Logistic regression for dichotomized counts.

PubMed

Preisser, John S; Das, Kalyan; Benecha, Habtamu; Stamm, John W

2016-12-01

Sometimes there is interest in a dichotomized outcome indicating whether a count variable is positive or zero. Under this scenario, the application of ordinary logistic regression may result in efficiency loss, which is quantifiable under an assumed model for the counts. In such situations, a shared-parameter hurdle model is investigated for more efficient estimation of regression parameters relating to overall effects of covariates on the dichotomous outcome, while handling count data with many zeroes. One model part provides a logistic regression containing marginal log odds ratio effects of primary interest, while an ancillary model part describes the mean count of a Poisson or negative binomial process in terms of nuisance regression parameters. Asymptotic efficiency of the logistic model parameter estimators of the two-part models is evaluated with respect to ordinary logistic regression. Simulations are used to assess the properties of the models with respect to power and Type I error, the latter investigated under both misspecified and correctly specified models. The methods are applied to data from a randomized clinical trial of three toothpaste formulations to prevent incident dental caries in a large population of Scottish schoolchildren. © The Author(s) 2014.

Fuzzy multinomial logistic regression analysis: A multi-objective programming approach

NASA Astrophysics Data System (ADS)

Abdalla, Hesham A.; El-Sayed, Amany A.; Hamed, Ramadan

2017-05-01

Parameter estimation for multinomial logistic regression is usually based on maximizing the likelihood function. For large well-balanced datasets, Maximum Likelihood (ML) estimation is a satisfactory approach. Unfortunately, ML can fail completely or at least produce poor results in terms of estimated probabilities and confidence intervals of parameters, specially for small datasets. In this study, a new approach based on fuzzy concepts is proposed to estimate parameters of the multinomial logistic regression. The study assumes that the parameters of multinomial logistic regression are fuzzy. Based on the extension principle stated by Zadeh and Bárdossy's proposition, a multi-objective programming approach is suggested to estimate these fuzzy parameters. A simulation study is used to evaluate the performance of the new approach versus Maximum likelihood (ML) approach. Results show that the new proposed model outperforms ML in cases of small datasets.

A Solution to Separation and Multicollinearity in Multiple Logistic Regression

PubMed Central

Shen, Jianzhao; Gao, Sujuan

2010-01-01

In dementia screening tests, item selection for shortening an existing screening test can be achieved using multiple logistic regression. However, maximum likelihood estimates for such logistic regression models often experience serious bias or even non-existence because of separation and multicollinearity problems resulting from a large number of highly correlated items. Firth (1993, Biometrika, 80(1), 27–38) proposed a penalized likelihood estimator for generalized linear models and it was shown to reduce bias and the non-existence problems. The ridge regression has been used in logistic regression to stabilize the estimates in cases of multicollinearity. However, neither solves the problems for each other. In this paper, we propose a double penalized maximum likelihood estimator combining Firth’s penalized likelihood equation with a ridge parameter. We present a simulation study evaluating the empirical performance of the double penalized likelihood estimator in small to moderate sample sizes. We demonstrate the proposed approach using a current screening data from a community-based dementia study. PMID:20376286

A Solution to Separation and Multicollinearity in Multiple Logistic Regression.

PubMed

Shen, Jianzhao; Gao, Sujuan

2008-10-01

In dementia screening tests, item selection for shortening an existing screening test can be achieved using multiple logistic regression. However, maximum likelihood estimates for such logistic regression models often experience serious bias or even non-existence because of separation and multicollinearity problems resulting from a large number of highly correlated items. Firth (1993, Biometrika, 80(1), 27-38) proposed a penalized likelihood estimator for generalized linear models and it was shown to reduce bias and the non-existence problems. The ridge regression has been used in logistic regression to stabilize the estimates in cases of multicollinearity. However, neither solves the problems for each other. In this paper, we propose a double penalized maximum likelihood estimator combining Firth's penalized likelihood equation with a ridge parameter. We present a simulation study evaluating the empirical performance of the double penalized likelihood estimator in small to moderate sample sizes. We demonstrate the proposed approach using a current screening data from a community-based dementia study.

Selecting risk factors: a comparison of discriminant analysis, logistic regression and Cox's regression model using data from the Tromsø Heart Study.

PubMed

Brenn, T; Arnesen, E

1985-01-01

For comparative evaluation, discriminant analysis, logistic regression and Cox's model were used to select risk factors for total and coronary deaths among 6595 men aged 20-49 followed for 9 years. Groups with mortality between 5 and 93 per 1000 were considered. Discriminant analysis selected variable sets only marginally different from the logistic and Cox methods which always selected the same sets. A time-saving option, offered for both the logistic and Cox selection, showed no advantage compared with discriminant analysis. Analysing more than 3800 subjects, the logistic and Cox methods consumed, respectively, 80 and 10 times more computer time than discriminant analysis. When including the same set of variables in non-stepwise analyses, all methods estimated coefficients that in most cases were almost identical. In conclusion, discriminant analysis is advocated for preliminary or stepwise analysis, otherwise Cox's method should be used.

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.

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.

Evaluation of methodology for the analysis of 'time-to-event' data in pharmacogenomic genome-wide association studies.

PubMed

Syed, Hamzah; Jorgensen, Andrea L; Morris, Andrew P

2016-06-01

To evaluate the power to detect associations between SNPs and time-to-event outcomes across a range of pharmacogenomic study designs while comparing alternative regression approaches. Simulations were conducted to compare Cox proportional hazards modeling accounting for censoring and logistic regression modeling of a dichotomized outcome at the end of the study. The Cox proportional hazards model was demonstrated to be more powerful than the logistic regression analysis. The difference in power between the approaches was highly dependent on the rate of censoring. Initial evaluation of single-nucleotide polymorphism association signals using computationally efficient software with dichotomized outcomes provides an effective screening tool for some design scenarios, and thus has important implications for the development of analytical protocols in pharmacogenomic studies.

[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.

Epidemiologic programs for computers and calculators. A microcomputer program for multiple logistic regression by unconditional and conditional maximum likelihood methods.

PubMed

Campos-Filho, N; Franco, E L

1989-02-01

A frequent procedure in matched case-control studies is to report results from the multivariate unmatched analyses if they do not differ substantially from the ones obtained after conditioning on the matching variables. Although conceptually simple, this rule requires that an extensive series of logistic regression models be evaluated by both the conditional and unconditional maximum likelihood methods. Most computer programs for logistic regression employ only one maximum likelihood method, which requires that the analyses be performed in separate steps. This paper describes a Pascal microcomputer (IBM PC) program that performs multiple logistic regression by both maximum likelihood estimation methods, which obviates the need for switching between programs to obtain relative risk estimates from both matched and unmatched analyses. The program calculates most standard statistics and allows factoring of categorical or continuous variables by two distinct methods of contrast. A built-in, descriptive statistics option allows the user to inspect the distribution of cases and controls across categories of any given variable.

Comparison of cranial sex determination by discriminant analysis and logistic regression.

PubMed

Amores-Ampuero, Anabel; Alemán, Inmaculada

2016-04-05

Various methods have been proposed for estimating dimorphism. The objective of this study was to compare sex determination results from cranial measurements using discriminant analysis or logistic regression. The study sample comprised 130 individuals (70 males) of known sex, age, and cause of death from San José cemetery in Granada (Spain). Measurements of 19 neurocranial dimensions and 11 splanchnocranial dimensions were subjected to discriminant analysis and logistic regression, and the percentages of correct classification were compared between the sex functions obtained with each method. The discriminant capacity of the selected variables was evaluated with a cross-validation procedure. The percentage accuracy with discriminant analysis was 78.2% for the neurocranium (82.4% in females and 74.6% in males) and 73.7% for the splanchnocranium (79.6% in females and 68.8% in males). These percentages were higher with logistic regression analysis: 85.7% for the neurocranium (in both sexes) and 94.1% for the splanchnocranium (100% in females and 91.7% in males).

Deletion Diagnostics for Alternating Logistic Regressions

PubMed Central

Preisser, John S.; By, Kunthel; Perin, Jamie; Qaqish, Bahjat F.

2013-01-01

Deletion diagnostics are introduced for the regression analysis of clustered binary outcomes estimated with alternating logistic regressions, an implementation of generalized estimating equations (GEE) that estimates regression coefficients in a marginal mean model and in a model for the intracluster association given by the log odds ratio. The diagnostics are developed within an estimating equations framework that recasts the estimating functions for association parameters based upon conditional residuals into equivalent functions based upon marginal residuals. Extensions of earlier work on GEE diagnostics follow directly, including computational formulae for one-step deletion diagnostics that measure the influence of a cluster of observations on the estimated regression parameters and on the overall marginal mean or association model fit. The diagnostic formulae are evaluated with simulations studies and with an application concerning an assessment of factors associated with health maintenance visits in primary care medical practices. The application and the simulations demonstrate that the proposed cluster-deletion diagnostics for alternating logistic regressions are good approximations of their exact fully iterated counterparts. PMID:22777960

No rationale for 1 variable per 10 events criterion for binary logistic regression analysis.

PubMed

van Smeden, Maarten; de Groot, Joris A H; Moons, Karel G M; Collins, Gary S; Altman, Douglas G; Eijkemans, Marinus J C; Reitsma, Johannes B

2016-11-24

Ten events per variable (EPV) is a widely advocated minimal criterion for sample size considerations in logistic regression analysis. Of three previous simulation studies that examined this minimal EPV criterion only one supports the use of a minimum of 10 EPV. In this paper, we examine the reasons for substantial differences between these extensive simulation studies. The current study uses Monte Carlo simulations to evaluate small sample bias, coverage of confidence intervals and mean square error of logit coefficients. Logistic regression models fitted by maximum likelihood and a modified estimation procedure, known as Firth's correction, are compared. The results show that besides EPV, the problems associated with low EPV depend on other factors such as the total sample size. It is also demonstrated that simulation results can be dominated by even a few simulated data sets for which the prediction of the outcome by the covariates is perfect ('separation'). We reveal that different approaches for identifying and handling separation leads to substantially different simulation results. We further show that Firth's correction can be used to improve the accuracy of regression coefficients and alleviate the problems associated with separation. The current evidence supporting EPV rules for binary logistic regression is weak. Given our findings, there is an urgent need for new research to provide guidance for supporting sample size considerations for binary logistic regression analysis.

The cross-validated AUC for MCP-logistic regression with high-dimensional data.

PubMed

Jiang, Dingfeng; Huang, Jian; Zhang, Ying

2013-10-01

We propose a cross-validated area under the receiving operator characteristic (ROC) curve (CV-AUC) criterion for tuning parameter selection for penalized methods in sparse, high-dimensional logistic regression models. We use this criterion in combination with the minimax concave penalty (MCP) method for variable selection. The CV-AUC criterion is specifically designed for optimizing the classification performance for binary outcome data. To implement the proposed approach, we derive an efficient coordinate descent algorithm to compute the MCP-logistic regression solution surface. Simulation studies are conducted to evaluate the finite sample performance of the proposed method and its comparison with the existing methods including the Akaike information criterion (AIC), Bayesian information criterion (BIC) or Extended BIC (EBIC). The model selected based on the CV-AUC criterion tends to have a larger predictive AUC and smaller classification error than those with tuning parameters selected using the AIC, BIC or EBIC. We illustrate the application of the MCP-logistic regression with the CV-AUC criterion on three microarray datasets from the studies that attempt to identify genes related to cancers. Our simulation studies and data examples demonstrate that the CV-AUC is an attractive method for tuning parameter selection for penalized methods in high-dimensional logistic regression models.

Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography.

PubMed

Kim, Sun Mi; Kim, Yongdai; Jeong, Kuhwan; Jeong, Heeyeong; Kim, Jiyoung

2018-01-01

The aim of this study was to compare the performance of image analysis for predicting breast cancer using two distinct regression models and to evaluate the usefulness of incorporating clinical and demographic data (CDD) into the image analysis in order to improve the diagnosis of breast cancer. This study included 139 solid masses from 139 patients who underwent a ultrasonography-guided core biopsy and had available CDD between June 2009 and April 2010. Three breast radiologists retrospectively reviewed 139 breast masses and described each lesion using the Breast Imaging Reporting and Data System (BI-RADS) lexicon. We applied and compared two regression methods-stepwise logistic (SL) regression and logistic least absolute shrinkage and selection operator (LASSO) regression-in which the BI-RADS descriptors and CDD were used as covariates. We investigated the performances of these regression methods and the agreement of radiologists in terms of test misclassification error and the area under the curve (AUC) of the tests. Logistic LASSO regression was superior (P<0.05) to SL regression, regardless of whether CDD was included in the covariates, in terms of test misclassification errors (0.234 vs. 0.253, without CDD; 0.196 vs. 0.258, with CDD) and AUC (0.785 vs. 0.759, without CDD; 0.873 vs. 0.735, with CDD). However, it was inferior (P<0.05) to the agreement of three radiologists in terms of test misclassification errors (0.234 vs. 0.168, without CDD; 0.196 vs. 0.088, with CDD) and the AUC without CDD (0.785 vs. 0.844, P<0.001), but was comparable to the AUC with CDD (0.873 vs. 0.880, P=0.141). Logistic LASSO regression based on BI-RADS descriptors and CDD showed better performance than SL in predicting the presence of breast cancer. The use of CDD as a supplement to the BI-RADS descriptors significantly improved the prediction of breast cancer using logistic LASSO regression.

Ensemble of trees approaches to risk adjustment for evaluating a hospital's performance.

PubMed

Liu, Yang; Traskin, Mikhail; Lorch, Scott A; George, Edward I; Small, Dylan

2015-03-01

A commonly used method for evaluating a hospital's performance on an outcome is to compare the hospital's observed outcome rate to the hospital's expected outcome rate given its patient (case) mix and service. The process of calculating the hospital's expected outcome rate given its patient mix and service is called risk adjustment (Iezzoni 1997). Risk adjustment is critical for accurately evaluating and comparing hospitals' performances since we would not want to unfairly penalize a hospital just because it treats sicker patients. The key to risk adjustment is accurately estimating the probability of an Outcome given patient characteristics. For cases with binary outcomes, the method that is commonly used in risk adjustment is logistic regression. In this paper, we consider ensemble of trees methods as alternatives for risk adjustment, including random forests and Bayesian additive regression trees (BART). Both random forests and BART are modern machine learning methods that have been shown recently to have excellent performance for prediction of outcomes in many settings. We apply these methods to carry out risk adjustment for the performance of neonatal intensive care units (NICU). We show that these ensemble of trees methods outperform logistic regression in predicting mortality among babies treated in NICU, and provide a superior method of risk adjustment compared to logistic regression.

Adjusting for Confounding in Early Postlaunch Settings: Going Beyond Logistic Regression Models.

PubMed

Schmidt, Amand F; Klungel, Olaf H; Groenwold, Rolf H H

2016-01-01

Postlaunch data on medical treatments can be analyzed to explore adverse events or relative effectiveness in real-life settings. These analyses are often complicated by the number of potential confounders and the possibility of model misspecification. We conducted a simulation study to compare the performance of logistic regression, propensity score, disease risk score, and stabilized inverse probability weighting methods to adjust for confounding. Model misspecification was induced in the independent derivation dataset. We evaluated performance using relative bias confidence interval coverage of the true effect, among other metrics. At low events per coefficient (1.0 and 0.5), the logistic regression estimates had a large relative bias (greater than -100%). Bias of the disease risk score estimates was at most 13.48% and 18.83%. For the propensity score model, this was 8.74% and >100%, respectively. At events per coefficient of 1.0 and 0.5, inverse probability weighting frequently failed or reduced to a crude regression, resulting in biases of -8.49% and 24.55%. Coverage of logistic regression estimates became less than the nominal level at events per coefficient ≤5. For the disease risk score, inverse probability weighting, and propensity score, coverage became less than nominal at events per coefficient ≤2.5, ≤1.0, and ≤1.0, respectively. Bias of misspecified disease risk score models was 16.55%. In settings with low events/exposed subjects per coefficient, disease risk score methods can be useful alternatives to logistic regression models, especially when propensity score models cannot be used. Despite better performance of disease risk score methods than logistic regression and propensity score models in small events per coefficient settings, bias, and coverage still deviated from nominal.

The alarming problems of confounding equivalence using logistic regression models in the perspective of causal diagrams.

PubMed

Yu, Yuanyuan; Li, Hongkai; Sun, Xiaoru; Su, Ping; Wang, Tingting; Liu, Yi; Yuan, Zhongshang; Liu, Yanxun; Xue, Fuzhong

2017-12-28

Confounders can produce spurious associations between exposure and outcome in observational studies. For majority of epidemiologists, adjusting for confounders using logistic regression model is their habitual method, though it has some problems in accuracy and precision. It is, therefore, important to highlight the problems of logistic regression and search the alternative method. Four causal diagram models were defined to summarize confounding equivalence. Both theoretical proofs and simulation studies were performed to verify whether conditioning on different confounding equivalence sets had the same bias-reducing potential and then to select the optimum adjusting strategy, in which logistic regression model and inverse probability weighting based marginal structural model (IPW-based-MSM) were compared. The "do-calculus" was used to calculate the true causal effect of exposure on outcome, then the bias and standard error were used to evaluate the performances of different strategies. Adjusting for different sets of confounding equivalence, as judged by identical Markov boundaries, produced different bias-reducing potential in the logistic regression model. For the sets satisfied G-admissibility, adjusting for the set including all the confounders reduced the equivalent bias to the one containing the parent nodes of the outcome, while the bias after adjusting for the parent nodes of exposure was not equivalent to them. In addition, all causal effect estimations through logistic regression were biased, although the estimation after adjusting for the parent nodes of exposure was nearest to the true causal effect. However, conditioning on different confounding equivalence sets had the same bias-reducing potential under IPW-based-MSM. Compared with logistic regression, the IPW-based-MSM could obtain unbiased causal effect estimation when the adjusted confounders satisfied G-admissibility and the optimal strategy was to adjust for the parent nodes of outcome, which obtained the highest precision. All adjustment strategies through logistic regression were biased for causal effect estimation, while IPW-based-MSM could always obtain unbiased estimation when the adjusted set satisfied G-admissibility. Thus, IPW-based-MSM was recommended to adjust for confounders set.

Analysis of a database to predict the result of allergy testing in vivo in patients with chronic nasal symptoms.

PubMed

Lacagnina, Valerio; Leto-Barone, Maria S; La Piana, Simona; Seidita, Aurelio; Pingitore, Giuseppe; Di Lorenzo, Gabriele

2014-01-01

This article uses the logistic regression model for diagnostic decision making in patients with chronic nasal symptoms. We studied the ability of the logistic regression model, obtained by the evaluation of a database, to detect patients with positive allergy skin-prick test (SPT) and patients with negative SPT. The model developed was validated using the data set obtained from another medical institution. The analysis was performed using a database obtained from a questionnaire administered to the patients with nasal symptoms containing personal data, clinical data, and results of allergy testing (SPT). All variables found to be significantly different between patients with positive and negative SPT (p < 0.05) were selected for the logistic regression models and were analyzed with backward stepwise logistic regression, evaluated with area under the curve of the receiver operating characteristic curve. A second set of patients from another institution was used to prove the model. The accuracy of the model in identifying, over the second set, both patients whose SPT will be positive and negative was high. The model detected 96% of patients with nasal symptoms and positive SPT and classified 94% of those with negative SPT. This study is preliminary to the creation of a software that could help the primary care doctors in a diagnostic decision making process (need of allergy testing) in patients complaining of chronic nasal symptoms.

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.

Matched samples logistic regression in case-control studies with missing values: when to break the matches.

PubMed

Hansson, Lisbeth; Khamis, Harry J

2008-12-01

Simulated data sets are used to evaluate conditional and unconditional maximum likelihood estimation in an individual case-control design with continuous covariates when there are different rates of excluded cases and different levels of other design parameters. The effectiveness of the estimation procedures is measured by method bias, variance of the estimators, root mean square error (RMSE) for logistic regression and the percentage of explained variation. Conditional estimation leads to higher RMSE than unconditional estimation in the presence of missing observations, especially for 1:1 matching. The RMSE is higher for the smaller stratum size, especially for the 1:1 matching. The percentage of explained variation appears to be insensitive to missing data, but is generally higher for the conditional estimation than for the unconditional estimation. It is particularly good for the 1:2 matching design. For minimizing RMSE, a high matching ratio is recommended; in this case, conditional and unconditional logistic regression models yield comparable levels of effectiveness. For maximizing the percentage of explained variation, the 1:2 matching design with the conditional logistic regression model is recommended.

Determination of osteoporosis risk factors using a multiple logistic regression model in postmenopausal Turkish women.

PubMed

Akkus, Zeki; Camdeviren, Handan; Celik, Fatma; Gur, Ali; Nas, Kemal

2005-09-01

To determine the risk factors of osteoporosis using a multiple binary logistic regression method and to assess the risk variables for osteoporosis, which is a major and growing health problem in many countries. We presented a case-control study, consisting of 126 postmenopausal healthy women as control group and 225 postmenopausal osteoporotic women as the case group. The study was carried out in the Department of Physical Medicine and Rehabilitation, Dicle University, Diyarbakir, Turkey between 1999-2002. The data from the 351 participants were collected using a standard questionnaire that contains 43 variables. A multiple logistic regression model was then used to evaluate the data and to find the best regression model. We classified 80.1% (281/351) of the participants using the regression model. Furthermore, the specificity value of the model was 67% (84/126) of the control group while the sensitivity value was 88% (197/225) of the case group. We found the distribution of residual values standardized for final model to be exponential using the Kolmogorow-Smirnow test (p=0.193). The receiver operating characteristic curve was found successful to predict patients with risk for osteoporosis. This study suggests that low levels of dietary calcium intake, physical activity, education, and longer duration of menopause are independent predictors of the risk of low bone density in our population. Adequate dietary calcium intake in combination with maintaining a daily physical activity, increasing educational level, decreasing birth rate, and duration of breast-feeding may contribute to healthy bones and play a role in practical prevention of osteoporosis in Southeast Anatolia. In addition, the findings of the present study indicate that the use of multivariate statistical method as a multiple logistic regression in osteoporosis, which maybe influenced by many variables, is better than univariate statistical evaluation.

Development and evaluation of habitat models for herpetofauna and small mammals

Treesearch

William M. Block; Michael L. Morrison; Peter E. Scott

1998-01-01

We evaluated the ability of discriminant analysis (DA), logistic regression (LR), and multiple regression (MR) to describe habitat use by amphibians, reptiles, and small mammals found in California oak woodlands. We also compared models derived from pitfall and live trapping data for several species. Habitat relations modeled by DA and LR produced similar results,...

Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble-based methods?

PubMed Central

Austin, Peter C; Lee, Douglas S; Steyerberg, Ewout W; Tu, Jack V

2012-01-01

In biomedical research, the logistic regression model is the most commonly used method for predicting the probability of a binary outcome. While many clinical researchers have expressed an enthusiasm for regression trees, this method may have limited accuracy for predicting health outcomes. We aimed to evaluate the improvement that is achieved by using ensemble-based methods, including bootstrap aggregation (bagging) of regression trees, random forests, and boosted regression trees. We analyzed 30-day mortality in two large cohorts of patients hospitalized with either acute myocardial infarction (N = 16,230) or congestive heart failure (N = 15,848) in two distinct eras (1999–2001 and 2004–2005). We found that both the in-sample and out-of-sample prediction of ensemble methods offered substantial improvement in predicting cardiovascular mortality compared to conventional regression trees. However, conventional logistic regression models that incorporated restricted cubic smoothing splines had even better performance. We conclude that ensemble methods from the data mining and machine learning literature increase the predictive performance of regression trees, but may not lead to clear advantages over conventional logistic regression models for predicting short-term mortality in population-based samples of subjects with cardiovascular disease. PMID:22777999

Evaluating the Locational Attributes of Education Management Organizations (EMOs)

ERIC Educational Resources Information Center

Gulosino, Charisse; Miron, Gary

2017-01-01

This study uses logistic and multinomial logistic regression models to analyze neighborhood factors affecting EMO (Education Management Organization)-operated schools' locational attributes (using census tracts) in 41 states for the 2014-2015 school year. Our research combines market-based school reform, institutional theory, and resource…

HEALER: homomorphic computation of ExAct Logistic rEgRession for secure rare disease variants analysis in GWAS

PubMed Central

Wang, Shuang; Zhang, Yuchen; Dai, Wenrui; Lauter, Kristin; Kim, Miran; Tang, Yuzhe; Xiong, Hongkai; Jiang, Xiaoqian

2016-01-01

Motivation: Genome-wide association studies (GWAS) have been widely used in discovering the association between genotypes and phenotypes. Human genome data contain valuable but highly sensitive information. Unprotected disclosure of such information might put individual’s privacy at risk. It is important to protect human genome data. Exact logistic regression is a bias-reduction method based on a penalized likelihood to discover rare variants that are associated with disease susceptibility. We propose the HEALER framework to facilitate secure rare variants analysis with a small sample size. Results: We target at the algorithm design aiming at reducing the computational and storage costs to learn a homomorphic exact logistic regression model (i.e. evaluate P-values of coefficients), where the circuit depth is proportional to the logarithmic scale of data size. We evaluate the algorithm performance using rare Kawasaki Disease datasets. Availability and implementation: Download HEALER at http://research.ucsd-dbmi.org/HEALER/ Contact: shw070@ucsd.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:26446135

The effect of high leverage points on the logistic ridge regression estimator having multicollinearity

NASA Astrophysics Data System (ADS)

Ariffin, Syaiba Balqish; Midi, Habshah

2014-06-01

This article is concerned with the performance of logistic ridge regression estimation technique in the presence of multicollinearity and high leverage points. In logistic regression, multicollinearity exists among predictors and in the information matrix. The maximum likelihood estimator suffers a huge setback in the presence of multicollinearity which cause regression estimates to have unduly large standard errors. To remedy this problem, a logistic ridge regression estimator is put forward. It is evident that the logistic ridge regression estimator outperforms the maximum likelihood approach for handling multicollinearity. The effect of high leverage points are then investigated on the performance of the logistic ridge regression estimator through real data set and simulation study. The findings signify that logistic ridge regression estimator fails to provide better parameter estimates in the presence of both high leverage points and multicollinearity.

Developmental Screening Referrals: Child and Family Factors that Predict Referral Completion

ERIC Educational Resources Information Center

Jennings, Danielle J.; Hanline, Mary Frances

2013-01-01

This study researched the predictive impact of developmental screening results and the effects of child and family characteristics on completion of referrals given for evaluation. Logistical and hierarchical logistic regression analyses were used to determine the significance of 10 independent variables on the predictor variable. The number of…

Sample size determination for logistic regression on a logit-normal distribution.

PubMed

Kim, Seongho; Heath, Elisabeth; Heilbrun, Lance

2017-06-01

Although the sample size for simple logistic regression can be readily determined using currently available methods, the sample size calculation for multiple logistic regression requires some additional information, such as the coefficient of determination ([Formula: see text]) of a covariate of interest with other covariates, which is often unavailable in practice. The response variable of logistic regression follows a logit-normal distribution which can be generated from a logistic transformation of a normal distribution. Using this property of logistic regression, we propose new methods of determining the sample size for simple and multiple logistic regressions using a normal transformation of outcome measures. Simulation studies and a motivating example show several advantages of the proposed methods over the existing methods: (i) no need for [Formula: see text] for multiple logistic regression, (ii) available interim or group-sequential designs, and (iii) much smaller required sample size.

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.

Using a binary logistic regression method and GIS for evaluating and mapping the groundwater spring potential in the Sultan Mountains (Aksehir, Turkey)

NASA Astrophysics Data System (ADS)

Ozdemir, Adnan

2011-07-01

SummaryThe purpose of this study is to produce a groundwater spring potential map of the Sultan Mountains in central Turkey, based on a logistic regression method within a Geographic Information System (GIS) environment. Using field surveys, the locations of the springs (440 springs) were determined in the study area. In this study, 17 spring-related factors were used in the analysis: geology, relative permeability, land use/land cover, precipitation, elevation, slope, aspect, total curvature, plan curvature, profile curvature, wetness index, stream power index, sediment transport capacity index, distance to drainage, distance to fault, drainage density, and fault density map. The coefficients of the predictor variables were estimated using binary logistic regression analysis and were used to calculate the groundwater spring potential for the entire study area. The accuracy of the final spring potential map was evaluated based on the observed springs. The accuracy of the model was evaluated by calculating the relative operating characteristics. The area value of the relative operating characteristic curve model was found to be 0.82. These results indicate that the model is a good estimator of the spring potential in the study area. The spring potential map shows that the areas of very low, low, moderate and high groundwater spring potential classes are 105.586 km 2 (28.99%), 74.271 km 2 (19.906%), 101.203 km 2 (27.14%), and 90.05 km 2 (24.671%), respectively. The interpretations of the potential map showed that stream power index, relative permeability of lithologies, geology, elevation, aspect, wetness index, plan curvature, and drainage density play major roles in spring occurrence and distribution in the Sultan Mountains. The logistic regression approach has not yet been used to delineate groundwater potential zones. In this study, the logistic regression method was used to locate potential zones for groundwater springs in the Sultan Mountains. The evolved model was found to be in strong agreement with the available groundwater spring test data. Hence, this method can be used routinely in groundwater exploration under favourable conditions.

Predicting risk for portal vein thrombosis in acute pancreatitis patients: A comparison of radical basis function artificial neural network and logistic regression models.

PubMed

Fei, Yang; Hu, Jian; Gao, Kun; Tu, Jianfeng; Li, Wei-Qin; Wang, Wei

2017-06-01

To construct a radical basis function (RBF) artificial neural networks (ANNs) model to predict the incidence of acute pancreatitis (AP)-induced portal vein thrombosis. The analysis included 353 patients with AP who had admitted between January 2011 and December 2015. RBF ANNs model and logistic regression model were constructed based on eleven factors relevant to AP respectively. Statistical indexes were used to evaluate the value of the prediction in two models. The predict sensitivity, specificity, positive predictive value, negative predictive value and accuracy by RBF ANNs model for PVT were 73.3%, 91.4%, 68.8%, 93.0% and 87.7%, respectively. There were significant differences between the RBF ANNs and logistic regression models in these parameters (P<0.05). In addition, a comparison of the area under receiver operating characteristic curves of the two models showed a statistically significant difference (P<0.05). The RBF ANNs model is more likely to predict the occurrence of PVT induced by AP than logistic regression model. D-dimer, AMY, Hct and PT were important prediction factors of approval for AP-induced PVT. Copyright © 2017 Elsevier Inc. All rights reserved.

The crux of the method: assumptions in ordinary least squares and logistic regression.

PubMed

Long, Rebecca G

2008-10-01

Logistic regression has increasingly become the tool of choice when analyzing data with a binary dependent variable. While resources relating to the technique are widely available, clear discussions of why logistic regression should be used in place of ordinary least squares regression are difficult to find. The current paper compares and contrasts the assumptions of ordinary least squares with those of logistic regression and explains why logistic regression's looser assumptions make it adept at handling violations of the more important assumptions in ordinary least squares.

Using Dominance Analysis to Determine Predictor Importance in Logistic Regression

ERIC Educational Resources Information Center

Azen, Razia; Traxel, Nicole

2009-01-01

This article proposes an extension of dominance analysis that allows researchers to determine the relative importance of predictors in logistic regression models. Criteria for choosing logistic regression R[superscript 2] analogues were determined and measures were selected that can be used to perform dominance analysis in logistic regression. A…

Evaluating the perennial stream using logistic regression in central Taiwan

NASA Astrophysics Data System (ADS)

Ruljigaljig, T.; Cheng, Y. S.; Lin, H. I.; Lee, C. H.; Yu, T. T.

2014-12-01

This study produces a perennial stream head potential map, based on a logistic regression method with a Geographic Information System (GIS). Perennial stream initiation locations, indicates the location of the groundwater and surface contact, were identified in the study area from field survey. The perennial stream potential map in central Taiwan was constructed using the relationship between perennial stream and their causative factors, such as Catchment area, slope gradient, aspect, elevation, groundwater recharge and precipitation. Here, the field surveys of 272 streams were determined in the study area. The areas under the curve for logistic regression methods were calculated as 0.87. The results illustrate the importance of catchment area and groundwater recharge as key factors within the model. The results obtained from the model within the GIS were then used to produce a map of perennial stream and estimate the location of perennial stream head.

Utility of an Abbreviated Dizziness Questionnaire to Differentiate between Causes of Vertigo and Guide Appropriate Referral: A Multicenter Prospective Blinded Study

PubMed Central

Roland, Lauren T.; Kallogjeri, Dorina; Sinks, Belinda C.; Rauch, Steven D.; Shepard, Neil T.; White, Judith A.; Goebel, Joel A.

2015-01-01

Objective Test performance of a focused dizziness questionnaire’s ability to discriminate between peripheral and non-peripheral causes of vertigo. Study Design Prospective multi-center Setting Four academic centers with experienced balance specialists Patients New dizzy patients Interventions A 32-question survey was given to participants. Balance specialists were blinded and a diagnosis was established for all participating patients within 6 months. Main outcomes Multinomial logistic regression was used to evaluate questionnaire performance in predicting final diagnosis and differentiating between peripheral and non-peripheral vertigo. Univariate and multivariable stepwise logistic regression were used to identify questions as significant predictors of the ultimate diagnosis. C-index was used to evaluate performance and discriminative power of the multivariable models. Results 437 patients participated in the study. Eight participants without confirmed diagnoses were excluded and 429 were included in the analysis. Multinomial regression revealed that the model had good overall predictive accuracy of 78.5% for the final diagnosis and 75.5% for differentiating between peripheral and non-peripheral vertigo. Univariate logistic regression identified significant predictors of three main categories of vertigo: peripheral, central and other. Predictors were entered into forward stepwise multivariable logistic regression. The discriminative power of the final models for peripheral, central and other causes were considered good as measured by c-indices of 0.75, 0.7 and 0.78, respectively. Conclusions This multicenter study demonstrates a focused dizziness questionnaire can accurately predict diagnosis for patients with chronic/relapsing dizziness referred to outpatient clinics. Additionally, this survey has significant capability to differentiate peripheral from non-peripheral causes of vertigo and may, in the future, serve as a screening tool for specialty referral. Clinical utility of this questionnaire to guide specialty referral is discussed. PMID:26485598

Utility of an Abbreviated Dizziness Questionnaire to Differentiate Between Causes of Vertigo and Guide Appropriate Referral: A Multicenter Prospective Blinded Study.

PubMed

Roland, Lauren T; Kallogjeri, Dorina; Sinks, Belinda C; Rauch, Steven D; Shepard, Neil T; White, Judith A; Goebel, Joel A

2015-12-01

Test performance of a focused dizziness questionnaire's ability to discriminate between peripheral and nonperipheral causes of vertigo. Prospective multicenter. Four academic centers with experienced balance specialists. New dizzy patients. A 32-question survey was given to participants. Balance specialists were blinded and a diagnosis was established for all participating patients within 6 months. Multinomial logistic regression was used to evaluate questionnaire performance in predicting final diagnosis and differentiating between peripheral and nonperipheral vertigo. Univariate and multivariable stepwise logistic regression were used to identify questions as significant predictors of the ultimate diagnosis. C-index was used to evaluate performance and discriminative power of the multivariable models. In total, 437 patients participated in the study. Eight participants without confirmed diagnoses were excluded and 429 were included in the analysis. Multinomial regression revealed that the model had good overall predictive accuracy of 78.5% for the final diagnosis and 75.5% for differentiating between peripheral and nonperipheral vertigo. Univariate logistic regression identified significant predictors of three main categories of vertigo: peripheral, central, and other. Predictors were entered into forward stepwise multivariable logistic regression. The discriminative power of the final models for peripheral, central, and other causes was considered good as measured by c-indices of 0.75, 0.7, and 0.78, respectively. This multicenter study demonstrates a focused dizziness questionnaire can accurately predict diagnosis for patients with chronic/relapsing dizziness referred to outpatient clinics. Additionally, this survey has significant capability to differentiate peripheral from nonperipheral causes of vertigo and may, in the future, serve as a screening tool for specialty referral. Clinical utility of this questionnaire to guide specialty referral is discussed.

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.

Applying Kaplan-Meier to Item Response Data

ERIC Educational Resources Information Center

McNeish, Daniel

2018-01-01

Some IRT models can be equivalently modeled in alternative frameworks such as logistic regression. Logistic regression can also model time-to-event data, which concerns the probability of an event occurring over time. Using the relation between time-to-event models and logistic regression and the relation between logistic regression and IRT, this…

Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat—Turkey)

NASA Astrophysics Data System (ADS)

Yilmaz, Işık

2009-06-01

The purpose of this study is to compare the landslide susceptibility mapping methods of frequency ratio (FR), logistic regression and artificial neural networks (ANN) applied in the Kat County (Tokat—Turkey). Digital elevation model (DEM) was first constructed using GIS software. Landslide-related factors such as geology, faults, drainage system, topographical elevation, slope angle, slope aspect, topographic wetness index (TWI) and stream power index (SPI) were used in the landslide susceptibility analyses. Landslide susceptibility maps were produced from the frequency ratio, logistic regression and neural networks models, and they were then compared by means of their validations. The higher accuracies of the susceptibility maps for all three models were obtained from the comparison of the landslide susceptibility maps with the known landslide locations. However, respective area under curve (AUC) values of 0.826, 0.842 and 0.852 for frequency ratio, logistic regression and artificial neural networks showed that the map obtained from ANN model is more accurate than the other models, accuracies of all models can be evaluated relatively similar. The results obtained in this study also showed that the frequency ratio model can be used as a simple tool in assessment of landslide susceptibility when a sufficient number of data were obtained. Input process, calculations and output process are very simple and can be readily understood in the frequency ratio model, however logistic regression and neural networks require the conversion of data to ASCII or other formats. Moreover, it is also very hard to process the large amount of data in the statistical package.

Visual grading characteristics and ordinal regression analysis during optimisation of CT head examinations.

PubMed

Zarb, Francis; McEntee, Mark F; Rainford, Louise

2015-06-01

To evaluate visual grading characteristics (VGC) and ordinal regression analysis during head CT optimisation as a potential alternative to visual grading assessment (VGA), traditionally employed to score anatomical visualisation. Patient images (n = 66) were obtained using current and optimised imaging protocols from two CT suites: a 16-slice scanner at the national Maltese centre for trauma and a 64-slice scanner in a private centre. Local resident radiologists (n = 6) performed VGA followed by VGC and ordinal regression analysis. VGC alone indicated that optimised protocols had similar image quality as current protocols. Ordinal logistic regression analysis provided an in-depth evaluation, criterion by criterion allowing the selective implementation of the protocols. The local radiology review panel supported the implementation of optimised protocols for brain CT examinations (including trauma) in one centre, achieving radiation dose reductions ranging from 24 % to 36 %. In the second centre a 29 % reduction in radiation dose was achieved for follow-up cases. The combined use of VGC and ordinal logistic regression analysis led to clinical decisions being taken on the implementation of the optimised protocols. This improved method of image quality analysis provided the evidence to support imaging protocol optimisation, resulting in significant radiation dose savings. • There is need for scientifically based image quality evaluation during CT optimisation. • VGC and ordinal regression analysis in combination led to better informed clinical decisions. • VGC and ordinal regression analysis led to dose reductions without compromising diagnostic efficacy.

Standards for Standardized Logistic Regression Coefficients

ERIC Educational Resources Information Center

Menard, Scott

2011-01-01

Standardized coefficients in logistic regression analysis have the same utility as standardized coefficients in linear regression analysis. Although there has been no consensus on the best way to construct standardized logistic regression coefficients, there is now sufficient evidence to suggest a single best approach to the construction of a…

Robust mislabel logistic regression without modeling mislabel probabilities.

PubMed

Hung, Hung; Jou, Zhi-Yu; Huang, Su-Yun

2018-03-01

Logistic regression is among the most widely used statistical methods for linear discriminant analysis. In many applications, we only observe possibly mislabeled responses. Fitting a conventional logistic regression can then lead to biased estimation. One common resolution is to fit a mislabel logistic regression model, which takes into consideration of mislabeled responses. Another common method is to adopt a robust M-estimation by down-weighting suspected instances. In this work, we propose a new robust mislabel logistic regression based on γ-divergence. Our proposal possesses two advantageous features: (1) It does not need to model the mislabel probabilities. (2) The minimum γ-divergence estimation leads to a weighted estimating equation without the need to include any bias correction term, that is, it is automatically bias-corrected. These features make the proposed γ-logistic regression more robust in model fitting and more intuitive for model interpretation through a simple weighting scheme. Our method is also easy to implement, and two types of algorithms are included. Simulation studies and the Pima data application are presented to demonstrate the performance of γ-logistic regression. © 2017, The International Biometric Society.

Detection of high GS risk group prostate tumors by diffusion tensor imaging and logistic regression modelling.

PubMed

Ertas, Gokhan

2018-07-01

To assess the value of joint evaluation of diffusion tensor imaging (DTI) measures by using logistic regression modelling to detect high GS risk group prostate tumors. Fifty tumors imaged using DTI on a 3 T MRI device were analyzed. Regions of interests focusing on the center of tumor foci and noncancerous tissue on the maps of mean diffusivity (MD) and fractional anisotropy (FA) were used to extract the minimum, the maximum and the mean measures. Measure ratio was computed by dividing tumor measure by noncancerous tissue measure. Logistic regression models were fitted for all possible pair combinations of the measures using 5-fold cross validation. Systematic differences are present for all MD measures and also for all FA measures in distinguishing the high risk tumors [GS ≥ 7(4 + 3)] from the low risk tumors [GS ≤ 7(3 + 4)] (P < 0.05). Smaller value for MD measures and larger value for FA measures indicate the high risk. The models enrolling the measures achieve good fits and good classification performances (R 2 adj  = 0.55-0.60, AUC = 0.88-0.91), however the models using the measure ratios perform better (R 2 adj  = 0.59-0.75, AUC = 0.88-0.95). The model that employs the ratios of minimum MD and maximum FA accomplishes the highest sensitivity, specificity and accuracy (Se = 77.8%, Sp = 96.9% and Acc = 90.0%). Joint evaluation of MD and FA diffusion tensor imaging measures is valuable to detect high GS risk group peripheral zone prostate tumors. However, use of the ratios of the measures improves the accuracy of the detections substantially. Logistic regression modelling provides a favorable solution for the joint evaluations easily adoptable in clinical practice. Copyright © 2018 Elsevier Inc. All rights reserved.

Should metacognition be measured by logistic regression?

PubMed

Rausch, Manuel; Zehetleitner, Michael

2017-03-01

Are logistic regression slopes suitable to quantify metacognitive sensitivity, i.e. the efficiency with which subjective reports differentiate between correct and incorrect task responses? We analytically show that logistic regression slopes are independent from rating criteria in one specific model of metacognition, which assumes (i) that rating decisions are based on sensory evidence generated independently of the sensory evidence used for primary task responses and (ii) that the distributions of evidence are logistic. Given a hierarchical model of metacognition, logistic regression slopes depend on rating criteria. According to all considered models, regression slopes depend on the primary task criterion. A reanalysis of previous data revealed that massive numbers of trials are required to distinguish between hierarchical and independent models with tolerable accuracy. It is argued that researchers who wish to use logistic regression as measure of metacognitive sensitivity need to control the primary task criterion and rating criteria. Copyright © 2017 Elsevier Inc. All rights reserved.

Impact of Colic Pain as a Significant Factor for Predicting the Stone Free Rate of One-Session Shock Wave Lithotripsy for Treating Ureter Stones: A Bayesian Logistic Regression Model Analysis

PubMed Central

Chung, Doo Yong; Cho, Kang Su; Lee, Dae Hun; Han, Jang Hee; Kang, Dong Hyuk; Jung, Hae Do; Kown, Jong Kyou; Ham, Won Sik; Choi, Young Deuk; Lee, Joo Yong

2015-01-01

Purpose This study was conducted to evaluate colic pain as a prognostic pretreatment factor that can influence ureter stone clearance and to estimate the probability of stone-free status in shock wave lithotripsy (SWL) patients with a ureter stone. Materials and Methods We retrospectively reviewed the medical records of 1,418 patients who underwent their first SWL between 2005 and 2013. Among these patients, 551 had a ureter stone measuring 4–20 mm and were thus eligible for our analyses. The colic pain as the chief complaint was defined as either subjective flank pain during history taking and physical examination. Propensity-scores for established for colic pain was calculated for each patient using multivariate logistic regression based upon the following covariates: age, maximal stone length (MSL), and mean stone density (MSD). Each factor was evaluated as predictor for stone-free status by Bayesian and non-Bayesian logistic regression model. Results After propensity-score matching, 217 patients were extracted in each group from the total patient cohort. There were no statistical differences in variables used in propensity- score matching. One-session success and stone-free rate were also higher in the painful group (73.7% and 71.0%, respectively) than in the painless group (63.6% and 60.4%, respectively). In multivariate non-Bayesian and Bayesian logistic regression models, a painful stone, shorter MSL, and lower MSD were significant factors for one-session stone-free status in patients who underwent SWL. Conclusions Colic pain in patients with ureter calculi was one of the significant predicting factors including MSL and MSD for one-session stone-free status of SWL. PMID:25902059

Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation

PubMed Central

Song, Yongsoo; Wang, Shuang; Xia, Yuhou; Jiang, Xiaoqian

2018-01-01

Background Learning a model without accessing raw data has been an intriguing idea to security and machine learning researchers for years. In an ideal setting, we want to encrypt sensitive data to store them on a commercial cloud and run certain analyses without ever decrypting the data to preserve privacy. Homomorphic encryption technique is a promising candidate for secure data outsourcing, but it is a very challenging task to support real-world machine learning tasks. Existing frameworks can only handle simplified cases with low-degree polynomials such as linear means classifier and linear discriminative analysis. Objective The goal of this study is to provide a practical support to the mainstream learning models (eg, logistic regression). Methods We adapted a novel homomorphic encryption scheme optimized for real numbers computation. We devised (1) the least squares approximation of the logistic function for accuracy and efficiency (ie, reduce computation cost) and (2) new packing and parallelization techniques. Results Using real-world datasets, we evaluated the performance of our model and demonstrated its feasibility in speed and memory consumption. For example, it took approximately 116 minutes to obtain the training model from the homomorphically encrypted Edinburgh dataset. In addition, it gives fairly accurate predictions on the testing dataset. Conclusions We present the first homomorphically encrypted logistic regression outsourcing model based on the critical observation that the precision loss of classification models is sufficiently small so that the decision plan stays still. PMID:29666041

Logistic models--an odd(s) kind of regression.

PubMed

Jupiter, Daniel C

2013-01-01

The logistic regression model bears some similarity to the multivariable linear regression with which we are familiar. However, the differences are great enough to warrant a discussion of the need for and interpretation of logistic regression. Copyright © 2013 American College of Foot and Ankle Surgeons. Published by Elsevier Inc. All rights reserved.

Modeling brook trout presence and absence from landscape variables using four different analytical methods

USGS Publications Warehouse

Steen, Paul J.; Passino-Reader, Dora R.; Wiley, Michael J.

2006-01-01

As a part of the Great Lakes Regional Aquatic Gap Analysis Project, we evaluated methodologies for modeling associations between fish species and habitat characteristics at a landscape scale. To do this, we created brook trout Salvelinus fontinalis presence and absence models based on four different techniques: multiple linear regression, logistic regression, neural networks, and classification trees. The models were tested in two ways: by application to an independent validation database and cross-validation using the training data, and by visual comparison of statewide distribution maps with historically recorded occurrences from the Michigan Fish Atlas. Although differences in the accuracy of our models were slight, the logistic regression model predicted with the least error, followed by multiple regression, then classification trees, then the neural networks. These models will provide natural resource managers a way to identify habitats requiring protection for the conservation of fish species.

Radiomorphometric analysis of frontal sinus for sex determination.

PubMed

Verma, Saumya; Mahima, V G; Patil, Karthikeya

2014-09-01

Sex determination of unknown individuals carries crucial significance in forensic research, in cases where fragments of skull persist with no likelihood of identification based on dental arch. In these instances sex determination becomes important to rule out certain number of possibilities instantly and helps in establishing a biological profile of human remains. The aim of the study is to evaluate a mathematical method based on logistic regression analysis capable of ascertaining the sex of individuals in the South Indian population. The study was conducted in the department of Oral Medicine and Radiology. The right and left areas, maximum height, width of frontal sinus were determined in 100 Caldwell views of 50 women and 50 men aged 20 years and above, with the help of Vernier callipers and a square grid with 1 square measuring 1mm(2) in area. Student's t-test, logistic regression analysis. The mean values of variables were greater in men, based on Student's t-test at 5% level of significance. The mathematical model based on logistic regression analysis gave percentage agreement of total area to correctly predict the female gender as 55.2%, of right area as 60.9% and of left area as 55.2%. The areas of the frontal sinus and the logistic regression proved to be unreliable in sex determination. (Logit = 0.924 - 0.00217 × right area).

Parameters Estimation of Geographically Weighted Ordinal Logistic Regression (GWOLR) Model

NASA Astrophysics Data System (ADS)

Zuhdi, Shaifudin; Retno Sari Saputro, Dewi; Widyaningsih, Purnami

2017-06-01

A regression model is the representation of relationship between independent variable and dependent variable. The dependent variable has categories used in the logistic regression model to calculate odds on. The logistic regression model for dependent variable has levels in the logistics regression model is ordinal. GWOLR model is an ordinal logistic regression model influenced the geographical location of the observation site. Parameters estimation in the model needed to determine the value of a population based on sample. The purpose of this research is to parameters estimation of GWOLR model using R software. Parameter estimation uses the data amount of dengue fever patients in Semarang City. Observation units used are 144 villages in Semarang City. The results of research get GWOLR model locally for each village and to know probability of number dengue fever patient categories.

PARAMETRIC AND NON PARAMETRIC (MARS: MULTIVARIATE ADDITIVE REGRESSION SPLINES) LOGISTIC REGRESSIONS FOR PREDICTION OF A DICHOTOMOUS RESPONSE VARIABLE WITH AN EXAMPLE FOR PRESENCE/ABSENCE OF AMPHIBIANS

EPA Science Inventory

The purpose of this report is to provide a reference manual that could be used by investigators for making informed use of logistic regression using two methods (standard logistic regression and MARS). The details for analyses of relationships between a dependent binary response ...

Predicting U.S. Army Reserve Unit Manning Using Market Demographics

DTIC Science & Technology

2015-06-01

develops linear regression , classification tree, and logistic regression models to determine the ability of the location to support manning requirements... logistic regression model delivers predictive results that allow decision-makers to identify locations with a high probability of meeting unit...manning requirements. The recommendation of this thesis is that the USAR implement the logistic regression model. 14. SUBJECT TERMS U.S

Analyzing Student Learning Outcomes: Usefulness of Logistic and Cox Regression Models. IR Applications, Volume 5

ERIC Educational Resources Information Center

Chen, Chau-Kuang

2005-01-01

Logistic and Cox regression methods are practical tools used to model the relationships between certain student learning outcomes and their relevant explanatory variables. The logistic regression model fits an S-shaped curve into a binary outcome with data points of zero and one. The Cox regression model allows investigators to study the duration…

Artificial Neural Network for the Prediction of Chromosomal Abnormalities in Azoospermic Males.

PubMed

Akinsal, Emre Can; Haznedar, Bulent; Baydilli, Numan; Kalinli, Adem; Ozturk, Ahmet; Ekmekçioğlu, Oğuz

2018-02-04

To evaluate whether an artifical neural network helps to diagnose any chromosomal abnormalities in azoospermic males. The data of azoospermic males attending to a tertiary academic referral center were evaluated retrospectively. Height, total testicular volume, follicle stimulating hormone, luteinising hormone, total testosterone and ejaculate volume of the patients were used for the analyses. In artificial neural network, the data of 310 azoospermics were used as the education and 115 as the test set. Logistic regression analyses and discriminant analyses were performed for statistical analyses. The tests were re-analysed with a neural network. Both logistic regression analyses and artificial neural network predicted the presence or absence of chromosomal abnormalities with more than 95% accuracy. The use of artificial neural network model has yielded satisfactory results in terms of distinguishing patients whether they have any chromosomal abnormality or not.

Logistic Regression: Concept and Application

ERIC Educational Resources Information Center

Cokluk, Omay

2010-01-01

The main focus of logistic regression analysis is classification of individuals in different groups. The aim of the present study is to explain basic concepts and processes of binary logistic regression analysis intended to determine the combination of independent variables which best explain the membership in certain groups called dichotomous…

Remote sensing and GIS-based landslide hazard analysis and cross-validation using multivariate logistic regression model on three test areas in Malaysia

NASA Astrophysics Data System (ADS)

Pradhan, Biswajeet

2010-05-01

This paper presents the results of the cross-validation of a multivariate logistic regression model using remote sensing data and GIS for landslide hazard analysis on the Penang, Cameron, and Selangor areas in Malaysia. Landslide locations in the study areas were identified by interpreting aerial photographs and satellite images, supported by field surveys. SPOT 5 and Landsat TM satellite imagery were used to map landcover and vegetation index, respectively. Maps of topography, soil type, lineaments and land cover were constructed from the spatial datasets. Ten factors which influence landslide occurrence, i.e., slope, aspect, curvature, distance from drainage, lithology, distance from lineaments, soil type, landcover, rainfall precipitation, and normalized difference vegetation index (ndvi), were extracted from the spatial database and the logistic regression coefficient of each factor was computed. Then the landslide hazard was analysed using the multivariate logistic regression coefficients derived not only from the data for the respective area but also using the logistic regression coefficients calculated from each of the other two areas (nine hazard maps in all) as a cross-validation of the model. For verification of the model, the results of the analyses were then compared with the field-verified landslide locations. Among the three cases of the application of logistic regression coefficient in the same study area, the case of Selangor based on the Selangor logistic regression coefficients showed the highest accuracy (94%), where as Penang based on the Penang coefficients showed the lowest accuracy (86%). Similarly, among the six cases from the cross application of logistic regression coefficient in other two areas, the case of Selangor based on logistic coefficient of Cameron showed highest (90%) prediction accuracy where as the case of Penang based on the Selangor logistic regression coefficients showed the lowest accuracy (79%). Qualitatively, the cross application model yields reasonable results which can be used for preliminary landslide hazard mapping.

An Entropy-Based Measure for Assessing Fuzziness in Logistic Regression

PubMed Central

Weiss, Brandi A.; Dardick, William

2015-01-01

This article introduces an entropy-based measure of data–model fit that can be used to assess the quality of logistic regression models. Entropy has previously been used in mixture-modeling to quantify how well individuals are classified into latent classes. The current study proposes the use of entropy for logistic regression models to quantify the quality of classification and separation of group membership. Entropy complements preexisting measures of data–model fit and provides unique information not contained in other measures. Hypothetical data scenarios, an applied example, and Monte Carlo simulation results are used to demonstrate the application of entropy in logistic regression. Entropy should be used in conjunction with other measures of data–model fit to assess how well logistic regression models classify cases into observed categories. PMID:29795897

Logistic regression applied to natural hazards: rare event logistic regression with replications

NASA Astrophysics Data System (ADS)

Guns, M.; Vanacker, V.

2012-06-01

Statistical analysis of natural hazards needs particular attention, as most of these phenomena are rare events. This study shows that the ordinary rare event logistic regression, as it is now commonly used in geomorphologic studies, does not always lead to a robust detection of controlling factors, as the results can be strongly sample-dependent. In this paper, we introduce some concepts of Monte Carlo simulations in rare event logistic regression. This technique, so-called rare event logistic regression with replications, combines the strength of probabilistic and statistical methods, and allows overcoming some of the limitations of previous developments through robust variable selection. This technique was here developed for the analyses of landslide controlling factors, but the concept is widely applicable for statistical analyses of natural hazards.

An Entropy-Based Measure for Assessing Fuzziness in Logistic Regression.

PubMed

Weiss, Brandi A; Dardick, William

2016-12-01

This article introduces an entropy-based measure of data-model fit that can be used to assess the quality of logistic regression models. Entropy has previously been used in mixture-modeling to quantify how well individuals are classified into latent classes. The current study proposes the use of entropy for logistic regression models to quantify the quality of classification and separation of group membership. Entropy complements preexisting measures of data-model fit and provides unique information not contained in other measures. Hypothetical data scenarios, an applied example, and Monte Carlo simulation results are used to demonstrate the application of entropy in logistic regression. Entropy should be used in conjunction with other measures of data-model fit to assess how well logistic regression models classify cases into observed categories.

Semiparametric time varying coefficient model for matched case-crossover studies.

PubMed

Ortega-Villa, Ana Maria; Kim, Inyoung; Kim, H

2017-03-15

In matched case-crossover studies, it is generally accepted that the covariates on which a case and associated controls are matched cannot exert a confounding effect on independent predictors included in the conditional logistic regression model. This is because any stratum effect is removed by the conditioning on the fixed number of sets of the case and controls in the stratum. Hence, the conditional logistic regression model is not able to detect any effects associated with the matching covariates by stratum. However, some matching covariates such as time often play an important role as an effect modification leading to incorrect statistical estimation and prediction. Therefore, we propose three approaches to evaluate effect modification by time. The first is a parametric approach, the second is a semiparametric penalized approach, and the third is a semiparametric Bayesian approach. Our parametric approach is a two-stage method, which uses conditional logistic regression in the first stage and then estimates polynomial regression in the second stage. Our semiparametric penalized and Bayesian approaches are one-stage approaches developed by using regression splines. Our semiparametric one stage approach allows us to not only detect the parametric relationship between the predictor and binary outcomes, but also evaluate nonparametric relationships between the predictor and time. We demonstrate the advantage of our semiparametric one-stage approaches using both a simulation study and an epidemiological example of a 1-4 bi-directional case-crossover study of childhood aseptic meningitis with drinking water turbidity. We also provide statistical inference for the semiparametric Bayesian approach using Bayes Factors. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation.

PubMed

Kim, Miran; Song, Yongsoo; Wang, Shuang; Xia, Yuhou; Jiang, Xiaoqian

2018-04-17

Learning a model without accessing raw data has been an intriguing idea to security and machine learning researchers for years. In an ideal setting, we want to encrypt sensitive data to store them on a commercial cloud and run certain analyses without ever decrypting the data to preserve privacy. Homomorphic encryption technique is a promising candidate for secure data outsourcing, but it is a very challenging task to support real-world machine learning tasks. Existing frameworks can only handle simplified cases with low-degree polynomials such as linear means classifier and linear discriminative analysis. The goal of this study is to provide a practical support to the mainstream learning models (eg, logistic regression). We adapted a novel homomorphic encryption scheme optimized for real numbers computation. We devised (1) the least squares approximation of the logistic function for accuracy and efficiency (ie, reduce computation cost) and (2) new packing and parallelization techniques. Using real-world datasets, we evaluated the performance of our model and demonstrated its feasibility in speed and memory consumption. For example, it took approximately 116 minutes to obtain the training model from the homomorphically encrypted Edinburgh dataset. In addition, it gives fairly accurate predictions on the testing dataset. We present the first homomorphically encrypted logistic regression outsourcing model based on the critical observation that the precision loss of classification models is sufficiently small so that the decision plan stays still. ©Miran Kim, Yongsoo Song, Shuang Wang, Yuhou Xia, Xiaoqian Jiang. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 17.04.2018.

FIRES: Fire Information Retrieval and Evaluation System - A program for fire danger rating analysis

Treesearch

Patricia L. Andrews; Larry S. Bradshaw

1997-01-01

A computer program, FIRES: Fire Information Retrieval and Evaluation System, provides methods for evaluating the performance of fire danger rating indexes. The relationship between fire danger indexes and historical fire occurrence and size is examined through logistic regression and percentiles. Historical seasonal trends of fire danger and fire occurrence can be...

Integration of logistic regression, Markov chain and cellular automata models to simulate urban expansion

NASA Astrophysics Data System (ADS)

Jokar Arsanjani, Jamal; Helbich, Marco; Kainz, Wolfgang; Darvishi Boloorani, Ali

2013-04-01

This research analyses the suburban expansion in the metropolitan area of Tehran, Iran. A hybrid model consisting of logistic regression model, Markov chain (MC), and cellular automata (CA) was designed to improve the performance of the standard logistic regression model. Environmental and socio-economic variables dealing with urban sprawl were operationalised to create a probability surface of spatiotemporal states of built-up land use for the years 2006, 2016, and 2026. For validation, the model was evaluated by means of relative operating characteristic values for different sets of variables. The approach was calibrated for 2006 by cross comparing of actual and simulated land use maps. The achieved outcomes represent a match of 89% between simulated and actual maps of 2006, which was satisfactory to approve the calibration process. Thereafter, the calibrated hybrid approach was implemented for forthcoming years. Finally, future land use maps for 2016 and 2026 were predicted by means of this hybrid approach. The simulated maps illustrate a new wave of suburban development in the vicinity of Tehran at the western border of the metropolis during the next decades.

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

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

[Analysis of rational clinical uses of traditional Chinese medicine injections and factors influencing adverse drug reactions].

PubMed

Sun, Shi-Guang; Li, Zi-Feng; Xie, Yan-Ming; Liu, Jian; Lu, Yan; Song, Yi-Fei; Han, Ying-Hua; Liu, Li-Da; Peng, Ting-Ting

2013-09-01

To rationalize the clinical use and safety are some of the key issues in the surveillance of traditional Chinese medicine injections (TCMIs). In this 2011 study, 240 medical records of patients who had been discharged following treatment with TCMIs between 1 and 12 month previously were randomly selected from hospital records. Consistency between clinical use and the description of TCMIs was evaluated. Research on drug use and adverse drug reactions/events using logistic regression analysis was carried out. There was poor consistency between clinical use and best practice advised in manuals on TCMIs. Over-dosage and overly concentrated administration of TCMIs occurred, with the outcome of modifying properties of the blood. Logistic regression analysis showed that, drug concentration was a valid predictor for both adverse drug reactions/events and benefits associated with TCMIs. Surveillance of rational clinical use and safety of TCMIs finds that clinical use should be consistent with technical drug manual specifications, and drug use should draw on multi-layered logistic regression analysis research to help avoid adverse drug reactions/events.

Testing Gene-Gene Interactions in the Case-Parents Design

PubMed Central

Yu, Zhaoxia

2011-01-01

The case-parents design has been widely used to detect genetic associations as it can prevent spurious association that could occur in population-based designs. When examining the effect of an individual genetic locus on a disease, logistic regressions developed by conditioning on parental genotypes provide complete protection from spurious association caused by population stratification. However, when testing gene-gene interactions, it is unknown whether conditional logistic regressions are still robust. Here we evaluate the robustness and efficiency of several gene-gene interaction tests that are derived from conditional logistic regressions. We found that in the presence of SNP genotype correlation due to population stratification or linkage disequilibrium, tests with incorrectly specified main-genetic-effect models can lead to inflated type I error rates. We also found that a test with fully flexible main genetic effects always maintains correct test size and its robustness can be achieved with negligible sacrifice of its power. When testing gene-gene interactions is the focus, the test allowing fully flexible main effects is recommended to be used. PMID:21778736

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

Blastocoele expansion degree predicts live birth after single blastocyst transfer for fresh and vitrified/warmed single blastocyst transfer cycles.

PubMed

Du, Qing-Yun; Wang, En-Yin; Huang, Yan; Guo, Xiao-Yi; Xiong, Yu-Jing; Yu, Yi-Ping; Yao, Gui-Dong; Shi, Sen-Lin; Sun, Ying-Pu

2016-04-01

To evaluate the independent effects of the degree of blastocoele expansion and re-expansion and the inner cell mass (ICM) and trophectoderm (TE) grades on predicting live birth after fresh and vitrified/warmed single blastocyst transfer. Retrospective study. Reproductive medical center. Women undergoing 844 fresh and 370 vitrified/warmed single blastocyst transfer cycles. None. Live-birth rate correlated with blastocyst morphology parameters by logistic regression analysis and Spearman correlations analysis. The degree of blastocoele expansion and re-expansion was the only blastocyst morphology parameter that exhibited a significant ability to predict live birth in both fresh and vitrified/warmed single blastocyst transfer cycles respectively by multivariate logistic regression and Spearman correlations analysis. Although the ICM grade was significantly related to live birth in fresh cycles according to the univariate model, its effect was not maintained in the multivariate logistic analysis. In vitrified/warmed cycles, neither ICM nor TE grade was correlated with live birth by logistic regression analysis. This study is the first to confirm that the degree of blastocoele expansion and re-expansion is a better predictor of live birth after both fresh and vitrified/warmed single blastocyst transfer cycles than ICM or TE grade. Copyright © 2016. Published by Elsevier Inc.

Power and Sample Size Calculations for Logistic Regression Tests for Differential Item Functioning

ERIC Educational Resources Information Center

Li, Zhushan

2014-01-01

Logistic regression is a popular method for detecting uniform and nonuniform differential item functioning (DIF) effects. Theoretical formulas for the power and sample size calculations are derived for likelihood ratio tests and Wald tests based on the asymptotic distribution of the maximum likelihood estimators for the logistic regression model.…

Comparison of standard maximum likelihood classification and polytomous logistic regression used in remote sensing

Treesearch

John Hogland; Nedret Billor; Nathaniel Anderson

2013-01-01

Discriminant analysis, referred to as maximum likelihood classification within popular remote sensing software packages, is a common supervised technique used by analysts. Polytomous logistic regression (PLR), also referred to as multinomial logistic regression, is an alternative classification approach that is less restrictive, more flexible, and easy to interpret. To...

Susceptibility assessment of earthquake-triggered landslides in El Salvador using logistic regression

NASA Astrophysics Data System (ADS)

García-Rodríguez, M. J.; Malpica, J. A.; Benito, B.; Díaz, M.

2008-03-01

This work has evaluated the probability of earthquake-triggered landslide occurrence in the whole of El Salvador, with a Geographic Information System (GIS) and a logistic regression model. Slope gradient, elevation, aspect, mean annual precipitation, lithology, land use, and terrain roughness are the predictor variables used to determine the dependent variable of occurrence or non-occurrence of landslides within an individual grid cell. The results illustrate the importance of terrain roughness and soil type as key factors within the model — using only these two variables the analysis returned a significance level of 89.4%. The results obtained from the model within the GIS were then used to produce a map of relative landslide susceptibility.

Multiple Imputation of a Randomly Censored Covariate Improves Logistic Regression Analysis.

PubMed

Atem, Folefac D; Qian, Jing; Maye, Jacqueline E; Johnson, Keith A; Betensky, Rebecca A

2016-01-01

Randomly censored covariates arise frequently in epidemiologic studies. The most commonly used methods, including complete case and single imputation or substitution, suffer from inefficiency and bias. They make strong parametric assumptions or they consider limit of detection censoring only. We employ multiple imputation, in conjunction with semi-parametric modeling of the censored covariate, to overcome these shortcomings and to facilitate robust estimation. We develop a multiple imputation approach for randomly censored covariates within the framework of a logistic regression model. We use the non-parametric estimate of the covariate distribution or the semiparametric Cox model estimate in the presence of additional covariates in the model. We evaluate this procedure in simulations, and compare its operating characteristics to those from the complete case analysis and a survival regression approach. We apply the procedures to an Alzheimer's study of the association between amyloid positivity and maternal age of onset of dementia. Multiple imputation achieves lower standard errors and higher power than the complete case approach under heavy and moderate censoring and is comparable under light censoring. The survival regression approach achieves the highest power among all procedures, but does not produce interpretable estimates of association. Multiple imputation offers a favorable alternative to complete case analysis and ad hoc substitution methods in the presence of randomly censored covariates within the framework of logistic regression.

Can shoulder dystocia be reliably predicted?

PubMed

Dodd, Jodie M; Catcheside, Britt; Scheil, Wendy

2012-06-01

To evaluate factors reported to increase the risk of shoulder dystocia, and to evaluate their predictive value at a population level. The South Australian Pregnancy Outcome Unit's population database from 2005 to 2010 was accessed to determine the occurrence of shoulder dystocia in addition to reported risk factors, including age, parity, self-reported ethnicity, presence of diabetes and infant birth weight. Odds ratios (and 95% confidence interval) of shoulder dystocia was calculated for each risk factor, which were then incorporated into a logistic regression model. Test characteristics for each variable in predicting shoulder dystocia were calculated. As a proportion of all births, the reported rate of shoulder dystocia increased significantly from 0.95% in 2005 to 1.38% in 2010 (P = 0.0002). Using a logistic regression model, induction of labour and infant birth weight greater than both 4000 and 4500 g were identified as significant independent predictors of shoulder dystocia. The value of risk factors alone and when incorporated into the logistic regression model was poorly predictive of the occurrence of shoulder dystocia. While there are a number of factors associated with an increased risk of shoulder dystocia, none are of sufficient sensitivity or positive predictive value to allow their use clinically to reliably and accurately identify the occurrence of shoulder dystocia. © 2012 The Authors ANZJOG © 2012 The Royal Australian and New Zealand College of Obstetricians and Gynaecologists.

