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.

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.

[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.

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.

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.

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.

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...

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.

Large unbalanced credit scoring using Lasso-logistic regression ensemble.

PubMed

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data.

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.

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.

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.

Modeling Governance KB with CATPCA to Overcome Multicollinearity in the Logistic Regression

NASA Astrophysics Data System (ADS)

Khikmah, L.; Wijayanto, H.; Syafitri, U. D.

2017-04-01

The problem often encounters in logistic regression modeling are multicollinearity problems. Data that have multicollinearity between explanatory variables with the result in the estimation of parameters to be bias. Besides, the multicollinearity will result in error in the classification. In general, to overcome multicollinearity in regression used stepwise regression. They are also another method to overcome multicollinearity which involves all variable for prediction. That is Principal Component Analysis (PCA). However, classical PCA in only for numeric data. Its data are categorical, one method to solve the problems is Categorical Principal Component Analysis (CATPCA). Data were used in this research were a part of data Demographic and Population Survey Indonesia (IDHS) 2012. This research focuses on the characteristic of women of using the contraceptive methods. Classification results evaluated using Area Under Curve (AUC) values. The higher the AUC value, the better. Based on AUC values, the classification of the contraceptive method using stepwise method (58.66%) is better than the logistic regression model (57.39%) and CATPCA (57.39%). Evaluation of the results of logistic regression using sensitivity, shows the opposite where CATPCA method (99.79%) is better than logistic regression method (92.43%) and stepwise (92.05%). Therefore in this study focuses on major class classification (using a contraceptive method), then the selected model is CATPCA because it can raise the level of the major class model accuracy.

Multinomial logistic regression in workers' health

NASA Astrophysics Data System (ADS)

Grilo, Luís M.; Grilo, Helena L.; Gonçalves, Sónia P.; Junça, Ana

2017-11-01

In European countries, namely in Portugal, it is common to hear some people mentioning that they are exposed to excessive and continuous psychosocial stressors at work. This is increasing in diverse activity sectors, such as, the Services sector. A representative sample was collected from a Portuguese Services' organization, by applying a survey (internationally validated), which variables were measured in five ordered categories in Likert-type scale. A multinomial logistic regression model is used to estimate the probability of each category of the dependent variable general health perception where, among other independent variables, burnout appear as statistically significant.

Large Unbalanced Credit Scoring Using Lasso-Logistic Regression Ensemble

PubMed Central

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data. PMID:25706988

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.

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

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.

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…

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…

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…

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

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

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

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

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

DOE PAGES

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

2017-09-22

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

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…

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.

A Bayesian goodness of fit test and semiparametric generalization of logistic regression with measurement data.

PubMed

Schörgendorfer, Angela; Branscum, Adam J; Hanson, Timothy E

2013-06-01

Logistic regression is a popular tool for risk analysis in medical and population health science. With continuous response data, it is common to create a dichotomous outcome for logistic regression analysis by specifying a threshold for positivity. Fitting a linear regression to the nondichotomized response variable assuming a logistic sampling model for the data has been empirically shown to yield more efficient estimates of odds ratios than ordinary logistic regression of the dichotomized endpoint. We illustrate that risk inference is not robust to departures from the parametric logistic distribution. Moreover, the model assumption of proportional odds is generally not satisfied when the condition of a logistic distribution for the data is violated, leading to biased inference from a parametric logistic analysis. We develop novel Bayesian semiparametric methodology for testing goodness of fit of parametric logistic regression with continuous measurement data. The testing procedures hold for any cutoff threshold and our approach simultaneously provides the ability to perform semiparametric risk estimation. Bayes factors are calculated using the Savage-Dickey ratio for testing the null hypothesis of logistic regression versus a semiparametric generalization. We propose a fully Bayesian and a computationally efficient empirical Bayesian approach to testing, and we present methods for semiparametric estimation of risks, relative risks, and odds ratios when parametric logistic regression fails. Theoretical results establish the consistency of the empirical Bayes test. Results from simulated data show that the proposed approach provides accurate inference irrespective of whether parametric assumptions hold or not. Evaluation of risk factors for obesity shows that different inferences are derived from an analysis of a real data set when deviations from a logistic distribution are permissible in a flexible semiparametric framework. © 2013, The International Biometric Society.

Dental health services utilization and associated factors in children 6 to 12 years old in a low-income country.

PubMed

Medina-Solis, Carlo Eduardo; Maupomé, Gerardo; del Socorro, Herrera Miriam; Pérez-Núñez, Ricardo; Avila-Burgos, Leticia; Lamadrid-Figueroa, Hector

2008-01-01

To determine the factors associated with the dental health services utilization among children ages 6 to 12 in León, Nicaragua. A cross-sectional study was carried out in 1,400 schoolchildren. Using a questionnaire, we determined information related to utilization and independent variables in the previous year. Oral health needs were established by means of a dental examination. To identify the independent variables associated with dental health services utilization, two types of multivariate regression models were used, according to the measurement scale of the outcome variable: a) frequency of utilization as (0) none, (1) one, and (2) two or more, analyzed with the ordered logistic regression and b) the type of service utilized as (0) none, (1) preventive services, (2) curative services, and (3) both services, analyzed with the multinomial logistic regression. The proportion of children who received at least one dental service in the 12 months prior to the study was 27.7 percent. The variables associated with utilization in the two models were older age, female sex, more frequent toothbrushing, positive attitude of the mother toward the child's oral health, higher socioeconomic level, and higher oral health needs. Various predisposing, enabling, and oral health needs variables were associated with higher dental health services utilization. As in prior reports elsewhere, these results from Nicaragua confirmed that utilization inequalities exist between socioeconomic groups. The multinomial logistic regression model evidenced the association of different variables depending on the type of service used.

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.

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.

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...

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…

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.

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.

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.

Modelling long-term fire occurrence factors in Spain by accounting for local variations with geographically weighted regression

NASA Astrophysics Data System (ADS)

Martínez-Fernández, J.; Chuvieco, E.; Koutsias, N.

