stephen L.

2002-01-01

Applied the technique of artificial neural networks to predict which students were likely to apply to one research university. Compared the results to the traditional analysis tool, logistic regression modeling. Found that the addition of artificial intelligence models was a useful new tool for predicting student application behavior. (EV)

Obtaining Predictions from Models Fit to Multiply Imputed Data

ERIC Educational Resources Information Center

Miles, Andrew

2016-01-01

Obtaining predictions from regression models fit to multiply imputed data can be challenging because treatments of multiple imputation seldom give clear guidance on how predictions can be calculated, and because available software often does not have built-in routines for performing the necessary calculations. This research note reviews how…

Soil sail content estimation in the yellow river delta with satellite hyperspectral data

USGS Publications Warehouse

Weng, Yongling; Gong, Peng; Zhu, Zhi-Liang

2008-01-01

Soil salinization is one of the most common land degradation processes and is a severe environmental hazard. The primary objective of this study is to investigate the potential of predicting salt content in soils with hyperspectral data acquired with EO-1 Hyperion. Both partial least-squares regression (PLSR) and conventional multiple linear regression (MLR), such as stepwise regression (SWR), were tested as the prediction model. PLSR is commonly used to overcome the problem caused by high-dimensional and correlated predictors. Chemical analysis of 95 samples collected from the top layer of soils in the Yellow River delta area shows that salt content was high on average, and the dominant chemicals in the saline soil were NaCl and MgCl2. Multivariate models were established between soil contents and hyperspectral data. Our results indicate that the PLSR technique with laboratory spectral data has a strong prediction capacity. Spectral bands at 1487-1527, 1971-1991, 2032-2092, and 2163-2355 nm possessed large absolute values of regression coefficients, with the largest coefficient at 2203 nm. We obtained a root mean squared error (RMSE) for calibration (with 61 samples) of RMSEC = 0.753 (R2 = 0.893) and a root mean squared error for validation (with 30 samples) of RMSEV = 0.574. The prediction model was applied on a pixel-by-pixel basis to a Hyperion reflectance image to yield a quantitative surface distribution map of soil salt content. The result was validated successfully from 38 sampling points. We obtained an RMSE estimate of 1.037 (R2 = 0.784) for the soil salt content map derived by the PLSR model. The salinity map derived from the SWR model shows that the predicted value is higher than the true value. These results demonstrate that the PLSR method is a more suitable technique than stepwise regression for quantitative estimation of soil salt content in a large area. ?? 2008 CASI.

SOME STATISTICAL ISSUES RELATED TO MULTIPLE LINEAR REGRESSION MODELING OF BEACH BACTERIA CONCENTRATIONS

EPA Science Inventory

As a fast and effective technique, the multiple linear regression (MLR) method has been widely used in modeling and prediction of beach bacteria concentrations. Among previous works on this subject, however, several issues were insufficiently or inconsistently addressed. Those is...

Temporal Synchronization Analysis for Improving Regression Modeling of Fecal Indicator Bacteria Levels

EPA Science Inventory

Multiple linear regression models are often used to predict levels of fecal indicator bacteria (FIB) in recreational swimming waters based on independent variables (IVs) such as meteorologic, hydrodynamic, and water-quality measures. The IVs used for these analyses are traditiona...

REGRESSION MODELS OF RESIDENTIAL EXPOSURE TO CHLORPYRIFOS AND DIAZINON

EPA Science Inventory

This study examines the ability of regression models to predict residential exposures to chlorpyrifos and diazinon, based on the information from the NHEXAS-AZ database. The robust method was used to generate "fill-in" values for samples that are below the detection l...

Modeling energy expenditure in children and adolescents using quantile regression

USDA-ARS?s Scientific Manuscript database

Advanced mathematical models have the potential to capture the complex metabolic and physiological processes that result in energy expenditure (EE). Study objective is to apply quantile regression (QR) to predict EE and determine quantile-dependent variation in covariate effects in nonobese and obes...

Support vector regression-guided unravelling: antioxidant capacity and quantitative structure-activity relationship predict reduction and promotion effects of flavonoids on acrylamide formation

PubMed Central

Huang, Mengmeng; Wei, Yan; Wang, Jun; Zhang, Yu

2016-01-01

We used the support vector regression (SVR) approach to predict and unravel reduction/promotion effect of characteristic flavonoids on the acrylamide formation under a low-moisture Maillard reaction system. Results demonstrated the reduction/promotion effects by flavonoids at addition levels of 1–10000 μmol/L. The maximal inhibition rates (51.7%, 68.8% and 26.1%) and promote rates (57.7%, 178.8% and 27.5%) caused by flavones, flavonols and isoflavones were observed at addition levels of 100 μmol/L and 10000 μmol/L, respectively. The reduction/promotion effects were closely related to the change of trolox equivalent antioxidant capacity (ΔTEAC) and well predicted by triple ΔTEAC measurements via SVR models (R: 0.633–0.900). Flavonols exhibit stronger effects on the acrylamide formation than flavones and isoflavones as well as their O-glycosides derivatives, which may be attributed to the number and position of phenolic and 3-enolic hydroxyls. The reduction/promotion effects were well predicted by using optimized quantitative structure-activity relationship (QSAR) descriptors and SVR models (R: 0.926–0.994). Compared to artificial neural network and multi-linear regression models, SVR models exhibited better fitting performance for both TEAC-dependent and QSAR descriptor-dependent predicting work. These observations demonstrated that the SVR models are competent for predicting our understanding on the future use of natural antioxidants for decreasing the acrylamide formation. PMID:27586851

Support vector regression-guided unravelling: antioxidant capacity and quantitative structure-activity relationship predict reduction and promotion effects of flavonoids on acrylamide formation

NASA Astrophysics Data System (ADS)

Huang, Mengmeng; Wei, Yan; Wang, Jun; Zhang, Yu

2016-09-01

We used the support vector regression (SVR) approach to predict and unravel reduction/promotion effect of characteristic flavonoids on the acrylamide formation under a low-moisture Maillard reaction system. Results demonstrated the reduction/promotion effects by flavonoids at addition levels of 1-10000 μmol/L. The maximal inhibition rates (51.7%, 68.8% and 26.1%) and promote rates (57.7%, 178.8% and 27.5%) caused by flavones, flavonols and isoflavones were observed at addition levels of 100 μmol/L and 10000 μmol/L, respectively. The reduction/promotion effects were closely related to the change of trolox equivalent antioxidant capacity (ΔTEAC) and well predicted by triple ΔTEAC measurements via SVR models (R: 0.633-0.900). Flavonols exhibit stronger effects on the acrylamide formation than flavones and isoflavones as well as their O-glycosides derivatives, which may be attributed to the number and position of phenolic and 3-enolic hydroxyls. The reduction/promotion effects were well predicted by using optimized quantitative structure-activity relationship (QSAR) descriptors and SVR models (R: 0.926-0.994). Compared to artificial neural network and multi-linear regression models, SVR models exhibited better fitting performance for both TEAC-dependent and QSAR descriptor-dependent predicting work. These observations demonstrated that the SVR models are competent for predicting our understanding on the future use of natural antioxidants for decreasing the acrylamide formation.

Test anxiety and academic performance in chiropractic students.

PubMed

Zhang, Niu; Henderson, Charles N R

2014-01-01

Objective : We assessed the level of students' test anxiety, and the relationship between test anxiety and academic performance. Methods : We recruited 166 third-quarter students. The Test Anxiety Inventory (TAI) was administered to all participants. Total scores from written examinations and objective structured clinical examinations (OSCEs) were used as response variables. Results : Multiple regression analysis shows that there was a modest, but statistically significant negative correlation between TAI scores and written exam scores, but not OSCE scores. Worry and emotionality were the best predictive models for written exam scores. Mean total anxiety and emotionality scores for females were significantly higher than those for males, but not worry scores. Conclusion : Moderate-to-high test anxiety was observed in 85% of the chiropractic students examined. However, total test anxiety, as measured by the TAI score, was a very weak predictive model for written exam performance. Multiple regression analysis demonstrated that replacing total anxiety (TAI) with worry and emotionality (TAI subscales) produces a much more effective predictive model of written exam performance. Sex, age, highest current academic degree, and ethnicity contributed little additional predictive power in either regression model. Moreover, TAI scores were not found to be statistically significant predictors of physical exam skill performance, as measured by OSCEs.

Analysis of Multivariate Experimental Data Using A Simplified Regression Model Search Algorithm

NASA Technical Reports Server (NTRS)

Ulbrich, Norbert Manfred

2013-01-01

A new regression model search algorithm was developed in 2011 that may be used to analyze both general multivariate experimental data sets and wind tunnel strain-gage balance calibration data. The new algorithm is a simplified version of a more complex search algorithm that was originally developed at the NASA Ames Balance Calibration Laboratory. The new algorithm has the advantage that it needs only about one tenth of the original algorithm's CPU time for the completion of a search. In addition, extensive testing showed that the prediction accuracy of math models obtained from the simplified algorithm is similar to the prediction accuracy of math models obtained from the original algorithm. The simplified algorithm, however, cannot guarantee that search constraints related to a set of statistical quality requirements are always satisfied in the optimized regression models. Therefore, the simplified search algorithm is not intended to replace the original search algorithm. Instead, it may be used to generate an alternate optimized regression model of experimental data whenever the application of the original search algorithm either fails or requires too much CPU time. Data from a machine calibration of NASA's MK40 force balance is used to illustrate the application of the new regression model search algorithm.

Predicting the occurrence of wildfires with binary structured additive regression models.

PubMed

Ríos-Pena, Laura; Kneib, Thomas; Cadarso-Suárez, Carmen; Marey-Pérez, Manuel

2017-02-01

Wildfires are one of the main environmental problems facing societies today, and in the case of Galicia (north-west Spain), they are the main cause of forest destruction. This paper used binary structured additive regression (STAR) for modelling the occurrence of wildfires in Galicia. Binary STAR models are a recent contribution to the classical logistic regression and binary generalized additive models. Their main advantage lies in their flexibility for modelling non-linear effects, while simultaneously incorporating spatial and temporal variables directly, thereby making it possible to reveal possible relationships among the variables considered. The results showed that the occurrence of wildfires depends on many covariates which display variable behaviour across space and time, and which largely determine the likelihood of ignition of a fire. The joint possibility of working on spatial scales with a resolution of 1 × 1 km cells and mapping predictions in a colour range makes STAR models a useful tool for plotting and predicting wildfire occurrence. Lastly, it will facilitate the development of fire behaviour models, which can be invaluable when it comes to drawing up fire-prevention and firefighting plans. Copyright © 2016 Elsevier Ltd. All rights reserved.

Performance Comparison of Systemic Inflammatory Response Syndrome with Logistic Regression Models to Predict Sepsis in Neonates

PubMed Central

Thakur, Jyoti; Pahuja, Sharvan Kumar; Pahuja, Roop

2017-01-01

In 2005, an international pediatric sepsis consensus conference defined systemic inflammatory response syndrome (SIRS) for children <18 years of age, but excluded premature infants. In 2012, Hofer et al. investigated the predictive power of SIRS for term neonates. In this paper, we examined the accuracy of SIRS in predicting sepsis in neonates, irrespective of their gestational age (i.e., pre-term, term, and post-term). We also created two prediction models, named Model A and Model B, using binary logistic regression. Both models performed better than SIRS. We also developed an android application so that physicians can easily use Model A and Model B in real-world scenarios. The sensitivity, specificity, positive likelihood ratio (PLR) and negative likelihood ratio (NLR) in cases of SIRS were 16.15%, 95.53%, 3.61, and 0.88, respectively, whereas they were 29.17%, 97.82%, 13.36, and 0.72, respectively, in the case of Model A, and 31.25%, 97.30%, 11.56, and 0.71, respectively, in the case of Model B. All models were significant with p < 0.001. PMID:29257099

Predicting recreational water quality advisories: A comparison of statistical methods

USGS Publications Warehouse

Brooks, Wesley R.; Corsi, Steven R.; Fienen, Michael N.; Carvin, Rebecca B.

2016-01-01

Epidemiological studies indicate that fecal indicator bacteria (FIB) in beach water are associated with illnesses among people having contact with the water. In order to mitigate public health impacts, many beaches are posted with an advisory when the concentration of FIB exceeds a beach action value. The most commonly used method of measuring FIB concentration takes 18–24 h before returning a result. In order to avoid the 24 h lag, it has become common to ”nowcast” the FIB concentration using statistical regressions on environmental surrogate variables. Most commonly, nowcast models are estimated using ordinary least squares regression, but other regression methods from the statistical and machine learning literature are sometimes used. This study compares 14 regression methods across 7 Wisconsin beaches to identify which consistently produces the most accurate predictions. A random forest model is identified as the most accurate, followed by multiple regression fit using the adaptive LASSO.

Basophile: Accurate Fragment Charge State Prediction Improves Peptide Identification Rates

DOE PAGES

Wang, Dong; Dasari, Surendra; Chambers, Matthew C.; ...

2013-03-07

In shotgun proteomics, database search algorithms rely on fragmentation models to predict fragment ions that should be observed for a given peptide sequence. The most widely used strategy (Naive model) is oversimplified, cleaving all peptide bonds with equal probability to produce fragments of all charges below that of the precursor ion. More accurate models, based on fragmentation simulation, are too computationally intensive for on-the-fly use in database search algorithms. We have created an ordinal-regression-based model called Basophile that takes fragment size and basic residue distribution into account when determining the charge retention during CID/higher-energy collision induced dissociation (HCD) of chargedmore » peptides. This model improves the accuracy of predictions by reducing the number of unnecessary fragments that are routinely predicted for highly-charged precursors. Basophile increased the identification rates by 26% (on average) over the Naive model, when analyzing triply-charged precursors from ion trap data. Basophile achieves simplicity and speed by solving the prediction problem with an ordinal regression equation, which can be incorporated into any database search software for shotgun proteomic identification.« less

Using partial least squares regression as a predictive tool in describing equine third metacarpal bone shape.

PubMed

Liley, Helen; Zhang, Ju; Firth, Elwyn; Fernandez, Justin; Besier, Thor

2017-11-01

Population variance in bone shape is an important consideration when applying the results of subject-specific computational models to a population. In this letter, we demonstrate the ability of partial least squares regression to provide an improved shape prediction of the equine third metacarpal epiphysis, using two easily obtained measurements.

CONTRIBUTION OF NUTRIENTS AND E. COLI TO SURFACE WATER CONDITION IN THE OZARKS I. USING PARTIAL LEAST SQUARES PREDICTIONS WHEN STANDARD REGRESSION ASSUMPTIONS ARE VIOLATED

EPA Science Inventory

We present here the application of PLS regression to predicting surface water total phosphorous, total ammonia and Escherichia coli from landscape metrics. The amount of variability in surface water constituents explained by each model reflects the composition of the contributi...

Using destination image to predict visitors' intention to revisit three Hudson River Valley, New York, communities

Treesearch

Rudy M. Schuster; Laura Sullivan; Duarte Morais; Diane Kuehn

2009-01-01

This analysis explores the differences in Affective and Cognitive Destination Image among three Hudson River Valley (New York) tourism communities. Multiple regressions were used with six dimensions of visitors' images to predict future intention to revisit. Two of the three regression models were significant. The only significantly contributing independent...

Scoring and staging systems using cox linear regression modeling and recursive partitioning.

PubMed

Lee, J W; Um, S H; Lee, J B; Mun, J; Cho, H

2006-01-01

Scoring and staging systems are used to determine the order and class of data according to predictors. Systems used for medical data, such as the Child-Turcotte-Pugh scoring and staging systems for ordering and classifying patients with liver disease, are often derived strictly from physicians' experience and intuition. We construct objective and data-based scoring/staging systems using statistical methods. We consider Cox linear regression modeling and recursive partitioning techniques for censored survival data. In particular, to obtain a target number of stages we propose cross-validation and amalgamation algorithms. We also propose an algorithm for constructing scoring and staging systems by integrating local Cox linear regression models into recursive partitioning, so that we can retain the merits of both methods such as superior predictive accuracy, ease of use, and detection of interactions between predictors. The staging system construction algorithms are compared by cross-validation evaluation of real data. The data-based cross-validation comparison shows that Cox linear regression modeling is somewhat better than recursive partitioning when there are only continuous predictors, while recursive partitioning is better when there are significant categorical predictors. The proposed local Cox linear recursive partitioning has better predictive accuracy than Cox linear modeling and simple recursive partitioning. This study indicates that integrating local linear modeling into recursive partitioning can significantly improve prediction accuracy in constructing scoring and staging systems.

A regression-kriging model for estimation of rainfall in the Laohahe basin

NASA Astrophysics Data System (ADS)

Wang, Hong; Ren, Li L.; Liu, Gao H.

2009-10-01

This paper presents a multivariate geostatistical algorithm called regression-kriging (RK) for predicting the spatial distribution of rainfall by incorporating five topographic/geographic factors of latitude, longitude, altitude, slope and aspect. The technique is illustrated using rainfall data collected at 52 rain gauges from the Laohahe basis in northeast China during 1986-2005 . Rainfall data from 44 stations were selected for modeling and the remaining 8 stations were used for model validation. To eliminate multicollinearity, the five explanatory factors were first transformed using factor analysis with three Principal Components (PCs) extracted. The rainfall data were then fitted using step-wise regression and residuals interpolated using SK. The regression coefficients were estimated by generalized least squares (GLS), which takes the spatial heteroskedasticity between rainfall and PCs into account. Finally, the rainfall prediction based on RK was compared with that predicted from ordinary kriging (OK) and ordinary least squares (OLS) multiple regression (MR). For correlated topographic factors are taken into account, RK improves the efficiency of predictions. RK achieved a lower relative root mean square error (RMSE) (44.67%) than MR (49.23%) and OK (73.60%) and a lower bias than MR and OK (23.82 versus 30.89 and 32.15 mm) for annual rainfall. It is much more effective for the wet season than for the dry season. RK is suitable for estimation of rainfall in areas where there are no stations nearby and where topography has a major influence on rainfall.

Conditional Density Estimation with HMM Based Support Vector Machines

NASA Astrophysics Data System (ADS)

Hu, Fasheng; Liu, Zhenqiu; Jia, Chunxin; Chen, Dechang

Conditional density estimation is very important in financial engineer, risk management, and other engineering computing problem. However, most regression models have a latent assumption that the probability density is a Gaussian distribution, which is not necessarily true in many real life applications. In this paper, we give a framework to estimate or predict the conditional density mixture dynamically. Through combining the Input-Output HMM with SVM regression together and building a SVM model in each state of the HMM, we can estimate a conditional density mixture instead of a single gaussian. With each SVM in each node, this model can be applied for not only regression but classifications as well. We applied this model to denoise the ECG data. The proposed method has the potential to apply to other time series such as stock market return predictions.

A Combination of Geographically Weighted Regression, Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping: A Case Study at Wanzhou in the Three Gorges Area, China

PubMed Central

Yu, Xianyu; Wang, Yi; Niu, Ruiqing; Hu, Youjian

2016-01-01

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%–19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides. PMID:27187430

A Combination of Geographically Weighted Regression, Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping: A Case Study at Wanzhou in the Three Gorges Area, China.

PubMed

Yu, Xianyu; Wang, Yi; Niu, Ruiqing; Hu, Youjian

2016-05-11

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%-19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides.

2012 Workplace and Gender Relations Survey of Reserve Component Members: Statistical Methodology Report

DTIC Science & Technology

2012-09-01

3,435 10,461 9.1 3.1 63 Unmarried with Children+ Unmarried without Children 439,495 0.01 10,350 43,870 10.1 2.2 64 Married with Children+ Married ...logistic regression model was used to predict the probability of eligibility for the survey (known eligibility vs . unknown eligibility). A second logistic...regression model was used to predict the probability of response among eligible sample members (complete response vs . non-response). CHAID (Chi

Prediction of random-regression coefficient for daily milk yield after 305 days in milk by using the regression-coefficient estimates from the first 305 days.

PubMed

Yamazaki, Takeshi; Takeda, Hisato; Hagiya, Koichi; Yamaguchi, Satoshi; Sasaki, Osamu

2018-03-13

Because lactation periods in dairy cows lengthen with increasing total milk production, it is important to predict individual productivities after 305 days in milk (DIM) to determine the optimal lactation period. We therefore examined whether the random regression (RR) coefficient from 306 to 450 DIM (M2) can be predicted from those during the first 305 DIM (M1) by using a random regression model. We analyzed test-day milk records from 85690 Holstein cows in their first lactations and 131727 cows in their later (second to fifth) lactations. Data in M1 and M2 were analyzed separately by using different single-trait RR animal models. We then performed a multiple regression analysis of the RR coefficients of M2 on those of M1 during the first and later lactations. The first-order Legendre polynomials were practical covariates of random regression for the milk yields of M2. All RR coefficients for the additive genetic (AG) effect and the intercept for the permanent environmental (PE) effect of M2 had moderate to strong correlations with the intercept for the AG effect of M1. The coefficients of determination for multiple regression of the combined intercepts for the AG and PE effects of M2 on the coefficients for the AG effect of M1 were moderate to high. The daily milk yields of M2 predicted by using the RR coefficients for the AG effect of M1 were highly correlated with those obtained by using the coefficients of M2. Milk production after 305 DIM can be predicted by using the RR coefficient estimates of the AG effect during the first 305 DIM.

Logistic Mixed Models to Investigate Implicit and Explicit Belief Tracking.

PubMed

Lages, Martin; Scheel, Anne

2016-01-01

We investigated the proposition of a two-systems Theory of Mind in adults' belief tracking. A sample of N = 45 participants predicted the choice of one of two opponent players after observing several rounds in an animated card game. Three matches of this card game were played and initial gaze direction on target and subsequent choice predictions were recorded for each belief task and participant. We conducted logistic regressions with mixed effects on the binary data and developed Bayesian logistic mixed models to infer implicit and explicit mentalizing in true belief and false belief tasks. Although logistic regressions with mixed effects predicted the data well a Bayesian logistic mixed model with latent task- and subject-specific parameters gave a better account of the data. As expected explicit choice predictions suggested a clear understanding of true and false beliefs (TB/FB). Surprisingly, however, model parameters for initial gaze direction also indicated belief tracking. We discuss why task-specific parameters for initial gaze directions are different from choice predictions yet reflect second-order perspective taking.

Predictive factors of early moderate/severe ovarian hyperstimulation syndrome in non-polycystic ovarian syndrome patients: a statistical model.

PubMed

Ashrafi, Mahnaz; Bahmanabadi, Akram; Akhond, Mohammad Reza; Arabipoor, Arezoo

2015-11-01

To evaluate demographic, medical history and clinical cycle characteristics of infertile non-polycystic ovary syndrome (NPCOS) women with the purpose of investigating their associations with the prevalence of moderate-to-severe OHSS. In this retrospective study, among 7073 in vitro fertilization and/or intracytoplasmic sperm injection (IVF/ICSI) cycles, 86 cases of NPCO patients who developed moderate-to-severe OHSS while being treated with IVF/ICSI cycles were analyzed during the period of January 2008 to December 2010 at Royan Institute. To review the OHSS risk factors, 172 NPCOS patients without developing OHSS, treated at the same period of time, were selected randomly by computer as control group. We used multiple logistic regression in a backward manner to build a prediction model. The regression analysis revealed that the variables, including age [odds ratio (OR) 0.9, confidence interval (CI) 0.81-0.99], antral follicles count (OR 4.3, CI 2.7-6.9), infertility cause (tubal factor, OR 11.5, CI 1.1-51.3), hypothyroidism (OR 3.8, CI 1.5-9.4) and positive history of ovarian surgery (OR 0.2, CI 0.05-0.9) were the most important predictors of OHSS. The regression model had an area under curve of 0.94, presenting an allowable discriminative performance that was equal with two strong predictive variables, including the number of follicles and serum estradiol level on human chorionic gonadotropin day. The predictive regression model based on primary characteristics of NPCOS patients had equal specificity in comparison with two mentioned strong predictive variables. Therefore, it may be beneficial to apply this model before the beginning of ovarian stimulation protocol.

Optimization of Regression Models of Experimental Data Using Confirmation Points

NASA Technical Reports Server (NTRS)

Ulbrich, N.

2010-01-01

A new search metric is discussed that may be used to better assess the predictive capability of different math term combinations during the optimization of a regression model of experimental data. The new search metric can be determined for each tested math term combination if the given experimental data set is split into two subsets. The first subset consists of data points that are only used to determine the coefficients of the regression model. The second subset consists of confirmation points that are exclusively used to test the regression model. The new search metric value is assigned after comparing two values that describe the quality of the fit of each subset. The first value is the standard deviation of the PRESS residuals of the data points. The second value is the standard deviation of the response residuals of the confirmation points. The greater of the two values is used as the new search metric value. This choice guarantees that both standard deviations are always less or equal to the value that is used during the optimization. Experimental data from the calibration of a wind tunnel strain-gage balance is used to illustrate the application of the new search metric. The new search metric ultimately generates an optimized regression model that was already tested at regression model independent confirmation points before it is ever used to predict an unknown response from a set of regressors.

Improved model of the retardance in citric acid coated ferrofluids using stepwise regression

NASA Astrophysics Data System (ADS)

Lin, J. F.; Qiu, X. R.

2017-06-01

Citric acid (CA) coated Fe3O4 ferrofluids (FFs) have been conducted for biomedical application. The magneto-optical retardance of CA coated FFs was measured by a Stokes polarimeter. Optimization and multiple regression of retardance in FFs were executed by Taguchi method and Microsoft Excel previously, and the F value of regression model was large enough. However, the model executed by Excel was not systematic. Instead we adopted the stepwise regression to model the retardance of CA coated FFs. From the results of stepwise regression by MATLAB, the developed model had highly predictable ability owing to F of 2.55897e+7 and correlation coefficient of one. The average absolute error of predicted retardances to measured retardances was just 0.0044%. Using the genetic algorithm (GA) in MATLAB, the optimized parametric combination was determined as [4.709 0.12 39.998 70.006] corresponding to the pH of suspension, molar ratio of CA to Fe3O4, CA volume, and coating temperature. The maximum retardance was found as 31.712°, close to that obtained by evolutionary solver in Excel and a relative error of -0.013%. Above all, the stepwise regression method was successfully used to model the retardance of CA coated FFs, and the maximum global retardance was determined by the use of GA.

Discriminating between adaptive and carcinogenic liver hypertrophy in rat studies using logistic ridge regression analysis of toxicogenomic data: The mode of action and predictive models

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

Liu, Shujie; Kawamoto, Taisuke; Morita, Osamu

Chemical exposure often results in liver hypertrophy in animal tests, characterized by increased liver weight, hepatocellular hypertrophy, and/or cell proliferation. While most of these changes are considered adaptive responses, there is concern that they may be associated with carcinogenesis. In this study, we have employed a toxicogenomic approach using a logistic ridge regression model to identify genes responsible for liver hypertrophy and hypertrophic hepatocarcinogenesis and to develop a predictive model for assessing hypertrophy-inducing compounds. Logistic regression models have previously been used in the quantification of epidemiological risk factors. DNA microarray data from the Toxicogenomics Project-Genomics Assisted Toxicity Evaluation System weremore » used to identify hypertrophy-related genes that are expressed differently in hypertrophy induced by carcinogens and non-carcinogens. Data were collected for 134 chemicals (72 non-hypertrophy-inducing chemicals, 27 hypertrophy-inducing non-carcinogenic chemicals, and 15 hypertrophy-inducing carcinogenic compounds). After applying logistic ridge regression analysis, 35 genes for liver hypertrophy (e.g., Acot1 and Abcc3) and 13 genes for hypertrophic hepatocarcinogenesis (e.g., Asns and Gpx2) were selected. The predictive models built using these genes were 94.8% and 82.7% accurate, respectively. Pathway analysis of the genes indicates that, aside from a xenobiotic metabolism-related pathway as an adaptive response for liver hypertrophy, amino acid biosynthesis and oxidative responses appear to be involved in hypertrophic hepatocarcinogenesis. Early detection and toxicogenomic characterization of liver hypertrophy using our models may be useful for predicting carcinogenesis. In addition, the identified genes provide novel insight into discrimination between adverse hypertrophy associated with carcinogenesis and adaptive hypertrophy in risk assessment. - Highlights: • Hypertrophy (H) and hypertrophic carcinogenesis (C) were studied by toxicogenomics. • Important genes for H and C were selected by logistic ridge regression analysis. • Amino acid biosynthesis and oxidative responses may be involved in C. • Predictive models for H and C provided 94.8% and 82.7% accuracy, respectively. • The identified genes could be useful for assessment of liver hypertrophy.« less

The application of neural network model to the simulation nitrous oxide emission in the hydro-fluctuation belt of Three Gorges Reservoir

NASA Astrophysics Data System (ADS)

Song, Lanlan

2017-04-01

Nitrous oxide is much more potent greenhouse gas than carbon dioxide. However, the estimation of N2O flux is usually clouded with uncertainty, mainly due to high spatial and temporal variations. This hampers the development of general mechanistic models for N2O emission as well, as most previously developed models were empirical or exhibited low predictability with numerous assumptions. In this study, we tested General Regression Neural Networks (GRNN) as an alternative to classic empirical models for simulating N2O emission in riparian zones of Reservoirs. GRNN and nonlinear regression (NLR) were applied to estimate the N2O flux of 1-year observations in riparian zones of Three Gorge Reservoir. NLR resulted in lower prediction power and higher residuals compared to GRNN. Although nonlinear regression model estimated similar average values of N2O, it could not capture the fluctuation patterns accurately. In contrast, GRNN model achieved a fairly high predictability, with an R2 of 0.59 for model validation, 0.77 for model calibration (training), and a low root mean square error (RMSE), indicating a high capacity to simulate the dynamics of N2O flux. According to a sensitivity analysis of the GRNN, nonlinear relationships between input variables and N2O flux were well explained. Our results suggest that the GRNN developed in this study has a greater performance in simulating variations in N2O flux than nonlinear regressions.

GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran.

PubMed

Naghibi, Seyed Amir; Pourghasemi, Hamid Reza; Dixon, Barnali

2016-01-01

Groundwater is considered one of the most valuable fresh water resources. The main objective of this study was to produce groundwater spring potential maps in the Koohrang Watershed, Chaharmahal-e-Bakhtiari Province, Iran, using three machine learning models: boosted regression tree (BRT), classification and regression tree (CART), and random forest (RF). Thirteen hydrological-geological-physiographical (HGP) factors that influence locations of springs were considered in this research. These factors include slope degree, slope aspect, altitude, topographic wetness index (TWI), slope length (LS), plan curvature, profile curvature, distance to rivers, distance to faults, lithology, land use, drainage density, and fault density. Subsequently, groundwater spring potential was modeled and mapped using CART, RF, and BRT algorithms. The predicted results from the three models were validated using the receiver operating characteristics curve (ROC). From 864 springs identified, 605 (≈70 %) locations were used for the spring potential mapping, while the remaining 259 (≈30 %) springs were used for the model validation. The area under the curve (AUC) for the BRT model was calculated as 0.8103 and for CART and RF the AUC were 0.7870 and 0.7119, respectively. Therefore, it was concluded that the BRT model produced the best prediction results while predicting locations of springs followed by CART and RF models, respectively. Geospatially integrated BRT, CART, and RF methods proved to be useful in generating the spring potential map (SPM) with reasonable accuracy.

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

Using the Johns Hopkins' Aggregated Diagnosis Groups (ADGs) to predict 1-year mortality in population-based cohorts of patients with diabetes in Ontario, Canada.

PubMed

Austin, P C; Shah, B R; Newman, A; Anderson, G M

2012-09-01

There are limited validated methods to ascertain comorbidities for risk adjustment in ambulatory populations of patients with diabetes using administrative health-care databases. The objective was to examine the ability of the Johns Hopkins' Aggregated Diagnosis Groups to predict mortality in population-based ambulatory samples of both incident and prevalent subjects with diabetes. Retrospective cohorts constructed using population-based administrative data. The incident cohort consisted of all 346,297 subjects diagnosed with diabetes between 1 April 2004 and 31 March 2008. The prevalent cohort consisted of all 879,849 subjects with pre-existing diabetes on 1 January, 2007. The outcome was death within 1 year of the subject's index date. A logistic regression model consisting of age, sex and indicator variables for 22 of the 32 Johns Hopkins' Aggregated Diagnosis Group categories had excellent discrimination for predicting mortality in incident diabetes patients: the c-statistic was 0.87 in an independent validation sample. A similar model had excellent discrimination for predicting mortality in prevalent diabetes patients: the c-statistic was 0.84 in an independent validation sample. Both models demonstrated very good calibration, denoting good agreement between observed and predicted mortality across the range of predicted mortality in which the large majority of subjects lay. For comparative purposes, regression models incorporating the Charlson comorbidity index, age and sex, age and sex, and age alone had poorer discrimination than the model that incorporated the Johns Hopkins' Aggregated Diagnosis Groups. Logistical regression models using age, sex and the John Hopkins' Aggregated Diagnosis Groups were able to accurately predict 1-year mortality in population-based samples of patients with diabetes. © 2011 The Authors. Diabetic Medicine © 2011 Diabetes UK.

Predicting acute pain after cesarean delivery using three simple questions.

PubMed

Pan, Peter H; Tonidandel, Ashley M; Aschenbrenner, Carol A; Houle, Timothy T; Harris, Lynne C; Eisenach, James C

2013-05-01

Interindividual variability in postoperative pain presents a clinical challenge. Preoperative quantitative sensory testing is useful but time consuming in predicting postoperative pain intensity. The current study was conducted to develop and validate a predictive model of acute postcesarean pain using a simple three-item preoperative questionnaire. A total of 200 women scheduled for elective cesarean delivery under subarachnoid anesthesia were enrolled (192 subjects analyzed). Patients were asked to rate the intensity of loudness of audio tones, their level of anxiety and anticipated pain, and analgesic need from surgery. Postoperatively, patients reported the intensity of evoked pain. Regression analysis was performed to generate a predictive model for pain from these measures. A validation cohort of 151 women was enrolled to test the reliability of the model (131 subjects analyzed). Responses from each of the three preoperative questions correlated moderately with 24-h evoked pain intensity (r = 0.24-0.33, P < 0.001). Audio tone rating added uniquely, but minimally, to the model and was not included in the predictive model. The multiple regression analysis yielded a statistically significant model (R = 0.20, P < 0.001), whereas the validation cohort showed reliably a very similar regression line (R = 0.18). In predicting the upper 20th percentile of evoked pain scores, the optimal cut point was 46.9 (z =0.24) such that sensitivity of 0.68 and specificity of 0.67 were as balanced as possible. This simple three-item questionnaire is useful to help predict postcesarean evoked pain intensity, and could be applied to further research and clinical application to tailor analgesic therapy to those who need it most.

A hybrid model for PM₂.₅ forecasting based on ensemble empirical mode decomposition and a general regression neural network.

PubMed

Zhou, Qingping; Jiang, Haiyan; Wang, Jianzhou; Zhou, Jianling

2014-10-15

Exposure to high concentrations of fine particulate matter (PM₂.₅) can cause serious health problems because PM₂.₅ contains microscopic solid or liquid droplets that are sufficiently small to be ingested deep into human lungs. Thus, daily prediction of PM₂.₅ levels is notably important for regulatory plans that inform the public and restrict social activities in advance when harmful episodes are foreseen. A hybrid EEMD-GRNN (ensemble empirical mode decomposition-general regression neural network) model based on data preprocessing and analysis is firstly proposed in this paper for one-day-ahead prediction of PM₂.₅ concentrations. The EEMD part is utilized to decompose original PM₂.₅ data into several intrinsic mode functions (IMFs), while the GRNN part is used for the prediction of each IMF. The hybrid EEMD-GRNN model is trained using input variables obtained from principal component regression (PCR) model to remove redundancy. These input variables accurately and succinctly reflect the relationships between PM₂.₅ and both air quality and meteorological data. The model is trained with data from January 1 to November 1, 2013 and is validated with data from November 2 to November 21, 2013 in Xi'an Province, China. The experimental results show that the developed hybrid EEMD-GRNN model outperforms a single GRNN model without EEMD, a multiple linear regression (MLR) model, a PCR model, and a traditional autoregressive integrated moving average (ARIMA) model. The hybrid model with fast and accurate results can be used to develop rapid air quality warning systems. Copyright © 2014 Elsevier B.V. All rights reserved.

Maximum Entropy Discrimination Poisson Regression for Software Reliability Modeling.

PubMed

Chatzis, Sotirios P; Andreou, Andreas S

2015-11-01

Reliably predicting software defects is one of the most significant tasks in software engineering. Two of the major components of modern software reliability modeling approaches are: 1) extraction of salient features for software system representation, based on appropriately designed software metrics and 2) development of intricate regression models for count data, to allow effective software reliability data modeling and prediction. Surprisingly, research in the latter frontier of count data regression modeling has been rather limited. More specifically, a lack of simple and efficient algorithms for posterior computation has made the Bayesian approaches appear unattractive, and thus underdeveloped in the context of software reliability modeling. In this paper, we try to address these issues by introducing a novel Bayesian regression model for count data, based on the concept of max-margin data modeling, effected in the context of a fully Bayesian model treatment with simple and efficient posterior distribution updates. Our novel approach yields a more discriminative learning technique, making more effective use of our training data during model inference. In addition, it allows of better handling uncertainty in the modeled data, which can be a significant problem when the training data are limited. We derive elegant inference algorithms for our model under the mean-field paradigm and exhibit its effectiveness using the publicly available benchmark data sets.

Analyzing degradation data with a random effects spline regression model

DOE PAGES

Fugate, Michael Lynn; Hamada, Michael Scott; Weaver, Brian Phillip

2017-03-17

This study proposes using a random effects spline regression model to analyze degradation data. Spline regression avoids having to specify a parametric function for the true degradation of an item. A distribution for the spline regression coefficients captures the variation of the true degradation curves from item to item. We illustrate the proposed methodology with a real example using a Bayesian approach. The Bayesian approach allows prediction of degradation of a population over time and estimation of reliability is easy to perform.

Analyzing degradation data with a random effects spline regression model

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

Fugate, Michael Lynn; Hamada, Michael Scott; Weaver, Brian Phillip

This study proposes using a random effects spline regression model to analyze degradation data. Spline regression avoids having to specify a parametric function for the true degradation of an item. A distribution for the spline regression coefficients captures the variation of the true degradation curves from item to item. We illustrate the proposed methodology with a real example using a Bayesian approach. The Bayesian approach allows prediction of degradation of a population over time and estimation of reliability is easy to perform.

Replica analysis of overfitting in regression models for time-to-event data

NASA Astrophysics Data System (ADS)

Coolen, A. C. C.; Barrett, J. E.; Paga, P.; Perez-Vicente, C. J.

2017-09-01

Overfitting, which happens when the number of parameters in a model is too large compared to the number of data points available for determining these parameters, is a serious and growing problem in survival analysis. While modern medicine presents us with data of unprecedented dimensionality, these data cannot yet be used effectively for clinical outcome prediction. Standard error measures in maximum likelihood regression, such as p-values and z-scores, are blind to overfitting, and even for Cox’s proportional hazards model (the main tool of medical statisticians), one finds in literature only rules of thumb on the number of samples required to avoid overfitting. In this paper we present a mathematical theory of overfitting in regression models for time-to-event data, which aims to increase our quantitative understanding of the problem and provide practical tools with which to correct regression outcomes for the impact of overfitting. It is based on the replica method, a statistical mechanical technique for the analysis of heterogeneous many-variable systems that has been used successfully for several decades in physics, biology, and computer science, but not yet in medical statistics. We develop the theory initially for arbitrary regression models for time-to-event data, and verify its predictions in detail for the popular Cox model.

Using Evidence-Based Decision Trees Instead of Formulas to Identify At-Risk Readers. REL 2014-036

ERIC Educational Resources Information Center

Koon, Sharon; Petscher, Yaacov; Foorman, Barbara R.

2014-01-01

This study examines whether the classification and regression tree (CART) model improves the early identification of students at risk for reading comprehension difficulties compared with the more difficult to interpret logistic regression model. CART is a type of predictive modeling that relies on nonparametric techniques. It presents results in…

Emergency Department Visit Forecasting and Dynamic Nursing Staff Allocation Using Machine Learning Techniques With Readily Available Open-Source Software.

PubMed

Zlotnik, Alexander; Gallardo-Antolín, Ascensión; Cuchí Alfaro, Miguel; Pérez Pérez, María Carmen; Montero Martínez, Juan Manuel

2015-08-01

Although emergency department visit forecasting can be of use for nurse staff planning, previous research has focused on models that lacked sufficient resolution and realistic error metrics for these predictions to be applied in practice. Using data from a 1100-bed specialized care hospital with 553,000 patients assigned to its healthcare area, forecasts with different prediction horizons, from 2 to 24 weeks ahead, with an 8-hour granularity, using support vector regression, M5P, and stratified average time-series models were generated with an open-source software package. As overstaffing and understaffing errors have different implications, error metrics and potential personnel monetary savings were calculated with a custom validation scheme, which simulated subsequent generation of predictions during a 4-year period. Results were then compared with a generalized estimating equation regression. Support vector regression and M5P models were found to be superior to the stratified average model with a 95% confidence interval. Our findings suggest that medium and severe understaffing situations could be reduced in more than an order of magnitude and average yearly savings of up to €683,500 could be achieved if dynamic nursing staff allocation was performed with support vector regression instead of the static staffing levels currently in use.

Predicting volume of distribution with decision tree-based regression methods using predicted tissue:plasma partition coefficients.

PubMed

Freitas, Alex A; Limbu, Kriti; Ghafourian, Taravat

2015-01-01

Volume of distribution is an important pharmacokinetic property that indicates the extent of a drug's distribution in the body tissues. This paper addresses the problem of how to estimate the apparent volume of distribution at steady state (Vss) of chemical compounds in the human body using decision tree-based regression methods from the area of data mining (or machine learning). Hence, the pros and cons of several different types of decision tree-based regression methods have been discussed. The regression methods predict Vss using, as predictive features, both the compounds' molecular descriptors and the compounds' tissue:plasma partition coefficients (Kt:p) - often used in physiologically-based pharmacokinetics. Therefore, this work has assessed whether the data mining-based prediction of Vss can be made more accurate by using as input not only the compounds' molecular descriptors but also (a subset of) their predicted Kt:p values. Comparison of the models that used only molecular descriptors, in particular, the Bagging decision tree (mean fold error of 2.33), with those employing predicted Kt:p values in addition to the molecular descriptors, such as the Bagging decision tree using adipose Kt:p (mean fold error of 2.29), indicated that the use of predicted Kt:p values as descriptors may be beneficial for accurate prediction of Vss using decision trees if prior feature selection is applied. Decision tree based models presented in this work have an accuracy that is reasonable and similar to the accuracy of reported Vss inter-species extrapolations in the literature. The estimation of Vss for new compounds in drug discovery will benefit from methods that are able to integrate large and varied sources of data and flexible non-linear data mining methods such as decision trees, which can produce interpretable models. Graphical AbstractDecision trees for the prediction of tissue partition coefficient and volume of distribution of drugs.

Issues and Importance of "Good" Starting Points for Nonlinear Regression for Mathematical Modeling with Maple: Basic Model Fitting to Make Predictions with Oscillating Data

ERIC Educational Resources Information Center

Fox, William

2012-01-01

The purpose of our modeling effort is to predict future outcomes. We assume the data collected are both accurate and relatively precise. For our oscillating data, we examined several mathematical modeling forms for predictions. We also examined both ignoring the oscillations as an important feature and including the oscillations as an important…

Development and evaluation of a regression-based model to predict cesium-137 concentration ratios for saltwater fish.

PubMed

Pinder, John E; Rowan, David J; Smith, Jim T

2016-02-01

Data from published studies and World Wide Web sources were combined to develop a regression model to predict (137)Cs concentration ratios for saltwater fish. Predictions were developed from 1) numeric trophic levels computed primarily from random resampling of known food items and 2) K concentrations in the saltwater for 65 samplings from 41 different species from both the Atlantic and Pacific Oceans. A number of different models were initially developed and evaluated for accuracy which was assessed as the ratios of independently measured concentration ratios to those predicted by the model. In contrast to freshwater systems, were K concentrations are highly variable and are an important factor in affecting fish concentration ratios, the less variable K concentrations in saltwater were relatively unimportant in affecting concentration ratios. As a result, the simplest model, which used only trophic level as a predictor, had comparable accuracies to more complex models that also included K concentrations. A test of model accuracy involving comparisons of 56 published concentration ratios from 51 species of marine fish to those predicted by the model indicated that 52 of the predicted concentration ratios were within a factor of 2 of the observed concentration ratios. Copyright © 2015 Elsevier Ltd. All rights reserved.

Introduction to statistical modelling 2: categorical variables and interactions in linear regression.

PubMed

Lunt, Mark

2015-07-01

In the first article in this series we explored the use of linear regression to predict an outcome variable from a number of predictive factors. It assumed that the predictive factors were measured on an interval scale. However, this article shows how categorical variables can also be included in a linear regression model, enabling predictions to be made separately for different groups and allowing for testing the hypothesis that the outcome differs between groups. The use of interaction terms to measure whether the effect of a particular predictor variable differs between groups is also explained. An alternative approach to testing the difference between groups of the effect of a given predictor, which consists of measuring the effect in each group separately and seeing whether the statistical significance differs between the groups, is shown to be misleading. © The Author 2013. Published by Oxford University Press on behalf of the British Society for Rheumatology. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Estimating irrigation water use in the humid eastern United States

USGS Publications Warehouse

Levin, Sara B.; Zarriello, Phillip J.

2013-01-01

Accurate accounting of irrigation water use is an important part of the U.S. Geological Survey National Water-Use Information Program and the WaterSMART initiative to help maintain sustainable water resources in the Nation. Irrigation water use in the humid eastern United States is not well characterized because of inadequate reporting and wide variability associated with climate, soils, crops, and farming practices. To better understand irrigation water use in the eastern United States, two types of predictive models were developed and compared by using metered irrigation water-use data for corn, cotton, peanut, and soybean crops in Georgia and turf farms in Rhode Island. Reliable metered irrigation data were limited to these areas. The first predictive model that was developed uses logistic regression to predict the occurrence of irrigation on the basis of antecedent climate conditions. Logistic regression equations were developed for corn, cotton, peanut, and soybean crops by using weekly irrigation water-use data from 36 metered sites in Georgia in 2009 and 2010 and turf farms in Rhode Island from 2000 to 2004. For the weeks when irrigation was predicted to take place, the irrigation water-use volume was estimated by multiplying the average metered irrigation application rate by the irrigated acreage for a given crop. The second predictive model that was developed is a crop-water-demand model that uses a daily soil water balance to estimate the water needs of a crop on a given day based on climate, soil, and plant properties. Crop-water-demand models were developed independently of reported irrigation water-use practices and relied on knowledge of plant properties that are available in the literature. Both modeling approaches require accurate accounting of irrigated area and crop type to estimate total irrigation water use. Water-use estimates from both modeling methods were compared to the metered irrigation data from Rhode Island and Georgia that were used to develop the models as well as two independent validation datasets from Georgia and Virginia that were not used in model development. Irrigation water-use estimates from the logistic regression method more closely matched mean reported irrigation rates than estimates from the crop-water-demand model when compared to the irrigation data used to develop the equations. The root mean squared errors (RMSEs) for the logistic regression estimates of mean annual irrigation ranged from 0.3 to 2.0 inches (in.) for the five crop types; RMSEs for the crop-water-demand models ranged from 1.4 to 3.9 in. However, when the models were applied and compared to the independent validation datasets from southwest Georgia from 2010, and from Virginia from 1999 to 2007, the crop-water-demand model estimates were as good as or better at predicting the mean irrigation volume than the logistic regression models for most crop types. RMSEs for logistic regression estimates of mean annual irrigation ranged from 1.0 to 7.0 in. for validation data from Georgia and from 1.8 to 4.9 in. for validation data from Virginia; RMSEs for crop-water-demand model estimates ranged from 2.1 to 5.8 in. for Georgia data and from 2.0 to 3.9 in. for Virginia data. In general, regression-based models performed better in areas that had quality daily or weekly irrigation data from which the regression equations were developed; however, the regression models were less reliable than the crop-water-demand models when applied outside the area for which they were developed. In most eastern coastal states that do not have quality irrigation data, the crop-water-demand model can be used more reliably. The development of predictive models of irrigation water use in this study was hindered by a lack of quality irrigation data. Many mid-Atlantic and New England states do not require irrigation water use to be reported. A survey of irrigation data from 14 eastern coastal states from Maine to Georgia indicated that, with the exception of the data in Georgia, irrigation data in the states that do require reporting commonly did not contain requisite ancillary information such as irrigated area or crop type, lacked precision, or were at an aggregated temporal scale making them unsuitable for use in the development of predictive models. Confidence in the reliability of either modeling method is affected by uncertainty in the reported data from which the models were developed or validated. Only through additional collection of quality data and further study can the accuracy and uncertainty of irrigation water-use estimates be improved in the humid eastern United States.

The Use of Linear Programming for Prediction.

ERIC Educational Resources Information Center

Schnittjer, Carl J.

The purpose of the study was to develop a linear programming model to be used for prediction, test the accuracy of the predictions, and compare the accuracy with that produced by curvilinear multiple regression analysis. (Author)

Prediction models for Arabica coffee beverage quality based on aroma analyses and chemometrics.

PubMed

Ribeiro, J S; Augusto, F; Salva, T J G; Ferreira, M M C

2012-11-15

In this work, soft modeling based on chemometric analyses of coffee beverage sensory data and the chromatographic profiles of volatile roasted coffee compounds is proposed to predict the scores of acidity, bitterness, flavor, cleanliness, body, and overall quality of the coffee beverage. A partial least squares (PLS) regression method was used to construct the models. The ordered predictor selection (OPS) algorithm was applied to select the compounds for the regression model of each sensory attribute in order to take only significant chromatographic peaks into account. The prediction errors of these models, using 4 or 5 latent variables, were equal to 0.28, 0.33, 0.35, 0.33, 0.34 and 0.41, for each of the attributes and compatible with the errors of the mean scores of the experts. Thus, the results proved the feasibility of using a similar methodology in on-line or routine applications to predict the sensory quality of Brazilian Arabica coffee. Copyright © 2012 Elsevier B.V. All rights reserved.

An investigation to improve the Menhaden fishery prediction and detection model through the application of ERTS-A data

NASA Technical Reports Server (NTRS)

Maughan, P. M. (Principal Investigator)

1973-01-01

The author has identified the following significant results. Linear regression of secchi disc visibility against number of sets yielded significant results in a number of instances. The variability seen in the slope of the regression lines is due to the nonuniformity of sample size. The longer the period sampled, the larger the total number of attempts. Further, there is no reason to expect either the influence of transparency or of other variables to remain constant throughout the season. However, the fact that the data for the entire season, variable as it is, was significant at the 5% level, suggests its potential utility for predictive modeling. Thus, this regression equation will be considered representative and will be utilized for the first numerical model. Secchi disc visibility was also regressed against number of sets for the three day period September 27-September 29, 1972 to determine if surface truth data supported the intense relationship between ERTS-1 identified turbidity and fishing effort previously discussed. A very negative correlation was found. These relationship lend additional credence to the hypothesis that ERTS imagery, when utilized as a source of visibility (turbidity) data, may be useful as a predictive tool.

Catchments as non-linear filters: evaluating data-driven approaches for spatio-temporal predictions in ungauged basins

NASA Astrophysics Data System (ADS)

Bellugi, D. G.; Tennant, C.; Larsen, L.

2016-12-01

Catchment and climate heterogeneity complicate prediction of runoff across time and space, and resulting parameter uncertainty can lead to large accumulated errors in hydrologic models, particularly in ungauged basins. Recently, data-driven modeling approaches have been shown to avoid the accumulated uncertainty associated with many physically-based models, providing an appealing alternative for hydrologic prediction. However, the effectiveness of different methods in hydrologically and geomorphically distinct catchments, and the robustness of these methods to changing climate and changing hydrologic processes remain to be tested. Here, we evaluate the use of machine learning techniques to predict daily runoff across time and space using only essential climatic forcing (e.g. precipitation, temperature, and potential evapotranspiration) time series as model input. Model training and testing was done using a high quality dataset of daily runoff and climate forcing data for 25+ years for 600+ minimally-disturbed catchments (drainage area range 5-25,000 km2, median size 336 km2) that cover a wide range of climatic and physical characteristics. Preliminary results using Support Vector Regression (SVR) suggest that in some catchments this nonlinear-based regression technique can accurately predict daily runoff, while the same approach fails in other catchments, indicating that the representation of climate inputs and/or catchment filter characteristics in the model structure need further refinement to increase performance. We bolster this analysis by using Sparse Identification of Nonlinear Dynamics (a sparse symbolic regression technique) to uncover the governing equations that describe runoff processes in catchments where SVR performed well and for ones where it performed poorly, thereby enabling inference about governing processes. This provides a robust means of examining how catchment complexity influences runoff prediction skill, and represents a contribution towards the integration of data-driven inference and physically-based models.

Weighted regression analysis and interval estimators

Treesearch

Donald W. Seegrist

1974-01-01

A method for deriving the weighted least squares estimators for the parameters of a multiple regression model. Confidence intervals for expected values, and prediction intervals for the means of future samples are given.

Estimating top-of-atmosphere thermal infrared radiance using MERRA-2 atmospheric data

NASA Astrophysics Data System (ADS)

Kleynhans, Tania; Montanaro, Matthew; Gerace, Aaron; Kanan, Christopher

2017-05-01

Thermal infrared satellite images have been widely used in environmental studies. However, satellites have limited temporal resolution, e.g., 16 day Landsat or 1 to 2 day Terra MODIS. This paper investigates the use of the Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) reanalysis data product, produced by NASA's Global Modeling and Assimilation Office (GMAO) to predict global topof-atmosphere (TOA) thermal infrared radiance. The high temporal resolution of the MERRA-2 data product presents opportunities for novel research and applications. Various methods were applied to estimate TOA radiance from MERRA-2 variables namely (1) a parameterized physics based method, (2) Linear regression models and (3) non-linear Support Vector Regression. Model prediction accuracy was evaluated using temporally and spatially coincident Moderate Resolution Imaging Spectroradiometer (MODIS) thermal infrared data as reference data. This research found that Support Vector Regression with a radial basis function kernel produced the lowest error rates. Sources of errors are discussed and defined. Further research is currently being conducted to train deep learning models to predict TOA thermal radiance

Perceived Organizational Support for Enhancing Welfare at Work: A Regression Tree Model

PubMed Central

Giorgi, Gabriele; Dubin, David; Perez, Javier Fiz

2016-01-01

When trying to examine outcomes such as welfare and well-being, research tends to focus on main effects and take into account limited numbers of variables at a time. There are a number of techniques that may help address this problem. For example, many statistical packages available in R provide easy-to-use methods of modeling complicated analysis such as classification and tree regression (i.e., recursive partitioning). The present research illustrates the value of recursive partitioning in the prediction of perceived organizational support in a sample of more than 6000 Italian bankers. Utilizing the tree function party package in R, we estimated a regression tree model predicting perceived organizational support from a multitude of job characteristics including job demand, lack of job control, lack of supervisor support, training, etc. The resulting model appears particularly helpful in pointing out several interactions in the prediction of perceived organizational support. In particular, training is the dominant factor. Another dimension that seems to influence organizational support is reporting (perceived communication about safety and stress concerns). Results are discussed from a theoretical and methodological point of view. PMID:28082924

Predictive landslide susceptibility mapping using spatial information in the Pechabun area of Thailand

NASA Astrophysics Data System (ADS)

Oh, Hyun-Joo; Lee, Saro; Chotikasathien, Wisut; Kim, Chang Hwan; Kwon, Ju Hyoung

2009-04-01

For predictive landslide susceptibility mapping, this study applied and verified probability model, the frequency ratio and statistical model, logistic regression at Pechabun, Thailand, using a geographic information system (GIS) and remote sensing. Landslide locations were identified in the study area from interpretation of aerial photographs and field surveys, and maps of the topography, geology and land cover were constructed to spatial database. The factors that influence landslide occurrence, such as slope gradient, slope aspect and curvature of topography and distance from drainage were calculated from the topographic database. Lithology and distance from fault were extracted and calculated from the geology database. Land cover was classified from Landsat TM satellite image. The frequency ratio and logistic regression coefficient were overlaid for landslide susceptibility mapping as each factor’s ratings. Then the landslide susceptibility map was verified and compared using the existing landslide location. As the verification results, the frequency ratio model showed 76.39% and logistic regression model showed 70.42% in prediction accuracy. The method can be used to reduce hazards associated with landslides and to plan land cover.