Forecasting the probability of future groundwater levels declining below specified low thresholds in the conterminous U.S.

USGS Publications Warehouse

Dudley, Robert W.; Hodgkins, Glenn A.; Dickinson, Jesse

2017-01-01

We present a logistic regression approach for forecasting the probability of future groundwater levels declining or maintaining below specific groundwater-level thresholds. We tested our approach on 102 groundwater wells in different climatic regions and aquifers of the United States that are part of the U.S. Geological Survey Groundwater Climate Response Network. We evaluated the importance of current groundwater levels, precipitation, streamflow, seasonal variability, Palmer Drought Severity Index, and atmosphere/ocean indices for developing the logistic regression equations. Several diagnostics of model fit were used to evaluate the regression equations, including testing of autocorrelation of residuals, goodness-of-fit metrics, and bootstrap validation testing. The probabilistic predictions were most successful at wells with high persistence (low month-to-month variability) in their groundwater records and at wells where the groundwater level remained below the defined low threshold for sustained periods (generally three months or longer). The model fit was weakest at wells with strong seasonal variability in levels and with shorter duration low-threshold events. We identified challenges in deriving probabilistic-forecasting models and possible approaches for addressing those challenges.

The psychological impact of terrorism: an epidemiologic study of posttraumatic stress disorder and associated factors in victims of the 1995-1996 bombings in France.

PubMed

Verger, Pierre; Dab, William; Lamping, Donna L; Loze, Jean-Yves; Deschaseaux-Voinet, Céline; Abenhaim, Lucien; Rouillon, Frédéric

2004-08-01

A wave of bombings struck France in 1995 and 1996, killing 12 people and injuring more than 200. The authors conducted follow-up evaluations with the victims in 1998 to determine the prevalence of and factors associated with posttraumatic stress disorder (PTSD). Victims directly exposed to the bombings (N=228) were recruited into a retrospective, cross-sectional study. Computer-assisted telephone interviews were conducted to evaluate PTSD, per DSM-IV criteria, and to assess health status before the attack, initial injury severity and perceived threat at the time of attack, and psychological symptoms, cosmetic impairment, hearing problems, and health service use at the time of the follow-up evaluation. Factors associated with PTSD were investigated with univariate logistic regression followed by multiple logistic regression analyses. A total of 196 respondents (86%) participated in the study. Of these, 19% had severe initial physical injuries (hospitalization exceeding 1 week). Problems reported at the follow-up evaluation included attack-related hearing problems (51%), cosmetic impairment (33%), and PTSD (31%) (95% confidence interval=24.5%-37.5%). Results of logistic regression analyses indicated that the risk of PTSD was significantly higher among women (odds ratio=2.54), participants age 35-54 (odds ratio=2.83), and those who had severe initial injuries (odds ratio=2.79) or cosmetic impairment (odds ratio=2.74) or who perceived substantial threat during the attack (odds ratio=3.99). The high prevalence of PTSD 2.6 years on average after a terrorist attack emphasizes the need for improved health services to address the intermediate and long-term consequences of terrorism.

An Entropy-Based Measure for Assessing Fuzziness in Logistic Regression

ERIC Educational Resources Information Center

Weiss, Brandi A.; Dardick, William

2016-01-01

This article introduces an entropy-based measure of data-model fit that can be used to assess the quality of logistic regression models. Entropy has previously been used in mixture-modeling to quantify how well individuals are classified into latent classes. The current study proposes the use of entropy for logistic regression models to quantify…

What Are the Odds of that? A Primer on Understanding Logistic Regression

ERIC Educational Resources Information Center

Huang, Francis L.; Moon, Tonya R.

2013-01-01

The purpose of this Methodological Brief is to present a brief primer on logistic regression, a commonly used technique when modeling dichotomous outcomes. Using data from the National Education Longitudinal Study of 1988 (NELS:88), logistic regression techniques were used to investigate student-level variables in eighth grade (i.e., enrolled in a…

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.

Assessing risk factors for periodontitis using regression

NASA Astrophysics Data System (ADS)

Lobo Pereira, J. A.; Ferreira, Maria Cristina; Oliveira, Teresa

2013-10-01

Multivariate statistical analysis is indispensable to assess the associations and interactions between different factors and the risk of periodontitis. Among others, regression analysis is a statistical technique widely used in healthcare to investigate and model the relationship between variables. In our work we study the impact of socio-demographic, medical and behavioral factors on periodontal health. Using regression, linear and logistic models, we can assess the relevance, as risk factors for periodontitis disease, of the following independent variables (IVs): Age, Gender, Diabetic Status, Education, Smoking status and Plaque Index. The multiple linear regression analysis model was built to evaluate the influence of IVs on mean Attachment Loss (AL). Thus, the regression coefficients along with respective p-values will be obtained as well as the respective p-values from the significance tests. The classification of a case (individual) adopted in the logistic model was the extent of the destruction of periodontal tissues defined by an Attachment Loss greater than or equal to 4 mm in 25% (AL≥4mm/≥25%) of sites surveyed. The association measures include the Odds Ratios together with the correspondent 95% confidence intervals.

On the Usefulness of a Multilevel Logistic Regression Approach to Person-Fit Analysis

ERIC Educational Resources Information Center

Conijn, Judith M.; Emons, Wilco H. M.; van Assen, Marcel A. L. M.; Sijtsma, Klaas

2011-01-01

The logistic person response function (PRF) models the probability of a correct response as a function of the item locations. Reise (2000) proposed to use the slope parameter of the logistic PRF as a person-fit measure. He reformulated the logistic PRF model as a multilevel logistic regression model and estimated the PRF parameters from this…

Neural network modeling for surgical decisions on traumatic brain injury patients.

PubMed

Li, Y C; Liu, L; Chiu, W T; Jian, W S

2000-01-01

Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial-basis-function (RBF) neural network. From the 12,640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73%, 68%), compared to (80%, 80%) from the RBF model and (88%, 80%) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P < 0.05). Among these models, the logistic regression has noticeably poorer calibration. This study demonstrated the feasibility of applying neural networks as the mechanism for TBI decision support systems based on clinical databases. The results also suggest that neural networks may be a better solution for complex, non-linear medical decision support systems than conventional statistical techniques such as logistic regression.

Bias in logistic regression due to imperfect diagnostic test results and practical correction approaches.

PubMed

Valle, Denis; Lima, Joanna M Tucker; Millar, Justin; Amratia, Punam; Haque, Ubydul

2015-11-04

Logistic regression is a statistical model widely used in cross-sectional and cohort studies to identify and quantify the effects of potential disease risk factors. However, the impact of imperfect tests on adjusted odds ratios (and thus on the identification of risk factors) is under-appreciated. The purpose of this article is to draw attention to the problem associated with modelling imperfect diagnostic tests, and propose simple Bayesian models to adequately address this issue. A systematic literature review was conducted to determine the proportion of malaria studies that appropriately accounted for false-negatives/false-positives in a logistic regression setting. Inference from the standard logistic regression was also compared with that from three proposed Bayesian models using simulations and malaria data from the western Brazilian Amazon. A systematic literature review suggests that malaria epidemiologists are largely unaware of the problem of using logistic regression to model imperfect diagnostic test results. Simulation results reveal that statistical inference can be substantially improved when using the proposed Bayesian models versus the standard logistic regression. Finally, analysis of original malaria data with one of the proposed Bayesian models reveals that microscopy sensitivity is strongly influenced by how long people have lived in the study region, and an important risk factor (i.e., participation in forest extractivism) is identified that would have been missed by standard logistic regression. Given the numerous diagnostic methods employed by malaria researchers and the ubiquitous use of logistic regression to model the results of these diagnostic tests, this paper provides critical guidelines to improve data analysis practice in the presence of misclassification error. Easy-to-use code that can be readily adapted to WinBUGS is provided, enabling straightforward implementation of the proposed Bayesian models.

Comparison of Logistic Regression and Random Forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy)

NASA Astrophysics Data System (ADS)

Trigila, Alessandro; Iadanza, Carla; Esposito, Carlo; Scarascia-Mugnozza, Gabriele

2015-11-01

The aim of this work is to define reliable susceptibility models for shallow landslides using Logistic Regression and Random Forests multivariate statistical techniques. The study area, located in North-East Sicily, was hit on October 1st 2009 by a severe rainstorm (225 mm of cumulative rainfall in 7 h) which caused flash floods and more than 1000 landslides. Several small villages, such as Giampilieri, were hit with 31 fatalities, 6 missing persons and damage to buildings and transportation infrastructures. Landslides, mainly types such as earth and debris translational slides evolving into debris flows, were triggered on steep slopes and involved colluvium and regolith materials which cover the underlying metamorphic bedrock. The work has been carried out with the following steps: i) realization of a detailed event landslide inventory map through field surveys coupled with observation of high resolution aerial colour orthophoto; ii) identification of landslide source areas; iii) data preparation of landslide controlling factors and descriptive statistics based on a bivariate method (Frequency Ratio) to get an initial overview on existing relationships between causative factors and shallow landslide source areas; iv) choice of criteria for the selection and sizing of the mapping unit; v) implementation of 5 multivariate statistical susceptibility models based on Logistic Regression and Random Forests techniques and focused on landslide source areas; vi) evaluation of the influence of sample size and type of sampling on results and performance of the models; vii) evaluation of the predictive capabilities of the models using ROC curve, AUC and contingency tables; viii) comparison of model results and obtained susceptibility maps; and ix) analysis of temporal variation of landslide susceptibility related to input parameter changes. Models based on Logistic Regression and Random Forests have demonstrated excellent predictive capabilities. Land use and wildfire variables were found to have a strong control on the occurrence of very rapid shallow landslides.

Changes of visual-field global indices after cataract surgery in primary open-angle glaucoma patients.

PubMed

Seol, Bo Ram; Jeoung, Jin Wook; Park, Ki Ho

2016-11-01

To determine changes of visual-field (VF) global indices after cataract surgery and the factors associated with the effect of cataracts on those indices in primary open-angle glaucoma (POAG) patients. A retrospective chart review of 60 POAG patients who had undergone phacoemulsification and intraocular lens insertion was conducted. All of the patients were evaluated with standard automated perimetry (SAP; 30-2 Swedish interactive threshold algorithm; Carl Zeiss Meditec Inc.) before and after surgery. VF global indices before surgery were compared with those after surgery. The best-corrected visual acuity, intraocular pressure (IOP), number of glaucoma medications before surgery, mean total deviation (TD) values, mean pattern deviation (PD) value, and mean TD-PD value were also compared with the corresponding postoperative values. Additionally, postoperative peak IOP and mean IOP were evaluated. Univariate and multivariate logistic regression analyses were performed to identify the factors associated with the effect of cataract on global indices. Mean deviation (MD) after cataract surgery was significantly improved compared with the preoperative MD. Pattern standard deviation (PSD) and visual-field index (VFI) after surgery were similar to those before surgery. Also, mean TD and mean TD-PD were significantly improved after surgery. The posterior subcapsular cataract (PSC) type showed greater MD changes than did the non-PSC type in both the univariate and multivariate logistic regression analyses. In the univariate logistic regression analysis, the preoperative TD-PD value and type of cataract were associated with MD change. However, in the multivariate logistic regression analysis, type of cataract was the only associated factor. None of the other factors was associated with MD change. MD was significantly affected by cataracts, whereas PSD and VFI were not. Most notably, the PSC type showed better MD improvement compared with the non-PSC type after cataract surgery. Clinicians therefore should carefully analyze VF examination results for POAG patients with the PSC type.

Evaluating risk factors for endemic human Salmonella Enteritidis infections with different phage types in Ontario, Canada using multinomial logistic regression and a case-case study approach

PubMed Central

2012-01-01

Background Identifying risk factors for Salmonella Enteritidis (SE) infections in Ontario will assist public health authorities to design effective control and prevention programs to reduce the burden of SE infections. Our research objective was to identify risk factors for acquiring SE infections with various phage types (PT) in Ontario, Canada. We hypothesized that certain PTs (e.g., PT8 and PT13a) have specific risk factors for infection. Methods Our study included endemic SE cases with various PTs whose isolates were submitted to the Public Health Laboratory-Toronto from January 20th to August 12th, 2011. Cases were interviewed using a standardized questionnaire that included questions pertaining to demographics, travel history, clinical symptoms, contact with animals, and food exposures. A multinomial logistic regression method using the Generalized Linear Latent and Mixed Model procedure and a case-case study design were used to identify risk factors for acquiring SE infections with various PTs in Ontario, Canada. In the multinomial logistic regression model, the outcome variable had three categories representing human infections caused by SE PT8, PT13a, and all other SE PTs (i.e., non-PT8/non-PT13a) as a referent category to which the other two categories were compared. Results In the multivariable model, SE PT8 was positively associated with contact with dogs (OR=2.17, 95% CI 1.01-4.68) and negatively associated with pepper consumption (OR=0.35, 95% CI 0.13-0.94), after adjusting for age categories and gender, and using exposure periods and health regions as random effects to account for clustering. Conclusions Our study findings offer interesting hypotheses about the role of phage type-specific risk factors. Multinomial logistic regression analysis and the case-case study approach are novel methodologies to evaluate associations among SE infections with different PTs and various risk factors. PMID:23057531

Logistic regression for risk factor modelling in stuttering research.

PubMed

Reed, Phil; Wu, Yaqionq

2013-06-01

To outline the uses of logistic regression and other statistical methods for risk factor analysis in the context of research on stuttering. The principles underlying the application of a logistic regression are illustrated, and the types of questions to which such a technique has been applied in the stuttering field are outlined. The assumptions and limitations of the technique are discussed with respect to existing stuttering research, and with respect to formulating appropriate research strategies to accommodate these considerations. Finally, some alternatives to the approach are briefly discussed. The way the statistical procedures are employed are demonstrated with some hypothetical data. Research into several practical issues concerning stuttering could benefit if risk factor modelling were used. Important examples are early diagnosis, prognosis (whether a child will recover or persist) and assessment of treatment outcome. After reading this article you will: (a) Summarize the situations in which logistic regression can be applied to a range of issues about stuttering; (b) Follow the steps in performing a logistic regression analysis; (c) Describe the assumptions of the logistic regression technique and the precautions that need to be checked when it is employed; (d) Be able to summarize its advantages over other techniques like estimation of group differences and simple regression. Copyright © 2012 Elsevier Inc. All rights reserved.

Dynamic Dimensionality Selection for Bayesian Classifier Ensembles

DTIC Science & Technology

2015-03-19

learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very cometitive to Logistic Regression but much more...classifier, Generative learning, Discriminative learning, Naïve Bayes, Feature selection, Logistic regression , higher order attribute independence 16...discriminative learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very cometitive to Logistic Regression but

Preserving Institutional Privacy in Distributed binary Logistic Regression.

PubMed

Wu, Yuan; Jiang, Xiaoqian; Ohno-Machado, Lucila

2012-01-01

Privacy is becoming a major concern when sharing biomedical data across institutions. Although methods for protecting privacy of individual patients have been proposed, it is not clear how to protect the institutional privacy, which is many times a critical concern of data custodians. Built upon our previous work, Grid Binary LOgistic REgression (GLORE)1, we developed an Institutional Privacy-preserving Distributed binary Logistic Regression model (IPDLR) that considers both individual and institutional privacy for building a logistic regression model in a distributed manner. We tested our method using both simulated and clinical data, showing how it is possible to protect the privacy of individuals and of institutions using a distributed strategy.

Covariate Imbalance and Adjustment for Logistic Regression Analysis of Clinical Trial Data

PubMed Central

Ciolino, Jody D.; Martin, Reneé H.; Zhao, Wenle; Jauch, Edward C.; Hill, Michael D.; Palesch, Yuko Y.

2014-01-01

In logistic regression analysis for binary clinical trial data, adjusted treatment effect estimates are often not equivalent to unadjusted estimates in the presence of influential covariates. This paper uses simulation to quantify the benefit of covariate adjustment in logistic regression. However, International Conference on Harmonization guidelines suggest that covariate adjustment be pre-specified. Unplanned adjusted analyses should be considered secondary. Results suggest that that if adjustment is not possible or unplanned in a logistic setting, balance in continuous covariates can alleviate some (but never all) of the shortcomings of unadjusted analyses. The case of log binomial regression is also explored. PMID:24138438

Differentially private distributed logistic regression using private and public data.

PubMed

Ji, Zhanglong; Jiang, Xiaoqian; Wang, Shuang; Xiong, Li; Ohno-Machado, Lucila

2014-01-01

Privacy protecting is an important issue in medical informatics and differential privacy is a state-of-the-art framework for data privacy research. Differential privacy offers provable privacy against attackers who have auxiliary information, and can be applied to data mining models (for example, logistic regression). However, differentially private methods sometimes introduce too much noise and make outputs less useful. Given available public data in medical research (e.g. from patients who sign open-consent agreements), we can design algorithms that use both public and private data sets to decrease the amount of noise that is introduced. In this paper, we modify the update step in Newton-Raphson method to propose a differentially private distributed logistic regression model based on both public and private data. We try our algorithm on three different data sets, and show its advantage over: (1) a logistic regression model based solely on public data, and (2) a differentially private distributed logistic regression model based on private data under various scenarios. Logistic regression models built with our new algorithm based on both private and public datasets demonstrate better utility than models that trained on private or public datasets alone without sacrificing the rigorous privacy guarantee.

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.

Bidirectional relationship between renal function and periodontal disease in older Japanese women.

PubMed

Yoshihara, Akihiro; Iwasaki, Masanori; Miyazaki, Hideo; Nakamura, Kazutoshi

2016-09-01

The purpose of this study was to evaluate the reciprocal effects of chronic kidney disease (CKD) and periodontal disease. A total of 332 postmenopausal never smoking women were enrolled, and their serum high-sensitivity C-reactive protein, serum osteocalcin and serum cystatin C levels were measured. Poor renal function was defined as serum cystatin C > 0.91 mg/l. Periodontal disease markers, including clinical attachment level and the periodontal inflamed surface area (PISA), were also evaluated. Logistic regression analysis was conducted to evaluate the relationships between renal function and periodontal disease markers, serum osteocalcin level and hsCRP level. The prevalence-rate ratios (PRRs) on multiple Poisson regression analyses were determined to evaluate the relationships between periodontal disease markers and serum osteocalcin, serum cystatin C and serum hsCRP levels. On logistic regression analysis, PISA was significantly associated with serum cystatin C level. The odds ratio for serum cystatin C level was 2.44 (p = 0.011). The PRR between serum cystatin C level and periodontal disease markers such as number of sites with clinical attachment level ≥6 mm was significantly positive (3.12, p < 0.001). Similar tendencies were shown for serum osteocalcin level. This study suggests that CKD and periodontal disease can have reciprocal effects. © 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Independent Prognostic Factors for Acute Organophosphorus Pesticide Poisoning.

PubMed

Tang, Weidong; Ruan, Feng; Chen, Qi; Chen, Suping; Shao, Xuebo; Gao, Jianbo; Zhang, Mao

2016-07-01

Acute organophosphorus pesticide poisoning (AOPP) is becoming a significant problem and a potential cause of human mortality because of the abuse of organophosphate compounds. This study aims to determine the independent prognostic factors of AOPP by using multivariate logistic regression analysis. The clinical data for 71 subjects with AOPP admitted to our hospital were retrospectively analyzed. This information included the Acute Physiology and Chronic Health Evaluation II (APACHE II) scores, 6-h post-admission blood lactate levels, post-admission 6-h lactate clearance rates, admission blood cholinesterase levels, 6-h post-admission blood cholinesterase levels, cholinesterase activity, blood pH, and other factors. Univariate analysis and multivariate logistic regression analyses were conducted to identify all prognostic factors and independent prognostic factors, respectively. A receiver operating characteristic curve was plotted to analyze the testing power of independent prognostic factors. Twelve of 71 subjects died. Admission blood lactate levels, 6-h post-admission blood lactate levels, post-admission 6-h lactate clearance rates, blood pH, and APACHE II scores were identified as prognostic factors for AOPP according to the univariate analysis, whereas only 6-h post-admission blood lactate levels, post-admission 6-h lactate clearance rates, and blood pH were independent prognostic factors identified by multivariate logistic regression analysis. The receiver operating characteristic analysis suggested that post-admission 6-h lactate clearance rates were of moderate diagnostic value. High 6-h post-admission blood lactate levels, low blood pH, and low post-admission 6-h lactate clearance rates were independent prognostic factors identified by multivariate logistic regression analysis. Copyright © 2016 by Daedalus Enterprises.

A local equation for differential diagnosis of β-thalassemia trait and iron deficiency anemia by logistic regression analysis in Southeast Iran.

PubMed

Sargolzaie, Narjes; Miri-Moghaddam, Ebrahim

2014-01-01

The most common differential diagnosis of β-thalassemia (β-thal) trait is iron deficiency anemia. Several red blood cell equations were introduced during different studies for differential diagnosis between β-thal trait and iron deficiency anemia. Due to genetic variations in different regions, these equations cannot be useful in all population. The aim of this study was to determine a native equation with high accuracy for differential diagnosis of β-thal trait and iron deficiency anemia for the Sistan and Baluchestan population by logistic regression analysis. We selected 77 iron deficiency anemia and 100 β-thal trait cases. We used binary logistic regression analysis and determined best equations for probability prediction of β-thal trait against iron deficiency anemia in our population. We compared diagnostic values and receiver operative characteristic (ROC) curve related to this equation and another 10 published equations in discriminating β-thal trait and iron deficiency anemia. The binary logistic regression analysis determined the best equation for best probability prediction of β-thal trait against iron deficiency anemia with area under curve (AUC) 0.998. Based on ROC curves and AUC, Green & King, England & Frazer, and then Sirdah indices, respectively, had the most accuracy after our equation. We suggest that to get the best equation and cut-off in each region, one needs to evaluate specific information of each region, specifically in areas where populations are homogeneous, to provide a specific formula for differentiating between β-thal trait and iron deficiency anemia.

Evolution of the Marine Officer Fitness Report: A Multivariate Analysis

DTIC Science & Technology

This thesis explores the evaluation behavior of United States Marine Corps (USMC) Reporting Seniors (RSs) from 2010 to 2017. Using fitness report...RSs evaluate the performance of subordinate active component unrestricted officer MROs over time. I estimate logistic regression models of the...lowest. However, these correlations indicating the effects of race matching on FITREP evaluations narrow in significance when performance-based factors

Supporting Regularized Logistic Regression Privately and Efficiently.

PubMed

Li, Wenfa; Liu, Hongzhe; Yang, Peng; Xie, Wei

2016-01-01

As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Concerns over data privacy make it increasingly difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used statistical model while at the same time has not been investigated from a data security and privacy perspective. We consider a common use scenario of multi-institution collaborative studies, such as in the form of research consortia or networks as widely seen in genetics, epidemiology, social sciences, etc. To make our privacy-enhancing solution practical, we demonstrate a non-conventional and computationally efficient method leveraging distributing computing and strong cryptography to provide comprehensive protection over individual-level and summary data. Extensive empirical evaluations on several studies validate the privacy guarantee, efficiency and scalability of our proposal. We also discuss the practical implications of our solution for large-scale studies and applications from various disciplines, including genetic and biomedical studies, smart grid, network analysis, etc.

Supporting Regularized Logistic Regression Privately and Efficiently

PubMed Central

Li, Wenfa; Liu, Hongzhe; Yang, Peng; Xie, Wei

2016-01-01

As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on. These domains often involve data of human subjects that are contingent upon strict privacy regulations. Concerns over data privacy make it increasingly difficult to coordinate and conduct large-scale collaborative studies, which typically rely on cross-institution data sharing and joint analysis. Our work here focuses on safeguarding regularized logistic regression, a widely-used statistical model while at the same time has not been investigated from a data security and privacy perspective. We consider a common use scenario of multi-institution collaborative studies, such as in the form of research consortia or networks as widely seen in genetics, epidemiology, social sciences, etc. To make our privacy-enhancing solution practical, we demonstrate a non-conventional and computationally efficient method leveraging distributing computing and strong cryptography to provide comprehensive protection over individual-level and summary data. Extensive empirical evaluations on several studies validate the privacy guarantee, efficiency and scalability of our proposal. We also discuss the practical implications of our solution for large-scale studies and applications from various disciplines, including genetic and biomedical studies, smart grid, network analysis, etc. PMID:27271738

Carotid artery intima-media complex thickening in patients with relatively long-surviving type 1 diabetes mellitus.

PubMed

Distiller, Larry A; Joffe, Barry I; Melville, Vanessa; Welman, Tania; Distiller, Greg B

2006-01-01

The factors responsible for premature coronary atherosclerosis in patients with type 1 diabetes are ill defined. We therefore assessed carotid intima-media complex thickness (IMT) in relatively long-surviving patients with type 1 diabetes as a marker of atherosclerosis and correlated this with traditional risk factors. Cross-sectional study of 148 patients with relatively long-surviving (>18 years) type 1 diabetes (76 men and 72 women) attending the Centre for Diabetes and Endocrinology, Johannesburg. The mean common carotid artery IMT and presence or absence of plaque was evaluated by high-resolution B-mode ultrasound. Their median age was 48 years and duration of diabetes 26 years (range 18-59 years). Traditional risk factors (age, duration of diabetes, glycemic control, hypertension, smoking and lipoprotein concentrations) were recorded. Three response variables were defined and modeled. Standard multiple regression was used for a continuous IMT variable, logistic regression for the presence/absence of plaque and ordinal logistic regression to model three categories of "risk." The median common carotid IMT was 0.62 mm (range 0.44-1.23 mm) with plaque detected in 28 cases. The multiple regression model found significant associations between IMT and current age (P=.001), duration of diabetes (P=.033), BMI (P=.008) and diagnosed hypertension (P=.046) with HDL showing a protective effect (P=.022). Current age (P=.001) and diagnosed hypertension (P=.004), smoking (P=.008) and retinopathy (P=.033) were significant in the logistic regression model. Current age was also significant in the ordinal logistic regression model (P<.001), as was total cholesterol/HDL ratio (P<.001) and mean HbA(1c) concentration (P=.073). The major factors influencing common carotid IMT in patients with relatively long-surviving type 1 diabetes are age, duration of diabetes, existing hypertension and HDL (protective) with a relatively minor role ascribed to relatively long-standing glycemic control.

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.

Estimating Contraceptive Prevalence Using Logistics Data for Short-Acting Methods: Analysis Across 30 Countries.

PubMed

Cunningham, Marc; Bock, Ariella; Brown, Niquelle; Sacher, Suzy; Hatch, Benjamin; Inglis, Andrew; Aronovich, Dana

2015-09-01

Contraceptive prevalence rate (CPR) is a vital indicator used by country governments, international donors, and other stakeholders for measuring progress in family planning programs against country targets and global initiatives as well as for estimating health outcomes. Because of the need for more frequent CPR estimates than population-based surveys currently provide, alternative approaches for estimating CPRs are being explored, including using contraceptive logistics data. Using data from the Demographic and Health Surveys (DHS) in 30 countries, population data from the United States Census Bureau International Database, and logistics data from the Procurement Planning and Monitoring Report (PPMR) and the Pipeline Monitoring and Procurement Planning System (PipeLine), we developed and evaluated 3 models to generate country-level, public-sector contraceptive prevalence estimates for injectable contraceptives, oral contraceptives, and male condoms. Models included: direct estimation through existing couple-years of protection (CYP) conversion factors, bivariate linear regression, and multivariate linear regression. Model evaluation consisted of comparing the referent DHS prevalence rates for each short-acting method with the model-generated prevalence rate using multiple metrics, including mean absolute error and proportion of countries where the modeled prevalence rate for each method was within 1, 2, or 5 percentage points of the DHS referent value. For the methods studied, family planning use estimates from public-sector logistics data were correlated with those from the DHS, validating the quality and accuracy of current public-sector logistics data. Logistics data for oral and injectable contraceptives were significantly associated (P<.05) with the referent DHS values for both bivariate and multivariate models. For condoms, however, that association was only significant for the bivariate model. With the exception of the CYP-based model for condoms, models were able to estimate public-sector prevalence rates for each short-acting method to within 2 percentage points in at least 85% of countries. Public-sector contraceptive logistics data are strongly correlated with public-sector prevalence rates for short-acting methods, demonstrating the quality of current logistics data and their ability to provide relatively accurate prevalence estimates. The models provide a starting point for generating interim estimates of contraceptive use when timely survey data are unavailable. All models except the condoms CYP model performed well; the regression models were most accurate but the CYP model offers the simplest calculation method. Future work extending the research to other modern methods, relating subnational logistics data with prevalence rates, and tracking that relationship over time is needed. © Cunningham et al.

Estimating Contraceptive Prevalence Using Logistics Data for Short-Acting Methods: Analysis Across 30 Countries

PubMed Central

Cunningham, Marc; Brown, Niquelle; Sacher, Suzy; Hatch, Benjamin; Inglis, Andrew; Aronovich, Dana

2015-01-01

Background: Contraceptive prevalence rate (CPR) is a vital indicator used by country governments, international donors, and other stakeholders for measuring progress in family planning programs against country targets and global initiatives as well as for estimating health outcomes. Because of the need for more frequent CPR estimates than population-based surveys currently provide, alternative approaches for estimating CPRs are being explored, including using contraceptive logistics data. Methods: Using data from the Demographic and Health Surveys (DHS) in 30 countries, population data from the United States Census Bureau International Database, and logistics data from the Procurement Planning and Monitoring Report (PPMR) and the Pipeline Monitoring and Procurement Planning System (PipeLine), we developed and evaluated 3 models to generate country-level, public-sector contraceptive prevalence estimates for injectable contraceptives, oral contraceptives, and male condoms. Models included: direct estimation through existing couple-years of protection (CYP) conversion factors, bivariate linear regression, and multivariate linear regression. Model evaluation consisted of comparing the referent DHS prevalence rates for each short-acting method with the model-generated prevalence rate using multiple metrics, including mean absolute error and proportion of countries where the modeled prevalence rate for each method was within 1, 2, or 5 percentage points of the DHS referent value. Results: For the methods studied, family planning use estimates from public-sector logistics data were correlated with those from the DHS, validating the quality and accuracy of current public-sector logistics data. Logistics data for oral and injectable contraceptives were significantly associated (P<.05) with the referent DHS values for both bivariate and multivariate models. For condoms, however, that association was only significant for the bivariate model. With the exception of the CYP-based model for condoms, models were able to estimate public-sector prevalence rates for each short-acting method to within 2 percentage points in at least 85% of countries. Conclusions: Public-sector contraceptive logistics data are strongly correlated with public-sector prevalence rates for short-acting methods, demonstrating the quality of current logistics data and their ability to provide relatively accurate prevalence estimates. The models provide a starting point for generating interim estimates of contraceptive use when timely survey data are unavailable. All models except the condoms CYP model performed well; the regression models were most accurate but the CYP model offers the simplest calculation method. Future work extending the research to other modern methods, relating subnational logistics data with prevalence rates, and tracking that relationship over time is needed. PMID:26374805

Interpretation of commonly used statistical regression models.

PubMed

Kasza, Jessica; Wolfe, Rory

2014-01-01

A review of some regression models commonly used in respiratory health applications is provided in this article. Simple linear regression, multiple linear regression, logistic regression and ordinal logistic regression are considered. The focus of this article is on the interpretation of the regression coefficients of each model, which are illustrated through the application of these models to a respiratory health research study. © 2013 The Authors. Respirology © 2013 Asian Pacific Society of Respirology.

Use of neural networks to model complex immunogenetic associations of disease: human leukocyte antigen impact on the progression of human immunodeficiency virus infection.

PubMed

Ioannidis, J P; McQueen, P G; Goedert, J J; Kaslow, R A

1998-03-01

Complex immunogenetic associations of disease involving a large number of gene products are difficult to evaluate with traditional statistical methods and may require complex modeling. The authors evaluated the performance of feed-forward backpropagation neural networks in predicting rapid progression to acquired immunodeficiency syndrome (AIDS) for patients with human immunodeficiency virus (HIV) infection on the basis of major histocompatibility complex variables. Networks were trained on data from patients from the Multicenter AIDS Cohort Study (n = 139) and then validated on patients from the DC Gay cohort (n = 102). The outcome of interest was rapid disease progression, defined as progression to AIDS in <6 years from seroconversion. Human leukocyte antigen (HLA) variables were selected as network inputs with multivariate regression and a previously described algorithm selecting markers with extreme point estimates for progression risk. Network performance was compared with that of logistic regression. Networks with 15 HLA inputs and a single hidden layer of five nodes achieved a sensitivity of 87.5% and specificity of 95.6% in the training set, vs. 77.0% and 76.9%, respectively, achieved by logistic regression. When validated on the DC Gay cohort, networks averaged a sensitivity of 59.1% and specificity of 74.3%, vs. 53.1% and 61.4%, respectively, for logistic regression. Neural networks offer further support to the notion that HIV disease progression may be dependent on complex interactions between different class I and class II alleles and transporters associated with antigen processing variants. The effect in the current models is of moderate magnitude, and more data as well as other host and pathogen variables may need to be considered to improve the performance of the models. Artificial intelligence methods may complement linear statistical methods for evaluating immunogenetic associations of disease.

Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks.

PubMed

Hsieh, Chung-Ho; Lu, Ruey-Hwa; Lee, Nai-Hsin; Chiu, Wen-Ta; Hsu, Min-Huei; Li, Yu-Chuan Jack

2011-01-01

Diagnosing acute appendicitis clinically is still difficult. We developed random forests, support vector machines, and artificial neural network models to diagnose acute appendicitis. Between January 2006 and December 2008, patients who had a consultation session with surgeons for suspected acute appendicitis were enrolled. Seventy-five percent of the data set was used to construct models including random forest, support vector machines, artificial neural networks, and logistic regression. Twenty-five percent of the data set was withheld to evaluate model performance. The area under the receiver operating characteristic curve (AUC) was used to evaluate performance, which was compared with that of the Alvarado score. Data from a total of 180 patients were collected, 135 used for training and 45 for testing. The mean age of patients was 39.4 years (range, 16-85). Final diagnosis revealed 115 patients with and 65 without appendicitis. The AUC of random forest, support vector machines, artificial neural networks, logistic regression, and Alvarado was 0.98, 0.96, 0.91, 0.87, and 0.77, respectively. The sensitivity, specificity, positive, and negative predictive values of random forest were 94%, 100%, 100%, and 87%, respectively. Random forest performed better than artificial neural networks, logistic regression, and Alvarado. We demonstrated that random forest can predict acute appendicitis with good accuracy and, deployed appropriately, can be an effective tool in clinical decision making. Copyright © 2011 Mosby, Inc. All rights reserved.

Differentially private distributed logistic regression using private and public data

PubMed Central

2014-01-01

Background Privacy protecting is an important issue in medical informatics and differential privacy is a state-of-the-art framework for data privacy research. Differential privacy offers provable privacy against attackers who have auxiliary information, and can be applied to data mining models (for example, logistic regression). However, differentially private methods sometimes introduce too much noise and make outputs less useful. Given available public data in medical research (e.g. from patients who sign open-consent agreements), we can design algorithms that use both public and private data sets to decrease the amount of noise that is introduced. Methodology In this paper, we modify the update step in Newton-Raphson method to propose a differentially private distributed logistic regression model based on both public and private data. Experiments and results We try our algorithm on three different data sets, and show its advantage over: (1) a logistic regression model based solely on public data, and (2) a differentially private distributed logistic regression model based on private data under various scenarios. Conclusion Logistic regression models built with our new algorithm based on both private and public datasets demonstrate better utility than models that trained on private or public datasets alone without sacrificing the rigorous privacy guarantee. PMID:25079786

A retrospective analysis to identify the factors affecting infection in patients undergoing chemotherapy.

PubMed

Park, Ji Hyun; Kim, Hyeon-Young; Lee, Hanna; Yun, Eun Kyoung

2015-12-01

This study compares the performance of the logistic regression and decision tree analysis methods for assessing the risk factors for infection in cancer patients undergoing chemotherapy. The subjects were 732 cancer patients who were receiving chemotherapy at K university hospital in Seoul, Korea. The data were collected between March 2011 and February 2013 and were processed for descriptive analysis, logistic regression and decision tree analysis using the IBM SPSS Statistics 19 and Modeler 15.1 programs. The most common risk factors for infection in cancer patients receiving chemotherapy were identified as alkylating agents, vinca alkaloid and underlying diabetes mellitus. The logistic regression explained 66.7% of the variation in the data in terms of sensitivity and 88.9% in terms of specificity. The decision tree analysis accounted for 55.0% of the variation in the data in terms of sensitivity and 89.0% in terms of specificity. As for the overall classification accuracy, the logistic regression explained 88.0% and the decision tree analysis explained 87.2%. The logistic regression analysis showed a higher degree of sensitivity and classification accuracy. Therefore, logistic regression analysis is concluded to be the more effective and useful method for establishing an infection prediction model for patients undergoing chemotherapy. Copyright © 2015 Elsevier Ltd. All rights reserved.

Performance and strategy comparisons of human listeners and logistic regression in discriminating underwater targets.

PubMed

Yang, Lixue; Chen, Kean

2015-11-01

To improve the design of underwater target recognition systems based on auditory perception, this study compared human listeners with automatic classifiers. Performances measures and strategies in three discrimination experiments, including discriminations between man-made and natural targets, between ships and submarines, and among three types of ships, were used. In the experiments, the subjects were asked to assign a score to each sound based on how confident they were about the category to which it belonged, and logistic regression, which represents linear discriminative models, also completed three similar tasks by utilizing many auditory features. The results indicated that the performances of logistic regression improved as the ratio between inter- and intra-class differences became larger, whereas the performances of the human subjects were limited by their unfamiliarity with the targets. Logistic regression performed better than the human subjects in all tasks but the discrimination between man-made and natural targets, and the strategies employed by excellent human subjects were similar to that of logistic regression. Logistic regression and several human subjects demonstrated similar performances when discriminating man-made and natural targets, but in this case, their strategies were not similar. An appropriate fusion of their strategies led to further improvement in recognition accuracy.

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.

Unitary Response Regression Models

ERIC Educational Resources Information Center

Lipovetsky, S.

2007-01-01

The dependent variable in a regular linear regression is a numerical variable, and in a logistic regression it is a binary or categorical variable. In these models the dependent variable has varying values. However, there are problems yielding an identity output of a constant value which can also be modelled in a linear or logistic regression with…

Binary logistic regression-Instrument for assessing museum indoor air impact on exhibits.

PubMed

Bucur, Elena; Danet, Andrei Florin; Lehr, Carol Blaziu; Lehr, Elena; Nita-Lazar, Mihai

2017-04-01

This paper presents a new way to assess the environmental impact on historical artifacts using binary logistic regression. The prediction of the impact on the exhibits during certain pollution scenarios (environmental impact) was calculated by a mathematical model based on the binary logistic regression; it allows the identification of those environmental parameters from a multitude of possible parameters with a significant impact on exhibitions and ranks them according to their severity effect. Air quality (NO 2 , SO 2 , O 3 and PM 2.5 ) and microclimate parameters (temperature, humidity) monitoring data from a case study conducted within exhibition and storage spaces of the Romanian National Aviation Museum Bucharest have been used for developing and validating the binary logistic regression method and the mathematical model. The logistic regression analysis was used on 794 data combinations (715 to develop of the model and 79 to validate it) by a Statistical Package for Social Sciences (SPSS 20.0). The results from the binary logistic regression analysis demonstrated that from six parameters taken into consideration, four of them present a significant effect upon exhibits in the following order: O 3 >PM 2.5 >NO 2 >humidity followed at a significant distance by the effects of SO 2 and temperature. The mathematical model, developed in this study, correctly predicted 95.1 % of the cumulated effect of the environmental parameters upon the exhibits. Moreover, this model could also be used in the decisional process regarding the preventive preservation measures that should be implemented within the exhibition space. The paper presents a new way to assess the environmental impact on historical artifacts using binary logistic regression. The mathematical model developed on the environmental parameters analyzed by the binary logistic regression method could be useful in a decision-making process establishing the best measures for pollution reduction and preventive preservation of exhibits.

Determining factors influencing survival of breast cancer by fuzzy logistic regression model.

PubMed

Nikbakht, Roya; Bahrampour, Abbas

2017-01-01

Fuzzy logistic regression model can be used for determining influential factors of disease. This study explores the important factors of actual predictive survival factors of breast cancer's patients. We used breast cancer data which collected by cancer registry of Kerman University of Medical Sciences during the period of 2000-2007. The variables such as morphology, grade, age, and treatments (surgery, radiotherapy, and chemotherapy) were applied in the fuzzy logistic regression model. Performance of model was determined in terms of mean degree of membership (MDM). The study results showed that almost 41% of patients were in neoplasm and malignant group and more than two-third of them were still alive after 5-year follow-up. Based on the fuzzy logistic model, the most important factors influencing survival were chemotherapy, morphology, and radiotherapy, respectively. Furthermore, the MDM criteria show that the fuzzy logistic regression have a good fit on the data (MDM = 0.86). Fuzzy logistic regression model showed that chemotherapy is more important than radiotherapy in survival of patients with breast cancer. In addition, another ability of this model is calculating possibilistic odds of survival in cancer patients. The results of this study can be applied in clinical research. Furthermore, there are few studies which applied the fuzzy logistic models. Furthermore, we recommend using this model in various research areas.

Integration of logistic regression and multicriteria land evaluation to simulation establishment of sustainable paddy field zone in Indramayu Regency, West Java Province, Indonesia

NASA Astrophysics Data System (ADS)

Nahib, Irmadi; Suryanta, Jaka; Niedyawati; Kardono, Priyadi; Turmudi; Lestari, Sri; Windiastuti, Rizka

2018-05-01

Ministry of Agriculture have targeted production of 1.718 million tons of dry grain harvest during period of 2016-2021 to achieve food self-sufficiency, through optimization of special commodities including paddy, soybean and corn. This research was conducted to develop a sustainable paddy field zone delineation model using logistic regression and multicriteria land evaluation in Indramayu Regency. A model was built on the characteristics of local function conversion by considering the concept of sustainable development. Spatial data overlay was constructed using available data, and then this model was built upon the occurrence of paddy field between 1998 and 2015. Equation for the model of paddy field changes obtained was: logit (paddy field conversion) = - 2.3048 + 0.0032*X1 – 0.0027*X2 + 0.0081*X3 + 0.0025*X4 + 0.0026*X5 + 0.0128*X6 – 0.0093*X7 + 0.0032*X8 + 0.0071*X9 – 0.0046*X10 where X1 to X10 were variables that determine the occurrence of changes in paddy fields, with a result value of Relative Operating Characteristics (ROC) of 0.8262. The weakest variable in influencing the change of paddy field function was X7 (paddy field price), while the most influential factor was X1 (distance from river). Result of the logistic regression was used as a weight for multicriteria land evaluation, which recommended three scenarios of paddy fields protection policy: standard, protective, and permissive. The result of this modelling, the priority paddy fields for protected scenario were obtained, as well as the buffer zones for the surrounding paddy fields.

Impact of clinical status and salivary conditions on xerostomia and oral health-related quality of life of adolescents with type 1 diabetes mellitus.

PubMed

Busato, Ivana Maria Saes; Ignácio, Sérgio Aparecido; Brancher, João Armando; Moysés, Simone Tetu; Azevedo-Alanis, Luciana Reis

2012-02-01

To investigate the influence of clinical status and salivary conditions on the presence of xerostomia on adolescents with and without type 1 diabetes mellitus (DM1), and further to investigate the influence of clinical status, salivary conditions and xerostomia on oral health-related quality of life (OHQoL) of those with DM1. A cross-sectional study was performed on 102 adolescents, 51 with DM1 and 51 nondiabetics. Xerostomia was detected by asking a question about the sensation of having 'dry mouth', and Oral Health Impact Profile-14 was used to measure the impact of xerostomia on OHQoL. The clinical status was assessed by using decayed, missing or filled and Community Periodontal indices, and by evaluating oral manifestations; and the following salivary conditions were evaluated: stimulated salivary flow, pH, buffer capacity, total protein, amylase, urea, calcium, and glucose salivary concentrations. Multiple logistic regression analysis was used to evaluate the influence of clinical status and salivary conditions on xerostomia and the impact of xerostomia on the OHQoL of adolescents with DM1. Clinical status and salivary conditions was shown to have no influence on the presence of xerostomia. Bivariate (P = 0.00) and logistic regression (P = 0.01) analysis showed a significant association between DM1 and xerostomia. Logistic regression analysis showed association between xerostomia (P = 0.00) and OHQoL, and caries experience (P = 0.03) and OHQoL. DM1 showed to be predictive of a high prevalence of xerostomia in adolescents. Caries experience and xerostomia showed to have a negative impact on the OHQoL of adolescents with DM1. © 2011 John Wiley & Sons A/S.

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.

C-reactive protein, platelets, and patent ductus arteriosus.

PubMed

Meinarde, Leonardo; Hillman, Macarena; Rizzotti, Alina; Basquiera, Ana Lisa; Tabares, Aldo; Cuestas, Eduardo

2016-12-01

The association between inflammation, platelets, and patent ductus arteriosus (PDA) has not been studied so far. The purpose of this study was to evaluate whether C-reactive protein (CRP) is related to low platelet count and PDA. This was a retrospective study of 88 infants with a birth weight ≤1500 g and a gestational age ≤30 weeks. Platelet count, CRP, and an echocardiogram were assessed in all infants. The subjects were matched by sex, gestational age, and birth weight. Differences were compared using the χ 2 , t-test, or Mann-Whitney U-test, as appropriate. Significant variables were entered into a logistic regression model. The association between CRP and platelets was evaluated by correlation and regression analysis. Platelet count (167 000 vs. 213 000 µl -1 , p = 0.015) was lower and the CRP (0.45 vs. 0.20 mg/dl, p = 0.002) was higher, and the platelet count correlated inversely with CRP (r = -0.145, p = 0.049) in the infants with vs. without PDA. Only CRP was independently associated with PDA in a logistic regression model (OR 64.1, 95% confidence interval 1.4-2941, p = 0.033).

Individual risk factors for deep infection and compromised fracture healing after intramedullary nailing of tibial shaft fractures: a single centre experience of 480 patients.

PubMed

Metsemakers, W-J; Handojo, K; Reynders, P; Sermon, A; Vanderschot, P; Nijs, S

2015-04-01

Despite modern advances in the treatment of tibial shaft fractures, complications including nonunion, malunion, and infection remain relatively frequent. A better understanding of these injuries and its complications could lead to prevention rather than treatment strategies. A retrospective study was performed to identify risk factors for deep infection and compromised fracture healing after intramedullary nailing (IMN) of tibial shaft fractures. Between January 2000 and January 2012, 480 consecutive patients with 486 tibial shaft fractures were enrolled in the study. Statistical analysis was performed to determine predictors of deep infection and compromised fracture healing. Compromised fracture healing was subdivided in delayed union and nonunion. The following independent variables were selected for analysis: age, sex, smoking, obesity, diabetes, American Society of Anaesthesiologists (ASA) classification, polytrauma, fracture type, open fractures, Gustilo type, primary external fixation (EF), time to nailing (TTN) and reaming. As primary statistical evaluation we performed a univariate analysis, followed by a multiple logistic regression model. Univariate regression analysis revealed similar risk factors for delayed union and nonunion, including fracture type, open fractures and Gustilo type. Factors affecting the occurrence of deep infection in this model were primary EF, a prolonged TTN, open fractures and Gustilo type. Multiple logistic regression analysis revealed polytrauma as the single risk factor for nonunion. With respect to delayed union, no risk factors could be identified. In the same statistical model, deep infection was correlated with primary EF. The purpose of this study was to evaluate risk factors of poor outcome after IMN of tibial shaft fractures. The univariate regression analysis showed that the nature of complications after tibial shaft nailing could be multifactorial. This was not confirmed in a multiple logistic regression model, which only revealed polytrauma and primary EF as risk factors for nonunion and deep infection, respectively. Future strategies should focus on prevention in high-risk populations such as polytrauma patients treated with EF. Copyright © 2014 Elsevier Ltd. All rights reserved.

Advanced colorectal neoplasia risk stratification by penalized logistic regression.

PubMed

Lin, Yunzhi; Yu, Menggang; Wang, Sijian; Chappell, Richard; Imperiale, Thomas F

2016-08-01

Colorectal cancer is the second leading cause of death from cancer in the United States. To facilitate the efficiency of colorectal cancer screening, there is a need to stratify risk for colorectal cancer among the 90% of US residents who are considered "average risk." In this article, we investigate such risk stratification rules for advanced colorectal neoplasia (colorectal cancer and advanced, precancerous polyps). We use a recently completed large cohort study of subjects who underwent a first screening colonoscopy. Logistic regression models have been used in the literature to estimate the risk of advanced colorectal neoplasia based on quantifiable risk factors. However, logistic regression may be prone to overfitting and instability in variable selection. Since most of the risk factors in our study have several categories, it was tempting to collapse these categories into fewer risk groups. We propose a penalized logistic regression method that automatically and simultaneously selects variables, groups categories, and estimates their coefficients by penalizing the [Formula: see text]-norm of both the coefficients and their differences. Hence, it encourages sparsity in the categories, i.e. grouping of the categories, and sparsity in the variables, i.e. variable selection. We apply the penalized logistic regression method to our data. The important variables are selected, with close categories simultaneously grouped, by penalized regression models with and without the interactions terms. The models are validated with 10-fold cross-validation. The receiver operating characteristic curves of the penalized regression models dominate the receiver operating characteristic curve of naive logistic regressions, indicating a superior discriminative performance. © The Author(s) 2013.

Sociodemographic Barriers to Early Detection of Autism: Screening and Evaluation Using the M-CHAT, M-CHAT-R, and Follow-Up

ERIC Educational Resources Information Center

Khowaja, Meena K.; Hazzard, Ann P.; Robins, Diana L.

2015-01-01

Parents (n = 11,845) completed the Modified Checklist for Autism in Toddlers (or its latest revision) at pediatric visits. Using sociodemographic predictors of maternal education and race, binary logistic regressions were utilized to examine differences in autism screening, diagnostic evaluation participation rates and outcomes, and reasons for…

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.

Evaluating the effect of a third-party implementation of resolution recovery on the quality of SPECT bone scan imaging using visual grading regression.

PubMed

Hay, Peter D; Smith, Julie; O'Connor, Richard A

2016-02-01

The aim of this study was to evaluate the benefits to SPECT bone scan image quality when applying resolution recovery (RR) during image reconstruction using software provided by a third-party supplier. Bone SPECT data from 90 clinical studies were reconstructed retrospectively using software supplied independent of the gamma camera manufacturer. The current clinical datasets contain 120×10 s projections and are reconstructed using an iterative method with a Butterworth postfilter. Five further reconstructions were created with the following characteristics: 10 s projections with a Butterworth postfilter (to assess intraobserver variation); 10 s projections with a Gaussian postfilter with and without RR; and 5 s projections with a Gaussian postfilter with and without RR. Two expert observers were asked to rate image quality on a five-point scale relative to our current clinical reconstruction. Datasets were anonymized and presented in random order. The benefits of RR on image scores were evaluated using ordinal logistic regression (visual grading regression). The application of RR during reconstruction increased the probability of both observers of scoring image quality as better than the current clinical reconstruction even where the dataset contained half the normal counts. Type of reconstruction and observer were both statistically significant variables in the ordinal logistic regression model. Visual grading regression was found to be a useful method for validating the local introduction of technological developments in nuclear medicine imaging. RR, as implemented by the independent software supplier, improved bone SPECT image quality when applied during image reconstruction. In the majority of clinical cases, acquisition times for bone SPECT intended for the purposes of localization can safely be halved (from 10 s projections to 5 s) when RR is applied.

Estimating the exceedance probability of rain rate by logistic regression

NASA Technical Reports Server (NTRS)

Chiu, Long S.; Kedem, Benjamin

1990-01-01

Recent studies have shown that the fraction of an area with rain intensity above a fixed threshold is highly correlated with the area-averaged rain rate. To estimate the fractional rainy area, a logistic regression model, which estimates the conditional probability that rain rate over an area exceeds a fixed threshold given the values of related covariates, is developed. The problem of dependency in the data in the estimation procedure is bypassed by the method of partial likelihood. Analyses of simulated scanning multichannel microwave radiometer and observed electrically scanning microwave radiometer data during the Global Atlantic Tropical Experiment period show that the use of logistic regression in pixel classification is superior to multiple regression in predicting whether rain rate at each pixel exceeds a given threshold, even in the presence of noisy data. The potential of the logistic regression technique in satellite rain rate estimation is discussed.

Comparison of naïve Bayes and logistic regression for computer-aided diagnosis of breast masses using ultrasound imaging

NASA Astrophysics Data System (ADS)

Cary, Theodore W.; Cwanger, Alyssa; Venkatesh, Santosh S.; Conant, Emily F.; Sehgal, Chandra M.

2012-03-01

This study compares the performance of two proven but very different machine learners, Naïve Bayes and logistic regression, for differentiating malignant and benign breast masses using ultrasound imaging. Ultrasound images of 266 masses were analyzed quantitatively for shape, echogenicity, margin characteristics, and texture features. These features along with patient age, race, and mammographic BI-RADS category were used to train Naïve Bayes and logistic regression classifiers to diagnose lesions as malignant or benign. ROC analysis was performed using all of the features and using only a subset that maximized information gain. Performance was determined by the area under the ROC curve, Az, obtained from leave-one-out cross validation. Naïve Bayes showed significant variation (Az 0.733 +/- 0.035 to 0.840 +/- 0.029, P < 0.002) with the choice of features, but the performance of logistic regression was relatively unchanged under feature selection (Az 0.839 +/- 0.029 to 0.859 +/- 0.028, P = 0.605). Out of 34 features, a subset of 6 gave the highest information gain: brightness difference, margin sharpness, depth-to-width, mammographic BI-RADs, age, and race. The probabilities of malignancy determined by Naïve Bayes and logistic regression after feature selection showed significant correlation (R2= 0.87, P < 0.0001). The diagnostic performance of Naïve Bayes and logistic regression can be comparable, but logistic regression is more robust. Since probability of malignancy cannot be measured directly, high correlation between the probabilities derived from two basic but dissimilar models increases confidence in the predictive power of machine learning models for characterizing solid breast masses on ultrasound.

Evaluation of Cox's model and logistic regression for matched case-control data with time-dependent covariates: a simulation study.

PubMed

Leffondré, Karen; Abrahamowicz, Michal; Siemiatycki, Jack

2003-12-30

Case-control studies are typically analysed using the conventional logistic model, which does not directly account for changes in the covariate values over time. Yet, many exposures may vary over time. The most natural alternative to handle such exposures would be to use the Cox model with time-dependent covariates. However, its application to case-control data opens the question of how to manipulate the risk sets. Through a simulation study, we investigate how the accuracy of the estimates of Cox's model depends on the operational definition of risk sets and/or on some aspects of the time-varying exposure. We also assess the estimates obtained from conventional logistic regression. The lifetime experience of a hypothetical population is first generated, and a matched case-control study is then simulated from this population. We control the frequency, the age at initiation, and the total duration of exposure, as well as the strengths of their effects. All models considered include a fixed-in-time covariate and one or two time-dependent covariate(s): the indicator of current exposure and/or the exposure duration. Simulation results show that none of the models always performs well. The discrepancies between the odds ratios yielded by logistic regression and the 'true' hazard ratio depend on both the type of the covariate and the strength of its effect. In addition, it seems that logistic regression has difficulty separating the effects of inter-correlated time-dependent covariates. By contrast, each of the two versions of Cox's model systematically induces either a serious under-estimation or a moderate over-estimation bias. The magnitude of the latter bias is proportional to the true effect, suggesting that an improved manipulation of the risk sets may eliminate, or at least reduce, the bias. Copyright 2003 JohnWiley & Sons, Ltd.

Variable Selection in Logistic Regression.

DTIC Science & Technology

1987-06-01

23 %. AUTIOR(.) S. CONTRACT OR GRANT NUMBE Rf.i %Z. D. Bai, P. R. Krishnaiah and . C. Zhao F49620-85- C-0008 " PERFORMING ORGANIZATION NAME AND AOORESS...d I7 IOK-TK- d 7 -I0 7’ VARIABLE SELECTION IN LOGISTIC REGRESSION Z. D. Bai, P. R. Krishnaiah and L. C. Zhao Center for Multivariate Analysis...University of Pittsburgh Center for Multivariate Analysis University of Pittsburgh Y !I VARIABLE SELECTION IN LOGISTIC REGRESSION Z- 0. Bai, P. R. Krishnaiah

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.

Modelling of binary logistic regression for obesity among secondary students in a rural area of Kedah

NASA Astrophysics Data System (ADS)

Kamaruddin, Ainur Amira; Ali, Zalila; Noor, Norlida Mohd.; Baharum, Adam; Ahmad, Wan Muhamad Amir W.

2014-07-01

Logistic regression analysis examines the influence of various factors on a dichotomous outcome by estimating the probability of the event's occurrence. Logistic regression, also called a logit model, is a statistical procedure used to model dichotomous outcomes. In the logit model the log odds of the dichotomous outcome is modeled as a linear combination of the predictor variables. The log odds ratio in logistic regression provides a description of the probabilistic relationship of the variables and the outcome. In conducting logistic regression, selection procedures are used in selecting important predictor variables, diagnostics are used to check that assumptions are valid which include independence of errors, linearity in the logit for continuous variables, absence of multicollinearity, and lack of strongly influential outliers and a test statistic is calculated to determine the aptness of the model. This study used the binary logistic regression model to investigate overweight and obesity among rural secondary school students on the basis of their demographics profile, medical history, diet and lifestyle. The results indicate that overweight and obesity of students are influenced by obesity in family and the interaction between a student's ethnicity and routine meals intake. The odds of a student being overweight and obese are higher for a student having a family history of obesity and for a non-Malay student who frequently takes routine meals as compared to a Malay student.

Methodologic considerations in the design and analysis of nested case-control studies: association between cytokines and postoperative delirium.

PubMed

Ngo, Long H; Inouye, Sharon K; Jones, Richard N; Travison, Thomas G; Libermann, Towia A; Dillon, Simon T; Kuchel, George A; Vasunilashorn, Sarinnapha M; Alsop, David C; Marcantonio, Edward R

2017-06-06

The nested case-control study (NCC) design within a prospective cohort study is used when outcome data are available for all subjects, but the exposure of interest has not been collected, and is difficult or prohibitively expensive to obtain for all subjects. A NCC analysis with good matching procedures yields estimates that are as efficient and unbiased as estimates from the full cohort study. We present methodological considerations in a matched NCC design and analysis, which include the choice of match algorithms, analysis methods to evaluate the association of exposures of interest with outcomes, and consideration of overmatching. Matched, NCC design within a longitudinal observational prospective cohort study in the setting of two academic hospitals. Study participants are patients aged over 70 years who underwent scheduled major non-cardiac surgery. The primary outcome was postoperative delirium from in-hospital interviews and medical record review. The main exposure was IL-6 concentration (pg/ml) from blood sampled at three time points before delirium occurred. We used nonparametric signed ranked test to test for the median of the paired differences. We used conditional logistic regression to model the risk of IL-6 on delirium incidence. Simulation was used to generate a sample of cohort data on which unconditional multivariable logistic regression was used, and the results were compared to those of the conditional logistic regression. Partial R-square was used to assess the level of overmatching. We found that the optimal match algorithm yielded more matched pairs than the greedy algorithm. The choice of analytic strategy-whether to consider measured cytokine levels as the predictor or outcome-- yielded inferences that have different clinical interpretations but similar levels of statistical significance. Estimation results from NCC design using conditional logistic regression, and from simulated cohort design using unconditional logistic regression, were similar. We found minimal evidence for overmatching. Using a matched NCC approach introduces methodological challenges into the study design and data analysis. Nonetheless, with careful selection of the match algorithm, match factors, and analysis methods, this design is cost effective and, for our study, yields estimates that are similar to those from a prospective cohort study design.

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

Understanding logistic regression analysis.

PubMed

Sperandei, Sandro

2014-01-01

Logistic regression is used to obtain odds ratio in the presence of more than one explanatory variable. The procedure is quite similar to multiple linear regression, with the exception that the response variable is binomial. The result is the impact of each variable on the odds ratio of the observed event of interest. The main advantage is to avoid confounding effects by analyzing the association of all variables together. In this article, we explain the logistic regression procedure using examples to make it as simple as possible. After definition of the technique, the basic interpretation of the results is highlighted and then some special issues are discussed.

The use of generalized estimating equations in the analysis of motor vehicle crash data.

PubMed

Hutchings, Caroline B; Knight, Stacey; Reading, James C

2003-01-01

The purpose of this study was to determine if it is necessary to use generalized estimating equations (GEEs) in the analysis of seat belt effectiveness in preventing injuries in motor vehicle crashes. The 1992 Utah crash dataset was used, excluding crash participants where seat belt use was not appropriate (n=93,633). The model used in the 1996 Report to Congress [Report to congress on benefits of safety belts and motorcycle helmets, based on data from the Crash Outcome Data Evaluation System (CODES). National Center for Statistics and Analysis, NHTSA, Washington, DC, February 1996] was analyzed for all occupants with logistic regression, one level of nesting (occupants within crashes), and two levels of nesting (occupants within vehicles within crashes) to compare the use of GEEs with logistic regression. When using one level of nesting compared to logistic regression, 13 of 16 variance estimates changed more than 10%, and eight of 16 parameter estimates changed more than 10%. In addition, three of the independent variables changed from significant to insignificant (alpha=0.05). With the use of two levels of nesting, two of 16 variance estimates and three of 16 parameter estimates changed more than 10% from the variance and parameter estimates in one level of nesting. One of the independent variables changed from insignificant to significant (alpha=0.05) in the two levels of nesting model; therefore, only two of the independent variables changed from significant to insignificant when the logistic regression model was compared to the two levels of nesting model. The odds ratio of seat belt effectiveness in preventing injuries was 12% lower when a one-level nested model was used. Based on these results, we stress the need to use a nested model and GEEs when analyzing motor vehicle crash data.

Modeling of geogenic radon in Switzerland based on ordered logistic regression.

PubMed

Kropat, Georg; Bochud, François; Murith, Christophe; Palacios Gruson, Martha; Baechler, Sébastien

2017-01-01

The estimation of the radon hazard of a future construction site should ideally be based on the geogenic radon potential (GRP), since this estimate is free of anthropogenic influences and building characteristics. The goal of this study was to evaluate terrestrial gamma dose rate (TGD), geology, fault lines and topsoil permeability as predictors for the creation of a GRP map based on logistic regression. Soil gas radon measurements (SRC) are more suited for the estimation of GRP than indoor radon measurements (IRC) since the former do not depend on ventilation and heating habits or building characteristics. However, SRC have only been measured at a few locations in Switzerland. In former studies a good correlation between spatial aggregates of IRC and SRC has been observed. That's why we used IRC measurements aggregated on a 10 km × 10 km grid to calibrate an ordered logistic regression model for geogenic radon potential (GRP). As predictors we took into account terrestrial gamma doserate, regrouped geological units, fault line density and the permeability of the soil. The classification success rate of the model results to 56% in case of the inclusion of all 4 predictor variables. Our results suggest that terrestrial gamma doserate and regrouped geological units are more suited to model GRP than fault line density and soil permeability. Ordered logistic regression is a promising tool for the modeling of GRP maps due to its simplicity and fast computation time. Future studies should account for additional variables to improve the modeling of high radon hazard in the Jura Mountains of Switzerland. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

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.

Multivariate logistic regression for predicting total culturable virus presence at the intake of a potable-water treatment plant: novel application of the atypical coliform/total coliform ratio.

PubMed

Black, L E; Brion, G M; Freitas, S J

2007-06-01

Predicting the presence of enteric viruses in surface waters is a complex modeling problem. Multiple water quality parameters that indicate the presence of human fecal material, the load of fecal material, and the amount of time fecal material has been in the environment are needed. This paper presents the results of a multiyear study of raw-water quality at the inlet of a potable-water plant that related 17 physical, chemical, and biological indices to the presence of enteric viruses as indicated by cytopathic changes in cell cultures. It was found that several simple, multivariate logistic regression models that could reliably identify observations of the presence or absence of total culturable virus could be fitted. The best models developed combined a fecal age indicator (the atypical coliform [AC]/total coliform [TC] ratio), the detectable presence of a human-associated sterol (epicoprostanol) to indicate the fecal source, and one of several fecal load indicators (the levels of Giardia species cysts, coliform bacteria, and coprostanol). The best fit to the data was found when the AC/TC ratio, the presence of epicoprostanol, and the density of fecal coliform bacteria were input into a simple, multivariate logistic regression equation, resulting in 84.5% and 78.6% accuracies for the identification of the presence and absence of total culturable virus, respectively. The AC/TC ratio was the most influential input variable in all of the models generated, but producing the best prediction required additional input related to the fecal source and the fecal load. The potential for replacing microbial indicators of fecal load with levels of coprostanol was proposed and evaluated by multivariate logistic regression modeling for the presence and absence of virus.

HRCT findings of collagen vascular disease-related interstitial pneumonia (CVD-IP): a comparative study among individual underlying diseases.

PubMed

Tanaka, N; Kunihiro, Y; Kubo, M; Kawano, R; Oishi, K; Ueda, K; Gondo, T

2018-05-29

To identify characteristic high-resolution computed tomography (CT) findings for individual collagen vascular disease (CVD)-related interstitial pneumonias (IPs). The HRCT findings of 187 patients with CVD, including 55 patients with rheumatoid arthritis (RA), 50 with systemic sclerosis (SSc), 46 with polymyositis/dermatomyositis (PM/DM), 15 with mixed connective tissue disease, 11 with primary Sjögren's syndrome, and 10 with systemic lupus erythematosus, were evaluated. Lung parenchymal abnormalities were compared among CVDs using χ 2 test, Kruskal-Wallis test, and multiple logistic regression analysis. A CT-pathology correlation was performed in 23 patients. In RA-IP, honeycombing was identified as the significant indicator based on multiple logistic regression analyses. Traction bronchiectasis (81.8%) was further identified as the most frequent finding based on χ 2 test. In SSc IP, lymph node enlargement and oesophageal dilatation were identified as the indicators based on multiple logistic regression analyses, and ground-glass opacity (GGO) was the most extensive based on Kruskal-Wallis test, which reflects the higher frequency of the pathological nonspecific interstitial pneumonia (NSIP) pattern present in the CT-pathology correlation. In PM/DM IP, airspace consolidation and the absence of honeycombing were identified as the indicators based on multiple logistic regression analyses, and predominance of consolidation over GGO (32.6%) and predominant subpleural distribution of GGO/consolidation (41.3%) were further identified as the most frequent findings based on χ 2 test, which reflects the higher frequency of the pathological NSIP and/or the organising pneumonia patterns present in the CT-pathology correlation. Several characteristic high-resolution CT findings with utility for estimating underlying CVD were identified. Copyright © 2018 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

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.

Habitat patch size and nesting success of yellow-breasted chats

Treesearch

Dick E. Burhans; Frank R. Thompson III

1999-01-01

We measured vegetation at shrub patches used for nesting by Yellow-breasted Chats (Icteria virens) to evaluate the importance of nesting habitat patch features on nest predation, cowbird parasitism, and nest site selection. Logistic regression models indicated that nests in small patches (average diameter

Comparing Methodologies for Developing an Early Warning System: Classification and Regression Tree Model versus Logistic Regression. REL 2015-077

ERIC Educational Resources Information Center

Koon, Sharon; Petscher, Yaacov

2015-01-01

The purpose of this report was to explicate the use of logistic regression and classification and regression tree (CART) analysis in the development of early warning systems. It was motivated by state education leaders' interest in maintaining high classification accuracy while simultaneously improving practitioner understanding of the rules by…

Construction of a pathological risk model of occult lymph node metastases for prognostication by semi-automated image analysis of tumor budding in early-stage oral squamous cell carcinoma

PubMed Central

Pedersen, Nicklas Juel; Jensen, David Hebbelstrup; Lelkaitis, Giedrius; Kiss, Katalin; Charabi, Birgitte; Specht, Lena; von Buchwald, Christian

2017-01-01

It is challenging to identify at diagnosis those patients with early oral squamous cell carcinoma (OSCC), who have a poor prognosis and those that have a high risk of harboring occult lymph node metastases. The aim of this study was to develop a standardized and objective digital scoring method to evaluate the predictive value of tumor budding. We developed a semi-automated image-analysis algorithm, Digital Tumor Bud Count (DTBC), to evaluate tumor budding. The algorithm was tested in 222 consecutive patients with early-stage OSCC and major endpoints were overall (OS) and progression free survival (PFS). We subsequently constructed and cross-validated a binary logistic regression model and evaluated its clinical utility by decision curve analysis. A high DTBC was an independent predictor of both poor OS and PFS in a multivariate Cox regression model. The logistic regression model was able to identify patients with occult lymph node metastases with an area under the curve (AUC) of 0.83 (95% CI: 0.78–0.89, P <0.001) and a 10-fold cross-validated AUC of 0.79. Compared to other known histopathological risk factors, the DTBC had a higher diagnostic accuracy. The proposed, novel risk model could be used as a guide to identify patients who would benefit from an up-front neck dissection. PMID:28212555

Embedded measures of performance validity using verbal fluency tests in a clinical sample.