2013-02-01

Humans are responsible for most forest fires in Europe, but anthropogenic factors behind these events are still poorly understood. We tried to identify the driving factors of human-caused fire occurrence in Spain by applying two different statistical approaches. Firstly, assuming stationary processes for the whole country, we created models based on multiple linear regression and binary logistic regression to find factors associated with fire density and fire presence, respectively. Secondly, we used geographically weighted regression (GWR) to better understand and explore the local and regional variations of those factors behind human-caused fire occurrence. The number of human-caused fires occurring within a 25-yr period (1983-2007) was computed for each of the 7638 Spanish mainland municipalities, creating a binary variable (fire/no fire) to develop logistic models, and a continuous variable (fire density) to build standard linear regression models. A total of 383 657 fires were registered in the study dataset. The binary logistic model, which estimates the probability of having/not having a fire, successfully classified 76.4% of the total observations, while the ordinary least squares (OLS) regression model explained 53% of the variation of the fire density patterns (adjusted R2 = 0.53). Both approaches confirmed, in addition to forest and climatic variables, the importance of variables related with agrarian activities, land abandonment, rural population exodus and developmental processes as underlying factors of fire occurrence. For the GWR approach, the explanatory power of the GW linear model for fire density using an adaptive bandwidth increased from 53% to 67%, while for the GW logistic model the correctly classified observations improved only slightly, from 76.4% to 78.4%, but significantly according to the corrected Akaike Information Criterion (AICc), from 3451.19 to 3321.19. The results from GWR indicated a significant spatial variation in the local parameter estimates for all the variables and an important reduction of the autocorrelation in the residuals of the GW linear model. Despite the fitting improvement of local models, GW regression, more than an alternative to "global" or traditional regression modelling, seems to be a valuable complement to explore the non-stationary relationships between the response variable and the explanatory variables. The synergy of global and local modelling provides insights into fire management and policy and helps further our understanding of the fire problem over large areas while at the same time recognizing its local character.

Landslide Hazard Mapping in Rwanda Using Logistic Regression

NASA Astrophysics Data System (ADS)

Piller, A.; Anderson, E.; Ballard, H.

2015-12-01

Landslides in the United States cause more than $1 billion in damages and 50 deaths per year (USGS 2014). Globally, figures are much more grave, yet monitoring, mapping and forecasting of these hazards are less than adequate. Seventy-five percent of the population of Rwanda earns a living from farming, mostly subsistence. Loss of farmland, housing, or life, to landslides is a very real hazard. Landslides in Rwanda have an impact at the economic, social, and environmental level. In a developing nation that faces challenges in tracking, cataloging, and predicting the numerous landslides that occur each year, satellite imagery and spatial analysis allow for remote study. We have focused on the development of a landslide inventory and a statistical methodology for assessing landslide hazards. Using logistic regression on approximately 30 test variables (i.e. slope, soil type, land cover, etc.) and a sample of over 200 landslides, we determine which variables are statistically most relevant to landslide occurrence in Rwanda. A preliminary predictive hazard map for Rwanda has been produced, using the variables selected from the logistic regression analysis.

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

A general equation to obtain multiple cut-off scores on a test from multinomial logistic regression.

PubMed

Bersabé, Rosa; Rivas, Teresa

2010-05-01

The authors derive a general equation to compute multiple cut-offs on a total test score in order to classify individuals into more than two ordinal categories. The equation is derived from the multinomial logistic regression (MLR) model, which is an extension of the binary logistic regression (BLR) model to accommodate polytomous outcome variables. From this analytical procedure, cut-off scores are established at the test score (the predictor variable) at which an individual is as likely to be in category j as in category j+1 of an ordinal outcome variable. The application of the complete procedure is illustrated by an example with data from an actual study on eating disorders. In this example, two cut-off scores on the Eating Attitudes Test (EAT-26) scores are obtained in order to classify individuals into three ordinal categories: asymptomatic, symptomatic and eating disorder. Diagnoses were made from the responses to a self-report (Q-EDD) that operationalises DSM-IV criteria for eating disorders. Alternatives to the MLR model to set multiple cut-off scores are discussed.

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.

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.

Application of classification tree and logistic regression for the management and health intervention plans in a community-based study.

PubMed

Teng, Ju-Hsi; Lin, Kuan-Chia; Ho, Bin-Shenq

2007-10-01

A community-based aboriginal study was conducted and analysed to explore the application of classification tree and logistic regression. A total of 1066 aboriginal residents in Yilan County were screened during 2003-2004. The independent variables include demographic characteristics, physical examinations, geographic location, health behaviours, dietary habits and family hereditary diseases history. Risk factors of cardiovascular diseases were selected as the dependent variables in further analysis. The completion rate for heath interview is 88.9%. The classification tree results find that if body mass index is higher than 25.72 kg m(-2) and the age is above 51 years, the predicted probability for number of cardiovascular risk factors > or =3 is 73.6% and the population is 322. If body mass index is higher than 26.35 kg m(-2) and geographical latitude of the village is lower than 24 degrees 22.8', the predicted probability for number of cardiovascular risk factors > or =4 is 60.8% and the population is 74. As the logistic regression results indicate that body mass index, drinking habit and menopause are the top three significant independent variables. The classification tree model specifically shows the discrimination paths and interactions between the risk groups. The logistic regression model presents and analyses the statistical independent factors of cardiovascular risks. Applying both models to specific situations will provide a different angle for the design and management of future health intervention plans after community-based study.

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

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.

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.

Advanced Statistics for Exotic Animal Practitioners.

PubMed

Hodsoll, John; Hellier, Jennifer M; Ryan, Elizabeth G

2017-09-01

Correlation and regression assess the association between 2 or more variables. This article reviews the core knowledge needed to understand these analyses, moving from visual analysis in scatter plots through correlation, simple and multiple linear regression, and logistic regression. Correlation estimates the strength and direction of a relationship between 2 variables. Regression can be considered more general and quantifies the numerical relationships between an outcome and 1 or multiple variables in terms of a best-fit line, allowing predictions to be made. Each technique is discussed with examples and the statistical assumptions underlying their correct application. Copyright © 2017 Elsevier Inc. All rights reserved.

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...

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.

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.

Regularization Paths for Conditional Logistic Regression: The clogitL1 Package.