Modeling individual tree survial

Treesearch

Quang V. Cao

2016-01-01

Information provided by growth and yield models is the basis for forest managers to make decisions on how to manage their forests. Among different types of growth models, whole-stand models offer predictions at stand level, whereas individual-tree models give detailed information at tree level. The well-known logistic regression is commonly used to predict tree...

Accounting for Slipping and Other False Negatives in Logistic Models of Student Learning

ERIC Educational Resources Information Center

MacLellan, Christopher J.; Liu, Ran; Koedinger, Kenneth R.

2015-01-01

Additive Factors Model (AFM) and Performance Factors Analysis (PFA) are two popular models of student learning that employ logistic regression to estimate parameters and predict performance. This is in contrast to Bayesian Knowledge Tracing (BKT) which uses a Hidden Markov Model formalism. While all three models tend to make similar predictions,…

A land use regression model for ambient ultrafine particles in Montreal, Canada: A comparison of linear regression and a machine learning approach.

PubMed

Weichenthal, Scott; Ryswyk, Keith Van; Goldstein, Alon; Bagg, Scott; Shekkarizfard, Maryam; Hatzopoulou, Marianne

2016-04-01

Existing evidence suggests that ambient ultrafine particles (UFPs) (<0.1µm) may contribute to acute cardiorespiratory morbidity. However, few studies have examined the long-term health effects of these pollutants owing in part to a need for exposure surfaces that can be applied in large population-based studies. To address this need, we developed a land use regression model for UFPs in Montreal, Canada using mobile monitoring data collected from 414 road segments during the summer and winter months between 2011 and 2012. Two different approaches were examined for model development including standard multivariable linear regression and a machine learning approach (kernel-based regularized least squares (KRLS)) that learns the functional form of covariate impacts on ambient UFP concentrations from the data. The final models included parameters for population density, ambient temperature and wind speed, land use parameters (park space and open space), length of local roads and rail, and estimated annual average NOx emissions from traffic. The final multivariable linear regression model explained 62% of the spatial variation in ambient UFP concentrations whereas the KRLS model explained 79% of the variance. The KRLS model performed slightly better than the linear regression model when evaluated using an external dataset (R(2)=0.58 vs. 0.55) or a cross-validation procedure (R(2)=0.67 vs. 0.60). In general, our findings suggest that the KRLS approach may offer modest improvements in predictive performance compared to standard multivariable linear regression models used to estimate spatial variations in ambient UFPs. However, differences in predictive performance were not statistically significant when evaluated using the cross-validation procedure. Crown Copyright © 2015. Published by Elsevier Inc. All rights reserved.

Two models for identification and predicting behaviour of an induction motor system

NASA Astrophysics Data System (ADS)

Kuo, Chien-Hsun

2018-01-01

System identification or modelling is the process of building mathematical models of dynamical systems based on the available input and output data from the systems. This paper introduces system identification by using ARX (Auto Regressive with eXogeneous input) and ARMAX (Auto Regressive Moving Average with eXogeneous input) models. Through the identified system model, the predicted output could be compared with the measured one to help prevent the motor faults from developing into a catastrophic machine failure and avoid unnecessary costs and delays caused by the need to carry out unscheduled repairs. The induction motor system is illustrated as an example. Numerical and experimental results are shown for the identified induction motor system.

A statistical learning framework for groundwater nitrate models of the Central Valley, California, USA

USGS Publications Warehouse

Nolan, Bernard T.; Fienen, Michael N.; Lorenz, David L.

2015-01-01

We used a statistical learning framework to evaluate the ability of three machine-learning methods to predict nitrate concentration in shallow groundwater of the Central Valley, California: boosted regression trees (BRT), artificial neural networks (ANN), and Bayesian networks (BN). Machine learning methods can learn complex patterns in the data but because of overfitting may not generalize well to new data. The statistical learning framework involves cross-validation (CV) training and testing data and a separate hold-out data set for model evaluation, with the goal of optimizing predictive performance by controlling for model overfit. The order of prediction performance according to both CV testing R2 and that for the hold-out data set was BRT > BN > ANN. For each method we identified two models based on CV testing results: that with maximum testing R2 and a version with R2 within one standard error of the maximum (the 1SE model). The former yielded CV training R2 values of 0.94–1.0. Cross-validation testing R2 values indicate predictive performance, and these were 0.22–0.39 for the maximum R2 models and 0.19–0.36 for the 1SE models. Evaluation with hold-out data suggested that the 1SE BRT and ANN models predicted better for an independent data set compared with the maximum R2 versions, which is relevant to extrapolation by mapping. Scatterplots of predicted vs. observed hold-out data obtained for final models helped identify prediction bias, which was fairly pronounced for ANN and BN. Lastly, the models were compared with multiple linear regression (MLR) and a previous random forest regression (RFR) model. Whereas BRT results were comparable to RFR, MLR had low hold-out R2 (0.07) and explained less than half the variation in the training data. Spatial patterns of predictions by the final, 1SE BRT model agreed reasonably well with previously observed patterns of nitrate occurrence in groundwater of the Central Valley.

Gaussian Process Regression for Predictive But Interpretable Machine Learning Models: An Example of Predicting Mental Workload across Tasks

PubMed Central

Caywood, Matthew S.; Roberts, Daniel M.; Colombe, Jeffrey B.; Greenwald, Hal S.; Weiland, Monica Z.

2017-01-01

There is increasing interest in real-time brain-computer interfaces (BCIs) for the passive monitoring of human cognitive state, including cognitive workload. Too often, however, effective BCIs based on machine learning techniques may function as “black boxes” that are difficult to analyze or interpret. In an effort toward more interpretable BCIs, we studied a family of N-back working memory tasks using a machine learning model, Gaussian Process Regression (GPR), which was both powerful and amenable to analysis. Participants performed the N-back task with three stimulus variants, auditory-verbal, visual-spatial, and visual-numeric, each at three working memory loads. GPR models were trained and tested on EEG data from all three task variants combined, in an effort to identify a model that could be predictive of mental workload demand regardless of stimulus modality. To provide a comparison for GPR performance, a model was additionally trained using multiple linear regression (MLR). The GPR model was effective when trained on individual participant EEG data, resulting in an average standardized mean squared error (sMSE) between true and predicted N-back levels of 0.44. In comparison, the MLR model using the same data resulted in an average sMSE of 0.55. We additionally demonstrate how GPR can be used to identify which EEG features are relevant for prediction of cognitive workload in an individual participant. A fraction of EEG features accounted for the majority of the model’s predictive power; using only the top 25% of features performed nearly as well as using 100% of features. Subsets of features identified by linear models (ANOVA) were not as efficient as subsets identified by GPR. This raises the possibility of BCIs that require fewer model features while capturing all of the information needed to achieve high predictive accuracy. PMID:28123359

Predicting nitrogen loading with land-cover composition: how can watershed size affect model performance?

PubMed

Zhang, Tao; Yang, Xiaojun

2013-01-01

Watershed-wide land-cover proportions can be used to predict the in-stream non-point source pollutant loadings through regression modeling. However, the model performance can vary greatly across different study sites and among various watersheds. Existing literature has shown that this type of regression modeling tends to perform better for large watersheds than for small ones, and that such a performance variation has been largely linked with different interwatershed landscape heterogeneity levels. The purpose of this study is to further examine the previously mentioned empirical observation based on a set of watersheds in the northern part of Georgia (USA) to explore the underlying causes of the variation in model performance. Through the combined use of the neutral landscape modeling approach and a spatially explicit nutrient loading model, we tested whether the regression model performance variation over the watershed groups ranging in size is due to the different watershed landscape heterogeneity levels. We adopted three neutral landscape modeling criteria that were tied with different similarity levels in watershed landscape properties and used the nutrient loading model to estimate the nitrogen loads for these neutral watersheds. Then we compared the regression model performance for the real and neutral landscape scenarios, respectively. We found that watershed size can affect the regression model performance both directly and indirectly. Along with the indirect effect through interwatershed heterogeneity, watershed size can directly affect the model performance over the watersheds varying in size. We also found that the regression model performance can be more significantly affected by other physiographic properties shaping nitrogen delivery effectiveness than the watershed land-cover heterogeneity. This study contrasts with many existing studies because it goes beyond hypothesis formulation based on empirical observations and into hypothesis testing to explore the fundamental mechanism.

Predicting Potential Changes in Suitable Habitat and Distribution by 2100 for Tree Species of the Eastern United States

Treesearch

Louis R Iverson; Anantha M. Prasad; Mark W. Schwartz; Mark W. Schwartz

2005-01-01

We predict current distribution and abundance for tree species present in eastern North America, and subsequently estimate potential suitable habitat for those species under a changed climate with 2 x CO2. We used a series of statistical models (i.e., Regression Tree Analysis (RTA), Multivariate Adaptive Regression Splines (MARS), Bagging Trees (...

Modeling and Prediction of Solvent Effect on Human Skin Permeability using Support Vector Regression and Random Forest.

PubMed

Baba, Hiromi; Takahara, Jun-ichi; Yamashita, Fumiyoshi; Hashida, Mitsuru

2015-11-01

The solvent effect on skin permeability is important for assessing the effectiveness and toxicological risk of new dermatological formulations in pharmaceuticals and cosmetics development. The solvent effect occurs by diverse mechanisms, which could be elucidated by efficient and reliable prediction models. However, such prediction models have been hampered by the small variety of permeants and mixture components archived in databases and by low predictive performance. Here, we propose a solution to both problems. We first compiled a novel large database of 412 samples from 261 structurally diverse permeants and 31 solvents reported in the literature. The data were carefully screened to ensure their collection under consistent experimental conditions. To construct a high-performance predictive model, we then applied support vector regression (SVR) and random forest (RF) with greedy stepwise descriptor selection to our database. The models were internally and externally validated. The SVR achieved higher performance statistics than RF. The (externally validated) determination coefficient, root mean square error, and mean absolute error of SVR were 0.899, 0.351, and 0.268, respectively. Moreover, because all descriptors are fully computational, our method can predict as-yet unsynthesized compounds. Our high-performance prediction model offers an attractive alternative to permeability experiments for pharmaceutical and cosmetic candidate screening and optimizing skin-permeable topical formulations.

Escherichia coli bacteria density in relation to turbidity, streamflow characteristics, and season in the Chattahoochee River near Atlanta, Georgia, October 2000 through September 2008—Description, statistical analysis, and predictive modeling

USGS Publications Warehouse

Lawrence, Stephen J.

2012-01-01

Regression analyses show that E. coli density in samples was strongly related to turbidity, streamflow characteristics, and season at both sites. The regression equation chosen for the Norcross data showed that 78 percent of the variability in E. coli density (in log base 10 units) was explained by the variability in turbidity values (in log base 10 units), streamflow event (dry-weather flow or stormflow), season (cool or warm), and an interaction term that is the cross product of streamflow event and turbidity. The regression equation chosen for the Atlanta data showed that 76 percent of the variability in E. coli density (in log base 10 units) was explained by the variability in turbidity values (in log base 10 units), water temperature, streamflow event, and an interaction term that is the cross product of streamflow event and turbidity. Residual analysis and model confirmation using new data indicated the regression equations selected at both sites predicted E. coli density within the 90 percent prediction intervals of the equations and could be used to predict E. coli density in real time at both sites.

BAYESIAN METHODS FOR REGIONAL-SCALE EUTROPHICATION MODELS. (R830887)

EPA Science Inventory

We demonstrate a Bayesian classification and regression tree (CART) approach to link multiple environmental stressors to biological responses and quantify uncertainty in model predictions. Such an approach can: (1) report prediction uncertainty, (2) be consistent with the amou...

Influential factors of red-light running at signalized intersection and prediction using a rare events logistic regression model.

PubMed

Ren, Yilong; Wang, Yunpeng; Wu, Xinkai; Yu, Guizhen; Ding, Chuan

2016-10-01

Red light running (RLR) has become a major safety concern at signalized intersection. To prevent RLR related crashes, it is critical to identify the factors that significantly impact the drivers' behaviors of RLR, and to predict potential RLR in real time. In this research, 9-month's RLR events extracted from high-resolution traffic data collected by loop detectors from three signalized intersections were applied to identify the factors that significantly affect RLR behaviors. The data analysis indicated that occupancy time, time gap, used yellow time, time left to yellow start, whether the preceding vehicle runs through the intersection during yellow, and whether there is a vehicle passing through the intersection on the adjacent lane were significantly factors for RLR behaviors. Furthermore, due to the rare events nature of RLR, a modified rare events logistic regression model was developed for RLR prediction. The rare events logistic regression method has been applied in many fields for rare events studies and shows impressive performance, but so far none of previous research has applied this method to study RLR. The results showed that the rare events logistic regression model performed significantly better than the standard logistic regression model. More importantly, the proposed RLR prediction method is purely based on loop detector data collected from a single advance loop detector located 400 feet away from stop-bar. This brings great potential for future field applications of the proposed method since loops have been widely implemented in many intersections and can collect data in real time. This research is expected to contribute to the improvement of intersection safety significantly. Copyright © 2016 Elsevier Ltd. All rights reserved.

Predicting Occurrence of Spine Surgery Complications Using "Big Data" Modeling of an Administrative Claims Database.

PubMed

Ratliff, John K; Balise, Ray; Veeravagu, Anand; Cole, Tyler S; Cheng, Ivan; Olshen, Richard A; Tian, Lu

2016-05-18

Postoperative metrics are increasingly important in determining standards of quality for physicians and hospitals. Although complications following spinal surgery have been described, procedural and patient variables have yet to be incorporated into a predictive model of adverse-event occurrence. We sought to develop a predictive model of complication occurrence after spine surgery. We used longitudinal prospective data from a national claims database and developed a predictive model incorporating complication type and frequency of occurrence following spine surgery procedures. We structured our model to assess the impact of features such as preoperative diagnosis, patient comorbidities, location in the spine, anterior versus posterior approach, whether fusion had been performed, whether instrumentation had been used, number of levels, and use of bone morphogenetic protein (BMP). We assessed a variety of adverse events. Prediction models were built using logistic regression with additive main effects and logistic regression with main effects as well as all 2 and 3-factor interactions. Least absolute shrinkage and selection operator (LASSO) regularization was used to select features. Competing approaches included boosted additive trees and the classification and regression trees (CART) algorithm. The final prediction performance was evaluated by estimating the area under a receiver operating characteristic curve (AUC) as predictions were applied to independent validation data and compared with the Charlson comorbidity score. The model was developed from 279,135 records of patients with a minimum duration of follow-up of 30 days. Preliminary assessment showed an adverse-event rate of 13.95%, well within norms reported in the literature. We used the first 80% of the records for training (to predict adverse events) and the remaining 20% of the records for validation. There was remarkable similarity among methods, with an AUC of 0.70 for predicting the occurrence of adverse events. The AUC using the Charlson comorbidity score was 0.61. The described model was more accurate than Charlson scoring (p < 0.01). We present a modeling effort based on administrative claims data that predicts the occurrence of complications after spine surgery. We believe that the development of a predictive modeling tool illustrating the risk of complication occurrence after spine surgery will aid in patient counseling and improve the accuracy of risk modeling strategies. Copyright © 2016 by The Journal of Bone and Joint Surgery, Incorporated.

On the calibration process of film dosimetry: OLS inverse regression versus WLS inverse prediction.

PubMed

Crop, F; Van Rompaye, B; Paelinck, L; Vakaet, L; Thierens, H; De Wagter, C

2008-07-21

The purpose of this study was both putting forward a statistically correct model for film calibration and the optimization of this process. A reliable calibration is needed in order to perform accurate reference dosimetry with radiographic (Gafchromic) film. Sometimes, an ordinary least squares simple linear (in the parameters) regression is applied to the dose-optical-density (OD) curve with the dose as a function of OD (inverse regression) or sometimes OD as a function of dose (inverse prediction). The application of a simple linear regression fit is an invalid method because heteroscedasticity of the data is not taken into account. This could lead to erroneous results originating from the calibration process itself and thus to a lower accuracy. In this work, we compare the ordinary least squares (OLS) inverse regression method with the correct weighted least squares (WLS) inverse prediction method to create calibration curves. We found that the OLS inverse regression method could lead to a prediction bias of up to 7.3 cGy at 300 cGy and total prediction errors of 3% or more for Gafchromic EBT film. Application of the WLS inverse prediction method resulted in a maximum prediction bias of 1.4 cGy and total prediction errors below 2% in a 0-400 cGy range. We developed a Monte-Carlo-based process to optimize calibrations, depending on the needs of the experiment. This type of thorough analysis can lead to a higher accuracy for film dosimetry.

A bioavailable strontium isoscape for Western Europe: A machine learning approach

PubMed Central

von Holstein, Isabella C. C.; Laffoon, Jason E.; Willmes, Malte; Liu, Xiao-Ming; Davies, Gareth R.

2018-01-01

Strontium isotope ratios (87Sr/86Sr) are gaining considerable interest as a geolocation tool and are now widely applied in archaeology, ecology, and forensic research. However, their application for provenance requires the development of baseline models predicting surficial 87Sr/86Sr variations (“isoscapes”). A variety of empirically-based and process-based models have been proposed to build terrestrial 87Sr/86Sr isoscapes but, in their current forms, those models are not mature enough to be integrated with continuous-probability surface models used in geographic assignment. In this study, we aim to overcome those limitations and to predict 87Sr/86Sr variations across Western Europe by combining process-based models and a series of remote-sensing geospatial products into a regression framework. We find that random forest regression significantly outperforms other commonly used regression and interpolation methods, and efficiently predicts the multi-scale patterning of 87Sr/86Sr variations by accounting for geological, geomorphological and atmospheric controls. Random forest regression also provides an easily interpretable and flexible framework to integrate different types of environmental auxiliary variables required to model the multi-scale patterning of 87Sr/86Sr variability. The method is transferable to different scales and resolutions and can be applied to the large collection of geospatial data available at local and global levels. The isoscape generated in this study provides the most accurate 87Sr/86Sr predictions in bioavailable strontium for Western Europe (R2 = 0.58 and RMSE = 0.0023) to date, as well as a conservative estimate of spatial uncertainty by applying quantile regression forest. We anticipate that the method presented in this study combined with the growing numbers of bioavailable 87Sr/86Sr data and satellite geospatial products will extend the applicability of the 87Sr/86Sr geo-profiling tool in provenance applications. PMID:29847595

The allometry of coarse root biomass: log-transformed linear regression or nonlinear regression?

PubMed

Lai, Jiangshan; Yang, Bo; Lin, Dunmei; Kerkhoff, Andrew J; Ma, Keping

2013-01-01

Precise estimation of root biomass is important for understanding carbon stocks and dynamics in forests. Traditionally, biomass estimates are based on allometric scaling relationships between stem diameter and coarse root biomass calculated using linear regression (LR) on log-transformed data. Recently, it has been suggested that nonlinear regression (NLR) is a preferable fitting method for scaling relationships. But while this claim has been contested on both theoretical and empirical grounds, and statistical methods have been developed to aid in choosing between the two methods in particular cases, few studies have examined the ramifications of erroneously applying NLR. Here, we use direct measurements of 159 trees belonging to three locally dominant species in east China to compare the LR and NLR models of diameter-root biomass allometry. We then contrast model predictions by estimating stand coarse root biomass based on census data from the nearby 24-ha Gutianshan forest plot and by testing the ability of the models to predict known root biomass values measured on multiple tropical species at the Pasoh Forest Reserve in Malaysia. Based on likelihood estimates for model error distributions, as well as the accuracy of extrapolative predictions, we find that LR on log-transformed data is superior to NLR for fitting diameter-root biomass scaling models. More importantly, inappropriately using NLR leads to grossly inaccurate stand biomass estimates, especially for stands dominated by smaller trees.

Spatial prediction of landslides using a hybrid machine learning approach based on Random Subspace and Classification and Regression Trees

NASA Astrophysics Data System (ADS)

Pham, Binh Thai; Prakash, Indra; Tien Bui, Dieu

2018-02-01

A hybrid machine learning approach of Random Subspace (RSS) and Classification And Regression Trees (CART) is proposed to develop a model named RSSCART for spatial prediction of landslides. This model is a combination of the RSS method which is known as an efficient ensemble technique and the CART which is a state of the art classifier. The Luc Yen district of Yen Bai province, a prominent landslide prone area of Viet Nam, was selected for the model development. Performance of the RSSCART model was evaluated through the Receiver Operating Characteristic (ROC) curve, statistical analysis methods, and the Chi Square test. Results were compared with other benchmark landslide models namely Support Vector Machines (SVM), single CART, Naïve Bayes Trees (NBT), and Logistic Regression (LR). In the development of model, ten important landslide affecting factors related with geomorphology, geology and geo-environment were considered namely slope angles, elevation, slope aspect, curvature, lithology, distance to faults, distance to rivers, distance to roads, and rainfall. Performance of the RSSCART model (AUC = 0.841) is the best compared with other popular landslide models namely SVM (0.835), single CART (0.822), NBT (0.821), and LR (0.723). These results indicate that performance of the RSSCART is a promising method for spatial landslide prediction.

Statistical Approaches for Spatiotemporal Prediction of Low Flows

NASA Astrophysics Data System (ADS)

Fangmann, A.; Haberlandt, U.

2017-12-01

An adequate assessment of regional climate change impacts on streamflow requires the integration of various sources of information and modeling approaches. This study proposes simple statistical tools for inclusion into model ensembles, which are fast and straightforward in their application, yet able to yield accurate streamflow predictions in time and space. Target variables for all approaches are annual low flow indices derived from a data set of 51 records of average daily discharge for northwestern Germany. The models require input of climatic data in the form of meteorological drought indices, derived from observed daily climatic variables, averaged over the streamflow gauges' catchments areas. Four different modeling approaches are analyzed. Basis for all pose multiple linear regression models that estimate low flows as a function of a set of meteorological indices and/or physiographic and climatic catchment descriptors. For the first method, individual regression models are fitted at each station, predicting annual low flow values from a set of annual meteorological indices, which are subsequently regionalized using a set of catchment characteristics. The second method combines temporal and spatial prediction within a single panel data regression model, allowing estimation of annual low flow values from input of both annual meteorological indices and catchment descriptors. The third and fourth methods represent non-stationary low flow frequency analyses and require fitting of regional distribution functions. Method three is subject to a spatiotemporal prediction of an index value, method four to estimation of L-moments that adapt the regional frequency distribution to the at-site conditions. The results show that method two outperforms successive prediction in time and space. Method three also shows a high performance in the near future period, but since it relies on a stationary distribution, its application for prediction of far future changes may be problematic. Spatiotemporal prediction of L-moments appeared highly uncertain for higher-order moments resulting in unrealistic future low flow values. All in all, the results promote an inclusion of simple statistical methods in climate change impact assessment.

Hyperspectral imaging for predicting the allicin and soluble solid content of garlic with variable selection algorithms and chemometric models.

PubMed

Rahman, Anisur; Faqeerzada, Mohammad A; Cho, Byoung-Kwan

2018-03-14

Allicin and soluble solid content (SSC) in garlic is the responsible for its pungent flavor and odor. However, current conventional methods such as the use of high-pressure liquid chromatography and a refractometer have critical drawbacks in that they are time-consuming, labor-intensive and destructive procedures. The present study aimed to predict allicin and SSC in garlic using hyperspectral imaging in combination with variable selection algorithms and calibration models. Hyperspectral images of 100 garlic cloves were acquired that covered two spectral ranges, from which the mean spectra of each clove were extracted. The calibration models included partial least squares (PLS) and least squares-support vector machine (LS-SVM) regression, as well as different spectral pre-processing techniques, from which the highest performing spectral preprocessing technique and spectral range were selected. Then, variable selection methods, such as regression coefficients, variable importance in projection (VIP) and the successive projections algorithm (SPA), were evaluated for the selection of effective wavelengths (EWs). Furthermore, PLS and LS-SVM regression methods were applied to quantitatively predict the quality attributes of garlic using the selected EWs. Of the established models, the SPA-LS-SVM model obtained an Rpred2 of 0.90 and standard error of prediction (SEP) of 1.01% for SSC prediction, whereas the VIP-LS-SVM model produced the best result with an Rpred2 of 0.83 and SEP of 0.19 mg g -1 for allicin prediction in the range 1000-1700 nm. Furthermore, chemical images of garlic were developed using the best predictive model to facilitate visualization of the spatial distributions of allicin and SSC. The present study clearly demonstrates that hyperspectral imaging combined with an appropriate chemometrics method can potentially be employed as a fast, non-invasive method to predict the allicin and SSC in garlic. © 2018 Society of Chemical Industry. © 2018 Society of Chemical Industry.

Applying quantitative adiposity feature analysis models to predict benefit of bevacizumab-based chemotherapy in ovarian cancer patients

NASA Astrophysics Data System (ADS)

Wang, Yunzhi; Qiu, Yuchen; Thai, Theresa; More, Kathleen; Ding, Kai; Liu, Hong; Zheng, Bin

2016-03-01

How to rationally identify epithelial ovarian cancer (EOC) patients who will benefit from bevacizumab or other antiangiogenic therapies is a critical issue in EOC treatments. The motivation of this study is to quantitatively measure adiposity features from CT images and investigate the feasibility of predicting potential benefit of EOC patients with or without receiving bevacizumab-based chemotherapy treatment using multivariate statistical models built based on quantitative adiposity image features. A dataset involving CT images from 59 advanced EOC patients were included. Among them, 32 patients received maintenance bevacizumab after primary chemotherapy and the remaining 27 patients did not. We developed a computer-aided detection (CAD) scheme to automatically segment subcutaneous fat areas (VFA) and visceral fat areas (SFA) and then extracted 7 adiposity-related quantitative features. Three multivariate data analysis models (linear regression, logistic regression and Cox proportional hazards regression) were performed respectively to investigate the potential association between the model-generated prediction results and the patients' progression-free survival (PFS) and overall survival (OS). The results show that using all 3 statistical models, a statistically significant association was detected between the model-generated results and both of the two clinical outcomes in the group of patients receiving maintenance bevacizumab (p<0.01), while there were no significant association for both PFS and OS in the group of patients without receiving maintenance bevacizumab. Therefore, this study demonstrated the feasibility of using quantitative adiposity-related CT image features based statistical prediction models to generate a new clinical marker and predict the clinical outcome of EOC patients receiving maintenance bevacizumab-based chemotherapy.

Implementations of geographically weighted lasso in spatial data with multicollinearity (Case study: Poverty modeling of Java Island)

NASA Astrophysics Data System (ADS)

Setiyorini, Anis; Suprijadi, Jadi; Handoko, Budhi

2017-03-01

Geographically Weighted Regression (GWR) is a regression model that takes into account the spatial heterogeneity effect. In the application of the GWR, inference on regression coefficients is often of interest, as is estimation and prediction of the response variable. Empirical research and studies have demonstrated that local correlation between explanatory variables can lead to estimated regression coefficients in GWR that are strongly correlated, a condition named multicollinearity. It later results on a large standard error on estimated regression coefficients, and, hence, problematic for inference on relationships between variables. Geographically Weighted Lasso (GWL) is a method which capable to deal with spatial heterogeneity and local multicollinearity in spatial data sets. GWL is a further development of GWR method, which adds a LASSO (Least Absolute Shrinkage and Selection Operator) constraint in parameter estimation. In this study, GWL will be applied by using fixed exponential kernel weights matrix to establish a poverty modeling of Java Island, Indonesia. The results of applying the GWL to poverty datasets show that this method stabilizes regression coefficients in the presence of multicollinearity and produces lower prediction and estimation error of the response variable than GWR does.