PubMed

Sugarman, Michael A; Axelrod, Bradley N

2015-01-01

The objective of this study was to determine to what extent verbal fluency measures can be used as performance validity indicators during neuropsychological evaluation. Participants were clinically referred for neuropsychological evaluation in an urban-based Veteran's Affairs hospital. Participants were placed into 2 groups based on their objectively evaluated effort on performance validity tests (PVTs). Individuals who exhibited credible performance (n = 431) failed 0 PVTs, and those with poor effort (n = 192) failed 2 or more PVTs. All participants completed the Controlled Oral Word Association Test (COWAT) and Animals verbal fluency measures. We evaluated how well verbal fluency scores could discriminate between the 2 groups. Raw scores and T scores for Animals discriminated between the credible performance and poor-effort groups with 90% specificity and greater than 40% sensitivity. COWAT scores had lower sensitivity for detecting poor effort. A combination of FAS and Animals scores into logistic regression models yielded acceptable group classification, with 90% specificity and greater than 44% sensitivity. Verbal fluency measures can yield adequate detection of poor effort during neuropsychological evaluation. We provide suggested cut points and logistic regression models for predicting the probability of poor effort in our clinical setting and offer suggested cutoff scores to optimize sensitivity and specificity.

Using Multiple and Logistic Regression to Estimate the Median WillCost and Probability of Cost and Schedule Overrun for Program Managers

DTIC Science & Technology

2017-03-23

PUBLIC RELEASE; DISTRIBUTION UNLIMITED Using Multiple and Logistic Regression to Estimate the Median Will- Cost and Probability of Cost and... Cost and Probability of Cost and Schedule Overrun for Program Managers Ryan C. Trudelle Follow this and additional works at: https://scholar.afit.edu...afit.edu. Recommended Citation Trudelle, Ryan C., "Using Multiple and Logistic Regression to Estimate the Median Will- Cost and Probability of Cost and

Expression of Proteins Involved in Epithelial-Mesenchymal Transition as Predictors of Metastasis and Survival in Breast Cancer Patients

DTIC Science & Technology

2013-11-01

Ptrend 0.78 0.62 0.75 Unconditional logistic regression was used to estimate odds ratios (OR) and 95 % confidence intervals (CI) for risk of node...Ptrend 0.71 0.67 Unconditional logistic regression was used to estimate odds ratios (OR) and 95 % confidence intervals (CI) for risk of high-grade tumors... logistic regression was used to estimate odds ratios (OR) and 95 % confidence intervals (CI) for the associations between each of the seven SNPs and

Comparison of Xenon-Enhanced Area-Detector CT and Krypton Ventilation SPECT/CT for Assessment of Pulmonary Functional Loss and Disease Severity in Smokers.

PubMed

Ohno, Yoshiharu; Fujisawa, Yasuko; Takenaka, Daisuke; Kaminaga, Shigeo; Seki, Shinichiro; Sugihara, Naoki; Yoshikawa, Takeshi

2018-02-01

The objective of this study was to compare the capability of xenon-enhanced area-detector CT (ADCT) performed with a subtraction technique and coregistered 81m Kr-ventilation SPECT/CT for the assessment of pulmonary functional loss and disease severity in smokers. Forty-six consecutive smokers (32 men and 14 women; mean age, 67.0 years) underwent prospective unenhanced and xenon-enhanced ADCT, 81m Kr-ventilation SPECT/CT, and pulmonary function tests. Disease severity was evaluated according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification. CT-based functional lung volume (FLV), the percentage of wall area to total airway area (WA%), and ventilated FLV on xenon-enhanced ADCT and SPECT/CT were calculated for each smoker. All indexes were correlated with percentage of forced expiratory volume in 1 second (%FEV 1 ) using step-wise regression analyses, and univariate and multivariate logistic regression analyses were performed. In addition, the diagnostic accuracy of the proposed model was compared with that of each radiologic index by means of McNemar analysis. Multivariate logistic regression showed that %FEV 1 was significantly affected (r = 0.77, r 2 = 0.59) by two factors: the first factor, ventilated FLV on xenon-enhanced ADCT (p < 0.0001); and the second factor, WA% (p = 0.004). Univariate logistic regression analyses indicated that all indexes significantly affected GOLD classification (p < 0.05). Multivariate logistic regression analyses revealed that ventilated FLV on xenon-enhanced ADCT and CT-based FLV significantly influenced GOLD classification (p < 0.0001). The diagnostic accuracy of the proposed model was significantly higher than that of ventilated FLV on SPECT/CT (p = 0.03) and WA% (p = 0.008). Xenon-enhanced ADCT is more effective than 81m Kr-ventilation SPECT/CT for the assessment of pulmonary functional loss and disease severity.

An Attempt at Quantifying Factors that Affect Efficiency in the Management of Solid Waste Produced by Commercial Businesses in the City of Tshwane, South Africa

PubMed Central

Worku, Yohannes; Muchie, Mammo

2012-01-01

Objective. The objective was to investigate factors that affect the efficient management of solid waste produced by commercial businesses operating in the city of Pretoria, South Africa. Methods. Data was gathered from 1,034 businesses. Efficiency in solid waste management was assessed by using a structural time-based model designed for evaluating efficiency as a function of the length of time required to manage waste. Data analysis was performed using statistical procedures such as frequency tables, Pearson's chi-square tests of association, and binary logistic regression analysis. Odds ratios estimated from logistic regression analysis were used for identifying key factors that affect efficiency in the proper disposal of waste. Results. The study showed that 857 of the 1,034 businesses selected for the study (83%) were found to be efficient enough with regards to the proper collection and disposal of solid waste. Based on odds ratios estimated from binary logistic regression analysis, efficiency in the proper management of solid waste was significantly influenced by 4 predictor variables. These 4 influential predictor variables are lack of adherence to waste management regulations, wrong perception, failure to provide customers with enough trash cans, and operation of businesses by employed managers, in a decreasing order of importance. PMID:23209483

Registered dietitian's personal beliefs and characteristics predict their teaching or intention to teach fresh vegetable food safety.

PubMed

Casagrande, Gina; LeJeune, Jeffery; Belury, Martha A; Medeiros, Lydia C

2011-04-01

The Theory of Planned Behavior was used to determine if dietitians personal characteristics and beliefs about fresh vegetable food safety predict whether they currently teach, intend to teach, or neither currently teach nor intend to teach food safety information to their clients. Dietitians who participated in direct client education responded to this web-based survey (n=327). The survey evaluated three independent belief variables: Subjective Norm, Attitudes, and Perceived Behavioral Control. Spearman rho correlations were completed to determine variables that correlated best with current teaching behavior. Multinomial logistical regression was conducted to determine if the belief variables significantly predicted dietitians teaching behavior. Binary logistic regression was used to determine which independent variable was the better predictor of whether dietitians currently taught. Controlling for age, income, education, and gender, the multinomial logistical regression was significant. Perceived behavioral control was the best predictor of whether a dietitian currently taught fresh vegetable food safety. Factors affecting whether dietitians currently taught were confidence in fresh vegetable food safety knowledge, being socially influenced, and a positive attitude toward the teaching behavior. These results validate the importance of teaching food safety effectively and may be used to create more informed food safety curriculum for dietitians. Copyright © 2011 Elsevier Ltd. All rights reserved.

Logistic regression function for detection of suspicious performance during baseline evaluations using concussion vital signs.

PubMed

Hill, Benjamin David; Womble, Melissa N; Rohling, Martin L

2015-01-01

This study utilized logistic regression to determine whether performance patterns on Concussion Vital Signs (CVS) could differentiate known groups with either genuine or feigned performance. For the embedded measure development group (n = 174), clinical patients and undergraduate students categorized as feigning obtained significantly lower scores on the overall test battery mean for the CVS, Shipley-2 composite score, and California Verbal Learning Test-Second Edition subtests than did genuinely performing individuals. The final full model of 3 predictor variables (Verbal Memory immediate hits, Verbal Memory immediate correct passes, and Stroop Test complex reaction time correct) was significant and correctly classified individuals in their known group 83% of the time (sensitivity = .65; specificity = .97) in a mixed sample of young-adult clinical cases and simulators. The CVS logistic regression function was applied to a separate undergraduate college group (n = 378) that was asked to perform genuinely and identified 5% as having possibly feigned performance indicating a low false-positive rate. The failure rate was 11% and 16% at baseline cognitive testing in samples of high school and college athletes, respectively. These findings have particular relevance given the increasing use of computerized test batteries for baseline cognitive testing and return-to-play decisions after concussion.

Prevalence and risk factors of non-carious cervical lesions related to occupational exposure to acid mists.

PubMed

Bomfim, Rafael Aiello; Crosato, Edgard; Mazzilli, Luiz Eugênio Nigro; Frias, Antonio Carlos

2015-01-01

This study evaluates the prevalence and risk factors of non-carious cervical lesions (NCCLs) in a Brazilian population of workers exposed and non-exposed to acid mists and chemical products. One hundred workers (46 exposed and 54 non-exposed) were evaluated in a Centro de Referência em Saúde do Trabalhador - CEREST (Worker's Health Reference Center). The workers responded to questionnaires regarding their personal information and about alcohol consumption and tobacco use. A clinical examination was conducted to evaluate the presence of NCCLs, according to WHO parameters. Statistical analyses were performed by unconditional logistic regression and multiple linear regression, with the critical level of p < 0.05. NCCLs were significantly associated with age groups (18-34, 35-44, 45-68 years). The unconditional logistic regression showed that the presence of NCCLs was better explained by age group (OR = 4.04; CI 95% 1.77-9.22) and occupational exposure to acid mists and chemical products (OR = 3.84; CI 95% 1.10-13.49), whereas the linear multiple regression revealed that NCCLs were better explained by years of smoking (p = 0.01) and age group (p = 0.04). The prevalence of NCCLs in the study population was particularly high (76.84%), and the risk factors for NCCLs were age, exposure to acid mists and smoking habit. Controlling risk factors through preventive and educative measures, allied to the use of personal protective equipment to prevent the occupational exposure to acid mists, may contribute to minimizing the prevalence of NCCLs.

Comprehension of texts by deaf elementary school students: The role of grammatical understanding.

PubMed

Barajas, Carmen; González-Cuenca, Antonia M; Carrero, Francisco

2016-12-01

The aim of this study was to analyze how the reading process of deaf Spanish elementary school students is affected both by those components that explain reading comprehension according to the Simple View of Reading model: decoding and linguistic comprehension (both lexical and grammatical) and by other variables that are external to the reading process: the type of assistive technology used, the age at which it is implanted or fitted, the participant's socioeconomic status and school stage. Forty-seven students aged between 6 and 13 years participated in the study; all presented with profound or severe prelingual bilateral deafness, and all used digital hearing aids or cochlear implants. Students' text comprehension skills, decoding skills and oral comprehension skills (both lexical and grammatical) were evaluated. Logistic regression analysis indicated that neither the type of assistive technology, age at time of fitting or activation, socioeconomic status, nor school stage could predict the presence or absence of difficulties in text comprehension. Furthermore, logistic regression analysis indicated that neither decoding skills, nor lexical age could predict competency in text comprehension; however, grammatical age could explain 41% of the variance. Probing deeper into the effect of grammatical understanding, logistic regression analysis indicated that a participant's understanding of reversible passive object-verb-subject sentences and reversible predicative subject-verb-object sentences accounted for 38% of the variance in text comprehension. Based on these results, we suggest that it might be beneficial to devise and evaluate interventions that focus specifically on grammatical comprehension. Copyright © 2016 Elsevier Ltd. All rights reserved.

Use and interpretation of logistic regression in habitat-selection studies

USGS Publications Warehouse

Keating, Kim A.; Cherry, Steve

2004-01-01

 Logistic regression is an important tool for wildlife habitat-selection studies, but the method frequently has been misapplied due to an inadequate understanding of the logistic model, its interpretation, and the influence of sampling design. To promote better use of this method, we review its application and interpretation under 3 sampling designs: random, case-control, and use-availability. Logistic regression is appropriate for habitat use-nonuse studies employing random sampling and can be used to directly model the conditional probability of use in such cases. Logistic regression also is appropriate for studies employing case-control sampling designs, but careful attention is required to interpret results correctly. Unless bias can be estimated or probability of use is small for all habitats, results of case-control studies should be interpreted as odds ratios, rather than probability of use or relative probability of use. When data are gathered under a use-availability design, logistic regression can be used to estimate approximate odds ratios if probability of use is small, at least on average. More generally, however, logistic regression is inappropriate for modeling habitat selection in use-availability studies. In particular, using logistic regression to fit the exponential model of Manly et al. (2002:100) does not guarantee maximum-likelihood estimates, valid probabilities, or valid likelihoods. We show that the resource selection function (RSF) commonly used for the exponential model is proportional to a logistic discriminant function. Thus, it may be used to rank habitats with respect to probability of use and to identify important habitat characteristics or their surrogates, but it is not guaranteed to be proportional to probability of use. Other problems associated with the exponential model also are discussed. We describe an alternative model based on Lancaster and Imbens (1996) that offers a method for estimating conditional probability of use in use-availability studies. Although promising, this model fails to converge to a unique solution in some important situations. Further work is needed to obtain a robust method that is broadly applicable to use-availability studies.

Evaluating construct validity of the second version of the Copenhagen Psychosocial Questionnaire through analysis of differential item functioning and differential item effect.

PubMed

Bjorner, Jakob Bue; Pejtersen, Jan Hyld

2010-02-01

To evaluate the construct validity of the Copenhagen Psychosocial Questionnaire II (COPSOQ II) by means of tests for differential item functioning (DIF) and differential item effect (DIE). We used a Danish general population postal survey (n = 4,732 with 3,517 wage earners) with a one-year register based follow up for long-term sickness absence. DIF was evaluated against age, gender, education, social class, public/private sector employment, and job type using ordinal logistic regression. DIE was evaluated against job satisfaction and self-rated health (using ordinal logistic regression), against depressive symptoms, burnout, and stress (using multiple linear regression), and against long-term sick leave (using a proportional hazards model). We used a cross-validation approach to counter the risk of significant results due to multiple testing. Out of 1,052 tests, we found 599 significant instances of DIF/DIE, 69 of which showed both practical and statistical significance across two independent samples. Most DIF occurred for job type (in 20 cases), while we found little DIF for age, gender, education, social class and sector. DIE seemed to pertain to particular items, which showed DIE in the same direction for several outcome variables. The results allowed a preliminary identification of items that have a positive impact on construct validity and items that have negative impact on construct validity. These results can be used to develop better shortform measures and to improve the conceptual framework, items and scales of the COPSOQ II. We conclude that tests of DIF and DIE are useful for evaluating construct validity.

Evidence for Specificity of Motor Impairments in Catching and Balance in Children with Autism

ERIC Educational Resources Information Center

Ament, Katarina; Mejia, Amanda; Buhlman, Rebecca; Erklin, Shannon; Caffo, Brian; Mostofsky, Stewart; Wodka, Ericka

2015-01-01

To evaluate evidence for motor impairment specificity in autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD). Children completed performance-based assessment of motor functioning (Movement Assessment Battery for Children: MABC-2). Logistic regression models were used to predict group membership. In the models…

School-Related Factors Affecting High School Seniors' Methamphetamine Use

ERIC Educational Resources Information Center

Stanley, Jarrod M.; Lo, Celia C.

2009-01-01

Data from the 2005 Monitoring the Future survey were used to examine relationships between school-related factors and high school seniors' lifetime methamphetamine use. The study applied logistic regression techniques to evaluate effects of social bonding variables and social learning variables on likelihood of lifetime methamphetamine use. The…

A Comparison of Strategies for Estimating Conditional DIF

ERIC Educational Resources Information Center

Moses, Tim; Miao, Jing; Dorans, Neil J.

2010-01-01

In this study, the accuracies of four strategies were compared for estimating conditional differential item functioning (DIF), including raw data, logistic regression, log-linear models, and kernel smoothing. Real data simulations were used to evaluate the estimation strategies across six items, DIF and No DIF situations, and four sample size…

Association of sleep disturbances with cognitive impairment and depression in maintenance memodialysis patients

USDA-ARS?s Scientific Manuscript database

There are few data on the relationship of sleep with measures of cognitive function and symptoms of depression in dialysis patients. We evaluated the relationship of sleep with cognitive function and symptoms of depression in 168 hemodialysis patients, using multivariable linear and logistic regress...

EVALUATING THE ROLE OF HABITAT QUALITY ON ESTABLISHMENT OF GM AGROSTIS STOLONIFERA PLANTS IN NON-AGRONOMIC SETTINGS

EPA Science Inventory

We compared soil chemistry and plant community data at non-agronomic mesic locations that either did or did not contain genetically modified (GM) Agrostis stolonifera. The best two-variable logistic regression model included soil Mn content and A. stolonifera cover and explained...

Risk adjustment in the American College of Surgeons National Surgical Quality Improvement Program: a comparison of logistic versus hierarchical modeling.

PubMed

Cohen, Mark E; Dimick, Justin B; Bilimoria, Karl Y; Ko, Clifford Y; Richards, Karen; Hall, Bruce Lee

2009-12-01

Although logistic regression has commonly been used to adjust for risk differences in patient and case mix to permit quality comparisons across hospitals, hierarchical modeling has been advocated as the preferred methodology, because it accounts for clustering of patients within hospitals. It is unclear whether hierarchical models would yield important differences in quality assessments compared with logistic models when applied to American College of Surgeons (ACS) National Surgical Quality Improvement Program (NSQIP) data. Our objective was to evaluate differences in logistic versus hierarchical modeling for identifying hospitals with outlying outcomes in the ACS-NSQIP. Data from ACS-NSQIP patients who underwent colorectal operations in 2008 at hospitals that reported at least 100 operations were used to generate logistic and hierarchical prediction models for 30-day morbidity and mortality. Differences in risk-adjusted performance (ratio of observed-to-expected events) and outlier detections from the two models were compared. Logistic and hierarchical models identified the same 25 hospitals as morbidity outliers (14 low and 11 high outliers), but the hierarchical model identified 2 additional high outliers. Both models identified the same eight hospitals as mortality outliers (five low and three high outliers). The values of observed-to-expected events ratios and p values from the two models were highly correlated. Results were similar when data were permitted from hospitals providing < 100 patients. When applied to ACS-NSQIP data, logistic and hierarchical models provided nearly identical results with respect to identification of hospitals' observed-to-expected events ratio outliers. As hierarchical models are prone to implementation problems, logistic regression will remain an accurate and efficient method for performing risk adjustment of hospital quality comparisons.

Logistic regression models of factors influencing the location of bioenergy and biofuels plants

Treesearch

T.M. Young; R.L. Zaretzki; J.H. Perdue; F.M. Guess; X. Liu

2011-01-01

Logistic regression models were developed to identify significant factors that influence the location of existing wood-using bioenergy/biofuels plants and traditional wood-using facilities. Logistic models provided quantitative insight for variables influencing the location of woody biomass-using facilities. Availability of "thinnings to a basal area of 31.7m2/ha...

Discrete post-processing of total cloud cover ensemble forecasts

NASA Astrophysics Data System (ADS)

Hemri, Stephan; Haiden, Thomas; Pappenberger, Florian

2017-04-01

This contribution presents an approach to post-process ensemble forecasts for the discrete and bounded weather variable of total cloud cover. Two methods for discrete statistical post-processing of ensemble predictions are tested. The first approach is based on multinomial logistic regression, the second involves a proportional odds logistic regression model. Applying them to total cloud cover raw ensemble forecasts from the European Centre for Medium-Range Weather Forecasts improves forecast skill significantly. Based on station-wise post-processing of raw ensemble total cloud cover forecasts for a global set of 3330 stations over the period from 2007 to early 2014, the more parsimonious proportional odds logistic regression model proved to slightly outperform the multinomial logistic regression model. Reference Hemri, S., Haiden, T., & Pappenberger, F. (2016). Discrete post-processing of total cloud cover ensemble forecasts. Monthly Weather Review 144, 2565-2577.

A Primer on Logistic Regression.

ERIC Educational Resources Information Center

Woldbeck, Tanya

This paper introduces logistic regression as a viable alternative when the researcher is faced with variables that are not continuous. If one is to use simple regression, the dependent variable must be measured on a continuous scale. In the behavioral sciences, it may not always be appropriate or possible to have a measured dependent variable on a…

Exploring students' patterns of reasoning

NASA Astrophysics Data System (ADS)

Matloob Haghanikar, Mojgan

As part of a collaborative study of the science preparation of elementary school teachers, we investigated the quality of students' reasoning and explored the relationship between sophistication of reasoning and the degree to which the courses were considered inquiry oriented. To probe students' reasoning, we developed open-ended written content questions with the distinguishing feature of applying recently learned concepts in a new context. We devised a protocol for developing written content questions that provided a common structure for probing and classifying students' sophistication level of reasoning. In designing our protocol, we considered several distinct criteria, and classified students' responses based on their performance for each criterion. First, we classified concepts into three types: Descriptive, Hypothetical, and Theoretical and categorized the abstraction levels of the responses in terms of the types of concepts and the inter-relationship between the concepts. Second, we devised a rubric based on Bloom's revised taxonomy with seven traits (both knowledge types and cognitive processes) and a defined set of criteria to evaluate each trait. Along with analyzing students' reasoning, we visited universities and observed the courses in which the students were enrolled. We used the Reformed Teaching Observation Protocol (RTOP) to rank the courses with respect to characteristics that are valued for the inquiry courses. We conducted logistic regression for a sample of 18courses with about 900 students and reported the results for performing logistic regression to estimate the relationship between traits of reasoning and RTOP score. In addition, we analyzed conceptual structure of students' responses, based on conceptual classification schemes, and clustered students' responses into six categories. We derived regression model, to estimate the relationship between the sophistication of the categories of conceptual structure and RTOP scores. However, the outcome variable with six categories required a more complicated regression model, known as multinomial logistic regression, generalized from binary logistic regression. With the large amount of collected data, we found that the likelihood of the higher cognitive processes were in favor of classes with higher measures on inquiry. However, the usage of more abstract concepts with higher order conceptual structures was less prevalent in higher RTOP courses.

[Influences of environmental factors and interaction of several chemokines gene-environmental on systemic lupus erythematosus].

PubMed

Ye, Dong-qing; Hu, Yi-song; Li, Xiang-pei; Huang, Fen; Yang, Shi-gui; Hao, Jia-hu; Yin, Jing; Zhang, Guo-qing; Liu, Hui-hui

2004-11-01

To explore the impact of environmental factors, daily lifestyle, psycho-social factors and the interactions between environmental factors and chemokines genes on systemic lupus erythematosus (SLE). Case-control study was carried out and environmental factors for SLE were analyzed by univariate and multivariate unconditional logistic regression. Interactions between environmental factors and chemokines polymorphism contributing to systemic lupus erythematosus were also analyzed by logistic regression model. There were nineteen factors associated with SLE when univariate unconditional logistic regression was used. However, when multivariate unconditional logistic regression was used, only five factors showed having impacts on the disease, in which drinking well water (OR=0.099) was protective factor for SLE, and multiple drug allergy (OR=8.174), over-exposure to sunshine (OR=18.339), taking antibiotics (OR=9.630) and oral contraceptives were risk factors for SLE. When unconditional logistic regression model was used, results showed that there was interaction between eating irritable food and -2518MCP-1G/G genotype (OR=4.387). No interaction between environmental factors was found that contributing to SLE in this study. Many environmental factors were related to SLE, and there was an interaction between -2518MCP-1G/G genotype and eating irritable food.

A deeper look at two concepts of measuring gene-gene interactions: logistic regression and interaction information revisited.

PubMed

Mielniczuk, Jan; Teisseyre, Paweł

2018-03-01

Detection of gene-gene interactions is one of the most important challenges in genome-wide case-control studies. Besides traditional logistic regression analysis, recently the entropy-based methods attracted a significant attention. Among entropy-based methods, interaction information is one of the most promising measures having many desirable properties. Although both logistic regression and interaction information have been used in several genome-wide association studies, the relationship between them has not been thoroughly investigated theoretically. The present paper attempts to fill this gap. We show that although certain connections between the two methods exist, in general they refer two different concepts of dependence and looking for interactions in those two senses leads to different approaches to interaction detection. We introduce ordering between interaction measures and specify conditions for independent and dependent genes under which interaction information is more discriminative measure than logistic regression. Moreover, we show that for so-called perfect distributions those measures are equivalent. The numerical experiments illustrate the theoretical findings indicating that interaction information and its modified version are more universal tools for detecting various types of interaction than logistic regression and linkage disequilibrium measures. © 2017 WILEY PERIODICALS, INC.

Telehealth Stroke Dysphagia Evaluation Is Safe and Effective.

PubMed

Morrell, Kate; Hyers, Megan; Stuchiner, Tamela; Lucas, Lindsay; Schwartz, Karissa; Mako, Jenniffer; Spinelli, Kateri J; Yanase, Lisa

2017-01-01

Rapid evaluation of dysphagia poststroke significantly lowers rates of aspiration pneumonia. Logistical barriers often significantly delay in-person dysphagia evaluation by speech language pathologists (SLPs) in remote and rural hospitals. Clinical swallow evaluations delivered via telehealth have been validated in a number of clinical contexts, yet no one has specifically validated a teleswallow evaluation for in-hospital post-stroke dysphagia assessment. A team of 6 SLPs experienced in stroke care and a telestroke neurologist designed, implemented, and tested a teleswallow evaluation for acute stroke patients, in which 100 patients across 2 affiliated, urban certified stroke centers were sequentially evaluated by a bedside and telehealth SLP. Inter-rater reliability was analyzed using percent agreement, Cohen's kappa, Kendall's tau-b, and Wilcoxon matched-pairs signed rank tests. Logistic regression models accounting for age and gender were used to test the impact of stroke severity and stroke location on agreement. We found excellent agreement for both liquid (91% agreement; kappa = 0.808; Kendall's tau-b = 0.813, p < 0.001; Wilcoxon signed rank = -0.818, p = 0.417) and solid (87% agreement; kappa = 0.792; Kendall's tau-b = 0.844, p < 0.001; Wilcoxon signed rank = 0.243, p = 0.808) dietary textures. From regression modeling, there is suggestive but inconclusive evidence that higher National Institute of Health Stroke Scale (NIHSS) scores correlate with lower levels of agreement for liquid diet recommendations (OR [95% CI] 0.895 [0.793-1.01]; p = 0.07). There was no impact of NIHSS score for solid diet recommendations and no impact of stroke location on solid or liquid diet recommendations. Qualitatively, we identified professional, logistical, technical, and patient barriers to implementation, many of which resolved with experience over time. Dysphagia evaluation by a remote SLP via telehealth is safe and effective following stroke. We plan to implement teleswallow across our multistate telestroke network as standard practice for poststroke dysphagia evaluation. © 2017 S. Karger AG, Basel.

Controlling Type I Error Rates in Assessing DIF for Logistic Regression Method Combined with SIBTEST Regression Correction Procedure and DIF-Free-Then-DIF Strategy

ERIC Educational Resources Information Center

Shih, Ching-Lin; Liu, Tien-Hsiang; Wang, Wen-Chung

2014-01-01

The simultaneous item bias test (SIBTEST) method regression procedure and the differential item functioning (DIF)-free-then-DIF strategy are applied to the logistic regression (LR) method simultaneously in this study. These procedures are used to adjust the effects of matching true score on observed score and to better control the Type I error…

Biomarker combinations for diagnosis and prognosis in multicenter studies: Principles and methods.

PubMed

Meisner, Allison; Parikh, Chirag R; Kerr, Kathleen F

2017-01-01

Many investigators are interested in combining biomarkers to predict a binary outcome or detect underlying disease. This endeavor is complicated by the fact that many biomarker studies involve data from multiple centers. Depending upon the relationship between center, the biomarkers, and the target of prediction, care must be taken when constructing and evaluating combinations of biomarkers. We introduce a taxonomy to describe the role of center and consider how a biomarker combination should be constructed and evaluated. We show that ignoring center, which is frequently done by clinical researchers, is often not appropriate. The limited statistical literature proposes using random intercept logistic regression models, an approach that we demonstrate is generally inadequate and may be misleading. We instead propose using fixed intercept logistic regression, which appropriately accounts for center without relying on untenable assumptions. After constructing the biomarker combination, we recommend using performance measures that account for the multicenter nature of the data, namely the center-adjusted area under the receiver operating characteristic curve. We apply these methods to data from a multicenter study of acute kidney injury after cardiac surgery. Appropriately accounting for center, both in construction and evaluation, may increase the likelihood of identifying clinically useful biomarker combinations.

Initial depressive episodes affect the risk of suicide attempts in Korean patients with bipolar disorder.

PubMed

Ryu, Vin; Jon, Duk-In; Cho, Hyun Sang; Kim, Se Joo; Lee, Eun; Kim, Eun Joo; Seok, Jeong-Ho

2010-09-01

Suicide is a major concern for increasing mortality in bipolar patients, but risk factors for suicide in bipolar disorder remain complex, including Korean patients. Medical records of bipolar patients were retrospectively reviewed to detect significant clinical characteristics associated with suicide attempts. A total of 579 medical records were retrospectively reviewed. Bipolar patients were divided into two groups with the presence of a history of suicide attempts. We compared demographic characteristics and clinical features between the two groups using an analysis of covariance and chi-square tests. Finally, logistic regression was performed to evaluate significant risk factors associated with suicide attempts in bipolar disorder. The prevalence of suicide attempt was 13.1% in our patient group. The presence of a depressive first episode was significantly different between attempters and nonattempters. Logistic regression analysis revealed that depressive first episodes and bipolar II disorder were significantly associated with suicide attempts in those patients. Clinicians should consider the polarity of the first mood episode when evaluating suicide risk in bipolar patients. This study has some limitations as a retrospective study and further studies with a prospective design are needed to replicate and evaluate risk factors for suicide in patients with bipolar disorder.

Evaluating the Relationship between Productivity and Quality in Emergency Departments

PubMed Central

Bastian, Nathaniel D.; Riordan, John P.

2017-01-01

Background In the United States, emergency departments (EDs) are constantly pressured to improve operational efficiency and quality in order to gain financial benefits and maintain a positive reputation. Objectives The first objective is to evaluate how efficiently EDs transform their input resources into quality outputs. The second objective is to investigate the relationship between the efficiency and quality performance of EDs and the factors affecting this relationship. Methods Using two data sources, we develop a data envelopment analysis (DEA) model to evaluate the relative efficiency of EDs. Based on the DEA result, we performed multinomial logistic regression to investigate the relationship between ED efficiency and quality performance. Results The DEA results indicated that the main source of inefficiencies was working hours of technicians. The multinomial logistic regression result indicated that the number of electrocardiograms and X-ray procedures conducted in the ED and the length of stay were significantly associated with the trade-offs between relative efficiency and quality. Structural ED characteristics did not influence the relationship between efficiency and quality. Conclusions Depending on the structural and operational characteristics of EDs, different factors can affect the relationship between efficiency and quality. PMID:29065673

Access disparities to Magnet hospitals for patients undergoing neurosurgical operations

PubMed Central

Missios, Symeon; Bekelis, Kimon

2017-01-01

Background Centers of excellence focusing on quality improvement have demonstrated superior outcomes for a variety of surgical interventions. We investigated the presence of access disparities to hospitals recognized by the Magnet Recognition Program of the American Nurses Credentialing Center (ANCC) for patients undergoing neurosurgical operations. Methods We performed a cohort study of all neurosurgery patients who were registered in the New York Statewide Planning and Research Cooperative System (SPARCS) database from 2009–2013. We examined the association of African-American race and lack of insurance with Magnet status hospitalization for neurosurgical procedures. A mixed effects propensity adjusted multivariable regression analysis was used to control for confounding. Results During the study period, 190,535 neurosurgical patients met the inclusion criteria. Using a multivariable logistic regression, we demonstrate that African-Americans had lower admission rates to Magnet institutions (OR 0.62; 95% CI, 0.58–0.67). This persisted in a mixed effects logistic regression model (OR 0.77; 95% CI, 0.70–0.83) to adjust for clustering at the patient county level, and a propensity score adjusted logistic regression model (OR 0.75; 95% CI, 0.69–0.82). Additionally, lack of insurance was associated with lower admission rates to Magnet institutions (OR 0.71; 95% CI, 0.68–0.73), in a multivariable logistic regression model. This persisted in a mixed effects logistic regression model (OR 0.72; 95% CI, 0.69–0.74), and a propensity score adjusted logistic regression model (OR 0.72; 95% CI, 0.69–0.75). Conclusions Using a comprehensive all-payer cohort of neurosurgery patients in New York State we identified an association of African-American race and lack of insurance with lower rates of admission to Magnet hospitals. PMID:28684152

On the use and misuse of scalar scores of confounders in design and analysis of observational studies.

PubMed

Pfeiffer, R M; Riedl, R

2015-08-15

We assess the asymptotic bias of estimates of exposure effects conditional on covariates when summary scores of confounders, instead of the confounders themselves, are used to analyze observational data. First, we study regression models for cohort data that are adjusted for summary scores. Second, we derive the asymptotic bias for case-control studies when cases and controls are matched on a summary score, and then analyzed either using conditional logistic regression or by unconditional logistic regression adjusted for the summary score. Two scores, the propensity score (PS) and the disease risk score (DRS) are studied in detail. For cohort analysis, when regression models are adjusted for the PS, the estimated conditional treatment effect is unbiased only for linear models, or at the null for non-linear models. Adjustment of cohort data for DRS yields unbiased estimates only for linear regression; all other estimates of exposure effects are biased. Matching cases and controls on DRS and analyzing them using conditional logistic regression yields unbiased estimates of exposure effect, whereas adjusting for the DRS in unconditional logistic regression yields biased estimates, even under the null hypothesis of no association. Matching cases and controls on the PS yield unbiased estimates only under the null for both conditional and unconditional logistic regression, adjusted for the PS. We study the bias for various confounding scenarios and compare our asymptotic results with those from simulations with limited sample sizes. To create realistic correlations among multiple confounders, we also based simulations on a real dataset. Copyright © 2015 John Wiley & Sons, Ltd.

Subjective vs objective evaluations of smile esthetics.

PubMed

Schabel, Brian J; Franchi, Lorenzo; Baccetti, Tiziano; McNamara, James A

2009-04-01

The aim of this study was to analyze the relationships between subjective evaluations of posttreatment smiles captured with clinical photography and rated by a panel of orthodontists and parents of orthodontic patients, and objective evaluations of the same smiles from the Smile Mesh program (TDG Computing, Philadelphia, Pa). The clinical photographs of 48 orthodontically treated patients were rated by a panel of 25 experienced orthodontists and 20 parents of patients. Independent samples t tests were used to test whether objective measurements were significantly different between subjects with "attractive" and "unattractive" smiles, and those with the "most attractive" and "least attractive" smiles. Additionally, logistic regression was performed to evaluate whether the measurements could predict whether a smile captured with clinical photography would be attractive or unattractive. The comparison between groups showed no significant differences for any measurement. Subjects with the "most unattractive" smiles had a significantly greater distance between the incisal edge of the maxillary central incisors and the lower lip during smiling, and a significantly smaller smile index than did those with the "most attractive" smiles. As shown by the coefficients of logistic regression, smile attractiveness could not be predicted by any objectively gathered measurement. No objective measure of the smile could predict attractive or unattractive smiles as judged subjectively.

Work related complaints of neck, shoulder and arm among computer office workers: a cross-sectional evaluation of prevalence and risk factors in a developing country.

PubMed

Ranasinghe, Priyanga; Perera, Yashasvi S; Lamabadusuriya, Dilusha A; Kulatunga, Supun; Jayawardana, Naveen; Rajapakse, Senaka; Katulanda, Prasad

2011-08-04

Complaints of arms, neck and shoulders (CANS) is common among computer office workers. We evaluated an aetiological model with physical/psychosocial risk-factors. We invited 2,500 computer office workers for the study. Data on prevalence and risk-factors of CANS were collected by validated Maastricht-Upper-extremity-Questionnaire. Workstations were evaluated by Occupational Safety and Health Administration (OSHA) Visual-Display-Terminal workstation-checklist. Participants' knowledge and awareness was evaluated by a set of expert-validated questions. A binary logistic regression analysis investigated relationships/correlations between risk-factors and symptoms. Sample size was 2,210. Mean age 30.8 ± 8.1 years, 50.8% were males. The 1-year prevalence of CANS was 56.9%, commonest region of complaint was forearm/hand (42.6%), followed by neck (36.7%) and shoulder/arm (32.0%). In those with CANS, 22.7% had taken treatment from a health care professional, only in 1.1% seeking medical advice an occupation-related injury had been suspected/diagnosed. In addition 9.3% reported CANS-related absenteeism from work, while 15.4% reported CANS causing disruption of normal activities. A majority of evaluated workstations in all participants (88.4%,) and in those with CANS (91.9%) had OSHA non-compliant workstations. In the binary logistic regression analyses female gender, daily computer usage, incorrect body posture, bad work-habits, work overload, poor social support and poor ergonomic knowledge were associated with CANS and its' severity In a multiple logistic regression analysis controlling for age, gender and duration of occupation, incorrect body posture, bad work-habits and daily computer usage were significant independent predictors of CANS. The prevalence of work-related CANS among computer office workers in Sri Lanka, a developing, South Asian country is high and comparable to prevalence in developed countries. Work-related physical factors, psychosocial factors and lack of awareness were all important associations of CANS and effective preventive strategies need to address all three areas.

Does clinical pretest probability influence image quality and diagnostic accuracy in dual-source coronary CT angiography?

PubMed

Thomas, Christoph; Brodoefel, Harald; Tsiflikas, Ilias; Bruckner, Friederike; Reimann, Anja; Ketelsen, Dominik; Drosch, Tanja; Claussen, Claus D; Kopp, Andreas; Heuschmid, Martin; Burgstahler, Christof

2010-02-01

To prospectively evaluate the influence of the clinical pretest probability assessed by the Morise score onto image quality and diagnostic accuracy in coronary dual-source computed tomography angiography (DSCTA). In 61 patients, DSCTA and invasive coronary angiography were performed. Subjective image quality and accuracy for stenosis detection (>50%) of DSCTA with invasive coronary angiography as gold standard were evaluated. The influence of pretest probability onto image quality and accuracy was assessed by logistic regression and chi-square testing. Correlations of image quality and accuracy with the Morise score were determined using linear regression. Thirty-eight patients were categorized into the high, 21 into the intermediate, and 2 into the low probability group. Accuracies for the detection of significant stenoses were 0.94, 0.97, and 1.00, respectively. Logistic regressions and chi-square tests showed statistically significant correlations between Morise score and image quality (P < .0001 and P < .001) and accuracy (P = .0049 and P = .027). Linear regression revealed a cutoff Morise score for a good image quality of 16 and a cutoff for a barely diagnostic image quality beyond the upper Morise scale. Pretest probability is a weak predictor of image quality and diagnostic accuracy in coronary DSCTA. A sufficient image quality for diagnostic images can be reached with all pretest probabilities. Therefore, coronary DSCTA might be suitable also for patients with a high pretest probability. Copyright 2010 AUR. Published by Elsevier Inc. All rights reserved.

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

Evaluating Federal Information Technology Program Success Based on Earned Value Management

ERIC Educational Resources Information Center

Moy, Mae N.

2016-01-01

Despite the use of earned value management (EVM) techniques to track development progress, federal information (IT) software programs continue to fail by not meeting identified business requirements. The purpose of this logistic regression study was to examine, using IT software data from federal agencies from 2011 to 2014, whether a relationship…

The Effectiveness of Using a Multiple Gating Approach to Discriminate among ADHD Subtypes

ERIC Educational Resources Information Center

Simonsen, Brandi M.; Bullis, Michael D.

2007-01-01

This study explored the ability of Systematically Progressive Assessment (SPA), a multiple gating approach for assessing students with attention-deficit/hyperactivity disorder (ADHD), to discriminate between subtypes of ADHD. A total of 48 students with ADHD (ages 6-11) were evaluated with three "gates" of assessment. Logistic regression analysis…

Frequency and clinical predictors of coronary artery disease in chronic renal failure renal transplant candidates.

PubMed

de Albuquerque Seixas, Emerson; Carmello, Beatriz Leone; Kojima, Christiane Akemi; Contti, Mariana Moraes; Modeli de Andrade, Luiz Gustavo; Maiello, José Roberto; Almeida, Fernando Antonio; Martin, Luis Cuadrado

2015-05-01

Cardiovascular diseases are major causes of mortality in chronic renal failure patients before and after renal transplantation. Among them, coronary disease presents a particular risk; however, risk predictors have been used to diagnose coronary heart disease. This study evaluated the frequency and importance of clinical predictors of coronary artery disease in chronic renal failure patients undergoing dialysis who were renal transplant candidates, and assessed a previously developed scoring system. Coronary angiographies conducted between March 2008 and April 2013 from 99 candidates for renal transplantation from two transplant centers in São Paulo state were analyzed for associations between significant coronary artery diseases (≥70% stenosis in one or more epicardial coronary arteries or ≥50% in the left main coronary artery) and clinical parameters. Univariate logistic regression analysis identified diabetes, angina, and/or previous infarction, clinical peripheral arterial disease and dyslipidemia as predictors of coronary artery disease. Multiple logistic regression analysis identified only diabetes and angina and/or previous infarction as independent predictors. The results corroborate previous studies demonstrating the importance of these factors when selecting patients for coronary angiography in clinical pretransplant evaluation.

Seroprevalence and Risk Factors of Chlamydia abortus Infection in Tibetan Sheep in Gansu Province, Northwest China

PubMed Central

Qin, Si-Yuan; Yin, Ming-Yang; Cong, Wei; Zhou, Dong-Hui; Zhang, Xiao-Xuan; Zhao, Quan; Zhu, Xing-Quan; Zhou, Ji-Zhang; Qian, Ai-Dong

2014-01-01

Chlamydia abortus, an important pathogen in a variety of animals, is associated with abortion in sheep. In the present study, 1732 blood samples, collected from Tibetan sheep between June 2013 and April 2014, were examined by the indirect hemagglutination (IHA) test, aiming to evaluate the seroprevalence and risk factors of C. abortus infection in Tibetan sheep. 323 of 1732 (18.65%) samples were seropositive for C. abortus antibodies at the cut-off of 1 : 16. A multivariate logistic regression analysis was used to evaluate the risk factors associated with seroprevalence, which could provide foundation to prevent and control C. abortus infection in Tibetan sheep. Gender of Tibetan sheep was left out of the final model because it is not significant in the logistic regression analysis (P > 0.05). Region, season, and age were considered as major risk factors associated with C. abortus infection in Tibetan sheep. Our study revealed a widespread and high prevalence of C. abortus infection in Tibetan sheep in Gansu province, northwest China, with higher exposure risk in different seasons and ages and distinct geographical distribution. PMID:25401129

Evaluation of spectral domain optical coherence tomography parameters in ocular hypertension, preperimetric, and early glaucoma.

PubMed

Aydogan, Tuğba; Akçay, BetÜl İlkay Sezgin; Kardeş, Esra; Ergin, Ahmet

2017-11-01

The objective of this study is to evaluate the diagnostic ability of retinal nerve fiber layer (RNFL), macular, optic nerve head (ONH) parameters in healthy subjects, ocular hypertension (OHT), preperimetric glaucoma (PPG), and early glaucoma (EG) patients, to reveal factors affecting the diagnostic ability of spectral domain-optical coherence tomography (SD-OCT) parameters and risk factors for glaucoma. Three hundred and twenty-six eyes (89 healthy, 77 OHT, 94 PPG, and 66 EG eyes) were analyzed. RNFL, macular, and ONH parameters were measured with SD-OCT. The area under the receiver operating characteristic curve (AUC) and sensitivity at 95% specificity was calculated. Logistic regression analysis was used to determine the glaucoma risk factors. Receiver operating characteristic regression analysis was used to evaluate the influence of covariates on the diagnostic ability of parameters. In PPG patients, parameters that had the largest AUC value were average RNFL thickness (0.83) and rim volume (0.83). In EG patients, parameter that had the largest AUC value was average RNFL thickness (0.98). The logistic regression analysis showed average RNFL thickness was a risk factor for both PPG and EG. Diagnostic ability of average RNFL and average ganglion cell complex thickness increased as disease severity increased. Signal strength index did not affect diagnostic abilities. Diagnostic ability of average RNFL and rim area increased as disc area increased. When evaluating patients with glaucoma, patients at risk for glaucoma, and healthy controls RNFL parameters deserve more attention in clinical practice. Further studies are needed to fully understand the influence of covariates on the diagnostic ability of OCT parameters.

MODELING SNAKE MICROHABITAT FROM RADIOTELEMETRY STUDIES USING POLYTOMOUS LOGISTIC REGRESSION

EPA Science Inventory

Multivariate analysis of snake microhabitat has historically used techniques that were derived under assumptions of normality and common covariance structure (e.g., discriminant function analysis, MANOVA). In this study, polytomous logistic regression (PLR which does not require ...

Gene-environment interaction between adiponectin gene polymorphisms and environmental factors on the risk of diabetic retinopathy.

PubMed

Li, Yuan; Wu, Qun Hong; Jiao, Ming Li; Fan, Xiao Hong; Hu, Quan; Hao, Yan Hua; Liu, Ruo Hong; Zhang, Wei; Cui, Yu; Han, Li Yuan

2015-01-01

To evaluate whether the adiponectin gene is associated with diabetic retinopathy (DR) risk and interaction with environmental factors modifies the DR risk, and to investigate the relationship between serum adiponectin levels and DR. Four adiponectin polymorphisms were evaluated in 372 DR cases and 145 controls. Differences in environmental factors between cases and controls were evaluated by unconditional logistic regression analysis. The model-free multifactor dimensionality reduction method and traditional multiple regression models were applied to explore interactions between the polymorphisms and environmental factors. Using the Bonferroni method, we found no significant associations between four adiponectin polymorphisms and DR susceptibility. Multivariate logistic regression found that physical activity played a protective role in the progress of DR, whereas family history of diabetes (odds ratio 1.75) and insulin therapy (odds ratio 1.78) were associated with an increased risk for DR. The interaction between the C-11377 G (rs266729) polymorphism and insulin therapy might be associated with DR risk. Family history of diabetes combined with insulin therapy also increased the risk of DR. No adiponectin gene polymorphisms influenced the serum adiponectin levels. Serum adiponectin levels did not differ between the DR group and non-DR group. No significant association was identified between four adiponectin polymorphisms and DR susceptibility after stringent Bonferroni correction. The interaction between C-11377G (rs266729) polymorphism and insulin therapy, as well as the interaction between family history of diabetes and insulin therapy, might be associated with DR susceptibility.

Modification of the Mantel-Haenszel and Logistic Regression DIF Procedures to Incorporate the SIBTEST Regression Correction

ERIC Educational Resources Information Center

DeMars, Christine E.

2009-01-01

The Mantel-Haenszel (MH) and logistic regression (LR) differential item functioning (DIF) procedures have inflated Type I error rates when there are large mean group differences, short tests, and large sample sizes.When there are large group differences in mean score, groups matched on the observed number-correct score differ on true score,…

Satellite rainfall retrieval by logistic regression

NASA Technical Reports Server (NTRS)

Chiu, Long S.

1986-01-01

The potential use of logistic regression in rainfall estimation from satellite measurements is investigated. Satellite measurements provide covariate information in terms of radiances from different remote sensors.The logistic regression technique can effectively accommodate many covariates and test their significance in the estimation. The outcome from the logistical model is the probability that the rainrate of a satellite pixel is above a certain threshold. By varying the thresholds, a rainrate histogram can be obtained, from which the mean and the variant can be estimated. A logistical model is developed and applied to rainfall data collected during GATE, using as covariates the fractional rain area and a radiance measurement which is deduced from a microwave temperature-rainrate relation. It is demonstrated that the fractional rain area is an important covariate in the model, consistent with the use of the so-called Area Time Integral in estimating total rain volume in other studies. To calibrate the logistical model, simulated rain fields generated by rainfield models with prescribed parameters are needed. A stringent test of the logistical model is its ability to recover the prescribed parameters of simulated rain fields. A rain field simulation model which preserves the fractional rain area and lognormality of rainrates as found in GATE is developed. A stochastic regression model of branching and immigration whose solutions are lognormally distributed in some asymptotic limits has also been developed.

Successful treatment algorithm for evaluation of early pregnancy after in vitro fertilization.

PubMed

Cookingham, Lisa Marii; Goossen, Rachel P; Sparks, Amy E T; Van Voorhis, Bradley J; Duran, Eyup Hakan

2015-10-01

To evaluate a prospectively implemented clinical algorithm for early identification of ectopic pregnancy (EP) and heterotopic pregnancy (HP) after assisted reproductive technology (ART). Analysis of prospectively collected data. Academic medical center. All ART-conceived pregnancies between January 1995 and June 2013. Early pregnancy monitoring via clinical algorithm with all pregnancies screened using human chorionic gonadotropin (hCG) levels and reported symptoms, with subsequent early ultrasound evaluation if hCG levels were abnormal or if the patient reported pain or vaginal bleeding. Algorithmic efficiency for diagnosis of EP and HP and their subsequent clinical outcomes using a binary forward stepwise logistic regression model built to determine predictors of early pregnancy failure. Of the 3,904 pregnancies included, the incidence of EP and HP was 0.77% and 0.46%, respectively. The algorithm selected 96.7% and 83.3% of pregnancies diagnosed with EP and HP, respectively, for early ultrasound evaluation, leading to earlier treatment and resolution. Logistic regression revealed that first hCG, second hCG, hCG slope, age, pain, and vaginal bleeding were all independent predictors of early pregnancy failure after ART. Our clinical algorithm for early pregnancy evaluation after ART is effective for identification and prompt intervention of EP and HP without significant over- or misdiagnosis, and avoids the potential catastrophic morbidity associated with delayed diagnosis. Copyright © 2015 American Society for Reproductive Medicine. Published by Elsevier Inc. All rights reserved.

Relationship between Enterobius vermicularis and the incidence of acute appendicitis.

PubMed

Ramezani, Mohammad Arash; Dehghani, Mahmoud Reza

2007-01-01

The objective of this study was to evaluate the relationship between Enterobius vermicularis and the occurrence of acute appendicitis. Over a ten year period of time, all appendix specimens received by the department of pathology were reviewed for pathologic changes and the existence of E. vermicularis. Logistic regression was carried out to determine the odds ratio (OR) of the relationship between E. vermicularis and acute appendicitis. A total of 5048 specimens were reviewed. E. vermicularis was found in 144 (2.9%) cases. After separating by sex and adjusting for age logistic regression analysis showed the OR of E. vermicularis appendiceal infestation was 1.275 (95% CI = 0.42-3.9) for males and 1.678 (95% CI = 0.61-4.65) for females. Age was an independent risk factor for acute appendicitis in males (OR = 1.01, 95% CI = 1.003-1.017) and females (OR = 1.012, 95% CI = 1.005-1.02).

Mixture model-based clustering and logistic regression for automatic detection of microaneurysms in retinal images

NASA Astrophysics Data System (ADS)

Sánchez, Clara I.; Hornero, Roberto; Mayo, Agustín; García, María

2009-02-01

Diabetic Retinopathy is one of the leading causes of blindness and vision defects in developed countries. An early detection and diagnosis is crucial to avoid visual complication. Microaneurysms are the first ocular signs of the presence of this ocular disease. Their detection is of paramount importance for the development of a computer-aided diagnosis technique which permits a prompt diagnosis of the disease. However, the detection of microaneurysms in retinal images is a difficult task due to the wide variability that these images usually present in screening programs. We propose a statistical approach based on mixture model-based clustering and logistic regression which is robust to the changes in the appearance of retinal fundus images. The method is evaluated on the public database proposed by the Retinal Online Challenge in order to obtain an objective performance measure and to allow a comparative study with other proposed algorithms.

Odontological approach to sexual dimorphism in southeastern France.

PubMed

Lladeres, Emilie; Saliba-Serre, Bérengère; Sastre, Julien; Foti, Bruno; Tardivo, Delphine; Adalian, Pascal

2013-01-01

The aim of this study was to establish a prediction formula to allow for the determination of sex among the southeastern French population using dental measurements. The sample consisted of 105 individuals (57 males and 48 females, aged between 18 and 25 years). Dental measurements were calculated using Euclidean distances, in three-dimensional space, from point coordinates obtained by a Microscribe. A multiple logistic regression analysis was performed to establish the prediction formula. Among 12 selected dental distances, a stepwise logistic regression analysis highlighted the two most significant discriminate predictors of sex: one located at the mandible and the other at the maxilla. A cutpoint was proposed to prediction of true sex. The prediction formula was then tested on a validation sample (20 males and 34 females, aged between 18 and 62 years and with a history of orthodontics or restorative care) to evaluate the accuracy of the method. © 2012 American Academy of Forensic Sciences.

Automatic segmentation and classification of mycobacterium tuberculosis with conventional light microscopy

NASA Astrophysics Data System (ADS)

Xu, Chao; Zhou, Dongxiang; Zhai, Yongping; Liu, Yunhui

2015-12-01

This paper realizes the automatic segmentation and classification of Mycobacterium tuberculosis with conventional light microscopy. First, the candidate bacillus objects are segmented by the marker-based watershed transform. The markers are obtained by an adaptive threshold segmentation based on the adaptive scale Gaussian filter. The scale of the Gaussian filter is determined according to the color model of the bacillus objects. Then the candidate objects are extracted integrally after region merging and contaminations elimination. Second, the shape features of the bacillus objects are characterized by the Hu moments, compactness, eccentricity, and roughness, which are used to classify the single, touching and non-bacillus objects. We evaluated the logistic regression, random forest, and intersection kernel support vector machines classifiers in classifying the bacillus objects respectively. Experimental results demonstrate that the proposed method yields to high robustness and accuracy. The logistic regression classifier performs best with an accuracy of 91.68%.

Practical Session: Logistic Regression

NASA Astrophysics Data System (ADS)

Clausel, M.; Grégoire, G.

2014-12-01

An exercise is proposed to illustrate the logistic regression. One investigates the different risk factors in the apparition of coronary heart disease. It has been proposed in Chapter 5 of the book of D.G. Kleinbaum and M. Klein, "Logistic Regression", Statistics for Biology and Health, Springer Science Business Media, LLC (2010) and also by D. Chessel and A.B. Dufour in Lyon 1 (see Sect. 6 of http://pbil.univ-lyon1.fr/R/pdf/tdr341.pdf). This example is based on data given in the file evans.txt coming from http://www.sph.emory.edu/dkleinb/logreg3.htm#data.

Multinomial logistic regression modelling of obesity and overweight among primary school students in a rural area of Negeri Sembilan

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

Ghazali, Amirul Syafiq Mohd; Ali, Zalila; Noor, Norlida Mohd

Multinomial logistic regression is widely used to model the outcomes of a polytomous response variable, a categorical dependent variable with more than two categories. The model assumes that the conditional mean of the dependent categorical variables is the logistic function of an affine combination of predictor variables. Its procedure gives a number of logistic regression models that make specific comparisons of the response categories. When there are q categories of the response variable, the model consists of q-1 logit equations which are fitted simultaneously. The model is validated by variable selection procedures, tests of regression coefficients, a significant test ofmore » the overall model, goodness-of-fit measures, and validation of predicted probabilities using odds ratio. This study used the multinomial logistic regression model to investigate obesity and overweight among primary school students in a rural area on the basis of their demographic profiles, lifestyles and on the diet and food intake. The results indicated that obesity and overweight of students are related to gender, religion, sleep duration, time spent on electronic games, breakfast intake in a week, with whom meals are taken, protein intake, and also, the interaction between breakfast intake in a week with sleep duration, and the interaction between gender and protein intake.« less

Multinomial logistic regression modelling of obesity and overweight among primary school students in a rural area of Negeri Sembilan

NASA Astrophysics Data System (ADS)

Ghazali, Amirul Syafiq Mohd; Ali, Zalila; Noor, Norlida Mohd; Baharum, Adam

2015-10-01

Multinomial logistic regression is widely used to model the outcomes of a polytomous response variable, a categorical dependent variable with more than two categories. The model assumes that the conditional mean of the dependent categorical variables is the logistic function of an affine combination of predictor variables. Its procedure gives a number of logistic regression models that make specific comparisons of the response categories. When there are q categories of the response variable, the model consists of q-1 logit equations which are fitted simultaneously. The model is validated by variable selection procedures, tests of regression coefficients, a significant test of the overall model, goodness-of-fit measures, and validation of predicted probabilities using odds ratio. This study used the multinomial logistic regression model to investigate obesity and overweight among primary school students in a rural area on the basis of their demographic profiles, lifestyles and on the diet and food intake. The results indicated that obesity and overweight of students are related to gender, religion, sleep duration, time spent on electronic games, breakfast intake in a week, with whom meals are taken, protein intake, and also, the interaction between breakfast intake in a week with sleep duration, and the interaction between gender and protein intake.

The effect of service satisfaction and spiritual well-being on the quality of life of patients with schizophrenia.

PubMed

Lanfredi, Mariangela; Candini, Valentina; Buizza, Chiara; Ferrari, Clarissa; Boero, Maria E; Giobbio, Gian M; Goldschmidt, Nicoletta; Greppo, Stefania; Iozzino, Laura; Maggi, Paolo; Melegari, Anna; Pasqualetti, Patrizio; Rossi, Giuseppe; de Girolamo, Giovanni

2014-05-15

Quality of life (QOL) has been considered an important outcome measure in psychiatric research and determinants of QOL have been widely investigated. We aimed at detecting predictors of QOL at baseline and at testing the longitudinal interrelations of the baseline predictors with QOL scores at a 1-year follow-up in a sample of patients living in Residential Facilities (RFs). Logistic regression models were adopted to evaluate the association between WHOQoL-Bref scores and potential determinants of QOL. In addition, all variables significantly associated with QOL domains in the final logistic regression model were included by using the Structural Equation Modeling (SEM). We included 139 patients with a diagnosis of schizophrenia spectrum. In the final logistic regression model level of activity, social support, age, service satisfaction, spiritual well-being and symptoms' severity were identified as predictors of QOL scores at baseline. Longitudinal analyses carried out by SEM showed that 40% of QOL follow-up variability was explained by QOL at baseline, and significant indirect effects toward QOL at follow-up were found for satisfaction with services and for social support. Rehabilitation plans for people with schizophrenia living in RFs should also consider mediators of change in subjective QOL such as satisfaction with mental health services. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Genetic variation of the androgen receptor and risk of myocardial infarction and ischemic stroke in women.

PubMed

Rexrode, Kathryn M; Ridker, Paul M; Hegener, Hillary H; Buring, Julie E; Manson, JoAnn E; Zee, Robert Y L

2008-05-01

Androgen receptors (AR) are expressed in endothelial cells and vascular smooth-muscle cells. Some studies suggest an association between AR gene variation and risk of cardiovascular disease (CVD) in men; however, the relationship has not been examined in women. Six haplotype block-tagging single nucleotide polymorphisms (rs962458, rs6152, rs1204038, rs2361634, rs1337080, rs1337082), as well as the cysteine, adenine, guanine (CAG) microsatellite in exon 1, of the AR gene were evaluated among 300 white postmenopausal women who developed CVD (158 myocardial infarctions and 142 ischemic strokes) and an equal number of matched controls within the Women's Health Study. Genotype distributions were similar between cases and controls, and genotypes were not significantly related to risk of CVD, myocardial infarctions or ischemic stroke in conditional logistic regression models. Seven common haplotypes were observed, but distributions did not differ between cases and controls nor were significant associations observed in logistic regression analysis. The median CAG repeat length was 21. In conditional logistic regression, there was no association between the number of alleles with CAG repeat length >or=21 (or >or=22) and risk of CVD, myocardial infarctions or ischemic stroke. No association between AR genetic variation, as measured by haplotype-tagging single nucleotide polymorphisms and CAG repeat number, and risk of CVD was observed in women.

Effects of Sleep Quality on the Association between Problematic Mobile Phone Use and Mental Health Symptoms in Chinese College Students.

PubMed

Tao, Shuman; Wu, Xiaoyan; Zhang, Yukun; Zhang, Shichen; Tong, Shilu; Tao, Fangbiao

2017-02-14

Problematic mobile phone use (PMPU) is a risk factor for both adolescents' sleep quality and mental health. It is important to examine the potential negative health effects of PMPU exposure. This study aims to evaluate PMPU and its association with mental health in Chinese college students. Furthermore, we investigated how sleep quality influences this association. In 2013, we collected data regarding participants' PMPU, sleep quality, and mental health (psychopathological symptoms, anxiety, and depressive symptoms) by standardized questionnaires in 4747 college students. Multivariate logistic regression analysis was applied to assess independent effects and interactions of PMPU and sleep quality with mental health. PMPU and poor sleep quality were observed in 28.2% and 9.8% of participants, respectively. Adjusted logistic regression models suggested independent associations of PMPU and sleep quality with mental health ( p < 0.001). Further regression analyses suggested a significant interaction between these measures ( p < 0.001). The study highlights that poor sleep quality may play a more significant role in increasing the risk of mental health problems in students with PMPU than in those without PMPU.

Support vector machine learning model for the prediction of sentinel node status in patients with cutaneous melanoma.

PubMed

Mocellin, Simone; Ambrosi, Alessandro; Montesco, Maria Cristina; Foletto, Mirto; Zavagno, Giorgio; Nitti, Donato; Lise, Mario; Rossi, Carlo Riccardo

2006-08-01

Currently, approximately 80% of melanoma patients undergoing sentinel node biopsy (SNB) have negative sentinel lymph nodes (SLNs), and no prediction system is reliable enough to be implemented in the clinical setting to reduce the number of SNB procedures. In this study, the predictive power of support vector machine (SVM)-based statistical analysis was tested. The clinical records of 246 patients who underwent SNB at our institution were used for this analysis. The following clinicopathologic variables were considered: the patient's age and sex and the tumor's histological subtype, Breslow thickness, Clark level, ulceration, mitotic index, lymphocyte infiltration, regression, angiolymphatic invasion, microsatellitosis, and growth phase. The results of SVM-based prediction of SLN status were compared with those achieved with logistic regression. The SLN positivity rate was 22% (52 of 234). When the accuracy was > or = 80%, the negative predictive value, positive predictive value, specificity, and sensitivity were 98%, 54%, 94%, and 77% and 82%, 41%, 69%, and 93% by using SVM and logistic regression, respectively. Moreover, SVM and logistic regression were associated with a diagnostic error and an SNB percentage reduction of (1) 1% and 60% and (2) 15% and 73%, respectively. The results from this pilot study suggest that SVM-based prediction of SLN status might be evaluated as a prognostic method to avoid the SNB procedure in 60% of patients currently eligible, with a very low error rate. If validated in larger series, this strategy would lead to obvious advantages in terms of both patient quality of life and costs for the health care system.

A comparison of rule-based and machine learning approaches for classifying patient portal messages.

PubMed

Cronin, Robert M; Fabbri, Daniel; Denny, Joshua C; Rosenbloom, S Trent; Jackson, Gretchen Purcell

2017-09-01

Secure messaging through patient portals is an increasingly popular way that consumers interact with healthcare providers. The increasing burden of secure messaging can affect clinic staffing and workflows. Manual management of portal messages is costly and time consuming. Automated classification of portal messages could potentially expedite message triage and delivery of care. We developed automated patient portal message classifiers with rule-based and machine learning techniques using bag of words and natural language processing (NLP) approaches. To evaluate classifier performance, we used a gold standard of 3253 portal messages manually categorized using a taxonomy of communication types (i.e., main categories of informational, medical, logistical, social, and other communications, and subcategories including prescriptions, appointments, problems, tests, follow-up, contact information, and acknowledgement). We evaluated our classifiers' accuracies in identifying individual communication types within portal messages with area under the receiver-operator curve (AUC). Portal messages often contain more than one type of communication. To predict all communication types within single messages, we used the Jaccard Index. We extracted the variables of importance for the random forest classifiers. The best performing approaches to classification for the major communication types were: logistic regression for medical communications (AUC: 0.899); basic (rule-based) for informational communications (AUC: 0.842); and random forests for social communications and logistical communications (AUCs: 0.875 and 0.925, respectively). The best performing classification approach of classifiers for individual communication subtypes was random forests for Logistical-Contact Information (AUC: 0.963). The Jaccard Indices by approach were: basic classifier, Jaccard Index: 0.674; Naïve Bayes, Jaccard Index: 0.799; random forests, Jaccard Index: 0.859; and logistic regression, Jaccard Index: 0.861. For medical communications, the most predictive variables were NLP concepts (e.g., Temporal_Concept, which maps to 'morning', 'evening' and Idea_or_Concept which maps to 'appointment' and 'refill'). For logistical communications, the most predictive variables contained similar numbers of NLP variables and words (e.g., Telephone mapping to 'phone', 'insurance'). For social and informational communications, the most predictive variables were words (e.g., social: 'thanks', 'much', informational: 'question', 'mean'). This study applies automated classification methods to the content of patient portal messages and evaluates the application of NLP techniques on consumer communications in patient portal messages. We demonstrated that random forest and logistic regression approaches accurately classified the content of portal messages, although the best approach to classification varied by communication type. Words were the most predictive variables for classification of most communication types, although NLP variables were most predictive for medical communication types. As adoption of patient portals increases, automated techniques could assist in understanding and managing growing volumes of messages. Further work is needed to improve classification performance to potentially support message triage and answering. Copyright © 2017 Elsevier B.V. All rights reserved.

A simple approach to power and sample size calculations in logistic regression and Cox regression models.

PubMed

Vaeth, Michael; Skovlund, Eva

2004-06-15

For a given regression problem it is possible to identify a suitably defined equivalent two-sample problem such that the power or sample size obtained for the two-sample problem also applies to the regression problem. For a standard linear regression model the equivalent two-sample problem is easily identified, but for generalized linear models and for Cox regression models the situation is more complicated. An approximately equivalent two-sample problem may, however, also be identified here. In particular, we show that for logistic regression and Cox regression models the equivalent two-sample problem is obtained by selecting two equally sized samples for which the parameters differ by a value equal to the slope times twice the standard deviation of the independent variable and further requiring that the overall expected number of events is unchanged. In a simulation study we examine the validity of this approach to power calculations in logistic regression and Cox regression models. Several different covariate distributions are considered for selected values of the overall response probability and a range of alternatives. For the Cox regression model we consider both constant and non-constant hazard rates. The results show that in general the approach is remarkably accurate even in relatively small samples. Some discrepancies are, however, found in small samples with few events and a highly skewed covariate distribution. Comparison with results based on alternative methods for logistic regression models with a single continuous covariate indicates that the proposed method is at least as good as its competitors. The method is easy to implement and therefore provides a simple way to extend the range of problems that can be covered by the usual formulas for power and sample size determination. Copyright 2004 John Wiley & Sons, Ltd.

Robust logistic regression to narrow down the winner's curse for rare and recessive susceptibility variants.

PubMed

Kesselmeier, Miriam; Lorenzo Bermejo, Justo

2017-11-01

Logistic regression is the most common technique used for genetic case-control association studies. A disadvantage of standard maximum likelihood estimators of the genotype relative risk (GRR) is their strong dependence on outlier subjects, for example, patients diagnosed at unusually young age. Robust methods are available to constrain outlier influence, but they are scarcely used in genetic studies. This article provides a non-intimidating introduction to robust logistic regression, and investigates its benefits and limitations in genetic association studies. We applied the bounded Huber and extended the R package 'robustbase' with the re-descending Hampel functions to down-weight outlier influence. Computer simulations were carried out to assess the type I error rate, mean squared error (MSE) and statistical power according to major characteristics of the genetic study and investigated markers. Simulations were complemented with the analysis of real data. Both standard and robust estimation controlled type I error rates. Standard logistic regression showed the highest power but standard GRR estimates also showed the largest bias and MSE, in particular for associated rare and recessive variants. For illustration, a recessive variant with a true GRR=6.32 and a minor allele frequency=0.05 investigated in a 1000 case/1000 control study by standard logistic regression resulted in power=0.60 and MSE=16.5. The corresponding figures for Huber-based estimation were power=0.51 and MSE=0.53. Overall, Hampel- and Huber-based GRR estimates did not differ much. Robust logistic regression may represent a valuable alternative to standard maximum likelihood estimation when the focus lies on risk prediction rather than identification of susceptibility variants. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Sperm Retrieval in Patients with Klinefelter Syndrome: A Skewed Regression Model Analysis.