PubMed

Reid, Stephen; Tibshirani, Rob

2014-07-01

We apply the cyclic coordinate descent algorithm of Friedman, Hastie, and Tibshirani (2010) to the fitting of a conditional logistic regression model with lasso [Formula: see text] and elastic net penalties. The sequential strong rules of Tibshirani, Bien, Hastie, Friedman, Taylor, Simon, and Tibshirani (2012) are also used in the algorithm and it is shown that these offer a considerable speed up over the standard coordinate descent algorithm with warm starts. Once implemented, the algorithm is used in simulation studies to compare the variable selection and prediction performance of the conditional logistic regression model against that of its unconditional (standard) counterpart. We find that the conditional model performs admirably on datasets drawn from a suitable conditional distribution, outperforming its unconditional counterpart at variable selection. The conditional model is also fit to a small real world dataset, demonstrating how we obtain regularization paths for the parameters of the model and how we apply cross validation for this method where natural unconditional prediction rules are hard to come by.

Regularization Paths for Conditional Logistic Regression: The clogitL1 Package

PubMed Central

Reid, Stephen; Tibshirani, Rob

2014-01-01

We apply the cyclic coordinate descent algorithm of Friedman, Hastie, and Tibshirani (2010) to the fitting of a conditional logistic regression model with lasso (ℓ1) and elastic net penalties. The sequential strong rules of Tibshirani, Bien, Hastie, Friedman, Taylor, Simon, and Tibshirani (2012) are also used in the algorithm and it is shown that these offer a considerable speed up over the standard coordinate descent algorithm with warm starts. Once implemented, the algorithm is used in simulation studies to compare the variable selection and prediction performance of the conditional logistic regression model against that of its unconditional (standard) counterpart. We find that the conditional model performs admirably on datasets drawn from a suitable conditional distribution, outperforming its unconditional counterpart at variable selection. The conditional model is also fit to a small real world dataset, demonstrating how we obtain regularization paths for the parameters of the model and how we apply cross validation for this method where natural unconditional prediction rules are hard to come by. PMID:26257587

Ordinal logistic regression analysis on the nutritional status of children in KarangKitri village

NASA Astrophysics Data System (ADS)

Ohyver, Margaretha; Yongharto, Kimmy Octavian

2015-09-01

Ordinal logistic regression is a statistical technique that can be used to describe the relationship between ordinal response variable with one or more independent variables. This method has been used in various fields including in the health field. In this research, ordinal logistic regression is used to describe the relationship between nutritional status of children with age, gender, height, and family status. Nutritional status of children in this research is divided into over nutrition, well nutrition, less nutrition, and malnutrition. The purpose for this research is to describe the characteristics of children in the KarangKitri Village and to determine the factors that influence the nutritional status of children in the KarangKitri village. There are three things that obtained from this research. First, there are still children who are not categorized as well nutritional status. Second, there are children who come from sufficient economic level which include in not normal status. Third, the factors that affect the nutritional level of children are age, family status, and height.

Analysis of an Environmental Exposure Health Questionnaire in a Metropolitan Minority Population Utilizing Logistic Regression and Support Vector Machines

PubMed Central

Chen, Chau-Kuang; Bruce, Michelle; Tyler, Lauren; Brown, Claudine; Garrett, Angelica; Goggins, Susan; Lewis-Polite, Brandy; Weriwoh, Mirabel L; Juarez, Paul D.; Hood, Darryl B.; Skelton, Tyler

2014-01-01

The goal of this study was to analyze a 54-item instrument for assessment of perception of exposure to environmental contaminants within the context of the built environment, or exposome. This exposome was defined in five domains to include 1) home and hobby, 2) school, 3) community, 4) occupation, and 5) exposure history. Interviews were conducted with child-bearing-age minority women at Metro Nashville General Hospital at Meharry Medical College. Data were analyzed utilizing DTReg software for Support Vector Machine (SVM) modeling followed by an SPSS package for a logistic regression model. The target (outcome) variable of interest was respondent's residence by ZIP code. The results demonstrate that the rank order of important variables with respect to SVM modeling versus traditional logistic regression models is almost identical. This is the first study documenting that SVM analysis has discriminate power for determination of higher-ordered spatial relationships on an environmental exposure history questionnaire. PMID:23395953

Analysis of an environmental exposure health questionnaire in a metropolitan minority population utilizing logistic regression and Support Vector Machines.

PubMed

Chen, Chau-Kuang; Bruce, Michelle; Tyler, Lauren; Brown, Claudine; Garrett, Angelica; Goggins, Susan; Lewis-Polite, Brandy; Weriwoh, Mirabel L; Juarez, Paul D; Hood, Darryl B; Skelton, Tyler

2013-02-01

The goal of this study was to analyze a 54-item instrument for assessment of perception of exposure to environmental contaminants within the context of the built environment, or exposome. This exposome was defined in five domains to include 1) home and hobby, 2) school, 3) community, 4) occupation, and 5) exposure history. Interviews were conducted with child-bearing-age minority women at Metro Nashville General Hospital at Meharry Medical College. Data were analyzed utilizing DTReg software for Support Vector Machine (SVM) modeling followed by an SPSS package for a logistic regression model. The target (outcome) variable of interest was respondent's residence by ZIP code. The results demonstrate that the rank order of important variables with respect to SVM modeling versus traditional logistic regression models is almost identical. This is the first study documenting that SVM analysis has discriminate power for determination of higher-ordered spatial relationships on an environmental exposure history questionnaire.

A Hybrid Approach of Stepwise Regression, Logistic Regression, Support Vector Machine, and Decision Tree for Forecasting Fraudulent Financial Statements

PubMed Central

Goo, Yeong-Jia James; Shen, Zone-De

2014-01-01

As the fraudulent financial statement of an enterprise is increasingly serious with each passing day, establishing a valid forecasting fraudulent financial statement model of an enterprise has become an important question for academic research and financial practice. After screening the important variables using the stepwise regression, the study also matches the logistic regression, support vector machine, and decision tree to construct the classification models to make a comparison. The study adopts financial and nonfinancial variables to assist in establishment of the forecasting fraudulent financial statement model. Research objects are the companies to which the fraudulent and nonfraudulent financial statement happened between years 1998 to 2012. The findings are that financial and nonfinancial information are effectively used to distinguish the fraudulent financial statement, and decision tree C5.0 has the best classification effect 85.71%. PMID:25302338

A hybrid approach of stepwise regression, logistic regression, support vector machine, and decision tree for forecasting fraudulent financial statements.