Daily Suspended Sediment Discharge Prediction Using Multiple Linear Regression and Artificial Neural Network

NASA Astrophysics Data System (ADS)

Uca; Toriman, Ekhwan; Jaafar, Othman; Maru, Rosmini; Arfan, Amal; Saleh Ahmar, Ansari

2018-01-01

Prediction of suspended sediment discharge in a catchments area is very important because it can be used to evaluation the erosion hazard, management of its water resources, water quality, hydrology project management (dams, reservoirs, and irrigation) and to determine the extent of the damage that occurred in the catchments. Multiple Linear Regression analysis and artificial neural network can be used to predict the amount of daily suspended sediment discharge. Regression analysis using the least square method, whereas artificial neural networks using Radial Basis Function (RBF) and feedforward multilayer perceptron with three learning algorithms namely Levenberg-Marquardt (LM), Scaled Conjugate Descent (SCD) and Broyden-Fletcher-Goldfarb-Shanno Quasi-Newton (BFGS). The number neuron of hidden layer is three to sixteen, while in output layer only one neuron because only one output target. The mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2 ) and coefficient of efficiency (CE) of the multiple linear regression (MLRg) value Model 2 (6 input variable independent) has the lowest the value of MAE and RMSE (0.0000002 and 13.6039) and highest R2 and CE (0.9971 and 0.9971). When compared between LM, SCG and RBF, the BFGS model structure 3-7-1 is the better and more accurate to prediction suspended sediment discharge in Jenderam catchment. The performance value in testing process, MAE and RMSE (13.5769 and 17.9011) is smallest, meanwhile R2 and CE (0.9999 and 0.9998) is the highest if it compared with the another BFGS Quasi-Newton model (6-3-1, 9-10-1 and 12-12-1). Based on the performance statistics value, MLRg, LM, SCG, BFGS and RBF suitable and accurately for prediction by modeling the non-linear complex behavior of suspended sediment responses to rainfall, water depth and discharge. The comparison between artificial neural network (ANN) and MLRg, the MLRg Model 2 accurately for to prediction suspended sediment discharge (kg/day) in Jenderan catchment area.

Application of third molar development and eruption models in estimating dental age in Malay sub-adults.

PubMed

Mohd Yusof, Mohd Yusmiaidil Putera; Cauwels, Rita; Deschepper, Ellen; Martens, Luc

2015-08-01

The third molar development (TMD) has been widely utilized as one of the radiographic method for dental age estimation. By using the same radiograph of the same individual, third molar eruption (TME) information can be incorporated to the TMD regression model. This study aims to evaluate the performance of dental age estimation in individual method models and the combined model (TMD and TME) based on the classic regressions of multiple linear and principal component analysis. A sample of 705 digital panoramic radiographs of Malay sub-adults aged between 14.1 and 23.8 years was collected. The techniques described by Gleiser and Hunt (modified by Kohler) and Olze were employed to stage the TMD and TME, respectively. The data was divided to develop three respective models based on the two regressions of multiple linear and principal component analysis. The trained models were then validated on the test sample and the accuracy of age prediction was compared between each model. The coefficient of determination (R²) and root mean square error (RMSE) were calculated. In both genders, adjusted R² yielded an increment in the linear regressions of combined model as compared to the individual models. The overall decrease in RMSE was detected in combined model as compared to TMD (0.03-0.06) and TME (0.2-0.8). In principal component regression, low value of adjusted R(2) and high RMSE except in male were exhibited in combined model. Dental age estimation is better predicted using combined model in multiple linear regression models. Copyright © 2015 Elsevier Ltd and Faculty of Forensic and Legal Medicine. All rights reserved.

Optimal selection of MULTI-model downscaled ensembles for interannual and seasonal climate prediction in the eastern seaboard of Thailand

NASA Astrophysics Data System (ADS)

Bejranonda, W.; Koch, M.

2010-12-01

Because of the imminent threat of the water resources of the eastern seaboard of Thailand, a climate impact study has been carried out there. To that avail, a hydrological watershed model is being used to simulate the future water availability in the wake of possible climate change in the region. The hydrological model is forced by predictions from global climate models (GCMs) that are to be downscaled in an appropriate manner. The challenge at that stage of the climate impact analysis lies then the in the choice of the best GCM and the (statistical) downscaling method. In this study the selection of coarse grid resolution output of the GCMs, transferring information to the fine grid of local climate-hydrology is achieved by cross-correlation and multiple linear regression using meteorological data in the eastern seaboard of Thailand observed between 1970-1999. The grids of 20 atmosphere/ocean global climate models (AOGCM), covering latitude 12.5-15.0 N and longitude 100.0-102.5 E were examined using the Climate-Change Scenario Generator (SCENGEN). With that tool the model efficiency of the prediction of daily precipitation and mean temperature was calculated by comparing the 1980-1999 ECMWF reanalysis predictions with the observed data during that time period. The root means square errors of the predictions were considered and ranked to select the top 5 models, namely, BCCR-BCM2.0, GISS-ER, ECHO-G, ECHAM5/MPI-OM and PCM. The daily time-series of 338 predictors in 9 runs of the 5 selected models were gathered from the CMIP3 multi-model database. Monthly time-serial cross-correlations between the climate predictors and the meteorological measurements from 25 rainfall, 4 minimum and maximum temperature, 4 humidity and 2 solar radiation stations in the study area were then computed and ranked. Using the ranked predictors, a multiple-linear regression model (downscaling transfer model) to forecast the local climate was set up. To improve the prediction power of this GCM downscaling approach, the regression equations were considered as a dynamic regression model that can alter the predictor by seasonal variation. The possible seasonal effect was examined for the 1974-1999 period which was equally divided into a calibration and verification sub-period. The calibrated model using the whole observed time-series was compared with the models separated into 2 seasons; dry and wet, 3 seasons; winter, summer and rainy, and 4 seasons; dry, pre-monsoon, first monsoon and second monsoon. The verification power of the various model variants was measured considering Akaike's information criterion (AIC) and the Nash-Sutcliffe coefficient of the corresponding model fit. The results show that the 4-seasons-variation prediction works best. The highest efficiency for the prediction of rainfall is achieved for the dry season, Oct-Mar, whereas the smallest efficiency is obtained in the monsoon seasons. The overall number of predictor giving top efficiency lies between 3 and 20 in the regression models. In the next, still ongoing stage of the climate impact study the predictions from this new, seasonally optimized downscaling transfer model are being used in the simulations of the future hydrological water budget in that region of Thailand.

Retention modelling of polychlorinated biphenyls in comprehensive two-dimensional gas chromatography.

PubMed

D'Archivio, Angelo Antonio; Incani, Angela; Ruggieri, Fabrizio

2011-01-01

In this paper, we use a quantitative structure-retention relationship (QSRR) method to predict the retention times of polychlorinated biphenyls (PCBs) in comprehensive two-dimensional gas chromatography (GC×GC). We analyse the GC×GC retention data taken from the literature by comparing predictive capability of different regression methods. The various models are generated using 70 out of 209 PCB congeners in the calibration stage, while their predictive performance is evaluated on the remaining 139 compounds. The two-dimensional chromatogram is initially estimated by separately modelling retention times of PCBs in the first and in the second column ((1) t (R) and (2) t (R), respectively). In particular, multilinear regression (MLR) combined with genetic algorithm (GA) variable selection is performed to extract two small subsets of predictors for (1) t (R) and (2) t (R) from a large set of theoretical molecular descriptors provided by the popular software Dragon, which after removal of highly correlated or almost constant variables consists of 237 structure-related quantities. Based on GA-MLR analysis, a four-dimensional and a five-dimensional relationship modelling (1) t (R) and (2) t (R), respectively, are identified. Single-response partial least square (PLS-1) regression is alternatively applied to independently model (1) t (R) and (2) t (R) without the need for preliminary GA variable selection. Further, we explore the possibility of predicting the two-dimensional chromatogram of PCBs in a single calibration procedure by using a two-response PLS (PLS-2) model or a feed-forward artificial neural network (ANN) with two output neurons. In the first case, regression is carried out on the full set of 237 descriptors, while the variables previously selected by GA-MLR are initially considered as ANN inputs and subjected to a sensitivity analysis to remove the redundant ones. Results show PLS-1 regression exhibits a noticeably better descriptive and predictive performance than the other investigated approaches. The observed values of determination coefficients for (1) t (R) and (2) t (R) in calibration (0.9999 and 0.9993, respectively) and prediction (0.9987 and 0.9793, respectively) provided by PLS-1 demonstrate that GC×GC behaviour of PCBs is properly modelled. In particular, the predicted two-dimensional GC×GC chromatogram of 139 PCBs not involved in the calibration stage closely resembles the experimental one. Based on the above lines of evidence, the proposed approach ensures accurate simulation of the whole GC×GC chromatogram of PCBs using experimental determination of only 1/3 retention data of representative congeners.

Hierarchical Bayesian spatial models for predicting multiple forest variables using waveform LiDAR, hyperspectral imagery, and large inventory datasets

USGS Publications Warehouse

Finley, Andrew O.; Banerjee, Sudipto; Cook, Bruce D.; Bradford, John B.

2013-01-01

In this paper we detail a multivariate spatial regression model that couples LiDAR, hyperspectral and forest inventory data to predict forest outcome variables at a high spatial resolution. The proposed model is used to analyze forest inventory data collected on the US Forest Service Penobscot Experimental Forest (PEF), ME, USA. In addition to helping meet the regression model's assumptions, results from the PEF analysis suggest that the addition of multivariate spatial random effects improves model fit and predictive ability, compared with two commonly applied modeling approaches. This improvement results from explicitly modeling the covariation among forest outcome variables and spatial dependence among observations through the random effects. Direct application of such multivariate models to even moderately large datasets is often computationally infeasible because of cubic order matrix algorithms involved in estimation. We apply a spatial dimension reduction technique to help overcome this computational hurdle without sacrificing richness in modeling.

Evaluation of regression-based 3-D shoulder rhythms.

PubMed

Xu, Xu; Dickerson, Clark R; Lin, Jia-Hua; McGorry, Raymond W

2016-08-01

The movements of the humerus, the clavicle, and the scapula are not completely independent. The coupled pattern of movement of these bones is called the shoulder rhythm. To date, multiple studies have focused on providing regression-based 3-D shoulder rhythms, in which the orientations of the clavicle and the scapula are estimated by the orientation of the humerus. In this study, six existing regression-based shoulder rhythms were evaluated by an independent dataset in terms of their predictability. The datasets include the measured orientations of the humerus, the clavicle, and the scapula of 14 participants over 118 different upper arm postures. The predicted orientations of the clavicle and the scapula were derived from applying those regression-based shoulder rhythms to the humerus orientation. The results indicated that none of those regression-based shoulder rhythms provides consistently more accurate results than the others. For all the joint angles and all the shoulder rhythms, the RMSE are all greater than 5°. Among those shoulder rhythms, the scapula lateral/medial rotation has the strongest correlation between the predicted and the measured angles, while the other thoracoclavicular and thoracoscapular bone orientation angles only showed a weak to moderate correlation. Since the regression-based shoulder rhythm has been adopted for shoulder biomechanical models to estimate shoulder muscle activities and structure loads, there needs to be further investigation on how the predicted error from the shoulder rhythm affects the output of the biomechanical model. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

Detecting influential observations in nonlinear regression modeling of groundwater flow

USGS Publications Warehouse

Yager, Richard M.

1998-01-01

Nonlinear regression is used to estimate optimal parameter values in models of groundwater flow to ensure that differences between predicted and observed heads and flows do not result from nonoptimal parameter values. Parameter estimates can be affected, however, by observations that disproportionately influence the regression, such as outliers that exert undue leverage on the objective function. Certain statistics developed for linear regression can be used to detect influential observations in nonlinear regression if the models are approximately linear. This paper discusses the application of Cook's D, which measures the effect of omitting a single observation on a set of estimated parameter values, and the statistical parameter DFBETAS, which quantifies the influence of an observation on each parameter. The influence statistics were used to (1) identify the influential observations in the calibration of a three-dimensional, groundwater flow model of a fractured-rock aquifer through nonlinear regression, and (2) quantify the effect of omitting influential observations on the set of estimated parameter values. Comparison of the spatial distribution of Cook's D with plots of model sensitivity shows that influential observations correspond to areas where the model heads are most sensitive to certain parameters, and where predicted groundwater flow rates are largest. Five of the six discharge observations were identified as influential, indicating that reliable measurements of groundwater flow rates are valuable data in model calibration. DFBETAS are computed and examined for an alternative model of the aquifer system to identify a parameterization error in the model design that resulted in overestimation of the effect of anisotropy on horizontal hydraulic conductivity.

Watershed regressions for pesticides (warp) models for predicting atrazine concentrations in Corn Belt streams

USGS Publications Warehouse

Stone, Wesley W.; Gilliom, Robert J.

2012-01-01

Watershed Regressions for Pesticides (WARP) models, previously developed for atrazine at the national scale, are improved for application to the United States (U.S.) Corn Belt region by developing region-specific models that include watershed characteristics that are influential in predicting atrazine concentration statistics within the Corn Belt. WARP models for the Corn Belt (WARP-CB) were developed for annual maximum moving-average (14-, 21-, 30-, 60-, and 90-day durations) and annual 95th-percentile atrazine concentrations in streams of the Corn Belt region. The WARP-CB models accounted for 53 to 62% of the variability in the various concentration statistics among the model-development sites. Model predictions were within a factor of 5 of the observed concentration statistic for over 90% of the model-development sites. The WARP-CB residuals and uncertainty are lower than those of the National WARP model for the same sites. Although atrazine-use intensity is the most important explanatory variable in the National WARP models, it is not a significant variable in the WARP-CB models. The WARP-CB models provide improved predictions for Corn Belt streams draining watersheds with atrazine-use intensities of 17 kg/km2 of watershed area or greater.

A menu-driven software package of Bayesian nonparametric (and parametric) mixed models for regression analysis and density estimation.

PubMed

Karabatsos, George

2017-02-01

Most of applied statistics involves regression analysis of data. In practice, it is important to specify a regression model that has minimal assumptions which are not violated by data, to ensure that statistical inferences from the model are informative and not misleading. This paper presents a stand-alone and menu-driven software package, Bayesian Regression: Nonparametric and Parametric Models, constructed from MATLAB Compiler. Currently, this package gives the user a choice from 83 Bayesian models for data analysis. They include 47 Bayesian nonparametric (BNP) infinite-mixture regression models; 5 BNP infinite-mixture models for density estimation; and 31 normal random effects models (HLMs), including normal linear models. Each of the 78 regression models handles either a continuous, binary, or ordinal dependent variable, and can handle multi-level (grouped) data. All 83 Bayesian models can handle the analysis of weighted observations (e.g., for meta-analysis), and the analysis of left-censored, right-censored, and/or interval-censored data. Each BNP infinite-mixture model has a mixture distribution assigned one of various BNP prior distributions, including priors defined by either the Dirichlet process, Pitman-Yor process (including the normalized stable process), beta (two-parameter) process, normalized inverse-Gaussian process, geometric weights prior, dependent Dirichlet process, or the dependent infinite-probits prior. The software user can mouse-click to select a Bayesian model and perform data analysis via Markov chain Monte Carlo (MCMC) sampling. After the sampling completes, the software automatically opens text output that reports MCMC-based estimates of the model's posterior distribution and model predictive fit to the data. Additional text and/or graphical output can be generated by mouse-clicking other menu options. This includes output of MCMC convergence analyses, and estimates of the model's posterior predictive distribution, for selected functionals and values of covariates. The software is illustrated through the BNP regression analysis of real data.

Table Rock Lake Water-Clarity Assessment Using Landsat Thematic Mapper Satellite Data

USGS Publications Warehouse

Krizanich, Gary; Finn, Michael P.

2009-01-01

Water quality of Table Rock Lake in southwestern Missouri is assessed using Landsat Thematic Mapper satellite data. A pilot study uses multidate satellite image scenes in conjunction with physical measurements of secchi disk transparency collected by the Lakes of Missouri Volunteer Program to construct a regression model used to estimate water clarity. The natural log of secchi disk transparency is the dependent variable in the regression and the independent variables are Thematic Mapper band 1 (blue) reflectance and a ratio of the band 1 and band 3 (red) reflectance. The regression model can be used to reliably predict water clarity anywhere within the lake. A pixel-level lake map of predicted water clarity or computed trophic state can be produced from the model output. Information derived from this model can be used by water-resource managers to assess water quality and evaluate effects of changes in the watershed on water quality.

Aqua/Aura Updated Inclination Adjust Maneuver Performance Prediction Model

NASA Technical Reports Server (NTRS)

Boone, Spencer

2017-01-01

This presentation will discuss the updated Inclination Adjust Maneuver (IAM) performance prediction model that was developed for Aqua and Aura following the 2017 IAM series. This updated model uses statistical regression methods to identify potential long-term trends in maneuver parameters, yielding improved predictions when re-planning past maneuvers. The presentation has been reviewed and approved by Eric Moyer, ESMO Deputy Project Manager.

Learning accurate and interpretable models based on regularized random forests regression

PubMed Central

2014-01-01

Background Many biology related research works combine data from multiple sources in an effort to understand the underlying problems. It is important to find and interpret the most important information from these sources. Thus it will be beneficial to have an effective algorithm that can simultaneously extract decision rules and select critical features for good interpretation while preserving the prediction performance. Methods In this study, we focus on regression problems for biological data where target outcomes are continuous. In general, models constructed from linear regression approaches are relatively easy to interpret. However, many practical biological applications are nonlinear in essence where we can hardly find a direct linear relationship between input and output. Nonlinear regression techniques can reveal nonlinear relationship of data, but are generally hard for human to interpret. We propose a rule based regression algorithm that uses 1-norm regularized random forests. The proposed approach simultaneously extracts a small number of rules from generated random forests and eliminates unimportant features. Results We tested the approach on some biological data sets. The proposed approach is able to construct a significantly smaller set of regression rules using a subset of attributes while achieving prediction performance comparable to that of random forests regression. Conclusion It demonstrates high potential in aiding prediction and interpretation of nonlinear relationships of the subject being studied. PMID:25350120

Accounting for measurement error in log regression models with applications to accelerated testing.

PubMed

Richardson, Robert; Tolley, H Dennis; Evenson, William E; Lunt, Barry M

2018-01-01

In regression settings, parameter estimates will be biased when the explanatory variables are measured with error. This bias can significantly affect modeling goals. In particular, accelerated lifetime testing involves an extrapolation of the fitted model, and a small amount of bias in parameter estimates may result in a significant increase in the bias of the extrapolated predictions. Additionally, bias may arise when the stochastic component of a log regression model is assumed to be multiplicative when the actual underlying stochastic component is additive. To account for these possible sources of bias, a log regression model with measurement error and additive error is approximated by a weighted regression model which can be estimated using Iteratively Re-weighted Least Squares. Using the reduced Eyring equation in an accelerated testing setting, the model is compared to previously accepted approaches to modeling accelerated testing data with both simulations and real data.

[Risk factor analysis of the patients with solitary pulmonary nodules and establishment of a prediction model for the probability of malignancy].

PubMed

Wang, X; Xu, Y H; Du, Z Y; Qian, Y J; Xu, Z H; Chen, R; Shi, M H

2018-02-23

Objective: This study aims to analyze the relationship among the clinical features, radiologic characteristics and pathological diagnosis in patients with solitary pulmonary nodules, and establish a prediction model for the probability of malignancy. Methods: Clinical data of 372 patients with solitary pulmonary nodules who underwent surgical resection with definite postoperative pathological diagnosis were retrospectively analyzed. In these cases, we collected clinical and radiologic features including gender, age, smoking history, history of tumor, family history of cancer, the location of lesion, ground-glass opacity, maximum diameter, calcification, vessel convergence sign, vacuole sign, pleural indentation, speculation and lobulation. The cases were divided to modeling group (268 cases) and validation group (104 cases). A new prediction model was established by logistic regression analying the data from modeling group. Then the data of validation group was planned to validate the efficiency of the new model, and was compared with three classical models(Mayo model, VA model and LiYun model). With the calculated probability values for each model from validation group, SPSS 22.0 was used to draw the receiver operating characteristic curve, to assess the predictive value of this new model. Results: 112 benign SPNs and 156 malignant SPNs were included in modeling group. Multivariable logistic regression analysis showed that gender, age, history of tumor, ground -glass opacity, maximum diameter, and speculation were independent predictors of malignancy in patients with SPN( P <0.05). We calculated a prediction model for the probability of malignancy as follow: p =e(x)/(1+ e(x)), x=-4.8029-0.743×gender+ 0.057×age+ 1.306×history of tumor+ 1.305×ground-glass opacity+ 0.051×maximum diameter+ 1.043×speculation. When the data of validation group was added to the four-mathematical prediction model, The area under the curve of our mathematical prediction model was 0.742, which is greater than other models (Mayo 0.696, VA 0.634, LiYun 0.681), while the differences between any two of the four models were not significant ( P >0.05). Conclusions: Age of patient, gender, history of tumor, ground-glass opacity, maximum diameter and speculation are independent predictors of malignancy in patients with solitary pulmonary nodule. This logistic regression prediction mathematic model is not inferior to those classical models in estimating the prognosis of SPNs.

Transdermal Rivastigmine Delivery for Alzheimer Disease: Amenability of Exposure Predictions of Rivastigmine and Metabolite, NAP226-90, by Linear Regression Model Using Limited Samples.

PubMed

Srinivas, Nuggehally R

2016-01-01

Although an optimized delivery of rivastigmine for management of Alzhiemer disease (AD) is provided by the transdermal patch, it is critical to establish a limited sampling strategy for the measurement of exposure of rivastigmine/NAP226-90. The relationship Cmax versus AUC0-24h for rivastigmine/NAP226-90 was established by regression models. The derived regression equations enabled the prediction AUC0-24h for rivastigmine and NAP226-90. Models were evaluated using statistical criteria. Mixed model was used to predict AUC0-24h for rivastigmine/NAP226-90 from time points such as 8 (C8h), 12 (C12h), and 18 (C18h) hours. Excellent correlation was established for between Cmax and AUC0-24h for rivastigmine and NAP226-90. AUC0-24h predictions of either rivastigmine or NAP226-90 were within 0.8- to 1.25-fold difference. The RMSE in the AUC0-24h predictions ranged from 17.6% to 21.9%, and the R for prediction were greater than 0.96 for both rivastigmine and NAP226-90. Use of mixed model for C8h, C12h, and C18h resulted in AUC0-24h within 1.5-fold difference for rivastigmine or NAP226-90. Cmax of rivastigmine and NAP226-90 was highly correlated with the corresponding AUC0-24h values confirming the role of a time point closer to Cmax for an effective AUC measurement of rivastigmine or the metabolite.

Heritability estimations for inner muscular fat in Hereford cattle using random regressions

USDA-ARS?s Scientific Manuscript database

Random regressions make possible to make genetic predictions and parameters estimation across a gradient of environments, allowing a more accurate and beneficial use of animals as breeders in specific environments. The objective of this study was to use random regression models to estimate heritabil...

LASSO NTCP predictors for the incidence of xerostomia in patients with head and neck squamous cell carcinoma and nasopharyngeal carcinoma

PubMed Central

Lee, Tsair-Fwu; Liou, Ming-Hsiang; Huang, Yu-Jie; Chao, Pei-Ju; Ting, Hui-Min; Lee, Hsiao-Yi

2014-01-01

To predict the incidence of moderate-to-severe patient-reported xerostomia among head and neck squamous cell carcinoma (HNSCC) and nasopharyngeal carcinoma (NPC) patients treated with intensity-modulated radiotherapy (IMRT). Multivariable normal tissue complication probability (NTCP) models were developed by using quality of life questionnaire datasets from 152 patients with HNSCC and 84 patients with NPC. The primary endpoint was defined as moderate-to-severe xerostomia after IMRT. The numbers of predictive factors for a multivariable logistic regression model were determined using the least absolute shrinkage and selection operator (LASSO) with bootstrapping technique. Four predictive models were achieved by LASSO with the smallest number of factors while preserving predictive value with higher AUC performance. For all models, the dosimetric factors for the mean dose given to the contralateral and ipsilateral parotid gland were selected as the most significant predictors. Followed by the different clinical and socio-economic factors being selected, namely age, financial status, T stage, and education for different models were chosen. The predicted incidence of xerostomia for HNSCC and NPC patients can be improved by using multivariable logistic regression models with LASSO technique. The predictive model developed in HNSCC cannot be generalized to NPC cohort treated with IMRT without validation and vice versa. PMID:25163814

The importance of molecular structures, endpoints' values, and predictivity parameters in QSAR research: QSAR analysis of a series of estrogen receptor binders.

PubMed

Li, Jiazhong; Gramatica, Paola

2010-11-01

Quantitative structure-activity relationship (QSAR) methodology aims to explore the relationship between molecular structures and experimental endpoints, producing a model for the prediction of new data; the predictive performance of the model must be checked by external validation. Clearly, the qualities of chemical structure information and experimental endpoints, as well as the statistical parameters used to verify the external predictivity have a strong influence on QSAR model reliability. Here, we emphasize the importance of these three aspects by analyzing our models on estrogen receptor binders (Endocrine disruptor knowledge base (EDKB) database). Endocrine disrupting chemicals, which mimic or antagonize the endogenous hormones such as estrogens, are a hot topic in environmental and toxicological sciences. QSAR shows great values in predicting the estrogenic activity and exploring the interactions between the estrogen receptor and ligands. We have verified our previously published model for additional external validation on new EDKB chemicals. Having found some errors in the used 3D molecular conformations, we redevelop a new model using the same data set with corrected structures, the same method (ordinary least-square regression, OLS) and DRAGON descriptors. The new model, based on some different descriptors, is more predictive on external prediction sets. Three different formulas to calculate correlation coefficient for the external prediction set (Q2 EXT) were compared, and the results indicated that the new proposal of Consonni et al. had more reasonable results, consistent with the conclusions from regression line, Williams plot and root mean square error (RMSE) values. Finally, the importance of reliable endpoints values has been highlighted by comparing the classification assignments of EDKB with those of another estrogen receptor binders database (METI): we found that 16.1% assignments of the common compounds were opposite (20 among 124 common compounds). In order to verify the real assignments for these inconsistent compounds, we predicted these samples, as a blind external set, by our regression models and compared the results with the two databases. The results indicated that most of the predictions were consistent with METI. Furthermore, we built a kNN classification model using the 104 consistent compounds to predict those inconsistent ones, and most of the predictions were also in agreement with METI database.

Discriminating between adaptive and carcinogenic liver hypertrophy in rat studies using logistic ridge regression analysis of toxicogenomic data: The mode of action and predictive models.

PubMed

Liu, Shujie; Kawamoto, Taisuke; Morita, Osamu; Yoshinari, Kouichi; Honda, Hiroshi

2017-03-01

Chemical exposure often results in liver hypertrophy in animal tests, characterized by increased liver weight, hepatocellular hypertrophy, and/or cell proliferation. While most of these changes are considered adaptive responses, there is concern that they may be associated with carcinogenesis. In this study, we have employed a toxicogenomic approach using a logistic ridge regression model to identify genes responsible for liver hypertrophy and hypertrophic hepatocarcinogenesis and to develop a predictive model for assessing hypertrophy-inducing compounds. Logistic regression models have previously been used in the quantification of epidemiological risk factors. DNA microarray data from the Toxicogenomics Project-Genomics Assisted Toxicity Evaluation System were used to identify hypertrophy-related genes that are expressed differently in hypertrophy induced by carcinogens and non-carcinogens. Data were collected for 134 chemicals (72 non-hypertrophy-inducing chemicals, 27 hypertrophy-inducing non-carcinogenic chemicals, and 15 hypertrophy-inducing carcinogenic compounds). After applying logistic ridge regression analysis, 35 genes for liver hypertrophy (e.g., Acot1 and Abcc3) and 13 genes for hypertrophic hepatocarcinogenesis (e.g., Asns and Gpx2) were selected. The predictive models built using these genes were 94.8% and 82.7% accurate, respectively. Pathway analysis of the genes indicates that, aside from a xenobiotic metabolism-related pathway as an adaptive response for liver hypertrophy, amino acid biosynthesis and oxidative responses appear to be involved in hypertrophic hepatocarcinogenesis. Early detection and toxicogenomic characterization of liver hypertrophy using our models may be useful for predicting carcinogenesis. In addition, the identified genes provide novel insight into discrimination between adverse hypertrophy associated with carcinogenesis and adaptive hypertrophy in risk assessment. Copyright © 2017 Elsevier Inc. All rights reserved.

Machine learning approaches to the social determinants of health in the health and retirement study.