PubMed

Chehrazi, Mohammad; Rahimiforoushani, Abbas; Sabbaghian, Marjan; Nourijelyani, Keramat; Sadighi Gilani, Mohammad Ali; Hoseini, Mostafa; Vesali, Samira; Yaseri, Mehdi; Alizadeh, Ahad; Mohammad, Kazem; Samani, Reza Omani

2017-01-01

The most common chromosomal abnormality due to non-obstructive azoospermia (NOA) is Klinefelter syndrome (KS) which occurs in 1-1.72 out of 500-1000 male infants. The probability of retrieving sperm as the outcome could be asymmetrically different between patients with and without KS, therefore logistic regression analysis is not a well-qualified test for this type of data. This study has been designed to evaluate skewed regression model analysis for data collected from microsurgical testicular sperm extraction (micro-TESE) among azoospermic patients with and without non-mosaic KS syndrome. This cohort study compared the micro-TESE outcome between 134 men with classic KS and 537 men with NOA and normal karyotype who were referred to Royan Institute between 2009 and 2011. In addition to our main outcome, which was sperm retrieval, we also used logistic and skewed regression analyses to compare the following demographic and hormonal factors: age, level of follicle stimulating hormone (FSH), luteinizing hormone (LH), and testosterone between the two groups. A comparison of the micro-TESE between the KS and control groups showed a success rate of 28.4% (38/134) for the KS group and 22.2% (119/537) for the control group. In the KS group, a significantly difference (P<0.001) existed between testosterone levels for the successful sperm retrieval group (3.4 ± 0.48 mg/mL) compared to the unsuccessful sperm retrieval group (2.33 ± 0.23 mg/mL). The index for quasi Akaike information criterion (QAIC) had a goodness of fit of 74 for the skewed model which was lower than logistic regression (QAIC=85). According to the results, skewed regression is more efficient in estimating sperm retrieval success when the data from patients with KS are analyzed. This finding should be investigated by conducting additional studies with different data structures.

A secure distributed logistic regression protocol for the detection of rare adverse drug events

PubMed Central

El Emam, Khaled; Samet, Saeed; Arbuckle, Luk; Tamblyn, Robyn; Earle, Craig; Kantarcioglu, Murat

2013-01-01

Background There is limited capacity to assess the comparative risks of medications after they enter the market. For rare adverse events, the pooling of data from multiple sources is necessary to have the power and sufficient population heterogeneity to detect differences in safety and effectiveness in genetic, ethnic and clinically defined subpopulations. However, combining datasets from different data custodians or jurisdictions to perform an analysis on the pooled data creates significant privacy concerns that would need to be addressed. Existing protocols for addressing these concerns can result in reduced analysis accuracy and can allow sensitive information to leak. Objective To develop a secure distributed multi-party computation protocol for logistic regression that provides strong privacy guarantees. Methods We developed a secure distributed logistic regression protocol using a single analysis center with multiple sites providing data. A theoretical security analysis demonstrates that the protocol is robust to plausible collusion attacks and does not allow the parties to gain new information from the data that are exchanged among them. The computational performance and accuracy of the protocol were evaluated on simulated datasets. Results The computational performance scales linearly as the dataset sizes increase. The addition of sites results in an exponential growth in computation time. However, for up to five sites, the time is still short and would not affect practical applications. The model parameters are the same as the results on pooled raw data analyzed in SAS, demonstrating high model accuracy. Conclusion The proposed protocol and prototype system would allow the development of logistic regression models in a secure manner without requiring the sharing of personal health information. This can alleviate one of the key barriers to the establishment of large-scale post-marketing surveillance programs. We extended the secure protocol to account for correlations among patients within sites through generalized estimating equations, and to accommodate other link functions by extending it to generalized linear models. PMID:22871397

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 secure distributed logistic regression protocol for the detection of rare adverse drug events.

PubMed

El Emam, Khaled; Samet, Saeed; Arbuckle, Luk; Tamblyn, Robyn; Earle, Craig; Kantarcioglu, Murat

2013-05-01

There is limited capacity to assess the comparative risks of medications after they enter the market. For rare adverse events, the pooling of data from multiple sources is necessary to have the power and sufficient population heterogeneity to detect differences in safety and effectiveness in genetic, ethnic and clinically defined subpopulations. However, combining datasets from different data custodians or jurisdictions to perform an analysis on the pooled data creates significant privacy concerns that would need to be addressed. Existing protocols for addressing these concerns can result in reduced analysis accuracy and can allow sensitive information to leak. To develop a secure distributed multi-party computation protocol for logistic regression that provides strong privacy guarantees. We developed a secure distributed logistic regression protocol using a single analysis center with multiple sites providing data. A theoretical security analysis demonstrates that the protocol is robust to plausible collusion attacks and does not allow the parties to gain new information from the data that are exchanged among them. The computational performance and accuracy of the protocol were evaluated on simulated datasets. The computational performance scales linearly as the dataset sizes increase. The addition of sites results in an exponential growth in computation time. However, for up to five sites, the time is still short and would not affect practical applications. The model parameters are the same as the results on pooled raw data analyzed in SAS, demonstrating high model accuracy. The proposed protocol and prototype system would allow the development of logistic regression models in a secure manner without requiring the sharing of personal health information. This can alleviate one of the key barriers to the establishment of large-scale post-marketing surveillance programs. We extended the secure protocol to account for correlations among patients within sites through generalized estimating equations, and to accommodate other link functions by extending it to generalized linear models.

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.

Lack of Correlation between Metallic Elements Analyzed in Hair by ICP-MS and Autism

ERIC Educational Resources Information Center

De Palma, Giuseppe; Catalani, Simona; Franco, Anna; Brighenti, Maurizio; Apostoli, Pietro

2012-01-01

A cross-sectional case-control study was carried out to evaluate the concentrations of metallic elements in the hair of 44 children with diagnosis of autism and 61 age-balanced controls. Unadjusted comparisons showed higher concentrations of molybdenum, lithium and selenium in autistic children. Logistic regression analysis confirmed the role of…

A comparison of two modeling approaches for evaluating wildlife--habitat relationships

Treesearch

Ryan A. Long; Jonathan D. Muir; Janet L. Rachlow; John G. Kie

2009-01-01

Studies of resource selection form the basis for much of our understanding of wildlife habitat requirements, and resource selection functions (RSFs), which predict relative probability of use, have been proposed as a unifying concept for analysis and interpretation of wildlife habitat data. Logistic regression that contrasts used and available or unused resource units...

Articulation of Cut Scores in the Context of the Next-Generation Assessments. Research Report. ETS RR-17-34

ERIC Educational Resources Information Center

Kannan, Priya; Sgammato, Adrienne

2017-01-01

Logistic regression (LR)-based methods have become increasingly popular for predicting and articulating cut scores. However, the precision of predictive relationships is largely dependent on the underlying correlations between the predictor and the criterion. In two simulation studies, we evaluated the impact of varying the underlying grade-level…

Factors Associated with Recruitment and Screening in the Treatment for Adolescents with Depression Study (TADS)

ERIC Educational Resources Information Center

May, Diane E.; Hallin, Mary J.; Kratochvil, Christopher J.; Puumala, Susan E.; Smith, Lynette S.; Reinecke, Mark A.; Silva, Susan G.; Weller, Elizabeth B.; Vitiello, Benedetto; Breland-Noble, Alfiee; March, John S.

2007-01-01

Objective: To examine factors associated with eligibility and randomization and consider the efficiency of recruitment methods. Method: Adolescents, ages 12 to 17 years, were telephone screened (N = 2,804) followed by in-person evaluation (N = 1,088) for the Treatment for Adolescents With Depression Study. Separate logistic regression models,…

Nonconvex Sparse Logistic Regression With Weakly Convex Regularization

NASA Astrophysics Data System (ADS)

Shen, Xinyue; Gu, Yuantao

2018-06-01

In this work we propose to fit a sparse logistic regression model by a weakly convex regularized nonconvex optimization problem. The idea is based on the finding that a weakly convex function as an approximation of the $\\ell_0$ pseudo norm is able to better induce sparsity than the commonly used $\\ell_1$ norm. For a class of weakly convex sparsity inducing functions, we prove the nonconvexity of the corresponding sparse logistic regression problem, and study its local optimality conditions and the choice of the regularization parameter to exclude trivial solutions. Despite the nonconvexity, a method based on proximal gradient descent is used to solve the general weakly convex sparse logistic regression, and its convergence behavior is studied theoretically. Then the general framework is applied to a specific weakly convex function, and a necessary and sufficient local optimality condition is provided. The solution method is instantiated in this case as an iterative firm-shrinkage algorithm, and its effectiveness is demonstrated in numerical experiments by both randomly generated and real datasets.

A comparative study on entrepreneurial attitudes modeled with logistic regression and Bayes nets.

PubMed

López Puga, Jorge; García García, Juan

2012-11-01

Entrepreneurship research is receiving increasing attention in our context, as entrepreneurs are key social agents involved in economic development. We compare the success of the dichotomic logistic regression model and the Bayes simple classifier to predict entrepreneurship, after manipulating the percentage of missing data and the level of categorization in predictors. A sample of undergraduate university students (N = 1230) completed five scales (motivation, attitude towards business creation, obstacles, deficiencies, and training needs) and we found that each of them predicted different aspects of the tendency to business creation. Additionally, our results show that the receiver operating characteristic (ROC) curve is affected by the rate of missing data in both techniques, but logistic regression seems to be more vulnerable when faced with missing data, whereas Bayes nets underperform slightly when categorization has been manipulated. Our study sheds light on the potential entrepreneur profile and we propose to use Bayesian networks as an additional alternative to overcome the weaknesses of logistic regression when missing data are present in applied research.

Stepwise Distributed Open Innovation Contests for Software Development: Acceleration of Genome-Wide Association Analysis

PubMed Central

Hill, Andrew; Loh, Po-Ru; Bharadwaj, Ragu B.; Pons, Pascal; Shang, Jingbo; Guinan, Eva; Lakhani, Karim; Kilty, Iain

2017-01-01

Abstract Background: The association of differing genotypes with disease-related phenotypic traits offers great potential to both help identify new therapeutic targets and support stratification of patients who would gain the greatest benefit from specific drug classes. Development of low-cost genotyping and sequencing has made collecting large-scale genotyping data routine in population and therapeutic intervention studies. In addition, a range of new technologies is being used to capture numerous new and complex phenotypic descriptors. As a result, genotype and phenotype datasets have grown exponentially. Genome-wide association studies associate genotypes and phenotypes using methods such as logistic regression. As existing tools for association analysis limit the efficiency by which value can be extracted from increasing volumes of data, there is a pressing need for new software tools that can accelerate association analyses on large genotype-phenotype datasets. Results: Using open innovation (OI) and contest-based crowdsourcing, the logistic regression analysis in a leading, community-standard genetics software package (PLINK 1.07) was substantially accelerated. OI allowed us to do this in <6 months by providing rapid access to highly skilled programmers with specialized, difficult-to-find skill sets. Through a crowd-based contest a combination of computational, numeric, and algorithmic approaches was identified that accelerated the logistic regression in PLINK 1.07 by 18- to 45-fold. Combining contest-derived logistic regression code with coarse-grained parallelization, multithreading, and associated changes to data initialization code further developed through distributed innovation, we achieved an end-to-end speedup of 591-fold for a data set size of 6678 subjects by 645 863 variants, compared to PLINK 1.07's logistic regression. This represents a reduction in run time from 4.8 hours to 29 seconds. Accelerated logistic regression code developed in this project has been incorporated into the PLINK2 project. Conclusions: Using iterative competition-based OI, we have developed a new, faster implementation of logistic regression for genome-wide association studies analysis. We present lessons learned and recommendations on running a successful OI process for bioinformatics. PMID:28327993

Stepwise Distributed Open Innovation Contests for Software Development: Acceleration of Genome-Wide Association Analysis.

PubMed

Hill, Andrew; Loh, Po-Ru; Bharadwaj, Ragu B; Pons, Pascal; Shang, Jingbo; Guinan, Eva; Lakhani, Karim; Kilty, Iain; Jelinsky, Scott A

2017-05-01

The association of differing genotypes with disease-related phenotypic traits offers great potential to both help identify new therapeutic targets and support stratification of patients who would gain the greatest benefit from specific drug classes. Development of low-cost genotyping and sequencing has made collecting large-scale genotyping data routine in population and therapeutic intervention studies. In addition, a range of new technologies is being used to capture numerous new and complex phenotypic descriptors. As a result, genotype and phenotype datasets have grown exponentially. Genome-wide association studies associate genotypes and phenotypes using methods such as logistic regression. As existing tools for association analysis limit the efficiency by which value can be extracted from increasing volumes of data, there is a pressing need for new software tools that can accelerate association analyses on large genotype-phenotype datasets. Using open innovation (OI) and contest-based crowdsourcing, the logistic regression analysis in a leading, community-standard genetics software package (PLINK 1.07) was substantially accelerated. OI allowed us to do this in <6 months by providing rapid access to highly skilled programmers with specialized, difficult-to-find skill sets. Through a crowd-based contest a combination of computational, numeric, and algorithmic approaches was identified that accelerated the logistic regression in PLINK 1.07 by 18- to 45-fold. Combining contest-derived logistic regression code with coarse-grained parallelization, multithreading, and associated changes to data initialization code further developed through distributed innovation, we achieved an end-to-end speedup of 591-fold for a data set size of 6678 subjects by 645 863 variants, compared to PLINK 1.07's logistic regression. This represents a reduction in run time from 4.8 hours to 29 seconds. Accelerated logistic regression code developed in this project has been incorporated into the PLINK2 project. Using iterative competition-based OI, we have developed a new, faster implementation of logistic regression for genome-wide association studies analysis. We present lessons learned and recommendations on running a successful OI process for bioinformatics. © The Author 2017. Published by Oxford University Press.

Easy and low-cost identification of metabolic syndrome in patients treated with second-generation antipsychotics: artificial neural network and logistic regression models.

PubMed

Lin, Chao-Cheng; Bai, Ya-Mei; Chen, Jen-Yeu; Hwang, Tzung-Jeng; Chen, Tzu-Ting; Chiu, Hung-Wen; Li, Yu-Chuan

2010-03-01

Metabolic syndrome (MetS) is an important side effect of second-generation antipsychotics (SGAs). However, many SGA-treated patients with MetS remain undetected. In this study, we trained and validated artificial neural network (ANN) and multiple logistic regression models without biochemical parameters to rapidly identify MetS in patients with SGA treatment. A total of 383 patients with a diagnosis of schizophrenia or schizoaffective disorder (DSM-IV criteria) with SGA treatment for more than 6 months were investigated to determine whether they met the MetS criteria according to the International Diabetes Federation. The data for these patients were collected between March 2005 and September 2005. The input variables of ANN and logistic regression were limited to demographic and anthropometric data only. All models were trained by randomly selecting two-thirds of the patient data and were internally validated with the remaining one-third of the data. The models were then externally validated with data from 69 patients from another hospital, collected between March 2008 and June 2008. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of all models. Both the final ANN and logistic regression models had high accuracy (88.3% vs 83.6%), sensitivity (93.1% vs 86.2%), and specificity (86.9% vs 83.8%) to identify MetS in the internal validation set. The mean +/- SD AUC was high for both the ANN and logistic regression models (0.934 +/- 0.033 vs 0.922 +/- 0.035, P = .63). During external validation, high AUC was still obtained for both models. Waist circumference and diastolic blood pressure were the common variables that were left in the final ANN and logistic regression models. Our study developed accurate ANN and logistic regression models to detect MetS in patients with SGA treatment. The models are likely to provide a noninvasive tool for large-scale screening of MetS in this group of patients. (c) 2010 Physicians Postgraduate Press, Inc.

Bayesian logistic regression in detection of gene-steroid interaction for cancer at PDLIM5 locus.

PubMed

Wang, Ke-Sheng; Owusu, Daniel; Pan, Yue; Xie, Changchun

2016-06-01

The PDZ and LIM domain 5 (PDLIM5) gene may play a role in cancer, bipolar disorder, major depression, alcohol dependence and schizophrenia; however, little is known about the interaction effect of steroid and PDLIM5 gene on cancer. This study examined 47 single-nucleotide polymorphisms (SNPs) within the PDLIM5 gene in the Marshfield sample with 716 cancer patients (any diagnosed cancer, excluding minor skin cancer) and 2848 noncancer controls. Multiple logistic regression model in PLINK software was used to examine the association of each SNP with cancer. Bayesian logistic regression in PROC GENMOD in SAS statistical software, ver. 9.4 was used to detect gene- steroid interactions influencing cancer. Single marker analysis using PLINK identified 12 SNPs associated with cancer (P< 0.05); especially, SNP rs6532496 revealed the strongest association with cancer (P = 6.84 × 10⁻³); while the next best signal was rs951613 (P = 7.46 × 10⁻³). Classic logistic regression in PROC GENMOD showed that both rs6532496 and rs951613 revealed strong gene-steroid interaction effects (OR=2.18, 95% CI=1.31-3.63 with P = 2.9 × 10⁻³ for rs6532496 and OR=2.07, 95% CI=1.24-3.45 with P = 5.43 × 10⁻³ for rs951613, respectively). Results from Bayesian logistic regression showed stronger interaction effects (OR=2.26, 95% CI=1.2-3.38 for rs6532496 and OR=2.14, 95% CI=1.14-3.2 for rs951613, respectively). All the 12 SNPs associated with cancer revealed significant gene-steroid interaction effects (P < 0.05); whereas 13 SNPs showed gene-steroid interaction effects without main effect on cancer. SNP rs4634230 revealed the strongest gene-steroid interaction effect (OR=2.49, 95% CI=1.5-4.13 with P = 4.0 × 10⁻⁴ based on the classic logistic regression and OR=2.59, 95% CI=1.4-3.97 from Bayesian logistic regression; respectively). This study provides evidence of common genetic variants within the PDLIM5 gene and interactions between PLDIM5 gene polymorphisms and steroid use influencing cancer.

Quantifying discrimination of Framingham risk functions with different survival C statistics.

PubMed

Pencina, Michael J; D'Agostino, Ralph B; Song, Linye

2012-07-10

Cardiovascular risk prediction functions offer an important diagnostic tool for clinicians and patients themselves. They are usually constructed with the use of parametric or semi-parametric survival regression models. It is essential to be able to evaluate the performance of these models, preferably with summaries that offer natural and intuitive interpretations. The concept of discrimination, popular in the logistic regression context, has been extended to survival analysis. However, the extension is not unique. In this paper, we define discrimination in survival analysis as the model's ability to separate those with longer event-free survival from those with shorter event-free survival within some time horizon of interest. This definition remains consistent with that used in logistic regression, in the sense that it assesses how well the model-based predictions match the observed data. Practical and conceptual examples and numerical simulations are employed to examine four C statistics proposed in the literature to evaluate the performance of survival models. We observe that they differ in the numerical values and aspects of discrimination that they capture. We conclude that the index proposed by Harrell is the most appropriate to capture discrimination described by the above definition. We suggest researchers report which C statistic they are using, provide a rationale for their selection, and be aware that comparing different indices across studies may not be meaningful. Copyright © 2012 John Wiley & Sons, Ltd.

Psychological trauma symptoms and Type 2 diabetes prevalence, glucose control, and treatment modality among American Indians in the Strong Heart Family Study

PubMed Central

Jacob, Michelle M.; Gonzales, Kelly L.; Calhoun, Darren; Beals, Janette; Muller, Clemma Jacobsen; Goldberg, Jack; Nelson, Lonnie; Welty, Thomas K.; Howard, Barbara V.

2013-01-01

Aims The aims of this paper are to examine the relationship between psychological trauma symptoms and Type 2 diabetes prevalence, glucose control, and treatment modality among 3,776 American Indians in Phase V of the Strong Heart Family Study. Methods This cross-sectional analysis measured psychological trauma symptoms using the National Anxiety Disorder Screening Day instrument, diabetes by American Diabetes Association criteria, and treatment modality by four categories: no medication, oral medication only, insulin only, or both oral medication and insulin. We used binary logistic regression to evaluate the association between psychological trauma symptoms and diabetes prevalence. We used ordinary least squares regression to evaluate the association between psychological trauma symptoms and glucose control. We used binary logistic regression to model the association of psychological trauma symptoms with treatment modality. Results Neither diabetes prevalence (22-31%; p = 0.19) nor control (8.0-8.6; p = 0.25) varied significantly by psychological trauma symptoms categories. However, diabetes treatment modality was associated with psychological trauma symptoms categories, as people with greater burden used either no medication, or both oral and insulin medications (odds ratio = 3.1, p < 0.001). Conclusions The positive relationship between treatment modality and psychological trauma symptoms suggests future research investigate patient and provider treatment decision making. PMID:24051029

Estimating interaction on an additive scale between continuous determinants in a logistic regression model.

PubMed

Knol, Mirjam J; van der Tweel, Ingeborg; Grobbee, Diederick E; Numans, Mattijs E; Geerlings, Mirjam I

2007-10-01

To determine the presence of interaction in epidemiologic research, typically a product term is added to the regression model. In linear regression, the regression coefficient of the product term reflects interaction as departure from additivity. However, in logistic regression it refers to interaction as departure from multiplicativity. Rothman has argued that interaction estimated as departure from additivity better reflects biologic interaction. So far, literature on estimating interaction on an additive scale using logistic regression only focused on dichotomous determinants. The objective of the present study was to provide the methods to estimate interaction between continuous determinants and to illustrate these methods with a clinical example. and results From the existing literature we derived the formulas to quantify interaction as departure from additivity between one continuous and one dichotomous determinant and between two continuous determinants using logistic regression. Bootstrapping was used to calculate the corresponding confidence intervals. To illustrate the theory with an empirical example, data from the Utrecht Health Project were used, with age and body mass index as risk factors for elevated diastolic blood pressure. The methods and formulas presented in this article are intended to assist epidemiologists to calculate interaction on an additive scale between two variables on a certain outcome. The proposed methods are included in a spreadsheet which is freely available at: http://www.juliuscenter.nl/additive-interaction.xls.

Logits and Tigers and Bears, Oh My! A Brief Look at the Simple Math of Logistic Regression and How It Can Improve Dissemination of Results

ERIC Educational Resources Information Center

Osborne, Jason W.

2012-01-01

Logistic regression is slowly gaining acceptance in the social sciences, and fills an important niche in the researcher's toolkit: being able to predict important outcomes that are not continuous in nature. While OLS regression is a valuable tool, it cannot routinely be used to predict outcomes that are binary or categorical in nature. These…

The Integrative Weaning Index in Elderly ICU Subjects.

PubMed

Azeredo, Leandro M; Nemer, Sérgio N; Barbas, Carmen Sv; Caldeira, Jefferson B; Noé, Rosângela; Guimarães, Bruno L; Caldas, Célia P

2017-03-01

With increasing life expectancy and ICU admission of elderly patients, mechanical ventilation, and weaning trials have increased worldwide. We evaluated a cohort with 479 subjects in the ICU. Patients younger than 18 y, tracheostomized, or with neurologic diseases were excluded, resulting in 331 subjects. Subjects ≥70 y old were considered elderly, whereas those <70 y old were considered non-elderly. Besides the conventional weaning indexes, we evaluated the performance of the integrative weaning index (IWI). The probability of successful weaning was investigated using relative risk and logistic regression. The Hosmer-Lemeshow goodness-of-fit test was used to calibrate and the C statistic was calculated to evaluate the association between predicted probabilities and observed proportions in the logistic regression model. Prevalence of successful weaning in the sample was 83.7%. There was no difference in mortality between elderly and non-elderly subjects ( P = .16), in days of mechanical ventilation ( P = .22) and days of weaning ( P = .55). In elderly subjects, the IWI was the only respiratory variable associated with mechanical ventilation weaning in this population ( P < .001). The IWI was the independent variable found in weaning of elderly subjects that may contribute to the critical moment of this population in intensive care. Copyright © 2017 by Daedalus Enterprises.

Geospatial techniques for allocating vulnerability zoning of geohazards along the Karakorum Highway, Gilgit-Baltistan-Pakistan

NASA Astrophysics Data System (ADS)

Khan, K. M.; Rashid, S.; Yaseen, M.; Ikram, M.

2016-12-01

The Karakoram Highway (KKH) 'eighth wonder of the world', constructed and completed by the consent of Pakistan and China in 1979 as a Friendship Highway. It connect Gilgit-Baltistan, a strategically prominent region of Pakistan, with Xinjiang region in China. Due to manifold geology/geomorphology, soil formation, steep slopes, climate change well as unsustainable anthropogenic activities, still, KKH is remarkably vulnerable to natural hazards i.e. land subsistence, landslides, erosion, rock fall, floods, debris flows, cyclical torrential rainfall and snowfall, lake outburst etc. Most of the time these geohazard's damaging effects jeopardized the life in the region. To ascertain the nature and frequency of the disaster and vulnerability zoning, a rating and management (logistic) analysis were made to investigate the spatiotemporal sharing of the natural hazard. The substantial dynamics of the physiograpy, geology, geomorphology, soils and climate were carefully understand while slope, aspect, elevation, profile curvature and rock hardness was calculated by different techniques. To assess the nature and intensity geospatial analysis were conducted and magnitude of every factor was gauged by using logistic regression. Moreover, ever relative variable was integrated in the evaluation process. Logistic regression and geospatial techniques were used to map the geohazard vulnerability zoning (GVZ). The GVZ model findings were endorsed by the reviews of documented hazards in the current years and the precision was realized more than 88.1 %. The study has proved the model authentication by highlighting the comfortable indenture among the vulnerability mapping and past documented hazards. By using a receiver operating characteristic curve, the logistic regression model made satisfactory results. The outcomes will be useful in sustainable land use and infrastructure planning, mainly in high risk zones for reduceing economic damages and community betterment.

Fall-related self-efficacy, not balance and mobility performance, is related to accidental falls in chronic stroke survivors with low bone mineral density

PubMed Central

Pang, Marco Y.C.; Eng, Janice J.

2011-01-01

Introduction Chronic stroke survivors with low bone mineral density (BMD) are particularly prone to fragility fractures. The purpose of this study was to identify the determinants of balance, mobility and falls in this sub-group of stroke patients. Methods Thirty nine chronic stroke survivors with low hip BMD (T-score <-1.0) were studied. Each subject was evaluated for: balance, mobility, leg muscle strength, spasticity, and falls-related self-efficacy. Any falls in the past 12 months were also recorded. Multiple regression analysis was used to identify the determinants of balance and mobility performance whereas logistic regression was used to identify the determinants of falls. Results Multiple regression analysis revealed that after adjusting for basic demographics, falls-related self-efficacy remained independently associated with balance/mobility performance (R2=0.494, P<0.001). Logistic regression showed that falls-related self-efficacy, but not balance and mobility performance, was a significant determinant of falls (odds ratio: 0.18, P=0.04). Conclusions Falls-related self-efficacy, but not mobility and balance performance, was the most important determinant of accidental falls. This psychological factor should not be overlooked in the prevention of fragility fractures among chronic stroke survivors with low hip BMD. PMID:18097709

Physical Activity, Body Size, Intentional Weight Loss and Breast Cancer Risk: Fellowship

DTIC Science & Technology

2000-10-01

unconditional logistic regression and were adjusted for physical activity at other time periods, age, body mass index , smoking status, postmenopausal hormone use ...This variable was used to evaluate tests for trend within the ’any vigorous activity’ group. Body mass index (BMI) was computed using recent weight... used to evaluate the relation of diabetes to the risk of endometrial cancer on the basis of body mass index (BMI). Cases (n = 723) were identified

Intermediate and advanced topics in multilevel logistic regression analysis

PubMed Central

Merlo, Juan

2017-01-01

Multilevel data occur frequently in health services, population and public health, and epidemiologic research. In such research, binary outcomes are common. Multilevel logistic regression models allow one to account for the clustering of subjects within clusters of higher‐level units when estimating the effect of subject and cluster characteristics on subject outcomes. A search of the PubMed database demonstrated that the use of multilevel or hierarchical regression models is increasing rapidly. However, our impression is that many analysts simply use multilevel regression models to account for the nuisance of within‐cluster homogeneity that is induced by clustering. In this article, we describe a suite of analyses that can complement the fitting of multilevel logistic regression models. These ancillary analyses permit analysts to estimate the marginal or population‐average effect of covariates measured at the subject and cluster level, in contrast to the within‐cluster or cluster‐specific effects arising from the original multilevel logistic regression model. We describe the interval odds ratio and the proportion of opposed odds ratios, which are summary measures of effect for cluster‐level covariates. We describe the variance partition coefficient and the median odds ratio which are measures of components of variance and heterogeneity in outcomes. These measures allow one to quantify the magnitude of the general contextual effect. We describe an R 2 measure that allows analysts to quantify the proportion of variation explained by different multilevel logistic regression models. We illustrate the application and interpretation of these measures by analyzing mortality in patients hospitalized with a diagnosis of acute myocardial infarction. © 2017 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd. PMID:28543517

Intermediate and advanced topics in multilevel logistic regression analysis.

PubMed

Austin, Peter C; Merlo, Juan

2017-09-10

Multilevel data occur frequently in health services, population and public health, and epidemiologic research. In such research, binary outcomes are common. Multilevel logistic regression models allow one to account for the clustering of subjects within clusters of higher-level units when estimating the effect of subject and cluster characteristics on subject outcomes. A search of the PubMed database demonstrated that the use of multilevel or hierarchical regression models is increasing rapidly. However, our impression is that many analysts simply use multilevel regression models to account for the nuisance of within-cluster homogeneity that is induced by clustering. In this article, we describe a suite of analyses that can complement the fitting of multilevel logistic regression models. These ancillary analyses permit analysts to estimate the marginal or population-average effect of covariates measured at the subject and cluster level, in contrast to the within-cluster or cluster-specific effects arising from the original multilevel logistic regression model. We describe the interval odds ratio and the proportion of opposed odds ratios, which are summary measures of effect for cluster-level covariates. We describe the variance partition coefficient and the median odds ratio which are measures of components of variance and heterogeneity in outcomes. These measures allow one to quantify the magnitude of the general contextual effect. We describe an R 2 measure that allows analysts to quantify the proportion of variation explained by different multilevel logistic regression models. We illustrate the application and interpretation of these measures by analyzing mortality in patients hospitalized with a diagnosis of acute myocardial infarction. © 2017 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd. © 2017 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.

[Value of the albumin to globulin ratio in predicting severity and prognosis in myasthenia gravis patients].

PubMed

Yang, D H; Su, Z Q; Chen, Y; Chen, Z B; Ding, Z N; Weng, Y Y; Li, J; Li, X; Tong, Q L; Han, Y X; Zhang, X

2016-03-08

To assess the predictive value of the albumin to globulin ratio (AGR) in evaluation of disease severity and prognosis in myasthenia gravis patients. A total of 135 myasthenia gravis (MG) patients were enrolled between February 2009 and March 2015. The AGR was detected on the first day of hospitalization and ranked from lowest to highest, and the patients were divided into three equal tertiles according to the AGR values, which were T1 (AGR <1.34), T2 (1.34≤AGR≤1.53) and T3 (AGR>1.53). The Kaplan-Meier curve was used to evaluate the prognostic value of AGR. Cox model analysis was used to evaluate the relevant factors. Multivariate Logistic regression analysis was used to find the predictors of myasthenia crisis during hospitalization. The median length of hospital stay for each tertile was: for the T1 21 days (15-35.5), T2 18 days (14-27.5), and T3 16 days (12-22.5) (P<0.01), and Kaplan-Meier curves showed significant difference among the three groups. In the univariate model, serum albumin, creatinine, AGR and MGFA clinical classification were related to prognosis of myasthenia gravis. At the multivariate Cox regression analysis, the AGR (P<0.001) and MGFA clinical classification (P<0.001) were independent predictive factors of disease severity and prognosis in myasthenia gravis patients. Respectively, the hazard ratio (HR) were 4.655 (95% CI: 2.355-9.202) and 0.596 (95% CI: 0.492-0.723). Multivariate Logistic regression analysis showed the AGR (P<0.001) and MGFA clinical classification were related to myasthenia crisis. The AGR may represent a simple, potentially useful predictive biomarker for evaluating the disease severity and prognosis of patients with myasthenia gravis.

Evaluation of spectral domain optical coherence tomography parameters in ocular hypertension, preperimetric, and early glaucoma

PubMed Central

Aydoğan, Tuğba; Akçay, Betül İlkay Sezgin; Kardeş, Esra; Ergin, Ahmet

2017-01-01

Purpose: The objective of this study is to evaluate the diagnostic ability of retinal nerve fiber layer (RNFL), macular, optic nerve head (ONH) parameters in healthy subjects, ocular hypertension (OHT), preperimetric glaucoma (PPG), and early glaucoma (EG) patients, to reveal factors affecting the diagnostic ability of spectral domain-optical coherence tomography (SD-OCT) parameters and risk factors for glaucoma. Methods: Three hundred and twenty-six eyes (89 healthy, 77 OHT, 94 PPG, and 66 EG eyes) were analyzed. RNFL, macular, and ONH parameters were measured with SD-OCT. The area under the receiver operating characteristic curve (AUC) and sensitivity at 95% specificity was calculated. Logistic regression analysis was used to determine the glaucoma risk factors. Receiver operating characteristic regression analysis was used to evaluate the influence of covariates on the diagnostic ability of parameters. Results: In PPG patients, parameters that had the largest AUC value were average RNFL thickness (0.83) and rim volume (0.83). In EG patients, parameter that had the largest AUC value was average RNFL thickness (0.98). The logistic regression analysis showed average RNFL thickness was a risk factor for both PPG and EG. Diagnostic ability of average RNFL and average ganglion cell complex thickness increased as disease severity increased. Signal strength index did not affect diagnostic abilities. Diagnostic ability of average RNFL and rim area increased as disc area increased. Conclusion: When evaluating patients with glaucoma, patients at risk for glaucoma, and healthy controls RNFL parameters deserve more attention in clinical practice. Further studies are needed to fully understand the influence of covariates on the diagnostic ability of OCT parameters. PMID:29133640

Study on a pattern classification method of soil quality based on simplified learning sample dataset

USGS Publications Warehouse

Zhang, Jiahua; Liu, S.; Hu, Y.; Tian, Y.

2011-01-01

Based on the massive soil information in current soil quality grade evaluation, this paper constructed an intelligent classification approach of soil quality grade depending on classical sampling techniques and disordered multiclassification Logistic regression model. As a case study to determine the learning sample capacity under certain confidence level and estimation accuracy, and use c-means algorithm to automatically extract the simplified learning sample dataset from the cultivated soil quality grade evaluation database for the study area, Long chuan county in Guangdong province, a disordered Logistic classifier model was then built and the calculation analysis steps of soil quality grade intelligent classification were given. The result indicated that the soil quality grade can be effectively learned and predicted by the extracted simplified dataset through this method, which changed the traditional method for soil quality grade evaluation. ?? 2011 IEEE.

Predicting Social Trust with Binary Logistic Regression

ERIC Educational Resources Information Center

Adwere-Boamah, Joseph; Hufstedler, Shirley

2015-01-01

This study used binary logistic regression to predict social trust with five demographic variables from a national sample of adult individuals who participated in The General Social Survey (GSS) in 2012. The five predictor variables were respondents' highest degree earned, race, sex, general happiness and the importance of personally assisting…

Effect of folic acid on appetite in children: ordinal logistic and fuzzy logistic regressions.

PubMed

Namdari, Mahshid; Abadi, Alireza; Taheri, S Mahmoud; Rezaei, Mansour; Kalantari, Naser; Omidvar, Nasrin

2014-03-01

Reduced appetite and low food intake are often a concern in preschool children, since it can lead to malnutrition, a leading cause of impaired growth and mortality in childhood. It is occasionally considered that folic acid has a positive effect on appetite enhancement and consequently growth in children. The aim of this study was to assess the effect of folic acid on the appetite of preschool children 3 to 6 y old. The study sample included 127 children ages 3 to 6 who were randomly selected from 20 preschools in the city of Tehran in 2011. Since appetite was measured by linguistic terms, a fuzzy logistic regression was applied for modeling. The obtained results were compared with a statistical ordinal logistic model. After controlling for the potential confounders, in a statistical ordinal logistic model, serum folate showed a significantly positive effect on appetite. A small but positive effect of folate was detected by fuzzy logistic regression. Based on fuzzy regression, the risk for poor appetite in preschool children was related to the employment status of their mothers. In this study, a positive association was detected between the levels of serum folate and improved appetite. For further investigation, a randomized controlled, double-blind clinical trial could be helpful to address causality. Copyright © 2014 Elsevier Inc. All rights reserved.

Prediction of spatially explicit rainfall intensity-duration thresholds for post-fire debris-flow generation in the western United States

NASA Astrophysics Data System (ADS)

Staley, Dennis; Negri, Jacquelyn; Kean, Jason

2016-04-01

Population expansion into fire-prone steeplands has resulted in an increase in post-fire debris-flow risk in the western United States. Logistic regression methods for determining debris-flow likelihood and the calculation of empirical rainfall intensity-duration thresholds for debris-flow initiation represent two common approaches for characterizing hazard and reducing risk. Logistic regression models are currently being used to rapidly assess debris-flow hazard in response to design storms of known intensities (e.g. a 10-year recurrence interval rainstorm). Empirical rainfall intensity-duration thresholds comprise a major component of the United States Geological Survey (USGS) and the National Weather Service (NWS) debris-flow early warning system at a regional scale in southern California. However, these two modeling approaches remain independent, with each approach having limitations that do not allow for synergistic local-scale (e.g. drainage-basin scale) characterization of debris-flow hazard during intense rainfall. The current logistic regression equations consider rainfall a unique independent variable, which prevents the direct calculation of the relation between rainfall intensity and debris-flow likelihood. Regional (e.g. mountain range or physiographic province scale) rainfall intensity-duration thresholds fail to provide insight into the basin-scale variability of post-fire debris-flow hazard and require an extensive database of historical debris-flow occurrence and rainfall characteristics. Here, we present a new approach that combines traditional logistic regression and intensity-duration threshold methodologies. This method allows for local characterization of both the likelihood that a debris-flow will occur at a given rainfall intensity, the direct calculation of the rainfall rates that will result in a given likelihood, and the ability to calculate spatially explicit rainfall intensity-duration thresholds for debris-flow generation in recently burned areas. Our approach synthesizes the two methods by incorporating measured rainfall intensity into each model variable (based on measures of topographic steepness, burn severity and surface properties) within the logistic regression equation. This approach provides a more realistic representation of the relation between rainfall intensity and debris-flow likelihood, as likelihood values asymptotically approach zero when rainfall intensity approaches 0 mm/h, and increase with more intense rainfall. Model performance was evaluated by comparing predictions to several existing regional thresholds. The model, based upon training data collected in southern California, USA, has proven to accurately predict rainfall intensity-duration thresholds for other areas in the western United States not included in the original training dataset. In addition, the improved logistic regression model shows promise for emergency planning purposes and real-time, site-specific early warning. With further validation, this model may permit the prediction of spatially-explicit intensity-duration thresholds for debris-flow generation in areas where empirically derived regional thresholds do not exist. This improvement would permit the expansion of the early-warning system into other regions susceptible to post-fire debris flow.

Relationships between common forest metrics and realized impacts of Hurricane Katrina on forest resources in Mississippi

Treesearch

Sonja N. Oswalt; Christopher M. Oswalt

2008-01-01

This paper compares and contrasts hurricane-related damage recorded across the Mississippi landscape in the 2 years following Katrina with initial damage assessments based on modeled parameters by the USDA Forest Service. Logistic and multiple regressions are used to evaluate the influence of stand characteristics on tree damage probability. Specifically, this paper...

Landscape evaluation of female black bear habitat effectiveness and capability in the North Cascades, Washington.

Treesearch

William L. Gaines; Andrea L. Lyons; John F. Lehmkuhl; Kenneth J. Raedeke

2005-01-01

We used logistic regression to derive scaled resource selection functions (RSFs) for female black bears at two study areas in the North Cascades Mountains. We tested the hypothesis that the influence of roads would result in potential habitat effectiveness (RSFs without the influence of roads) being greater than realized habitat effectiveness (RSFs with roads). Roads...

Application of Bayesian methods to habitat selection modeling of the northern spotted owl in California: new statistical methods for wildlife research

Treesearch

Howard B. Stauffer; Cynthia J. Zabel; Jeffrey R. Dunk

2005-01-01

We compared a set of competing logistic regression habitat selection models for Northern Spotted Owls (Strix occidentalis caurina) in California. The habitat selection models were estimated, compared, evaluated, and tested using multiple sample datasets collected on federal forestlands in northern California. We used Bayesian methods in interpreting...

Mountain pine beetle attack in ponderosa pine: Comparing methods for rating susceptibility

Treesearch

David C. Chojnacky; Barbara J. Bentz; Jesse A. Logan

2000-01-01

Two empirical methods for rating susceptibility of mountain pine beetle attack in ponderosa pine were evaluated. The methods were compared to stand data modeled to objectively rate each sampled stand for susceptibly to bark-beetle attack. Data on bark-beetle attacks, from a survey of 45 sites throughout the Colorado Plateau, were modeled using logistic regression to...

The intermediate endpoint effect in logistic and probit regression

PubMed Central

MacKinnon, DP; Lockwood, CM; Brown, CH; Wang, W; Hoffman, JM

2010-01-01

Background An intermediate endpoint is hypothesized to be in the middle of the causal sequence relating an independent variable to a dependent variable. The intermediate variable is also called a surrogate or mediating variable and the corresponding effect is called the mediated, surrogate endpoint, or intermediate endpoint effect. Clinical studies are often designed to change an intermediate or surrogate endpoint and through this intermediate change influence the ultimate endpoint. In many intermediate endpoint clinical studies the dependent variable is binary, and logistic or probit regression is used. Purpose The purpose of this study is to describe a limitation of a widely used approach to assessing intermediate endpoint effects and to propose an alternative method, based on products of coefficients, that yields more accurate results. Methods The intermediate endpoint model for a binary outcome is described for a true binary outcome and for a dichotomization of a latent continuous outcome. Plots of true values and a simulation study are used to evaluate the different methods. Results Distorted estimates of the intermediate endpoint effect and incorrect conclusions can result from the application of widely used methods to assess the intermediate endpoint effect. The same problem occurs for the proportion of an effect explained by an intermediate endpoint, which has been suggested as a useful measure for identifying intermediate endpoints. A solution to this problem is given based on the relationship between latent variable modeling and logistic or probit regression. Limitations More complicated intermediate variable models are not addressed in the study, although the methods described in the article can be extended to these more complicated models. Conclusions Researchers are encouraged to use an intermediate endpoint method based on the product of regression coefficients. A common method based on difference in coefficient methods can lead to distorted conclusions regarding the intermediate effect. PMID:17942466

Vitamin D and Male Sexual Function: A Transversal and Longitudinal Study.

PubMed

Tirabassi, Giacomo; Sudano, Maurizio; Salvio, Gianmaria; Cutini, Melissa; Muscogiuri, Giovanna; Corona, Giovanni; Balercia, Giancarlo

2018-01-01

The effects of vitamin D on sexual function are very unclear. Therefore, we aimed at evaluating the possible association between vitamin D and sexual function and at assessing the influence of vitamin D administration on sexual function. We retrospectively studied 114 men by evaluating clinical, biochemical, and sexual parameters. A subsample ( n = 41) was also studied longitudinally before and after vitamin D replacement therapy. In the whole sample, after performing logistic regression models, higher levels of 25(OH) vitamin D were significantly associated with high values of total testosterone and of all the International Index of Erectile Function (IIEF) questionnaire parameters. On the other hand, higher levels of total testosterone were positively and significantly associated with high levels of erectile function and IIEF total score. After vitamin D replacement therapy, total and free testosterone increased and erectile function improved, whereas other sexual parameters did not change significantly. At logistic regression analysis, higher levels of vitamin D increase (Δ-) were significantly associated with high values of Δ-erectile function after adjustment for Δ-testosterone. Vitamin D is important for the wellness of male sexual function, and vitamin D administration improves sexual function.

Use of multilevel logistic regression to identify the causes of differential item functioning.

PubMed

Balluerka, Nekane; Gorostiaga, Arantxa; Gómez-Benito, Juana; Hidalgo, María Dolores

2010-11-01

Given that a key function of tests is to serve as evaluation instruments and for decision making in the fields of psychology and education, the possibility that some of their items may show differential behaviour is a major concern for psychometricians. In recent decades, important progress has been made as regards the efficacy of techniques designed to detect this differential item functioning (DIF). However, the findings are scant when it comes to explaining its causes. The present study addresses this problem from the perspective of multilevel analysis. Starting from a case study in the area of transcultural comparisons, multilevel logistic regression is used: 1) to identify the item characteristics associated with the presence of DIF; 2) to estimate the proportion of variation in the DIF coefficients that is explained by these characteristics; and 3) to evaluate alternative explanations of the DIF by comparing the explanatory power or fit of different sequential models. The comparison of these models confirmed one of the two alternatives (familiarity with the stimulus) and rejected the other (the topic area) as being a cause of differential functioning with respect to the compared groups.

The likelihood of achieving quantified road safety targets: a binary logistic regression model for possible factors.

PubMed

Sze, N N; Wong, S C; Lee, C Y

2014-12-01

In past several decades, many countries have set quantified road safety targets to motivate transport authorities to develop systematic road safety strategies and measures and facilitate the achievement of continuous road safety improvement. Studies have been conducted to evaluate the association between the setting of quantified road safety targets and road fatality reduction, in both the short and long run, by comparing road fatalities before and after the implementation of a quantified road safety target. However, not much work has been done to evaluate whether the quantified road safety targets are actually achieved. In this study, we used a binary logistic regression model to examine the factors - including vehicle ownership, fatality rate, and national income, in addition to level of ambition and duration of target - that contribute to a target's success. We analyzed 55 quantified road safety targets set by 29 countries from 1981 to 2009, and the results indicate that targets that are in progress and with lower level of ambitions had a higher likelihood of eventually being achieved. Moreover, possible interaction effects on the association between level of ambition and the likelihood of success are also revealed. Copyright © 2014 Elsevier Ltd. All rights reserved.

Clustering performance comparison using K-means and expectation maximization algorithms.

PubMed

Jung, Yong Gyu; Kang, Min Soo; Heo, Jun

2014-11-14

Clustering is an important means of data mining based on separating data categories by similar features. Unlike the classification algorithm, clustering belongs to the unsupervised type of algorithms. Two representatives of the clustering algorithms are the K -means and the expectation maximization (EM) algorithm. Linear regression analysis was extended to the category-type dependent variable, while logistic regression was achieved using a linear combination of independent variables. To predict the possibility of occurrence of an event, a statistical approach is used. However, the classification of all data by means of logistic regression analysis cannot guarantee the accuracy of the results. In this paper, the logistic regression analysis is applied to EM clusters and the K -means clustering method for quality assessment of red wine, and a method is proposed for ensuring the accuracy of the classification results.

Modeling recall memory for emotional objects in Alzheimer's disease.

PubMed

Sundstrøm, Martin

2011-07-01

To examine whether emotional memory (EM) of objects with self-reference in Alzheimer's disease (AD) can be modeled with binomial logistic regression in a free recall and an object recognition test to predict EM enhancement. Twenty patients with AD and twenty healthy controls were studied. Six objects (three presented as gifts) were shown to each participant. Ten minutes later, a free recall and a recognition test were applied. The recognition test had target-objects mixed with six similar distracter objects. Participants were asked to name any object in the recall test and identify each object in the recognition test as known or unknown. The total of gift objects recalled in AD patients (41.6%) was larger than neutral objects (13.3%) and a significant EM recall effect for gifts was found (Wilcoxon: p < .003). EM was not found for recognition in AD patients due to a ceiling effect. Healthy older adults scored overall higher in recall and recognition but showed no EM enhancement due to a ceiling effect. A logistic regression showed that likelihood of emotional recall memory can be modeled as a function of MMSE score (p < .014) and object status (p < .0001) as gift or non-gift. Recall memory was enhanced in AD patients for emotional objects indicating that EM in mild to moderate AD although impaired can be provoked with strong emotional load. The logistic regression model suggests that EM declines with the progression of AD rather than disrupts and may be a useful tool for evaluating magnitude of emotional load.

Pediatric Irritable Bowel Syndrome Patient and Parental Characteristics Differ by Care Management Type.

PubMed

Hollier, John M; Czyzewski, Danita I; Self, Mariella M; Weidler, Erica M; Smith, E O'Brian; Shulman, Robert J

2017-03-01

This study evaluates whether certain patient or parental characteristics are associated with gastroenterology (GI) referral versus primary pediatrics care for pediatric irritable bowel syndrome (IBS). A retrospective clinical trial sample of patients meeting pediatric Rome III IBS criteria was assembled from a single metropolitan health care system. Baseline socioeconomic status (SES) and clinical symptom measures were gathered. Various instruments measured participant and parental psychosocial traits. Study outcomes were stratified by GI referral versus primary pediatrics care. Two separate analyses of SES measures and GI clinical symptoms and psychosocial measures identified key factors by univariate and multiple logistic regression analyses. For each analysis, identified factors were placed in unadjusted and adjusted multivariate logistic regression models to assess their impact in predicting GI referral. Of the 239 participants, 152 were referred to pediatric GI, and 87 were managed in primary pediatrics care. Of the SES and clinical symptom factors, child self-assessment of abdominal pain duration and lower percentage of people living in poverty were the strongest predictors of GI referral. Among the psychosocial measures, parental assessment of their child's functional disability was the sole predictor of GI referral. In multivariate logistic regression models, all selected factors continued to predict GI referral in each model. Socioeconomic environment, clinical symptoms, and functional disability are associated with GI referral. Future interventions designed to ameliorate the effect of these identified factors could reduce unnecessary specialty consultations and health care overutilization for IBS.

Training to Provide Psychiatric Genetic Counseling: How Does It Impact Recent Graduates' and Current Students' Readiness to Provide Genetic Counseling for Individuals with Psychiatric Illness and Attitudes towards this Population?

PubMed

Low, Ashley; Dixon, Shannan; Higgs, Amanda; Joines, Jessica; Hippman, Catriona

2018-02-01

Mental illness is extremely common and genetic counselors frequently see patients with mental illness. Genetic counselors report discomfort in providing psychiatric genetic counseling (GC), suggesting the need to look critically at training for psychiatric GC. This study aimed to investigate psychiatric GC training and its impact on perceived preparedness to provide psychiatric GC (preparedness). Current students and recent graduates were invited to complete an anonymous survey evaluating psychiatric GC training and outcomes. Bivariate correlations (p<.10) identified variables for inclusion in a logistic regression model to predict preparedness. Data were checked for assumptions underlying logistic regression. The logistic regression model for the 286 respondents [χ 2 (8)=84.87, p<.001] explained between 37.1% (Cox & Snell R 2 =.371) and 49.7% (Nagelkerke R 2 =.497) of the variance in preparedness scores. More frequent psychiatric GC instruction (OR=5.13), more active methods for practicing risk assessment (OR=4.43), and education on providing resources for mental illness (OR=4.99) made uniquely significant contributions to the model (p<.001). Responses to open-ended questions revealed interest in further psychiatric GC training, particularly enabling "hands on" experience. This exploratory study suggests that enriching GC training through more frequent psychiatric GC instruction and more active opportunities to practice psychiatric GC skills will support students in feeling more prepared to provide psychiatric GC after graduation.

A Powerful Test for Comparing Multiple Regression Functions.

PubMed

Maity, Arnab

2012-09-01

In this article, we address the important problem of comparison of two or more population regression functions. Recently, Pardo-Fernández, Van Keilegom and González-Manteiga (2007) developed test statistics for simple nonparametric regression models: Y(ij) = θ(j)(Z(ij)) + σ(j)(Z(ij))∊(ij), based on empirical distributions of the errors in each population j = 1, … , J. In this paper, we propose a test for equality of the θ(j)(·) based on the concept of generalized likelihood ratio type statistics. We also generalize our test for other nonparametric regression setups, e.g, nonparametric logistic regression, where the loglikelihood for population j is any general smooth function [Formula: see text]. We describe a resampling procedure to obtain the critical values of the test. In addition, we present a simulation study to evaluate the performance of the proposed test and compare our results to those in Pardo-Fernández et al. (2007).

Racial/ethnic and educational differences in the estimated odds of recent nitrite use among adult household residents in the United States: an illustration of matching and conditional logistic regression.

PubMed

Delva, J; Spencer, M S; Lin, J K

2000-01-01

This article compares estimates of the relative odds of nitrite use obtained from weighted unconditional logistic regression with estimates obtained from conditional logistic regression after post-stratification and matching of cases with controls by neighborhood of residence. We illustrate these methods by comparing the odds associated with nitrite use among adults of four racial/ethnic groups, with and without a high school education. We used aggregated data from the 1994-B through 1996 National Household Survey on Drug Abuse (NHSDA). Difference between the methods and implications for analysis and inference are discussed.

Strategies for Testing Statistical and Practical Significance in Detecting DIF with Logistic Regression Models

ERIC Educational Resources Information Center

Fidalgo, Angel M.; Alavi, Seyed Mohammad; Amirian, Seyed Mohammad Reza

2014-01-01

This study examines three controversial aspects in differential item functioning (DIF) detection by logistic regression (LR) models: first, the relative effectiveness of different analytical strategies for detecting DIF; second, the suitability of the Wald statistic for determining the statistical significance of the parameters of interest; and…

Iterative Purification and Effect Size Use with Logistic Regression for Differential Item Functioning Detection

ERIC Educational Resources Information Center

French, Brian F.; Maller, Susan J.

2007-01-01

Two unresolved implementation issues with logistic regression (LR) for differential item functioning (DIF) detection include ability purification and effect size use. Purification is suggested to control inaccuracies in DIF detection as a result of DIF items in the ability estimate. Additionally, effect size use may be beneficial in controlling…

A Note on Three Statistical Tests in the Logistic Regression DIF Procedure

ERIC Educational Resources Information Center

Paek, Insu

2012-01-01

Although logistic regression became one of the well-known methods in detecting differential item functioning (DIF), its three statistical tests, the Wald, likelihood ratio (LR), and score tests, which are readily available under the maximum likelihood, do not seem to be consistently distinguished in DIF literature. This paper provides a clarifying…

"Let Me Count the Ways:" Fostering Reasons for Living among Low-Income, Suicidal, African American Women

ERIC Educational Resources Information Center

West, Lindsey M.; Davis, Telsie A.; Thompson, Martie P.; Kaslow, Nadine J.

2011-01-01

Protective factors for fostering reasons for living were examined among low-income, suicidal, African American women. Bivariate logistic regressions revealed that higher levels of optimism, spiritual well-being, and family social support predicted reasons for living. Multivariate logistic regressions indicated that spiritual well-being showed…

Comparison of Two Approaches for Handling Missing Covariates in Logistic Regression

ERIC Educational Resources Information Center

Peng, Chao-Ying Joanne; Zhu, Jin

2008-01-01

For the past 25 years, methodological advances have been made in missing data treatment. Most published work has focused on missing data in dependent variables under various conditions. The present study seeks to fill the void by comparing two approaches for handling missing data in categorical covariates in logistic regression: the…

Comparison of IRT Likelihood Ratio Test and Logistic Regression DIF Detection Procedures

ERIC Educational Resources Information Center

Atar, Burcu; Kamata, Akihito

2011-01-01

The Type I error rates and the power of IRT likelihood ratio test and cumulative logit ordinal logistic regression procedures in detecting differential item functioning (DIF) for polytomously scored items were investigated in this Monte Carlo simulation study. For this purpose, 54 simulation conditions (combinations of 3 sample sizes, 2 sample…

Multiple Logistic Regression Analysis of Cigarette Use among High School Students

ERIC Educational Resources Information Center

Adwere-Boamah, Joseph

2011-01-01

A binary logistic regression analysis was performed to predict high school students' cigarette smoking behavior from selected predictors from 2009 CDC Youth Risk Behavior Surveillance Survey. The specific target student behavior of interest was frequent cigarette use. Five predictor variables included in the model were: a) race, b) frequency of…

Modeling Polytomous Item Responses Using Simultaneously Estimated Multinomial Logistic Regression Models

ERIC Educational Resources Information Center

Anderson, Carolyn J.; Verkuilen, Jay; Peyton, Buddy L.

2010-01-01

Survey items with multiple response categories and multiple-choice test questions are ubiquitous in psychological and educational research. We illustrate the use of log-multiplicative association (LMA) models that are extensions of the well-known multinomial logistic regression model for multiple dependent outcome variables to reanalyze a set of…

Propensity Score Estimation with Data Mining Techniques: Alternatives to Logistic Regression

ERIC Educational Resources Information Center

Keller, Bryan S. B.; Kim, Jee-Seon; Steiner, Peter M.

2013-01-01

Propensity score analysis (PSA) is a methodological technique which may correct for selection bias in a quasi-experiment by modeling the selection process using observed covariates. Because logistic regression is well understood by researchers in a variety of fields and easy to implement in a number of popular software packages, it has…

Two-factor logistic regression in pediatric liver transplantation

NASA Astrophysics Data System (ADS)

Uzunova, Yordanka; Prodanova, Krasimira; Spasov, Lyubomir

2017-12-01

Using a two-factor logistic regression analysis an estimate is derived for the probability of absence of infections in the early postoperative period after pediatric liver transplantation. The influence of both the bilirubin level and the international normalized ratio of prothrombin time of blood coagulation at the 5th postoperative day is studied.

Predictors of Placement Stability at the State Level: The Use of Logistic Regression to Inform Practice

ERIC Educational Resources Information Center

Courtney, Jon R.; Prophet, Retta

2011-01-01

Placement instability is often associated with a number of negative outcomes for children. To gain state level contextual knowledge of factors associated with placement stability/instability, logistic regression was applied to selected variables from the New Mexico Adoption and Foster Care Administrative Reporting System dataset. Predictors…

Classifying machinery condition using oil samples and binary logistic regression

NASA Astrophysics Data System (ADS)

Phillips, J.; Cripps, E.; Lau, John W.; Hodkiewicz, M. R.

2015-08-01

The era of big data has resulted in an explosion of condition monitoring information. The result is an increasing motivation to automate the costly and time consuming human elements involved in the classification of machine health. When working with industry it is important to build an understanding and hence some trust in the classification scheme for those who use the analysis to initiate maintenance tasks. Typically "black box" approaches such as artificial neural networks (ANN) and support vector machines (SVM) can be difficult to provide ease of interpretability. In contrast, this paper argues that logistic regression offers easy interpretability to industry experts, providing insight to the drivers of the human classification process and to the ramifications of potential misclassification. Of course, accuracy is of foremost importance in any automated classification scheme, so we also provide a comparative study based on predictive performance of logistic regression, ANN and SVM. A real world oil analysis data set from engines on mining trucks is presented and using cross-validation we demonstrate that logistic regression out-performs the ANN and SVM approaches in terms of prediction for healthy/not healthy engines.

Length bias correction in gene ontology enrichment analysis using logistic regression.

PubMed

Mi, Gu; Di, Yanming; Emerson, Sarah; Cumbie, Jason S; Chang, Jeff H

2012-01-01

When assessing differential gene expression from RNA sequencing data, commonly used statistical tests tend to have greater power to detect differential expression of genes encoding longer transcripts. This phenomenon, called "length bias", will influence subsequent analyses such as Gene Ontology enrichment analysis. In the presence of length bias, Gene Ontology categories that include longer genes are more likely to be identified as enriched. These categories, however, are not necessarily biologically more relevant. We show that one can effectively adjust for length bias in Gene Ontology analysis by including transcript length as a covariate in a logistic regression model. The logistic regression model makes the statistical issue underlying length bias more transparent: transcript length becomes a confounding factor when it correlates with both the Gene Ontology membership and the significance of the differential expression test. The inclusion of the transcript length as a covariate allows one to investigate the direct correlation between the Gene Ontology membership and the significance of testing differential expression, conditional on the transcript length. We present both real and simulated data examples to show that the logistic regression approach is simple, effective, and flexible.

Label-noise resistant logistic regression for functional data classification with an application to Alzheimer's disease study.

PubMed

Lee, Seokho; Shin, Hyejin; Lee, Sang Han

2016-12-01

Alzheimer's disease (AD) is usually diagnosed by clinicians through cognitive and functional performance test with a potential risk of misdiagnosis. Since the progression of AD is known to cause structural changes in the corpus callosum (CC), the CC thickness can be used as a functional covariate in AD classification problem for a diagnosis. However, misclassified class labels negatively impact the classification performance. Motivated by AD-CC association studies, we propose a logistic regression for functional data classification that is robust to misdiagnosis or label noise. Specifically, our logistic regression model is constructed by adopting individual intercepts to functional logistic regression model. This approach enables to indicate which observations are possibly mislabeled and also lead to a robust and efficient classifier. An effective algorithm using MM algorithm provides simple closed-form update formulas. We test our method using synthetic datasets to demonstrate its superiority over an existing method, and apply it to differentiating patients with AD from healthy normals based on CC from MRI. © 2016, The International Biometric Society.

The Effect of Latent Binary Variables on the Uncertainty of the Prediction of a Dichotomous Outcome Using Logistic Regression Based Propensity Score Matching.

PubMed

Szekér, Szabolcs; Vathy-Fogarassy, Ágnes

2018-01-01

Logistic regression based propensity score matching is a widely used method in case-control studies to select the individuals of the control group. This method creates a suitable control group if all factors affecting the output variable are known. However, if relevant latent variables exist as well, which are not taken into account during the calculations, the quality of the control group is uncertain. In this paper, we present a statistics-based research in which we try to determine the relationship between the accuracy of the logistic regression model and the uncertainty of the dependent variable of the control group defined by propensity score matching. Our analyses show that there is a linear correlation between the fit of the logistic regression model and the uncertainty of the output variable. In certain cases, a latent binary explanatory variable can result in a relative error of up to 70% in the prediction of the outcome variable. The observed phenomenon calls the attention of analysts to an important point, which must be taken into account when deducting conclusions.

A large-scale assessment of two-way SNP interactions in breast cancer susceptibility using 46 450 cases and 42 461 controls from the breast cancer association consortium

PubMed Central

Milne, Roger L.; Herranz, Jesús; Michailidou, Kyriaki; Dennis, Joe; Tyrer, Jonathan P.; Zamora, M. Pilar; Arias-Perez, José Ignacio; González-Neira, Anna; Pita, Guillermo; Alonso, M. Rosario; Wang, Qin; Bolla, Manjeet K.; Czene, Kamila; Eriksson, Mikael; Humphreys, Keith; Darabi, Hatef; Li, Jingmei; Anton-Culver, Hoda; Neuhausen, Susan L.; Ziogas, Argyrios; Clarke, Christina A.; Hopper, John L.; Dite, Gillian S.; Apicella, Carmel; Southey, Melissa C.; Chenevix-Trench, Georgia; Swerdlow, Anthony; Ashworth, Alan; Orr, Nicholas; Schoemaker, Minouk; Jakubowska, Anna; Lubinski, Jan; Jaworska-Bieniek, Katarzyna; Durda, Katarzyna; Andrulis, Irene L.; Knight, Julia A.; Glendon, Gord; Mulligan, Anna Marie; Bojesen, Stig E.; Nordestgaard, Børge G.; Flyger, Henrik; Nevanlinna, Heli; Muranen, Taru A.; Aittomäki, Kristiina; Blomqvist, Carl; Chang-Claude, Jenny; Rudolph, Anja; Seibold, Petra; Flesch-Janys, Dieter; Wang, Xianshu; Olson, Janet E.; Vachon, Celine; Purrington, Kristen; Winqvist, Robert; Pylkäs, Katri; Jukkola-Vuorinen, Arja; Grip, Mervi; Dunning, Alison M.; Shah, Mitul; Guénel, Pascal; Truong, Thérèse; Sanchez, Marie; Mulot, Claire; Brenner, Hermann; Dieffenbach, Aida Karina; Arndt, Volker; Stegmaier, Christa; Lindblom, Annika; Margolin, Sara; Hooning, Maartje J.; Hollestelle, Antoinette; Collée, J. Margriet; Jager, Agnes; Cox, Angela; Brock, Ian W.; Reed, Malcolm W.R.; Devilee, Peter; Tollenaar, Robert A.E.M.; Seynaeve, Caroline; Haiman, Christopher A.; Henderson, Brian E.; Schumacher, Fredrick; Le Marchand, Loic; Simard, Jacques; Dumont, Martine; Soucy, Penny; Dörk, Thilo; Bogdanova, Natalia V.; Hamann, Ute; Försti, Asta; Rüdiger, Thomas; Ulmer, Hans-Ulrich; Fasching, Peter A.; Häberle, Lothar; Ekici, Arif B.; Beckmann, Matthias W.; Fletcher, Olivia; Johnson, Nichola; dos Santos Silva, Isabel; Peto, Julian; Radice, Paolo; Peterlongo, Paolo; Peissel, Bernard; Mariani, Paolo; Giles, Graham G.; Severi, Gianluca; Baglietto, Laura; Sawyer, Elinor; Tomlinson, Ian; Kerin, Michael; Miller, Nicola; Marme, Federik; Burwinkel, Barbara; Mannermaa, Arto; Kataja, Vesa; Kosma, Veli-Matti; Hartikainen, Jaana M.; Lambrechts, Diether; Yesilyurt, Betul T.; Floris, Giuseppe; Leunen, Karin; Alnæs, Grethe Grenaker; Kristensen, Vessela; Børresen-Dale, Anne-Lise; García-Closas, Montserrat; Chanock, Stephen J.; Lissowska, Jolanta; Figueroa, Jonine D.; Schmidt, Marjanka K.; Broeks, Annegien; Verhoef, Senno; Rutgers, Emiel J.; Brauch, Hiltrud; Brüning, Thomas; Ko, Yon-Dschun; Couch, Fergus J.; Toland, Amanda E.; Yannoukakos, Drakoulis; Pharoah, Paul D.P.; Hall, Per; Benítez, Javier; Malats, Núria; Easton, Douglas F.

2014-01-01

Part of the substantial unexplained familial aggregation of breast cancer may be due to interactions between common variants, but few studies have had adequate statistical power to detect interactions of realistic magnitude. We aimed to assess all two-way interactions in breast cancer susceptibility between 70 917 single nucleotide polymorphisms (SNPs) selected primarily based on prior evidence of a marginal effect. Thirty-eight international studies contributed data for 46 450 breast cancer cases and 42 461 controls of European origin as part of a multi-consortium project (COGS). First, SNPs were preselected based on evidence (P < 0.01) of a per-allele main effect, and all two-way combinations of those were evaluated by a per-allele (1 d.f.) test for interaction using logistic regression. Second, all 2.5 billion possible two-SNP combinations were evaluated using Boolean operation-based screening and testing, and SNP pairs with the strongest evidence of interaction (P < 10−4) were selected for more careful assessment by logistic regression. Under the first approach, 3277 SNPs were preselected, but an evaluation of all possible two-SNP combinations (1 d.f.) identified no interactions at P < 10−8. Results from the second analytic approach were consistent with those from the first (P > 10−10). In summary, we observed little evidence of two-way SNP interactions in breast cancer susceptibility, despite the large number of SNPs with potential marginal effects considered and the very large sample size. This finding may have important implications for risk prediction, simplifying the modelling required. Further comprehensive, large-scale genome-wide interaction studies may identify novel interacting loci if the inherent logistic and computational challenges can be overcome. PMID:24242184

A large-scale assessment of two-way SNP interactions in breast cancer susceptibility using 46,450 cases and 42,461 controls from the breast cancer association consortium.