PubMed

Chen, Suduan; Goo, Yeong-Jia James; Shen, Zone-De

2014-01-01

As the fraudulent financial statement of an enterprise is increasingly serious with each passing day, establishing a valid forecasting fraudulent financial statement model of an enterprise has become an important question for academic research and financial practice. After screening the important variables using the stepwise regression, the study also matches the logistic regression, support vector machine, and decision tree to construct the classification models to make a comparison. The study adopts financial and nonfinancial variables to assist in establishment of the forecasting fraudulent financial statement model. Research objects are the companies to which the fraudulent and nonfraudulent financial statement happened between years 1998 to 2012. The findings are that financial and nonfinancial information are effectively used to distinguish the fraudulent financial statement, and decision tree C5.0 has the best classification effect 85.71%.

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.

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

PubMed

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

2016-01-01

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

Prediction of 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.

Selenium in irrigated agricultural areas of the western United States

USGS Publications Warehouse

Nolan, B.T.; Clark, M.L.

1997-01-01

A logistic regression model was developed to predict the likelihood that Se exceeds the USEPA chronic criterion for aquatic life (5 ??g/L) in irrigated agricultural areas of the western USA. Preliminary analysis of explanatory variables used in the model indicated that surface-water Se concentration increased with increasing dissolved solids (DS) concentration and with the presence of Upper Cretaceous, mainly marine sediment. The presence or absence of Cretaceous sediment was the major variable affecting Se concentration in surface-water samples from the National Irrigation Water Quality Program. Median Se concentration was 14 ??g/L in samples from areas underlain by Cretaceous sediments and < 1 ??g/L in samples from areas underlain by non-Cretaceous sediments. Wilcoxon rank sum tests indicated that elevated Se concentrations in samples from areas with Cretaceous sediments, irrigated areas, and from closed lakes and ponds were statistically significant. Spearman correlations indicated that Se was positively correlated with a binary geology variable (0.64) and DS (0.45). Logistic regression models indicated that the concentration of Se in surface water was almost certain to exceed the Environmental Protection Agency aquatic-life chronic criterion of 5 ??g/L when DS was greater than 3000 mg/L in areas with Cretaceous sediments. The 'best' logistic regression model correctly predicted Se exceedances and nonexceedances 84.4% of the time, and model sensitivity was 80.7%. A regional map of Cretaceous sediment showed the location of potential problem areas. The map and logistic regression model are tools that can be used to determine the potential for Se contamination of irrigated agricultural areas in the western USA.

Introduction to the use of regression models in epidemiology.

PubMed

Bender, Ralf

2009-01-01

Regression modeling is one of the most important statistical techniques used in analytical epidemiology. By means of regression models the effect of one or several explanatory variables (e.g., exposures, subject characteristics, risk factors) on a response variable such as mortality or cancer can be investigated. From multiple regression models, adjusted effect estimates can be obtained that take the effect of potential confounders into account. Regression methods can be applied in all epidemiologic study designs so that they represent a universal tool for data analysis in epidemiology. Different kinds of regression models have been developed in dependence on the measurement scale of the response variable and the study design. The most important methods are linear regression for continuous outcomes, logistic regression for binary outcomes, Cox regression for time-to-event data, and Poisson regression for frequencies and rates. This chapter provides a nontechnical introduction to these regression models with illustrating examples from cancer research.

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.

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).

Computational procedures for probing interactions in OLS and logistic regression: SPSS and SAS implementations.

PubMed

Hayes, Andrew F; Matthes, Jörg

2009-08-01

Researchers often hypothesize moderated effects, in which the effect of an independent variable on an outcome variable depends on the value of a moderator variable. Such an effect reveals itself statistically as an interaction between the independent and moderator variables in a model of the outcome variable. When an interaction is found, it is important to probe the interaction, for theories and hypotheses often predict not just interaction but a specific pattern of effects of the focal independent variable as a function of the moderator. This article describes the familiar pick-a-point approach and the much less familiar Johnson-Neyman technique for probing interactions in linear models and introduces macros for SPSS and SAS to simplify the computations and facilitate the probing of interactions in ordinary least squares and logistic regression. A script version of the SPSS macro is also available for users who prefer a point-and-click user interface rather than command syntax.

Prescription-drug-related risk in driving: comparing conventional and lasso shrinkage logistic regressions.

PubMed

Avalos, Marta; Adroher, Nuria Duran; Lagarde, Emmanuel; Thiessard, Frantz; Grandvalet, Yves; Contrand, Benjamin; Orriols, Ludivine

2012-09-01

Large data sets with many variables provide particular challenges when constructing analytic models. Lasso-related methods provide a useful tool, although one that remains unfamiliar to most epidemiologists. We illustrate the application of lasso methods in an analysis of the impact of prescribed drugs on the risk of a road traffic crash, using a large French nationwide database (PLoS Med 2010;7:e1000366). In the original case-control study, the authors analyzed each exposure separately. We use the lasso method, which can simultaneously perform estimation and variable selection in a single model. We compare point estimates and confidence intervals using (1) a separate logistic regression model for each drug with a Bonferroni correction and (2) lasso shrinkage logistic regression analysis. Shrinkage regression had little effect on (bias corrected) point estimates, but led to less conservative results, noticeably for drugs with moderate levels of exposure. Carbamates, carboxamide derivative and fatty acid derivative antiepileptics, drugs used in opioid dependence, and mineral supplements of potassium showed stronger associations. Lasso is a relevant method in the analysis of databases with large number of exposures and can be recommended as an alternative to conventional strategies.

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.

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.