PubMed

Seligman, Benjamin; Tuljapurkar, Shripad; Rehkopf, David

2018-04-01

Social and economic factors are important predictors of health and of recognized importance for health systems. However, machine learning, used elsewhere in the biomedical literature, has not been extensively applied to study relationships between society and health. We investigate how machine learning may add to our understanding of social determinants of health using data from the Health and Retirement Study. A linear regression of age and gender, and a parsimonious theory-based regression additionally incorporating income, wealth, and education, were used to predict systolic blood pressure, body mass index, waist circumference, and telomere length. Prediction, fit, and interpretability were compared across four machine learning methods: linear regression, penalized regressions, random forests, and neural networks. All models had poor out-of-sample prediction. Most machine learning models performed similarly to the simpler models. However, neural networks greatly outperformed the three other methods. Neural networks also had good fit to the data ( R 2 between 0.4-0.6, versus <0.3 for all others). Across machine learning models, nine variables were frequently selected or highly weighted as predictors: dental visits, current smoking, self-rated health, serial-seven subtractions, probability of receiving an inheritance, probability of leaving an inheritance of at least $10,000, number of children ever born, African-American race, and gender. Some of the machine learning methods do not improve prediction or fit beyond simpler models, however, neural networks performed well. The predictors identified across models suggest underlying social factors that are important predictors of biological indicators of chronic disease, and that the non-linear and interactive relationships between variables fundamental to the neural network approach may be important to consider.

A regression-based 3-D shoulder rhythm.

PubMed

Xu, Xu; Lin, Jia-hua; McGorry, Raymond W

2014-03-21

In biomechanical modeling of the shoulder, it is important to know the orientation of each bone in the shoulder girdle when estimating the loads on each musculoskeletal element. However, because of the soft tissue overlying the bones, it is difficult to accurately derive the orientation of the clavicle and scapula using surface markers during dynamic movement. The purpose of this study is to develop two regression models which predict the orientation of the clavicle and the scapula. The first regression model uses humerus orientation and individual factors such as age, gender, and anthropometry data as the predictors. The second regression model includes only the humerus orientation as the predictor. Thirty-eight participants performed 118 static postures covering the volume of the right hand reach. The orientation of the thorax, clavicle, scapula and humerus were measured with a motion tracking system. Regression analysis was performed on the Euler angles decomposed from the orientation of each bone from 26 randomly selected participants. The regression models were then validated with the remaining 12 participants. The results indicate that for the first model, the r(2) of the predicted orientation of the clavicle and the scapula ranged between 0.31 and 0.65, and the RMSE obtained from the validation dataset ranged from 6.92° to 10.39°. For the second model, the r(2) ranged between 0.19 and 0.57, and the RMSE obtained from the validation dataset ranged from 6.62° and 11.13°. The derived regression-based shoulder rhythm could be useful in future biomechanical modeling of the shoulder. Copyright © 2014 The Authors. Published by Elsevier Ltd.. All rights reserved.

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.

Assessing the prediction accuracy of a cure model for censored survival data with long-term survivors: Application to breast cancer data.

PubMed

Asano, Junichi; Hirakawa, Akihiro

2017-01-01

The Cox proportional hazards cure model is a survival model incorporating a cure rate with the assumption that the population contains both uncured and cured individuals. It contains a logistic regression for the cure rate, and a Cox regression to estimate the hazard for uncured patients. A single predictive model for both the cure and hazard can be developed by using a cure model that simultaneously predicts the cure rate and hazards for uncured patients; however, model selection is a challenge because of the lack of a measure for quantifying the predictive accuracy of a cure model. Recently, we developed an area under the receiver operating characteristic curve (AUC) for determining the cure rate in a cure model (Asano et al., 2014), but the hazards measure for uncured patients was not resolved. In this article, we propose novel C-statistics that are weighted by the patients' cure status (i.e., cured, uncured, or censored cases) for the cure model. The operating characteristics of the proposed C-statistics and their confidence interval were examined by simulation analyses. We also illustrate methods for predictive model selection and for further interpretation of variables using the proposed AUCs and C-statistics via application to breast cancer data.

A linear regression model for predicting PNW estuarine temperatures in a changing climate

EPA Science Inventory

Pacific Northwest coastal regions, estuaries, and associated ecosystems are vulnerable to the potential effects of climate change, especially to changes in nearshore water temperature. While predictive climate models simulate future air temperatures, no such projections exist for...

Prediction of HDR quality by combining perceptually transformed display measurements with machine learning

NASA Astrophysics Data System (ADS)

Choudhury, Anustup; Farrell, Suzanne; Atkins, Robin; Daly, Scott

2017-09-01

We present an approach to predict overall HDR display quality as a function of key HDR display parameters. We first performed subjective experiments on a high quality HDR display that explored five key HDR display parameters: maximum luminance, minimum luminance, color gamut, bit-depth and local contrast. Subjects rated overall quality for different combinations of these display parameters. We explored two models | a physical model solely based on physically measured display characteristics and a perceptual model that transforms physical parameters using human vision system models. For the perceptual model, we use a family of metrics based on a recently published color volume model (ICT-CP), which consists of the PQ luminance non-linearity (ST2084) and LMS-based opponent color, as well as an estimate of the display point spread function. To predict overall visual quality, we apply linear regression and machine learning techniques such as Multilayer Perceptron, RBF and SVM networks. We use RMSE and Pearson/Spearman correlation coefficients to quantify performance. We found that the perceptual model is better at predicting subjective quality than the physical model and that SVM is better at prediction than linear regression. The significance and contribution of each display parameter was investigated. In addition, we found that combined parameters such as contrast do not improve prediction. Traditional perceptual models were also evaluated and we found that models based on the PQ non-linearity performed better.

A Pre-Screening Questionnaire to Predict Non-24-Hour Sleep-Wake Rhythm Disorder (N24HSWD) among the Blind

PubMed Central

Flynn-Evans, Erin E.; Lockley, Steven W.

2016-01-01

Study Objectives: There is currently no questionnaire-based pre-screening tool available to detect non-24-hour sleep-wake rhythm disorder (N24HSWD) among blind patients. Our goal was to develop such a tool, derived from gold standard, objective hormonal measures of circadian entrainment status, for the detection of N24HSWD among those with visual impairment. Methods: We evaluated the contribution of 40 variables in their ability to predict N24HSWD among 127 blind women, classified using urinary 6-sulfatoxymelatonin period, an objective marker of circadian entrainment status in this population. We subjected the 40 candidate predictors to 1,000 bootstrapped iterations of a logistic regression forward selection model to predict N24HSWD, with model inclusion set at the p < 0.05 level. We removed any predictors that were not selected at least 1% of the time in the 1,000 bootstrapped models and applied a second round of 1,000 bootstrapped logistic regression forward selection models to the remaining 23 candidate predictors. We included all questions that were selected at least 10% of the time in the final model. We subjected the selected predictors to a final logistic regression model to predict N24SWD over 1,000 bootstrapped models to calculate the concordance statistic and adjusted optimism of the final model. We used this information to generate a predictive model and determined the sensitivity and specificity of the model. Finally, we applied the model to a cohort of 1,262 blind women who completed the survey, but did not collect urine samples. Results: The final model consisted of eight questions. The concordance statistic, adjusted for bootstrapping, was 0.85. The positive predictive value was 88%, the negative predictive value was 79%. Applying this model to our larger dataset of women, we found that 61% of those without light perception, and 27% with some degree of light perception, would be referred for further screening for N24HSWD. Conclusions: Our model has predictive utility sufficient to serve as a pre-screening questionnaire for N24HSWD among the blind. Citation: Flynn-Evans EE, Lockley SW. A pre-screening questionnaire to predict non-24-hour sleep-wake rhythm disorder (N24HSWD) among the blind. J Clin Sleep Med 2016;12(5):703–710. PMID:26951421

Building and validation of a prognostic model for predicting extracorporeal circuit clotting in patients with continuous renal replacement therapy.

PubMed

Fu, Xia; Liang, Xinling; Song, Li; Huang, Huigen; Wang, Jing; Chen, Yuanhan; Zhang, Li; Quan, Zilin; Shi, Wei

2014-04-01

To develop a predictive model for circuit clotting in patients with continuous renal replacement therapy (CRRT). A total of 425 cases were selected. 302 cases were used to develop a predictive model of extracorporeal circuit life span during CRRT without citrate anticoagulation in 24 h, and 123 cases were used to validate the model. The prediction formula was developed using multivariate Cox proportional-hazards regression analysis, from which a risk score was assigned. The mean survival time of the circuit was 15.0 ± 1.3 h, and the rate of circuit clotting was 66.6 % during 24 h of CRRT. Five significant variables were assigned a predicting score according to the regression coefficient: insufficient blood flow, no anticoagulation, hematocrit ≥0.37, lactic acid of arterial blood gas analysis ≤3 mmol/L and APTT < 44.2 s. The Hosmer-Lemeshow test showed no significant difference between the predicted and actual circuit clotting (R (2) = 0.232; P = 0.301). A risk score that includes the five above-mentioned variables can be used to predict the likelihood of extracorporeal circuit clotting in patients undergoing CRRT.

Application of principal component regression and artificial neural network in FT-NIR soluble solids content determination of intact pear fruit

NASA Astrophysics Data System (ADS)

Ying, Yibin; Liu, Yande; Fu, Xiaping; Lu, Huishan

2005-11-01

The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. However, majority of today's applications of ANNs is back-propagate feed-forward ANN (BP-ANN). In this paper, back-propagation artificial neural networks (BP-ANN) were applied for modeling soluble solid content (SSC) of intact pear from their Fourier transform near infrared (FT-NIR) spectra. One hundred and sixty-four pear samples were used to build the calibration models and evaluate the models predictive ability. The results are compared to the classical calibration approaches, i.e. principal component regression (PCR), partial least squares (PLS) and non-linear PLS (NPLS). The effects of the optimal methods of training parameters on the prediction model were also investigated. BP-ANN combine with principle component regression (PCR) resulted always better than the classical PCR, PLS and Weight-PLS methods, from the point of view of the predictive ability. Based on the results, it can be concluded that FT-NIR spectroscopy and BP-ANN models can be properly employed for rapid and nondestructive determination of fruit internal quality.

Error modeling for surrogates of dynamical systems using machine learning: Machine-learning-based error model for surrogates of dynamical systems

DOE PAGES

Trehan, Sumeet; Carlberg, Kevin T.; Durlofsky, Louis J.

2017-07-14

A machine learning–based framework for modeling the error introduced by surrogate models of parameterized dynamical systems is proposed. The framework entails the use of high-dimensional regression techniques (eg, random forests, and LASSO) to map a large set of inexpensively computed “error indicators” (ie, features) produced by the surrogate model at a given time instance to a prediction of the surrogate-model error in a quantity of interest (QoI). This eliminates the need for the user to hand-select a small number of informative features. The methodology requires a training set of parameter instances at which the time-dependent surrogate-model error is computed bymore » simulating both the high-fidelity and surrogate models. Using these training data, the method first determines regression-model locality (via classification or clustering) and subsequently constructs a “local” regression model to predict the time-instantaneous error within each identified region of feature space. We consider 2 uses for the resulting error model: (1) as a correction to the surrogate-model QoI prediction at each time instance and (2) as a way to statistically model arbitrary functions of the time-dependent surrogate-model error (eg, time-integrated errors). We then apply the proposed framework to model errors in reduced-order models of nonlinear oil-water subsurface flow simulations, with time-varying well-control (bottom-hole pressure) parameters. The reduced-order models used in this work entail application of trajectory piecewise linearization in conjunction with proper orthogonal decomposition. Moreover, when the first use of the method is considered, numerical experiments demonstrate consistent improvement in accuracy in the time-instantaneous QoI prediction relative to the original surrogate model, across a large number of test cases. When the second use is considered, results show that the proposed method provides accurate statistical predictions of the time- and well-averaged errors.« less

Error modeling for surrogates of dynamical systems using machine learning: Machine-learning-based error model for surrogates of dynamical systems

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

Trehan, Sumeet; Carlberg, Kevin T.; Durlofsky, Louis J.

A machine learning–based framework for modeling the error introduced by surrogate models of parameterized dynamical systems is proposed. The framework entails the use of high-dimensional regression techniques (eg, random forests, and LASSO) to map a large set of inexpensively computed “error indicators” (ie, features) produced by the surrogate model at a given time instance to a prediction of the surrogate-model error in a quantity of interest (QoI). This eliminates the need for the user to hand-select a small number of informative features. The methodology requires a training set of parameter instances at which the time-dependent surrogate-model error is computed bymore » simulating both the high-fidelity and surrogate models. Using these training data, the method first determines regression-model locality (via classification or clustering) and subsequently constructs a “local” regression model to predict the time-instantaneous error within each identified region of feature space. We consider 2 uses for the resulting error model: (1) as a correction to the surrogate-model QoI prediction at each time instance and (2) as a way to statistically model arbitrary functions of the time-dependent surrogate-model error (eg, time-integrated errors). We then apply the proposed framework to model errors in reduced-order models of nonlinear oil-water subsurface flow simulations, with time-varying well-control (bottom-hole pressure) parameters. The reduced-order models used in this work entail application of trajectory piecewise linearization in conjunction with proper orthogonal decomposition. Moreover, when the first use of the method is considered, numerical experiments demonstrate consistent improvement in accuracy in the time-instantaneous QoI prediction relative to the original surrogate model, across a large number of test cases. When the second use is considered, results show that the proposed method provides accurate statistical predictions of the time- and well-averaged errors.« less

Multitrait, Random Regression, or Simple Repeatability Model in High-Throughput Phenotyping Data Improve Genomic Prediction for Wheat Grain Yield.

PubMed

Sun, Jin; Rutkoski, Jessica E; Poland, Jesse A; Crossa, José; Jannink, Jean-Luc; Sorrells, Mark E

2017-07-01

High-throughput phenotyping (HTP) platforms can be used to measure traits that are genetically correlated with wheat ( L.) grain yield across time. Incorporating such secondary traits in the multivariate pedigree and genomic prediction models would be desirable to improve indirect selection for grain yield. In this study, we evaluated three statistical models, simple repeatability (SR), multitrait (MT), and random regression (RR), for the longitudinal data of secondary traits and compared the impact of the proposed models for secondary traits on their predictive abilities for grain yield. Grain yield and secondary traits, canopy temperature (CT) and normalized difference vegetation index (NDVI), were collected in five diverse environments for 557 wheat lines with available pedigree and genomic information. A two-stage analysis was applied for pedigree and genomic selection (GS). First, secondary traits were fitted by SR, MT, or RR models, separately, within each environment. Then, best linear unbiased predictions (BLUPs) of secondary traits from the above models were used in the multivariate prediction models to compare predictive abilities for grain yield. Predictive ability was substantially improved by 70%, on average, from multivariate pedigree and genomic models when including secondary traits in both training and test populations. Additionally, (i) predictive abilities slightly varied for MT, RR, or SR models in this data set, (ii) results indicated that including BLUPs of secondary traits from the MT model was the best in severe drought, and (iii) the RR model was slightly better than SR and MT models under drought environment. Copyright © 2017 Crop Science Society of America.

Nonparametric Stochastic Model for Uncertainty Quantifi cation of Short-term Wind Speed Forecasts

NASA Astrophysics Data System (ADS)

AL-Shehhi, A. M.; Chaouch, M.; Ouarda, T.

2014-12-01

Wind energy is increasing in importance as a renewable energy source due to its potential role in reducing carbon emissions. It is a safe, clean, and inexhaustible source of energy. The amount of wind energy generated by wind turbines is closely related to the wind speed. Wind speed forecasting plays a vital role in the wind energy sector in terms of wind turbine optimal operation, wind energy dispatch and scheduling, efficient energy harvesting etc. It is also considered during planning, design, and assessment of any proposed wind project. Therefore, accurate prediction of wind speed carries a particular importance and plays significant roles in the wind industry. Many methods have been proposed in the literature for short-term wind speed forecasting. These methods are usually based on modeling historical fixed time intervals of the wind speed data and using it for future prediction. The methods mainly include statistical models such as ARMA, ARIMA model, physical models for instance numerical weather prediction and artificial Intelligence techniques for example support vector machine and neural networks. In this paper, we are interested in estimating hourly wind speed measures in United Arab Emirates (UAE). More precisely, we predict hourly wind speed using a nonparametric kernel estimation of the regression and volatility functions pertaining to nonlinear autoregressive model with ARCH model, which includes unknown nonlinear regression function and volatility function already discussed in the literature. The unknown nonlinear regression function describe the dependence between the value of the wind speed at time t and its historical data at time t -1, t - 2, … , t - d. This function plays a key role to predict hourly wind speed process. The volatility function, i.e., the conditional variance given the past, measures the risk associated to this prediction. Since the regression and the volatility functions are supposed to be unknown, they are estimated using nonparametric kernel methods. In addition, to the pointwise hourly wind speed forecasts, a confidence interval is also provided which allows to quantify the uncertainty around the forecasts.

Incorporating local land use regression and satellite aerosol optical depth in a hybrid model of spatiotemporal PM2.5 exposures in the Mid-Atlantic states.

PubMed

Kloog, Itai; Nordio, Francesco; Coull, Brent A; Schwartz, Joel

2012-11-06

Satellite-derived aerosol optical depth (AOD) measurements have the potential to provide spatiotemporally resolved predictions of both long and short-term exposures, but previous studies have generally shown moderate predictive power and lacked detailed high spatio- temporal resolution predictions across large domains. We aimed at extending our previous work by validating our model in another region with different geographical and metrological characteristics, and incorporating fine scale land use regression and nonrandom missingness to better predict PM(2.5) concentrations for days with or without satellite AOD measures. We start by calibrating AOD data for 2000-2008 across the Mid-Atlantic. We used mixed models regressing PM(2.5) measurements against day-specific random intercepts, and fixed and random AOD and temperature slopes. We used inverse probability weighting to account for nonrandom missingness of AOD, nested regions within days to capture spatial variation in the daily calibration, and introduced a penalization method that reduces the dimensionality of the large number of spatial and temporal predictors without selecting different predictors in different locations. We then take advantage of the association between grid-cell specific AOD values and PM(2.5) monitoring data, together with associations between AOD values in neighboring grid cells to develop grid cell predictions when AOD is missing. Finally to get local predictions (at the resolution of 50 m), we regressed the residuals from the predictions for each monitor from these previous steps against the local land use variables specific for each monitor. "Out-of-sample" 10-fold cross-validation was used to quantify the accuracy of our predictions at each step. For all days without AOD values, model performance was excellent (mean "out-of-sample" R(2) = 0.81, year-to-year variation 0.79-0.84). Upon removal of outliers in the PM(2.5) monitoring data, the results of the cross validation procedure was even better (overall mean "out of sample"R(2) of 0.85). Further, cross validation results revealed no bias in the predicted concentrations (Slope of observed vs predicted = 0.97-1.01). Our model allows one to reliably assess short-term and long-term human exposures in order to investigate both the acute and effects of ambient particles, respectively.

Limited Sampling Strategy for Accurate Prediction of Pharmacokinetics of Saroglitazar: A 3-point Linear Regression Model Development and Successful Prediction of Human Exposure.

PubMed

Joshi, Shuchi N; Srinivas, Nuggehally R; Parmar, Deven V

2018-03-01

Our aim was to develop and validate the extrapolative performance of a regression model using a limited sampling strategy for accurate estimation of the area under the plasma concentration versus time curve for saroglitazar. Healthy subject pharmacokinetic data from a well-powered food-effect study (fasted vs fed treatments; n = 50) was used in this work. The first 25 subjects' serial plasma concentration data up to 72 hours and corresponding AUC 0-t (ie, 72 hours) from the fasting group comprised a training dataset to develop the limited sampling model. The internal datasets for prediction included the remaining 25 subjects from the fasting group and all 50 subjects from the fed condition of the same study. The external datasets included pharmacokinetic data for saroglitazar from previous single-dose clinical studies. Limited sampling models were composed of 1-, 2-, and 3-concentration-time points' correlation with AUC 0-t of saroglitazar. Only models with regression coefficients (R 2 ) >0.90 were screened for further evaluation. The best R 2 model was validated for its utility based on mean prediction error, mean absolute prediction error, and root mean square error. Both correlations between predicted and observed AUC 0-t of saroglitazar and verification of precision and bias using Bland-Altman plot were carried out. None of the evaluated 1- and 2-concentration-time points models achieved R 2 > 0.90. Among the various 3-concentration-time points models, only 4 equations passed the predefined criterion of R 2 > 0.90. Limited sampling models with time points 0.5, 2, and 8 hours (R 2 = 0.9323) and 0.75, 2, and 8 hours (R 2 = 0.9375) were validated. Mean prediction error, mean absolute prediction error, and root mean square error were <30% (predefined criterion) and correlation (r) was at least 0.7950 for the consolidated internal and external datasets of 102 healthy subjects for the AUC 0-t prediction of saroglitazar. The same models, when applied to the AUC 0-t prediction of saroglitazar sulfoxide, showed mean prediction error, mean absolute prediction error, and root mean square error <30% and correlation (r) was at least 0.9339 in the same pool of healthy subjects. A 3-concentration-time points limited sampling model predicts the exposure of saroglitazar (ie, AUC 0-t ) within predefined acceptable bias and imprecision limit. Same model was also used to predict AUC 0-∞ . The same limited sampling model was found to predict the exposure of saroglitazar sulfoxide within predefined criteria. This model can find utility during late-phase clinical development of saroglitazar in the patient population. Copyright © 2018 Elsevier HS Journals, Inc. All rights reserved.

Using Performance Data Gathered at Several Stages of Achievement in Predicting Subsequent Performance.

ERIC Educational Resources Information Center

Owen, Steven V.; Feldhusen, John F.

This study compares the effectiveness of three models of multivariate prediction for academic success in identifying the criterion variance of achievement in nursing education. The first model involves the use of an optimum set of predictors and one equation derived from a regression analysis on first semester grade average in predicting the…

Very-short-term wind power prediction by a hybrid model with single- and multi-step approaches

NASA Astrophysics Data System (ADS)

Mohammed, E.; Wang, S.; Yu, J.

2017-05-01

Very-short-term wind power prediction (VSTWPP) has played an essential role for the operation of electric power systems. This paper aims at improving and applying a hybrid method of VSTWPP based on historical data. The hybrid method is combined by multiple linear regressions and least square (MLR&LS), which is intended for reducing prediction errors. The predicted values are obtained through two sub-processes:1) transform the time-series data of actual wind power into the power ratio, and then predict the power ratio;2) use the predicted power ratio to predict the wind power. Besides, the proposed method can include two prediction approaches: single-step prediction (SSP) and multi-step prediction (MSP). WPP is tested comparatively by auto-regressive moving average (ARMA) model from the predicted values and errors. The validity of the proposed hybrid method is confirmed in terms of error analysis by using probability density function (PDF), mean absolute percent error (MAPE) and means square error (MSE). Meanwhile, comparison of the correlation coefficients between the actual values and the predicted values for different prediction times and window has confirmed that MSP approach by using the hybrid model is the most accurate while comparing to SSP approach and ARMA. The MLR&LS is accurate and promising for solving problems in WPP.

Mapping soil textural fractions across a large watershed in north-east Florida.

PubMed

Lamsal, S; Mishra, U

2010-08-01

Assessment of regional scale soil spatial variation and mapping their distribution is constrained by sparse data which are collected using field surveys that are labor intensive and cost prohibitive. We explored geostatistical (ordinary kriging-OK), regression (Regression Tree-RT), and hybrid methods (RT plus residual Sequential Gaussian Simulation-SGS) to map soil textural fractions across the Santa Fe River Watershed (3585 km(2)) in north-east Florida. Soil samples collected from four depths (L1: 0-30 cm, L2: 30-60 cm, L3: 60-120 cm, and L4: 120-180 cm) at 141 locations were analyzed for soil textural fractions (sand, silt and clay contents), and combined with textural data (15 profiles) assembled under the Florida Soil Characterization program. Textural fractions in L1 and L2 were autocorrelated, and spatially mapped across the watershed. OK performance was poor, which may be attributed to the sparse sampling. RT model structure varied among textural fractions, and the model explained variations ranged from 25% for L1 silt to 61% for L2 clay content. Regression residuals were simulated using SGS, and the average of simulated residuals were used to approximate regression residual distribution map, which were added to regression trend maps. Independent validation of the prediction maps showed that regression models performed slightly better than OK, and regression combined with average of simulated regression residuals improved predictions beyond the regression model. Sand content >90% in both 0-30 and 30-60 cm covered 80.6% of the watershed area. Copyright 2010 Elsevier Ltd. All rights reserved.

Clinical Decision Support Model to Predict Occlusal Force in Bruxism Patients.

PubMed

Thanathornwong, Bhornsawan; Suebnukarn, Siriwan

2017-10-01

The aim of this study was to develop a decision support model for the prediction of occlusal force from the size and color of articulating paper markings in bruxism patients. We used the information from the datasets of 30 bruxism patients in which digital measurements of the size and color of articulating paper markings (12-µm Hanel; Coltene/Whaledent GmbH, Langenau, Germany) on canine protected hard stabilization splints were measured in pixels (P) and in red (R), green (G), and blue (B) values using Adobe Photoshop software (Adobe Systems, San Jose, CA, USA). The occlusal force (F) was measured using T-Scan III (Tekscan Inc., South Boston, MA, USA). The multiple regression equation was applied to predict F from the P and RGB. Model evaluation was performed using the datasets from 10 new patients. The patient's occlusal force measured by T-Scan III was used as a 'gold standard' to compare with the occlusal force predicted by the multiple regression model. The results demonstrate that the correlation between the occlusal force and the pixels and RGB of the articulating paper markings was positive (F = 1.62×P + 0.07×R -0.08×G + 0.08×B + 4.74; R 2 = 0.34). There was a high degree of agreement between the occlusal force of the patient measured using T-Scan III and the occlusal force predicted by the model (kappa value = 0.82). The results obtained demonstrate that the multiple regression model can predict the occlusal force using the digital values for the size and color of the articulating paper markings in bruxism patients.

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.

Clinical Decision Support Model to Predict Occlusal Force in Bruxism Patients

PubMed Central

Thanathornwong, Bhornsawan

2017-01-01

Objectives The aim of this study was to develop a decision support model for the prediction of occlusal force from the size and color of articulating paper markings in bruxism patients. Methods We used the information from the datasets of 30 bruxism patients in which digital measurements of the size and color of articulating paper markings (12-µm Hanel; Coltene/Whaledent GmbH, Langenau, Germany) on canine protected hard stabilization splints were measured in pixels (P) and in red (R), green (G), and blue (B) values using Adobe Photoshop software (Adobe Systems, San Jose, CA, USA). The occlusal force (F) was measured using T-Scan III (Tekscan Inc., South Boston, MA, USA). The multiple regression equation was applied to predict F from the P and RGB. Model evaluation was performed using the datasets from 10 new patients. The patient's occlusal force measured by T-Scan III was used as a ‘gold standard’ to compare with the occlusal force predicted by the multiple regression model. Results The results demonstrate that the correlation between the occlusal force and the pixels and RGB of the articulating paper markings was positive (F = 1.62×P + 0.07×R –0.08×G + 0.08×B + 4.74; R2 = 0.34). There was a high degree of agreement between the occlusal force of the patient measured using T-Scan III and the occlusal force predicted by the model (kappa value = 0.82). Conclusions The results obtained demonstrate that the multiple regression model can predict the occlusal force using the digital values for the size and color of the articulating paper markings in bruxism patients. PMID:29181234

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

Reliability analysis of C-130 turboprop engine components using artificial neural network

NASA Astrophysics Data System (ADS)

Qattan, Nizar A.

In this study, we predict the failure rate of Lockheed C-130 Engine Turbine. More than thirty years of local operational field data were used for failure rate prediction and validation. The Weibull regression model and the Artificial Neural Network model including (feed-forward back-propagation, radial basis neural network, and multilayer perceptron neural network model); will be utilized to perform this study. For this purpose, the thesis will be divided into five major parts. First part deals with Weibull regression model to predict the turbine general failure rate, and the rate of failures that require overhaul maintenance. The second part will cover the Artificial Neural Network (ANN) model utilizing the feed-forward back-propagation algorithm as a learning rule. The MATLAB package will be used in order to build and design a code to simulate the given data, the inputs to the neural network are the independent variables, the output is the general failure rate of the turbine, and the failures which required overhaul maintenance. In the third part we predict the general failure rate of the turbine and the failures which require overhaul maintenance, using radial basis neural network model on MATLAB tool box. In the fourth part we compare the predictions of the feed-forward back-propagation model, with that of Weibull regression model, and radial basis neural network model. The results show that the failure rate predicted by the feed-forward back-propagation artificial neural network model is closer in agreement with radial basis neural network model compared with the actual field-data, than the failure rate predicted by the Weibull model. By the end of the study, we forecast the general failure rate of the Lockheed C-130 Engine Turbine, the failures which required overhaul maintenance and six categorical failures using multilayer perceptron neural network (MLP) model on DTREG commercial software. The results also give an insight into the reliability of the engine turbine under actual operating conditions, which can be used by aircraft operators for assessing system and component failures and customizing the maintenance programs recommended by the manufacturer.