PubMed

Milne, Roger L; Herranz, Jesús; Michailidou, Kyriaki; Dennis, Joe; Tyrer, Jonathan P; Zamora, M Pilar; Arias-Perez, José Ignacio; González-Neira, Anna; Pita, Guillermo; Alonso, M Rosario; Wang, Qin; Bolla, Manjeet K; Czene, Kamila; Eriksson, Mikael; Humphreys, Keith; Darabi, Hatef; Li, Jingmei; Anton-Culver, Hoda; Neuhausen, Susan L; Ziogas, Argyrios; Clarke, Christina A; Hopper, John L; Dite, Gillian S; Apicella, Carmel; Southey, Melissa C; Chenevix-Trench, Georgia; Swerdlow, Anthony; Ashworth, Alan; Orr, Nicholas; Schoemaker, Minouk; Jakubowska, Anna; Lubinski, Jan; Jaworska-Bieniek, Katarzyna; Durda, Katarzyna; Andrulis, Irene L; Knight, Julia A; Glendon, Gord; Mulligan, Anna Marie; Bojesen, Stig E; Nordestgaard, Børge G; Flyger, Henrik; Nevanlinna, Heli; Muranen, Taru A; Aittomäki, Kristiina; Blomqvist, Carl; Chang-Claude, Jenny; Rudolph, Anja; Seibold, Petra; Flesch-Janys, Dieter; Wang, Xianshu; Olson, Janet E; Vachon, Celine; Purrington, Kristen; Winqvist, Robert; Pylkäs, Katri; Jukkola-Vuorinen, Arja; Grip, Mervi; Dunning, Alison M; Shah, Mitul; Guénel, Pascal; Truong, Thérèse; Sanchez, Marie; Mulot, Claire; Brenner, Hermann; Dieffenbach, Aida Karina; Arndt, Volker; Stegmaier, Christa; Lindblom, Annika; Margolin, Sara; Hooning, Maartje J; Hollestelle, Antoinette; Collée, J Margriet; Jager, Agnes; Cox, Angela; Brock, Ian W; Reed, Malcolm W R; Devilee, Peter; Tollenaar, Robert A E M; Seynaeve, Caroline; Haiman, Christopher A; Henderson, Brian E; Schumacher, Fredrick; Le Marchand, Loic; Simard, Jacques; Dumont, Martine; Soucy, Penny; Dörk, Thilo; Bogdanova, Natalia V; Hamann, Ute; Försti, Asta; Rüdiger, Thomas; Ulmer, Hans-Ulrich; Fasching, Peter A; Häberle, Lothar; Ekici, Arif B; Beckmann, Matthias W; Fletcher, Olivia; Johnson, Nichola; dos Santos Silva, Isabel; Peto, Julian; Radice, Paolo; Peterlongo, Paolo; Peissel, Bernard; Mariani, Paolo; Giles, Graham G; Severi, Gianluca; Baglietto, Laura; Sawyer, Elinor; Tomlinson, Ian; Kerin, Michael; Miller, Nicola; Marme, Federik; Burwinkel, Barbara; Mannermaa, Arto; Kataja, Vesa; Kosma, Veli-Matti; Hartikainen, Jaana M; Lambrechts, Diether; Yesilyurt, Betul T; Floris, Giuseppe; Leunen, Karin; Alnæs, Grethe Grenaker; Kristensen, Vessela; Børresen-Dale, Anne-Lise; García-Closas, Montserrat; Chanock, Stephen J; Lissowska, Jolanta; Figueroa, Jonine D; Schmidt, Marjanka K; Broeks, Annegien; Verhoef, Senno; Rutgers, Emiel J; Brauch, Hiltrud; Brüning, Thomas; Ko, Yon-Dschun; Couch, Fergus J; Toland, Amanda E; Yannoukakos, Drakoulis; Pharoah, Paul D P; Hall, Per; Benítez, Javier; Malats, Núria; Easton, Douglas F

2014-04-01

Part of the substantial unexplained familial aggregation of breast cancer may be due to interactions between common variants, but few studies have had adequate statistical power to detect interactions of realistic magnitude. We aimed to assess all two-way interactions in breast cancer susceptibility between 70,917 single nucleotide polymorphisms (SNPs) selected primarily based on prior evidence of a marginal effect. Thirty-eight international studies contributed data for 46,450 breast cancer cases and 42,461 controls of European origin as part of a multi-consortium project (COGS). First, SNPs were preselected based on evidence (P < 0.01) of a per-allele main effect, and all two-way combinations of those were evaluated by a per-allele (1 d.f.) test for interaction using logistic regression. Second, all 2.5 billion possible two-SNP combinations were evaluated using Boolean operation-based screening and testing, and SNP pairs with the strongest evidence of interaction (P < 10(-4)) were selected for more careful assessment by logistic regression. Under the first approach, 3277 SNPs were preselected, but an evaluation of all possible two-SNP combinations (1 d.f.) identified no interactions at P < 10(-8). Results from the second analytic approach were consistent with those from the first (P > 10(-10)). In summary, we observed little evidence of two-way SNP interactions in breast cancer susceptibility, despite the large number of SNPs with potential marginal effects considered and the very large sample size. This finding may have important implications for risk prediction, simplifying the modelling required. Further comprehensive, large-scale genome-wide interaction studies may identify novel interacting loci if the inherent logistic and computational challenges can be overcome.

Logistic regression for circular data

NASA Astrophysics Data System (ADS)

Al-Daffaie, Kadhem; Khan, Shahjahan

2017-05-01

This paper considers the relationship between a binary response and a circular predictor. It develops the logistic regression model by employing the linear-circular regression approach. The maximum likelihood method is used to estimate the parameters. The Newton-Raphson numerical method is used to find the estimated values of the parameters. A data set from weather records of Toowoomba city is analysed by the proposed methods. Moreover, a simulation study is considered. The R software is used for all computations and simulations.

Naval Research Logistics Quarterly. Volume 28. Number 3,

DTIC Science & Technology

1981-09-01

denotes component-wise maximum. f has antone (isotone) differences on C x D if for cl < c2 and d, < d2, NAVAL RESEARCH LOGISTICS QUARTERLY VOL. 28...or negative correlations and linear or nonlinear regressions. Given are the mo- ments to order two and, for special cases, (he regression function and...data sets. We designate this bnb distribution as G - B - N(a, 0, v). The distribution admits only of positive correlation and linear regressions

Regression approaches in the test-negative study design for assessment of influenza vaccine effectiveness.

PubMed

Bond, H S; Sullivan, S G; Cowling, B J

2016-06-01

Influenza vaccination is the most practical means available for preventing influenza virus infection and is widely used in many countries. Because vaccine components and circulating strains frequently change, it is important to continually monitor vaccine effectiveness (VE). The test-negative design is frequently used to estimate VE. In this design, patients meeting the same clinical case definition are recruited and tested for influenza; those who test positive are the cases and those who test negative form the comparison group. When determining VE in these studies, the typical approach has been to use logistic regression, adjusting for potential confounders. Because vaccine coverage and influenza incidence change throughout the season, time is included among these confounders. While most studies use unconditional logistic regression, adjusting for time, an alternative approach is to use conditional logistic regression, matching on time. Here, we used simulation data to examine the potential for both regression approaches to permit accurate and robust estimates of VE. In situations where vaccine coverage changed during the influenza season, the conditional model and unconditional models adjusting for categorical week and using a spline function for week provided more accurate estimates. We illustrated the two approaches on data from a test-negative study of influenza VE against hospitalization in children in Hong Kong which resulted in the conditional logistic regression model providing the best fit to the data.

Effects of Sleep Quality on the Association between Problematic Mobile Phone Use and Mental Health Symptoms in Chinese College Students

PubMed Central

Tao, Shuman; Wu, Xiaoyan; Zhang, Yukun; Zhang, Shichen; Tong, Shilu; Tao, Fangbiao

2017-01-01

Problematic mobile phone use (PMPU) is a risk factor for both adolescents’ sleep quality and mental health. It is important to examine the potential negative health effects of PMPU exposure. This study aims to evaluate PMPU and its association with mental health in Chinese college students. Furthermore, we investigated how sleep quality influences this association. In 2013, we collected data regarding participants’ PMPU, sleep quality, and mental health (psychopathological symptoms, anxiety, and depressive symptoms) by standardized questionnaires in 4747 college students. Multivariate logistic regression analysis was applied to assess independent effects and interactions of PMPU and sleep quality with mental health. PMPU and poor sleep quality were observed in 28.2% and 9.8% of participants, respectively. Adjusted logistic regression models suggested independent associations of PMPU and sleep quality with mental health (p < 0.001). Further regression analyses suggested a significant interaction between these measures (p < 0.001). The study highlights that poor sleep quality may play a more significant role in increasing the risk of mental health problems in students with PMPU than in those without PMPU. PMID:28216583

A novel hybrid method of beta-turn identification in protein using binary logistic regression and neural network

PubMed Central

Asghari, Mehdi Poursheikhali; Hayatshahi, Sayyed Hamed Sadat; Abdolmaleki, Parviz

2012-01-01

From both the structural and functional points of view, β-turns play important biological roles in proteins. In the present study, a novel two-stage hybrid procedure has been developed to identify β-turns in proteins. Binary logistic regression was initially used for the first time to select significant sequence parameters in identification of β-turns due to a re-substitution test procedure. Sequence parameters were consisted of 80 amino acid positional occurrences and 20 amino acid percentages in sequence. Among these parameters, the most significant ones which were selected by binary logistic regression model, were percentages of Gly, Ser and the occurrence of Asn in position i+2, respectively, in sequence. These significant parameters have the highest effect on the constitution of a β-turn sequence. A neural network model was then constructed and fed by the parameters selected by binary logistic regression to build a hybrid predictor. The networks have been trained and tested on a non-homologous dataset of 565 protein chains. With applying a nine fold cross-validation test on the dataset, the network reached an overall accuracy (Qtotal) of 74, which is comparable with results of the other β-turn prediction methods. In conclusion, this study proves that the parameter selection ability of binary logistic regression together with the prediction capability of neural networks lead to the development of more precise models for identifying β-turns in proteins. PMID:27418910

A novel hybrid method of beta-turn identification in protein using binary logistic regression and neural network.

PubMed

Asghari, Mehdi Poursheikhali; Hayatshahi, Sayyed Hamed Sadat; Abdolmaleki, Parviz

2012-01-01

From both the structural and functional points of view, β-turns play important biological roles in proteins. In the present study, a novel two-stage hybrid procedure has been developed to identify β-turns in proteins. Binary logistic regression was initially used for the first time to select significant sequence parameters in identification of β-turns due to a re-substitution test procedure. Sequence parameters were consisted of 80 amino acid positional occurrences and 20 amino acid percentages in sequence. Among these parameters, the most significant ones which were selected by binary logistic regression model, were percentages of Gly, Ser and the occurrence of Asn in position i+2, respectively, in sequence. These significant parameters have the highest effect on the constitution of a β-turn sequence. A neural network model was then constructed and fed by the parameters selected by binary logistic regression to build a hybrid predictor. The networks have been trained and tested on a non-homologous dataset of 565 protein chains. With applying a nine fold cross-validation test on the dataset, the network reached an overall accuracy (Qtotal) of 74, which is comparable with results of the other β-turn prediction methods. In conclusion, this study proves that the parameter selection ability of binary logistic regression together with the prediction capability of neural networks lead to the development of more precise models for identifying β-turns in proteins.

Differential item functioning analysis with ordinal logistic regression techniques. DIFdetect and difwithpar.

PubMed

Crane, Paul K; Gibbons, Laura E; Jolley, Lance; van Belle, Gerald

2006-11-01

We present an ordinal logistic regression model for identification of items with differential item functioning (DIF) and apply this model to a Mini-Mental State Examination (MMSE) dataset. We employ item response theory ability estimation in our models. Three nested ordinal logistic regression models are applied to each item. Model testing begins with examination of the statistical significance of the interaction term between ability and the group indicator, consistent with nonuniform DIF. Then we turn our attention to the coefficient of the ability term in models with and without the group term. If including the group term has a marked effect on that coefficient, we declare that it has uniform DIF. We examined DIF related to language of test administration in addition to self-reported race, Hispanic ethnicity, age, years of education, and sex. We used PARSCALE for IRT analyses and STATA for ordinal logistic regression approaches. We used an iterative technique for adjusting IRT ability estimates on the basis of DIF findings. Five items were found to have DIF related to language. These same items also had DIF related to other covariates. The ordinal logistic regression approach to DIF detection, when combined with IRT ability estimates, provides a reasonable alternative for DIF detection. There appear to be several items with significant DIF related to language of test administration in the MMSE. More attention needs to be paid to the specific criteria used to determine whether an item has DIF, not just the technique used to identify DIF.

Conditional Poisson models: a flexible alternative to conditional logistic case cross-over analysis.

PubMed

Armstrong, Ben G; Gasparrini, Antonio; Tobias, Aurelio

2014-11-24

The time stratified case cross-over approach is a popular alternative to conventional time series regression for analysing associations between time series of environmental exposures (air pollution, weather) and counts of health outcomes. These are almost always analyzed using conditional logistic regression on data expanded to case-control (case crossover) format, but this has some limitations. In particular adjusting for overdispersion and auto-correlation in the counts is not possible. It has been established that a Poisson model for counts with stratum indicators gives identical estimates to those from conditional logistic regression and does not have these limitations, but it is little used, probably because of the overheads in estimating many stratum parameters. The conditional Poisson model avoids estimating stratum parameters by conditioning on the total event count in each stratum, thus simplifying the computing and increasing the number of strata for which fitting is feasible compared with the standard unconditional Poisson model. Unlike the conditional logistic model, the conditional Poisson model does not require expanding the data, and can adjust for overdispersion and auto-correlation. It is available in Stata, R, and other packages. By applying to some real data and using simulations, we demonstrate that conditional Poisson models were simpler to code and shorter to run than are conditional logistic analyses and can be fitted to larger data sets than possible with standard Poisson models. Allowing for overdispersion or autocorrelation was possible with the conditional Poisson model but when not required this model gave identical estimates to those from conditional logistic regression. Conditional Poisson regression models provide an alternative to case crossover analysis of stratified time series data with some advantages. The conditional Poisson model can also be used in other contexts in which primary control for confounding is by fine stratification.

Use of generalized ordered logistic regression for the analysis of multidrug resistance data.

PubMed

Agga, Getahun E; Scott, H Morgan

2015-10-01

Statistical analysis of antimicrobial resistance data largely focuses on individual antimicrobial's binary outcome (susceptible or resistant). However, bacteria are becoming increasingly multidrug resistant (MDR). Statistical analysis of MDR data is mostly descriptive often with tabular or graphical presentations. Here we report the applicability of generalized ordinal logistic regression model for the analysis of MDR data. A total of 1,152 Escherichia coli, isolated from the feces of weaned pigs experimentally supplemented with chlortetracycline (CTC) and copper, were tested for susceptibilities against 15 antimicrobials and were binary classified into resistant or susceptible. The 15 antimicrobial agents tested were grouped into eight different antimicrobial classes. We defined MDR as the number of antimicrobial classes to which E. coli isolates were resistant ranging from 0 to 8. Proportionality of the odds assumption of the ordinal logistic regression model was violated only for the effect of treatment period (pre-treatment, during-treatment and post-treatment); but not for the effect of CTC or copper supplementation. Subsequently, a partially constrained generalized ordinal logistic model was built that allows for the effect of treatment period to vary while constraining the effects of treatment (CTC and copper supplementation) to be constant across the levels of MDR classes. Copper (Proportional Odds Ratio [Prop OR]=1.03; 95% CI=0.73-1.47) and CTC (Prop OR=1.1; 95% CI=0.78-1.56) supplementation were not significantly associated with the level of MDR adjusted for the effect of treatment period. MDR generally declined over the trial period. In conclusion, generalized ordered logistic regression can be used for the analysis of ordinal data such as MDR data when the proportionality assumptions for ordered logistic regression are violated. Published by Elsevier B.V.

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.

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.

PREDICTION OF MALIGNANT BREAST LESIONS FROM MRI FEATURES: A COMPARISON OF ARTIFICIAL NEURAL NETWORK AND LOGISTIC REGRESSION TECHNIQUES

PubMed Central

McLaren, Christine E.; Chen, Wen-Pin; Nie, Ke; Su, Min-Ying

2009-01-01

Rationale and Objectives Dynamic contrast enhanced MRI (DCE-MRI) is a clinical imaging modality for detection and diagnosis of breast lesions. Analytical methods were compared for diagnostic feature selection and performance of lesion classification to differentiate between malignant and benign lesions in patients. Materials and Methods The study included 43 malignant and 28 benign histologically-proven lesions. Eight morphological parameters, ten gray level co-occurrence matrices (GLCM) texture features, and fourteen Laws’ texture features were obtained using automated lesion segmentation and quantitative feature extraction. Artificial neural network (ANN) and logistic regression analysis were compared for selection of the best predictors of malignant lesions among the normalized features. Results Using ANN, the final four selected features were compactness, energy, homogeneity, and Law_LS, with area under the receiver operating characteristic curve (AUC) = 0.82, and accuracy = 0.76. The diagnostic performance of these 4-features computed on the basis of logistic regression yielded AUC = 0.80 (95% CI, 0.688 to 0.905), similar to that of ANN. The analysis also shows that the odds of a malignant lesion decreased by 48% (95% CI, 25% to 92%) for every increase of 1 SD in the Law_LS feature, adjusted for differences in compactness, energy, and homogeneity. Using logistic regression with z-score transformation, a model comprised of compactness, NRL entropy, and gray level sum average was selected, and it had the highest overall accuracy of 0.75 among all models, with AUC = 0.77 (95% CI, 0.660 to 0.880). When logistic modeling of transformations using the Box-Cox method was performed, the most parsimonious model with predictors, compactness and Law_LS, had an AUC of 0.79 (95% CI, 0.672 to 0.898). Conclusion The diagnostic performance of models selected by ANN and logistic regression was similar. The analytic methods were found to be roughly equivalent in terms of predictive ability when a small number of variables were chosen. The robust ANN methodology utilizes a sophisticated non-linear model, while logistic regression analysis provides insightful information to enhance interpretation of the model features. PMID:19409817

Logistic regression analysis of factors associated with avascular necrosis of the femoral head following femoral neck fractures in middle-aged and elderly patients.

PubMed

Ai, Zi-Sheng; Gao, You-Shui; Sun, Yuan; Liu, Yue; Zhang, Chang-Qing; Jiang, Cheng-Hua

2013-03-01

Risk factors for femoral neck fracture-induced avascular necrosis of the femoral head have not been elucidated clearly in middle-aged and elderly patients. Moreover, the high incidence of screw removal in China and its effect on the fate of the involved femoral head require statistical methods to reflect their intrinsic relationship. Ninety-nine patients older than 45 years with femoral neck fracture were treated by internal fixation between May 1999 and April 2004. Descriptive analysis, interaction analysis between associated factors, single factor logistic regression, multivariate logistic regression, and detailed interaction analysis were employed to explore potential relationships among associated factors. Avascular necrosis of the femoral head was found in 15 cases (15.2 %). Age × the status of implants (removal vs. maintenance) and gender × the timing of reduction were interactive according to two-factor interactive analysis. Age, the displacement of fractures, the quality of reduction, and the status of implants were found to be significant factors in single factor logistic regression analysis. Age, age × the status of implants, and the quality of reduction were found to be significant factors in multivariate logistic regression analysis. In fine interaction analysis after multivariate logistic regression analysis, implant removal was the most important risk factor for avascular necrosis in 56-to-85-year-old patients, with a risk ratio of 26.00 (95 % CI = 3.076-219.747). The middle-aged and elderly have less incidence of avascular necrosis of the femoral head following femoral neck fractures treated by cannulated screws. The removal of cannulated screws can induce a significantly high incidence of avascular necrosis of the femoral head in elderly patients, while a high-quality reduction is helpful to reduce avascular necrosis.

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.

Regression discontinuity was a valid design for dichotomous outcomes in three randomized trials.

PubMed

van Leeuwen, Nikki; Lingsma, Hester F; Mooijaart, Simon P; Nieboer, Daan; Trompet, Stella; Steyerberg, Ewout W

2018-06-01

Regression discontinuity (RD) is a quasi-experimental design that may provide valid estimates of treatment effects in case of continuous outcomes. We aimed to evaluate validity and precision in the RD design for dichotomous outcomes. We performed validation studies in three large randomized controlled trials (RCTs) (Corticosteroid Randomization After Significant Head injury [CRASH], the Global Utilization of Streptokinase and Tissue Plasminogen Activator for Occluded Coronary Arteries [GUSTO], and PROspective Study of Pravastatin in elderly individuals at risk of vascular disease [PROSPER]). To mimic the RD design, we selected patients above and below a cutoff (e.g., age 75 years) randomized to treatment and control, respectively. Adjusted logistic regression models using restricted cubic splines (RCS) and polynomials and local logistic regression models estimated the odds ratio (OR) for treatment, with 95% confidence intervals (CIs) to indicate precision. In CRASH, treatment increased mortality with OR 1.22 [95% CI 1.06-1.40] in the RCT. The RD estimates were 1.42 (0.94-2.16) and 1.13 (0.90-1.40) with RCS adjustment and local regression, respectively. In GUSTO, treatment reduced mortality (OR 0.83 [0.72-0.95]), with more extreme estimates in the RD analysis (OR 0.57 [0.35; 0.92] and 0.67 [0.51; 0.86]). In PROSPER, similar RCT and RD estimates were found, again with less precision in RD designs. We conclude that the RD design provides similar but substantially less precise treatment effect estimates compared with an RCT, with local regression being the preferred method of analysis. Copyright © 2018 Elsevier Inc. All rights reserved.

Providing written language services in the schools: the time is now.

PubMed

Fallon, Karen A; Katz, Lauren A

2011-01-01

The current study was conducted to investigate the provision of written language services by school-based speech-language pathologists (SLPs). Specifically, the study examined SLPs' knowledge, attitudes, and collaborative practices in the area of written language services as well as the variables that impact provision of these services. Public school-based SLPs from across the country were solicited for participation in an online, Web-based survey. Data from 645 full-time SLPs from 49 states were evaluated using descriptive statistics and logistic regression. Many school-based SLPs reported not providing any services in the area of written language to students with written language weaknesses. Knowledge, attitudes, and collaborative practices were mixed. A logistic regression revealed three variables likely to predict high levels of service provision in the area of written language. Data from the current study revealed that many struggling readers and writers on school-based SLPs' caseloads are not receiving services from their SLPs. Implications for SLPs' preservice preparation, continuing education, and doctoral preparation are discussed.

The severity of Minamata disease declined in 25 years: temporal profile of the neurological findings analyzed by multiple logistic regression model.

PubMed

Uchino, Makoto; Hirano, Teruyuki; Satoh, Hiroshi; Arimura, Kimiyoshi; Nakagawa, Masanori; Wakamiya, Jyunji

2005-01-01

Minamata disease (MD) was caused by ingestion of seafood from the methylmercury-contaminated areas. Although 50 years have passed since the discovery of MD, there have been only a few studies on the temporal profile of neurological findings in certified MD patients. Thus, we evaluated changes in neurological symptoms and signs of MD using discriminants by multiple logistic regression analysis. The severity of predictive index declined in 25 years in most of the patients. Only a few patients showed aggravation of neurological findings, which was due to complications such as spino-cerebellar degeneration. Patients with chronic MD aged over 45 years had several concomitant diseases so that their clinical pictures were complicated. It was difficult to differentiate chronic MD using statistically established discriminants based on sensory disturbance alone. In conclusion, the severity of MD declined in 25 years along with the modification by age-related concomitant disorders.

Efficient logistic regression designs under an imperfect population identifier.

PubMed

Albert, Paul S; Liu, Aiyi; Nansel, Tonja

2014-03-01

Motivated by actual study designs, this article considers efficient logistic regression designs where the population is identified with a binary test that is subject to diagnostic error. We consider the case where the imperfect test is obtained on all participants, while the gold standard test is measured on a small chosen subsample. Under maximum-likelihood estimation, we evaluate the optimal design in terms of sample selection as well as verification. We show that there may be substantial efficiency gains by choosing a small percentage of individuals who test negative on the imperfect test for inclusion in the sample (e.g., verifying 90% test-positive cases). We also show that a two-stage design may be a good practical alternative to a fixed design in some situations. Under optimal and nearly optimal designs, we compare maximum-likelihood and semi-parametric efficient estimators under correct and misspecified models with simulations. The methodology is illustrated with an analysis from a diabetes behavioral intervention trial. © 2013, The International Biometric Society.

Rank-Optimized Logistic Matrix Regression toward Improved Matrix Data Classification.

PubMed

Zhang, Jianguang; Jiang, Jianmin

2018-02-01

While existing logistic regression suffers from overfitting and often fails in considering structural information, we propose a novel matrix-based logistic regression to overcome the weakness. In the proposed method, 2D matrices are directly used to learn two groups of parameter vectors along each dimension without vectorization, which allows the proposed method to fully exploit the underlying structural information embedded inside the 2D matrices. Further, we add a joint [Formula: see text]-norm on two parameter matrices, which are organized by aligning each group of parameter vectors in columns. This added co-regularization term has two roles-enhancing the effect of regularization and optimizing the rank during the learning process. With our proposed fast iterative solution, we carried out extensive experiments. The results show that in comparison to both the traditional tensor-based methods and the vector-based regression methods, our proposed solution achieves better performance for matrix data classifications.

Explicit criteria for prioritization of cataract surgery

PubMed Central

Ma Quintana, José; Escobar, Antonio; Bilbao, Amaia

2006-01-01

Background Consensus techniques have been used previously to create explicit criteria to prioritize cataract extraction; however, the appropriateness of the intervention was not included explicitly in previous studies. We developed a prioritization tool for cataract extraction according to the RAND method. Methods Criteria were developed using a modified Delphi panel judgment process. A panel of 11 ophthalmologists was assembled. Ratings were analyzed regarding the level of agreement among panelists. We studied the effect of all variables on the final panel score using general linear and logistic regression models. Priority scoring systems were developed by means of optimal scaling and general linear models. The explicit criteria developed were summarized by means of regression tree analysis. Results Eight variables were considered to create the indications. Of the 310 indications that the panel evaluated, 22.6% were considered high priority, 52.3% intermediate priority, and 25.2% low priority. Agreement was reached for 31.9% of the indications and disagreement for 0.3%. Logistic regression and general linear models showed that the preoperative visual acuity of the cataractous eye, visual function, and anticipated visual acuity postoperatively were the most influential variables. Alternative and simple scoring systems were obtained by optimal scaling and general linear models where the previous variables were also the most important. The decision tree also shows the importance of the previous variables and the appropriateness of the intervention. Conclusion Our results showed acceptable validity as an evaluation and management tool for prioritizing cataract extraction. It also provides easy algorithms for use in clinical practice. PMID:16512893

Detecting DIF in Polytomous Items Using MACS, IRT and Ordinal Logistic Regression

ERIC Educational Resources Information Center

Elosua, Paula; Wells, Craig

2013-01-01

The purpose of the present study was to compare the Type I error rate and power of two model-based procedures, the mean and covariance structure model (MACS) and the item response theory (IRT), and an observed-score based procedure, ordinal logistic regression, for detecting differential item functioning (DIF) in polytomous items. A simulation…

Accuracy of Bayes and Logistic Regression Subscale Probabilities for Educational and Certification Tests

ERIC Educational Resources Information Center

Rudner, Lawrence

2016-01-01

In the machine learning literature, it is commonly accepted as fact that as calibration sample sizes increase, Naïve Bayes classifiers initially outperform Logistic Regression classifiers in terms of classification accuracy. Applied to subtests from an on-line final examination and from a highly regarded certification examination, this study shows…

Comparing Linear Discriminant Function with Logistic Regression for the Two-Group Classification Problem.

ERIC Educational Resources Information Center

Fan, Xitao; Wang, Lin

The Monte Carlo study compared the performance of predictive discriminant analysis (PDA) and that of logistic regression (LR) for the two-group classification problem. Prior probabilities were used for classification, but the cost of misclassification was assumed to be equal. The study used a fully crossed three-factor experimental design (with…

Effects of Social Class and School Conditions on Educational Enrollment and Achievement of Boys and Girls in Rural Viet Nam

ERIC Educational Resources Information Center

Nguyen, Phuong L.

2006-01-01

This study examines the effects of parental SES, school quality, and community factors on children's enrollment and achievement in rural areas in Viet Nam, using logistic regression and ordered logistic regression. Multivariate analysis reveals significant differences in educational enrollment and outcomes by level of household expenditures and…

School Exits in the Milwaukee Parental Choice Program: Evidence of a Marketplace?

ERIC Educational Resources Information Center

Ford, Michael

2011-01-01

This article examines whether the large number of school exits from the Milwaukee school voucher program is evidence of a marketplace. Two logistic regression and multinomial logistic regression models tested the relation between the inability to draw large numbers of voucher students and the ability for a private school to remain viable. Data on…

Hierarchical Bayesian Logistic Regression to forecast metabolic control in type 2 DM patients.

PubMed

Dagliati, Arianna; Malovini, Alberto; Decata, Pasquale; Cogni, Giulia; Teliti, Marsida; Sacchi, Lucia; Cerra, Carlo; Chiovato, Luca; Bellazzi, Riccardo

2016-01-01

In this work we present our efforts in building a model able to forecast patients' changes in clinical conditions when repeated measurements are available. In this case the available risk calculators are typically not applicable. We propose a Hierarchical Bayesian Logistic Regression model, which allows taking into account individual and population variability in model parameters estimate. The model is used to predict metabolic control and its variation in type 2 diabetes mellitus. In particular we have analyzed a population of more than 1000 Italian type 2 diabetic patients, collected within the European project Mosaic. The results obtained in terms of Matthews Correlation Coefficient are significantly better than the ones gathered with standard logistic regression model, based on data pooling.

An empirical study of statistical properties of variance partition coefficients for multi-level logistic regression models

USGS Publications Warehouse

Li, Ji; Gray, B.R.; Bates, D.M.

2008-01-01

Partitioning the variance of a response by design levels is challenging for binomial and other discrete outcomes. Goldstein (2003) proposed four definitions for variance partitioning coefficients (VPC) under a two-level logistic regression model. In this study, we explicitly derived formulae for multi-level logistic regression model and subsequently studied the distributional properties of the calculated VPCs. Using simulations and a vegetation dataset, we demonstrated associations between different VPC definitions, the importance of methods for estimating VPCs (by comparing VPC obtained using Laplace and penalized quasilikehood methods), and bivariate dependence between VPCs calculated at different levels. Such an empirical study lends an immediate support to wider applications of VPC in scientific data analysis.

Model building strategy for logistic regression: purposeful selection.

PubMed

Zhang, Zhongheng

2016-03-01

Logistic regression is one of the most commonly used models to account for confounders in medical literature. The article introduces how to perform purposeful selection model building strategy with R. I stress on the use of likelihood ratio test to see whether deleting a variable will have significant impact on model fit. A deleted variable should also be checked for whether it is an important adjustment of remaining covariates. Interaction should be checked to disentangle complex relationship between covariates and their synergistic effect on response variable. Model should be checked for the goodness-of-fit (GOF). In other words, how the fitted model reflects the real data. Hosmer-Lemeshow GOF test is the most widely used for logistic regression model.

Retention of Children and Their Families in the Longitudinal Outcome Study of the Comprehensive Community Mental Health Services for Children and Their Families Program: A Multilevel Analysis

ERIC Educational Resources Information Center

Gebreselassie, Tesfayi; Stephens, Robert L.; Maples, Connie J.; Johnson, Stacy F.; Tucker, Alyce L.

2014-01-01

Predictors of retention of participants in a longitudinal study and heterogeneity between communities were investigated using a multilevel logistic regression model. Data from the longitudinal outcome study of the national evaluation of the Comprehensive Community Mental Health Services for Children and Their Families program and information on…

Determinants of Increasing Duration of First Unemployment among First Degree Holders in Rwanda: A Logistic Regression Analysis

ERIC Educational Resources Information Center

Niragire, François; Nshimyiryo, Alphonse

2017-01-01

Unexpectedly, the duration of first unemployment among first degree holders has quickly increased in Rwanda after considerable loss of the skilled labour during the war and Genocide perpetrated against Tutsi in 1994. The time it takes a higher education graduate to land a first employment is a key indicator for the evaluation of and optimal…

Operative factors associated with short-term outcome in horses with large colon volvulus: 47 cases from 2006 to 2013

PubMed Central

Gonzalez, L. M.; Fogle, C. A.; Baker, W. T.; Hughes, F. E.; Law, J. M.; Motsinger-Reif, A. A.; Blikslager, A. T.

2014-01-01

Summary Reasons for performing the study There is an important need for objective parameters that accurately predict the outcome of horses with large colon volvulus. Objectives To evaluate the predictive value of a series of histomorphometric parameters on short-term outcome, as well as the impact of colonic resection on horses with large colon volvulus. Study Design Retrospective cohort study Methods Adult horses admitted to the Equine and Farm Animal Veterinary Center at North Carolina State University, Peterson & Smith and Chino Valley Equine Hospitals between 2006–2013 undergoing an exploratory celiotomy, diagnosed with large colon volvulus of ≥360 degrees, where a pelvic flexure biopsy was obtained, and that recovered from general anaesthesia, were selected for inclusion in the study. Logistic regression was used to determine associations between signalment, histomorphometric measurements of interstitial: crypt ratio, degree of haemorrhage, percentage loss of luminal and glandular epithelium, as well as colonic resection with short-term outcome (discharge from the hospital). Results Pelvic flexure biopsies from 47 horses with large colon volvulus were evaluated. Factors that were significantly associated with short-term outcome on univariate logistic regression were Thoroughbred breed (P = 0.04), interstitial: crypt ratio >1 (P = 0.02) and haemorrhage score ≥3 (P = 0.005). Resection (P = 0.92) was not found to be significantly associated with short-term outcome. No combined factors increased the likelihood of death in forward stepwise logistic regression modelling. A digitally quantified haemorrhage area measurement strengthened the association of haemorrhage with non-survival in cases of large colon volvulus. Conclusions Histomorphometric measurements of interstitial: crypt ratio and degree of haemorrhage predict short-term outcome in cases of large colon volvulus. Resection was not associated with short-term outcome in horses selected for this study. Accurate quantification of mucosal haemorrhage at the time of surgery may improve veterinary surgeons’ prognostic capabilities in horses with large colon volvulus. PMID:24735170

Operative factors associated with short-term outcome in horses with large colon volvulus: 47 cases from 2006 to 2013.

PubMed

Gonzalez, L M; Fogle, C A; Baker, W T; Hughes, F E; Law, J M; Motsinger-Reif, A A; Blikslager, A T

2015-05-01

There is an important need for objective parameters that accurately predict the outcome of horses with large colon volvulus. To evaluate the predictive value of a series of histomorphometric parameters on short-term outcome, as well as the impact of colonic resection on horses with large colon volvulus. Retrospective cohort study. Adult horses admitted to the Equine and Farm Animal Veterinary Center at North Carolina State University, Peterson and Smith and Chino Valley Equine Hospitals between 2006 and 2013 that underwent an exploratory coeliotomy, diagnosed with large colon volvulus of ≥360 degrees, where a pelvic flexure biopsy was obtained, and that recovered from general anaesthesia, were selected for inclusion in the study. Logistic regression was used to determine associations between signalment, histomorphometric measurements of interstitium-to-crypt ratio, degree of haemorrhage, percentage loss of luminal and glandular epithelium, as well as colonic resection with short-term outcome (discharge from the hospital). Pelvic flexure biopsies from 47 horses with large colon volvulus were evaluated. Factors that were significantly associated with short-term outcome on univariate logistic regression were Thoroughbred breed (P = 0.04), interstitium-to-crypt ratio >1 (P = 0.02) and haemorrhage score ≥3 (P = 0.005). Resection (P = 0.92) was not found to be associated significantly with short-term outcome. No combined factors increased the likelihood of death in forward stepwise logistic regression modelling. A digitally quantified measurement of haemorrhage area strengthened the association of haemorrhage with nonsurvival in cases of large colon volvulus. Histomorphometric measurements of interstitium-to-crypt ratio and degree of haemorrhage predict short-term outcome in cases of large colon volvulus. Resection was not associated with short-term outcome in horses selected for this study. Accurate quantification of mucosal haemorrhage at the time of surgery may improve veterinary surgeons' prognostic capabilities in horses with large colon volvulus. © 2014 EVJ Ltd.

SU-F-R-22: Malignancy Classification for Small Pulmonary Nodules with Radiomics and Logistic Regression

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

Huang, W; Tu, S

Purpose: We conducted a retrospective study of Radiomics research for classifying malignancy of small pulmonary nodules. A machine learning algorithm of logistic regression and open research platform of Radiomics, IBEX (Imaging Biomarker Explorer), were used to evaluate the classification accuracy. Methods: The training set included 100 CT image series from cancer patients with small pulmonary nodules where the average diameter is 1.10 cm. These patients registered at Chang Gung Memorial Hospital and received a CT-guided operation of lung cancer lobectomy. The specimens were classified by experienced pathologists with a B (benign) or M (malignant). CT images with slice thickness ofmore » 0.625 mm were acquired from a GE BrightSpeed 16 scanner. The study was formally approved by our institutional internal review board. Nodules were delineated and 374 feature parameters were extracted from IBEX. We first used the t-test and p-value criteria to study which feature can differentiate between group B and M. Then we implemented a logistic regression algorithm to perform nodule malignancy classification. 10-fold cross-validation and the receiver operating characteristic curve (ROC) were used to evaluate the classification accuracy. Finally hierarchical clustering analysis, Spearman rank correlation coefficient, and clustering heat map were used to further study correlation characteristics among different features. Results: 238 features were found differentiable between group B and M based on whether their statistical p-values were less than 0.05. A forward search algorithm was used to select an optimal combination of features for the best classification and 9 features were identified. Our study found the best accuracy of classifying malignancy was 0.79±0.01 with the 10-fold cross-validation. The area under the ROC curve was 0.81±0.02. Conclusion: Benign nodules may be treated as a malignant tumor in low-dose CT and patients may undergo unnecessary surgeries or treatments. Our study may help radiologists to differentiate nodule malignancy for low-dose CT.« less

Prayer at Midlife is Associated with Reduced Risk of Cognitive Decline in Arabic Women

PubMed Central

Inzelberg, Rivka; Afgin, Anne E; Massarwa, Magda; Schechtman, Edna; Israeli-Korn, Simon D.; Strugatsky, Rosa; Abuful, Amin; Kravitz, Efrat; Farrer, Lindsay A.; Friedland, Robert P.

2013-01-01

Midlife habits may be important for the later development of Alzheimer's disease (AD). We estimated the contribution of midlife prayer to the development of cognitive decline. In a door-to-door survey, residents aged ≥65 years were systematically evaluated in Arabic including medical history, neurological, cognitive examination, and a midlife leisure-activities questionnaire. Praying was assessed by the number of monthly praying hours at midlife. Stepwise logistic regression models were used to evaluate the effect of prayer on the odds of mild cognitive impairment (MCI) and AD versus cognitively normal individuals. Of 935 individuals that were approached, 778 [normal controls (n=448), AD (n=92) and MCI (n=238)] were evaluated. A higher proportion of cognitively normal individuals engaged in prayer at midlife [(87%) versus MCI (71%) or AD (69%) (p<0.0001)]. Since 94% of males engaged in prayer, the effect on cognitive decline could not be assessed in men. Among women, stepwise logistic regression adjusted for age and education, showed that prayer was significantly associated with reduced risk of MCI (p=0.027, OR=0.55, 95% CI 0.33-0.94), but not AD. Among individuals endorsing prayer activity, the amount of prayer was not associated with MCI or AD in either gender. Praying at midlife is associated with lower risk of mild cognitive impairment in women. PMID:23116476

Ultrasound predictors of mortality in monochorionic twins with selective intrauterine growth restriction.

PubMed

Ishii, K; Murakoshi, T; Hayashi, S; Saito, M; Sago, H; Takahashi, Y; Sumie, M; Nakata, M; Matsushita, M; Shinno, T; Naruse, H; Torii, Y

2011-01-01

The aim of this study was to evaluate the use of ultrasound assessment to predict risk of mortality in expectantly managed monochorionic twin fetuses with selective intrauterine growth restriction (sIUGR). This was a retrospective study of 101 monochorionic twin pregnancies diagnosed with sIUGR before 26 weeks of gestation. All patients were under expectant management during the observation period. At the initial evaluation, the presence or absence of each of the following abnormalities was documented: oligohydramnios; stuck twin phenomenon; severe IUGR < 3(rd) centile of estimated fetal weight; abnormal Doppler in the umbilical artery; and polyhydramnios in the larger twin. The relationships between these ultrasound findings and mortality of sIUGR fetuses were evaluated using multiple logistic regression analysis. Of 101 sIUGR twins, 22 (21.8%) fetuses suffered intrauterine demise and nine (8.9%) suffered neonatal death; 70 (69.3%) survived the neonatal period. Multiple logistic regression analysis revealed that the stuck twin phenomenon (odds ratio (OR): 14.5; 95% CI: 2.2-93.2; P = 0.006) and constantly absent diastolic flow in the umbilical artery (OR: 29.4; 95% CI: 3.3-264.0; P = 0.003) were significant risk factors for mortality. Not only abnormal Doppler flow in the umbilical artery but also severe oligohydramnios should be recognized as important indicators for mortality in monochorionic twins with sIUGR.

Prayer at midlife is associated with reduced risk of cognitive decline in Arabic women.

PubMed

Inzelberg, Rivka; Afgin, Anne E; Massarwa, Magda; Schechtman, Edna; Israeli-Korn, Simon D; Strugatsky, Rosa; Abuful, Amin; Kravitz, Efrat; Farrer, Lindsay A; Friedland, Robert P

2013-03-01

Midlife habits may be important for the later development of Alzheimer's disease (AD). We estimated the contribution of midlife prayer to the development of cognitive decline. In a door-to-door survey, residents aged ≥65 years were systematically evaluated in Arabic including medical history, neurological, cognitive examination, and a midlife leisure-activities questionnaire. Praying was assessed by the number of monthly praying hours at midlife. Stepwise logistic regression models were used to evaluate the effect of prayer on the odds of mild cognitive impairment (MCI) and AD versus cognitively normal individuals. Of 935 individuals that were approached, 778 [normal controls (n=448), AD (n=92) and MCI (n=238)] were evaluated. A higher proportion of cognitively normal individuals engaged in prayer at midlife [(87%) versus MCI (71%) or AD (69%) (p<0.0001)]. Since 94% of males engaged in prayer, the effect on cognitive decline could not be assessed in men. Among women, stepwise logistic regression adjusted for age and education, showed that prayer was significantly associated with reduced risk of MCI (p=0.027, OR=0.55, 95% CI 0.33-0.94), but not AD. Among individuals endorsing prayer activity, the amount of prayer was not associated with MCI or AD in either gender. Praying at midlife is associated with lower risk of mild cognitive impairment in women.

Multivariate Models for Prediction of Human Skin Sensitization ...

EPA Pesticide Factsheets

One of the lnteragency Coordinating Committee on the Validation of Alternative Method's (ICCVAM) top priorities is the development and evaluation of non-animal approaches to identify potential skin sensitizers. The complexity of biological events necessary to produce skin sensitization suggests that no single alternative method will replace the currently accepted animal tests. ICCVAM is evaluating an integrated approach to testing and assessment based on the adverse outcome pathway for skin sensitization that uses machine learning approaches to predict human skin sensitization hazard. We combined data from three in chemico or in vitro assays - the direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT) and KeratinoSens TM assay - six physicochemical properties and an in silico read-across prediction of skin sensitization hazard into 12 variable groups. The variable groups were evaluated using two machine learning approaches , logistic regression and support vector machine, to predict human skin sensitization hazard. Models were trained on 72 substances and tested on an external set of 24 substances. The six models (three logistic regression and three support vector machine) with the highest accuracy (92%) used: (1) DPRA, h-CLAT and read-across; (2) DPRA, h-CLAT, read-across and KeratinoSens; or (3) DPRA, h-CLAT, read-across, KeratinoSens and log P. The models performed better at predicting human skin sensitization hazard than the murine

Transnasal endoscopic evaluation of swallowing: a bedside technique to evaluate ability to swallow pureed diets in elderly patients with dysphagia.

PubMed

Sakamoto, Torao; Horiuchi, Akira; Nakayama, Yoshiko

2013-08-01

Endoscopic evaluation of swallowing (EES) is not commonly used by gastroenterologists to evaluate swallowing in patients with dysphagia. To use transnasal endoscopy to identify factors predicting successful or failed swallowing of pureed foods in elderly patients with dysphagia. EES of pureed foods was performed by a gastroenterologist using a small-calibre transnasal endoscope. Factors related to successful versus unsuccessful swallowing of pureed foods were analyzed with regard to age, comorbid diseases, swallowing activity, saliva pooling, vallecular residues, pharyngeal residues and airway penetration⁄aspiration. Unsuccessful swallowing was defined in patients who could not eat pureed foods at bedside during hospitalization. Logistic regression analysis was used to identify independent predictors of swallowing of pureed foods. During a six-year period, 458 consecutive patients (mean age 80 years [range 39 to 97 years]) were considered for the study, including 285 (62%) men. Saliva pooling, vallecular residues, pharyngeal residues and penetration⁄aspiration were found in 240 (52%), 73 (16%), 226 (49%) and 232 patients (51%), respectively. Overall, 247 patients (54%) failed to swallow pureed foods. Multivariate logistic regression analysis demonstrated that the presence of pharyngeal residues (OR 6.0) and saliva pooling (OR 4.6) occurred significantly more frequently in patients who failed to swallow pureed foods. Pharyngeal residues and saliva pooling predicted impaired swallowing of pureed foods. Transnasal EES performed by a gastroenterologist provided a unique bedside method of assessing the ability to swallow pureed foods in elderly patients with dysphagia.

Comparison and validation of injury risk classifiers for advanced automated crash notification systems.

PubMed

Kusano, Kristofer; Gabler, Hampton C

2014-01-01

The odds of death for a seriously injured crash victim are drastically reduced if he or she received care at a trauma center. Advanced automated crash notification (AACN) algorithms are postcrash safety systems that use data measured by the vehicles during the crash to predict the likelihood of occupants being seriously injured. The accuracy of these models are crucial to the success of an AACN. The objective of this study was to compare the predictive performance of competing injury risk models and algorithms: logistic regression, random forest, AdaBoost, naïve Bayes, support vector machine, and classification k-nearest neighbors. This study compared machine learning algorithms to the widely adopted logistic regression modeling approach. Machine learning algorithms have not been commonly studied in the motor vehicle injury literature. Machine learning algorithms may have higher predictive power than logistic regression, despite the drawback of lacking the ability to perform statistical inference. To evaluate the performance of these algorithms, data on 16,398 vehicles involved in non-rollover collisions were extracted from the NASS-CDS. Vehicles with any occupants having an Injury Severity Score (ISS) of 15 or greater were defined as those requiring victims to be treated at a trauma center. The performance of each model was evaluated using cross-validation. Cross-validation assesses how a model will perform in the future given new data not used for model training. The crash ΔV (change in velocity during the crash), damage side (struck side of the vehicle), seat belt use, vehicle body type, number of events, occupant age, and occupant sex were used as predictors in each model. Logistic regression slightly outperformed the machine learning algorithms based on sensitivity and specificity of the models. Previous studies on AACN risk curves used the same data to train and test the power of the models and as a result had higher sensitivity compared to the cross-validated results from this study. Future studies should account for future data; for example, by using cross-validation or risk presenting optimistic predictions of field performance. Past algorithms have been criticized for relying on age and sex, being difficult to measure by vehicle sensors, and inaccuracies in classifying damage side. The models with accurate damage side and including age/sex did outperform models with less accurate damage side and without age/sex, but the differences were small, suggesting that the success of AACN is not reliant on these predictors.

Assessing landslide susceptibility by statistical data analysis and GIS: the case of Daunia (Apulian Apennines, Italy)

NASA Astrophysics Data System (ADS)

Ceppi, C.; Mancini, F.; Ritrovato, G.

2009-04-01

This study aim at the landslide susceptibility mapping within an area of the Daunia (Apulian Apennines, Italy) by a multivariate statistical method and data manipulation in a Geographical Information System (GIS) environment. Among the variety of existing statistical data analysis techniques, the logistic regression was chosen to produce a susceptibility map all over an area where small settlements are historically threatened by landslide phenomena. By logistic regression a best fitting between the presence or absence of landslide (dependent variable) and the set of independent variables is performed on the basis of a maximum likelihood criterion, bringing to the estimation of regression coefficients. The reliability of such analysis is therefore due to the ability to quantify the proneness to landslide occurrences by the probability level produced by the analysis. The inventory of dependent and independent variables were managed in a GIS, where geometric properties and attributes have been translated into raster cells in order to proceed with the logistic regression by means of SPSS (Statistical Package for the Social Sciences) package. A landslide inventory was used to produce the bivariate dependent variable whereas the independent set of variable concerned with slope, aspect, elevation, curvature, drained area, lithology and land use after their reductions to dummy variables. The effect of independent parameters on landslide occurrence was assessed by the corresponding coefficient in the logistic regression function, highlighting a major role played by the land use variable in determining occurrence and distribution of phenomena. Once the outcomes of the logistic regression are determined, data are re-introduced in the GIS to produce a map reporting the proneness to landslide as predicted level of probability. As validation of results and regression model a cell-by-cell comparison between the susceptibility map and the initial inventory of landslide events was performed and an agreement at 75% level achieved.

Survival analysis of postoperative nausea and vomiting in patients receiving patient-controlled epidural analgesia.

PubMed

Lee, Shang-Yi; Hung, Chih-Jen; Chen, Chih-Chieh; Wu, Chih-Cheng

2014-11-01

Postoperative nausea and vomiting as well as postoperative pain are two major concerns when patients undergo surgery and receive anesthetics. Various models and predictive methods have been developed to investigate the risk factors of postoperative nausea and vomiting, and different types of preventive managements have subsequently been developed. However, there continues to be a wide variation in the previously reported incidence rates of postoperative nausea and vomiting. This may have occurred because patients were assessed at different time points, coupled with the overall limitation of the statistical methods used. However, using survival analysis with Cox regression, and thus factoring in these time effects, may solve this statistical limitation and reveal risk factors related to the occurrence of postoperative nausea and vomiting in the following period. In this retrospective, observational, uni-institutional study, we analyzed the results of 229 patients who received patient-controlled epidural analgesia following surgery from June 2007 to December 2007. We investigated the risk factors for the occurrence of postoperative nausea and vomiting, and also assessed the effect of evaluating patients at different time points using the Cox proportional hazards model. Furthermore, the results of this inquiry were compared with those results using logistic regression. The overall incidence of postoperative nausea and vomiting in our study was 35.4%. Using logistic regression, we found that only sex, but not the total doses and the average dose of opioids, had significant effects on the occurrence of postoperative nausea and vomiting at some time points. Cox regression showed that, when patients consumed a higher average dose of opioids, this correlated with a higher incidence of postoperative nausea and vomiting with a hazard ratio of 1.286. Survival analysis using Cox regression showed that the average consumption of opioids played an important role in postoperative nausea and vomiting, a result not found by logistic regression. Therefore, the incidence of postoperative nausea and vomiting in patients cannot be reliably determined on the basis of a single visit at one point in time. Copyright © 2014. Published by Elsevier Taiwan.

Modelling the spatial distribution of Fasciola hepatica in bovines using decision tree, logistic regression and GIS query approaches for Brazil.

PubMed

Bennema, S C; Molento, M B; Scholte, R G; Carvalho, O S; Pritsch, I

2017-11-01

Fascioliasis is a condition caused by the trematode Fasciola hepatica. In this paper, the spatial distribution of F. hepatica in bovines in Brazil was modelled using a decision tree approach and a logistic regression, combined with a geographic information system (GIS) query. In the decision tree and the logistic model, isothermality had the strongest influence on disease prevalence. Also, the 50-year average precipitation in the warmest quarter of the year was included as a risk factor, having a negative influence on the parasite prevalence. The risk maps developed using both techniques, showed a predicted higher prevalence mainly in the South of Brazil. The prediction performance seemed to be high, but both techniques failed to reach a high accuracy in predicting the medium and high prevalence classes to the entire country. The GIS query map, based on the range of isothermality, minimum temperature of coldest month, precipitation of warmest quarter of the year, altitude and the average dailyland surface temperature, showed a possibility of presence of F. hepatica in a very large area. The risk maps produced using these methods can be used to focus activities of animal and public health programmes, even on non-evaluated F. hepatica areas.

Item Response Theory Modeling of the Philadelphia Naming Test.

PubMed

Fergadiotis, Gerasimos; Kellough, Stacey; Hula, William D

2015-06-01

In this study, we investigated the fit of the Philadelphia Naming Test (PNT; Roach, Schwartz, Martin, Grewal, & Brecher, 1996) to an item-response-theory measurement model, estimated the precision of the resulting scores and item parameters, and provided a theoretical rationale for the interpretation of PNT overall scores by relating explanatory variables to item difficulty. This article describes the statistical model underlying the computer adaptive PNT presented in a companion article (Hula, Kellough, & Fergadiotis, 2015). Using archival data, we evaluated the fit of the PNT to 1- and 2-parameter logistic models and examined the precision of the resulting parameter estimates. We regressed the item difficulty estimates on three predictor variables: word length, age of acquisition, and contextual diversity. The 2-parameter logistic model demonstrated marginally better fit, but the fit of the 1-parameter logistic model was adequate. Precision was excellent for both person ability and item difficulty estimates. Word length, age of acquisition, and contextual diversity all independently contributed to variance in item difficulty. Item-response-theory methods can be productively used to analyze and quantify anomia severity in aphasia. Regression of item difficulty on lexical variables supported the validity of the PNT and interpretation of anomia severity scores in the context of current word-finding models.

Blood oxygen level dependent magnetic resonance imaging for detecting pathological patterns in lupus nephritis patients: a preliminary study using a decision tree model.

PubMed

Shi, Huilan; Jia, Junya; Li, Dong; Wei, Li; Shang, Wenya; Zheng, Zhenfeng

2018-02-09

Precise renal histopathological diagnosis will guide therapy strategy in patients with lupus nephritis. Blood oxygen level dependent (BOLD) magnetic resonance imaging (MRI) has been applicable noninvasive technique in renal disease. This current study was performed to explore whether BOLD MRI could contribute to diagnose renal pathological pattern. Adult patients with lupus nephritis renal pathological diagnosis were recruited for this study. Renal biopsy tissues were assessed based on the lupus nephritis ISN/RPS 2003 classification. The Blood oxygen level dependent magnetic resonance imaging (BOLD-MRI) was used to obtain functional magnetic resonance parameter, R2* values. Several functions of R2* values were calculated and used to construct algorithmic models for renal pathological patterns. In addition, the algorithmic models were compared as to their diagnostic capability. Both Histopathology and BOLD MRI were used to examine a total of twelve patients. Renal pathological patterns included five classes III (including 3 as class III + V) and seven classes IV (including 4 as class IV + V). Three algorithmic models, including decision tree, line discriminant, and logistic regression, were constructed to distinguish the renal pathological pattern of class III and class IV. The sensitivity of the decision tree model was better than that of the line discriminant model (71.87% vs 59.48%, P < 0.001) and inferior to that of the Logistic regression model (71.87% vs 78.71%, P < 0.001). The specificity of decision tree model was equivalent to that of the line discriminant model (63.87% vs 63.73%, P = 0.939) and higher than that of the logistic regression model (63.87% vs 38.0%, P < 0.001). The Area under the ROC curve (AUROCC) of the decision tree model was greater than that of the line discriminant model (0.765 vs 0.629, P < 0.001) and logistic regression model (0.765 vs 0.662, P < 0.001). BOLD MRI is a useful non-invasive imaging technique for the evaluation of lupus nephritis. Decision tree models constructed using functions of R2* values may facilitate the prediction of renal pathological patterns.

A Comparison of Logistic Regression, Neural Networks, and Classification Trees Predicting Success of Actuarial Students

ERIC Educational Resources Information Center

Schumacher, Phyllis; Olinsky, Alan; Quinn, John; Smith, Richard

2010-01-01

The authors extended previous research by 2 of the authors who conducted a study designed to predict the successful completion of students enrolled in an actuarial program. They used logistic regression to determine the probability of an actuarial student graduating in the major or dropping out. They compared the results of this study with those…

Logistic regression accuracy across different spatial and temporal scales for a wide-ranging species, the marbled murrelet

Treesearch

Carolyn B. Meyer; Sherri L. Miller; C. John Ralph

2004-01-01

The scale at which habitat variables are measured affects the accuracy of resource selection functions in predicting animal use of sites. We used logistic regression models for a wide-ranging species, the marbled murrelet, (Brachyramphus marmoratus) in a large region in California to address how much changing the spatial or temporal scale of...

Odds Ratio, Delta, ETS Classification, and Standardization Measures of DIF Magnitude for Binary Logistic Regression

ERIC Educational Resources Information Center

Monahan, Patrick O.; McHorney, Colleen A.; Stump, Timothy E.; Perkins, Anthony J.

2007-01-01

Previous methodological and applied studies that used binary logistic regression (LR) for detection of differential item functioning (DIF) in dichotomously scored items either did not report an effect size or did not employ several useful measures of DIF magnitude derived from the LR model. Equations are provided for these effect size indices.…

A Generalized Logistic Regression Procedure to Detect Differential Item Functioning among Multiple Groups

ERIC Educational Resources Information Center

Magis, David; Raiche, Gilles; Beland, Sebastien; Gerard, Paul

2011-01-01

We present an extension of the logistic regression procedure to identify dichotomous differential item functioning (DIF) in the presence of more than two groups of respondents. Starting from the usual framework of a single focal group, we propose a general approach to estimate the item response functions in each group and to test for the presence…

Risk Factors of Falls in Community-Dwelling Older Adults: Logistic Regression Tree Analysis

ERIC Educational Resources Information Center

Yamashita, Takashi; Noe, Douglas A.; Bailer, A. John

2012-01-01

Purpose of the Study: A novel logistic regression tree-based method was applied to identify fall risk factors and possible interaction effects of those risk factors. Design and Methods: A nationally representative sample of American older adults aged 65 years and older (N = 9,592) in the Health and Retirement Study 2004 and 2006 modules was used.…

Estimation of Logistic Regression Models in Small Samples. A Simulation Study Using a Weakly Informative Default Prior Distribution

ERIC Educational Resources Information Center

Gordovil-Merino, Amalia; Guardia-Olmos, Joan; Pero-Cebollero, Maribel

2012-01-01

In this paper, we used simulations to compare the performance of classical and Bayesian estimations in logistic regression models using small samples. In the performed simulations, conditions were varied, including the type of relationship between independent and dependent variable values (i.e., unrelated and related values), the type of variable…

Using multiple logistic regression and GIS technology to predict landslide hazard in northeast Kansas, USA

USGS Publications Warehouse

Ohlmacher, G.C.; Davis, J.C.

2003-01-01

Landslides in the hilly terrain along the Kansas and Missouri rivers in northeastern Kansas have caused millions of dollars in property damage during the last decade. To address this problem, a statistical method called multiple logistic regression has been used to create a landslide-hazard map for Atchison, Kansas, and surrounding areas. Data included digitized geology, slopes, and landslides, manipulated using ArcView GIS. Logistic regression relates predictor variables to the occurrence or nonoccurrence of landslides within geographic cells and uses the relationship to produce a map showing the probability of future landslides, given local slopes and geologic units. Results indicated that slope is the most important variable for estimating landslide hazard in the study area. Geologic units consisting mostly of shale, siltstone, and sandstone were most susceptible to landslides. Soil type and aspect ratio were considered but excluded from the final analysis because these variables did not significantly add to the predictive power of the logistic regression. Soil types were highly correlated with the geologic units, and no significant relationships existed between landslides and slope aspect. ?? 2003 Elsevier Science B.V. All rights reserved.

A Method for Calculating the Probability of Successfully Completing a Rocket Propulsion Ground Test

NASA Technical Reports Server (NTRS)

Messer, Bradley

2007-01-01

Propulsion ground test facilities face the daily challenge of scheduling multiple customers into limited facility space and successfully completing their propulsion test projects. Over the last decade NASA s propulsion test facilities have performed hundreds of tests, collected thousands of seconds of test data, and exceeded the capabilities of numerous test facility and test article components. A logistic regression mathematical modeling technique has been developed to predict the probability of successfully completing a rocket propulsion test. A logistic regression model is a mathematical modeling approach that can be used to describe the relationship of several independent predictor variables X(sub 1), X(sub 2),.., X(sub k) to a binary or dichotomous dependent variable Y, where Y can only be one of two possible outcomes, in this case Success or Failure of accomplishing a full duration test. The use of logistic regression modeling is not new; however, modeling propulsion ground test facilities using logistic regression is both a new and unique application of the statistical technique. Results from this type of model provide project managers with insight and confidence into the effectiveness of rocket propulsion ground testing.

Alternative approach to modeling bacterial lag time, using logistic regression as a function of time, temperature, pH, and sodium chloride concentration.

PubMed

Koseki, Shige; Nonaka, Junko

2012-09-01

The objective of this study was to develop a probabilistic model to predict the end of lag time (λ) during the growth of Bacillus cereus vegetative cells as a function of temperature, pH, and salt concentration using logistic regression. The developed λ model was subsequently combined with a logistic differential equation to simulate bacterial numbers over time. To develop a novel model for λ, we determined whether bacterial growth had begun, i.e., whether λ had ended, at each time point during the growth kinetics. The growth of B. cereus was evaluated by optical density (OD) measurements in culture media for various pHs (5.5 ∼ 7.0) and salt concentrations (0.5 ∼ 2.0%) at static temperatures (10 ∼ 20°C). The probability of the end of λ was modeled using dichotomous judgments obtained at each OD measurement point concerning whether a significant increase had been observed. The probability of the end of λ was described as a function of time, temperature, pH, and salt concentration and showed a high goodness of fit. The λ model was validated with independent data sets of B. cereus growth in culture media and foods, indicating acceptable performance. Furthermore, the λ model, in combination with a logistic differential equation, enabled a simulation of the population of B. cereus in various foods over time at static and/or fluctuating temperatures with high accuracy. Thus, this newly developed modeling procedure enables the description of λ using observable environmental parameters without any conceptual assumptions and the simulation of bacterial numbers over time with the use of a logistic differential equation.

Evaluation of the Risk Factors for a Rotator Cuff Retear After Repair Surgery.

PubMed

Lee, Yeong Seok; Jeong, Jeung Yeol; Park, Chan-Deok; Kang, Seung Gyoon; Yoo, Jae Chul

2017-07-01

A retear is a significant clinical problem after rotator cuff repair. However, no study has evaluated the retear rate with regard to the extent of footprint coverage. To evaluate the preoperative and intraoperative factors for a retear after rotator cuff repair, and to confirm the relationship with the extent of footprint coverage. Cohort study; Level of evidence, 3. Data were retrospectively collected from 693 patients who underwent arthroscopic rotator cuff repair between January 2006 and December 2014. All repairs were classified into 4 types of completeness of repair according to the amount of footprint coverage at the end of surgery. All patients underwent magnetic resonance imaging (MRI) after a mean postoperative duration of 5.4 months. Preoperative demographic data, functional scores, range of motion, and global fatty degeneration on preoperative MRI and intraoperative variables including the tear size, completeness of rotator cuff repair, concomitant subscapularis repair, number of suture anchors used, repair technique (single-row or transosseous-equivalent double-row repair), and surgical duration were evaluated. Furthermore, the factors associated with failure using the single-row technique and transosseous-equivalent double-row technique were analyzed separately. The retear rate was 7.22%. Univariate analysis revealed that rotator cuff retears were affected by age; the presence of inflammatory arthritis; the completeness of rotator cuff repair; the initial tear size; the number of suture anchors; mean operative time; functional visual analog scale scores; Simple Shoulder Test findings; American Shoulder and Elbow Surgeons scores; and fatty degeneration of the supraspinatus, infraspinatus, and subscapularis. Multivariate logistic regression analysis revealed patient age, initial tear size, and fatty degeneration of the supraspinatus as independent risk factors for a rotator cuff retear. Multivariate logistic regression analysis of the single-row group revealed patient age and fatty degeneration of the supraspinatus as independent risk factors for a rotator cuff retear. Multivariate logistic regression analysis of the transosseous-equivalent double-row group revealed a frozen shoulder as an independent risk factor for a rotator cuff retear. Our results suggest that patient age, initial tear size, and fatty degeneration of the supraspinatus are independent risk factors for a rotator cuff retear, whereas the completeness of rotator cuff repair based on the extent of footprint coverage and repair technique are not.

Evaluation of affective temperament and anxiety-depression levels of patients with polycystic ovary syndrome.

PubMed

Asik, Mehmet; Altinbas, Kursat; Eroglu, Mustafa; Karaahmet, Elif; Erbag, Gokhan; Ertekin, Hulya; Sen, Hacer

2015-10-01

Women with polycystic ovary syndrome (PCOS) are reported to experience depressive episodes at a higher rate than healthy controls (HC). Affective temperament features are psychiatric markers that may help to predict and identify vulnerability to depression in women with PCOS. Our aim was to evaluate the affective temperaments of women with PCOS and to investigate the association with depression and anxiety levels and laboratory variables in comparison with HC. The study included 71 women with PCOS and 50 HC. Hormonal evaluations were performed for women with PCOS. Physical examination, clinical history, Hospital Anxiety and Depression Scale (HADS) and TEMPS-A were performed for all subjects. Differences between groups were evaluated using Student's t-tests and Mann-Whitney U tests. Correlations and logistic regression tests were performed. All temperament subtype scores, except hyperthymic, and HADS anxiety, depression, and total scores were significantly higher in patients with PCOS compared to HC. A statistically significant positive correlation was found between BMI and irritable temperament, and insulin and HADS depression scores in patients with PCOS. Additionally, hirsutism score and menstrual irregularity were correlated with HADS depression, anxiety and total scores in PCOS patients. In logistic regression analysis, depression was not affected by PCOS, hirsutism score or menstrual irregularity. However, HADS anxiety score was associated with hirsutism score. Our study is the first to evaluate the affective temperament features of women with PCOS. Consequently, establishing affective temperament properties for women with PCOS may help clinicians predict those patients with PCOS who are at risk for depressive and anxiety disorders. Copyright © 2015 Elsevier B.V. All rights reserved.

Factors related to treatment refusal in Taiwanese cancer patients.

PubMed

Chiang, Ting-Yu; Wang, Chao-Hui; Lin, Yu-Fen; Chou, Shu-Lan; Wang, Ching-Ting; Juang, Hsiao-Ting; Lin, Yung-Chang; Lin, Mei-Hsiang

2015-01-01

Incidence and mortality rates for cancer have increased dramatically in the recent 30 years in Taiwan. However, not all patients receive treatment. Treatment refusal might impair patient survival and life quality. In order to improve this situation, we proposed this study to evaluate factors that are related to refusal of treatment in cancer patients via a cancer case manager system. This study analysed data from a case management system during the period from 2010 to 2012 at a medical center in Northern Taiwan. We enrolled a total of 14,974 patients who were diagnosed with cancer. Using the PRECEDE Model as a framework, we conducted logistic regression analysis to identify independent variables that are significantly associated with refusal of therapy in cancer patients. A multivariate logistic regression model was also applied to estimate adjusted the odds ratios (ORs) with 95% confidence intervals (95%CI). A total of 253 patients (1.69%) refused treatment. The multivariate logistic regression result showed that the high risk factors for refusal of treatment in cancer patient included: concerns about adverse effects (p<0.001), poor performance(p<0.001), changes in medical condition (p<0.001), timing of case manager contact (p=.026), the methods by which case manager contact patients (p<0.001) and the frequency that case managers contact patients (≥10times) (p=0.016). Cancer patients who refuse treatment have poor survival. The present study provides evidence of factors that are related to refusal of therapy and might be helpful for further application and improvement of cancer care.

Comparison of the Relationship between Women' Empowerment and Fertility between Single-child and Multi-child Families

PubMed Central

Saberi, Tahereh; Ehsanpour, Soheila; Mahaki, Behzad; Kohan, Shahnaz

2018-01-01

Background: The reduction in fertility and increase in the number of single-child families in Iran will result in an increased risk of population aging. One of the factors affecting fertility is women's empowerment. This study aimed to evaluate the relationship between women's empowerment and fertility in single-child and multi-child families. Materials and Methods: This case-control study was conducted among 350 women (120 who had only 1 child as case group and 230 who had 2 or more children as control group) of 15–49 years of age in Isfahan, Iran, in 2016. For data collection, a 2-part questionnaire was designed. Data were analyzed using independent t-test, Chi-square test, and logistic regression analysis. Results: The difference between average scores of women's empowerment in the case group 54.08 (9.88) and control group 51.47 (8.57) was significant (p = 0.002). Simple logistic regression analysis showed that under diploma education, compared to postgraduate education, (OR = 0.21, p = 0.001) and being a housewife, compared to being employed, (OR = 0.45, p = 0.004) decreased the odds of having only 1 child. Multiple logistic regression results showed that the relationship between women's empowerment and fertility was not significant (p = 0.265). Conclusions: Although women in single-child families were more empowered, this was not the main reason for their preference to have only 1 child. In fact, educated and employed women postpone marriage and childbearing and limit fertility to only 1 child despite their desire. PMID:29628961

Mortality-Associated Characteristics of Patients with Traumatic Brain Injury at the University Teaching Hospital of Kigali, Rwanda.