The comparison of landslide ratio-based and general logistic regression landslide susceptibility models in the Chishan watershed after 2009 Typhoon Morakot

NASA Astrophysics Data System (ADS)

WU, Chunhung

2015-04-01

The research built the original logistic regression landslide susceptibility model (abbreviated as or-LRLSM) and landslide ratio-based ogistic regression landslide susceptibility model (abbreviated as lr-LRLSM), compared the performance and explained the error source of two models. The research assumes that the performance of the logistic regression model can be better if the distribution of landslide ratio and weighted value of each variable is similar. Landslide ratio is the ratio of landslide area to total area in the specific area and an useful index to evaluate the seriousness of landslide disaster in Taiwan. The research adopted the landside inventory induced by 2009 Typhoon Morakot in the Chishan watershed, which was the most serious disaster event in the last decade, in Taiwan. The research adopted the 20 m grid as the basic unit in building the LRLSM, and six variables, including elevation, slope, aspect, geological formation, accumulated rainfall, and bank erosion, were included in the two models. The six variables were divided as continuous variables, including elevation, slope, and accumulated rainfall, and categorical variables, including aspect, geological formation and bank erosion in building the or-LRLSM, while all variables, which were classified based on landslide ratio, were categorical variables in building the lr-LRLSM. Because the count of whole basic unit in the Chishan watershed was too much to calculate by using commercial software, the research took random sampling instead of the whole basic units. The research adopted equal proportions of landslide unit and not landslide unit in logistic regression analysis. The research took 10 times random sampling and selected the group with the best Cox & Snell R2 value and Nagelkerker R2 value as the database for the following analysis. Based on the best result from 10 random sampling groups, the or-LRLSM (lr-LRLSM) is significant at the 1% level with Cox & Snell R2 = 0.190 (0.196) and Nagelkerke R2 = 0.253 (0.260). The unit with the landslide susceptibility value > 0.5 (≦ 0.5) will be classified as a predicted landslide unit (not landslide unit). The AUC, i.e. the area under the relative operating characteristic curve, of or-LRLSM in the Chishan watershed is 0.72, while that of lr-LRLSM is 0.77. Furthermore, the average correct ratio of lr-LRLSM (73.3%) is better than that of or-LRLSM (68.3%). The research analyzed in detail the error sources from the two models. In continuous variables, using the landslide ratio-based classification in building the lr-LRLSM can let the distribution of weighted value more similar to distribution of landslide ratio in the range of continuous variable than that in building the or-LRLSM. In categorical variables, the meaning of using the landslide ratio-based classification in building the lr-LRLSM is to gather the parameters with approximate landslide ratio together. The mean correct ratio in continuous variables (categorical variables) by using the lr-LRLSM is better than that in or-LRLSM by 0.6 ~ 2.6% (1.7% ~ 6.0%). Building the landslide susceptibility model by using landslide ratio-based classification is practical and of better performance than that by using the original logistic regression.

Sparse modeling of spatial environmental variables associated with asthma

PubMed Central

Chang, Timothy S.; Gangnon, Ronald E.; Page, C. David; Buckingham, William R.; Tandias, Aman; Cowan, Kelly J.; Tomasallo, Carrie D.; Arndt, Brian G.; Hanrahan, Lawrence P.; Guilbert, Theresa W.

2014-01-01

Geographically distributed environmental factors influence the burden of diseases such as asthma. Our objective was to identify sparse environmental variables associated with asthma diagnosis gathered from a large electronic health record (EHR) dataset while controlling for spatial variation. An EHR dataset from the University of Wisconsin’s Family Medicine, Internal Medicine and Pediatrics Departments was obtained for 199,220 patients aged 5–50 years over a three-year period. Each patient’s home address was geocoded to one of 3,456 geographic census block groups. Over one thousand block group variables were obtained from a commercial database. We developed a Sparse Spatial Environmental Analysis (SASEA). Using this method, the environmental variables were first dimensionally reduced with sparse principal component analysis. Logistic thin plate regression spline modeling was then used to identify block group variables associated with asthma from sparse principal components. The addresses of patients from the EHR dataset were distributed throughout the majority of Wisconsin’s geography. Logistic thin plate regression spline modeling captured spatial variation of asthma. Four sparse principal components identified via model selection consisted of food at home, dog ownership, household size, and disposable income variables. In rural areas, dog ownership and renter occupied housing units from significant sparse principal components were associated with asthma. Our main contribution is the incorporation of sparsity in spatial modeling. SASEA sequentially added sparse principal components to Logistic thin plate regression spline modeling. This method allowed association of geographically distributed environmental factors with asthma using EHR and environmental datasets. SASEA can be applied to other diseases with environmental risk factors. PMID:25533437

Sparse modeling of spatial environmental variables associated with asthma.

PubMed

Chang, Timothy S; Gangnon, Ronald E; David Page, C; Buckingham, William R; Tandias, Aman; Cowan, Kelly J; Tomasallo, Carrie D; Arndt, Brian G; Hanrahan, Lawrence P; Guilbert, Theresa W

2015-02-01

Geographically distributed environmental factors influence the burden of diseases such as asthma. Our objective was to identify sparse environmental variables associated with asthma diagnosis gathered from a large electronic health record (EHR) dataset while controlling for spatial variation. An EHR dataset from the University of Wisconsin's Family Medicine, Internal Medicine and Pediatrics Departments was obtained for 199,220 patients aged 5-50years over a three-year period. Each patient's home address was geocoded to one of 3456 geographic census block groups. Over one thousand block group variables were obtained from a commercial database. We developed a Sparse Spatial Environmental Analysis (SASEA). Using this method, the environmental variables were first dimensionally reduced with sparse principal component analysis. Logistic thin plate regression spline modeling was then used to identify block group variables associated with asthma from sparse principal components. The addresses of patients from the EHR dataset were distributed throughout the majority of Wisconsin's geography. Logistic thin plate regression spline modeling captured spatial variation of asthma. Four sparse principal components identified via model selection consisted of food at home, dog ownership, household size, and disposable income variables. In rural areas, dog ownership and renter occupied housing units from significant sparse principal components were associated with asthma. Our main contribution is the incorporation of sparsity in spatial modeling. SASEA sequentially added sparse principal components to Logistic thin plate regression spline modeling. This method allowed association of geographically distributed environmental factors with asthma using EHR and environmental datasets. SASEA can be applied to other diseases with environmental risk factors. Copyright © 2014 Elsevier Inc. All rights reserved.