Binary Logistic Regression Versus Boosted Regression Trees in Assessing Landslide Susceptibility for Multiple-Occurring Regional Landslide Events: Application to the 2009 Storm Event in Messina (Sicily, southern Italy).

NASA Astrophysics Data System (ADS)

Lombardo, L.; Cama, M.; Maerker, M.; Parisi, L.; Rotigliano, E.

2014-12-01

This study aims at comparing the performances of Binary Logistic Regression (BLR) and Boosted Regression Trees (BRT) methods in assessing landslide susceptibility for multiple-occurrence regional landslide events within the Mediterranean region. A test area was selected in the north-eastern sector of Sicily (southern Italy), corresponding to the catchments of the Briga and the Giampilieri streams both stretching for few kilometres from the Peloritan ridge (eastern Sicily, Italy) to the Ionian sea. This area was struck on the 1st October 2009 by an extreme climatic event resulting in thousands of rapid shallow landslides, mainly of debris flows and debris avalanches types involving the weathered layer of a low to high grade metamorphic bedrock. Exploiting the same set of predictors and the 2009 landslide archive, BLR- and BRT-based susceptibility models were obtained for the two catchments separately, adopting a random partition (RP) technique for validation; besides, the models trained in one of the two catchments (Briga) were tested in predicting the landslide distribution in the other (Giampilieri), adopting a spatial partition (SP) based validation procedure. All the validation procedures were based on multi-folds tests so to evaluate and compare the reliability of the fitting, the prediction skill, the coherence in the predictor selection and the precision of the susceptibility estimates. All the obtained models for the two methods produced very high predictive performances, with a general congruence between BLR and BRT in the predictor importance. In particular, the research highlighted that BRT-models reached a higher prediction performance with respect to BLR-models, for RP based modelling, whilst for the SP-based models the difference in predictive skills between the two methods dropped drastically, converging to an analogous excellent performance. However, when looking at the precision of the probability estimates, BLR demonstrated to produce more robust models in terms of selected predictors and coefficients, as well as of dispersion of the estimated probabilities around the mean value for each mapped pixel. The difference in the behaviour could be interpreted as the result of overfitting effects, which heavily affect decision tree classification more than logistic regression techniques.

Using a GIS model to assess terrestrial salamander response to alternative forest management plans

Treesearch

Eric J. Gustafson; Nathan L. Murphy; Thomas R. Crow

2001-01-01

A GIS model predicting the spatial distribution of terrestrial salamander abundance based on topography and forest age was developed using parameters derived from the literature. The model was tested by sampling salamander abundance across the full range of site conditions used in the model. A regression of the predictions of our GIS model against these sample data...

Extrapolation of a predictive model for growth of a low inoculum size of Salmonella typhimurium DT104 on chicken skin to higher inoculum sizes

USDA-ARS?s Scientific Manuscript database

Validation of model predictions for independent variables not included in model development can save time and money by identifying conditions for which new models are not needed. A single strain of Salmonella Typhimurium DT104 was used to develop a general regression neural network model for growth...

A Comparison of Conventional Linear Regression Methods and Neural Networks for Forecasting Educational Spending.

ERIC Educational Resources Information Center

Baker, Bruce D.; Richards, Craig E.

1999-01-01

Applies neural network methods for forecasting 1991-95 per-pupil expenditures in U.S. public elementary and secondary schools. Forecasting models included the National Center for Education Statistics' multivariate regression model and three neural architectures. Regarding prediction accuracy, neural network results were comparable or superior to…

Development of a hybrid proximal sensing method for rapid identification of petroleum contaminated soils.

PubMed

Chakraborty, Somsubhra; Weindorf, David C; Li, Bin; Ali Aldabaa, Abdalsamad Abdalsatar; Ghosh, Rakesh Kumar; Paul, Sathi; Nasim Ali, Md

2015-05-01

Using 108 petroleum contaminated soil samples, this pilot study proposed a new analytical approach of combining visible near-infrared diffuse reflectance spectroscopy (VisNIR DRS) and portable X-ray fluorescence spectrometry (PXRF) for rapid and improved quantification of soil petroleum contamination. Results indicated that an advanced fused model where VisNIR DRS spectra-based penalized spline regression (PSR) was used to predict total petroleum hydrocarbon followed by PXRF elemental data-based random forest regression was used to model the PSR residuals, it outperformed (R(2)=0.78, residual prediction deviation (RPD)=2.19) all other models tested, even producing better generalization than using VisNIR DRS alone (RPD's of 1.64, 1.86, and 1.96 for random forest, penalized spline regression, and partial least squares regression, respectively). Additionally, unsupervised principal component analysis using the PXRF+VisNIR DRS system qualitatively separated contaminated soils from control samples. Fusion of PXRF elemental data and VisNIR derivative spectra produced an optimized model for total petroleum hydrocarbon quantification in soils. Copyright © 2015 Elsevier B.V. All rights reserved.

Voxel-wise prostate cell density prediction using multiparametric magnetic resonance imaging and machine learning.

PubMed

Sun, Yu; Reynolds, Hayley M; Wraith, Darren; Williams, Scott; Finnegan, Mary E; Mitchell, Catherine; Murphy, Declan; Haworth, Annette

2018-04-26

There are currently no methods to estimate cell density in the prostate. This study aimed to develop predictive models to estimate prostate cell density from multiparametric magnetic resonance imaging (mpMRI) data at a voxel level using machine learning techniques. In vivo mpMRI data were collected from 30 patients before radical prostatectomy. Sequences included T2-weighted imaging, diffusion-weighted imaging and dynamic contrast-enhanced imaging. Ground truth cell density maps were computed from histology and co-registered with mpMRI. Feature extraction and selection were performed on mpMRI data. Final models were fitted using three regression algorithms including multivariate adaptive regression spline (MARS), polynomial regression (PR) and generalised additive model (GAM). Model parameters were optimised using leave-one-out cross-validation on the training data and model performance was evaluated on test data using root mean square error (RMSE) measurements. Predictive models to estimate voxel-wise prostate cell density were successfully trained and tested using the three algorithms. The best model (GAM) achieved a RMSE of 1.06 (± 0.06) × 10 3 cells/mm 2 and a relative deviation of 13.3 ± 0.8%. Prostate cell density can be quantitatively estimated non-invasively from mpMRI data using high-quality co-registered data at a voxel level. These cell density predictions could be used for tissue classification, treatment response evaluation and personalised radiotherapy.

Bitterness intensity prediction of berberine hydrochloride using an electronic tongue and a GA-BP neural network.

PubMed

Liu, Ruixin; Zhang, Xiaodong; Zhang, Lu; Gao, Xiaojie; Li, Huiling; Shi, Junhan; Li, Xuelin

2014-06-01

The aim of this study was to predict the bitterness intensity of a drug using an electronic tongue (e-tongue). The model drug of berberine hydrochloride was used to establish a bitterness prediction model (BPM), based on the taste evaluation of bitterness intensity by a taste panel, the data provided by the e-tongue and a genetic algorithm-back-propagation neural network (GA-BP) modeling method. The modeling characteristics of the GA-BP were compared with those of multiple linear regression, partial least square regression and BP methods. The determination coefficient of the BPM was 0.99965±0.00004, the root mean square error of cross-validation was 0.1398±0.0488 and the correlation coefficient of the cross-validation between the true and predicted values was 0.9959±0.0027. The model is superior to the other three models based on these indicators. In conclusion, the model established in this study has a high fitting degree and may be used for the bitterness prediction modeling of berberine hydrochloride of different concentrations. The model also provides a reference for the generation of BPMs of other drugs. Additionally, the algorithm of the study is able to conduct a rapid and accurate quantitative analysis of the data provided by the e-tongue.

Bitterness intensity prediction of berberine hydrochloride using an electronic tongue and a GA-BP neural network

PubMed Central

LIU, RUIXIN; ZHANG, XIAODONG; ZHANG, LU; GAO, XIAOJIE; LI, HUILING; SHI, JUNHAN; LI, XUELIN

2014-01-01

The aim of this study was to predict the bitterness intensity of a drug using an electronic tongue (e-tongue). The model drug of berberine hydrochloride was used to establish a bitterness prediction model (BPM), based on the taste evaluation of bitterness intensity by a taste panel, the data provided by the e-tongue and a genetic algorithm-back-propagation neural network (GA-BP) modeling method. The modeling characteristics of the GA-BP were compared with those of multiple linear regression, partial least square regression and BP methods. The determination coefficient of the BPM was 0.99965±0.00004, the root mean square error of cross-validation was 0.1398±0.0488 and the correlation coefficient of the cross-validation between the true and predicted values was 0.9959±0.0027. The model is superior to the other three models based on these indicators. In conclusion, the model established in this study has a high fitting degree and may be used for the bitterness prediction modeling of berberine hydrochloride of different concentrations. The model also provides a reference for the generation of BPMs of other drugs. Additionally, the algorithm of the study is able to conduct a rapid and accurate quantitative analysis of the data provided by the e-tongue. PMID:24926369

A comparative analysis of predictive models of morbidity in intensive care unit after cardiac surgery - part II: an illustrative example.

PubMed

Cevenini, Gabriele; Barbini, Emanuela; Scolletta, Sabino; Biagioli, Bonizella; Giomarelli, Pierpaolo; Barbini, Paolo

2007-11-22

Popular predictive models for estimating morbidity probability after heart surgery are compared critically in a unitary framework. The study is divided into two parts. In the first part modelling techniques and intrinsic strengths and weaknesses of different approaches were discussed from a theoretical point of view. In this second part the performances of the same models are evaluated in an illustrative example. Eight models were developed: Bayes linear and quadratic models, k-nearest neighbour model, logistic regression model, Higgins and direct scoring systems and two feed-forward artificial neural networks with one and two layers. Cardiovascular, respiratory, neurological, renal, infectious and hemorrhagic complications were defined as morbidity. Training and testing sets each of 545 cases were used. The optimal set of predictors was chosen among a collection of 78 preoperative, intraoperative and postoperative variables by a stepwise procedure. Discrimination and calibration were evaluated by the area under the receiver operating characteristic curve and Hosmer-Lemeshow goodness-of-fit test, respectively. Scoring systems and the logistic regression model required the largest set of predictors, while Bayesian and k-nearest neighbour models were much more parsimonious. In testing data, all models showed acceptable discrimination capacities, however the Bayes quadratic model, using only three predictors, provided the best performance. All models showed satisfactory generalization ability: again the Bayes quadratic model exhibited the best generalization, while artificial neural networks and scoring systems gave the worst results. Finally, poor calibration was obtained when using scoring systems, k-nearest neighbour model and artificial neural networks, while Bayes (after recalibration) and logistic regression models gave adequate results. Although all the predictive models showed acceptable discrimination performance in the example considered, the Bayes and logistic regression models seemed better than the others, because they also had good generalization and calibration. The Bayes quadratic model seemed to be a convincing alternative to the much more usual Bayes linear and logistic regression models. It showed its capacity to identify a minimum core of predictors generally recognized as essential to pragmatically evaluate the risk of developing morbidity after heart surgery.

Assessment of parametric uncertainty for groundwater reactive transport modeling,

USGS Publications Warehouse

Shi, Xiaoqing; Ye, Ming; Curtis, Gary P.; Miller, Geoffery L.; Meyer, Philip D.; Kohler, Matthias; Yabusaki, Steve; Wu, Jichun

2014-01-01

The validity of using Gaussian assumptions for model residuals in uncertainty quantification of a groundwater reactive transport model was evaluated in this study. Least squares regression methods explicitly assume Gaussian residuals, and the assumption leads to Gaussian likelihood functions, model parameters, and model predictions. While the Bayesian methods do not explicitly require the Gaussian assumption, Gaussian residuals are widely used. This paper shows that the residuals of the reactive transport model are non-Gaussian, heteroscedastic, and correlated in time; characterizing them requires using a generalized likelihood function such as the formal generalized likelihood function developed by Schoups and Vrugt (2010). For the surface complexation model considered in this study for simulating uranium reactive transport in groundwater, parametric uncertainty is quantified using the least squares regression methods and Bayesian methods with both Gaussian and formal generalized likelihood functions. While the least squares methods and Bayesian methods with Gaussian likelihood function produce similar Gaussian parameter distributions, the parameter distributions of Bayesian uncertainty quantification using the formal generalized likelihood function are non-Gaussian. In addition, predictive performance of formal generalized likelihood function is superior to that of least squares regression and Bayesian methods with Gaussian likelihood function. The Bayesian uncertainty quantification is conducted using the differential evolution adaptive metropolis (DREAM(zs)) algorithm; as a Markov chain Monte Carlo (MCMC) method, it is a robust tool for quantifying uncertainty in groundwater reactive transport models. For the surface complexation model, the regression-based local sensitivity analysis and Morris- and DREAM(ZS)-based global sensitivity analysis yield almost identical ranking of parameter importance. The uncertainty analysis may help select appropriate likelihood functions, improve model calibration, and reduce predictive uncertainty in other groundwater reactive transport and environmental modeling.

Predicting Student Success on the Texas Chemistry STAAR Test: A Logistic Regression Analysis

ERIC Educational Resources Information Center

Johnson, William L.; Johnson, Annabel M.; Johnson, Jared

2012-01-01

Background: The context is the new Texas STAAR end-of-course testing program. Purpose: The authors developed a logistic regression model to predict who would pass-or-fail the new Texas chemistry STAAR end-of-course exam. Setting: Robert E. Lee High School (5A) with an enrollment of 2700 students, Tyler, Texas. Date of the study was the 2011-2012…

Analytics of Radioactive Materials Released in the Fukushima Daiichi Nuclear Accident

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

Egarievwe, Stephen U.; Nuclear Engineering Department, University of Tennessee, Knoxville, TN; Coble, Jamie B.

The 2011 Fukushima Daiichi nuclear accident in Japan resulted in the release of radioactive materials into the atmosphere, the nearby sea, and the surrounding land. Following the accident, several meteorological models were used to predict the transport of the radioactive materials to other continents such as North America and Europe. Also of high importance is the dispersion of radioactive materials locally and within Japan. Based on the International Atomic Energy Agency (IAEA) Convention on Early Notification of a nuclear accident, several radiological data sets were collected on the accident by the Japanese authorities. Among the radioactive materials monitored, are I-131more » and Cs-137 which form the major contributions to the contamination of drinking water. The radiation dose in the atmosphere was also measured. It is impractical to measure contamination and radiation dose in every place of interest. Therefore, modeling helps to predict contamination and radiation dose. Some modeling studies that have been reported in the literature include the simulation of transport and deposition of I-131 and Cs-137 from the accident, Cs-137 deposition and contamination of Japanese soils, and preliminary estimates of I-131 and Cs-137 discharged from the plant into the atmosphere. In this paper, we present statistical analytics of I-131 and Cs-137 with the goal of predicting gamma dose from the Fukushima Daiichi nuclear accident. The data sets used in our study were collected from the IAEA Fukushima Monitoring Database. As part of this study, we investigated several regression models to find the best algorithm for modeling the gamma dose. The modeling techniques used in our study include linear regression, principal component regression (PCR), partial least square (PLS) regression, and ridge regression. Our preliminary results on the first set of data showed that the linear regression model with one variable was the best with a root mean square error of 0.0133 μSv/h, compared to 0.0210 μSv/h for PCR, 0.231 μSv/h for ridge regression L-curve, 0.0856 μSv/h for PLS, and 0.0860 μSv/h for ridge regression cross validation. Complete results using the full datasets for these models will also be presented. (authors)« less

Improving the Spatial Prediction of Soil Organic Carbon Stocks in a Complex Tropical Mountain Landscape by Methodological Specifications in Machine Learning Approaches.

PubMed

Ließ, Mareike; Schmidt, Johannes; Glaser, Bruno

2016-01-01

Tropical forests are significant carbon sinks and their soils' carbon storage potential is immense. However, little is known about the soil organic carbon (SOC) stocks of tropical mountain areas whose complex soil-landscape and difficult accessibility pose a challenge to spatial analysis. The choice of methodology for spatial prediction is of high importance to improve the expected poor model results in case of low predictor-response correlations. Four aspects were considered to improve model performance in predicting SOC stocks of the organic layer of a tropical mountain forest landscape: Different spatial predictor settings, predictor selection strategies, various machine learning algorithms and model tuning. Five machine learning algorithms: random forests, artificial neural networks, multivariate adaptive regression splines, boosted regression trees and support vector machines were trained and tuned to predict SOC stocks from predictors derived from a digital elevation model and satellite image. Topographical predictors were calculated with a GIS search radius of 45 to 615 m. Finally, three predictor selection strategies were applied to the total set of 236 predictors. All machine learning algorithms-including the model tuning and predictor selection-were compared via five repetitions of a tenfold cross-validation. The boosted regression tree algorithm resulted in the overall best model. SOC stocks ranged between 0.2 to 17.7 kg m-2, displaying a huge variability with diffuse insolation and curvatures of different scale guiding the spatial pattern. Predictor selection and model tuning improved the models' predictive performance in all five machine learning algorithms. The rather low number of selected predictors favours forward compared to backward selection procedures. Choosing predictors due to their indiviual performance was vanquished by the two procedures which accounted for predictor interaction.

Technical note: A linear model for predicting δ13 Cprotein.

PubMed

Pestle, William J; Hubbe, Mark; Smith, Erin K; Stevenson, Joseph M

2015-08-01

Development of a model for the prediction of δ(13) Cprotein from δ(13) Ccollagen and Δ(13) Cap-co . Model-generated values could, in turn, serve as "consumer" inputs for multisource mixture modeling of paleodiet. Linear regression analysis of previously published controlled diet data facilitated the development of a mathematical model for predicting δ(13) Cprotein (and an experimentally generated error term) from isotopic data routinely generated during the analysis of osseous remains (δ(13) Cco and Δ(13) Cap-co ). Regression analysis resulted in a two-term linear model (δ(13) Cprotein (%) = (0.78 × δ(13) Cco ) - (0.58× Δ(13) Cap-co ) - 4.7), possessing a high R-value of 0.93 (r(2)  = 0.86, P < 0.01), and experimentally generated error terms of ±1.9% for any predicted individual value of δ(13) Cprotein . This model was tested using isotopic data from Formative Period individuals from northern Chile's Atacama Desert. The model presented here appears to hold significant potential for the prediction of the carbon isotope signature of dietary protein using only such data as is routinely generated in the course of stable isotope analysis of human osseous remains. These predicted values are ideal for use in multisource mixture modeling of dietary protein source contribution. © 2015 Wiley Periodicals, Inc.

Near infrared spectrometric technique for testing fruit quality: optimisation of regression models using genetic algorithms

NASA Astrophysics Data System (ADS)

Isingizwe Nturambirwe, J. Frédéric; Perold, Willem J.; Opara, Umezuruike L.

2016-02-01

Near infrared (NIR) spectroscopy has gained extensive use in quality evaluation. It is arguably one of the most advanced spectroscopic tools in non-destructive quality testing of food stuff, from measurement to data analysis and interpretation. NIR spectral data are interpreted through means often involving multivariate statistical analysis, sometimes associated with optimisation techniques for model improvement. The objective of this research was to explore the extent to which genetic algorithms (GA) can be used to enhance model development, for predicting fruit quality. Apple fruits were used, and NIR spectra in the range from 12000 to 4000 cm-1 were acquired on both bruised and healthy tissues, with different degrees of mechanical damage. GAs were used in combination with partial least squares regression methods to develop bruise severity prediction models, and compared to PLS models developed using the full NIR spectrum. A classification model was developed, which clearly separated bruised from unbruised apple tissue. GAs helped improve prediction models by over 10%, in comparison with full spectrum-based models, as evaluated in terms of error of prediction (Root Mean Square Error of Cross-validation). PLS models to predict internal quality, such as sugar content and acidity were developed and compared to the versions optimized by genetic algorithm. Overall, the results highlighted the potential use of GA method to improve speed and accuracy of fruit quality prediction.

Modeling critical habitat for Flammulated Owls (Otus flammeolus)

Treesearch

David A. Christie; Astrid M. van Woudenberg

1997-01-01

Multiple logistic regression analysis was used to produce a prediction model for Flammulated Owl (Otus flammeolus) breeding habitat within the Kamloops Forest Region in south-central British Columbia. Using the model equation, a pilot habitat prediction map was created within a Geographic Information System (GIS) environment that had a 75.7 percent...

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.

Predictive model of third molar eruption after second molar extraction.

PubMed

De-la-Rosa-Gay, Cristina; Valmaseda-Castellón, Eduard; Gay-Escoda, Cosme

2010-03-01

Extraction of second permanent molars is an option for providing space in orthodontic treatment. Although many articles have described its impact on the outcome, there are few data on the prognosis of the eruption of the adjacent third molars. The aims of this investigation were to provide predictive models of eruption of third molars after second permanent molar extraction and to validate them. A total of 48 patients (ages, 11-23 years) who had 128 second permanent molars (54 maxillary, 74 mandibular) extracted during orthodontic treatment were followed until eruption of the third molars was complete. A lineal regression model predicted the final angle of the third molars with the permanent first molar by using the variables of initial angle, jaw, and the developmental stage of the third molar. A logistic regression model predicted the probability of correct eruption by using the variables of initial angle, jaw, sex, age, and the developmental stage of the third molar. 2010 American Association of Orthodontists. Published by Mosby, Inc. All rights reserved.

A new predictive indicator for development of pressure ulcers in bedridden patients based on common laboratory tests results.

PubMed

Hatanaka, N; Yamamoto, Y; Ichihara, K; Mastuo, S; Nakamura, Y; Watanabe, M; Iwatani, Y

2008-04-01

Various scales have been devised to predict development of pressure ulcers on the basis of clinical and laboratory data, such as the Braden Scale (Braden score), which is used to monitor activity and skin conditions of bedridden patients. However, none of these scales facilitates clinically reliable prediction. To develop a clinical laboratory data-based predictive equation for the development of pressure ulcers. Subjects were 149 hospitalised patients with respiratory disorders who were monitored for the development of pressure ulcers over a 3-month period. The proportional hazards model (Cox regression) was used to analyse the results of 12 basic laboratory tests on the day of hospitalisation in comparison with Braden score. Pressure ulcers developed in 38 patients within the study period. A Cox regression model consisting solely of Braden scale items showed that none of these items contributed to significantly predicting pressure ulcers. Rather, a combination of haemoglobin (Hb), C-reactive protein (CRP), albumin (Alb), age, and gender produced the best model for prediction. Using the set of explanatory variables, we created a new indicator based on a multiple logistic regression equation. The new indicator showed high sensitivity (0.73) and specificity (0.70), and its diagnostic power was higher than that of Alb, Hb, CRP, or the Braden score alone. The new indicator may become a more useful clinical tool for predicting presser ulcers than Braden score. The new indicator warrants verification studies to facilitate its clinical implementation in the future.

Simple to complex modeling of breathing volume using a motion sensor.

PubMed

John, Dinesh; Staudenmayer, John; Freedson, Patty

2013-06-01

To compare simple and complex modeling techniques to estimate categories of low, medium, and high ventilation (VE) from ActiGraph™ activity counts. Vertical axis ActiGraph™ GT1M activity counts, oxygen consumption and VE were measured during treadmill walking and running, sports, household chores and labor-intensive employment activities. Categories of low (<19.3 l/min), medium (19.3 to 35.4 l/min) and high (>35.4 l/min) VEs were derived from activity intensity classifications (light <2.9 METs, moderate 3.0 to 5.9 METs and vigorous >6.0 METs). We examined the accuracy of two simple techniques (multiple regression and activity count cut-point analyses) and one complex (random forest technique) modeling technique in predicting VE from activity counts. Prediction accuracy of the complex random forest technique was marginally better than the simple multiple regression method. Both techniques accurately predicted VE categories almost 80% of the time. The multiple regression and random forest techniques were more accurate (85 to 88%) in predicting medium VE. Both techniques predicted the high VE (70 to 73%) with greater accuracy than low VE (57 to 60%). Actigraph™ cut-points for light, medium and high VEs were <1381, 1381 to 3660 and >3660 cpm. There were minor differences in prediction accuracy between the multiple regression and the random forest technique. This study provides methods to objectively estimate VE categories using activity monitors that can easily be deployed in the field. Objective estimates of VE should provide a better understanding of the dose-response relationship between internal exposure to pollutants and disease. Copyright © 2013 Elsevier B.V. All rights reserved.

Analysis of Variables to Predict First Year Persistence Using Logistic Regression Analysis at the University of South Florida: Model v2.0

ERIC Educational Resources Information Center

Herreid, Charlene H.; Miller, Thomas E.

2009-01-01

This article is the fourth in a series of articles describing an attrition prediction and intervention project at the University of South Florida (USF) in Tampa. In this article, the researchers describe the updated version of the prediction model. The original model was developed from a sample of about 900 First Time in College (FTIC) students…

QSAR Analysis of 2-Amino or 2-Methyl-1-Substituted Benzimidazoles Against Pseudomonas aeruginosa

PubMed Central

Podunavac-Kuzmanović, Sanja O.; Cvetković, Dragoljub D.; Barna, Dijana J.

2009-01-01

A set of benzimidazole derivatives were tested for their inhibitory activities against the Gram-negative bacterium Pseudomonas aeruginosa and minimum inhibitory concentrations were determined for all the compounds. Quantitative structure activity relationship (QSAR) analysis was applied to fourteen of the abovementioned derivatives using a combination of various physicochemical, steric, electronic, and structural molecular descriptors. A multiple linear regression (MLR) procedure was used to model the relationships between molecular descriptors and the antibacterial activity of the benzimidazole derivatives. The stepwise regression method was used to derive the most significant models as a calibration model for predicting the inhibitory activity of this class of molecules. The best QSAR models were further validated by a leave one out technique as well as by the calculation of statistical parameters for the established theoretical models. To confirm the predictive power of the models, an external set of molecules was used. High agreement between experimental and predicted inhibitory values, obtained in the validation procedure, indicated the good quality of the derived QSAR models. PMID:19468332

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.

Logistic Mixed Models to Investigate Implicit and Explicit Belief Tracking

PubMed Central

Lages, Martin; Scheel, Anne

2016-01-01

We investigated the proposition of a two-systems Theory of Mind in adults’ belief tracking. A sample of N = 45 participants predicted the choice of one of two opponent players after observing several rounds in an animated card game. Three matches of this card game were played and initial gaze direction on target and subsequent choice predictions were recorded for each belief task and participant. We conducted logistic regressions with mixed effects on the binary data and developed Bayesian logistic mixed models to infer implicit and explicit mentalizing in true belief and false belief tasks. Although logistic regressions with mixed effects predicted the data well a Bayesian logistic mixed model with latent task- and subject-specific parameters gave a better account of the data. As expected explicit choice predictions suggested a clear understanding of true and false beliefs (TB/FB). Surprisingly, however, model parameters for initial gaze direction also indicated belief tracking. We discuss why task-specific parameters for initial gaze directions are different from choice predictions yet reflect second-order perspective taking. PMID:27853440

Regularization Paths for Conditional Logistic Regression: The clogitL1 Package.

PubMed

Reid, Stephen; Tibshirani, Rob

2014-07-01

We apply the cyclic coordinate descent algorithm of Friedman, Hastie, and Tibshirani (2010) to the fitting of a conditional logistic regression model with lasso [Formula: see text] and elastic net penalties. The sequential strong rules of Tibshirani, Bien, Hastie, Friedman, Taylor, Simon, and Tibshirani (2012) are also used in the algorithm and it is shown that these offer a considerable speed up over the standard coordinate descent algorithm with warm starts. Once implemented, the algorithm is used in simulation studies to compare the variable selection and prediction performance of the conditional logistic regression model against that of its unconditional (standard) counterpart. We find that the conditional model performs admirably on datasets drawn from a suitable conditional distribution, outperforming its unconditional counterpart at variable selection. The conditional model is also fit to a small real world dataset, demonstrating how we obtain regularization paths for the parameters of the model and how we apply cross validation for this method where natural unconditional prediction rules are hard to come by.