PubMed

Krebs, Elizabeth; Gerardo, Charles J; Park, Lawrence P; Nickenig Vissoci, Joao Ricardo; Byiringiro, Jean Claude; Byiringiro, Fidele; Rulisa, Stephen; Thielman, Nathan M; Staton, Catherine A

2017-06-01

Traumatic brain injury (TBI) is a leading cause of death and disability. Patients with TBI in low and middle-income countries have worse outcomes than patients in high-income countries. We evaluated important clinical indicators associated with mortality for patients with TBI at University Teaching Hospital of Kigali, Kigali, Rwanda. A prospective consecutive sampling of patients with TBI presenting to University Teaching Hospital of Kigali Accident and Emergency Department was screened for inclusion criteria: reported head trauma, alteration in consciousness, headache, and visible head trauma. Exclusion criteria were age <10 years, >48 hours after injury, and repeat visit. Data were assessed for association with death using logistic regression. Significant variables were included in a multivariate logistic regression model and refined via backward elimination. Between October 7, 2013, and April 6, 2014, 684 patients were enrolled; 14 (2%) were excluded because of incomplete data. Of patients, 81% were male with mean age of 31 years (range, 10-89 years; SD 11.8). Most patients (80%) had mild TBI (Glasgow Coma Scale [GCS] score 13-15); 10% had moderate (GCS score 9-12) and 10% had severe (GCS score 3-8) TBI. Multivariate logistic regression determined that GCS score <13, hypoxia, bradycardia, tachycardia, and age >50 years were significantly associated with death. GCS score <13, hypoxia, bradycardia, tachycardia, and age >50 years were associated with mortality. These findings inform future research that may guide clinicians in prioritizing care for patients at highest risk of mortality. Copyright © 2017 Elsevier Inc. All rights reserved.

Logistic regression analysis of the risk factors of anastomotic fistula after radical resection of esophageal‐cardiac cancer

PubMed Central

Huang, Jinxi; Wang, Chenghu; Yuan, Weiwei; Zhang, Zhandong; Chen, Beibei; Zhang, Xiefu

2017-01-01

Background This study was conducted to investigate the risk factors of anastomotic fistula after the radical resection of esophageal‐cardiac cancer. Methods Five hundred and forty‐four esophageal‐cardiac cancer patients who underwent surgery and had complete clinical data were included in the study. Fifty patients diagnosed with postoperative anastomotic fistula were considered the case group and the remaining 494 subjects who did not develop postoperative anastomotic fistula were considered the control. The potential risk factors for anastomotic fistula, such as age, gender, diabetes history, smoking history, were collected and compared between the groups. Statistically significant variables were substituted into logistic regression to further evaluate the independent risk factors for postoperative anastomotic fistulas in esophageal‐cardiac cancer. Results The incidence of anastomotic fistulas was 9.2% (50/544). Logistic regression analysis revealed that female gender (P < 0.05), laparoscopic surgery (P < 0.05), decreased postoperative albumin (P < 0.05), and postoperative renal dysfunction (P < 0.05) were independent risk factors for anastomotic fistulas in patients who received surgery for esophageal‐cardiac cancer. Of the 50 anastomotic fistulas, 16 cases were small fistulas, which were only discovered by conventional imaging examination and not presenting clinical symptoms. All of the anastomotic fistulas occurred within seven days after surgery. Five of the patients with anastomotic fistulas underwent a second surgery and three died. Conclusion Female patients with esophageal‐cardiac cancer treated with endoscopic surgery and suffering from postoperative hypoproteinemia and renal dysfunction were susceptible to postoperative anastomotic fistula. PMID:28940985

EXpectation Propagation LOgistic REgRession (EXPLORER): Distributed Privacy-Preserving Online Model Learning

PubMed Central

Wang, Shuang; Jiang, Xiaoqian; Wu, Yuan; Cui, Lijuan; Cheng, Samuel; Ohno-Machado, Lucila

2013-01-01

We developed an EXpectation Propagation LOgistic REgRession (EXPLORER) model for distributed privacy-preserving online learning. The proposed framework provides a high level guarantee for protecting sensitive information, since the information exchanged between the server and the client is the encrypted posterior distribution of coefficients. Through experimental results, EXPLORER shows the same performance (e.g., discrimination, calibration, feature selection etc.) as the traditional frequentist Logistic Regression model, but provides more flexibility in model updating. That is, EXPLORER can be updated one point at a time rather than having to retrain the entire data set when new observations are recorded. The proposed EXPLORER supports asynchronized communication, which relieves the participants from coordinating with one another, and prevents service breakdown from the absence of participants or interrupted communications. PMID:23562651

Dietary consumption patterns and laryngeal cancer risk.

PubMed

Vlastarakos, Petros V; Vassileiou, Andrianna; Delicha, Evie; Kikidis, Dimitrios; Protopapas, Dimosthenis; Nikolopoulos, Thomas P

2016-06-01

We conducted a case-control study to investigate the effect of diet on laryngeal carcinogenesis. Our study population was made up of 140 participants-70 patients with laryngeal cancer (LC) and 70 controls with a non-neoplastic condition that was unrelated to diet, smoking, or alcohol. A food-frequency questionnaire determined the mean consumption of 113 different items during the 3 years prior to symptom onset. Total energy intake and cooking mode were also noted. The relative risk, odds ratio (OR), and 95% confidence interval (CI) were estimated by multiple logistic regression analysis. We found that the total energy intake was significantly higher in the LC group (p < 0.001), and that the difference remained statistically significant after logistic regression analysis (p < 0.001; OR: 118.70). Notably, meat consumption was higher in the LC group (p < 0.001), and the difference remained significant after logistic regression analysis (p = 0.029; OR: 1.16). LC patients also consumed significantly more fried food (p = 0.036); this difference also remained significant in the logistic regression model (p = 0.026; OR: 5.45). The LC group also consumed significantly more seafood (p = 0.012); the difference persisted after logistic regression analysis (p = 0.009; OR: 2.48), with the consumption of shrimp proving detrimental (p = 0.049; OR: 2.18). Finally, the intake of zinc was significantly higher in the LC group before and after logistic regression analysis (p = 0.034 and p = 0.011; OR: 30.15, respectively). Cereal consumption (including pastas) was also higher among the LC patients (p = 0.043), with logistic regression analysis showing that their negative effect was possibly associated with the sauces and dressings that traditionally accompany pasta dishes (p = 0.006; OR: 4.78). Conversely, a higher consumption of dairy products was found in controls (p < 0.05); logistic regression analysis showed that calcium appeared to be protective at the micronutrient level (p < 0.001; OR: 0.27). We found no difference in the overall consumption of fruits and vegetables between the LC patients and controls; however, the LC patients did have a greater consumption of cooked tomatoes and cooked root vegetables (p = 0.039 for both), and the controls had more consumption of leeks (p = 0.042) and, among controls younger than 65 years, cooked beans (p = 0.037). Lemon (p = 0.037), squeezed fruit juice (p = 0.032), and watermelon (p = 0.018) were also more frequently consumed by the controls. Other differences at the micronutrient level included greater consumption by the LC patients of retinol (p = 0.044), polyunsaturated fats (p = 0.041), and linoleic acid (p = 0.008); LC patients younger than 65 years also had greater intake of riboflavin (p = 0.045). We conclude that the differences in dietary consumption patterns between LC patients and controls indicate a possible role for lifestyle modifications involving nutritional factors as a means of decreasing the risk of laryngeal cancer.

Comparison of V50 Shot Placement on Final Outcome

DTIC Science & Technology

2014-11-01

molecular- weight polyethylene (UHMWPE). In V50 testing of those types of materials, large delaminations may occur that influence the results. This...placement, a proper evaluation of materials may not be possible. 15. SUBJECT TERMS ballistics, V50 test, logistic regression , statistical inference...from an impact. While this may work with ceramics or metal armor, it is inappropriate for use on composite armors like ultra-high-molecular- weight

Is the economic crisis affecting birth outcome in Spain? Evaluation of temporal trend in underweight at birth (2003-2012).

PubMed

Varea, Carlos; Terán, José Manuel; Bernis, Cristina; Bogin, Barry; González-González, Antonio

2016-01-01

There is growing evidence of the impact of the current European economic crisis on health. In Spain, since 2008, there have been increasing levels of impoverishment and inequality, and important cuts in social services. The objective is to evaluate the impact of the economic crisis on underweight at birth in Spain. Trends in underweight at birth were examined between 2003 and 2012. Underweight at birth is defined as a singleton, term neonatal weight lesser than -2 SD from the median weight at birth for each sex estimated by the WHO Standard Growth Reference. Using data from the Statistical Bulletin of Childbirth, 2 933 485 live births born to Spanish mothers have been analysed. Descriptive analysis, seasonal decomposition analysis and crude and adjusted logistic regression including individual maternal and foetal variables as well as exogenous economic indicators have been performed. Results demonstrate a significant increase in the prevalence of underweight at birth from 2008. All maternal-foetal categories were affected, including those showing the lowest prevalence before the crisis. In the full adjusted logistic regression, year-on-year GDP per capita remains predictive on underweight at birth risk. Previous trends in maternal socio-demographic profiles and a direct impact of the crisis are discussed to explain the trends described.

Inverse associations between perceived racism and coronary artery calcification.

PubMed

Everage, Nicholas J; Gjelsvik, Annie; McGarvey, Stephen T; Linkletter, Crystal D; Loucks, Eric B

2012-03-01

To evaluate whether racial discrimination is associated with coronary artery calcification (CAC) in African-American participants of the Coronary Artery Risk Development in Young Adults (CARDIA) study. The study included American Black men (n = 571) and women (n = 791) aged 33 to 45 years in the CARDIA study. Perceived racial discrimination was assessed based on the Experiences of Discrimination scale (range, 1-35). CAC was evaluated using computed tomography. Primary analyses assessed associations between perceived racial discrimination and presence of CAC using multivariable-adjusted logistic regression analysis, adjusted for age, gender, socioeconomic position (SEP), psychosocial variables, and coronary heart disease (CHD) risk factors. In age- and gender-adjusted logistic regression models, odds of CAC decreased as the perceived racial discrimination score increased (odds ratio [OR], 0.94; 95% confidence interval [CI], 0.90-0.98 per 1-unit increase in Experiences of Discrimination scale). The relationship did not markedly change after further adjustment for SEP, psychosocial variables, or CHD risk factors (OR, 0.93; 95% CI, 0.87-0.99). Perceived racial discrimination was negatively associated with CAC in this study. Estimation of more forms of racial discrimination as well as replication of analyses in other samples will help to confirm or refute these findings. Copyright © 2012 Elsevier Inc. All rights reserved.

Risk factors for persistent gestational trophoblastic neoplasia.

PubMed

Kuyumcuoglu, Umur; Guzel, Ali Irfan; Erdemoglu, Mahmut; Celik, Yusuf

2011-01-01

This retrospective study evaluated the risk factors for persistent gestational trophoblastic disease (GTN) and determined their odds ratios. This study included 100 cases with GTN admitted to our clinic. Possible risk factors recorded were age, gravidity, parity, size of the neoplasia, and beta-human chorionic gonadotropin levels (beta-hCG) before and after the procedure. Statistical analyses consisted of the independent sample t-test and logistic regression using the statistical package SPSS ver. 15.0 for Windows (SPSS, Chicago, IL, USA). Twenty of the cases had persistent GTN, and the differences between these and the others cases were evaluated. The size of the neoplasia and histopathological type of GTN had no statistical relationship with persistence, whereas age, gravidity, and beta-hCG levels were significant risk factors for persistent GTN (p < 0.05). The odds ratios (95% confidence interval (CI)) for age, gravidity, and pre- and post-evacuation beta-hCG levels determined using logistic regression were 4.678 (0.97-22.44), 7.315 (1.16-46.16), 2.637 (1.41-4.94), and 2.339 (1.52-3.60), respectively. Patient age, gravidity, and beta-hCG levels were risk factors for persistent GTN, whereas the size of the neoplasia and histopathological type of GTN were not significant risk factors.

Assessment of Differential Item Functioning in Health-Related Outcomes: A Simulation and Empirical Analysis with Hierarchical Polytomous Data

PubMed Central

Sharafi, Zahra

2017-01-01

Background The purpose of this study was to evaluate the effectiveness of two methods of detecting differential item functioning (DIF) in the presence of multilevel data and polytomously scored items. The assessment of DIF with multilevel data (e.g., patients nested within hospitals, hospitals nested within districts) from large-scale assessment programs has received considerable attention but very few studies evaluated the effect of hierarchical structure of data on DIF detection for polytomously scored items. Methods The ordinal logistic regression (OLR) and hierarchical ordinal logistic regression (HOLR) were utilized to assess DIF in simulated and real multilevel polytomous data. Six factors (DIF magnitude, grouping variable, intraclass correlation coefficient, number of clusters, number of participants per cluster, and item discrimination parameter) with a fully crossed design were considered in the simulation study. Furthermore, data of Pediatric Quality of Life Inventory™ (PedsQL™) 4.0 collected from 576 healthy school children were analyzed. Results Overall, results indicate that both methods performed equivalently in terms of controlling Type I error and detection power rates. Conclusions The current study showed negligible difference between OLR and HOLR in detecting DIF with polytomously scored items in a hierarchical structure. Implications and considerations while analyzing real data were also discussed. PMID:29312463

Assessment of Differential Item Functioning in Health-Related Outcomes: A Simulation and Empirical Analysis with Hierarchical Polytomous Data.

PubMed

Sharafi, Zahra; Mousavi, Amin; Ayatollahi, Seyyed Mohammad Taghi; Jafari, Peyman

2017-01-01

The purpose of this study was to evaluate the effectiveness of two methods of detecting differential item functioning (DIF) in the presence of multilevel data and polytomously scored items. The assessment of DIF with multilevel data (e.g., patients nested within hospitals, hospitals nested within districts) from large-scale assessment programs has received considerable attention but very few studies evaluated the effect of hierarchical structure of data on DIF detection for polytomously scored items. The ordinal logistic regression (OLR) and hierarchical ordinal logistic regression (HOLR) were utilized to assess DIF in simulated and real multilevel polytomous data. Six factors (DIF magnitude, grouping variable, intraclass correlation coefficient, number of clusters, number of participants per cluster, and item discrimination parameter) with a fully crossed design were considered in the simulation study. Furthermore, data of Pediatric Quality of Life Inventory™ (PedsQL™) 4.0 collected from 576 healthy school children were analyzed. Overall, results indicate that both methods performed equivalently in terms of controlling Type I error and detection power rates. The current study showed negligible difference between OLR and HOLR in detecting DIF with polytomously scored items in a hierarchical structure. Implications and considerations while analyzing real data were also discussed.

The association between dietary lignans, phytoestrogen-rich foods, and fiber intake and postmenopausal breast cancer risk: a German case-control study.

PubMed

Zaineddin, Aida Karina; Buck, Katharina; Vrieling, Alina; Heinz, Judith; Flesch-Janys, Dieter; Linseisen, Jakob; Chang-Claude, Jenny

2012-01-01

Phytoestrogens are structurally similar to estrogens and may affect breast cancer risk by mimicking estrogenic/antiestrogenic properties. In Western societies, whole grains and possibly soy foods are rich sources of phytoestrogens. A population-based case-control study in German postmenopausal women was used to evaluate the association of phytoestrogen-rich foods and dietary lignans with breast cancer risk. Dietary data were collected from 2,884 cases and 5,509 controls using a validated food-frequency questionnaire, which included additional questions phytoestrogen-rich foods. Associations were assessed using conditional logistic regression. All analyses were adjusted for relevant risk and confounding factors. Polytomous logistic regression analysis was performed to evaluate the associations by estrogen receptor (ER) status. High and low consumption of soybeans as well as of sunflower and pumpkin seeds were associated with significantly reduced breast cancer risk compared to no consumption (OR = 0.83, 95% CI = 0.70-0.97; and OR = 0.66, 95% CI = 0.77-0.97, respectively). The observed associations were not differential by ER status. No statistically significant associations were found for dietary intake of plant lignans, fiber, or the calculated enterolignans. Our results provide evidence for a reduced postmenopausal breast cancer risk associated with increased consumption of sunflower and pumpkin seeds and soybeans.

Constructive thinking, rational intelligence and irritable bowel syndrome.

PubMed

Rey, Enrique; Moreno Ortega, Marta; Garcia Alonso, Monica-Olga; Diaz-Rubio, Manuel

2009-07-07

To evaluate rational and experiential intelligence in irritable bowel syndrome (IBS) sufferers. We recruited 100 subjects with IBS as per Rome II criteria (50 consulters and 50 non-consulters) and 100 healthy controls, matched by age, sex and educational level. Cases and controls completed a clinical questionnaire (including symptom characteristics and medical consultation) and the following tests: rational-intelligence (Wechsler Adult Intelligence Scale, 3rd edition); experiential-intelligence (Constructive Thinking Inventory); personality (NEO personality inventory); psychopathology (MMPI-2), anxiety (state-trait anxiety inventory) and life events (social readjustment rating scale). Analysis of variance was used to compare the test results of IBS-sufferers and controls, and a logistic regression model was then constructed and adjusted for age, sex and educational level to evaluate any possible association with IBS. No differences were found between IBS cases and controls in terms of IQ (102.0 +/- 10.8 vs 102.8 +/- 12.6), but IBS sufferers scored significantly lower in global constructive thinking (43.7 +/- 9.4 vs 49.6 +/- 9.7). In the logistic regression model, global constructive thinking score was independently linked to suffering from IBS [OR 0.92 (0.87-0.97)], without significant OR for total IQ. IBS subjects do not show lower rational intelligence than controls, but lower experiential intelligence is nevertheless associated with IBS.

Association between Diet and Lifestyle Habits and Irritable Bowel Syndrome: A Case-Control Study

PubMed Central

Guo, Yu-Bin; Zhuang, Kang-Min; Kuang, Lei; Zhan, Qiang; Wang, Xian-Fei; Liu, Si-De

2015-01-01

Background/Aims Recent papers have highlighted the role of diet and lifestyle habits in irritable bowel syndrome (IBS), but very few population-based studies have evaluated this association in developing countries. The aim of this study was to evaluate the association between diet and lifestyle habits and IBS. Methods A food frequency and lifestyle habits questionnaire was used to record the diet and lifestyle habits of 78 IBS subjects and 79 healthy subjects. Cross-tabulation analysis and logistic regression were used to reveal any association among lifestyle habits, eating habits, food consumption frequency, and other associated conditions. Results The results from logistic regression analysis indicated that IBS was associated with irregular eating (odds ratio [OR], 3.257), physical inactivity (OR, 3.588), and good quality sleep (OR, 0.132). IBS subjects ate fruit (OR, 3.082) vegetables (OR, 3.778), and legumes (OR, 2.111) and drank tea (OR, 2.221) significantly more frequently than the control subjects. After adjusting for age and sex, irregular eating (OR, 3.963), physical inactivity (OR, 6.297), eating vegetables (OR, 7.904), legumes (OR, 2.674), drinking tea (OR, 3.421) and good quality sleep (OR, 0.054) were independent predictors of IBS. Conclusions This study reveals a possible association between diet and lifestyle habits and IBS. PMID:25266811

Development and evaluation of an electromagnetic hypersensitivity questionnaire for Japanese people

PubMed Central

Tokiya, Mikiko; Mizuki, Masami; Miyata, Mikio; Kanatani, Kumiko T.; Takagi, Airi; Tsurikisawa, Naomi; Kame, Setsuko; Katoh, Takahiko; Tsujiuchi, Takuya; Kumano, Hiroaki

2016-01-01

The purpose of the present study was to evaluate the validity and reliability of a Japanese version of an electromagnetic hypersensitivity (EHS) questionnaire, originally developed by Eltiti et al. in the United Kingdom. Using this Japanese EHS questionnaire, surveys were conducted on 1306 controls and 127 self‐selected EHS subjects in Japan. Principal component analysis of controls revealed eight principal symptom groups, namely, nervous, skin‐related, head‐related, auditory and vestibular, musculoskeletal, allergy‐related, sensory, and heart/chest‐related. The reliability of the Japanese EHS questionnaire was confirmed by high to moderate intraclass correlation coefficients in a test–retest analysis, and high Cronbach's α coefficients (0.853–0.953) from each subscale. A comparison of scores of each subscale between self‐selected EHS subjects and age‐ and sex‐matched controls using bivariate logistic regression analysis, Mann–Whitney U‐ and χ 2 tests, verified the validity of the questionnaire. This study demonstrated that the Japanese EHS questionnaire is reliable and valid, and can be used for surveillance of EHS individuals in Japan. Furthermore, based on multiple logistic regression and receiver operating characteristic analyses, we propose specific preliminary criteria for screening EHS individuals in Japan. Bioelectromagnetics. 37:353–372, 2016. © 2016 The Authors. Bioelectromagnetics Published by Wiley Periodicals, Inc. PMID:27324106

What does theory-driven evaluation add to the analysis of self-reported outcomes of diabetes education? A comparative realist evaluation of a participatory patient education approach.

PubMed

Pals, Regitze A S; Olesen, Kasper; Willaing, Ingrid

2016-06-01

To explore the effects of the Next Education (NEED) patient education approach in diabetes education. We tested the use of the NEED approach at eight intervention sites (n=193). Six additional sites served as controls (n=58). Data were collected through questionnaires, interviews and observations. We analysed data using descriptive statistics, logistic regression and systematic text condensation. Results from logistic regression demonstrated better overall assessment of education program experiences and enhanced self-reported improvements in maintaining medications correctly among patients from intervention sites, as compared to control sites. Interviews and observations suggested that improvements in health behavior could be explained by mechanisms related to the education setting, including using person-centeredness and dialogue. However, similar mechanisms were observed at control sites. Observations suggested that the quality of group dynamics, patients' motivation and educators' ability to facilitate participation in education, supported by the NEED approach, contributed to better results at intervention sites. The use of participatory approaches and, in particular, the NEED patient education approach in group-based diabetes education improved self-management skills and health behavior outcomes among individuals with diabetes. The use of dialogue tools in diabetes education is advised for educators. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Epidemiological characteristics of measles from 2000 to 2014: Results of a measles catch-up vaccination campaign in Xianyang, China.

PubMed

Zhang, Rong-Qiang; Li, Hong-Bing; Li, Feng-Ying; Han, Li-Xin; Xiong, Yong-Min

This study was a cross-sectional case-control study aimed at (1) identifying risk factors contributing to the measles epidemic and (2) evaluating the impacts of measles-containing vaccines (MCVs), with the goal of providing evidence-based recommendations for measles elimination strategies in China. Data on measles cases from 2000 to 2014 were obtained from a passive surveillance system at the Center for Diseases Prevention and Control in Xianyang. The effectiveness of MCVs was evaluated in 357 patients with a vaccination history and 503 healthy randomly selected controls. Patient data were subjected to multivariable logistic regression modeling. From 2005 to 2014, the average incidence of measles in Xianyang was 5.42 cases per 100,000 people. The second MCV dose was highly protective in 8-month-old infants. MCVs in general have been highly protective in 8-month-old infants. Multivariable logistic regression modeling indicated that age (≥2 years vs. <2years), MCV dose 2 vaccination, and MV vaccination were each independently associated with measles case status. In conclusions: A MCV should be administered on time to all age-eligible children, reproductive-age women, and migrant populations, to maximize herd immunity to measles. Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.

A Comparison of the Logistic Regression and Contingency Table Methods for Simultaneous Detection of Uniform and Nonuniform DIF

ERIC Educational Resources Information Center

Guler, Nese; Penfield, Randall D.

2009-01-01

In this study, we investigate the logistic regression (LR), Mantel-Haenszel (MH), and Breslow-Day (BD) procedures for the simultaneous detection of both uniform and nonuniform differential item functioning (DIF). A simulation study was used to assess and compare the Type I error rate and power of a combined decision rule (CDR), which assesses DIF…

The Overall Odds Ratio as an Intuitive Effect Size Index for Multiple Logistic Regression: Examination of Further Refinements

ERIC Educational Resources Information Center

Le, Huy; Marcus, Justin

2012-01-01

This study used Monte Carlo simulation to examine the properties of the overall odds ratio (OOR), which was recently introduced as an index for overall effect size in multiple logistic regression. It was found that the OOR was relatively independent of study base rate and performed better than most commonly used R-square analogs in indexing model…

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…

Using ROC curves to compare neural networks and logistic regression for modeling individual noncatastrophic tree mortality

Treesearch

Susan L. King

2003-01-01

The performance of two classifiers, logistic regression and neural networks, are compared for modeling noncatastrophic individual tree mortality for 21 species of trees in West Virginia. The output of the classifier is usually a continuous number between 0 and 1. A threshold is selected between 0 and 1 and all of the trees below the threshold are classified as...

Logistic regression trees for initial selection of interesting loci in case-control studies

PubMed Central

Nickolov, Radoslav Z; Milanov, Valentin B

2007-01-01

Modern genetic epidemiology faces the challenge of dealing with hundreds of thousands of genetic markers. The selection of a small initial subset of interesting markers for further investigation can greatly facilitate genetic studies. In this contribution we suggest the use of a logistic regression tree algorithm known as logistic tree with unbiased selection. Using the simulated data provided for Genetic Analysis Workshop 15, we show how this algorithm, with incorporation of multifactor dimensionality reduction method, can reduce an initial large pool of markers to a small set that includes the interesting markers with high probability. PMID:18466557

Polymorphism Thr160Thr in SRD5A1, involved in the progesterone metabolism, modifies postmenopausal breast cancer risk associated with menopausal hormone therapy.

PubMed

Hein, R; Abbas, S; Seibold, P; Salazar, R; Flesch-Janys, D; Chang-Claude, J

2012-01-01

Menopausal hormone therapy (MHT) is associated with an increased breast cancer risk in postmenopausal women, with combined estrogen-progestagen therapy posing a greater risk than estrogen monotherapy. However, few studies focused on potential effect modification of MHT-associated breast cancer risk by genetic polymorphisms in the progesterone metabolism. We assessed effect modification of MHT use by five coding single nucleotide polymorphisms (SNPs) in the progesterone metabolizing enzymes AKR1C3 (rs7741), AKR1C4 (rs3829125, rs17134592), and SRD5A1 (rs248793, rs3736316) using a two-center population-based case-control study from Germany with 2,502 postmenopausal breast cancer patients and 4,833 matched controls. An empirical-Bayes procedure that tests for interaction using a weighted combination of the prospective and the retrospective case-control estimators as well as standard prospective logistic regression were applied to assess multiplicative statistical interaction between polymorphisms and duration of MHT use with regard to breast cancer risk assuming a log-additive mode of inheritance. No genetic marginal effects were observed. Breast cancer risk associated with duration of combined therapy was significantly modified by SRD5A1_rs3736316, showing a reduced risk elevation in carriers of the minor allele (p (interaction,empirical-Bayes) = 0.006 using the empirical-Bayes method, p (interaction,logistic regression) = 0.013 using logistic regression). The risk associated with duration of use of monotherapy was increased by AKR1C3_rs7741 in minor allele carriers (p (interaction,empirical-Bayes) = 0.083, p (interaction,logistic regression) = 0.029) and decreased in minor allele carriers of two SNPs in AKR1C4 (rs3829125: p (interaction,empirical-Bayes) = 0.07, p (interaction,logistic regression) = 0.021; rs17134592: p (interaction,empirical-Bayes) = 0.101, p (interaction,logistic regression) = 0.038). After Bonferroni correction for multiple testing only SRD5A1_rs3736316 assessed using the empirical-Bayes method remained significant. Postmenopausal breast cancer risk associated with combined therapy may be modified by genetic variation in SRD5A1. Further well-powered studies are, however, required to replicate our finding.

Logistic Regression Likelihood Ratio Test Analysis for Detecting Signals of Adverse Events in Post-market Safety Surveillance.

PubMed

Nam, Kijoeng; Henderson, Nicholas C; Rohan, Patricia; Woo, Emily Jane; Russek-Cohen, Estelle

2017-01-01

The Vaccine Adverse Event Reporting System (VAERS) and other product surveillance systems compile reports of product-associated adverse events (AEs), and these reports may include a wide range of information including age, gender, and concomitant vaccines. Controlling for possible confounding variables such as these is an important task when utilizing surveillance systems to monitor post-market product safety. A common method for handling possible confounders is to compare observed product-AE combinations with adjusted baseline frequencies where the adjustments are made by stratifying on observable characteristics. Though approaches such as these have proven to be useful, in this article we propose a more flexible logistic regression approach which allows for covariates of all types rather than relying solely on stratification. Indeed, a main advantage of our approach is that the general regression framework provides flexibility to incorporate additional information such as demographic factors and concomitant vaccines. As part of our covariate-adjusted method, we outline a procedure for signal detection that accounts for multiple comparisons and controls the overall Type 1 error rate. To demonstrate the effectiveness of our approach, we illustrate our method with an example involving febrile convulsion, and we further evaluate its performance in a series of simulation studies.

Applications of statistics to medical science, III. Correlation and regression.

PubMed

Watanabe, Hiroshi

2012-01-01

In this third part of a series surveying medical statistics, the concepts of correlation and regression are reviewed. In particular, methods of linear regression and logistic regression are discussed. Arguments related to survival analysis will be made in a subsequent paper.

Filtering data from the collaborative initial glaucoma treatment study for improved identification of glaucoma progression.

PubMed

Schell, Greggory J; Lavieri, Mariel S; Stein, Joshua D; Musch, David C

2013-12-21

Open-angle glaucoma (OAG) is a prevalent, degenerate ocular disease which can lead to blindness without proper clinical management. The tests used to assess disease progression are susceptible to process and measurement noise. The aim of this study was to develop a methodology which accounts for the inherent noise in the data and improve significant disease progression identification. Longitudinal observations from the Collaborative Initial Glaucoma Treatment Study (CIGTS) were used to parameterize and validate a Kalman filter model and logistic regression function. The Kalman filter estimates the true value of biomarkers associated with OAG and forecasts future values of these variables. We develop two logistic regression models via generalized estimating equations (GEE) for calculating the probability of experiencing significant OAG progression: one model based on the raw measurements from CIGTS and another model based on the Kalman filter estimates of the CIGTS data. Receiver operating characteristic (ROC) curves and associated area under the ROC curve (AUC) estimates are calculated using cross-fold validation. The logistic regression model developed using Kalman filter estimates as data input achieves higher sensitivity and specificity than the model developed using raw measurements. The mean AUC for the Kalman filter-based model is 0.961 while the mean AUC for the raw measurements model is 0.889. Hence, using the probability function generated via Kalman filter estimates and GEE for logistic regression, we are able to more accurately classify patients and instances as experiencing significant OAG progression. A Kalman filter approach for estimating the true value of OAG biomarkers resulted in data input which improved the accuracy of a logistic regression classification model compared to a model using raw measurements as input. This methodology accounts for process and measurement noise to enable improved discrimination between progression and nonprogression in chronic diseases.

Computing group cardinality constraint solutions for logistic regression problems.

PubMed

Zhang, Yong; Kwon, Dongjin; Pohl, Kilian M

2017-01-01

We derive an algorithm to directly solve logistic regression based on cardinality constraint, group sparsity and use it to classify intra-subject MRI sequences (e.g. cine MRIs) of healthy from diseased subjects. Group cardinality constraint models are often applied to medical images in order to avoid overfitting of the classifier to the training data. Solutions within these models are generally determined by relaxing the cardinality constraint to a weighted feature selection scheme. However, these solutions relate to the original sparse problem only under specific assumptions, which generally do not hold for medical image applications. In addition, inferring clinical meaning from features weighted by a classifier is an ongoing topic of discussion. Avoiding weighing features, we propose to directly solve the group cardinality constraint logistic regression problem by generalizing the Penalty Decomposition method. To do so, we assume that an intra-subject series of images represents repeated samples of the same disease patterns. We model this assumption by combining series of measurements created by a feature across time into a single group. Our algorithm then derives a solution within that model by decoupling the minimization of the logistic regression function from enforcing the group sparsity constraint. The minimum to the smooth and convex logistic regression problem is determined via gradient descent while we derive a closed form solution for finding a sparse approximation of that minimum. We apply our method to cine MRI of 38 healthy controls and 44 adult patients that received reconstructive surgery of Tetralogy of Fallot (TOF) during infancy. Our method correctly identifies regions impacted by TOF and generally obtains statistically significant higher classification accuracy than alternative solutions to this model, i.e., ones relaxing group cardinality constraints. Copyright © 2016 Elsevier B.V. All rights reserved.

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.

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.

Artificial neural network, genetic algorithm, and logistic regression applications for predicting renal colic in emergency settings.

PubMed

Eken, Cenker; Bilge, Ugur; Kartal, Mutlu; Eray, Oktay

2009-06-03

Logistic regression is the most common statistical model for processing multivariate data in the medical literature. Artificial intelligence models like an artificial neural network (ANN) and genetic algorithm (GA) may also be useful to interpret medical data. The purpose of this study was to perform artificial intelligence models on a medical data sheet and compare to logistic regression. ANN, GA, and logistic regression analysis were carried out on a data sheet of a previously published article regarding patients presenting to an emergency department with flank pain suspicious for renal colic. The study population was composed of 227 patients: 176 patients had a diagnosis of urinary stone, while 51 ultimately had no calculus. The GA found two decision rules in predicting urinary stones. Rule 1 consisted of being male, pain not spreading to back, and no fever. In rule 2, pelvicaliceal dilatation on bedside ultrasonography replaced no fever. ANN, GA rule 1, GA rule 2, and logistic regression had a sensitivity of 94.9, 67.6, 56.8, and 95.5%, a specificity of 78.4, 76.47, 86.3, and 47.1%, a positive likelihood ratio of 4.4, 2.9, 4.1, and 1.8, and a negative likelihood ratio of 0.06, 0.42, 0.5, and 0.09, respectively. The area under the curve was found to be 0.867, 0.720, 0.715, and 0.713 for all applications, respectively. Data mining techniques such as ANN and GA can be used for predicting renal colic in emergency settings and to constitute clinical decision rules. They may be an alternative to conventional multivariate analysis applications used in biostatistics.

Application of logistic regression for landslide susceptibility zoning of Cekmece Area, Istanbul, Turkey

NASA Astrophysics Data System (ADS)

Duman, T. Y.; Can, T.; Gokceoglu, C.; Nefeslioglu, H. A.; Sonmez, H.

2006-11-01

As a result of industrialization, throughout the world, cities have been growing rapidly for the last century. One typical example of these growing cities is Istanbul, the population of which is over 10 million. Due to rapid urbanization, new areas suitable for settlement and engineering structures are necessary. The Cekmece area located west of the Istanbul metropolitan area is studied, because the landslide activity is extensive in this area. The purpose of this study is to develop a model that can be used to characterize landslide susceptibility in map form using logistic regression analysis of an extensive landslide database. A database of landslide activity was constructed using both aerial-photography and field studies. About 19.2% of the selected study area is covered by deep-seated landslides. The landslides that occur in the area are primarily located in sandstones with interbedded permeable and impermeable layers such as claystone, siltstone and mudstone. About 31.95% of the total landslide area is located at this unit. To apply logistic regression analyses, a data matrix including 37 variables was constructed. The variables used in the forwards stepwise analyses are different measures of slope, aspect, elevation, stream power index (SPI), plan curvature, profile curvature, geology, geomorphology and relative permeability of lithological units. A total of 25 variables were identified as exerting strong influence on landslide occurrence, and included by the logistic regression equation. Wald statistics values indicate that lithology, SPI and slope are more important than the other parameters in the equation. Beta coefficients of the 25 variables included the logistic regression equation provide a model for landslide susceptibility in the Cekmece area. This model is used to generate a landslide susceptibility map that correctly classified 83.8% of the landslide-prone areas.

Serum Wisteria floribunda agglutinin-positive Mac-2-binding protein evaluates liver function and predicts prognosis in liver cirrhosis.

PubMed

Xu, Wen Ping; Wang, Ze Rui; Zou, Xia; Zhao, Chen; Wang, Rui; Shi, Pei Mei; Yuan, Zong Li; Yang, Fang; Zeng, Xin; Wang, Pei Qin; Sultan, Sakhawat; Zhang, Yan; Xie, Wei Fen

2018-04-01

Wisteria floribunda agglutinin-positive Mac-2-binding protein (WFA + -M2BP) is a novel glycobiomarker for evaluating liver fibrosis, but less is known about its role in liver cirrhosis (LC). This study aimed to investigate the utility of WFA + -M2BP in evaluating liver function and predicting prognosis of cirrhotic patients. We retrospectively included 197 patients with LC between 2013 and 2016. Serum WFA + -M2BP and various biochemical parameters were measured in all patients. With a median follow-up of 23 months, liver-related complications and deaths of 160 patients were recorded. The accuracy of WFA + -M2BP in evaluating liver function, predicting decompensation and mortality were measured by the receiver operating characteristic (ROC) curve, logistic and Cox's regression analyses, respectively. WFA + -M2BP levels increased with elevated Child-Pugh classification, especially in patients with hepatitis B virus (HBV) infection. ROC analysis confirmed the high reliability of WFA + -M2BP for the assessment of liver function using Child-Pugh classification. WFA + -M2BP was also significantly positively correlated with the model for end-stage liver disease (MELD) score. Multivariate logistic regression analysis indicated WFA + -M2BP as an independent predictor of clinical decompensation for compensated patients (odds ratio 11.958, 95% confidence interval [CI] 1.876-76.226, P = 0.009), and multivariate Cox's regression analysis verified WFA + -M2BP as an independent risk factor for liver-related death in patients with HBV infection (hazards ratio 10.596, 95% CI 1.356-82.820, P = 0.024). Serum WFA + -M2BP is a reliable predictor of liver function and prognosis in LC and could be incorporated into clinical surveillance strategies for LC patients, especially those with HBV infection. © 2018 Chinese Medical Association Shanghai Branch, Chinese Society of Gastroenterology, Renji Hospital Affiliated to Shanghai Jiaotong University School of Medicine and John Wiley & Sons Australia, Ltd.

New robust statistical procedures for the polytomous logistic regression models.

PubMed

Castilla, Elena; Ghosh, Abhik; Martin, Nirian; Pardo, Leandro

2018-05-17

This article derives a new family of estimators, namely the minimum density power divergence estimators, as a robust generalization of the maximum likelihood estimator for the polytomous logistic regression model. Based on these estimators, a family of Wald-type test statistics for linear hypotheses is introduced. Robustness properties of both the proposed estimators and the test statistics are theoretically studied through the classical influence function analysis. Appropriate real life examples are presented to justify the requirement of suitable robust statistical procedures in place of the likelihood based inference for the polytomous logistic regression model. The validity of the theoretical results established in the article are further confirmed empirically through suitable simulation studies. Finally, an approach for the data-driven selection of the robustness tuning parameter is proposed with empirical justifications. © 2018, The International Biometric Society.

Updated logistic regression equations for the calculation of post-fire debris-flow likelihood in the western United States

USGS Publications Warehouse

Staley, Dennis M.; Negri, Jacquelyn A.; Kean, Jason W.; Laber, Jayme L.; Tillery, Anne C.; Youberg, Ann M.

2016-06-30

Wildfire can significantly alter the hydrologic response of a watershed to the extent that even modest rainstorms can generate dangerous flash floods and debris flows. To reduce public exposure to hazard, the U.S. Geological Survey produces post-fire debris-flow hazard assessments for select fires in the western United States. We use publicly available geospatial data describing basin morphology, burn severity, soil properties, and rainfall characteristics to estimate the statistical likelihood that debris flows will occur in response to a storm of a given rainfall intensity. Using an empirical database and refined geospatial analysis methods, we defined new equations for the prediction of debris-flow likelihood using logistic regression methods. We showed that the new logistic regression model outperformed previous models used to predict debris-flow likelihood.

Nowcasting of Low-Visibility Procedure States with Ordered Logistic Regression at Vienna International Airport

NASA Astrophysics Data System (ADS)

Kneringer, Philipp; Dietz, Sebastian; Mayr, Georg J.; Zeileis, Achim

2017-04-01

Low-visibility conditions have a large impact on aviation safety and economic efficiency of airports and airlines. To support decision makers, we develop a statistical probabilistic nowcasting tool for the occurrence of capacity-reducing operations related to low visibility. The probabilities of four different low visibility classes are predicted with an ordered logistic regression model based on time series of meteorological point measurements. Potential predictor variables for the statistical models are visibility, humidity, temperature and wind measurements at several measurement sites. A stepwise variable selection method indicates that visibility and humidity measurements are the most important model inputs. The forecasts are tested with a 30 minute forecast interval up to two hours, which is a sufficient time span for tactical planning at Vienna Airport. The ordered logistic regression models outperform persistence and are competitive with human forecasters.

EXpectation Propagation LOgistic REgRession (EXPLORER): distributed privacy-preserving online model learning.

PubMed

Wang, Shuang; Jiang, Xiaoqian; Wu, Yuan; Cui, Lijuan; Cheng, Samuel; Ohno-Machado, Lucila

2013-06-01

We developed an EXpectation Propagation LOgistic REgRession (EXPLORER) model for distributed privacy-preserving online learning. The proposed framework provides a high level guarantee for protecting sensitive information, since the information exchanged between the server and the client is the encrypted posterior distribution of coefficients. Through experimental results, EXPLORER shows the same performance (e.g., discrimination, calibration, feature selection, etc.) as the traditional frequentist logistic regression model, but provides more flexibility in model updating. That is, EXPLORER can be updated one point at a time rather than having to retrain the entire data set when new observations are recorded. The proposed EXPLORER supports asynchronized communication, which relieves the participants from coordinating with one another, and prevents service breakdown from the absence of participants or interrupted communications. Copyright © 2013 Elsevier Inc. All rights reserved.

Neighborhood food environment and body mass index among Japanese older adults: results from the Aichi Gerontological Evaluation Study (AGES)

PubMed Central

2011-01-01

Background The majority of studies of the local food environment in relation to obesity risk have been conducted in the US, UK, and Australia. The evidence remains limited to western societies. The aim of this paper is to examine the association of local food environment to body mass index (BMI) in a study of older Japanese individuals. Methods The analysis was based on 12,595 respondents from cross-sectional data of the Aichi Gerontological Evaluation Study (AGES), conducted in 2006 and 2007. Using Geographic Information Systems (GIS), we mapped respondents' access to supermarkets, convenience stores, and fast food outlets, based on a street network (both the distance to the nearest stores and the number of stores within 500 m of the respondents' home). Multiple linear regression and logistic regression analyses were performed to examine the association between food environment and BMI. Results In contrast to previous reports, we found that better access to supermarkets was related to higher BMI. Better access to fast food outlets or convenience stores was also associated with higher BMI, but only among those living alone. The logistic regression analysis, using categorized BMI, showed that the access to supermarkets was only related to being overweight or obese, but not related to being underweight. Conclusions Our findings provide mixed support for the types of food environment measures previously used in western settings. Importantly, our results suggest the need to develop culture-specific approaches to characterizing neighborhood contexts when hypotheses are extrapolated across national borders. PMID:21777439

Collagen Triple Helix Repeat Containing-1 (CTHRC1) Expression in Oral Squamous Cell Carcinoma (OSCC): Prognostic Value and Clinico-Pathological Implications

PubMed Central

Lee, Chia Ee; Vincent-Chong, Vui King; Ramanathan, Anand; Kallarakkal, Thomas George; Karen-Ng, Lee Peng; Ghani, Wan Maria Nabillah; Rahman, Zainal Ariff Abdul; Ismail, Siti Mazlipah; Abraham, Mannil Thomas; Tay, Keng Kiong; Mustafa, Wan Mahadzir Wan; Cheong, Sok Ching; Zain, Rosnah Binti

2015-01-01

BACKGROUND: Collagen Triple Helix Repeat Containing 1 (CTHRC1) is a protein often found to be over-expressed in various types of human cancers. However, correlation between CTHRC1 expression level with clinico-pathological characteristics and prognosis in oral cancer remains unclear. Therefore, this study aimed to determine mRNA and protein expression of CTHRC1 in oral squamous cell carcinoma (OSCC) and to evaluate the clinical and prognostic impact of CTHRC1 in OSCC. METHODS: In this study, mRNA and protein expression of CTHRC1 in OSCCs were determined by quantitative PCR and immunohistochemistry, respectively. The association between CTHRC1 and clinico-pathological parameters were evaluated by univariate and multivariate binary logistic regression analyses. Correlation between CTHRC1 protein expressions with survival were analysed using Kaplan-Meier and Cox regression models. RESULTS: Current study demonstrated CTHRC1 was significantly overexpressed at the mRNA level in OSCC. Univariate analyses indicated a high-expression of CTHRC1 that was significantly associated with advanced stage pTNM staging, tumour size ≥ 4 cm and positive lymph node metastasis (LNM). However, only positive LNM remained significant after adjusting with other confounder factors in multivariate logistic regression analyses. Kaplan-Meier survival analyses and Cox model demonstrated that patients with high-expression of CTHRC1 protein were associated with poor prognosis and is an independent prognostic factor in OSCC. CONCLUSION: This study indicated that over-expression of CTHRC1 potentially as an independent predictor for positive LNM and poor prognosis in OSCC. PMID:26664254

Color vision impairment in multiple sclerosis points to retinal ganglion cell damage.

PubMed

Lampert, E J; Andorra, M; Torres-Torres, R; Ortiz-Pérez, S; Llufriu, S; Sepúlveda, M; Sola, N; Saiz, A; Sánchez-Dalmau, B; Villoslada, P; Martínez-Lapiscina, Elena H

2015-11-01

Multiple Sclerosis (MS) results in color vision impairment regardless of optic neuritis (ON). The exact location of injury remains undefined. The objective of this study is to identify the region leading to dyschromatopsia in MS patients' NON-eyes. We evaluated Spearman correlations between color vision and measures of different regions in the afferent visual pathway in 106 MS patients. Regions with significant correlations were included in logistic regression models to assess their independent role in dyschromatopsia. We evaluated color vision with Hardy-Rand-Rittler plates and retinal damage using Optical Coherence Tomography. We ran SIENAX to measure Normalized Brain Parenchymal Volume (NBPV), FIRST for thalamus volume and Freesurfer for visual cortex areas. We found moderate, significant correlations between color vision and macular retinal nerve fiber layer (rho = 0.289, p = 0.003), ganglion cell complex (GCC = GCIP) (rho = 0.353, p < 0.001), thalamus (rho = 0.361, p < 0.001), and lesion volume within the optic radiations (rho = -0.230, p = 0.030). Only GCC thickness remained significant (p = 0.023) in the logistic regression model. In the final model including lesion load and NBPV as markers of diffuse neuroaxonal damage, GCC remained associated with dyschromatopsia [OR = 0.88 95 % CI (0.80-0.97) p = 0.016]. This association remained significant when we also added sex, age, and disease duration as covariates in the regression model. Dyschromatopsia in NON-eyes is due to damage of retinal ganglion cells (RGC) in MS. Color vision can serve as a marker of RGC damage in MS.

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.

Cytopathologic differential diagnosis of low-grade urothelial carcinoma and reactive urothelial proliferation in bladder washings: a logistic regression analysis.

PubMed

Cakir, Ebru; Kucuk, Ulku; Pala, Emel Ebru; Sezer, Ozlem; Ekin, Rahmi Gokhan; Cakmak, Ozgur

2017-05-01

Conventional cytomorphologic assessment is the first step to establish an accurate diagnosis in urinary cytology. In cytologic preparations, the separation of low-grade urothelial carcinoma (LGUC) from reactive urothelial proliferation (RUP) can be exceedingly difficult. The bladder washing cytologies of 32 LGUC and 29 RUP were reviewed. The cytologic slides were examined for the presence or absence of the 28 cytologic features. The cytologic criteria showing statistical significance in LGUC were increased numbers of monotonous single (non-umbrella) cells, three-dimensional cellular papillary clusters without fibrovascular cores, irregular bordered clusters, atypical single cells, irregular nuclear overlap, cytoplasmic homogeneity, increased N/C ratio, pleomorphism, nuclear border irregularity, nuclear eccentricity, elongated nuclei, and hyperchromasia (p ˂ 0.05), and the cytologic criteria showing statistical significance in RUP were inflammatory background, mixture of small and large urothelial cells, loose monolayer aggregates, and vacuolated cytoplasm (p ˂ 0.05). When these variables were subjected to a stepwise logistic regression analysis, four features were selected to distinguish LGUC from RUP: increased numbers of monotonous single (non-umbrella) cells, increased nuclear cytoplasmic ratio, hyperchromasia, and presence of small and large urothelial cells (p = 0.0001). By this logistic model of the 32 cases with proven LGUC, the stepwise logistic regression analysis correctly predicted 31 (96.9%) patients with this diagnosis, and of the 29 patients with RUP, the logistic model correctly predicted 26 (89.7%) patients as having this disease. There are several cytologic features to separate LGUC from RUP. Stepwise logistic regression analysis is a valuable tool for determining the most useful cytologic criteria to distinguish these entities. © 2017 APMIS. Published by John Wiley & Sons Ltd.

Science of Test Research Consortium: Year Two Final Report

DTIC Science & Technology

2012-10-02

July 2012. Analysis of an Intervention for Small Unmanned Aerial System ( SUAS ) Accidents, submitted to Quality Engineering, LQEN-2012-0056. Stone... Systems Engineering. Wolf, S. E., R. R. Hill, and J. J. Pignatiello. June 2012. Using Neural Networks and Logistic Regression to Model Small Unmanned ...Human Retina. 6. Wolf, S. E. March 2012. Modeling Small Unmanned Aerial System Mishaps using Logistic Regression and Artificial Neural Networks. 7

Binary Logistic Regression Analysis for Detecting Differential Item Functioning: Effectiveness of R[superscript 2] and Delta Log Odds Ratio Effect Size Measures

ERIC Educational Resources Information Center

Hidalgo, Mª Dolores; Gómez-Benito, Juana; Zumbo, Bruno D.

2014-01-01

The authors analyze the effectiveness of the R[superscript 2] and delta log odds ratio effect size measures when using logistic regression analysis to detect differential item functioning (DIF) in dichotomous items. A simulation study was carried out, and the Type I error rate and power estimates under conditions in which only statistical testing…

Logistic quantile regression provides improved estimates for bounded avian counts: a case study of California Spotted Owl fledgling production

Treesearch

Brian S. Cade; Barry R. Noon; Rick D. Scherer; John J. Keane

2017-01-01

Counts of avian fledglings, nestlings, or clutch size that are bounded below by zero and above by some small integer form a discrete random variable distribution that is not approximated well by conventional parametric count distributions such as the Poisson or negative binomial. We developed a logistic quantile regression model to provide estimates of the empirical...

Comparison of four methods for deriving hospital standardised mortality ratios from a single hierarchical logistic regression model.

PubMed

Mohammed, Mohammed A; Manktelow, Bradley N; Hofer, Timothy P

2016-04-01

There is interest in deriving case-mix adjusted standardised mortality ratios so that comparisons between healthcare providers, such as hospitals, can be undertaken in the controversial belief that variability in standardised mortality ratios reflects quality of care. Typically standardised mortality ratios are derived using a fixed effects logistic regression model, without a hospital term in the model. This fails to account for the hierarchical structure of the data - patients nested within hospitals - and so a hierarchical logistic regression model is more appropriate. However, four methods have been advocated for deriving standardised mortality ratios from a hierarchical logistic regression model, but their agreement is not known and neither do we know which is to be preferred. We found significant differences between the four types of standardised mortality ratios because they reflect a range of underlying conceptual issues. The most subtle issue is the distinction between asking how an average patient fares in different hospitals versus how patients at a given hospital fare at an average hospital. Since the answers to these questions are not the same and since the choice between these two approaches is not obvious, the extent to which profiling hospitals on mortality can be undertaken safely and reliably, without resolving these methodological issues, remains questionable. © The Author(s) 2012.

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 comparison of three methods of assessing differential item functioning (DIF) in the Hospital Anxiety Depression Scale: ordinal logistic regression, Rasch analysis and the Mantel chi-square procedure.

PubMed

Cameron, Isobel M; Scott, Neil W; Adler, Mats; Reid, Ian C

2014-12-01

It is important for clinical practice and research that measurement scales of well-being and quality of life exhibit only minimal differential item functioning (DIF). DIF occurs where different groups of people endorse items in a scale to different extents after being matched by the intended scale attribute. We investigate the equivalence or otherwise of common methods of assessing DIF. Three methods of measuring age- and sex-related DIF (ordinal logistic regression, Rasch analysis and Mantel χ(2) procedure) were applied to Hospital Anxiety Depression Scale (HADS) data pertaining to a sample of 1,068 patients consulting primary care practitioners. Three items were flagged by all three approaches as having either age- or sex-related DIF with a consistent direction of effect; a further three items identified did not meet stricter criteria for important DIF using at least one method. When applying strict criteria for significant DIF, ordinal logistic regression was slightly less sensitive. Ordinal logistic regression, Rasch analysis and contingency table methods yielded consistent results when identifying DIF in the HADS depression and HADS anxiety scales. Regardless of methods applied, investigators should use a combination of statistical significance, magnitude of the DIF effect and investigator judgement when interpreting the results.

Extreme Sparse Multinomial Logistic Regression: A Fast and Robust Framework for Hyperspectral Image Classification

NASA Astrophysics Data System (ADS)

Cao, Faxian; Yang, Zhijing; Ren, Jinchang; Ling, Wing-Kuen; Zhao, Huimin; Marshall, Stephen

2017-12-01

Although the sparse multinomial logistic regression (SMLR) has provided a useful tool for sparse classification, it suffers from inefficacy in dealing with high dimensional features and manually set initial regressor values. This has significantly constrained its applications for hyperspectral image (HSI) classification. In order to tackle these two drawbacks, an extreme sparse multinomial logistic regression (ESMLR) is proposed for effective classification of HSI. First, the HSI dataset is projected to a new feature space with randomly generated weight and bias. Second, an optimization model is established by the Lagrange multiplier method and the dual principle to automatically determine a good initial regressor for SMLR via minimizing the training error and the regressor value. Furthermore, the extended multi-attribute profiles (EMAPs) are utilized for extracting both the spectral and spatial features. A combinational linear multiple features learning (MFL) method is proposed to further enhance the features extracted by ESMLR and EMAPs. Finally, the logistic regression via the variable splitting and the augmented Lagrangian (LORSAL) is adopted in the proposed framework for reducing the computational time. Experiments are conducted on two well-known HSI datasets, namely the Indian Pines dataset and the Pavia University dataset, which have shown the fast and robust performance of the proposed ESMLR framework.

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.

[Analysis of risk factors for dry eye syndrome in visual display terminal workers].

PubMed

Zhu, Yong; Yu, Wen-lan; Xu, Ming; Han, Lei; Cao, Wen-dong; Zhang, Hong-bing; Zhang, Heng-dong

2013-08-01

To analyze the risk factors for dry eye syndrome in visual display terminal (VDT) workers and to provide a scientific basis for protecting the eye health of VDT workers. Questionnaire survey, Schirmer I test, tear break-up time test, and workshop microenvironment evaluation were performed in 185 VDT workers. Multivariate logistic regression analysis was performed to determine the risk factors for dry eye syndrome in VDT workers after adjustment for confounding factors. In the logistic regression model, the regression coefficients of daily mean time of exposure to screen, daily mean time of watching TV, parallel screen-eye angle, upward screen-eye angle, eye-screen distance of less than 20 cm, irregular breaks during screen-exposed work, age, and female gender on the results of Schirmer I test were 0.153, 0.548, 0.400, 0.796, 0.234, 0.516, 0.559, and -0.685, respectively; the regression coefficients of daily mean time of exposure to screen, parallel screen-eye angle, upward screen-eye angle, age, working years, and female gender on tear break-up time were 0.021, 0.625, 2.652, 0.749, 0.403, and 1.481, respectively. Daily mean time of exposure to screen, daily mean time of watching TV, parallel screen-eye angle, upward screen-eye angle, eye-screen distance of less than 20 cm, irregular breaks during screen-exposed work, age, and working years are risk factors for dry eye syndrome in VDT workers.

Evaluation of Six Recombinant Proteins for Serological Diagnosis of Lyme Borreliosis in China.

PubMed

Liu, Wei; Liu, Hui Xin; Zhang, Lin; Hou, Xue Xia; Wan, Kang Lin; Hao, Qin

2016-05-01

In this study, we evaluated the diagnostic efficiency of six recombinant proteins for the serodiagnosis of Lyme borreliosis (LB) and screened out the appropriate antigens to support the production of a Chinese clinical ELISA (enzyme-linked immunosorbent assay) kit for LB. Six recombinant antigens, Fla B.g, OspC B.a, OspC B.g, P39 B.g, P83 B.g, and VlsE B.a, were used for ELISA to detect serum antibodies in LB, syphilis, and healthy controls. The ELISA results were used to generate receiver operating characteristic (ROC) curves, and the sensitivity and specificity of each protein was evaluated. All recombinant proteins were evaluated and screened by using logistic regression models. Two IgG (VlsE and OspC B.g) and two IgM (OspC B.g and OspC B.a) antigens were left by the logistic regression model screened. VlsE had the highest specificity for syphilis samples in the IgG test (87.7%, P<0.05). OspC B.g had the highest diagnostic value in the IgM test (AUC=0.871). Interactive effects between OspC B.a and Fla B.g could reduce the specificity of the ELISA. Three recombinant antigens, OspC B.g, OspC B.a, and VlsE B.a, were useful for ELISAs of LB. Additionally, the interaction between OspC B.a and Fla B.g should be examined in future research. Copyright © 2016 The Editorial Board of Biomedical and Environmental Sciences. Published by China CDC. All rights reserved.

The association between patient participation and functional gain following inpatient rehabilitation.

PubMed

Morghen, Sara; Morandi, Alessandro; Guccione, Andrew A; Bozzini, Michela; Guerini, Fabio; Gatti, Roberto; Del Santo, Francesco; Gentile, Simona; Trabucchi, Marco; Bellelli, Giuseppe

2017-08-01

To evaluate patients' participation during physical therapy sessions as assessed with the Pittsburgh rehabilitation participation scale (PRPS) as a possible predictor of functional gain after rehabilitation training. All patients aged 65 years or older consecutively admitted to a Department of Rehabilitation and Aged Care (DRAC) were evaluated on admission regarding their health, nutritional, functional and cognitive status. Functional status was assessed with the functional independence measure (FIM) on admission and at discharge. Participation during rehabilitation sessions was measured with the PRPS. Functional gain was evaluated using the Montebello rehabilitation factor score (MRFS efficacy), and patients stratified in two groups according to their level of functional gain and their sociodemographic, clinical and functional characteristics were compared. Predictors of poor functional gain were evaluated using a multivariable logistic regression model adjusted for confounding factors. A total of 556 subjects were included in this study. Patients with poor functional gain at discharge demonstrated lower participation during physical therapy sessions were significantly older, more cognitively and functionally impaired on admission, more depressed, more comorbid, and more frequently admitted for cardiac disease or immobility syndrome than their counterparts. There was a significant linear association between PRPS scores and MRFS efficacy. In a multivariable logistic regression model, participation was independently associated with functional gain at discharge (odds ratio 1.51, 95 % confidence interval 1.19-1.91). This study showed that participation during physical therapy affects the extent of functional gain at discharge in a large population of older patients with multiple diseases receiving in-hospital rehabilitation.

Electrophysiology and optical coherence tomography to evaluate Parkinson disease severity.

PubMed

Garcia-Martin, Elena; Rodriguez-Mena, Diego; Satue, Maria; Almarcegui, Carmen; Dolz, Isabel; Alarcia, Raquel; Seral, Maria; Polo, Vicente; Larrosa, Jose M; Pablo, Luis E

2014-02-04

To evaluate correlations between visual evoked potentials (VEP), pattern electroretinogram (PERG), and macular and retinal nerve fiber layer (RNFL) thickness measured by optical coherence tomography (OCT) and the severity of Parkinson disease (PD). Forty-six PD patients and 33 age and sex-matched healthy controls were enrolled, and underwent VEP, PERG, and OCT measurements of macular and RNFL thicknesses, and evaluation of PD severity using the Hoehn and Yahr scale to measure PD symptom progression, the Schwab and England Activities of Daily Living Scale (SE-ADL) to evaluate patient quality of life (QOL), and disease duration. Logistical regression was performed to analyze which measures, if any, could predict PD symptom progression or effect on QOL. Visual functional parameters (best corrected visual acuity, mean deviation of visual field, PERG positive (P) component at 50 ms -P50- and negative (N) component at 95 ms -N95- component amplitude, and PERG P50 component latency) and structural parameters (OCT measurements of RNFL and retinal thickness) were decreased in PD patients compared with healthy controls. OCT measurements were significantly negatively correlated with the Hoehn and Yahr scale, and significantly positively correlated with the SE-ADL scale. Based on logistical regression analysis, fovea thickness provided by OCT equipment predicted PD severity, and QOL and amplitude of the PERG N95 component predicted a lower SE-ADL score. Patients with greater damage in the RNFL tend to have lower QOL and more severe PD symptoms. Foveal thicknesses and the PERG N95 component provide good biomarkers for predicting QOL and disease severity.

Carboxyhemoglobin and methemoglobin levels as prognostic markers in acute pulmonary embolism.

PubMed

Kakavas, Sotirios; Papanikolaou, Aggeliki; Ballis, Evangelos; Tatsis, Nikolaos; Goga, Christina; Tatsis, Georgios

2015-04-01

Carboxyhemoglobin (COHb) and methemoglobin (MetHb) levels have been associated with a poor outcome in patients with various pathological conditions including cardiovascular diseases. Our aim was to retrospectively assess the prognostic value of arterial COHb and MetHb in patients with acute pulmonary embolism (PE). We conducted a retrospective study of 156 patients admitted in a pulmonary clinic due to acute PE. Measured variables during emergency department evaluation that were retrospectively analyzed included the ratio of the partial pressure of oxygen in arterial blood to the fraction of oxygen in inspired gas, Acute Physiology and Chronic Health Evaluation II score, risk stratification indices, and arterial blood gases. The association between arterial COHb and MetHb levels and disease severity or mortality was evaluated using bivariate tests and logistic regression analysis. Arterial COHb and MetHb levels correlated with Acute Physiology and Chronic Health Evaluation II and pulmonary severity index scores. Furthermore, arterial COHb and MetHb levels were associated with troponin T and N-terminal pro-B-type natriuretic peptide levels. In univariate logistic regression analysis, COHb and MetHb levels were both significantly associated with an increased risk of death. However, in multivariate analysis, only COHb remained significant as an independent predictor of in-hospital mortality. Our preliminary data suggest that arterial COHb and MetHb levels reflect the severity of acute PE, whereas COHb levels are independent predictors of in hospital death in patients in this clinical setting. These findings require further prospective validation. Copyright © 2015 Elsevier Inc. All rights reserved.

Inter- and intraexaminer reliability of bitewing radiography and near-infrared light transillumination for proximal caries detection and assessment.

PubMed

Litzenburger, Friederike; Heck, Katrin; Pitchika, Vinay; Neuhaus, Klaus W; Jost, Fabian N; Hickel, Reinhard; Jablonski-Momeni, Anahita; Welk, Alexander; Lederer, Alexander; Kühnisch, Jan

2018-02-01

The purpose of this in vitro study was to evaluate the inter- and intraexaminer reliability of digital bitewing (DBW) radiography and near-infrared light transillumination (NIRT) for proximal caries detection and assessment in posterior teeth. From a pool of 85 patients, 100 corresponding pairs of DBW and NIRT images (~1/3 healthy, ~1/3 with enamel caries and ~1/3 with dentin caries) were chosen. 12 dentists with different professional status and clinical experience repeated the evaluation in two blinded cycles. Two experienced dentists provided a reference diagnosis after analysing all images independently. Statistical analysis included the calculation of simple (κ) and weighted Kappa (wκ) values as a measure of reliability. Logistic regression with a backward elimination model was used to investigate the influence of the diagnostic method, evaluation cycle, type of tooth, and clinical experience on reliability. Altogether, inter- and intraexaminer reliability exhibited good to excellent κ and wκ values for DBW radiography (Inter: κ = 0.60/ 0.63; wκ = 0.74/0.76; Intra: κ = 0.64; wκ = 0.77) and NIRT (Inter: κ = 0.74/0.64; wκ = 0.86/0.82; Intra: κ = 0.68; wκ = 0.84). The backward elimination model revealed NIRT to be significantly more reliable than DBW radiography. This study revealed a good to excellent inter- and intraexaminer reliability for proximal caries detection using DBW and NIRT images. The logistic regression analysis revealed significantly better reliability for NIRT. Additionally, the first evaluation cycle was more reliable according to the reference diagnoses.

Computed Tomographic Evaluation of Posttreatment Soft-Tissue Changes by Using a Lymphedema Scoring System in Patients with Oral Cancer.

PubMed

Akashi, Masaya; Teraoka, Shun; Kakei, Yasumasa; Kusumoto, Junya; Hasegawa, Takumi; Minamikawa, Tsutomu; Hashikawa, Kazunobu; Komori, Takahide

2018-04-01

This study aimed to evaluate posttreatment soft-tissue changes in patients with oral cancer with computed tomography (CT). To accomplish that purpose, a scoring system was established, referring to the criteria of lower leg lymphedema (LE). One hundred and six necks in 95 patients who underwent oral oncologic surgery with neck dissection (ND) were analyzed retrospectively using routine follow-up CT images. A two-point scoring system to evaluate soft-tissue changes (so-called "LE score") was established as follows: Necks with a "honeycombing" appearance were assigned 1 point. Necks with "taller than wide" fat lobules were assigned 1 point. Necks with neither appearance were assigned 0 points. Comparisons between patients with LE score ≥1 and LE score = 0 at 6 months postoperatively were performed using the Fisher exact test for discrete variables and the Mann-Whitney U test for continuous variables. Univariate predictors associated with posttreatment changes (i.e., LE score ≥1 at 6 months postoperatively) were entered into a multivariate logistic regression analysis. Values of p < 0.05 were considered to indicate statistical significance. The occurrence of the posttreatment soft-tissue changes was 32%. Multivariate logistic regression analysis showed that postoperative radiation therapy (RT) and bilateral ND were potential risk factors of posttreatment soft-tissue changes on CT images. Sequential evaluation of "honeycombing" and the "taller than wide" appearances on routine follow-up CT revealed the persistence of posttreatment soft-tissue changes in patients who underwent oral cancer treatment, and those potential risk factors were postoperative RT and bilateral ND.

Transnasal endoscopic evaluation of swallowing: A bedside technique to evaluate ability to swallow pureed diets in elderly patients with dysphagia

PubMed Central

Sakamoto, Torao; Horiuchi, Akira; Nakayama, Yoshiko

2013-01-01

BACKGROUND: Endoscopic evaluation of swallowing (EES) is not commonly used by gastroenterologists to evaluate swallowing in patients with dysphagia. OBJECTIVE: To use transnasal endoscopy to identify factors predicting successful or failed swallowing of pureed foods in elderly patients with dysphagia. METHODS: EES of pureed foods was performed by a gastroenterologist using a small-calibre transnasal endoscope. Factors related to successful versus unsuccessful swallowing of pureed foods were analyzed with regard to age, comorbid diseases, swallowing activity, saliva pooling, vallecular residues, pharyngeal residues and airway penetration/aspiration. Unsuccessful swallowing was defined in patients who could not eat pureed foods at bedside during hospitalization. Logistic regression analysis was used to identify independent predictors of swallowing of pureed foods. RESULTS: During a six-year period, 458 consecutive patients (mean age 80 years [range 39 to 97 years]) were considered for the study, including 285 (62%) men. Saliva pooling, vallecular residues, pharyngeal residues and penetration/aspiration were found in 240 (52%), 73 (16%), 226 (49%) and 232 patients (51%), respectively. Overall, 247 patients (54%) failed to swallow pureed foods. Multivariate logistic regression analysis demonstrated that the presence of pharyngeal residues (OR 6.0) and saliva pooling (OR 4.6) occurred significantly more frequently in patients who failed to swallow pureed foods. CONCLUSIONS: Pharyngeal residues and saliva pooling predicted impaired swallowing of pureed foods. Transnasal EES performed by a gastroenterologist provided a unique bedside method of assessing the ability to swallow pureed foods in elderly patients with dysphagia. PMID:23936875

Risk factors for antepartum fetal death.