Development of a statistical model for the determination of the probability of riverbank erosion in a Meditteranean river basin

NASA Astrophysics Data System (ADS)

Varouchakis, Emmanouil; Kourgialas, Nektarios; Karatzas, George; Giannakis, Georgios; Lilli, Maria; Nikolaidis, Nikolaos

2014-05-01

Riverbank erosion affects the river morphology and the local habitat and results in riparian land loss, damage to property and infrastructures, ultimately weakening flood defences. An important issue concerning riverbank erosion is the identification of the areas vulnerable to erosion, as it allows for predicting changes and assists with stream management and restoration. One way to predict the vulnerable to erosion areas is to determine the erosion probability by identifying the underlying relations between riverbank erosion and the geomorphological and/or hydrological variables that prevent or stimulate erosion. A statistical model for evaluating the probability of erosion based on a series of independent local variables and by using logistic regression is developed in this work. The main variables affecting erosion are vegetation index (stability), the presence or absence of meanders, bank material (classification), stream power, bank height, river bank slope, riverbed slope, cross section width and water velocities (Luppi et al. 2009). In statistics, 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 (continuous or categorical). The probabilities of the possible outcomes are modelled as a function of 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. 1 = "presence of erosion" and 0 = "no erosion") for any value of the independent variables. The regression coefficients are estimated by using maximum likelihood estimation. The erosion occurrence probability can be calculated in conjunction with the model deviance regarding the independent variables tested (Atkinson et al. 2003). The developed statistical model is applied to the Koiliaris River Basin in the island of Crete, Greece. The aim is to determine the probability of erosion along the Koiliaris' riverbanks considering a series of independent geomorphological and/or hydrological variables. Data for the river bank slope and for the river cross section width are available at ten locations along the river. The riverbank has indications of erosion at six of the ten locations while four has remained stable. Based on a recent work, measurements for the two independent variables and data regarding bank stability are available at eight different locations along the river. These locations were used as validation points for the proposed statistical model. The results show a very close agreement between the observed erosion indications and the statistical model as the probability of erosion was accurately predicted at seven out of the eight locations. The next step is to apply the model at more locations along the riverbanks. In November 2013, stakes were inserted at selected locations in order to be able to identify the presence or absence of erosion after the winter period. In April 2014 the presence or absence of erosion will be identified and the model results will be compared to the field data. Our intent is to extend the model by increasing the number of independent variables in order to indentify the key factors favouring erosion along the Koiliaris River. We aim at developing an easy to use statistical tool that will provide a quantified measure of the erosion probability along the riverbanks, which could consequently be used to prevent erosion and flooding events. Atkinson, P. M., German, S. E., Sear, D. A. and Clark, M. J. 2003. Exploring the relations between riverbank erosion and geomorphological controls using geographically weighted logistic regression. Geographical Analysis, 35 (1), 58-82. Luppi, L., Rinaldi, M., Teruggi, L. B., Darby, S. E. and Nardi, L. 2009. Monitoring and numerical modelling of riverbank erosion processes: A case study along the Cecina River (central Italy). Earth Surface Processes and Landforms, 34 (4), 530-546. 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.

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.

John Snow, William Farr and the 1849 outbreak of cholera that affected London: a reworking of the data highlights the importance of the water supply.

PubMed

Bingham, P; Verlander, N Q; Cheal, M J

2004-09-01

This paper examines why Snow's contention that cholera was principally spread by water was not accepted in the 1850s by the medical elite. The consequence of rejection was that hundreds in the UK continued to die. Logistic regression was used to re-analyse data, first published in 1852 by William Farr, consisting of the 1849 mortality rate from cholera and eight potential explanatory variables for the 38 registration districts of London. Logistic regression does not support Farr's original conclusion that a district's elevation above high water was the most important explanatory variable. Elevation above high water, water supply and poor rate each have an independent significant effect on district cholera mortality rate, but in terms of size of effect, it can be argued that water supply most strongly 'invited' further consideration. The science of epidemiology, that Farr helped to found, has continued to advance. Had logistic regression been available to Farr, its application to his 1852 data set would have changed his conclusion.

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.

Serum magnesium but not calcium was associated with hemorrhagic transformation in stroke overall and stroke subtypes: a case-control study in China.

PubMed

Tan, Ge; Yuan, Ruozhen; Wei, ChenChen; Xu, Mangmang; Liu, Ming

2018-05-26

Association between serum calcium and magnesium versus hemorrhagic transformation (HT) remains to be identified. A total of 1212 non-thrombolysis patients with serum calcium and magnesium collected within 24 h from stroke onset were enrolled. Backward stepwise multivariate logistic regression analysis was conducted to investigate association between calcium and magnesium versus HT. Calcium and magnesium were entered into logistic regression analysis in two models, separately: model 1, as continuous variable (per 1-mmol/L increase), and model 2, as four-categorized variable (being collapsed into quartiles). HT occurred in 140 patients (11.6%). Serum calcium was slightly lower in patients with HT than in patient without HT (P = 0.273). But serum magnesium was significantly lower in patients with HT than in patients without HT (P = 0.007). In logistic regression analysis, calcium displayed no association with HT. Magnesium, as either continuous or four-categorized variable, was independently and inversely associated with HT in stroke overall and stroke of large-artery atherosclerosis (LAA). The results demonstrated that serum calcium had no association with HT in patients without thrombolysis after acute ischemic stroke. Serum magnesium in low level was independently associated with increasing HT in stroke overall and particularly in stroke of LAA.

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.

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

PubMed

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

2017-10-26

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

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

USGS Publications Warehouse

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

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 conditional distribution of a bounded discrete random variable. The logistic quantile regression model requires that counts are randomly jittered to a continuous random variable, logit transformed to bound them between specified lower and upper values, then estimated in conventional linear quantile regression, repeating the 3 steps and averaging estimates. Back-transformation to the original discrete scale relies on the fact that quantiles are equivariant to monotonic transformations. We demonstrate this statistical procedure by modeling 20 years of California Spotted Owl fledgling production (0−3 per territory) on the Lassen National Forest, California, USA, as related to climate, demographic, and landscape habitat characteristics at territories. Spotted Owl fledgling counts increased nonlinearly with decreasing precipitation in the early nesting period, in the winter prior to nesting, and in the prior growing season; with increasing minimum temperatures in the early nesting period; with adult compared to subadult parents; when there was no fledgling production in the prior year; and when percentage of the landscape surrounding nesting sites (202 ha) with trees ≥25 m height increased. Changes in production were primarily driven by changes in the proportion of territories with 2 or 3 fledglings. Average variances of the discrete cumulative distributions of the estimated fledgling counts indicated that temporal changes in climate and parent age class explained 18% of the annual variance in owl fledgling production, which was 34% of the total variance. Prior fledgling production explained as much of the variance in the fledgling counts as climate, parent age class, and landscape habitat predictors. Our logistic quantile regression model can be used for any discrete response variables with fixed upper and lower bounds.