Regularization Paths for Conditional Logistic Regression: The clogitL1 Package

PubMed Central

Reid, Stephen; Tibshirani, Rob

2014-01-01

We apply the cyclic coordinate descent algorithm of Friedman, Hastie, and Tibshirani (2010) to the fitting of a conditional logistic regression model with lasso (ℓ1) and elastic net penalties. The sequential strong rules of Tibshirani, Bien, Hastie, Friedman, Taylor, Simon, and Tibshirani (2012) are also used in the algorithm and it is shown that these offer a considerable speed up over the standard coordinate descent algorithm with warm starts. Once implemented, the algorithm is used in simulation studies to compare the variable selection and prediction performance of the conditional logistic regression model against that of its unconditional (standard) counterpart. We find that the conditional model performs admirably on datasets drawn from a suitable conditional distribution, outperforming its unconditional counterpart at variable selection. The conditional model is also fit to a small real world dataset, demonstrating how we obtain regularization paths for the parameters of the model and how we apply cross validation for this method where natural unconditional prediction rules are hard to come by. PMID:26257587

[Quantitative structure-gas chromatographic retention relationship of polycyclic aromatic sulfur heterocycles using molecular electronegativity-distance vector].

PubMed

Li, Zhenghua; Cheng, Fansheng; Xia, Zhining

2011-01-01

The chemical structures of 114 polycyclic aromatic sulfur heterocycles (PASHs) have been studied by molecular electronegativity-distance vector (MEDV). The linear relationships between gas chromatographic retention index and the MEDV have been established by a multiple linear regression (MLR) model. The results of variable selection by stepwise multiple regression (SMR) and the powerful predictive abilities of the optimization model appraised by leave-one-out cross-validation showed that the optimization model with the correlation coefficient (R) of 0.994 7 and the cross-validated correlation coefficient (Rcv) of 0.994 0 possessed the best statistical quality. Furthermore, when the 114 PASHs compounds were divided into calibration and test sets in the ratio of 2:1, the statistical analysis showed our models possesses almost equal statistical quality, the very similar regression coefficients and the good robustness. The quantitative structure-retention relationship (QSRR) model established may provide a convenient and powerful method for predicting the gas chromatographic retention of PASHs.

An algebraic method for constructing stable and consistent autoregressive filters

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

Harlim, John, E-mail: jharlim@psu.edu; Department of Meteorology, the Pennsylvania State University, University Park, PA 16802; Hong, Hoon, E-mail: hong@ncsu.edu

2015-02-15

In this paper, we introduce an algebraic method to construct stable and consistent univariate autoregressive (AR) models of low order for filtering and predicting nonlinear turbulent signals with memory depth. By stable, we refer to the classical stability condition for the AR model. By consistent, we refer to the classical consistency constraints of Adams–Bashforth methods of order-two. One attractive feature of this algebraic method is that the model parameters can be obtained without directly knowing any training data set as opposed to many standard, regression-based parameterization methods. It takes only long-time average statistics as inputs. The proposed method provides amore » discretization time step interval which guarantees the existence of stable and consistent AR model and simultaneously produces the parameters for the AR models. In our numerical examples with two chaotic time series with different characteristics of decaying time scales, we find that the proposed AR models produce significantly more accurate short-term predictive skill and comparable filtering skill relative to the linear regression-based AR models. These encouraging results are robust across wide ranges of discretization times, observation times, and observation noise variances. Finally, we also find that the proposed model produces an improved short-time prediction relative to the linear regression-based AR-models in forecasting a data set that characterizes the variability of the Madden–Julian Oscillation, a dominant tropical atmospheric wave pattern.« less

Development of a partial least squares-artificial neural network (PLS-ANN) hybrid model for the prediction of consumer liking scores of ready-to-drink green tea beverages.

PubMed

Yu, Peigen; Low, Mei Yin; Zhou, Weibiao

2018-01-01

In order to develop products that would be preferred by consumers, the effects of the chemical compositions of ready-to-drink green tea beverages on consumer liking were studied through regression analyses. Green tea model systems were prepared by dosing solutions of 0.1% green tea extract with differing concentrations of eight flavour keys deemed to be important for green tea aroma and taste, based on a D-optimal experimental design, before undergoing commercial sterilisation. Sensory evaluation of the green tea model system was carried out using an untrained consumer panel to obtain hedonic liking scores of the samples. Regression models were subsequently trained to objectively predict the consumer liking scores of the green tea model systems. A linear partial least squares (PLS) regression model was developed to describe the effects of the eight flavour keys on consumer liking, with a coefficient of determination (R 2 ) of 0.733, and a root-mean-square error (RMSE) of 3.53%. The PLS model was further augmented with an artificial neural network (ANN) to establish a PLS-ANN hybrid model. The established hybrid model was found to give a better prediction of consumer liking scores, based on its R 2 (0.875) and RMSE (2.41%). Copyright © 2017 Elsevier Ltd. All rights reserved.

Regression-Based Norms for a Bi-factor Model for Scoring the Brief Test of Adult Cognition by Telephone (BTACT).

PubMed

Gurnani, Ashita S; John, Samantha E; Gavett, Brandon E

2015-05-01

The current study developed regression-based normative adjustments for a bi-factor model of the The Brief Test of Adult Cognition by Telephone (BTACT). Archival data from the Midlife Development in the United States-II Cognitive Project were used to develop eight separate linear regression models that predicted bi-factor BTACT scores, accounting for age, education, gender, and occupation-alone and in various combinations. All regression models provided statistically significant fit to the data. A three-predictor regression model fit best and accounted for 32.8% of the variance in the global bi-factor BTACT score. The fit of the regression models was not improved by gender. Eight different regression models are presented to allow the user flexibility in applying demographic corrections to the bi-factor BTACT scores. Occupation corrections, while not widely used, may provide useful demographic adjustments for adult populations or for those individuals who have attained an occupational status not commensurate with expected educational attainment. © The Author 2015. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Regression Model Term Selection for the Analysis of Strain-Gage Balance Calibration Data

NASA Technical Reports Server (NTRS)

Ulbrich, Norbert Manfred; Volden, Thomas R.

2010-01-01

The paper discusses the selection of regression model terms for the analysis of wind tunnel strain-gage balance calibration data. Different function class combinations are presented that may be used to analyze calibration data using either a non-iterative or an iterative method. The role of the intercept term in a regression model of calibration data is reviewed. In addition, useful algorithms and metrics originating from linear algebra and statistics are recommended that will help an analyst (i) to identify and avoid both linear and near-linear dependencies between regression model terms and (ii) to make sure that the selected regression model of the calibration data uses only statistically significant terms. Three different tests are suggested that may be used to objectively assess the predictive capability of the final regression model of the calibration data. These tests use both the original data points and regression model independent confirmation points. Finally, data from a simplified manual calibration of the Ames MK40 balance is used to illustrate the application of some of the metrics and tests to a realistic calibration data set.

An Effect Size for Regression Predictors in Meta-Analysis

ERIC Educational Resources Information Center

Aloe, Ariel M.; Becker, Betsy Jane

2012-01-01

A new effect size representing the predictive power of an independent variable from a multiple regression model is presented. The index, denoted as r[subscript sp], is the semipartial correlation of the predictor with the outcome of interest. This effect size can be computed when multiple predictor variables are included in the regression model…

Personality predicts time to remission and clinical status in hypochondriasis during a 6-year follow-up.

PubMed

Greeven, Anja; van Balkom, Anton J L M; Spinhoven, Philip

2014-05-01

We aimed to investigate whether personality characteristics predict time to remission and psychiatric status. The follow-up was at most 6 years and was performed within the scope of a randomized controlled trial that investigated the efficacy of cognitive behavioral therapy, paroxetine, and placebo in hypochondriasis. The Life Chart Interview was administered to investigate for each year if remission had occurred. Personality was assessed at pretest by the Abbreviated Dutch Temperament and Character Inventory. Cox's regression models for recurrent events were compared with logistic regression models. Sixteen (36.4%) of 44 patients achieved remission during the follow-up period. Cox's regression yielded approximately the same results as the logistic regression. Being less harm avoidant and more cooperative were associated with a shorter time to remission and a remitted state after the follow-up period. Personality variables seem to be relevant for describing patients with a more chronic course of hypochondriacal complaints.

Schistosomiasis Breeding Environment Situation Analysis in Dongting Lake Area

NASA Astrophysics Data System (ADS)

Li, Chuanrong; Jia, Yuanyuan; Ma, Lingling; Liu, Zhaoyan; Qian, Yonggang

2013-01-01

Monitoring environmental characteristics, such as vegetation, soil moisture et al., of Oncomelania hupensis (O. hupensis)’ spatial/temporal distribution is of vital importance to the schistosomiasis prevention and control. In this study, the relationship between environmental factors derived from remotely sensed data and the density of O. hupensis was analyzed by a multiple linear regression model. Secondly, spatial analysis of the regression residual was investigated by the semi-variogram method. Thirdly, spatial analysis of the regression residual and the multiple linear regression model were both employed to estimate the spatial variation of O. hupensis density. Finally, the approach was used to monitor and predict the spatial and temporal variations of oncomelania of Dongting Lake region, China. And the areas of potential O. hupensis habitats were predicted and the influence of Three Gorges Dam (TGB)project on the density of O. hupensis was analyzed.

lazar: a modular predictive toxicology framework

PubMed Central

Maunz, Andreas; Gütlein, Martin; Rautenberg, Micha; Vorgrimmler, David; Gebele, Denis; Helma, Christoph

2013-01-01

lazar (lazy structure–activity relationships) is a modular framework for predictive toxicology. Similar to the read across procedure in toxicological risk assessment, lazar creates local QSAR (quantitative structure–activity relationship) models for each compound to be predicted. Model developers can choose between a large variety of algorithms for descriptor calculation and selection, chemical similarity indices, and model building. This paper presents a high level description of the lazar framework and discusses the performance of example classification and regression models. PMID:23761761

Predictive Ability of Pender's Health Promotion Model for Physical Activity and Exercise in People with Spinal Cord Injuries: A Hierarchical Regression Analysis

ERIC Educational Resources Information Center

Keegan, John P.; Chan, Fong; Ditchman, Nicole; Chiu, Chung-Yi

2012-01-01

The main objective of this study was to validate Pender's Health Promotion Model (HPM) as a motivational model for exercise/physical activity self-management for people with spinal cord injuries (SCIs). Quantitative descriptive research design using hierarchical regression analysis (HRA) was used. A total of 126 individuals with SCI were recruited…

Assessment of traffic noise levels in urban areas using different soft computing techniques.

PubMed

Tomić, J; Bogojević, N; Pljakić, M; Šumarac-Pavlović, D

2016-10-01

Available traffic noise prediction models are usually based on regression analysis of experimental data, and this paper presents the application of soft computing techniques in traffic noise prediction. Two mathematical models are proposed and their predictions are compared to data collected by traffic noise monitoring in urban areas, as well as to predictions of commonly used traffic noise models. The results show that application of evolutionary algorithms and neural networks may improve process of development, as well as accuracy of traffic noise prediction.

Ensemble projections of wildfire activity and carbonaceous aerosol concentrations over the western United States in the mid-21st century

PubMed Central

Yue, Xu; Mickley, Loretta J.; Logan, Jennifer A.; Kaplan, Jed O.

2013-01-01

We estimate future wildfire activity over the western United States during the mid-21st century (2046–2065), based on results from 15 climate models following the A1B scenario. We develop fire prediction models by regressing meteorological variables from the current and previous years together with fire indexes onto observed regional area burned. The regressions explain 0.25–0.60 of the variance in observed annual area burned during 1980–2004, depending on the ecoregion. We also parameterize daily area burned with temperature, precipitation, and relative humidity. This approach explains ~0.5 of the variance in observed area burned over forest ecoregions but shows no predictive capability in the semi-arid regions of Nevada and California. By applying the meteorological fields from 15 climate models to our fire prediction models, we quantify the robustness of our wildfire projections at mid-century. We calculate increases of 24–124% in area burned using regressions and 63–169% with the parameterization. Our projections are most robust in the southwestern desert, where all GCMs predict significant (p<0.05) meteorological changes. For forested ecoregions, more GCMs predict significant increases in future area burned with the parameterization than with the regressions, because the latter approach is sensitive to hydrological variables that show large inter-model variability in the climate projections. The parameterization predicts that the fire season lengthens by 23 days in the warmer and drier climate at mid-century. Using a chemical transport model, we find that wildfire emissions will increase summertime surface organic carbon aerosol over the western United States by 46–70% and black carbon by 20–27% at midcentury, relative to the present day. The pollution is most enhanced during extreme episodes: above the 84th percentile of concentrations, OC increases by ~90% and BC by ~50%, while visibility decreases from 130 km to 100 km in 32 Federal Class 1 areas in Rocky Mountains Forest. PMID:24015109

Improving the Spatial Prediction of Soil Organic Carbon Stocks in a Complex Tropical Mountain Landscape by Methodological Specifications in Machine Learning Approaches

PubMed Central

Schmidt, Johannes; Glaser, Bruno

2016-01-01

Tropical forests are significant carbon sinks and their soils’ carbon storage potential is immense. However, little is known about the soil organic carbon (SOC) stocks of tropical mountain areas whose complex soil-landscape and difficult accessibility pose a challenge to spatial analysis. The choice of methodology for spatial prediction is of high importance to improve the expected poor model results in case of low predictor-response correlations. Four aspects were considered to improve model performance in predicting SOC stocks of the organic layer of a tropical mountain forest landscape: Different spatial predictor settings, predictor selection strategies, various machine learning algorithms and model tuning. Five machine learning algorithms: random forests, artificial neural networks, multivariate adaptive regression splines, boosted regression trees and support vector machines were trained and tuned to predict SOC stocks from predictors derived from a digital elevation model and satellite image. Topographical predictors were calculated with a GIS search radius of 45 to 615 m. Finally, three predictor selection strategies were applied to the total set of 236 predictors. All machine learning algorithms—including the model tuning and predictor selection—were compared via five repetitions of a tenfold cross-validation. The boosted regression tree algorithm resulted in the overall best model. SOC stocks ranged between 0.2 to 17.7 kg m-2, displaying a huge variability with diffuse insolation and curvatures of different scale guiding the spatial pattern. Predictor selection and model tuning improved the models’ predictive performance in all five machine learning algorithms. The rather low number of selected predictors favours forward compared to backward selection procedures. Choosing predictors due to their indiviual performance was vanquished by the two procedures which accounted for predictor interaction. PMID:27128736

Cross-validation pitfalls when selecting and assessing regression and classification models.

PubMed

Krstajic, Damjan; Buturovic, Ljubomir J; Leahy, David E; Thomas, Simon

2014-03-29

We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches. We describe in detail an algorithm for repeated grid-search V-fold cross-validation for parameter tuning in classification and regression, and we define a repeated nested cross-validation algorithm for model assessment. As regards variable selection and parameter tuning we define two algorithms (repeated grid-search cross-validation and double cross-validation), and provide arguments for using the repeated grid-search in the general case. We show results of our algorithms on seven QSAR datasets. The variation of the prediction performance, which is the result of choosing different splits of the dataset in V-fold cross-validation, needs to be taken into account when selecting and assessing classification and regression models. We demonstrate the importance of repeating cross-validation when selecting an optimal model, as well as the importance of repeating nested cross-validation when assessing a prediction error.

Mortality Predicted Accuracy for Hepatocellular Carcinoma Patients with Hepatic Resection Using Artificial Neural Network

PubMed Central

Chiu, Herng-Chia; Ho, Te-Wei; Lee, King-Teh; Chen, Hong-Yaw; Ho, Wen-Hsien

2013-01-01

The aim of this present study is firstly to compare significant predictors of mortality for hepatocellular carcinoma (HCC) patients undergoing resection between artificial neural network (ANN) and logistic regression (LR) models and secondly to evaluate the predictive accuracy of ANN and LR in different survival year estimation models. We constructed a prognostic model for 434 patients with 21 potential input variables by Cox regression model. Model performance was measured by numbers of significant predictors and predictive accuracy. The results indicated that ANN had double to triple numbers of significant predictors at 1-, 3-, and 5-year survival models as compared with LR models. Scores of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of 1-, 3-, and 5-year survival estimation models using ANN were superior to those of LR in all the training sets and most of the validation sets. The study demonstrated that ANN not only had a great number of predictors of mortality variables but also provided accurate prediction, as compared with conventional methods. It is suggested that physicians consider using data mining methods as supplemental tools for clinical decision-making and prognostic evaluation. PMID:23737707

Antibacterial Activity of Imidazolium-Based Ionic Liquids Investigated by QSAR Modeling and Experimental Studies.

PubMed

Hodyna, Diana; Kovalishyn, Vasyl; Rogalsky, Sergiy; Blagodatnyi, Volodymyr; Petko, Kirill; Metelytsia, Larisa

2016-09-01

Predictive QSAR models for the inhibitors of B. subtilis and Ps. aeruginosa among imidazolium-based ionic liquids were developed using literary data. The regression QSAR models were created through Artificial Neural Network and k-nearest neighbor procedures. The classification QSAR models were constructed using WEKA-RF (random forest) method. The predictive ability of the models was tested by fivefold cross-validation; giving q(2) = 0.77-0.92 for regression models and accuracy 83-88% for classification models. Twenty synthesized samples of 1,3-dialkylimidazolium ionic liquids with predictive value of activity level of antimicrobial potential were evaluated. For all asymmetric 1,3-dialkylimidazolium ionic liquids, only compounds containing at least one radical with alkyl chain length of 12 carbon atoms showed high antibacterial activity. However, the activity of symmetric 1,3-dialkylimidazolium salts was found to have opposite relationship with the length of aliphatic radical being maximum for compounds based on 1,3-dioctylimidazolium cation. The obtained experimental results suggested that the application of classification QSAR models is more accurate for the prediction of activity of new imidazolium-based ILs as potential antibacterials. © 2016 John Wiley & Sons A/S.

Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

PubMed Central

Singal, Amit G.; Mukherjee, Ashin; Elmunzer, B. Joseph; Higgins, Peter DR; Lok, Anna S.; Zhu, Ji; Marrero, Jorge A; Waljee, Akbar K

2015-01-01

Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (p<0.001) and integrated discrimination improvement (p=0.04). The HALT-C model had a c-statistic of 0.60 (95%CI 0.50-0.70) in the validation cohort and was outperformed by the machine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC. PMID:24169273

Developing a NIR multispectral imaging for prediction and visualization of peanut protein content using variable selection algorithms

NASA Astrophysics Data System (ADS)

Cheng, Jun-Hu; Jin, Huali; Liu, Zhiwei

2018-01-01

The feasibility of developing a multispectral imaging method using important wavelengths from hyperspectral images selected by genetic algorithm (GA), successive projection algorithm (SPA) and regression coefficient (RC) methods for modeling and predicting protein content in peanut kernel was investigated for the first time. Partial least squares regression (PLSR) calibration model was established between the spectral data from the selected optimal wavelengths and the reference measured protein content ranged from 23.46% to 28.43%. The RC-PLSR model established using eight key wavelengths (1153, 1567, 1972, 2143, 2288, 2339, 2389 and 2446 nm) showed the best predictive results with the coefficient of determination of prediction (R2P) of 0.901, and root mean square error of prediction (RMSEP) of 0.108 and residual predictive deviation (RPD) of 2.32. Based on the obtained best model and image processing algorithms, the distribution maps of protein content were generated. The overall results of this study indicated that developing a rapid and online multispectral imaging system using the feature wavelengths and PLSR analysis is potential and feasible for determination of the protein content in peanut kernels.

A multilateral modelling of Youth Soccer Performance Index (YSPI)

NASA Astrophysics Data System (ADS)

Bisyri Husin Musawi Maliki, Ahmad; Razali Abdullah, Mohamad; Juahir, Hafizan; Abdullah, Farhana; Ain Shahirah Abdullah, Nurul; Muazu Musa, Rabiu; Musliha Mat-Rasid, Siti; Adnan, Aleesha; Azura Kosni, Norlaila; Muhamad, Wan Siti Amalina Wan; Afiqah Mohamad Nasir, Nur

2018-04-01

This study aims to identify the most dominant factors that influencing performance of soccer player and to predict group performance for soccer players. A total of 184 of youth soccer players from Malaysia sport school and six soccer academy encompasses as respondence of the study. Exploratory factor analysis (EFA) and Confirmatory factor analysis (CFA) were computed to identify the most dominant factors whereas reducing the initial 26 parameters with recommended >0.5 of factor loading. Meanwhile, prediction of the soccer performance was predicted by regression model. CFA revealed that sit and reach, vertical jump, VO2max, age, weight, height, sitting height, calf circumference (cc), medial upper arm circumference (muac), maturation, bicep, triceps, subscapular, suprailiac, 5M, 10M, and 20M speed were the most dominant factors. Further index analysis forming Youth Soccer Performance Index (YSPI) resulting by categorizing three groups namely, high, moderate, and low. The regression model for this study was significant set as p < 0.001 and R2 is 0.8222 which explained that the model contributed a total of 82% prediction ability to predict the whole set of the variables. The significant parameters in contributing prediction of YSPI are discussed. As a conclusion, the precision of the prediction models by integrating a multilateral factor reflecting for predicting potential soccer player and hopefully can create a competitive soccer games.

Improving stability of prediction models based on correlated omics data by using network approaches.

PubMed

Tissier, Renaud; Houwing-Duistermaat, Jeanine; Rodríguez-Girondo, Mar

2018-01-01

Building prediction models based on complex omics datasets such as transcriptomics, proteomics, metabolomics remains a challenge in bioinformatics and biostatistics. Regularized regression techniques are typically used to deal with the high dimensionality of these datasets. However, due to the presence of correlation in the datasets, it is difficult to select the best model and application of these methods yields unstable results. We propose a novel strategy for model selection where the obtained models also perform well in terms of overall predictability. Several three step approaches are considered, where the steps are 1) network construction, 2) clustering to empirically derive modules or pathways, and 3) building a prediction model incorporating the information on the modules. For the first step, we use weighted correlation networks and Gaussian graphical modelling. Identification of groups of features is performed by hierarchical clustering. The grouping information is included in the prediction model by using group-based variable selection or group-specific penalization. We compare the performance of our new approaches with standard regularized regression via simulations. Based on these results we provide recommendations for selecting a strategy for building a prediction model given the specific goal of the analysis and the sizes of the datasets. Finally we illustrate the advantages of our approach by application of the methodology to two problems, namely prediction of body mass index in the DIetary, Lifestyle, and Genetic determinants of Obesity and Metabolic syndrome study (DILGOM) and prediction of response of each breast cancer cell line to treatment with specific drugs using a breast cancer cell lines pharmacogenomics dataset.

Comparison of linear and non-linear models for predicting energy expenditure from raw accelerometer data.

PubMed

Montoye, Alexander H K; Begum, Munni; Henning, Zachary; Pfeiffer, Karin A

2017-02-01

This study had three purposes, all related to evaluating energy expenditure (EE) prediction accuracy from body-worn accelerometers: (1) compare linear regression to linear mixed models, (2) compare linear models to artificial neural network models, and (3) compare accuracy of accelerometers placed on the hip, thigh, and wrists. Forty individuals performed 13 activities in a 90 min semi-structured, laboratory-based protocol. Participants wore accelerometers on the right hip, right thigh, and both wrists and a portable metabolic analyzer (EE criterion). Four EE prediction models were developed for each accelerometer: linear regression, linear mixed, and two ANN models. EE prediction accuracy was assessed using correlations, root mean square error (RMSE), and bias and was compared across models and accelerometers using repeated-measures analysis of variance. For all accelerometer placements, there were no significant differences for correlations or RMSE between linear regression and linear mixed models (correlations: r  =  0.71-0.88, RMSE: 1.11-1.61 METs; p  >  0.05). For the thigh-worn accelerometer, there were no differences in correlations or RMSE between linear and ANN models (ANN-correlations: r  =  0.89, RMSE: 1.07-1.08 METs. Linear models-correlations: r  =  0.88, RMSE: 1.10-1.11 METs; p  >  0.05). Conversely, one ANN had higher correlations and lower RMSE than both linear models for the hip (ANN-correlation: r  =  0.88, RMSE: 1.12 METs. Linear models-correlations: r  =  0.86, RMSE: 1.18-1.19 METs; p  <  0.05), and both ANNs had higher correlations and lower RMSE than both linear models for the wrist-worn accelerometers (ANN-correlations: r  =  0.82-0.84, RMSE: 1.26-1.32 METs. Linear models-correlations: r  =  0.71-0.73, RMSE: 1.55-1.61 METs; p  <  0.01). For studies using wrist-worn accelerometers, machine learning models offer a significant improvement in EE prediction accuracy over linear models. Conversely, linear models showed similar EE prediction accuracy to machine learning models for hip- and thigh-worn accelerometers and may be viable alternative modeling techniques for EE prediction for hip- or thigh-worn accelerometers.

Wheat flour dough Alveograph characteristics predicted by Mixolab regression models.

PubMed

Codină, Georgiana Gabriela; Mironeasa, Silvia; Mironeasa, Costel; Popa, Ciprian N; Tamba-Berehoiu, Radiana

2012-02-01

In Romania, the Alveograph is the most used device to evaluate the rheological properties of wheat flour dough, but lately the Mixolab device has begun to play an important role in the breadmaking industry. These two instruments are based on different principles but there are some correlations that can be found between the parameters determined by the Mixolab and the rheological properties of wheat dough measured with the Alveograph. Statistical analysis on 80 wheat flour samples using the backward stepwise multiple regression method showed that Mixolab values using the ‘Chopin S’ protocol (40 samples) and ‘Chopin + ’ protocol (40 samples) can be used to elaborate predictive models for estimating the value of the rheological properties of wheat dough: baking strength (W), dough tenacity (P) and extensibility (L). The correlation analysis confirmed significant findings (P < 0.05 and P < 0.01) between the parameters of wheat dough studied by the Mixolab and its rheological properties measured with the Alveograph. A number of six predictive linear equations were obtained. Linear regression models gave multiple regression coefficients with R²(adjusted) > 0.70 for P, R²(adjusted) > 0.70 for W and R²(adjusted) > 0.38 for L, at a 95% confidence interval. Copyright © 2011 Society of Chemical Industry.

Seasonal forecasting of high wind speeds over Western Europe

NASA Astrophysics Data System (ADS)

Palutikof, J. P.; Holt, T.

2003-04-01

As financial losses associated with extreme weather events escalate, there is interest from end users in the forestry and insurance industries, for example, in the development of seasonal forecasting models with a long lead time. This study uses exceedences of the 90th, 95th, and 99th percentiles of daily maximum wind speed over the period 1958 to present to derive predictands of winter wind extremes. The source data is the 6-hourly NCEP Reanalysis gridded surface wind field. Predictor variables include principal components of Atlantic sea surface temperature and several indices of climate variability, including the NAO and SOI. Lead times of up to a year are considered, in monthly increments. Three regression techniques are evaluated; multiple linear regression (MLR), principal component regression (PCR), and partial least squares regression (PLS). PCR and PLS proved considerably superior to MLR with much lower standard errors. PLS was chosen to formulate the predictive model since it offers more flexibility in experimental design and gave slightly better results than PCR. The results indicate that winter windiness can be predicted with considerable skill one year ahead for much of coastal Europe, but that this deteriorates rapidly in the hinterland. The experiment succeeded in highlighting PLS as a very useful method for developing more precise forecasting models, and in identifying areas of high predictability.

Predicting Active Users' Personality Based on Micro-Blogging Behaviors

PubMed Central

Hao, Bibo; Guan, Zengda; Zhu, Tingshao

2014-01-01

Because of its richness and availability, micro-blogging has become an ideal platform for conducting psychological research. In this paper, we proposed to predict active users' personality traits through micro-blogging behaviors. 547 Chinese active users of micro-blogging participated in this study. Their personality traits were measured by the Big Five Inventory, and digital records of micro-blogging behaviors were collected via web crawlers. After extracting 845 micro-blogging behavioral features, we first trained classification models utilizing Support Vector Machine (SVM), differentiating participants with high and low scores on each dimension of the Big Five Inventory. The classification accuracy ranged from 84% to 92%. We also built regression models utilizing PaceRegression methods, predicting participants' scores on each dimension of the Big Five Inventory. The Pearson correlation coefficients between predicted scores and actual scores ranged from 0.48 to 0.54. Results indicated that active users' personality traits could be predicted by micro-blogging behaviors. PMID:24465462

Regression analysis using dependent Polya trees.