PubMed

Oron, T; Sheiner, E; Shoham-Vardi, I; Mazor, M; Katz, M; Hallak, M

2001-09-01

To determine the demographic, maternal, pregnancy-related and fetal risk factors for antepartum fetal death (APFD). From our perinatal database between the years 1990 and 1997, 68,870 singleton birth files were analyzed. Fetuses weighing < 1,000 g at birth and those with structural malformations and/or known chromosomal anomalies were excluded from the study. In order to determine independent factors contributing to APFD, a multiple logistic regression model was constructed. During the study period there were 246 cases of APFD (3.6 per 1,000 births). The following obstetric factors significantly correlated with APFD in a multiple logistic regression model: preterm deliveries: small size for gestational age (SGA), multiparity (> 5 deliveries), oligohydramnios, placental abruption, umbilical cord complications (cord around the neck and true knot of cord), pathologic presentations (nonvertex) and meconium-stained amniotic fluid. APFD was not significantly associated with advanced maternal age. APFD was significantly associated with several risk factors. Placental and umbilical cord pathologies might be the direct cause of death. Grand multiparity, oligohydramnios, meconium-stained amniotic fluid, pathologic presentations and suspected SGA should be carefully evaluated during pregnancy in order to decrease the incidence of APFD.

Cannabis, tobacco and domestic fumes intake are associated with nasopharyngeal carcinoma in North Africa.

PubMed

Feng, B-J; Khyatti, M; Ben-Ayoub, W; Dahmoul, S; Ayad, M; Maachi, F; Bedadra, W; Abdoun, M; Mesli, S; Bakkali, H; Jalbout, M; Hamdi-Cherif, M; Boualga, K; Bouaouina, N; Chouchane, L; Benider, A; Ben-Ayed, F; Goldgar, D E; Corbex, M

2009-10-06

The lifestyle risk factors for nasopharyngeal carcinoma (NPC) in North Africa are not known. From 2002 to 2005, we interviewed 636 patients and 615 controls from Algeria, Morocco and Tunisia, frequency-matched by centre, age, sex, and childhood household type (urban/rural). Conditional logistic regression was used to evaluate the association of lifestyles with NPC risk, controlling for socioeconomic status and dietary risk factors. Cigarette smoking and snuff (tobacco powder with additives) intake were significantly associated with differentiated NPC but not with undifferentiated carcinoma (UCNT), which is the major histological type of NPC in these populations. As demonstrated by a stratified permutation test and by conditional logistic regression, marijuana smoking significantly elevated NPC risk independently of cigarette smoking, suggesting dissimilar carcinogenic mechanisms between cannabis and tobacco. Domestic cooking fumes intake by using kanoun (compact charcoal oven) during childhood increased NPC risk, whereas exposure during adulthood had less effect. Neither alcohol nor shisha (water pipe) was associated with risk. Tobacco, cannabis and domestic cooking fumes intake are risk factors for NPC in western North Africa.

Cannabis, tobacco and domestic fumes intake are associated with nasopharyngeal carcinoma in North Africa

PubMed Central

Feng, B-J; Khyatti, M; Ben-Ayoub, W; Dahmoul, S; Ayad, M; Maachi, F; Bedadra, W; Abdoun, M; Mesli, S; Bakkali, H; Jalbout, M; Hamdi-Cherif, M; Boualga, K; Bouaouina, N; Chouchane, L; Benider, A; Ben-Ayed, F; Goldgar, D E; Corbex, M

2009-01-01

Background: The lifestyle risk factors for nasopharyngeal carcinoma (NPC) in North Africa are not known. Methods: From 2002 to 2005, we interviewed 636 patients and 615 controls from Algeria, Morocco and Tunisia, frequency-matched by centre, age, sex, and childhood household type (urban/rural). Conditional logistic regression was used to evaluate the association of lifestyles with NPC risk, controlling for socioeconomic status and dietary risk factors. Results: Cigarette smoking and snuff (tobacco powder with additives) intake were significantly associated with differentiated NPC but not with undifferentiated carcinoma (UCNT), which is the major histological type of NPC in these populations. As demonstrated by a stratified permutation test and by conditional logistic regression, marijuana smoking significantly elevated NPC risk independently of cigarette smoking, suggesting dissimilar carcinogenic mechanisms between cannabis and tobacco. Domestic cooking fumes intake by using kanoun (compact charcoal oven) during childhood increased NPC risk, whereas exposure during adulthood had less effect. Neither alcohol nor shisha (water pipe) was associated with risk. Conclusion: Tobacco, cannabis and domestic cooking fumes intake are risk factors for NPC in western North Africa. PMID:19724280

Variational dynamic background model for keyword spotting in handwritten documents

NASA Astrophysics Data System (ADS)

Kumar, Gaurav; Wshah, Safwan; Govindaraju, Venu

2013-12-01

We propose a bayesian framework for keyword spotting in handwritten documents. This work is an extension to our previous work where we proposed dynamic background model, DBM for keyword spotting that takes into account the local character level scores and global word level scores to learn a logistic regression classifier to separate keywords from non-keywords. In this work, we add a bayesian layer on top of the DBM called the variational dynamic background model, VDBM. The logistic regression classifier uses the sigmoid function to separate keywords from non-keywords. The sigmoid function being neither convex nor concave, exact inference of VDBM becomes intractable. An expectation maximization step is proposed to do approximate inference. The advantage of VDBM over the DBM is multi-fold. Firstly, being bayesian, it prevents over-fitting of data. Secondly, it provides better modeling of data and an improved prediction of unseen data. VDBM is evaluated on the IAM dataset and the results prove that it outperforms our prior work and other state of the art line based word spotting system.

Vitamin D levels and their associations with survival and major disease outcomes in a large cohort of patients with chronic graft-vs-host disease

PubMed Central

Katić, Mašenjka; Pirsl, Filip; Steinberg, Seth M.; Dobbin, Marnie; Curtis, Lauren M.; Pulanić, Dražen; Desnica, Lana; Titarenko, Irina; Pavletic, Steven Z.

2016-01-01

Aim To identify the factors associated with vitamin D status in patients with chronic graft-vs-host disease (cGVHD) and evaluate the association between serum vitamin D (25(OH)D) levels and cGVHD characteristics and clinical outcomes defined by the National Institutes of Health (NIH) criteria. Methods 310 cGVHD patients enrolled in the NIH cGVHD natural history study (clinicaltrials.gov: NCT00092235) were analyzed. Univariate analysis and multiple logistic regression were used to determine the associations between various parameters and 25(OH)D levels, dichotomized into categorical variables: ≤20 and >20 ng/mL, and as a continuous parameter. Multiple logistic regression was used to develop a predictive model for low vitamin D. Survival analysis and association between cGVHD outcomes and 25(OH)D as a continuous as well as categorical variable: ≤20 and >20 ng/mL; <50 and ≥50 ng/mL, and among three ordered categories: ≤20, 20-50, and ≥50 ng/mL, was performed. PMID:27374829

Gender differences in social support and leisure-time physical activity.

PubMed

Oliveira, Aldair J; Lopes, Claudia S; Rostila, Mikael; Werneck, Guilherme Loureiro; Griep, Rosane Härter; Leon, Antônio Carlos Monteiro Ponce de; Faerstein, Eduardo

2014-08-01

To identify gender differences in social support dimensions' effect on adults' leisure-time physical activity maintenance, type, and time. Longitudinal study of 1,278 non-faculty public employees at a university in Rio de Janeiro, RJ, Southeastern Brazil. Physical activity was evaluated using a dichotomous question with a two-week reference period, and further questions concerning leisure-time physical activity type (individual or group) and time spent on the activity. Social support was measured with the Medical Outcomes Study Social Support Scale. For the analysis, logistic regression models were adjusted separately by gender. A multinomial logistic regression showed an association between material support and individual activities among women (OR = 2.76; 95%CI 1.2;6.5). Affective support was associated with time spent on leisure-time physical activity only among men (OR = 1.80; 95%CI 1.1;3.2). All dimensions of social support that were examined influenced either the type of, or the time spent on, leisure-time physical activity. In some social support dimensions, the associations detected varied by gender. Future studies should attempt to elucidate the mechanisms involved in these gender differences.

Hyperhomocysteinemia is a risk factor for Alzheimer's disease in an Algerian population.

PubMed

Nazef, Khaled; Khelil, Malika; Chelouti, Hiba; Kacimi, Ghouti; Bendini, Mohamed; Tazir, Meriem; Belarbi, Soraya; El Hadi Cherifi, Mohamed; Djerdjouri, Bahia

2014-04-01

There is growing evidence that increased blood concentration of total homocysteine (tHcy) may be a risk factor for Alzheimer's disease (AD). The present study was conducted to evaluate the association of serum tHcy and other biochemical risk factors with AD. This is a case-control study including 41 individuals diagnosed with AD and 46 nondemented controls. Serum levels of all studied biochemical parameters were performed. Univariate logistic regression showed a significant increase of tHcy (p = 0.008), urea (p = 0.036) and a significant decrease of vitamin B12 (p = 0.012) in AD group vs. controls. Using multivariate logistic regression, tHcy (p = 0.007, OR = 1.376) appeared as an independent risk factor predictor of AD. There was a significant positive correlation between tHcy and creatinine (p <0.0001). A negative correlation was found between tHcy and vitamin B12 (p <0.0001). Our findings support that hyperhomocysteinemia is a risk factor for AD in an Algerian population and is also associated with vitamin B12 deficiency. Copyright © 2014 IMSS. Published by Elsevier Inc. All rights reserved.

Liver Rapid Reference Set Application: Kevin Qu-Quest (2011) — EDRN Public Portal

Cancer.gov

We propose to evaluate the performance of a novel serum biomarker panel for early detection of hepatocellular carcinoma (HCC). This panel is based on markers from the ubiquitin-proteasome system (UPS) in combination with the existing known HCC biomarkers, namely, alpha-fetoprotein (AFP), AFP-L3%, and des-y-carboxy prothrombin (DCP). To this end, we applied multivariate logistic regression analysis to optimize this biomarker algorithm tool.

Intracerebral hemorrhage after external ventricular drain placement: an evaluation of risk factors for post-procedural hemorrhagic complications.

PubMed

Rowe, A Shaun; Rinehart, Derrick R; Lezatte, Stephanie; Langdon, J Russell

2018-03-07

The objective of this study was to evaluate and identify the risk factors for developing a new or enlarged intracranial hemorrhage (ICH) after the placement of an external ventricular drain. A single center, nested case-control study of individuals who received an external ventricular drain from June 1, 2011 to June 30, 2014 was conducted at a large academic medical center. A bivariate analysis was conducted to compare those individuals who experienced a post-procedural intracranial hemorrhage to those who did not experience a new bleed. The variables identified as having a p-value less than 0.15 in the bivariate analysis were then evaluated using a multivariate logistic regression model. Twenty-seven of the eighty-one study participants experienced a new or enlarged intracranial hemorrhage after the placement of an external ventricular drain. Of these twenty-seven patients, 6 individuals received an antiplatelet within ninety-six hours of external ventricular drain placement (p = 0.024). The multivariate logistic regression model identified antiplatelet use within 96 h of external ventricular drain insertion as an independent risk factor for post-EVD ICH (OR 13.1; 95% CI 1.95-88.6; p = 0.008). Compared to those study participants who did not receive an antiplatelet within 96 h of external ventricular drain placement, those participants who did receive an antiplatelet were 13.1 times more likely to exhibit a new or enlarged intracranial hemorrhage.

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features

PubMed Central

Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-01-01

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout (Oncorhynchus mykiss) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k-Nearest neighbours (k-NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k-NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet’s effects on fish skin. PMID:29596375

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features.

PubMed

Saberioon, Mohammadmehdi; Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-03-29

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout ( Oncorhynchus mykiss ) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k -Nearest neighbours ( k -NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k -NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet's effects on fish skin.

Beyond logistic regression: structural equations modelling for binary variables and its application to investigating unobserved confounders.

PubMed

Kupek, Emil

2006-03-15

Structural equation modelling (SEM) has been increasingly used in medical statistics for solving a system of related regression equations. However, a great obstacle for its wider use has been its difficulty in handling categorical variables within the framework of generalised linear models. A large data set with a known structure among two related outcomes and three independent variables was generated to investigate the use of Yule's transformation of odds ratio (OR) into Q-metric by (OR-1)/(OR+1) to approximate Pearson's correlation coefficients between binary variables whose covariance structure can be further analysed by SEM. Percent of correctly classified events and non-events was compared with the classification obtained by logistic regression. The performance of SEM based on Q-metric was also checked on a small (N = 100) random sample of the data generated and on a real data set. SEM successfully recovered the generated model structure. SEM of real data suggested a significant influence of a latent confounding variable which would have not been detectable by standard logistic regression. SEM classification performance was broadly similar to that of the logistic regression. The analysis of binary data can be greatly enhanced by Yule's transformation of odds ratios into estimated correlation matrix that can be further analysed by SEM. The interpretation of results is aided by expressing them as odds ratios which are the most frequently used measure of effect in medical statistics.

Predictors of postoperative outcomes of cubital tunnel syndrome treatments using multiple logistic regression analysis.

PubMed

Suzuki, Taku; Iwamoto, Takuji; Shizu, Kanae; Suzuki, Katsuji; Yamada, Harumoto; Sato, Kazuki

2017-05-01

This retrospective study was designed to investigate prognostic factors for postoperative outcomes for cubital tunnel syndrome (CubTS) using multiple logistic regression analysis with a large number of patients. Eighty-three patients with CubTS who underwent surgeries were enrolled. The following potential prognostic factors for disease severity were selected according to previous reports: sex, age, type of surgery, disease duration, body mass index, cervical lesion, presence of diabetes mellitus, Workers' Compensation status, preoperative severity, and preoperative electrodiagnostic testing. Postoperative severity of disease was assessed 2 years after surgery by Messina's criteria which is an outcome measure specifically for CubTS. Bivariate analysis was performed to select candidate prognostic factors for multiple linear regression analyses. Multiple logistic regression analysis was conducted to identify the association between postoperative severity and selected prognostic factors. Both bivariate and multiple linear regression analysis revealed only preoperative severity as an independent risk factor for poor prognosis, while other factors did not show any significant association. Although conflicting results exist regarding prognosis of CubTS, this study supports evidence from previous studies and concludes early surgical intervention portends the most favorable prognosis. Copyright © 2017 The Japanese Orthopaedic Association. Published by Elsevier B.V. All rights reserved.

Differentiation of orbital lymphoma and idiopathic orbital inflammatory pseudotumor: combined diagnostic value of conventional MRI and histogram analysis of ADC maps.

PubMed

Ren, Jiliang; Yuan, Ying; Wu, Yingwei; Tao, Xiaofeng

2018-05-02

The overlap of morphological feature and mean ADC value restricted clinical application of MRI in the differential diagnosis of orbital lymphoma and idiopathic orbital inflammatory pseudotumor (IOIP). In this paper, we aimed to retrospectively evaluate the combined diagnostic value of conventional magnetic resonance imaging (MRI) and whole-tumor histogram analysis of apparent diffusion coefficient (ADC) maps in the differentiation of the two lesions. In total, 18 patients with orbital lymphoma and 22 patients with IOIP were included, who underwent both conventional MRI and diffusion weighted imaging before treatment. Conventional MRI features and histogram parameters derived from ADC maps, including mean ADC (ADC mean ), median ADC (ADC median ), skewness, kurtosis, 10th, 25th, 75th and 90th percentiles of ADC (ADC 10 , ADC 25 , ADC 75 , ADC 90 ) were evaluated and compared between orbital lymphoma and IOIP. Multivariate logistic regression analysis was used to identify the most valuable variables for discriminating. Differential model was built upon the selected variables and receiver operating characteristic (ROC) analysis was also performed to determine the differential ability of the model. Multivariate logistic regression showed ADC 10 (P = 0.023) and involvement of orbit preseptal space (P = 0.029) were the most promising indexes in the discrimination of orbital lymphoma and IOIP. The logistic model defined by ADC 10 and involvement of orbit preseptal space was built, which achieved an AUC of 0.939, with sensitivity of 77.30% and specificity of 94.40%. Conventional MRI feature of involvement of orbit preseptal space and ADC histogram parameter of ADC 10 are valuable in differential diagnosis of orbital lymphoma and IOIP.

Preoperative predictive model of recovery of urinary continence after radical prostatectomy.

PubMed

Matsushita, Kazuhito; Kent, Matthew T; Vickers, Andrew J; von Bodman, Christian; Bernstein, Melanie; Touijer, Karim A; Coleman, Jonathan A; Laudone, Vincent T; Scardino, Peter T; Eastham, James A; Akin, Oguz; Sandhu, Jaspreet S

2015-10-01

To build a predictive model of urinary continence recovery after radical prostatectomy (RP) that incorporates magnetic resonance imaging (MRI) parameters and clinical data. We conducted a retrospective review of data from 2,849 patients who underwent pelvic staging MRI before RP from November 2001 to June 2010. We used logistic regression to evaluate the association between each MRI variable and continence at 6 or 12 months, adjusting for age, body mass index (BMI) and American Society of Anesthesiologists (ASA) score, and then used multivariable logistic regression to create our model. A nomogram was constructed using the multivariable logistic regression models. In all, 68% (1,742/2,559) and 82% (2,205/2,689) regained function at 6 and 12 months, respectively. In the base model, age, BMI and ASA score were significant predictors of continence at 6 or 12 months on univariate analysis (P < 0.005). Among the preoperative MRI measurements, membranous urethral length, which showed great significance, was incorporated into the base model to create the full model. For continence recovery at 6 months, the addition of membranous urethral length increased the area under the curve (AUC) to 0.664 for the validation set, an increase of 0.064 over the base model. For continence recovery at 12 months, the AUC was 0.674, an increase of 0.085 over the base model. Using our model, the likelihood of continence recovery increases with membranous urethral length and decreases with age, BMI and ASA score. This model could be used for patient counselling and for the identification of patients at high risk for urinary incontinence in whom to study changes in operative technique that improve urinary function after RP. © 2015 The Authors BJU International © 2015 BJU International Published by John Wiley & Sons Ltd.

Optimization of Game Formats in U-10 Soccer Using Logistic Regression Analysis

PubMed Central

Amatria, Mario; Arana, Javier; Anguera, M. Teresa; Garzón, Belén

2016-01-01

Abstract Small-sided games provide young soccer players with better opportunities to develop their skills and progress as individual and team players. There is, however, little evidence on the effectiveness of different game formats in different age groups, and furthermore, these formats can vary between and even within countries. The Royal Spanish Soccer Association replaced the traditional grassroots 7-a-side format (F-7) with the 8-a-side format (F-8) in the 2011-12 season and the country’s regional federations gradually followed suit. The aim of this observational methodology study was to investigate which of these formats best suited the learning needs of U-10 players transitioning from 5-aside futsal. We built a multiple logistic regression model to predict the success of offensive moves depending on the game format and the area of the pitch in which the move was initiated. Success was defined as a shot at the goal. We also built two simple logistic regression models to evaluate how the game format influenced the acquisition of technicaltactical skills. It was found that the probability of a shot at the goal was higher in F-7 than in F-8 for moves initiated in the Creation Sector-Own Half (0.08 vs 0.07) and the Creation Sector-Opponent's Half (0.18 vs 0.16). The probability was the same (0.04) in the Safety Sector. Children also had more opportunities to control the ball and pass or take a shot in the F-7 format (0.24 vs 0.20), and these were also more likely to be successful in this format (0.28 vs 0.19). PMID:28031768

Left atrial accessory appendages, diverticula, and left-sided septal pouch in multi-slice computed tomography. Association with atrial fibrillation and cerebrovascular accidents.

PubMed

Hołda, Mateusz K; Koziej, Mateusz; Wszołek, Karolina; Pawlik, Wiesław; Krawczyk-Ożóg, Agata; Sorysz, Danuta; Łoboda, Piotr; Kuźma, Katarzyna; Kuniewicz, Marcin; Lelakowski, Jacek; Dudek, Dariusz; Klimek-Piotrowska, Wiesława

2017-10-01

The aim of this study is to provide a morphometric description of the left-sided septal pouch (LSSP), left atrial accessory appendages, and diverticula using cardiac multi-slice computed tomography (MSCT) and to compare results between patient subgroups. Two hundred and ninety four patients (42.9% females) with a mean of 69.4±13.1years of age were investigated using MSCT. The presence of the LSSP, left atrial accessory appendages, and diverticula was evaluated. Multiple logistic regression analysis was performed to check whether the presence of additional left atrial structures is associated with increased risk of atrial fibrillation and cerebrovascular accidents. At least one additional left atrial structure was present in 51.7% of patients. A single LSSP, left atrial diverticulum, and accessory appendage were present in 35.7%, 16.0%, and 4.1% of patients, respectively. After adjusting for other risk factors via multiple logistic regression, patients with LSSP are more likely to have atrial fibrillation (OR=2.00, 95% CI=1.14-3.48, p=0.01). The presence of a LSSP was found to be associated with an increased risk of transient ischemic attack using multiple logistic regression analysis after adjustment for other risk factors (OR=3.88, 95% CI=1.10-13.69, p=0.03). In conclusion LSSPs, accessory appendages, and diverticula are highly prevalent anatomic structures within the left atrium, which could be easily identified by MSCT. The presence of LSSP is associated with increased risk for atrial fibrillation and transient ischemic attack. Copyright © 2017 Elsevier B.V. All rights reserved.

Resident Self-Assessment and Learning Goal Development: Evaluation of Resident-Reported Competence and Future Goals.

PubMed

Li, Su-Ting T; Paterniti, Debora A; Tancredi, Daniel J; Burke, Ann E; Trimm, R Franklin; Guillot, Ann; Guralnick, Susan; Mahan, John D

2015-01-01

To determine incidence of learning goals by competency area and to assess which goals fall into competency areas with lower self-assessment scores. Cross-sectional analysis of existing deidentified American Academy of Pediatrics' PediaLink individualized learning plan data for the academic year 2009-2010. Residents self-assessed competencies in the 6 Accreditation Council for Graduate Medical Education (ACGME) competency areas and wrote learning goals. Textual responses for goals were mapped to 6 ACGME competency areas, future practice, or personal attributes. Adjusted mean differences and associations were estimated using multiple linear and logistic regression. A total of 2254 residents reported 6078 goals. Residents self-assessed their systems-based practice (51.8) and medical knowledge (53.0) competencies lowest and professionalism (68.9) and interpersonal and communication skills (62.2) highest. Residents were most likely to identify goals involving medical knowledge (70.5%) and patient care (50.5%) and least likely to write goals on systems-based practice (11.0%) and professionalism (6.9%). In logistic regression analysis adjusting for postgraduate year (PGY), gender, and degree type (MD/DO), resident-reported goal area showed no association with the learner's relative self-assessment score for that competency area. In the conditional logistic regression analysis, with each learner serving as his or her own control, senior residents (PGY2/3+s) who rated themselves relatively lower in a competency area were more likely to write a learning goal in that area than were PGY1s. Senior residents appear to develop better skills and/or motivation to explicitly turn self-assessed learning gaps into learning goals, suggesting that individualized learning plans may help improve self-regulated learning during residency. Copyright © 2015 Academic Pediatric Association. Published by Elsevier Inc. All rights reserved.

Analysis of mortality in a cohort of 650 cases of bacteremic osteoarticular infections.

PubMed

Gomez-Junyent, Joan; Murillo, Oscar; Grau, Imma; Benavent, Eva; Ribera, Alba; Cabo, Xavier; Tubau, Fe; Ariza, Javier; Pallares, Roman

2018-01-31

The mortality of patients with bacteremic osteoarticular infections (B-OAIs) is poorly understood. Whether certain types of OAIs carry higher mortality or interventions like surgical debridement can improve prognosis, are unclarified questions. Retrospective analysis of a prospective cohort of patients with B-OAIs treated at a teaching hospital in Barcelona (1985-2014), analyzing mortality (30-day case-fatality rate). B-OAIs were categorized as peripheral septic arthritis or other OAIs. Factors influencing mortality were analyzed using logistic regression models. The association of surgical debridement with mortality in patients with peripheral septic arthritis was evaluated with a multivariate logistic regression model and a propensity score matching analysis. Among 650 cases of B-OAIs, mortality was 12.2% (41.8% of deaths within 7 days). Compared with other B-OAI, cases of peripheral septic arthritis were associated with higher mortality (18.6% vs 8.3%, p < 0.001). In a multiple logistic regression model, peripheral septic arthritis was an independent predictor of mortality (adjusted odds ratio [OR] 2.12; 95% CI: 1.22-3.69; p = 0.008). Cases with peripheral septic arthritis managed with surgical debridement had lower mortality than those managed without surgery (14.7% vs 33.3%; p = 0.003). Surgical debridement was associated with reduced mortality after adjusting for covariates (adjusted OR 0.23; 95% CI: 0.09-0.57; p = 0.002) and in the propensity score matching analysis (OR 0.81; 95% CI: 0.68-0.96; p = 0.014). Among patients with B-OAIs, mortality was greater in those with peripheral septic arthritis. Surgical debridement was associated with decreased mortality in cases of peripheral septic arthritis. Copyright © 2018 Elsevier Inc. All rights reserved.

Effect of duration of denervation on outcomes of ansa-recurrent laryngeal nerve reinnervation.

PubMed

Li, Meng; Chen, Shicai; Wang, Wei; Chen, Donghui; Zhu, Minhui; Liu, Fei; Zhang, Caiyun; Li, Yan; Zheng, Hongliang

2014-08-01

To investigate the efficacy of laryngeal reinnervation with ansa cervicalis among unilateral vocal fold paralysis (UVFP) patients with different denervation durations. We retrospectively reviewed 349 consecutive UVFP cases of delayed ansa cervicalis to the recurrent laryngeal nerve (RLN) anastomosis. Potential influencing factors were analyzed in multivariable logistic regression analysis. Stratification analysis performed was aimed at one of the identified significant variables: denervation duration. Videostroboscopy, perceptual evaluation, acoustic analysis, maximum phonation time (MPT), and laryngeal electromyography (EMG) were performed preoperatively and postoperatively. Gender, age, preoperative EMG status and denervation duration were analyzed in multivariable logistic regression analysis. Stratification analysis was performed on denervation duration, which was divided into three groups according to the interval between RLN injury and reinnervation: group A, 6 to 12 months; group B, 12 to 24 months; and group C, > 24 months. Age, preoperative EMG, and denervation duration were identified as significant variables in multivariable logistic regression analysis. Stratification analysis on denervation duration showed significant differences between group A and C and between group B and C (P < 0.05)-but showed no significant difference between group A and B (P > 0.05) with regard to parameters overall grade, jitter, shimmer, noise-to-harmonics ratio, MPT, and postoperative EMG. In addition, videostroboscopic and laryngeal EMG data, perceptual and acoustic parameters, and MPT values were significantly improved postoperatively in each denervation duration group (P < 0.01). Although delayed laryngeal reinnervation is proved valid for UVFP, surgical outcome is better if the procedure is performed within 2 years after nerve injury than that over 2 years. © 2014 The American Laryngological, Rhinological and Otological Society, Inc.

Logistic regression analysis of the risk factors of anastomotic fistula after radical resection of esophageal-cardiac cancer.

PubMed

Huang, Jinxi; Zhou, Yi; Wang, Chenghu; Yuan, Weiwei; Zhang, Zhandong; Chen, Beibei; Zhang, Xiefu

2017-11-01

This study was conducted to investigate the risk factors of anastomotic fistula after the radical resection of esophageal-cardiac cancer. Five hundred and forty-four esophageal-cardiac cancer patients who underwent surgery and had complete clinical data were included in the study. Fifty patients diagnosed with postoperative anastomotic fistula were considered the case group and the remaining 494 subjects who did not develop postoperative anastomotic fistula were considered the control. The potential risk factors for anastomotic fistula, such as age, gender, diabetes history, smoking history, were collected and compared between the groups. Statistically significant variables were substituted into logistic regression to further evaluate the independent risk factors for postoperative anastomotic fistulas in esophageal-cardiac cancer. The incidence of anastomotic fistulas was 9.2% (50/544). Logistic regression analysis revealed that female gender (P < 0.05), laparoscopic surgery (P < 0.05), decreased postoperative albumin (P < 0.05), and postoperative renal dysfunction (P < 0.05) were independent risk factors for anastomotic fistulas in patients who received surgery for esophageal-cardiac cancer. Of the 50 anastomotic fistulas, 16 cases were small fistulas, which were only discovered by conventional imaging examination and not presenting clinical symptoms. All of the anastomotic fistulas occurred within seven days after surgery. Five of the patients with anastomotic fistulas underwent a second surgery and three died. Female patients with esophageal-cardiac cancer treated with endoscopic surgery and suffering from postoperative hypoproteinemia and renal dysfunction were susceptible to postoperative anastomotic fistula. © 2017 The Authors. Thoracic Cancer published by China Lung Oncology Group and John Wiley & Sons Australia, Ltd.

Prediction model of critical weight loss in cancer patients during particle therapy.

PubMed

Zhang, Zhihong; Zhu, Yu; Zhang, Lijuan; Wang, Ziying; Wan, Hongwei

2018-01-01

The objective of this study is to investigate the predictors of critical weight loss in cancer patients receiving particle therapy, and build a prediction model based on its predictive factors. Patients receiving particle therapy were enroled between June 2015 and June 2016. Body weight was measured at the start and end of particle therapy. Association between critical weight loss (defined as >5%) during particle therapy and patients' demographic, clinical characteristic, pre-therapeutic nutrition risk screening (NRS 2002) and BMI were evaluated by logistic regression and decision tree analysis. Finally, 375 cancer patients receiving particle therapy were included. Mean weight loss was 0.55 kg, and 11.5% of patients experienced critical weight loss during particle therapy. The main predictors of critical weight loss during particle therapy were head and neck tumour location, total radiation dose ≥70 Gy on the primary tumour, and without post-surgery, as indicated by both logistic regression and decision tree analysis. Prediction model that includes tumour locations, total radiation dose and post-surgery had a good predictive ability, with the area under receiver operating characteristic curve 0.79 (95% CI: 0.71-0.88) and 0.78 (95% CI: 0.69-0.86) for decision tree and logistic regression model, respectively. Cancer patients with head and neck tumour location, total radiation dose ≥70 Gy and without post-surgery were at higher risk of critical weight loss during particle therapy, and early intensive nutrition counselling or intervention should be target at this population. © The Author 2017. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Validation of use of the International Consultation on Incontinence Questionnaire-Urinary Incontinence-Short Form (ICIQ-UI-SF) for impairment rating: a transversal retrospective study of 120 patients.

PubMed

Timmermans, Luc; Falez, Freddy; Mélot, Christian; Wespes, Eric

2013-09-01

A urinary incontinence impairment rating must be a highly accurate, non-invasive exploration of the condition using International Classification of Functioning (ICF)-based assessment tools. The objective of this study was to identify the best evaluation test and to determine an impairment rating model of urinary incontinence. In performing a cross-sectional study comparing successive urodynamic tests using both the International Consultation on Incontinence Questionnaire-Urinary Incontinence-Short Form (ICIQ-UI-SF) and the 1-hr pad-weighing test in 120 patients, we performed statistical likelihood ratio analysis and used logistic regression to calculate the probability of urodynamic incontinence using the most significant independent predictors. Subsequently, we created a template that was based on the significant predictors and the probability of urodynamic incontinence. The mean ICIQ-UI-SF score was 13.5 ± 4.6, and the median pad test value was 8 g. The discrimination statistic (receiver operating characteristic) described how well the urodynamic observations matched the ICIQ-UI-SF scores (under curve area (UDA):0.689) and the pad test data (UDA: 0.693). Using logistic regression analysis, we demonstrated that the best independent predictors of urodynamic incontinence were the patient's age and the ICIQ-UI-SF score. The logistic regression model permitted us to construct an equation to determine the probability of urodynamic incontinence. Using these tools, we created a template to generate a probability index of urodynamic urinary incontinence. Using this probability index, relative to the patient and to the maximum impairment of the whole person (MIWP) relative to urinary incontinence, we were able to calculate a patient's permanent impairment. Copyright © 2012 Wiley Periodicals, Inc.

Willingness to Accept HIV Pre-Exposure Prophylaxis among Chinese Men Who Have Sex with Men

PubMed Central

Li, Shuming; Li, Dongliang; Zhang, Lifen; Fan, Wensheng; Yang, Xueying; Yu, Mingrun; Xiao, Dong; Yan, Li; Zhang, Zheng; Shi, Wei; Luo, Fengji; Ruan, Yuhua; Jin, Qi

2012-01-01

Objective We investigated the awareness and acceptability of pre-exposure prophylaxis (PrEP) among men who have sex with men (MSM) and potential predicting factors. Methods This study was conducted among MSM in Beijing, China. Study participants, randomly selected from an MSM cohort, completed a structured questionnaire, and provided their blood samples to test for HIV infection and syphilis. Univariate logistic regression analyses were performed to evaluate the factors associated with willingness to accept (WTA) PrEP. Factors independently associated with willingness to accept were identified by entering variables into stepwise logistic regression analysis. Results A total of 152 MSM completed the survey; 11.2% had ever heard of PrEP and 67.8% were willing to accept it. Univariate analysis showed that age, years of education, consistent condom use in the past 6 months, heterosexual behavior in the past 6 months, having ever heard of PrEP and the side effects of antiretroviral drugs, and worry about antiretroviral drugs cost were significantly associated with willingness to accept PrEP. In the multivariate logistic regression model, only consistent condom use in the past 6 months (odds ratio [OR]: 0.31; 95% confidence interval [CI]: 0.13–0.70) and having ever heard of the side effects of antiretroviral drugs (OR: 0.30; 95% CI: 0.14–0.67) were independently associated with willingness to accept PrEP. Conclusions The awareness of PrEP in the MSM population was low. Sexual behavioral characteristics and knowledge about ART drugs may have effects on willingness to accept PrEP. Comprehensive prevention strategies should be recommended in the MSM community. PMID:22479320

The impact of the 2008 financial crisis on food security and food expenditures in Mexico: a disproportionate effect on the vulnerable.

PubMed

Vilar-Compte, Mireya; Sandoval-Olascoaga, Sebastian; Bernal-Stuart, Ana; Shimoga, Sandhya; Vargas-Bustamante, Arturo

2015-11-01

The present paper investigated the impact of the 2008 financial crisis on food security in Mexico and how it disproportionally affected vulnerable households. A generalized ordered logistic regression was estimated to assess the impact of the crisis on households' food security status. An ordinary least squares and a quantile regression were estimated to evaluate the effect of the financial crisis on a continuous proxy measure of food security defined as the share of a household's current income devoted to food expenditures. Setting Both analyses were performed using pooled cross-sectional data from the Mexican National Household Income and Expenditure Survey 2008 and 2010. The analytical sample included 29,468 households in 2008 and 27,654 in 2010. The generalized ordered logistic model showed that the financial crisis significantly (P<0·05) decreased the probability of being food secure, mildly or moderately food insecure, compared with being severely food insecure (OR=0·74). A similar but smaller effect was found when comparing severely and moderately food-insecure households with mildly food-insecure and food-secure households (OR=0·81). The ordinary least squares model showed that the crisis significantly (P<0·05) increased the share of total income spent on food (β coefficient of 0·02). The quantile regression confirmed the findings suggested by the generalized ordered logistic model, showing that the effects of the crisis were more profound among poorer households. The results suggest that households that were more vulnerable before the financial crisis saw a worsened effect in terms of food insecurity with the crisis. Findings were consistent with both measures of food security--one based on self-reported experience and the other based on food spending.

Nailfold capillaroscopy for prediction of novel future severe organ involvement in systemic sclerosis.

PubMed

Smith, Vanessa; Riccieri, Valeria; Pizzorni, Carmen; Decuman, Saskia; Deschepper, Ellen; Bonroy, Carolien; Sulli, Alberto; Piette, Yves; De Keyser, Filip; Cutolo, Maurizio

2013-12-01

Assessment of associations of nailfold videocapillaroscopy (NVC) scleroderma (systemic sclerosis; SSc) ("early," "active," and "late") with novel future severe clinical involvement in 2 independent cohorts. Sixty-six consecutive Belgian and 82 Italian patients with SSc underwent NVC at baseline. Images were blindly assessed and classified into normal, early, active, or late NVC pattern. Clinical evaluation was performed for 9 organ systems (general, peripheral vascular, skin, joint, muscle, gastrointestinal tract, lung, heart, and kidney) according to the Medsger disease severity scale (DSS) at baseline and in the future (18-24 months of followup). Severe clinical involvement was defined as category 2 to 4 per organ of the DSS. Logistic regression analysis (continuous NVC predictor variable) was performed. The OR to develop novel future severe organ involvement was stronger according to more severe NVC patterns and similar in both cohorts. In simple logistic regression analysis the OR in the Belgian/Italian cohort was 2.16 (95% CI 1.19-4.47, p = 0.010)/2.33 (95% CI 1.36-4.22, p = 0.002) for the early NVC SSc pattern, 4.68/5.42 for the active pattern, and 10.14/12.63 for the late pattern versus the normal pattern. In multiple logistic regression analysis, adjusting for disease duration, subset, and vasoactive medication, the OR was 2.99 (95% CI 1.31-8.82, p = 0.007)/1.88 (95% CI 1.00-3.71, p = 0.050) for the early NVC SSc pattern, 8.93/3.54 for the active pattern, and 26.69/6.66 for the late pattern versus the normal pattern. Capillaroscopy may be predictive of novel future severe organ involvement in SSc, as attested by 2 independent cohorts.

Association Between Duration of Breast Feeding and Metabolic Syndrome: The Korean National Health and Nutrition Examination Surveys.

PubMed

Choi, Se Rin; Kim, Yong Min; Cho, Min Su; Kim, So Hyun; Shim, Young Suk

2017-04-01

This study aimed to evaluate the association of the lifelong duration of breast feeding with metabolic syndrome (MetS) and its components in Korean parous women aged 19-50 years. A total of 4724 participants from the Korean National Health and Nutritional Survey were included. Subjects were divided into four groups according to the duration of breast feeding: ≤5, 6-11, 12-23, or ≥24 months groups. The adjusted odds ratios (ORs) of MetS and its components were assessed according to the duration of breast feeding. Women who breastfed for 6-11 months had an OR of 0.67 (95% confidence interval [CI], 0.54-0.86) for elevated blood pressure (BP) compared with those who breastfed for ≤5 months after adjustment for possible confounders in a multivariable logistic regression analyses. Women who breastfed for 12-23 months were associated with an OR of 0.68 (95% CI, 0.54-0.86) for elevated BP, an OR of 0.78 (95% CI, 0.62-0.97) for elevated glucose, and an OR of 0.73 (95% CI, 0.56-0.95) for MetS compared with those who breastfed for ≤5 months in a multivariable logistic regression analyses. Women who breastfed for ≥24 months had an OR of 0.62 (95% CI, 0.52-0.84) for elevated glucose, an OR of 0.76 (95% CI, 0.60-0.96) for elevated triglycerides, and an OR of 0.70 (95% CI, 0.53-0.92) for MetS compared with those who breastfed for ≤5 months in a multivariable logistic regression analyses. Our results suggest that lifelong breast feeding for ≥12 months may be associated with lower risk for MetS.

A Logistic Regression Analysis of Turkey's 15-Year-Olds' Scoring above the OECD Average on the PISA'09 Reading Assessment

ERIC Educational Resources Information Center

Kasapoglu, Koray

2014-01-01

This study aims to investigate which factors are associated with Turkey's 15-year-olds' scoring above the OECD average (493) on the PISA'09 reading assessment. Collected from a total of 4,996 15-year-old students from Turkey, data were analyzed by logistic regression analysis in order to model the data of students who were split into two: (1)…

Upgrade Summer Severe Weather Tool

NASA Technical Reports Server (NTRS)

Watson, Leela

2011-01-01

The goal of this task was to upgrade to the existing severe weather database by adding observations from the 2010 warm season, update the verification dataset with results from the 2010 warm season, use statistical logistic regression analysis on the database and develop a new forecast tool. The AMU analyzed 7 stability parameters that showed the possibility of providing guidance in forecasting severe weather, calculated verification statistics for the Total Threat Score (TTS), and calculated warm season verification statistics for the 2010 season. The AMU also performed statistical logistic regression analysis on the 22-year severe weather database. The results indicated that the logistic regression equation did not show an increase in skill over the previously developed TTS. The equation showed less accuracy than TTS at predicting severe weather, little ability to distinguish between severe and non-severe weather days, and worse standard categorical accuracy measures and skill scores over TTS.

Estimating the Probability of Rare Events Occurring Using a Local Model Averaging.

PubMed

Chen, Jin-Hua; Chen, Chun-Shu; Huang, Meng-Fan; Lin, Hung-Chih

2016-10-01

In statistical applications, logistic regression is a popular method for analyzing binary data accompanied by explanatory variables. But when one of the two outcomes is rare, the estimation of model parameters has been shown to be severely biased and hence estimating the probability of rare events occurring based on a logistic regression model would be inaccurate. In this article, we focus on estimating the probability of rare events occurring based on logistic regression models. Instead of selecting a best model, we propose a local model averaging procedure based on a data perturbation technique applied to different information criteria to obtain different probability estimates of rare events occurring. Then an approximately unbiased estimator of Kullback-Leibler loss is used to choose the best one among them. We design complete simulations to show the effectiveness of our approach. For illustration, a necrotizing enterocolitis (NEC) data set is analyzed. © 2016 Society for Risk Analysis.

The use of logistic regression to enhance risk assessment and decision making by mental health administrators.

PubMed

Menditto, Anthony A; Linhorst, Donald M; Coleman, James C; Beck, Niels C

2006-04-01

Development of policies and procedures to contend with the risks presented by elopement, aggression, and suicidal behaviors are long-standing challenges for mental health administrators. Guidance in making such judgments can be obtained through the use of a multivariate statistical technique known as logistic regression. This procedure can be used to develop a predictive equation that is mathematically formulated to use the best combination of predictors, rather than considering just one factor at a time. This paper presents an overview of logistic regression and its utility in mental health administrative decision making. A case example of its application is presented using data on elopements from Missouri's long-term state psychiatric hospitals. Ultimately, the use of statistical prediction analyses tempered with differential qualitative weighting of classification errors can augment decision-making processes in a manner that provides guidance and flexibility while wrestling with the complex problem of risk assessment and decision making.

An application in identifying high-risk populations in alternative tobacco product use utilizing logistic regression and CART: a heuristic comparison.

PubMed

Lei, Yang; Nollen, Nikki; Ahluwahlia, Jasjit S; Yu, Qing; Mayo, Matthew S

2015-04-09

Other forms of tobacco use are increasing in prevalence, yet most tobacco control efforts are aimed at cigarettes. In light of this, it is important to identify individuals who are using both cigarettes and alternative tobacco products (ATPs). Most previous studies have used regression models. We conducted a traditional logistic regression model and a classification and regression tree (CART) model to illustrate and discuss the added advantages of using CART in the setting of identifying high-risk subgroups of ATP users among cigarettes smokers. The data were collected from an online cross-sectional survey administered by Survey Sampling International between July 5, 2012 and August 15, 2012. Eligible participants self-identified as current smokers, African American, White, or Latino (of any race), were English-speaking, and were at least 25 years old. The study sample included 2,376 participants and was divided into independent training and validation samples for a hold out validation. Logistic regression and CART models were used to examine the important predictors of cigarettes + ATP users. The logistic regression model identified nine important factors: gender, age, race, nicotine dependence, buying cigarettes or borrowing, whether the price of cigarettes influences the brand purchased, whether the participants set limits on cigarettes per day, alcohol use scores, and discrimination frequencies. The C-index of the logistic regression model was 0.74, indicating good discriminatory capability. The model performed well in the validation cohort also with good discrimination (c-index = 0.73) and excellent calibration (R-square = 0.96 in the calibration regression). The parsimonious CART model identified gender, age, alcohol use score, race, and discrimination frequencies to be the most important factors. It also revealed interesting partial interactions. The c-index is 0.70 for the training sample and 0.69 for the validation sample. The misclassification rate was 0.342 for the training sample and 0.346 for the validation sample. The CART model was easier to interpret and discovered target populations that possess clinical significance. This study suggests that the non-parametric CART model is parsimonious, potentially easier to interpret, and provides additional information in identifying the subgroups at high risk of ATP use among cigarette smokers.

Risk factors affecting human traumatic tympanic membrane perforation regeneration therapy using fibroblast growth factor-2.

PubMed

Lou, Zhengcai; Yang, Jian; Tang, Yongmei; Xiao, Jian

2015-01-01

The use of growth factors to achieve closure of human traumatic tympanic membrane perforations (TMPs) has recently been demonstrated. However, pretreatment factors affecting healing outcomes have seldom been discussed. The objective of this study was to evaluate pretreatment factors contributing to the success or failure of healing of TMPs using fibroblast growth factor-2 (FGF-2). A retrospective cohort study of 99 patients (43 males, 56 females) with traumatic TMPs who were observed for at least 6 months after FGF-2 treatment between March 2011 and December 2012. Eleven factors considered likely to affect the outcome of perforation closure were evaluated statistically using univariate and multivariate logistic regression analysis. Each traumatic TMP was treated by direct application of FGF-2. Complete closure versus failure to close. In total, 99 patients were analyzed. The total closure rate was 92/99 (92.9%) at 6 months; the mean closure time was 10.59 ±  6.81 days. The closure rate did not significantly differ between perforations with or without inverted edges (100.0% vs. 91.4%, p = 0.087), among different size groups (p = 0.768), or among different periods of exposure to injury (p = 0.051). However, the closure rate was significantly different between the high- and low-dose FGF-2 groups (85.0% vs. 98.3%, p = 0.010) and between perforations where the umbo or malleus was or was not involved in perforation (85.4% vs. 98.3%, p = 0.012). Additionally, univariate logistic regression analysis tests showed that it was difficult to achieve healing of these perforations with a history of chronic otitis media or residual TM calcification (p = 0.006), the umbo or malleus was involved in perforation (p = 0.038), and with a high dose of FGF-2 (p = 0.035) compared with control groups. Multivariate logistic regression analysis showed that only a history of chronic otitis media and residual TM calcification and perforation close to the umbo or malleus were associated with non-healing of the TM perforation (p = 0.03 and p = 0.017, respectively) with relative risk factors. Direct application of FGF-2 can be used in all traumatic TMPs, the size of the perforation and inverted edges did not affect the closure rate, and the most beneficial dose was sufficient to keep the residual eardrum environment moist, but without adding liquid. Additionally, multivariate logistic regression analysis revealed that a large perforation was not a major risk factor for nonhealing of TM perforations. However, a history of chronic otitis media, residual TM calcification and involvement of the umbo or malleus in perforation were significant risk factors.

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.

Identification of immune correlates of protection in Shigella infection by application of machine learning.

PubMed

Arevalillo, Jorge M; Sztein, Marcelo B; Kotloff, Karen L; Levine, Myron M; Simon, Jakub K

2017-10-01

Immunologic correlates of protection are important in vaccine development because they give insight into mechanisms of protection, assist in the identification of promising vaccine candidates, and serve as endpoints in bridging clinical vaccine studies. Our goal is the development of a methodology to identify immunologic correlates of protection using the Shigella challenge as a model. The proposed methodology utilizes the Random Forests (RF) machine learning algorithm as well as Classification and Regression Trees (CART) to detect immune markers that predict protection, identify interactions between variables, and define optimal cutoffs. Logistic regression modeling is applied to estimate the probability of protection and the confidence interval (CI) for such a probability is computed by bootstrapping the logistic regression models. The results demonstrate that the combination of Classification and Regression Trees and Random Forests complements the standard logistic regression and uncovers subtle immune interactions. Specific levels of immunoglobulin IgG antibody in blood on the day of challenge predicted protection in 75% (95% CI 67-86). Of those subjects that did not have blood IgG at or above a defined threshold, 100% were protected if they had IgA antibody secreting cells above a defined threshold. Comparison with the results obtained by applying only logistic regression modeling with standard Akaike Information Criterion for model selection shows the usefulness of the proposed method. Given the complexity of the immune system, the use of machine learning methods may enhance traditional statistical approaches. When applied together, they offer a novel way to quantify important immune correlates of protection that may help the development of vaccines. Copyright © 2017 Elsevier Inc. All rights reserved.

The quest for conditional independence in prospectivity modeling: weights-of-evidence, boost weights-of-evidence, and logistic regression

NASA Astrophysics Data System (ADS)

Schaeben, Helmut; Semmler, Georg

2016-09-01

The objective of prospectivity modeling is prediction of the conditional probability of the presence T = 1 or absence T = 0 of a target T given favorable or prohibitive predictors B, or construction of a two classes 0,1 classification of T. A special case of logistic regression called weights-of-evidence (WofE) is geologists' favorite method of prospectivity modeling due to its apparent simplicity. However, the numerical simplicity is deceiving as it is implied by the severe mathematical modeling assumption of joint conditional independence of all predictors given the target. General weights of evidence are explicitly introduced which are as simple to estimate as conventional weights, i.e., by counting, but do not require conditional independence. Complementary to the regression view is the classification view on prospectivity modeling. Boosting is the construction of a strong classifier from a set of weak classifiers. From the regression point of view it is closely related to logistic regression. Boost weights-of-evidence (BoostWofE) was introduced into prospectivity modeling to counterbalance violations of the assumption of conditional independence even though relaxation of modeling assumptions with respect to weak classifiers was not the (initial) purpose of boosting. In the original publication of BoostWofE a fabricated dataset was used to "validate" this approach. Using the same fabricated dataset it is shown that BoostWofE cannot generally compensate lacking conditional independence whatever the consecutively processing order of predictors. Thus the alleged features of BoostWofE are disproved by way of counterexamples, while theoretical findings are confirmed that logistic regression including interaction terms can exactly compensate violations of joint conditional independence if the predictors are indicators.

Comparison of two landslide susceptibility assessments in the Champagne-Ardenne region (France)

NASA Astrophysics Data System (ADS)

Den Eeckhaut, M. Van; Marre, A.; Poesen, J.

2010-02-01

The vineyards of the Montagne de Reims are mostly planted on steep south-oriented cuesta fronts receiving a maximum of sun radiation. Due to the location of the vineyards on steep hillslopes, the viticultural activity is threatened by slope failures. This study attempts to better understand the spatial patterns of landslide susceptibility in the Champagne-Ardenne region by comparing a heuristic (qualitative) and a statistical (quantitative) model in a 1120 km² study area. The heuristic landslide susceptibility model was adopted from the Bureau de Recherches Géologiques et Minières, the GEGEAA - Reims University and the Comité Interprofessionnel du Vin de Champagne. In this model, expert knowledge of the region was used to assign weights to all slope classes and lithologies present in the area, but the final susceptibility map was never evaluated with the location of mapped landslides. For the statistical landslide susceptibility assessment, logistic regression was applied to a dataset of 291 'old' (Holocene) landslides. The robustness of the logistic regression model was evaluated and ROC curves were used for model calibration and validation. With regard to the variables assumed to be important environmental factors controlling landslides, the two models are in agreement. They both indicate that present and future landslides are mainly controlled by slope gradient and lithology. However, the comparison of the two landslide susceptibility maps through (1) an evaluation with the location of mapped 'old' landslides and through (2) a temporal validation with spatial data of 'recent' (1960-1999; n = 48) and 'very recent' (2000-2008; n = 46) landslides showed a better prediction capacity for the statistical model produced in this study compared to the heuristic model. In total, the statistically-derived landslide susceptibility map succeeded in correctly classifying 81.0% of the 'old' and 91.6% of the 'recent' and 'very recent' landslides. On the susceptibility map derived from the heuristic model, on the other hand, only 54.6% of the 'old' and 64.0% of the 'recent' and 'very recent' landslides were correctly classified as unstable. Hence, the landslide susceptibility map obtained from logistic regression is a better tool for regional landslide susceptibility analysis in the study area of the Montagne de Reims. The accurate classification of zones with very high and high susceptibility allows delineating zones where viticulturists should be informed and where implementation of precaution measures is needed to secure slope stability.

Separation in Logistic Regression: Causes, Consequences, and Control.

PubMed

Mansournia, Mohammad Ali; Geroldinger, Angelika; Greenland, Sander; Heinze, Georg

2018-04-01

Separation is encountered in regression models with a discrete outcome (such as logistic regression) where the covariates perfectly predict the outcome. It is most frequent under the same conditions that lead to small-sample and sparse-data bias, such as presence of a rare outcome, rare exposures, highly correlated covariates, or covariates with strong effects. In theory, separation will produce infinite estimates for some coefficients. In practice, however, separation may be unnoticed or mishandled because of software limits in recognizing and handling the problem and in notifying the user. We discuss causes of separation in logistic regression and describe how common software packages deal with it. We then describe methods that remove separation, focusing on the same penalized-likelihood techniques used to address more general sparse-data problems. These methods improve accuracy, avoid software problems, and allow interpretation as Bayesian analyses with weakly informative priors. We discuss likelihood penalties, including some that can be implemented easily with any software package, and their relative advantages and disadvantages. We provide an illustration of ideas and methods using data from a case-control study of contraceptive practices and urinary tract infection.

Modeling the dynamics of urban growth using multinomial logistic regression: a case study of Jiayu County, Hubei Province, China

NASA Astrophysics Data System (ADS)

Nong, Yu; Du, Qingyun; Wang, Kun; Miao, Lei; Zhang, Weiwei

2008-10-01

Urban growth modeling, one of the most important aspects of land use and land cover change study, has attracted substantial attention because it helps to comprehend the mechanisms of land use change thus helps relevant policies made. This study applied multinomial logistic regression to model urban growth in the Jiayu county of Hubei province, China to discover the relationship between urban growth and the driving forces of which biophysical and social-economic factors are selected as independent variables. This type of regression is similar to binary logistic regression, but it is more general because the dependent variable is not restricted to two categories, as those previous studies did. The multinomial one can simulate the process of multiple land use competition between urban land, bare land, cultivated land and orchard land. Taking the land use type of Urban as reference category, parameters could be estimated with odds ratio. A probability map is generated from the model to predict where urban growth will occur as a result of the computation.

Prediction of primary vs secondary hypertension in children.

PubMed

Baracco, Rossana; Kapur, Gaurav; Mattoo, Tej; Jain, Amrish; Valentini, Rudolph; Ahmed, Maheen; Thomas, Ronald

2012-05-01

Despite current guidelines, variability exists in the workup of hypertensive children due to physician preferences. The study evaluates primary vs secondary hypertension diagnosis from investigations routinely performed in hypertensive children. This retrospective study included children 5 to 19 years with primary and secondary hypertension. The proportions of abnormal laboratory and imaging tests were compared between primary and secondary hypertension groups. Risk factors for primary vs secondary hypertension were evaluated by logistic regression and likelihood function analysis. Patients with secondary hypertension were younger (5-12 years) and had a higher proportion of abnormal creatinine, renal ultrasound, and echocardiogram findings. There was no significant difference in abnormal results of thyroid function, urine catecholamines, plasma renin, and aldosterone. Abnormal renal ultrasound findings and age were predictors of secondary hypertension by regression and likelihood function analysis. Children aged 5 to 12 years with abnormal renal ultrasound findings and high diastolic blood pressures are at higher risk for secondary hypertension that requires detailed evaluation. © 2012 Wiley Periodicals, Inc.

Regional danger assessment of Debris flow and its engineering mitigation practice in Sichuan-Tibet highway

NASA Astrophysics Data System (ADS)

Su, Pengcheng; Sun, Zhengchao; li, Yong

2017-04-01

Luding-Kangding highway cross the eastern edge of Qinghai-Tibet Plateau where belong to the most deep canyon area of plateau and mountains in western Sichuan with high mountain and steep slope. This area belongs to the intersection among Xianshuihe, Longmenshan and Anninghe fault zones which are best known in Sichuan province. In the region, seismic intensity is with high frequency and strength, new tectonic movement is strong, rock is cracked, there are much loose solid materials. Debris flow disaster is well developed under the multiple effects of the earthquake, strong rainfall and human activity which poses a great threat to the local people's life and property security. So this paper chooses Kangding and LuDing as the study area to do the debris flow hazard assessment through the in-depth analysis of development characteristics and formation mechanism of debris flow. Which can provide important evidence for local disaster assessment and early warning forecast. It also has the important scientific significance and practical value to safeguard the people's life and property safety and the security implementation of the national major project. In this article, occurrence mechanism of debris flow disasters in the study area is explored, factor of evaluation with high impact to debris flow hazards is identified, the database of initial evaluation factors is made by the evaluation unit of basin. The factors with high impact to hazards occurrence are selected by using the stepwise regression method of logistic regression model, at the same time the factors with low impact are eliminated, then the hazard evaluation factor system of debris flow is determined in the study area. Then every factors of evaluation factor system are quantified, and the weights of all evaluation factors are determined by using the analysis of stepwise regression. The debris flows hazard assessment and regionalization of all the whole study area are achieved eventually after establishing the hazard assessment model. In this paper, regional debris flows hazard assessment method with strong universality and reliable evaluation result is presented. The whole study area is divided into 1674 units by automatically extracting and artificial identification, and then 11 factors are selected as the initial assessment factors of debris flow hazard assessment in the study area. The factors of the evaluation index system are quantified using the method of standardized watershed unit amount ratio. The relationship between debris flow occurrence and each evaluation factor is simulated using logistic regression model. The weights of evaluation factors are determined, and the model of debris flows hazard assessment is established in the study area. Danger assessment result of debris flow was applied in line optimization and engineering disaster reduction of Sichuan-Tibet highway (section of Luding-Kangding).

Prediction of performance on the RCMP physical ability requirement evaluation.

PubMed

Stanish, H I; Wood, T M; Campagna, P

1999-08-01

The Royal Canadian Mounted Police use the Physical Ability Requirement Evaluation (PARE) for screening applicants. The purposes of this investigation were to identify those field tests of physical fitness that were associated with PARE performance and determine which most accurately classified successful and unsuccessful PARE performers. The participants were 27 female and 21 male volunteers. Testing included measures of aerobic power, anaerobic power, agility, muscular strength, muscular endurance, and body composition. Multiple regression analysis revealed a three-variable model for males (70-lb bench press, standing long jump, and agility) explaining 79% of the variability in PARE time, whereas a one-variable model (agility) explained 43% of the variability for females. Analysis of the classification accuracy of the males' data was prohibited because 91% of the males passed the PARE. Classification accuracy of the females' data, using logistic regression, produced a two-variable model (agility, 1.5-mile endurance run) with 93% overall classification accuracy.

Elevated Fasting Blood Glucose Is Predictive of Poor Outcome in Non-Diabetic Stroke Patients: A Sub-Group Analysis of SMART.

PubMed

Yao, Ming; Ni, Jun; Zhou, Lixin; Peng, Bin; Zhu, Yicheng; Cui, Liying

2016-01-01

Although increasing evidence suggests that hyperglycemia following acute stroke adversely affects clinical outcome, whether the association between glycaemia and functional outcome varies between stroke patients with\\without pre-diagnosed diabetes remains controversial. We aimed to investigate the relationship between the fasting blood glucose (FBG) and the 6-month functional outcome in a subgroup of SMART cohort and further to assess whether this association varied based on the status of pre-diagnosed diabetes. Data of 2862 patients with acute ischemic stroke (629 with pre-diagnosed diabetics) enrolled from SMART cohort were analyzed. Functional outcome at 6-month post-stroke was measured by modified Rankin Scale (mRS) and categorized as favorable (mRS:0-2) or poor (mRS:3-5). Binary logistic regression model, adjusting for age, gender, educational level, history of hypertension and stroke, baseline NIHSS and treatment group, was used in the whole cohort to evaluate the association between admission FBG and functional outcome. Stratified logistic regression analyses were further performed based on the presence/absence of pre-diabetes history. In the whole cohort, multivariable logistical regression showed that poor functional outcome was associated with elevated FBG (OR1.21 (95%CI 1.07-1.37), p = 0.002), older age (OR1.64 (95% CI1.38-1.94), p<0.001), higher NIHSS (OR2.90 (95%CI 2.52-3.33), p<0.001) and hypertension (OR1.42 (95%CI 1.13-1.98), p = 0.04). Stratified logistical regression analysis showed that the association between FBG and functional outcome remained significant only in patients without pre-diagnosed diabetes (OR1.26 (95%CI 1.03-1.55), p = 0.023), but not in those with premorbid diagnosis of diabetes (p = 0.885). The present results demonstrate a significant association between elevated FBG after stroke and poor functional outcome in patients without pre-diagnosed diabetes, but not in diabetics. This finding confirms the importance of glycemic control during acute phase of ischemic stroke especially in patients without pre-diagnosed diabetes. Further investigation for developing optimal strategies to control blood glucose level in hyperglycemic setting is therefore of great importance. ClinicalTrials.gov NCT00664846.

The association between insured male expatriates' knowledge of health insurance benefits and lack of access to health care in Saudi Arabia.

PubMed

Alkhamis, Abdulwahab A

2018-03-15

Insufficient knowledge of health insurance benefits could be associated with lack of access to health care, particularly for minority populations. This study aims to assess the association between expatriates' knowledge of health insurance benefits and lack of access to health care. A cross-sectional study design was conducted from March 2015 to February 2016 among 3398 insured male expatriates in Riyadh, Saudi Arabia. The dependent variable was binary and expresses access or lack of access to health care. Independent variables included perceived and validated knowledge of health insurance benefits and other variables. Data were summarized by computing frequencies and percentage of all quantities of variables. To evaluate variations in knowledge, personal and job characteristics with lack of access to health care, the Chi square test was used. Odds ratio (OR) and 95% confidence interval (CI) were recorded for each independent variable. Multiple logistic regression and stepwise logistic regression were performed and adjusted ORs were extracted. Descriptive analysis showed that 15% of participants lacked access to health care. The majority of these were unskilled laborers, usually with no education (17.5%), who had been working for less than 3 years (28.1%) in Saudi Arabia. A total of 23.3% worked for companies with less than 50 employees and 16.5% earned less than 4500 Saudi Riyals monthly ($1200). Many (20.3%) were young (< 30 years old) or older (17.9% ≥ 56 years old) and had no formal education (24.7%). Nearly half had fair or poor health status (49.5%), were uncomfortable conversing in Arabic (29.7%) or English (16.7%) and lacked previous knowledge of health insurance (18%). For perceived knowledge of health insurance, 55.2% scored 1 or 0 from total of 3. For validated knowledge, 16.9% scored 1 or 0 from total score of 4. Multiple logistic regression analysis showed that only perceived knowledge of health insurance had significant associations with lack of access to health care ((OR) = 0.393, (CI) = 0.335-0.461), but the result was insignificant for validated knowledge. Stepwise logistic regression gave similar findings. Our results confirmed that low perceived knowledge of health insurance in expatriates was associated with less access to health care.

Creating Cost Growth Models for the Engineering and Manufacturing Development Phase of Acquisition Using Logistic and Multiple Regression

DTIC Science & Technology

2004-03-01

constant variance via an analysis of the residuals, as well as the Breusch - Pagan test (see Figure 3 below). As a result, we follow the footsteps of...reasonably normal, which ensures that our residuals meet the assumption of constant variance by passing the Breusch - Pagan test (see Figure 4 below...sections for Research and Development, Test and Evaluation (RDT&E), procurement and military construction (Jarvaise, 1996:3). While differing

Logistic regression model can reduce unnecessary artificial liver support in hepatitis B virus-associated acute-on-chronic liver failure: decision curve analysis.

PubMed

Qin, Gang; Bian, Zhao-Lian; Shen, Yi; Zhang, Lei; Zhu, Xiao-Hong; Liu, Yan-Mei; Shao, Jian-Guo

2016-06-04

Several models have been proposed to predict the short-term outcome of acute-on-chronic liver failure (ACLF) after treatment. We aimed to determine whether better decisions for artificial liver support system (ALSS) treatment could be made with a model than without, through decision curve analysis (DCA). The medical profiles of a cohort of 232 patients with hepatitis B virus (HBV)-associated ACLF were retrospectively analyzed to explore the role of plasma prothrombin activity (PTA), model for end-stage liver disease (MELD) and logistic regression model (LRM) in identifying patients who could benefit from ALSS. The accuracy and reliability of PTA, MELD and LRM were evaluated with previously reported cutoffs. DCA was performed to evaluate the clinical role of these models in predicting the treatment outcome. With the cut-off value of 0.2, LRM had sensitivity of 92.6 %, specificity of 42.3 % and an area under the receiving operating characteristic curve (AUC) of 0.68, which showed superior discrimination over PTA and MELD. DCA revealed that the LRM-guided ALSS treatment was superior over other strategies including "treating all" and MELD-guided therapy, for the midrange threshold probabilities of 16 to 64 %. The use of LRM-guided ALSS treatment could increase both the accuracy and efficiency of this procedure, allowing the avoidance of unnecessary ALSS.

Deep cerebral microbleeds are negatively associated with HDL-C in elderly first-time ischemic stroke patients.

PubMed

Igase, Michiya; Kohara, Katsuhiko; Igase, Keiji; Yamashita, Shiro; Fujisawa, Mutsuo; Katagi, Ryosuke; Miki, Tetsuro

2013-02-15

Cerebral microbleeds (CMBs) detected on T2*-weighted MRI gradient-echo have been associated with increased risk of cerebral infarction. We evaluated risk factors for these lesions in a cohort of first-time ischemic stroke patients. Presence of CMBs in consecutive first-time ischemic stroke patients was evaluated. The location of CMBs was classified by cerebral region as strictly lobar (lobar CMBs) and deep or infratentorial (deep CMBs). Logistic regression analysis was performed to determine the contribution of lipid profile to the presence of CMBs. One hundred and sixteen patients with a mean age of 70±10years were recruited. CMBs were present in 74 patients. The deep CMBs group had significantly lower HDL-C levels than those without CMBs. In univariable analysis, advanced periventricular hyperintensity grade (PVH>2) and decreased HDL-C were significantly associated with the deep but not the lobar CMB group. On logistic regression analysis, HDL-C (beta=-0.06, p=0.002) and PVH grade >2 (beta=3.40, p=0.005) were independent determinants of deep CMBs. Low HDL-C may be a risk factor of deep CMBs, including advanced PVH status, in elderly patients with acute ischemic stroke. Management of HDL-C levels might be a therapeutic target for the prevention of recurrence of stroke. Copyright © 2012 Elsevier B.V. All rights reserved.

Association between chronic viral hepatitis infection and breast cancer risk: a nationwide population-based case-control study

PubMed Central

2011-01-01

Background In Taiwan, there is a high incidence of breast cancer and a high prevalence of viral hepatitis. In this case-control study, we used a population-based insurance dataset to evaluate whether breast cancer in women is associated with chronic viral hepatitis infection. Methods From the claims data, we identified 1,958 patients with newly diagnosed breast cancer during the period 2000-2008. A randomly selected, age-matched cohort of 7,832 subjects without cancer was selected for comparison. Multivariable logistic regression models were constructed to calculate odds ratios of breast cancer associated with viral hepatitis after adjustment for age, residential area, occupation, urbanization, and income. The age-specific (<50 years and ≥50 years) risk of breast cancer was also evaluated. Results There were no significant differences in the prevalence of hepatitis C virus (HCV) infection, hepatitis B virus (HBV), or the prevalence of combined HBC/HBV infection between breast cancer patients and control subjects (p = 0.48). Multivariable logistic regression analysis, however, revealed that age <50 years was associated with a 2-fold greater risk of developing breast cancer (OR = 2.03, 95% CI = 1.23-3.34). Conclusions HCV infection, but not HBV infection, appears to be associated with early onset risk of breast cancer in areas endemic for HCV and HBV. This finding needs to be replicated in further studies. PMID:22115285

Loop versus divided colostomy for the management of anorectal malformations.

PubMed

Oda, Omar; Davies, Dafydd; Colapinto, Kimberly; Gerstle, J Ted

2014-01-01

The purpose of this study was to compare the clinical outcomes of loop and divided colostomies in patients with anorectal malformations (ARM). We performed a retrospective cohort study reviewing the medical records of all patients with ARM managed with diverting colostomies between 2000 and 2010 at our institution. Independent variables and outcomes of stoma complications were analyzed by parametric measures and logistic regression. One hundred forty-four patients managed with a colostomy for ARM were evaluated (37.5% females, 50.7% loop, 49.3% divided). The incidence of patients with loop and divided colostomies who developed stoma-related complications was 31.5 and 15.5%, respectively (p=0.031). The incidence of prolapse was 17.8 and 2.8%, respectively (p=0.005). Multivariable-logistic regression controlling for other significant independent variables found loop colostomies to be positively associated with the development of a stoma complication (OR 3.13, 95%CI (1.09, 8.96), p=0.033). When individual complications were evaluated, it was only stoma prolapse that was more likely in patients with loop colostomies (OR 8.75, 95%CI (1.74, 44.16), p=0.009). Because of the higher incidence of prolapse, loop colostomies were found to be associated with a higher total incidence of complications than divided stomas. The development of other complications, including urinary tract infections (UTIs) and megarectum, were independent of the type of colostomy performed. © 2014.