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.

Correlation and simple linear regression.

PubMed

Eberly, Lynn E

2007-01-01

This chapter highlights important steps in using correlation and simple linear regression to address scientific questions about the association of two continuous variables with each other. These steps include estimation and inference, assessing model fit, the connection between regression and ANOVA, and study design. Examples in microbiology are used throughout. This chapter provides a framework that is helpful in understanding more complex statistical techniques, such as multiple linear regression, linear mixed effects models, logistic regression, and proportional hazards regression.

PAKDD Data Mining Competition 2009: New Ways of Using Known Methods

NASA Astrophysics Data System (ADS)

Linhart, Chaim; Harari, Guy; Abramovich, Sharon; Buchris, Altina

The PAKDD 2009 competition focuses on the problem of credit risk assessment. As required, we had to confront the problem of the robustness of the credit-scoring model against performance degradation caused by gradual market changes along a few years of business operation. We utilized the following standard models: logistic regression, KNN, SVM, GBM and decision tree. The novelty of our approach is two-fold: the integration of existing models, namely feeding the results of KNN as an input variable to the logistic regression, and re-coding categorical variables as numerical values that represent each category's statistical impact on the target label. The best solution we obtained reached 3rd place in the competition, with an AUC score of 0.655.

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

PubMed

Vetter, Thomas R; Schober, Patrick

2018-05-15

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

Combining biological and psychosocial baseline variables did not improve prediction of outcome of a very-low-energy diet in a clinic referral population.

PubMed

Sumithran, P; Purcell, K; Kuyruk, S; Proietto, J; Prendergast, L A

2018-02-01

Consistent, strong predictors of obesity treatment outcomes have not been identified. It has been suggested that broadening the range of predictor variables examined may be valuable. We explored methods to predict outcomes of a very-low-energy diet (VLED)-based programme in a clinically comparable setting, using a wide array of pre-intervention biological and psychosocial participant data. A total of 61 women and 39 men (mean ± standard deviation [SD] body mass index: 39.8 ± 7.3 kg/m 2 ) underwent an 8-week VLED and 12-month follow-up. At baseline, participants underwent a blood test and assessment of psychological, social and behavioural factors previously associated with treatment outcomes. Logistic regression, linear discriminant analysis, decision trees and random forests were used to model outcomes from baseline variables. Of the 100 participants, 88 completed the VLED and 42 attended the Week 60 visit. Overall prediction rates for weight loss of ≥10% at weeks 8 and 60, and attrition at Week 60, using combined data were between 77.8 and 87.6% for logistic regression, and lower for other methods. When logistic regression analyses included only baseline demographic and anthropometric variables, prediction rates were 76.2-86.1%. In this population, considering a wide range of biological and psychosocial data did not improve outcome prediction compared to simply-obtained baseline characteristics. © 2017 World Obesity Federation.

An investigation on fatality of drivers in vehicle-fixed object accidents on expressways in China: Using multinomial logistic regression model.

PubMed

Peng, Yong; Peng, Shuangling; Wang, Xinghua; Tan, Shiyang

2018-06-01

This study aims to identify the effects of characteristics of vehicle, roadway, driver, and environment on fatality of drivers in vehicle-fixed object accidents on expressways in Changsha-Zhuzhou-Xiangtan district of Hunan province in China by developing multinomial logistic regression models. For this purpose, 121 vehicle-fixed object accidents from 2011-2017 are included in the modeling process. First, descriptive statistical analysis is made to understand the main characteristics of the vehicle-fixed object crashes. Then, 19 explanatory variables are selected, and correlation analysis of each two variables is conducted to choose the variables to be concluded. Finally, five multinomial logistic regression models including different independent variables are compared, and the model with best fitting and prediction capability is chosen as the final model. The results showed that the turning direction in avoiding fixed objects raised the possibility that drivers would die. About 64% of drivers died in the accident were found being ejected out of the car, of which 50% did not use a seatbelt before the fatal accidents. Drivers are likely to die when they encounter bad weather on the expressway. Drivers with less than 10 years of driving experience are more likely to die in these accidents. Fatigue or distracted driving is also a significant factor in fatality of drivers. Findings from this research provide an insight into reducing fatality of drivers in vehicle-fixed object accidents.

Detecting Anomalies in Process Control Networks

NASA Astrophysics Data System (ADS)

Rrushi, Julian; Kang, Kyoung-Don

This paper presents the estimation-inspection algorithm, a statistical algorithm for anomaly detection in process control networks. The algorithm determines if the payload of a network packet that is about to be processed by a control system is normal or abnormal based on the effect that the packet will have on a variable stored in control system memory. The estimation part of the algorithm uses logistic regression integrated with maximum likelihood estimation in an inductive machine learning process to estimate a series of statistical parameters; these parameters are used in conjunction with logistic regression formulas to form a probability mass function for each variable stored in control system memory. The inspection part of the algorithm uses the probability mass functions to estimate the normalcy probability of a specific value that a network packet writes to a variable. Experimental results demonstrate that the algorithm is very effective at detecting anomalies in process control networks.

Binary logistic regression modelling: Measuring the probability of relapse cases among drug addict

NASA Astrophysics Data System (ADS)

Ismail, Mohd Tahir; Alias, Siti Nor Shadila

2014-07-01

For many years Malaysia faced the drug addiction issues. The most serious case is relapse phenomenon among treated drug addict (drug addict who have under gone the rehabilitation programme at Narcotic Addiction Rehabilitation Centre, PUSPEN). Thus, the main objective of this study is to find the most significant factor that contributes to relapse to happen. The binary logistic regression analysis was employed to model the relationship between independent variables (predictors) and dependent variable. The dependent variable is the status of the drug addict either relapse, (Yes coded as 1) or not, (No coded as 0). Meanwhile the predictors involved are age, age at first taking drug, family history, education level, family crisis, community support and self motivation. The total of the sample is 200 which the data are provided by AADK (National Antidrug Agency). The finding of the study revealed that age and self motivation are statistically significant towards the relapse cases..