PubMed

Schörgendorfer, Angela; Branscum, Adam J

2013-11-30

Many commonly used models for linear regression analysis force overly simplistic shape and scale constraints on the residual structure of data. We propose a semiparametric Bayesian model for regression analysis that produces data-driven inference by using a new type of dependent Polya tree prior to model arbitrary residual distributions that are allowed to evolve across increasing levels of an ordinal covariate (e.g., time, in repeated measurement studies). By modeling residual distributions at consecutive covariate levels or time points using separate, but dependent Polya tree priors, distributional information is pooled while allowing for broad pliability to accommodate many types of changing residual distributions. We can use the proposed dependent residual structure in a wide range of regression settings, including fixed-effects and mixed-effects linear and nonlinear models for cross-sectional, prospective, and repeated measurement data. A simulation study illustrates the flexibility of our novel semiparametric regression model to accurately capture evolving residual distributions. In an application to immune development data on immunoglobulin G antibodies in children, our new model outperforms several contemporary semiparametric regression models based on a predictive model selection criterion. Copyright © 2013 John Wiley & Sons, Ltd.

Residential magnetic fields predicted from wiring configurations: I. Exposure model.

PubMed

Bowman, J D; Thomas, D C; Jiang, L; Jiang, F; Peters, J M

1999-10-01

A physically based model for residential magnetic fields from electric transmission and distribution wiring was developed to reanalyze the Los Angeles study of childhood leukemia by London et al. For this exposure model, magnetic field measurements were fitted to a function of wire configuration attributes that was derived from a multipole expansion of the Law of Biot and Savart. The model parameters were determined by nonlinear regression techniques, using wiring data, distances, and the geometric mean of the ELF magnetic field magnitude from 24-h bedroom measurements taken at 288 homes during the epidemiologic study. The best fit to the measurement data was obtained with separate models for the two major utilities serving Los Angeles County. This model's predictions produced a correlation of 0.40 with the measured fields, an improvement on the 0.27 correlation obtained with the Wertheimer-Leeper (WL) wire code. For the leukemia risk analysis in a companion paper, the regression model predicts exposures to the 24-h geometric mean of the ELF magnetic fields in Los Angeles homes where only wiring data and distances have been obtained. Since these input parameters for the exposure model usually do not change for many years, the predicted magnetic fields will be stable over long time periods, just like the WL code. If the geometric mean is not the exposure metric associated with cancer, this regression technique could be used to estimate long-term exposures to temporal variability metrics and other characteristics of the ELF magnetic field which may be cancer risk factors.

Studying Individual Differences in Predictability with Gamma Regression and Nonlinear Multilevel Models

ERIC Educational Resources Information Center

Culpepper, Steven Andrew

2010-01-01

Statistical prediction remains an important tool for decisions in a variety of disciplines. An equally important issue is identifying factors that contribute to more or less accurate predictions. The time series literature includes well developed methods for studying predictability and volatility over time. This article develops…

Simulating land-use changes by incorporating spatial autocorrelation and self-organization in CLUE-S modeling: a case study in Zengcheng District, Guangzhou, China

NASA Astrophysics Data System (ADS)

Mei, Zhixiong; Wu, Hao; Li, Shiyun

2018-06-01

The Conversion of Land Use and its Effects at Small regional extent (CLUE-S), which is a widely used model for land-use simulation, utilizes logistic regression to estimate the relationships between land use and its drivers, and thus, predict land-use change probabilities. However, logistic regression disregards possible spatial autocorrelation and self-organization in land-use data. Autologistic regression can depict spatial autocorrelation but cannot address self-organization, while logistic regression by considering only self-organization (NElogistic regression) fails to capture spatial autocorrelation. Therefore, this study developed a regression (NE-autologistic regression) method, which incorporated both spatial autocorrelation and self-organization, to improve CLUE-S. The Zengcheng District of Guangzhou, China was selected as the study area. The land-use data of 2001, 2005, and 2009, as well as 10 typical driving factors, were used to validate the proposed regression method and the improved CLUE-S model. Then, three future land-use scenarios in 2020: the natural growth scenario, ecological protection scenario, and economic development scenario, were simulated using the improved model. Validation results showed that NE-autologistic regression performed better than logistic regression, autologistic regression, and NE-logistic regression in predicting land-use change probabilities. The spatial allocation accuracy and kappa values of NE-autologistic-CLUE-S were higher than those of logistic-CLUE-S, autologistic-CLUE-S, and NE-logistic-CLUE-S for the simulations of two periods, 2001-2009 and 2005-2009, which proved that the improved CLUE-S model achieved the best simulation and was thereby effective to a certain extent. The scenario simulation results indicated that under all three scenarios, traffic land and residential/industrial land would increase, whereas arable land and unused land would decrease during 2009-2020. Apparent differences also existed in the simulated change sizes and locations of each land-use type under different scenarios. The results not only demonstrate the validity of the improved model but also provide a valuable reference for relevant policy-makers.

Evaluation and prediction of shrub cover in coastal Oregon forests (USA)

Treesearch

Becky K. Kerns; Janet L. Ohmann

2004-01-01

We used data from regional forest inventories and research programs, coupled with mapped climatic and topographic information, to explore relationships and develop multiple linear regression (MLR) and regression tree models for total and deciduous shrub cover in the Oregon coastal province. Results from both types of models indicate that forest structure variables were...

Anticipating Mathematics Performance: A Cross-Validation Comparison of AID3 and Regression. AIR 1988 Annual Forum Paper.

ERIC Educational Resources Information Center

Bloom, Allan M.; And Others

In response to the increasing importance of student performance in required classes, research was conducted to compare two prediction procedures, linear modeling using multiple regression and nonlinear modeling using AID3. Performance in the first college math course (College Mathematics, Calculus, or Business Calculus Matrices) was the dependent…

Using Regression Analysis in Departmental Budget Allocations. IR Applications, Volume 24, November 1, 2009

ERIC Educational Resources Information Center

Luna, Andrew L.; Brennan, Kelly A.

2009-01-01

This study uses a regression model to determine if a significant difference exists between the actual budget allocation that an academic department received and the model's predicted budget allocation for that same department. Budget data from a Southeastern Master's/Comprehensive state university were used as the dependent variable, and the…

Prediction of Return-to-original-work after an Industrial Accident Using Machine Learning and Comparison of Techniques

PubMed Central

2018-01-01

Background Many studies have tried to develop predictors for return-to-work (RTW). However, since complex factors have been demonstrated to predict RTW, it is difficult to use them practically. This study investigated whether factors used in previous studies could predict whether an individual had returned to his/her original work by four years after termination of the worker's recovery period. Methods An initial logistic regression analysis of 1,567 participants of the fourth Panel Study of Worker's Compensation Insurance yielded odds ratios. The participants were divided into two subsets, a training dataset and a test dataset. Using the training dataset, logistic regression, decision tree, random forest, and support vector machine models were established, and important variables of each model were identified. The predictive abilities of the different models were compared. Results The analysis showed that only earned income and company-related factors significantly affected return-to-original-work (RTOW). The random forest model showed the best accuracy among the tested machine learning models; however, the difference was not prominent. Conclusion It is possible to predict a worker's probability of RTOW using machine learning techniques with moderate accuracy. PMID:29736160

Using data mining to predict success in a weight loss trial.

PubMed

Batterham, M; Tapsell, L; Charlton, K; O'Shea, J; Thorne, R

2017-08-01

Traditional methods for predicting weight loss success use regression approaches, which make the assumption that the relationships between the independent and dependent (or logit of the dependent) variable are linear. The aim of the present study was to investigate the relationship between common demographic and early weight loss variables to predict weight loss success at 12 months without making this assumption. Data mining methods (decision trees, generalised additive models and multivariate adaptive regression splines), in addition to logistic regression, were employed to predict: (i) weight loss success (defined as ≥5%) at the end of a 12-month dietary intervention using demographic variables [body mass index (BMI), sex and age]; percentage weight loss at 1 month; and (iii) the difference between actual and predicted weight loss using an energy balance model. The methods were compared by assessing model parsimony and the area under the curve (AUC). The decision tree provided the most clinically useful model and had a good accuracy (AUC 0.720 95% confidence interval = 0.600-0.840). Percentage weight loss at 1 month (≥0.75%) was the strongest predictor for successful weight loss. Within those individuals losing ≥0.75%, individuals with a BMI (≥27 kg m -2 ) were more likely to be successful than those with a BMI between 25 and 27 kg m -2 . Data mining methods can provide a more accurate way of assessing relationships when conventional assumptions are not met. In the present study, a decision tree provided the most parsimonious model. Given that early weight loss cannot be predicted before randomisation, incorporating this information into a post randomisation trial design may give better weight loss results. © 2017 The British Dietetic Association Ltd.

A Ranking Approach to Genomic Selection.

PubMed

Blondel, Mathieu; Onogi, Akio; Iwata, Hiroyoshi; Ueda, Naonori

2015-01-01

Genomic selection (GS) is a recent selective breeding method which uses predictive models based on whole-genome molecular markers. Until now, existing studies formulated GS as the problem of modeling an individual's breeding value for a particular trait of interest, i.e., as a regression problem. To assess predictive accuracy of the model, the Pearson correlation between observed and predicted trait values was used. In this paper, we propose to formulate GS as the problem of ranking individuals according to their breeding value. Our proposed framework allows us to employ machine learning methods for ranking which had previously not been considered in the GS literature. To assess ranking accuracy of a model, we introduce a new measure originating from the information retrieval literature called normalized discounted cumulative gain (NDCG). NDCG rewards more strongly models which assign a high rank to individuals with high breeding value. Therefore, NDCG reflects a prerequisite objective in selective breeding: accurate selection of individuals with high breeding value. We conducted a comparison of 10 existing regression methods and 3 new ranking methods on 6 datasets, consisting of 4 plant species and 25 traits. Our experimental results suggest that tree-based ensemble methods including McRank, Random Forests and Gradient Boosting Regression Trees achieve excellent ranking accuracy. RKHS regression and RankSVM also achieve good accuracy when used with an RBF kernel. Traditional regression methods such as Bayesian lasso, wBSR and BayesC were found less suitable for ranking. Pearson correlation was found to correlate poorly with NDCG. Our study suggests two important messages. First, ranking methods are a promising research direction in GS. Second, NDCG can be a useful evaluation measure for GS.

Assessing Principal Component Regression Prediction of Neurochemicals Detected with Fast-Scan Cyclic Voltammetry

PubMed Central

2011-01-01

Principal component regression is a multivariate data analysis approach routinely used to predict neurochemical concentrations from in vivo fast-scan cyclic voltammetry measurements. This mathematical procedure can rapidly be employed with present day computer programming languages. Here, we evaluate several methods that can be used to evaluate and improve multivariate concentration determination. The cyclic voltammetric representation of the calculated regression vector is shown to be a valuable tool in determining whether the calculated multivariate model is chemically appropriate. The use of Cook’s distance successfully identified outliers contained within in vivo fast-scan cyclic voltammetry training sets. This work also presents the first direct interpretation of a residual color plot and demonstrated the effect of peak shifts on predicted dopamine concentrations. Finally, separate analyses of smaller increments of a single continuous measurement could not be concatenated without substantial error in the predicted neurochemical concentrations due to electrode drift. Taken together, these tools allow for the construction of more robust multivariate calibration models and provide the first approach to assess the predictive ability of a procedure that is inherently impossible to validate because of the lack of in vivo standards. PMID:21966586

Assessing principal component regression prediction of neurochemicals detected with fast-scan cyclic voltammetry.

PubMed

Keithley, Richard B; Wightman, R Mark

2011-06-07

Principal component regression is a multivariate data analysis approach routinely used to predict neurochemical concentrations from in vivo fast-scan cyclic voltammetry measurements. This mathematical procedure can rapidly be employed with present day computer programming languages. Here, we evaluate several methods that can be used to evaluate and improve multivariate concentration determination. The cyclic voltammetric representation of the calculated regression vector is shown to be a valuable tool in determining whether the calculated multivariate model is chemically appropriate. The use of Cook's distance successfully identified outliers contained within in vivo fast-scan cyclic voltammetry training sets. This work also presents the first direct interpretation of a residual color plot and demonstrated the effect of peak shifts on predicted dopamine concentrations. Finally, separate analyses of smaller increments of a single continuous measurement could not be concatenated without substantial error in the predicted neurochemical concentrations due to electrode drift. Taken together, these tools allow for the construction of more robust multivariate calibration models and provide the first approach to assess the predictive ability of a procedure that is inherently impossible to validate because of the lack of in vivo standards.

Bias and uncertainty in regression-calibrated models of groundwater flow in heterogeneous media

USGS Publications Warehouse

Cooley, R.L.; Christensen, S.

2006-01-01

Groundwater models need to account for detailed but generally unknown spatial variability (heterogeneity) of the hydrogeologic model inputs. To address this problem we replace the large, m-dimensional stochastic vector ?? that reflects both small and large scales of heterogeneity in the inputs by a lumped or smoothed m-dimensional approximation ????*, where ?? is an interpolation matrix and ??* is a stochastic vector of parameters. Vector ??* has small enough dimension to allow its estimation with the available data. The consequence of the replacement is that model function f(????*) written in terms of the approximate inputs is in error with respect to the same model function written in terms of ??, ??,f(??), which is assumed to be nearly exact. The difference f(??) - f(????*), termed model error, is spatially correlated, generates prediction biases, and causes standard confidence and prediction intervals to be too small. Model error is accounted for in the weighted nonlinear regression methodology developed to estimate ??* and assess model uncertainties by incorporating the second-moment matrix of the model errors into the weight matrix. Techniques developed by statisticians to analyze classical nonlinear regression methods are extended to analyze the revised method. The analysis develops analytical expressions for bias terms reflecting the interaction of model nonlinearity and model error, for correction factors needed to adjust the sizes of confidence and prediction intervals for this interaction, and for correction factors needed to adjust the sizes of confidence and prediction intervals for possible use of a diagonal weight matrix in place of the correct one. If terms expressing the degree of intrinsic nonlinearity for f(??) and f(????*) are small, then most of the biases are small and the correction factors are reduced in magnitude. Biases, correction factors, and confidence and prediction intervals were obtained for a test problem for which model error is large to test robustness of the methodology. Numerical results conform with the theoretical analysis. ?? 2005 Elsevier Ltd. All rights reserved.

QSAR, docking and ADMET studies of artemisinin derivatives for antimalarial activity targeting plasmepsin II, a hemoglobin-degrading enzyme from P. falciparum.

PubMed

Qidwai, Tabish; Yadav, Dharmendra K; Khan, Feroz; Dhawan, Sangeeta; Bhakuni, R S

2012-01-01

This work presents the development of quantitative structure activity relationship (QSAR) model to predict the antimalarial activity of artemisinin derivatives. The structures of the molecules are represented by chemical descriptors that encode topological, geometric, and electronic structure features. Screening through QSAR model suggested that compounds A24, A24a, A53, A54, A62 and A64 possess significant antimalarial activity. Linear model is developed by the multiple linear regression method to link structures to their reported antimalarial activity. The correlation in terms of regression coefficient (r(2)) was 0.90 and prediction accuracy of model in terms of cross validation regression coefficient (rCV(2)) was 0.82. This study indicates that chemical properties viz., atom count (all atoms), connectivity index (order 1, standard), ring count (all rings), shape index (basic kappa, order 2), and solvent accessibility surface area are well correlated with antimalarial activity. The docking study showed high binding affinity of predicted active compounds against antimalarial target Plasmepsins (Plm-II). Further studies for oral bioavailability, ADMET and toxicity risk assessment suggest that compound A24, A24a, A53, A54, A62 and A64 exhibits marked antimalarial activity comparable to standard antimalarial drugs. Later one of the predicted active compound A64 was chemically synthesized, structure elucidated by NMR and in vivo tested in multidrug resistant strain of Plasmodium yoelii nigeriensis infected mice. The experimental results obtained agreed well with the predicted values.

Estimation of streamflow, base flow, and nitrate-nitrogen loads in Iowa using multiple linear regression models

USGS Publications Warehouse

Schilling, K.E.; Wolter, C.F.

2005-01-01

Nineteen variables, including precipitation, soils and geology, land use, and basin morphologic characteristics, were evaluated to develop Iowa regression models to predict total streamflow (Q), base flow (Qb), storm flow (Qs) and base flow percentage (%Qb) in gauged and ungauged watersheds in the state. Discharge records from a set of 33 watersheds across the state for the 1980 to 2000 period were separated into Qb and Qs. Multiple linear regression found that 75.5 percent of long term average Q was explained by rainfall, sand content, and row crop percentage variables, whereas 88.5 percent of Qb was explained by these three variables plus permeability and floodplain area variables. Qs was explained by average rainfall and %Qb was a function of row crop percentage, permeability, and basin slope variables. Regional regression models developed for long term average Q and Qb were adapted to annual rainfall and showed good correlation between measured and predicted values. Combining the regression model for Q with an estimate of mean annual nitrate concentration, a map of potential nitrate loads in the state was produced. Results from this study have important implications for understanding geomorphic and land use controls on streamflow and base flow in Iowa watersheds and similar agriculture dominated watersheds in the glaciated Midwest. (JAWRA) (Copyright ?? 2005).

Spatial prediction of soil texture in region Centre (France) from summary data

NASA Astrophysics Data System (ADS)

Dobarco, Mercedes Roman; Saby, Nicolas; Paroissien, Jean-Baptiste; Orton, Tom G.

2015-04-01

Soil texture is a key controlling factor of important soil functions like water and nutrient holding capacity, retention of pollutants, drainage, soil biodiversity, and C cycling. High resolution soil texture maps enhance our understanding of the spatial distribution of soil properties and provide valuable information for decision making and crop management, environmental protection, and hydrological planning. We predicted the soil texture of agricultural topsoils in the Region Centre (France) combining regression and area-to-point kriging. Soil texture data was collected from the French soil-test database (BDAT), which is populated with soil analysis performed by farmers' demand. To protect the anonymity of the farms the data was treated by commune. In a first step, summary statistics of environmental covariates by commune were used to develop prediction models with Cubist, boosted regression trees, and random forests. In a second step the residuals of each individual observation were summarized by commune and kriged following the method developed by Orton et al. (2012). This approach allowed to include non-linear relationships among covariates and soil texture while accounting for the uncertainty on areal means in the area-to-point kriging step. Independent validation of the models was done using data from the systematic soil monitoring network of French soils. Future work will compare the performance of these models with a non-stationary variance geostatistical model using the most important covariates and summary statistics of texture data. The results will inform on whether the later and statistically more-challenging approach improves significantly texture predictions or whether the more simple area-to-point regression kriging can offer satisfactory results. The application of area-to-point regression kriging at national level using BDAT data has the potential to improve soil texture predictions for agricultural topsoils, especially when combined with existing maps (i.e., model ensemble).

Prediction of siRNA potency using sparse logistic regression.

PubMed

Hu, Wei; Hu, John

2014-06-01

RNA interference (RNAi) can modulate gene expression at post-transcriptional as well as transcriptional levels. Short interfering RNA (siRNA) serves as a trigger for the RNAi gene inhibition mechanism, and therefore is a crucial intermediate step in RNAi. There have been extensive studies to identify the sequence characteristics of potent siRNAs. One such study built a linear model using LASSO (Least Absolute Shrinkage and Selection Operator) to measure the contribution of each siRNA sequence feature. This model is simple and interpretable, but it requires a large number of nonzero weights. We have introduced a novel technique, sparse logistic regression, to build a linear model using single-position specific nucleotide compositions which has the same prediction accuracy of the linear model based on LASSO. The weights in our new model share the same general trend as those in the previous model, but have only 25 nonzero weights out of a total 84 weights, a 54% reduction compared to the previous model. Contrary to the linear model based on LASSO, our model suggests that only a few positions are influential on the efficacy of the siRNA, which are the 5' and 3' ends and the seed region of siRNA sequences. We also employed sparse logistic regression to build a linear model using dual-position specific nucleotide compositions, a task LASSO is not able to accomplish well due to its high dimensional nature. Our results demonstrate the superiority of sparse logistic regression as a technique for both feature selection and regression over LASSO in the context of siRNA design.

BFLCRM: A BAYESIAN FUNCTIONAL LINEAR COX REGRESSION MODEL FOR PREDICTING TIME TO CONVERSION TO ALZHEIMER’S DISEASE*

PubMed Central

Lee, Eunjee; Zhu, Hongtu; Kong, Dehan; Wang, Yalin; Giovanello, Kelly Sullivan; Ibrahim, Joseph G

2015-01-01

The aim of this paper is to develop a Bayesian functional linear Cox regression model (BFLCRM) with both functional and scalar covariates. This new development is motivated by establishing the likelihood of conversion to Alzheimer’s disease (AD) in 346 patients with mild cognitive impairment (MCI) enrolled in the Alzheimer’s Disease Neuroimaging Initiative 1 (ADNI-1) and the early markers of conversion. These 346 MCI patients were followed over 48 months, with 161 MCI participants progressing to AD at 48 months. The functional linear Cox regression model was used to establish that functional covariates including hippocampus surface morphology and scalar covariates including brain MRI volumes, cognitive performance (ADAS-Cog), and APOE status can accurately predict time to onset of AD. Posterior computation proceeds via an efficient Markov chain Monte Carlo algorithm. A simulation study is performed to evaluate the finite sample performance of BFLCRM. PMID:26900412

A crash-prediction model for multilane roads.

PubMed

Caliendo, Ciro; Guida, Maurizio; Parisi, Alessandra

2007-07-01

Considerable research has been carried out in recent years to establish relationships between crashes and traffic flow, geometric infrastructure characteristics and environmental factors for two-lane rural roads. Crash-prediction models focused on multilane rural roads, however, have rarely been investigated. In addition, most research has paid but little attention to the safety effects of variables such as stopping sight distance and pavement surface characteristics. Moreover, the statistical approaches have generally included Poisson and Negative Binomial regression models, whilst Negative Multinomial regression model has been used to a lesser extent. Finally, as far as the authors are aware, prediction models involving all the above-mentioned factors have still not been developed in Italy for multilane roads, such as motorways. Thus, in this paper crash-prediction models for a four-lane median-divided Italian motorway were set up on the basis of accident data observed during a 5-year monitoring period extending between 1999 and 2003. The Poisson, Negative Binomial and Negative Multinomial regression models, applied separately to tangents and curves, were used to model the frequency of accident occurrence. Model parameters were estimated by the Maximum Likelihood Method, and the Generalized Likelihood Ratio Test was applied to detect the significant variables to be included in the model equation. Goodness-of-fit was measured by means of both the explained fraction of total variation and the explained fraction of systematic variation. The Cumulative Residuals Method was also used to test the adequacy of a regression model throughout the range of each variable. The candidate set of explanatory variables was: length (L), curvature (1/R), annual average daily traffic (AADT), sight distance (SD), side friction coefficient (SFC), longitudinal slope (LS) and the presence of a junction (J). Separate prediction models for total crashes and for fatal and injury crashes only were considered. For curves it is shown that significant variables are L, 1/R and AADT, whereas for tangents they are L, AADT and junctions. The effect of rain precipitation was analysed on the basis of hourly rainfall data and assumptions about drying time. It is shown that a wet pavement significantly increases the number of crashes. The models developed in this paper for Italian motorways appear to be useful for many applications such as the detection of critical factors, the estimation of accident reduction due to infrastructure and pavement improvement, and the predictions of accidents counts when comparing different design options. Thus this research may represent a point of reference for engineers in adjusting or designing multilane roads.

The use of regression tree analysis for predicting the functional outcome following traumatic spinal cord injury.

PubMed

Facchinello, Yann; Beauséjour, Marie; Richard-Denis, Andreane; Thompson, Cynthia; Mac-Thiong, Jean-Marc

2017-10-25

Predicting the long-term functional outcome following traumatic spinal cord injury is needed to adapt medical strategies and to plan an optimized rehabilitation. This study investigates the use of regression tree for the development of predictive models based on acute clinical and demographic predictors. This prospective study was performed on 172 patients hospitalized following traumatic spinal cord injury. Functional outcome was quantified using the Spinal Cord Independence Measure collected within the first-year post injury. Age, delay prior to surgery and Injury Severity Score were considered as continuous predictors while energy of injury, trauma mechanisms, neurological level of injury, injury severity, occurrence of early spasticity, urinary tract infection, pressure ulcer and pneumonia were coded as categorical inputs. A simplified model was built using only injury severity, neurological level, energy and age as predictor and was compared to a more complex model considering all 11 predictors mentioned above The models built using 4 and 11 predictors were found to explain 51.4% and 62.3% of the variance of the Spinal Cord Independence Measure total score after validation, respectively. The severity of the neurological deficit at admission was found to be the most important predictor. Other important predictors were the Injury Severity Score, age, neurological level and delay prior to surgery. Regression trees offer promising performances for predicting the functional outcome after a traumatic spinal cord injury. It could help to determine the number and type of predictors leading to a prediction model of the functional outcome that can be used clinically in the future.

Universal LD50 predictions using deep learning

EPA Science Inventory

NICEATM Predictive Models for Acute Oral Systemic Toxicity LD50 entry Risa R. Sayre (sayre.risa@epa.gov) & Christopher M. Grulke Our approach uses an ensemble of multilayer perceptron regressions to predict rat acute oral LD50 values from chemical features. Features were genera...

Predictive Models of target organ and Systemic toxicities (BOSC)

EPA Science Inventory

The objective of this work is to predict the hazard classification and point of departure (PoD) of untested chemicals in repeat-dose animal testing studies. We used supervised machine learning to objectively evaluate the predictive accuracy of different classification and regress...

Cervical Vertebral Body's Volume as a New Parameter for Predicting the Skeletal Maturation Stages.

PubMed

Choi, Youn-Kyung; Kim, Jinmi; Yamaguchi, Tetsutaro; Maki, Koutaro; Ko, Ching-Chang; Kim, Yong-Il

2016-01-01

This study aimed to determine the correlation between the volumetric parameters derived from the images of the second, third, and fourth cervical vertebrae by using cone beam computed tomography with skeletal maturation stages and to propose a new formula for predicting skeletal maturation by using regression analysis. We obtained the estimation of skeletal maturation levels from hand-wrist radiographs and volume parameters derived from the second, third, and fourth cervical vertebrae bodies from 102 Japanese patients (54 women and 48 men, 5-18 years of age). We performed Pearson's correlation coefficient analysis and simple regression analysis. All volume parameters derived from the second, third, and fourth cervical vertebrae exhibited statistically significant correlations (P < 0.05). The simple regression model with the greatest R-square indicated the fourth-cervical-vertebra volume as an independent variable with a variance inflation factor less than ten. The explanation power was 81.76%. Volumetric parameters of cervical vertebrae using cone beam computed tomography are useful in regression models. The derived regression model has the potential for clinical application as it enables a simple and quantitative analysis to evaluate skeletal maturation level.

Cervical Vertebral Body's Volume as a New Parameter for Predicting the Skeletal Maturation Stages

PubMed Central

Choi, Youn-Kyung; Kim, Jinmi; Maki, Koutaro; Ko, Ching-Chang

2016-01-01

This study aimed to determine the correlation between the volumetric parameters derived from the images of the second, third, and fourth cervical vertebrae by using cone beam computed tomography with skeletal maturation stages and to propose a new formula for predicting skeletal maturation by using regression analysis. We obtained the estimation of skeletal maturation levels from hand-wrist radiographs and volume parameters derived from the second, third, and fourth cervical vertebrae bodies from 102 Japanese patients (54 women and 48 men, 5–18 years of age). We performed Pearson's correlation coefficient analysis and simple regression analysis. All volume parameters derived from the second, third, and fourth cervical vertebrae exhibited statistically significant correlations (P < 0.05). The simple regression model with the greatest R-square indicated the fourth-cervical-vertebra volume as an independent variable with a variance inflation factor less than ten. The explanation power was 81.76%. Volumetric parameters of cervical vertebrae using cone beam computed tomography are useful in regression models. The derived regression model has the potential for clinical application as it enables a simple and quantitative analysis to evaluate skeletal maturation level. PMID:27340668