Constructive thinking, rational intelligence and irritable bowel syndrome

PubMed Central

Rey, Enrique; Ortega, Marta Moreno; Alonso, Monica Olga Garcia; Diaz-Rubio, Manuel

2009-01-01

AIM: To evaluate rational and experiential intelligence in irritable bowel syndrome (IBS) sufferers. METHODS: We recruited 100 subjects with IBS as per Rome II criteria (50 consulters and 50 non-consulters) and 100 healthy controls, matched by age, sex and educational level. Cases and controls completed a clinical questionnaire (including symptom characteristics and medical consultation) and the following tests: rational-intelligence (Wechsler Adult Intelligence Scale, 3rd edition); experiential-intelligence (Constructive Thinking Inventory); personality (NEO personality inventory); psychopathology (MMPI-2), anxiety (state-trait anxiety inventory) and life events (social readjustment rating scale). Analysis of variance was used to compare the test results of IBS-sufferers and controls, and a logistic regression model was then constructed and adjusted for age, sex and educational level to evaluate any possible association with IBS. RESULTS: No differences were found between IBS cases and controls in terms of IQ (102.0 ± 10.8 vs 102.8 ± 12.6), but IBS sufferers scored significantly lower in global constructive thinking (43.7 ± 9.4 vs 49.6 ± 9.7). In the logistic regression model, global constructive thinking score was independently linked to suffering from IBS [OR 0.92 (0.87-0.97)], without significant OR for total IQ. CONCLUSION: IBS subjects do not show lower rational intelligence than controls, but lower experiential intelligence is nevertheless associated with IBS. PMID:19575489

Determinants of physician utilization, emergency room use, and hospitalizations among populations with multiple health vulnerabilities.

PubMed

Small, La Fleur F

2011-09-01

Understanding the factors that influence differing types of health care utilization within vulnerable groups can serve as a basis for projecting future health care needs, forecasting future health care expenditures, and influencing social policy. In this article the Behavioral Model for Vulnerable Populations is used to evaluate discretionary (physician visits) and non-discretionary (emergency room visits, and hospitalizations) health utilization patterns of a sample of 1466 respondents with one or more vulnerable health classification. Reported vulnerabilities include: (1) persons with substance disorders; (2) homeless persons; (3) persons with mental health problems; (4) victims of violent crime; (5) persons diagnosed with HIV/AIDS; (6) and persons in receipt of public benefits. Hierarchical logistic regression is used on three nested models to model factors that influence physician visits, emergency room visits, and hospitalizations. Additionally, bivariate logistic regression analyses are completed using a vulnerability index to evaluate the impact of increased numbers of vulnerability on all three forms of health care utilization. Findings from this study suggest the Behavioral Model of Vulnerable Populations be employed in future research regarding health care utilization patterns among vulnerable populations. This article encourages further research investigating the cumulative effect of health vulnerabilities on the use of non-discretionary services so that this behavior could be better understood and appropriate social policies and behavioral interventions implemented.

Biopharmaceutical industry-sponsored global clinical trials in emerging countries.

PubMed

Alvarenga, Lenio Souza; Martins, Elisabeth Nogueira

2010-01-01

To evaluate biopharmaceutical industry-sponsored clinical trials placed in countries previously described as emerging regions for clinical research, and potential differences for those placed in Brazil. Data regarding recruitment of subjects for clinical trials were retrieved from www.clinicaltrials.gov on February 2nd 2009. Proportions of sites in each country were compared among emerging countries. Multiple logistic regressions were performed to evaluate whether trial placement in Brazil could be predicted by trial location in other countries and/or by trial features. A total of 8,501 trials were then active and 1,170 (13.8%) included sites in emerging countries (i.e., Argentina, Brazil, China, Czech Republic, Hungary, India, Mexico, Poland, Russia, South Korea, and South Africa). South Korea and China presented a significantly higher proportion of sites when compared to other countries (p<0.05). Multiple logistic regressions detected no negative correlation between placement in other countries when compared to Brazil. Trials involving subjects with less than 15 years of age, those with targeted recruitment of at least 1,000 subjects, and seven sponsors were identified as significant predictors of trial placement in Brazil. No clear direct competition between Brazil and other emerging countries was detected. South Korea showed the higher proportion of sites and ranked third in total number of trials, appearing as a major player in attractiveness for biopharmaceutical industry-sponsored clinical trials.

Arteriovenous fistula maturation in patients with permanent access created prior to or after hemodialysis initiation.

PubMed

Duque, Juan C; Martinez, Laisel; Tabbara, Marwan; Dvorquez, Denise; Mehandru, Sushil K; Asif, Arif; Vazquez-Padron, Roberto I; Salman, Loay H

2017-05-15

Multiple factors and comorbidities have been implicated in the ability of arteriovenous fistulas (AVF) to mature, including vessel anatomy, advanced age, and the presence of coronary artery disease or peripheral vascular disease. However, little is known about the role of uremia on AVF primary failure. In this study, we attempt to evaluate the effect of uremia on AVF maturation by comparing AVF outcomes between pre-dialysis chronic kidney disease (CKD) stage five patients and those who had their AVF created after hemodialysis (HD) initiation. We included 612 patients who underwent AVF creation between 2003 and 2015 at the University of Miami Hospital and Jackson Memorial Hospital. Effects of uremia on primary failure were evaluated using univariate statistical comparisons and multivariate logistic regression analyses. Primary failure occurred in 28.1% and 26.3% of patients with an AVF created prior to or after HD initiation, respectively (p = 0.73). The time of HD initiation was not associated with AVF maturation in multivariate logistic regression analysis (p = 0.57). In addition, pre-operative blood urea nitrogen (p = 0.78), estimated glomerular filtration rate (p = 0.66), and serum creatinine levels (p = 0.14) were not associated with AVF primary failure in pre-dialysis patients. Our results show that clearance of uremia with regular HD treatments prior to AVF creation does not improve the frequency of vascular access maturation.

Outcome and prognostic factors in critically ill patients with systemic lupus erythematosus: a retrospective study.

PubMed

Hsu, Chia-Lin; Chen, Kuan-Yu; Yeh, Pu-Sheng; Hsu, Yeong-Long; Chang, Hou-Tai; Shau, Wen-Yi; Yu, Chia-Li; Yang, Pan-Chyr

2005-06-01

Systemic lupus erythematosus (SLE) is an archetypal autoimmune disease, involving multiple organ systems with varying course and prognosis. However, there is a paucity of clinical data regarding prognostic factors in SLE patients admitted to the intensive care unit (ICU). From January 1992 to December 2000, all patients admitted to the ICU with a diagnosis of SLE were included. Patients were excluded if the diagnosis of SLE was established at or after ICU admission. A multivariate logistic regression model was applied using Acute Physiology and Chronic Health Evaluation II scores and variables that were at least moderately associated (P < 0.2) with survival in the univariate analysis. A total of 51 patients meeting the criteria were included. The mortality rate was 47%. The most common cause of admission was pneumonia with acute respiratory distress syndrome. Multivariate logistic regression analysis showed that intracranial haemorrhage occurring while the patient was in the ICU (relative risk = 18.68), complicating gastrointestinal bleeding (relative risk = 6.97) and concurrent septic shock (relative risk = 77.06) were associated with greater risk of dying, whereas causes of ICU admission and Acute Physiology and Chronic Health Evaluation II score were not significantly associated with death. The mortality rate in critically ill SLE patients was high. Gastrointestinal bleeding, intracranial haemorrhage and septic shock were significant prognostic factors in SLE patients admitted to the ICU.

Between-centre variability in transfer function analysis, a widely used method for linear quantification of the dynamic pressure–flow relation: The CARNet study

PubMed Central

Meel-van den Abeelen, Aisha S.S.; Simpson, David M.; Wang, Lotte J.Y.; Slump, Cornelis H.; Zhang, Rong; Tarumi, Takashi; Rickards, Caroline A.; Payne, Stephen; Mitsis, Georgios D.; Kostoglou, Kyriaki; Marmarelis, Vasilis; Shin, Dae; Tzeng, Yu-Chieh; Ainslie, Philip N.; Gommer, Erik; Müller, Martin; Dorado, Alexander C.; Smielewski, Peter; Yelicich, Bernardo; Puppo, Corina; Liu, Xiuyun; Czosnyka, Marek; Wang, Cheng-Yen; Novak, Vera; Panerai, Ronney B.; Claassen, Jurgen A.H.R.

2014-01-01

Transfer function analysis (TFA) is a frequently used method to assess dynamic cerebral autoregulation (CA) using spontaneous oscillations in blood pressure (BP) and cerebral blood flow velocity (CBFV). However, controversies and variations exist in how research groups utilise TFA, causing high variability in interpretation. The objective of this study was to evaluate between-centre variability in TFA outcome metrics. 15 centres analysed the same 70 BP and CBFV datasets from healthy subjects (n = 50 rest; n = 20 during hypercapnia); 10 additional datasets were computer-generated. Each centre used their in-house TFA methods; however, certain parameters were specified to reduce a priori between-centre variability. Hypercapnia was used to assess discriminatory performance and synthetic data to evaluate effects of parameter settings. Results were analysed using the Mann–Whitney test and logistic regression. A large non-homogeneous variation was found in TFA outcome metrics between the centres. Logistic regression demonstrated that 11 centres were able to distinguish between normal and impaired CA with an AUC > 0.85. Further analysis identified TFA settings that are associated with large variation in outcome measures. These results indicate the need for standardisation of TFA settings in order to reduce between-centre variability and to allow accurate comparison between studies. Suggestions on optimal signal processing methods are proposed. PMID:24725709

Investigation of possibility of surface rupture derived from PFDHA and calculation of surface displacement based on dislocation

NASA Astrophysics Data System (ADS)

Inoue, N.; Kitada, N.; Irikura, K.

2013-12-01

A probability of surface rupture is important to configure the seismic source, such as area sources or fault models, for a seismic hazard evaluation. In Japan, Takemura (1998) estimated the probability based on the historical earthquake data. Kagawa et al. (2004) evaluated the probability based on a numerical simulation of surface displacements. The estimated probability indicates a sigmoid curve and increases between Mj (the local magnitude defined and calculated by Japan Meteorological Agency) =6.5 and Mj=7.0. The probability of surface rupture is also used in a probabilistic fault displacement analysis (PFDHA). The probability is determined from the collected earthquake catalog, which were classified into two categories: with surface rupture or without surface rupture. The logistic regression is performed for the classified earthquake data. Youngs et al. (2003), Ross and Moss (2011) and Petersen et al. (2011) indicate the logistic curves of the probability of surface rupture by normal, reverse and strike-slip faults, respectively. Takao et al. (2013) shows the logistic curve derived from only Japanese earthquake data. The Japanese probability curve shows the sharply increasing in narrow magnitude range by comparison with other curves. In this study, we estimated the probability of surface rupture applying the logistic analysis to the surface displacement derived from a surface displacement calculation. A source fault was defined in according to the procedure of Kagawa et al. (2004), which determined a seismic moment from a magnitude and estimated the area size of the asperity and the amount of slip. Strike slip and reverse faults were considered as source faults. We applied Wang et al. (2003) for calculations. The surface displacements with defined source faults were calculated by varying the depth of the fault. A threshold value as 5cm of surface displacement was used to evaluate whether a surface rupture reach or do not reach to the surface. We carried out the logistic regression analysis to the calculated displacements, which were classified by the above threshold. The estimated probability curve indicated the similar trend to the result of Takao et al. (2013). The probability of revere faults is larger than that of strike slip faults. On the other hand, PFDHA results show different trends. The probability of reverse faults at higher magnitude is lower than that of strike slip and normal faults. Ross and Moss (2011) suggested that the sediment and/or rock over the fault compress and not reach the displacement to the surface enough. The numerical theory applied in this study cannot deal with a complex initial situation such as topography.

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.

[A case-control study: association between oral hygiene and oral cancer in non-smoking and non-drinking women].

PubMed

Wu, J F; Lin, L S; Chen, F; Liu, F Q; Huang, J F; Yan, L J; Liu, F P; Qiu, Y; Zheng, X Y; Cai, L; He, B C

2017-08-06

Objective: To evaluate the influence of oral hygiene on risk of oral cancer in non-smoking and non-drinking women. Methods: From September 2010 to February 2016, 242 non-smoking and non-drinking female patients with pathologically confirmed oral cancer were recruited in a hospital of Fuzhou, and another 856 non-smoking and non-drinking healthy women from health examination center in the same hospital were selected as control group. Five oral hygiene related variables including the frequency of teeth brushing, number of teeth lost, poor prosthesis, regular dental visits and recurrent dental ulceration were used to develop oral hygiene index model. Unconditional logistic regression was used to calculate odds ratios ( OR ) and 95% confidence intervals (95 %CI ). The area under the receiver operating characteristic curve (AUROC) was used to evaluate the predictability of the oral hygiene index model. Multivariate logistic regression model was used to analyze the association between oral hygiene index and the incidence of oral cancer. Results: Teeth brushing <2 twice daily, teeth lost ≥5, poor prosthesis, no regular dental visits, recurrent dental ulceration were risk factors for the incidence of oral cancer in non-smoking and non-drinking women, the corresponding OR (95 %CI ) were 1.50 (1.08-2.09), 1.81 (1.15-2.85), 1.51 (1.03-2.23), 1.73 (1.15-2.59), 7.30 (4.00-13.30), respectively. The AUROC of the oral hygiene index model was 0.705 9, indicating a high predictability. Multivariate logistic regression showed that the oral hygiene index was associated with risk of oral cancer. The higher the score, the higher risk was observed. The corresponding OR (95 %CI ) of oral hygiene index scores (score 1, score 2, score 3, score 4-5) were 2.51 (0.84-7.53), 4.68 (1.59-13.71), 6.47 (2.18-19.25), 15.29 (5.08-45.99), respectively. Conclusion: Oral hygiene could influence the incidence of oral cancer in non-smoking and non-drinking women, and oral hygiene index has a certain significance in assessing the combined effects of oral hygiene.

Model selection for logistic regression models

NASA Astrophysics Data System (ADS)

Duller, Christine

2012-09-01

Model selection for logistic regression models decides which of some given potential regressors have an effect and hence should be included in the final model. The second interesting question is whether a certain factor is heterogeneous among some subsets, i.e. whether the model should include a random intercept or not. In this paper these questions will be answered with classical as well as with Bayesian methods. The application show some results of recent research projects in medicine and business administration.

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.

Unconditional or Conditional Logistic Regression Model for Age-Matched Case-Control Data?

PubMed

Kuo, Chia-Ling; Duan, Yinghui; Grady, James

2018-01-01

Matching on demographic variables is commonly used in case-control studies to adjust for confounding at the design stage. There is a presumption that matched data need to be analyzed by matched methods. Conditional logistic regression has become a standard for matched case-control data to tackle the sparse data problem. The sparse data problem, however, may not be a concern for loose-matching data when the matching between cases and controls is not unique, and one case can be matched to other controls without substantially changing the association. Data matched on a few demographic variables are clearly loose-matching data, and we hypothesize that unconditional logistic regression is a proper method to perform. To address the hypothesis, we compare unconditional and conditional logistic regression models by precision in estimates and hypothesis testing using simulated matched case-control data. Our results support our hypothesis; however, the unconditional model is not as robust as the conditional model to the matching distortion that the matching process not only makes cases and controls similar for matching variables but also for the exposure status. When the study design involves other complex features or the computational burden is high, matching in loose-matching data can be ignored for negligible loss in testing and estimation if the distributions of matching variables are not extremely different between cases and controls.

Unconditional or Conditional Logistic Regression Model for Age-Matched Case–Control Data?

PubMed Central

Kuo, Chia-Ling; Duan, Yinghui; Grady, James

2018-01-01

Matching on demographic variables is commonly used in case–control studies to adjust for confounding at the design stage. There is a presumption that matched data need to be analyzed by matched methods. Conditional logistic regression has become a standard for matched case–control data to tackle the sparse data problem. The sparse data problem, however, may not be a concern for loose-matching data when the matching between cases and controls is not unique, and one case can be matched to other controls without substantially changing the association. Data matched on a few demographic variables are clearly loose-matching data, and we hypothesize that unconditional logistic regression is a proper method to perform. To address the hypothesis, we compare unconditional and conditional logistic regression models by precision in estimates and hypothesis testing using simulated matched case–control data. Our results support our hypothesis; however, the unconditional model is not as robust as the conditional model to the matching distortion that the matching process not only makes cases and controls similar for matching variables but also for the exposure status. When the study design involves other complex features or the computational burden is high, matching in loose-matching data can be ignored for negligible loss in testing and estimation if the distributions of matching variables are not extremely different between cases and controls. PMID:29552553

Estimating multilevel logistic regression models when the number of clusters is low: a comparison of different statistical software procedures.

PubMed

Austin, Peter C

2010-04-22

Multilevel logistic regression models are increasingly being used to analyze clustered data in medical, public health, epidemiological, and educational research. Procedures for estimating the parameters of such models are available in many statistical software packages. There is currently little evidence on the minimum number of clusters necessary to reliably fit multilevel regression models. We conducted a Monte Carlo study to compare the performance of different statistical software procedures for estimating multilevel logistic regression models when the number of clusters was low. We examined procedures available in BUGS, HLM, R, SAS, and Stata. We found that there were qualitative differences in the performance of different software procedures for estimating multilevel logistic models when the number of clusters was low. Among the likelihood-based procedures, estimation methods based on adaptive Gauss-Hermite approximations to the likelihood (glmer in R and xtlogit in Stata) or adaptive Gaussian quadrature (Proc NLMIXED in SAS) tended to have superior performance for estimating variance components when the number of clusters was small, compared to software procedures based on penalized quasi-likelihood. However, only Bayesian estimation with BUGS allowed for accurate estimation of variance components when there were fewer than 10 clusters. For all statistical software procedures, estimation of variance components tended to be poor when there were only five subjects per cluster, regardless of the number of clusters.

Building a Decision Support System for Inpatient Admission Prediction With the Manchester Triage System and Administrative Check-in Variables.

PubMed

Zlotnik, Alexander; Alfaro, Miguel Cuchí; Pérez, María Carmen Pérez; Gallardo-Antolín, Ascensión; Martínez, Juan Manuel Montero

2016-05-01

The usage of decision support tools in emergency departments, based on predictive models, capable of estimating the probability of admission for patients in the emergency department may give nursing staff the possibility of allocating resources in advance. We present a methodology for developing and building one such system for a large specialized care hospital using a logistic regression and an artificial neural network model using nine routinely collected variables available right at the end of the triage process.A database of 255.668 triaged nonobstetric emergency department presentations from the Ramon y Cajal University Hospital of Madrid, from January 2011 to December 2012, was used to develop and test the models, with 66% of the data used for derivation and 34% for validation, with an ordered nonrandom partition. On the validation dataset areas under the receiver operating characteristic curve were 0.8568 (95% confidence interval, 0.8508-0.8583) for the logistic regression model and 0.8575 (95% confidence interval, 0.8540-0. 8610) for the artificial neural network model. χ Values for Hosmer-Lemeshow fixed "deciles of risk" were 65.32 for the logistic regression model and 17.28 for the artificial neural network model. A nomogram was generated upon the logistic regression model and an automated software decision support system with a Web interface was built based on the artificial neural network model.

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.

Added sugars and periodontal disease in young adults: an analysis of NHANES III data.

PubMed

Lula, Estevam C O; Ribeiro, Cecilia C C; Hugo, Fernando N; Alves, Cláudia M C; Silva, Antônio A M

2014-10-01

Added sugar consumption seems to trigger a hyperinflammatory state and may result in visceral adiposity, dyslipidemia, and insulin resistance. These conditions are risk factors for periodontal disease. However, the role of sugar intake in the cause of periodontal disease has not been adequately studied. We evaluated the association between the frequency of added sugar consumption and periodontal disease in young adults by using NHANES III data. Data from 2437 young adults (aged 18-25 y) who participated in NHANES III (1988-1994) were analyzed. We estimated the frequency of added sugar consumption by using food-frequency questionnaire responses. We considered periodontal disease to be present in teeth with bleeding on probing and a probing depth ≥3 mm at one or more sites. We evaluated this outcome as a discrete variable in Poisson regression models and as a categorical variable in multinomial logistic regression models adjusted for sex, age, race-ethnicity, education, poverty-income ratio, tobacco exposure, previous diagnosis of diabetes, and body mass index. A high consumption of added sugars was associated with a greater prevalence of periodontal disease in middle [prevalence ratio (PR): 1.39; 95% CI: 1.02, 1.89] and upper (PR: 1.42; 95% CI: 1.08, 1.85) tertiles of consumption in the adjusted Poisson regression model. The upper tertile of added sugar intake was associated with periodontal disease in ≥2 teeth (PR: 1.73; 95% CI: 1.19, 2.52) but not with periodontal disease in only one tooth (PR: 0.85; 95% CI: 0.54, 1.34) in the adjusted multinomial logistic regression model. A high frequency of consumption of added sugars is associated with periodontal disease, independent of traditional risk factors, suggesting that this consumption pattern may contribute to the systemic inflammation observed in periodontal disease and associated noncommunicable diseases. © 2014 American Society for Nutrition.

Predicting the risk of patients with biopsy Gleason score 6 to harbor a higher grade cancer.

PubMed

Gofrit, Ofer N; Zorn, Kevin C; Taxy, Jerome B; Lin, Shang; Zagaja, Gregory P; Steinberg, Gary D; Shalhav, Arieh L

2007-11-01

Prostate cancer Gleason score 3 + 3 = 6 is currently the most common score assigned on prostatic biopsies. We analyzed the clinical variables that predict the likelihood of a patient with biopsy Gleason score 6 to harbor a higher grade tumor. The study population consisted of 448 patients with a mean age of 59.1 years who underwent radical prostatectomy between February 2003 to October 2006 for Gleason score 6 adenocarcinoma. The effect of preoperative variables on the probability of a Gleason score upgrade on final pathological evaluation was evaluated using logistic regression, and classification and regression tree analysis. Gleason score upgrade was found in 91 of 448 patients (20.3%). Logistic regression showed that only serum prostate specific antigen and the greatest percent of cancer in a core were significantly associated with a score upgrade (p = 0.0014 and 0.023, respectively). Classification and regression tree analysis showed that the risk of a Gleason score upgrade was 62% when serum prostate specific antigen was higher than 12 ng/ml and 18% when serum prostate specific antigen was 12 ng/ml or less. In patients with serum prostate specific antigen lower than 12 ng/ml the risk of a score upgrade could be dichotomized at a greatest percent of cancer in a core of 5%. The risk was 22.6% and 10.5% when the greatest percent of cancer in a core was higher than 5% and 5% or lower, respectively. The probability of patients with a prostate biopsy Gleason score of 6 to conceal a Gleason score of 7 or higher can be predicted using serum prostate specific antigen and the greatest percent of cancer in a core. With these parameters it is possible to predict upgrade rates as high as 62% and as low as 10.5%.

Basic Diagnosis and Prediction of Persistent Contrail Occurrence using High-resolution Numerical Weather Analyses/Forecasts and Logistic Regression. Part II: Evaluation of Sample Models

NASA Technical Reports Server (NTRS)

Duda, David P.; Minnis, Patrick

2009-01-01

Previous studies have shown that probabilistic forecasting may be a useful method for predicting persistent contrail formation. A probabilistic forecast to accurately predict contrail formation over the contiguous United States (CONUS) is created by using meteorological data based on hourly meteorological analyses from the Advanced Regional Prediction System (ARPS) and from the Rapid Update Cycle (RUC) as well as GOES water vapor channel measurements, combined with surface and satellite observations of contrails. Two groups of logistic models were created. The first group of models (SURFACE models) is based on surface-based contrail observations supplemented with satellite observations of contrail occurrence. The second group of models (OUTBREAK models) is derived from a selected subgroup of satellite-based observations of widespread persistent contrails. The mean accuracies for both the SURFACE and OUTBREAK models typically exceeded 75 percent when based on the RUC or ARPS analysis data, but decreased when the logistic models were derived from ARPS forecast data.

[Use of multiple regression models in observational studies (1970-2013) and requirements of the STROBE guidelines in Spanish scientific journals].

PubMed

Real, J; Cleries, R; Forné, C; Roso-Llorach, A; Martínez-Sánchez, J M

In medicine and biomedical research, statistical techniques like logistic, linear, Cox and Poisson regression are widely known. The main objective is to describe the evolution of multivariate techniques used in observational studies indexed in PubMed (1970-2013), and to check the requirements of the STROBE guidelines in the author guidelines in Spanish journals indexed in PubMed. A targeted PubMed search was performed to identify papers that used logistic linear Cox and Poisson models. Furthermore, a review was also made of the author guidelines of journals published in Spain and indexed in PubMed and Web of Science. Only 6.1% of the indexed manuscripts included a term related to multivariate analysis, increasing from 0.14% in 1980 to 12.3% in 2013. In 2013, 6.7, 2.5, 3.5, and 0.31% of the manuscripts contained terms related to logistic, linear, Cox and Poisson regression, respectively. On the other hand, 12.8% of journals author guidelines explicitly recommend to follow the STROBE guidelines, and 35.9% recommend the CONSORT guideline. A low percentage of Spanish scientific journals indexed in PubMed include the STROBE statement requirement in the author guidelines. Multivariate regression models in published observational studies such as logistic regression, linear, Cox and Poisson are increasingly used both at international level, as well as in journals published in Spanish. Copyright © 2015 Sociedad Española de Médicos de Atención Primaria (SEMERGEN). Publicado por Elsevier España, S.L.U. All rights reserved.

The microbiological profile and presence of bloodstream infection influence mortality rates in necrotizing fasciitis

PubMed Central

2011-01-01

Introduction Necrotizing fasciitis (NF) is a life threatening infectious disease with a high mortality rate. We carried out a microbiological characterization of the causative pathogens. We investigated the correlation of mortality in NF with bloodstream infection and with the presence of co-morbidities. Methods In this retrospective study, we analyzed 323 patients who presented with necrotizing fasciitis at two different institutions. Bloodstream infection (BSI) was defined as a positive blood culture result. The patients were categorized as survivors and non-survivors. Eleven clinically important variables which were statistically significant by univariate analysis were selected for multivariate regression analysis and a stepwise logistic regression model was developed to determine the association between BSI and mortality. Results Univariate logistic regression analysis showed that patients with hypotension, heart disease, liver disease, presence of Vibrio spp. in wound cultures, presence of fungus in wound cultures, and presence of Streptococcus group A, Aeromonas spp. or Vibrio spp. in blood cultures, had a significantly higher risk of in-hospital mortality. Our multivariate logistic regression analysis showed a higher risk of mortality in patients with pre-existing conditions like hypotension, heart disease, and liver disease. Multivariate logistic regression analysis also showed that presence of Vibrio spp in wound cultures, and presence of Streptococcus Group A in blood cultures were associated with a high risk of mortality while debridement > = 3 was associated with improved survival. Conclusions Mortality in patients with necrotizing fasciitis was significantly associated with the presence of Vibrio in wound cultures and Streptococcus group A in blood cultures. PMID:21693053

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.

[Biodiversity and depressive symptoms in Mexican adults: Exploration of beneficial environmental effects].

PubMed

Duarte-Tagles, Héctor; Salinas-Rodríguez, Aarón; Idrovo, Álvaro J; Búrquez, Alberto; Corral-Verdugo, Víctor

2015-08-01

Depression is a highly prevalent illness among adults, and it is the second most frequently reported mental disorder in urban settings in México. Exposure to natural environments and its components may improve the mental health of the population. To evaluate the association between biodiversity indicators and the prevalence of depressive symptoms among the adult population (20 to 65 years of age) in México. Information from the Encuesta Nacional de Salud y Nutrición 2006 (ENSANUT 2006) and the Compendio de Estadísticas Ambientales 2008 was analyzed. A biodiversity index was constructed based on the species richness and ecoregions in each state. A multilevel logistic regression model was built with random intercepts and a multiple logistic regression was generated with clustering by state. The factors associated with depressive symptoms were being female, self-perceived as indigenous, lower education level, not living with a partner, lack of steady paid work, having a chronic illness and drinking alcohol. The biodiversity index was found to be inversely associated with the prevalence of depressive symptoms when defined as a continuous variable, and the results from the regression were grouped by state (OR=0.71; 95% CI = 0.59-0.87). Although the design was cross-sectional, this study adds to the evidence of the potential benefits to mental health from contact with nature and its components.

Combining logistic regression with classification and regression tree to predict quality of care in a home health nursing data set.

PubMed

Guo, Huey-Ming; Shyu, Yea-Ing Lotus; Chang, Her-Kun

2006-01-01

In this article, the authors provide an overview of a research method to predict quality of care in home health nursing data set. The results of this study can be visualized through classification an regression tree (CART) graphs. The analysis was more effective, and the results were more informative since the home health nursing dataset was analyzed with a combination of the logistic regression and CART, these two techniques complete each other. And the results more informative that more patients' characters were related to quality of care in home care. The results contributed to home health nurse predict patient outcome in case management. Improved prediction is needed for interventions to be appropriately targeted for improved patient outcome and quality of care.

A general framework for the use of logistic regression models in meta-analysis.

PubMed

Simmonds, Mark C; Higgins, Julian Pt

2016-12-01

Where individual participant data are available for every randomised trial in a meta-analysis of dichotomous event outcomes, "one-stage" random-effects logistic regression models have been proposed as a way to analyse these data. Such models can also be used even when individual participant data are not available and we have only summary contingency table data. One benefit of this one-stage regression model over conventional meta-analysis methods is that it maximises the correct binomial likelihood for the data and so does not require the common assumption that effect estimates are normally distributed. A second benefit of using this model is that it may be applied, with only minor modification, in a range of meta-analytic scenarios, including meta-regression, network meta-analyses and meta-analyses of diagnostic test accuracy. This single model can potentially replace the variety of often complex methods used in these areas. This paper considers, with a range of meta-analysis examples, how random-effects logistic regression models may be used in a number of different types of meta-analyses. This one-stage approach is compared with widely used meta-analysis methods including Bayesian network meta-analysis and the bivariate and hierarchical summary receiver operating characteristic (ROC) models for meta-analyses of diagnostic test accuracy. © The Author(s) 2014.

Asthma exacerbation and proximity of residence to major roads: a population-based matched case-control study among the pediatric Medicaid population in Detroit, Michigan

PubMed Central

2011-01-01

Background The relationship between asthma and traffic-related pollutants has received considerable attention. The use of individual-level exposure measures, such as residence location or proximity to emission sources, may avoid ecological biases. Method This study focused on the pediatric Medicaid population in Detroit, MI, a high-risk population for asthma-related events. A population-based matched case-control analysis was used to investigate associations between acute asthma outcomes and proximity of residence to major roads, including freeways. Asthma cases were identified as all children who made at least one asthma claim, including inpatient and emergency department visits, during the three-year study period, 2004-06. Individually matched controls were randomly selected from the rest of the Medicaid population on the basis of non-respiratory related illness. We used conditional logistic regression with distance as both categorical and continuous variables, and examined non-linear relationships with distance using polynomial splines. The conditional logistic regression models were then extended by considering multiple asthma states (based on the frequency of acute asthma outcomes) using polychotomous conditional logistic regression. Results Asthma events were associated with proximity to primary roads with an odds ratio of 0.97 (95% CI: 0.94, 0.99) for a 1 km increase in distance using conditional logistic regression, implying that asthma events are less likely as the distance between the residence and a primary road increases. Similar relationships and effect sizes were found using polychotomous conditional logistic regression. Another plausible exposure metric, a reduced form response surface model that represents atmospheric dispersion of pollutants from roads, was not associated under that exposure model. Conclusions There is moderately strong evidence of elevated risk of asthma close to major roads based on the results obtained in this population-based matched case-control study. PMID:21513554

Cluster Analysis of Campylobacter jejuni Genotypes Isolated from Small and Medium-Sized Mammalian Wildlife and Bovine Livestock from Ontario Farms.

PubMed

Viswanathan, M; Pearl, D L; Taboada, E N; Parmley, E J; Mutschall, S K; Jardine, C M

2017-05-01

Using data collected from a cross-sectional study of 25 farms (eight beef, eight swine and nine dairy) in 2010, we assessed clustering of molecular subtypes of C. jejuni based on a Campylobacter-specific 40 gene comparative genomic fingerprinting assay (CGF40) subtypes, using unweighted pair-group method with arithmetic mean (UPGMA) analysis, and multiple correspondence analysis. Exact logistic regression was used to determine which genes differentiate wildlife and livestock subtypes in our study population. A total of 33 bovine livestock (17 beef and 16 dairy), 26 wildlife (20 raccoon (Procyon lotor), five skunk (Mephitis mephitis) and one mouse (Peromyscus spp.) C. jejuni isolates were subtyped using CGF40. Dendrogram analysis, based on UPGMA, showed distinct branches separating bovine livestock and mammalian wildlife isolates. Furthermore, two-dimensional multiple correspondence analysis was highly concordant with dendrogram analysis showing clear differentiation between livestock and wildlife CGF40 subtypes. Based on multilevel logistic regression models with a random intercept for farm of origin, we found that isolates in general, and raccoons more specifically, were significantly more likely to be part of the wildlife branch. Exact logistic regression conducted gene by gene revealed 15 genes that were predictive of whether an isolate was of wildlife or bovine livestock isolate origin. Both multiple correspondence analysis and exact logistic regression revealed that in most cases, the presence of a particular gene (13 of 15) was associated with an isolate being of livestock rather than wildlife origin. In conclusion, the evidence gained from dendrogram analysis, multiple correspondence analysis and exact logistic regression indicates that mammalian wildlife carry CGF40 subtypes of C. jejuni distinct from those carried by bovine livestock. Future studies focused on source attribution of C. jejuni in human infections will help determine whether wildlife transmit Campylobacter jejuni directly to humans. © 2016 Blackwell Verlag GmbH.

Pathologic response after preoperative therapy predicts prognosis of Chinese colorectal cancer patients with liver metastases.

PubMed

Wang, Yun; Yuan, Yun-Fei; Lin, Hao-Cheng; Li, Bin-Kui; Wang, Feng-Hua; Wang, Zhi-Qiang; Ding, Pei-Rong; Chen, Gong; Wu, Xiao-Jun; Lu, Zhen-Hai; Pan, Zhi-Zhong; Wan, De-Sen; Sun, Peng; Yan, Shu-Mei; Xu, Rui-Hua; Li, Yu-Hong

2017-10-02

Pathologic response is evaluated according to the extent of tumor regression and is used to estimate the efficacy of preoperative treatment. Several studies have reported the association between the pathologic response and clinical outcomes of colorectal cancer patients with liver metastases who underwent hepatectomy. However, to date, no data from Chinese patients have been reported. In this study, we aimed to evaluate the association between the pathologic response to pre-hepatectomy chemotherapy and prognosis in a cohort of Chinese patients. In this retrospective study, we analyzed the data of 380 liver metastases in 159 patients. The pathologic response was evaluated according to the tumor regression grade (TRG). The prognostic role of pathologic response in recurrence-free survival (RFS) and overall survival (OS) was assessed using Kaplan-Meier curves with the log-rank test and multivariate Cox models. Factors that had potential influence on pathologic response were also analyzed using multivariate logistic regression and Kruskal-Wallis/Mann-Whitney U tests. Patients whose tumors achieved pathologic response after preoperative chemotherapy had significant longer RFS and OS than patients whose tumor had no pathologic response to chemotherapy (median RFS: 9.9 vs. 6.5 months, P = 0.009; median OS: 40.7 vs. 28.1 months, P = 0.040). Multivariate logistic regression and Kruskal-Wallis/Mann-Whitney U tests showed that metastases with small diameter, metastases from the left-side primary tumors, and metastases from patients receiving long-duration chemotherapy had higher pathologic response rates than their control metastases (all P < 0.05). A decrease in the serum carcinoembryonic antigen (CEA) level after preoperative chemotherapy predicted an increased pathologic response rate (P < 0.05). Although the application of targeted therapy did not significantly influence TRG scores of all cases of metastases, the addition of cetuximab to chemotherapy resulted in a higher pathologic response rate when combined with irinotecan-based regimens rather than with oxaliplatin-based regimens. We found that the evaluation of pathologic response may predict the prognosis of Chinese colorectal cancer patients with liver metastases after preoperative chemotherapy. Small tumor diameter, long-duration chemotherapy, left primary tumor, and decreased serum CEA level after chemotherapy are associated with increased pathologic response rates.

Job stress models, depressive disorders and work performance of engineers in microelectronics industry.

PubMed

Chen, Sung-Wei; Wang, Po-Chuan; Hsin, Ping-Lung; Oates, Anthony; Sun, I-Wen; Liu, Shen-Ing

2011-01-01

Microelectronic engineers are considered valuable human capital contributing significantly toward economic development, but they may encounter stressful work conditions in the context of a globalized industry. The study aims at identifying risk factors of depressive disorders primarily based on job stress models, the Demand-Control-Support and Effort-Reward Imbalance models, and at evaluating whether depressive disorders impair work performance in microelectronics engineers in Taiwan. The case-control study was conducted among 678 microelectronics engineers, 452 controls and 226 cases with depressive disorders which were defined by a score 17 or more on the Beck Depression Inventory and a psychiatrist's diagnosis. The self-administered questionnaires included the Job Content Questionnaire, Effort-Reward Imbalance Questionnaire, demography, psychosocial factors, health behaviors and work performance. Hierarchical logistic regression was applied to identify risk factors of depressive disorders. Multivariate linear regressions were used to determine factors affecting work performance. By hierarchical logistic regression, risk factors of depressive disorders are high demands, low work social support, high effort/reward ratio and low frequency of physical exercise. Combining the two job stress models may have better predictive power for depressive disorders than adopting either model alone. Three multivariate linear regressions provide similar results indicating that depressive disorders are associated with impaired work performance in terms of absence, role limitation and social functioning limitation. The results may provide insight into the applicability of job stress models in a globalized high-tech industry considerably focused in non-Western countries, and the design of workplace preventive strategies for depressive disorders in Asian electronics engineering population.

Which Measurement of Blood Pressure Is More Associated With Albuminuria in Patients With Type 2 Diabetes: Central Blood Pressure or Peripheral Blood Pressure?

PubMed

Kitagawa, Noriyuki; Okada, Hiroshi; Tanaka, Muhei; Hashimoto, Yoshitaka; Kimura, Toshihiro; Nakano, Koji; Yamazaki, Masahiro; Hasegawa, Goji; Nakamura, Naoto; Fukui, Michiaki

2016-08-01

The aim of this study was to investigate whether central systolic blood pressure (SBP) was associated with albuminuria, defined as urinary albumin excretion (UAE) ≥30 mg/g creatinine, and, if so, whether the relationship of central SBP with albuminuria was stronger than that of peripheral SBP in patients with type 2 diabetes. The authors performed a cross-sectional study in 294 outpatients with type 2 diabetes. The relationship between peripheral SBP or central SBP and UAE using regression analysis was evaluated, and the odds ratios of peripheral SBP or central SBP were calculated to identify albuminuria using logistic regression model. Moreover, the area under the receiver operating characteristic curve (AUC) of central SBP was compared with that of peripheral SBP to identify albuminuria. Multiple regression analysis demonstrated that peripheral SBP (β=0.255, P<.0001) or central SBP (r=0.227, P<.0001) was associated with UAE. Multiple logistic regression analysis demonstrated that peripheral SBP (odds ratio, 1.029; 95% confidence interval, 1.016-1.043) or central SBP (odds ratio, 1.022; 95% confidence interval, 1.011-1.034) was associated with an increased odds of albuminuria. In addition, AUC of peripheral SBP was significantly greater than that of central SBP to identify albuminuria (P=0.035). Peripheral SBP is superior to central SBP in identifying albuminuria, although both peripheral and central SBP are associated with UAE in patients with type 2 diabetes. © 2016 Wiley Periodicals, Inc.

Modeling the safety impacts of driving hours and rest breaks on truck drivers considering time-dependent covariates.

PubMed

Chen, Chen; Xie, Yuanchang

2014-12-01

Driving hours and rest breaks are closely related to driver fatigue, which is a major contributor to truck crashes. This study investigates the effects of driving hours and rest breaks on commercial truck driver safety. A discrete-time logistic regression model is used to evaluate the crash odds ratios of driving hours and rest breaks. Driving time is divided into 11 one hour intervals. These intervals and rest breaks are modeled as dummy variables. In addition, a Cox proportional hazards regression model with time-dependent covariates is used to assess the transient effects of rest breaks, which consists of a fixed effect and a variable effect. Data collected from two national truckload carriers in 2009 and 2010 are used. The discrete-time logistic regression result indicates that only the crash odds ratio of the 11th driving hour is statistically significant. Taking one, two, and three rest breaks can reduce drivers' crash odds by 68%, 83%, and 85%, respectively, compared to drivers who did not take any rest breaks. The Cox regression result shows clear transient effects for rest breaks. It also suggests that drivers may need some time to adjust themselves to normal driving tasks after a rest break. Overall, the third rest break's safety benefit is very limited based on the results of both models. The findings of this research can help policy makers better understand the impact of driving time and rest breaks and develop more effective rules to improve commercial truck safety. Copyright © 2014 National Safety Council and Elsevier Ltd. All rights reserved.

Fall-related self-efficacy, not balance and mobility performance, is related to accidental falls in chronic stroke survivors with low bone mineral density.

PubMed

Pang, M Y C; Eng, J J

2008-07-01

Chronic stroke survivors with low hip bone density are particularly prone to fractures. This study shows that fear of falling is independently associated with falls in this population. Thus, fear of falling should not be overlooked in the prevention of fragility fractures in these patients. Chronic stroke survivors with low bone mineral density (BMD) are particularly prone to fragility fractures. The purpose of this study was to identify the determinants of balance, mobility and falls in this sub-group of stroke patients. Thirty-nine chronic stroke survivors with low hip BMD (T-score <-1.0) were studied. Each subject was evaluated for the following: balance, mobility, leg muscle strength, spasticity, and fall-related self-efficacy. Any falls in the past 12 months were also recorded. Multiple regression analysis was used to identify the determinants of balance and mobility performance, whereas logistic regression was used to identify the determinants of falls. Multiple regression analysis revealed that after adjusting for basic demographics, fall-related self-efficacy remained independently associated with balance/mobility performance (R2 = 0.494, P < 0.001). Logistic regression showed that fall-related self-efficacy, but not balance and mobility performance, was a significant determinant of falls (odds ratio: 0.18, P = 0.04). Fall-related self-efficacy, but not mobility and balance performance, was the most important determinant of accidental falls. This psychological factor should not be overlooked in the prevention of fragility fractures among chronic stroke survivors with low hip BMD.

Comparison of 21-Gauge and 22-Gauge Aspiration Needle in Endobronchial Ultrasound-Guided Transbronchial Needle Aspiration

PubMed Central

Akulian, Jason; Lechtzin, Noah; Yasin, Faiza; Kamdar, Biren; Ernst, Armin; Ost, David E.; Ray, Cynthia; Greenhill, Sarah R.; Jimenez, Carlos A.; Filner, Joshua; Feller-Kopman, David

2013-01-01

Background: Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a minimally invasive procedure originally performed using a 22-gauge (22G) needle. A recently introduced 21-gauge (21G) needle may improve the diagnostic yield and sample adequacy of EBUS-TBNA, but prior smaller studies have shown conflicting results. To our knowledge, this is the largest study undertaken to date to determine whether the 21G needle adds diagnostic benefit. Methods: We retrospectively evaluated the results of 1,299 patients from the American College of Chest Physicians Quality Improvement Registry, Education, and Evaluation (AQuIRE) Diagnostic Registry who underwent EBUS-TBNA between February 2009 and September 2010 at six centers throughout the United States. Data collection included patient demographics, sample adequacy, and diagnostic yield. Analysis consisted of univariate and multivariate hierarchical logistic regression comparing diagnostic yield and sample adequacy of EBUS-TBNA specimens by needle gauge. Results: A total of 1,235 patients met inclusion criteria. Sample adequacy was obtained in 94.9% of the 22G needle group and in 94.6% of the 21G needle group (P = .81). A diagnosis was made in 51.4% of the 22G and 51.3% of the 21G groups (P = .98). Multivariate hierarchical logistic regression showed no statistical difference in sample adequacy or diagnostic yield between the two groups. The presence of rapid onsite cytologic evaluation was associated with significantly fewer needle passes per procedure when using the 21G needle (P < .001). Conclusions: There is no difference in specimen adequacy or diagnostic yield between the 21G and 22G needle groups. EBUS-TBNA in conjunction with rapid onsite cytologic evaluation and a 21G needle is associated with fewer needle passes compared with a 22G needle. PMID:23632441

Sex differences regarding the impact of physical activity on left ventricular systolic function in elderly patients with an acute coronary event.

PubMed

Aggelopoulos, Panagiotis; Chrysohoou, Christina; Pitsavos, Christos; Panagiotakos, Demosthenes B; Vaina, Sophia; Brili, Stella; Lazaros, George; Vavouranakis, Manolis; Stefanadis, Christodoulos

2014-01-01

Regular physical activity has been associated with less severity of an acute coronary syndrome (ACS), lower in-hospital mortality rates, and an improved short term prognosis. This study evaluated the relationship between physical activity status and the development of left ventricular systolic dysfunction (LVSD) according to inflammation and sex in elderly patients who had had an ACS. We analyzed prospectively collected data from 355 male (age 74 ± 6 years) and 137 female (76 ± 6 years) patients who were hospitalized with an ACS. LVSD was evaluated by echocardiography on the 5th day of hospitalization and physical activity status was assessed by a self-reported questionnaire. Inflammatory response was evaluated by measuring C-reactive protein levels. Logistic regression models were applied to evaluate the effect of physical activity status on the development of LVSD and inflammatory response at entry. Physical inactivity had a higher prevalence in women who developed LVSD than in the female patients with preserved systolic function (46% vs. 20%, p=0.02). There was a significant positive association between physical activity levels and ejection fraction in women (p=0.06), but not in men (p=0.30). Multiadjusted logistic regression showed that women who were physically active had 76% lower odds (95%CI: 1-94%) of developing LVSD compared to their sedentary counterparts. Furthermore, physical activity was inversely associated with C-reactive protein levels in both sexes (p=0.08). Long-term involvement in a physically active lifestyle seems to confer further cardio-protection by reducing the inflammatory response and preserving left ventricular systolic function in elderly female, but not male patients with an ACS.

An Ecological Study of the Association between Air Pollution and Hepatocellular Carcinoma Incidence in Texas.

PubMed

Cicalese, Luca; Raun, Loren; Shirafkan, Ali; Campos, Laura; Zorzi, Daria; Montalbano, Mauro; Rhoads, Colin; Gazis, Valia; Ensor, Katherine; Rastellini, Cristiana

2017-11-01

Primary liver cancer is a significant cause of cancer-related death in both the United States and the world at large. Hepatocellular carcinoma comprises 90% of these primary liver cancers and has numerous known etiologies. Evaluation of these identified etiologies and other traditional risk factors cannot explain the high incidence rates of hepatocellular carcinoma in Texas. Texas is home to the second largest petrochemical industry and agricultural industry in the nation; industrial activity and exposure to pathogenic chemicals have never been assessed as potential links to the state's increased incidence rate of hepatocellular carcinoma. The association between the county-level concentrations of 4 air pollutants known to be linked to liver cancer, vinyl chloride, arsenic, benzene, and 1,3-butadiene, and hepatocellular carcinoma rates was evaluated using nonparametric generalized additive logistic regression and gamma regression models. Hepatocellular carcinoma incidence rates for 2000-2013 were evaluated in comparison to 1996 and 1999 pollution concentrations and hepatocellular carcinoma rates for the subset of 2006-2013 were evaluated in comparison to 2002 and 2005 pollution concentrations, respectively. The analysis indicates that the relationship between the incidence of liver cancer and air pollution and risk factors is nonlinear. There is a consistent significant positive association between the incidence of liver cancer and hepatitis C prevalence rates (gamma all years, p < 0.05) and vinyl chloride concentrations (logistic 2002 and 2005, p < 0.0001; gamma 2002 and 2005, p < 0.05). This study suggests that vinyl chloride is a significant contributor to the incidence of liver cancer in Texas. The relationship is notably nonlinear. Further, the study supports the association between incidence of liver cancer and prevalence of hepatitis B.

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

The logistic model for predicting the non-gonoactive Aedes aegypti females.

PubMed

Reyes-Villanueva, Filiberto; Rodríguez-Pérez, Mario A

2004-01-01

To estimate, using logistic regression, the likelihood of occurrence of a non-gonoactive Aedes aegypti female, previously fed human blood, with relation to body size and collection method. This study was conducted in Monterrey, Mexico, between 1994 and 1996. Ten samplings of 60 mosquitoes of Ae. aegypti females were carried out in three dengue endemic areas: six of biting females, two of emerging mosquitoes, and two of indoor resting females. Gravid females, as well as those with blood in the gut were removed. Mosquitoes were taken to the laboratory and engorged on human blood. After 48 hours, ovaries were dissected to register whether they were gonoactive or non-gonoactive. Wing-length in mm was an indicator for body size. The logistic regression model was used to assess the likelihood of non-gonoactivity, as a binary variable, in relation to wing-length and collection method. Of the 600 females, 164 (27%) remained non-gonoactive, with a wing-length range of 1.9-3.2 mm, almost equal to that of all females (1.8-3.3 mm). The logistic regression model showed a significant likelihood of a female remaining non-gonoactive (Y=1). The collection method did not influence the binary response, but there was an inverse relationship between non-gonoactivity and wing-length. Dengue vector populations from Monterrey, Mexico display a wide-range body size. Logistic regression was a useful tool to estimate the likelihood for an engorged female to remain non-gonoactive. The necessity for a second blood meal is present in any female, but small mosquitoes are more likely to bite again within a 2-day interval, in order to attain egg maturation. The English version of this paper is available too at: http://www.insp.mx/salud/index.html.

Modeling and managing risk early in software development

NASA Technical Reports Server (NTRS)

Briand, Lionel C.; Thomas, William M.; Hetmanski, Christopher J.

1993-01-01

In order to improve the quality of the software development process, we need to be able to build empirical multivariate models based on data collectable early in the software process. These models need to be both useful for prediction and easy to interpret, so that remedial actions may be taken in order to control and optimize the development process. We present an automated modeling technique which can be used as an alternative to regression techniques. We show how it can be used to facilitate the identification and aid the interpretation of the significant trends which characterize 'high risk' components in several Ada systems. Finally, we evaluate the effectiveness of our technique based on a comparison with logistic regression based models.

A nomogram based on mammary ductoscopic indicators for evaluating the risk of breast cancer in intraductal neoplasms with nipple discharge.

PubMed

Lian, Zhen-Qiang; Wang, Qi; Zhang, An-Qin; Zhang, Jiang-Yu; Han, Xiao-Rong; Yu, Hai-Yun; Xie, Si-Mei

2015-04-01

Mammary ductoscopy (MD) is commonly used to detect intraductal lesions associated with nipple discharge. This study investigated the relationships between ductoscopic image-based indicators and breast cancer risk, and developed a nomogram for evaluating breast cancer risk in intraductal neoplasms with nipple discharge. A total of 879 consecutive inpatients (916 breasts) with nipple discharge who underwent selective duct excision for intraductal neoplasms detected by MD from June 2008 to April 2014 were analyzed retrospectively. A nomogram was developed using a multivariate logistic regression model based on data from a training set (687 cases) and validated in an independent validation set (229 cases). A Youden-derived cut-off value was assigned to the nomogram for the diagnosis of breast cancer. Color of discharge, location, appearance, and surface of neoplasm, and morphology of ductal wall were independent predictors for breast cancer in multivariate logistic regression analysis. A nomogram based on these predictors performed well. The P value of the Hosmer-Lemeshow test for the prediction model was 0.36. Area under the curve values of 0.812 (95 % confidence interval (CI) 0.763-0.860) and 0.738 (95 % CI 0.635-0.841) was obtained in the training and validation sets, respectively. The accuracies of the nomogram for breast cancer diagnosis were 71.2 % in the training set and 75.5 % in the validation set. We developed a nomogram for evaluating breast cancer risk in intraductal neoplasms with nipple discharge based on MD image findings. This model may aid individual risk assessment and guide treatment in clinical practice.

Prevalence of cognitive and functional impairment in a community sample in Ribeirão Preto, Brazil.

PubMed

Lopes, Marcos A; Hototian, Sergio R; Bustamante, Sonia E Z; Azevedo, Dionísio; Tatsch, Mariana; Bazzarella, Mário C; Litvoc, Júlio; Bottino, Cássio M C

2007-08-01

This study aimed at estimating the prevalence of cognitive and functional impairment (CFI) in a community sample in Ribeirão Preto, Brazil, evaluating its distribution in relation to various socio-demographic and clinical factors. The population was a representative sample aged 60 and older, from three different socio-economic classes. Cluster sampling was applied. Instruments used to select CFI (a syndromic category that does not exclude dementia): 'Mini Mental State Examination' (MMSE), 'Fuld Object Memory Evaluation' (FOME), 'Informant Questionnaire on Cognitive Decline in the Elderly' (IQCODE), 'Bayer Activities of Daily Living Scale' (B-ADL) and clinical interviews. The data obtained were submitted to bivariate and logistic regression analysis. A sample of 1.145 elderly persons was evaluated, with a mean age of 70.9 years (60-100; DP: 7.7); 63.4% were female, and 52.8% had up to 4 years of schooling. CFI prevalence was 18.9% (n = 217). Following logistic regression analysis, higher age, low education, stroke, epilepsy and depression were associated with CFI. Female sex, widowhood, low social class and head trauma were associated with CFI only on bivariate analysis. CFI prevalence results were similar to those found by studies in Brazil, Puerto Rico and Malaysia. Cognitive and functional impairment is a rather heterogeneous condition which may be associated with various clinical conditions found in the elderly population. Due to its high prevalence and association with higher mortality and disability rates, this clinical syndrome should receive more attention on public health intervention planning.

Can You Ride a Bicycle? The Ability to Ride a Bicycle Prevents Reduced Social Function in Older Adults With Mobility Limitation

PubMed Central

Sakurai, Ryota; Kawai, Hisashi; Yoshida, Hideyo; Fukaya, Taro; Suzuki, Hiroyuki; Kim, Hunkyung; Hirano, Hirohiko; Ihara, Kazushige; Obuchi, Shuichi; Fujiwara, Yoshinori

2016-01-01

Background The health benefits of bicycling in older adults with mobility limitation (ML) are unclear. We investigated ML and functional capacity of older cyclists by evaluating their instrumental activities of daily living (IADL), intellectual activity, and social function. Methods On the basis of interviews, 614 community-dwelling older adults (after excluding 63 participants who never cycled) were classified as cyclists with ML, cyclists without ML, non-cyclists with ML (who ceased bicycling due to physical difficulties), or non-cyclists without ML (who ceased bicycling for other reasons). A cyclist was defined as a person who cycled at least a few times per month, and ML was defined as difficulty walking 1 km or climbing stairs without using a handrail. Functional capacity and physical ability were evaluated by standardized tests. Results Regular cycling was documented in 399 participants, and 74 of them (18.5%) had ML; among non-cyclists, 49 had ML, and 166 did not. Logistic regression analysis for evaluating the relationship between bicycling and functional capacity revealed that non-cyclists with ML were more likely to have reduced IADL and social function compared to cyclists with ML. However, logistic regression analysis also revealed that the risk of bicycle-related falls was significantly associated with ML among older cyclists. Conclusions The ability and opportunity to bicycle may prevent reduced IADL and social function in older adults with ML, although older adults with ML have a higher risk of falls during bicycling. It is important to develop a safe environment for bicycling for older adults. PMID:26902165

Ultrasonographic Evaluation of Cervical Lymph Nodes in Thyroid Cancer.

PubMed

Machado, Maria Regina Marrocos; Tavares, Marcos Roberto; Buchpiguel, Carlos Alberto; Chammas, Maria Cristina

2017-02-01

Objective To determine what ultrasonographic features can identify metastatic cervical lymph nodes, both preoperatively and in recurrences after complete thyroidectomy. Study Design Prospective. Setting Outpatient clinic, Department of Head and Neck Surgery, School of Medicine, University of São Paulo, Brazil. Subjects and Methods A total of 1976 lymph nodes were evaluated in 118 patients submitted to total thyroidectomy with or without cervical lymph node dissection. All the patients were examined by cervical ultrasonography, preoperatively and/or postoperatively. The following factors were assessed: number, size, shape, margins, presence of fatty hilum, cortex, echotexture, echogenicity, presence of microcalcification, presence of necrosis, and type of vascularity. The specificity, sensitivity, positive predictive value, and negative predictive value of each variable were calculated. Univariate and multivariate logistic regression analyses were conducted. A receiver operator characteristic (ROC) curve was plotted to determine the best cutoff value for the number of variables to discriminate malignant lymph nodes. Results Significant differences were found between metastatic and benign lymph nodes with regard to all of the variables evaluated ( P < .05). Logistic regression analysis revealed that size and echogenicity were the best combination of altered variables (odds ratio, 40.080 and 7.288, respectively) in discriminating malignancy. The ROC curve analysis showed that 4 was the best cutoff value for the number of altered variables to discriminate malignant lymph nodes, with a combined specificity of 85.7%, sensitivity of 96.4%, and efficiency of 91.0%. Conclusion Greater diagnostic accuracy was achieved by associating the ultrasonographic variables assessed rather than by considering them individually.

Ultrasonographic Diagnosis of Biliary Atresia Based on a Decision-Making Tree Model.

PubMed

Lee, So Mi; Cheon, Jung-Eun; Choi, Young Hun; Kim, Woo Sun; Cho, Hyun-Hae; Cho, Hyun-Hye; Kim, In-One; You, Sun Kyoung

2015-01-01

To assess the diagnostic value of various ultrasound (US) findings and to make a decision-tree model for US diagnosis of biliary atresia (BA). From March 2008 to January 2014, the following US findings were retrospectively evaluated in 100 infants with cholestatic jaundice (BA, n = 46; non-BA, n = 54): length and morphology of the gallbladder, triangular cord thickness, hepatic artery and portal vein diameters, and visualization of the common bile duct. Logistic regression analyses were performed to determine the features that would be useful in predicting BA. Conditional inference tree analysis was used to generate a decision-making tree for classifying patients into the BA or non-BA groups. Multivariate logistic regression analysis showed that abnormal gallbladder morphology and greater triangular cord thickness were significant predictors of BA (p = 0.003 and 0.001; adjusted odds ratio: 345.6 and 65.6, respectively). In the decision-making tree using conditional inference tree analysis, gallbladder morphology and triangular cord thickness (optimal cutoff value of triangular cord thickness, 3.4 mm) were also selected as significant discriminators for differential diagnosis of BA, and gallbladder morphology was the first discriminator. The diagnostic performance of the decision-making tree was excellent, with sensitivity of 100% (46/46), specificity of 94.4% (51/54), and overall accuracy of 97% (97/100). Abnormal gallbladder morphology and greater triangular cord thickness (> 3.4 mm) were the most useful predictors of BA on US. We suggest that the gallbladder morphology should be evaluated first and that triangular cord thickness should be evaluated subsequently in cases with normal gallbladder morphology.

Potential serum biomarkers from a metabolomics study of autism

PubMed Central

Wang, Han; Liang, Shuang; Wang, Maoqing; Gao, Jingquan; Sun, Caihong; Wang, Jia; Xia, Wei; Wu, Shiying; Sumner, Susan J.; Zhang, Fengyu; Sun, Changhao; Wu, Lijie

2016-01-01

Background Early detection and diagnosis are very important for autism. Current diagnosis of autism relies mainly on some observational questionnaires and interview tools that may involve a great variability. We performed a metabolomics analysis of serum to identify potential biomarkers for the early diagnosis and clinical evaluation of autism. Methods We analyzed a discovery cohort of patients with autism and participants without autism in the Chinese Han population using ultra-performance liquid chromatography quadrupole time-of-flight tandem mass spectrometry (UPLC/Q-TOF MS/MS) to detect metabolic changes in serum associated with autism. The potential metabolite candidates for biomarkers were individually validated in an additional independent cohort of cases and controls. We built a multiple logistic regression model to evaluate the validated biomarkers. Results We included 73 patients and 63 controls in the discovery cohort and 100 cases and 100 controls in the validation cohort. Metabolomic analysis of serum in the discovery stage identified 17 metabolites, 11 of which were validated in an independent cohort. A multiple logistic regression model built on the 11 validated metabolites fit well in both cohorts. The model consistently showed that autism was associated with 2 particular metabolites: sphingosine 1-phosphate and docosahexaenoic acid. Limitations While autism is diagnosed predominantly in boys, we were unable to perform the analysis by sex owing to difficulty recruiting enough female patients. Other limitations include the need to perform test–retest assessment within the same individual and the relatively small sample size. Conclusion Two metabolites have potential as biomarkers for the clinical diagnosis and evaluation of autism. PMID:26395811

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…

A decision support model for investment on P2P lending platform.

PubMed

Zeng, Xiangxiang; Liu, Li; Leung, Stephen; Du, Jiangze; Wang, Xun; Li, Tao

2017-01-01

Peer-to-peer (P2P) lending, as a novel economic lending model, has triggered new challenges on making effective investment decisions. In a P2P lending platform, one lender can invest N loans and a loan may be accepted by M investors, thus forming a bipartite graph. Basing on the bipartite graph model, we built an iteration computation model to evaluate the unknown loans. To validate the proposed model, we perform extensive experiments on real-world data from the largest American P2P lending marketplace-Prosper. By comparing our experimental results with those obtained by Bayes and Logistic Regression, we show that our computation model can help borrowers select good loans and help lenders make good investment decisions. Experimental results also show that the Logistic classification model is a good complement to our iterative computation model, which motivates us to integrate the two classification models. The experimental results of the hybrid classification model demonstrate that the logistic classification model and our iteration computation model are complementary to each other. We conclude that the hybrid model (i.e., the integration of iterative computation model and Logistic classification model) is more efficient and stable than the individual model alone.

A decision support model for investment on P2P lending platform

PubMed Central

Liu, Li; Leung, Stephen; Du, Jiangze; Wang, Xun; Li, Tao

2017-01-01

Peer-to-peer (P2P) lending, as a novel economic lending model, has triggered new challenges on making effective investment decisions. In a P2P lending platform, one lender can invest N loans and a loan may be accepted by M investors, thus forming a bipartite graph. Basing on the bipartite graph model, we built an iteration computation model to evaluate the unknown loans. To validate the proposed model, we perform extensive experiments on real-world data from the largest American P2P lending marketplace—Prosper. By comparing our experimental results with those obtained by Bayes and Logistic Regression, we show that our computation model can help borrowers select good loans and help lenders make good investment decisions. Experimental results also show that the Logistic classification model is a good complement to our iterative computation model, which motivates us to integrate the two classification models. The experimental results of the hybrid classification model demonstrate that the logistic classification model and our iteration computation model are complementary to each other. We conclude that the hybrid model (i.e., the integration of iterative computation model and Logistic classification model) is more efficient and stable than the individual model alone. PMID:28877234

[Econometric and ethical validation of regression logistics. Reducing of the number of patients in the evaluation of mortality].

PubMed

Castiel, D; Herve, C

1992-01-01

In general, a large number of patients is needed to conclude whether the results of a therapeutic strategy are significant or not. One can lower this number with a logit. The method has been proposed in an article published recently (Cost-utility analysis of early thrombolytic therapy, Pharmaco Economics, 1992). The present article is an essay aimed at validating the method, both from the econometric and ethical points of view.

Fusion of multiscale wavelet-based fractal analysis on retina image for stroke prediction.

PubMed

Che Azemin, M Z; Kumar, Dinesh K; Wong, T Y; Wang, J J; Kawasaki, R; Mitchell, P; Arjunan, Sridhar P

2010-01-01

In this paper, we present a novel method of analyzing retinal vasculature using Fourier Fractal Dimension to extract the complexity of the retinal vasculature enhanced at different wavelet scales. Logistic regression was used as a fusion method to model the classifier for 5-year stroke prediction. The efficacy of this technique has been tested using standard pattern recognition performance evaluation, Receivers Operating Characteristics (ROC) analysis and medical prediction statistics, odds ratio. Stroke prediction model was developed using the proposed system.

Parenting styles and alcohol consumption among Brazilian adolescents.

PubMed

Paiva, Fernando Santana; Bastos, Ronaldo Rocha; Ronzani, Telmo Mota

2012-10-01

This study evaluates the correlation between alcohol consumption in adolescence and parenting styles of socialization among Brazilian adolescents. The sample was composed of 273 adolescents, 58% whom were males. Instruments were: 1) Sociodemographic Questionnaire; 2) Demand and Responsiveness Scales; 3) Drug Use Screening Inventory (DUSI). Study analyses employed multiple correspondence analysis and logistic regression. Maternal, but not paternal, authoritative and authoritarian parenting styles were directly related to adolescent alcohol intake. The style that mothers use to interact with their children may influence uptake of high-risk behaviors.

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.

Regression Analysis of Optical Coherence Tomography Disc Variables for Glaucoma Diagnosis.

PubMed

Richter, Grace M; Zhang, Xinbo; Tan, Ou; Francis, Brian A; Chopra, Vikas; Greenfield, David S; Varma, Rohit; Schuman, Joel S; Huang, David

2016-08-01

To report diagnostic accuracy of optical coherence tomography (OCT) disc variables using both time-domain (TD) and Fourier-domain (FD) OCT, and to improve the use of OCT disc variable measurements for glaucoma diagnosis through regression analyses that adjust for optic disc size and axial length-based magnification error. Observational, cross-sectional. In total, 180 normal eyes of 112 participants and 180 eyes of 138 participants with perimetric glaucoma from the Advanced Imaging for Glaucoma Study. Diagnostic variables evaluated from TD-OCT and FD-OCT were: disc area, rim area, rim volume, optic nerve head volume, vertical cup-to-disc ratio (CDR), and horizontal CDR. These were compared with overall retinal nerve fiber layer thickness and ganglion cell complex. Regression analyses were performed that corrected for optic disc size and axial length. Area-under-receiver-operating curves (AUROC) were used to assess diagnostic accuracy before and after the adjustments. An index based on multiple logistic regression that combined optic disc variables with axial length was also explored with the aim of improving diagnostic accuracy of disc variables. Comparison of diagnostic accuracy of disc variables, as measured by AUROC. The unadjusted disc variables with the highest diagnostic accuracies were: rim volume for TD-OCT (AUROC=0.864) and vertical CDR (AUROC=0.874) for FD-OCT. Magnification correction significantly worsened diagnostic accuracy for rim variables, and while optic disc size adjustments partially restored diagnostic accuracy, the adjusted AUROCs were still lower. Axial length adjustments to disc variables in the form of multiple logistic regression indices led to a slight but insignificant improvement in diagnostic accuracy. Our various regression approaches were not able to significantly improve disc-based OCT glaucoma diagnosis. However, disc rim area and vertical CDR had very high diagnostic accuracy, and these disc variables can serve to complement additional OCT measurements for diagnosis of glaucoma.

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.

Computational tools for exact conditional logistic regression.

PubMed

Corcoran, C; Mehta, C; Patel, N; Senchaudhuri, P

Logistic regression analyses are often challenged by the inability of unconditional likelihood-based approximations to yield consistent, valid estimates and p-values for model parameters. This can be due to sparseness or separability in the data. Conditional logistic regression, though useful in such situations, can also be computationally unfeasible when the sample size or number of explanatory covariates is large. We review recent developments that allow efficient approximate conditional inference, including Monte Carlo sampling and saddlepoint approximations. We demonstrate through real examples that these methods enable the analysis of significantly larger and more complex data sets. We find in this investigation that for these moderately large data sets Monte Carlo seems a better alternative, as it provides unbiased estimates of the exact results and can be executed in less CPU time than can the single saddlepoint approximation. Moreover, the double saddlepoint approximation, while computationally the easiest to obtain, offers little practical advantage. It produces unreliable results and cannot be computed when a maximum likelihood solution does not exist. Copyright 2001 John Wiley & Sons, Ltd.