Identifying the Factors That Influence Change in SEBD Using Logistic Regression Analysis

ERIC Educational Resources Information Center

Camilleri, Liberato; Cefai, Carmel

2013-01-01

Multiple linear regression and ANOVA models are widely used in applications since they provide effective statistical tools for assessing the relationship between a continuous dependent variable and several predictors. However these models rely heavily on linearity and normality assumptions and they do not accommodate categorical dependent…

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.

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.

The relationship of bone and blood lead to hypertension: Further analyses of the normative aging study data

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

Hu, H.; Kim, Rokho; Korrick, S.

1996-12-31

In an earlier report based on participants in the Veterans Administration Normative Aging Study, we found a significant association between the risk of hypertension and lead levels in tibia. To examine the possible confounding effects of education and occupation, we considered in this study five levels of education and three levels of occupation as independent variables in the statistical model. Of 1,171 active subjects seen between August 1991 and December 1994, 563 provided complete data for this analysis. In the initial logistic regression model, acre and body mass index, family history of hypertension, and dietary sodium intake, but neither cumulativemore » smoking nor alcohol ingestion, conferred increased odds ratios for being hypertensive that were statistically significant. When the lead biomarkers were added separately to this initial logistic model, tibia lead and patella lead levels were associated with significantly elevated odds ratios for hypertension. In the final backward elimination logistic regression model that included categorical variables for education and occupation, the only variables retained were body mass index, family history of hypertension, and tibia lead level. We conclude that education and occupation variables were not confounding the association between the lead biomarkers and hypertension that we reported previously. 27 refs., 3 tabs.« less

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.

Hip fracture in the elderly: a re-analysis of the EPIDOS study with causal Bayesian networks.

PubMed

Caillet, Pascal; Klemm, Sarah; Ducher, Michel; Aussem, Alexandre; Schott, Anne-Marie

2015-01-01

Hip fractures commonly result in permanent disability, institutionalization or death in elderly. Existing hip-fracture predicting tools are underused in clinical practice, partly due to their lack of intuitive interpretation. By use of a graphical layer, Bayesian network models could increase the attractiveness of fracture prediction tools. Our aim was to study the potential contribution of a causal Bayesian network in this clinical setting. A logistic regression was performed as a standard control approach to check the robustness of the causal Bayesian network approach. EPIDOS is a multicenter study, conducted in an ambulatory care setting in five French cities between 1992 and 1996 and updated in 2010. The study included 7598 women aged 75 years or older, in which fractures were assessed quarterly during 4 years. A causal Bayesian network and a logistic regression were performed on EPIDOS data to describe major variables involved in hip fractures occurrences. Both models had similar association estimations and predictive performances. They detected gait speed and mineral bone density as variables the most involved in the fracture process. The causal Bayesian network showed that gait speed and bone mineral density were directly connected to fracture and seem to mediate the influence of all the other variables included in our model. The logistic regression approach detected multiple interactions involving psychotropic drug use, age and bone mineral density. Both approaches retrieved similar variables as predictors of hip fractures. However, Bayesian network highlighted the whole web of relation between the variables involved in the analysis, suggesting a possible mechanism leading to hip fracture. According to the latter results, intervention focusing concomitantly on gait speed and bone mineral density may be necessary for an optimal prevention of hip fracture occurrence in elderly people.

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.

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…

Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression

PubMed Central

Dipnall, Joanna F.

2016-01-01

Background Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study. Methods The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009–2010). Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators. Results After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30), serum glucose (OR 1.01; 95% CI 1.00, 1.01) and total bilirubin (OR 0.12; 95% CI 0.05, 0.28). Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016), and current smokers (p<0.001). Conclusion The systematic use of a hybrid methodology for variable selection, fusing data mining techniques using a machine learning algorithm with traditional statistical modelling, accounted for missing data and complex survey sampling methodology and was demonstrated to be a useful tool for detecting three biomarkers associated with depression for future hypothesis generation: red cell distribution width, serum glucose and total bilirubin. PMID:26848571

Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression.

PubMed

Dipnall, Joanna F; Pasco, Julie A; Berk, Michael; Williams, Lana J; Dodd, Seetal; Jacka, Felice N; Meyer, Denny

2016-01-01

Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study. The study used a three-step methodology amalgamating multiple imputation, a machine learning boosted regression algorithm and logistic regression, to identify key biomarkers associated with depression in the National Health and Nutrition Examination Study (2009-2010). Depression was measured using the Patient Health Questionnaire-9 and 67 biomarkers were analysed. Covariates in this study included gender, age, race, smoking, food security, Poverty Income Ratio, Body Mass Index, physical activity, alcohol use, medical conditions and medications. The final imputed weighted multiple logistic regression model included possible confounders and moderators. After the creation of 20 imputation data sets from multiple chained regression sequences, machine learning boosted regression initially identified 21 biomarkers associated with depression. Using traditional logistic regression methods, including controlling for possible confounders and moderators, a final set of three biomarkers were selected. The final three biomarkers from the novel hybrid variable selection methodology were red cell distribution width (OR 1.15; 95% CI 1.01, 1.30), serum glucose (OR 1.01; 95% CI 1.00, 1.01) and total bilirubin (OR 0.12; 95% CI 0.05, 0.28). Significant interactions were found between total bilirubin with Mexican American/Hispanic group (p = 0.016), and current smokers (p<0.001). The systematic use of a hybrid methodology for variable selection, fusing data mining techniques using a machine learning algorithm with traditional statistical modelling, accounted for missing data and complex survey sampling methodology and was demonstrated to be a useful tool for detecting three biomarkers associated with depression for future hypothesis generation: red cell distribution width, serum glucose and total bilirubin.

Predictors of condom use and refusal among the population of Free State province in South Africa

PubMed Central

2012-01-01

Background This study investigated the extent and predictors of condom use and condom refusal in the Free State province in South Africa. Methods Through a household survey conducted in the Free Sate province of South Africa, 5,837 adults were interviewed. Univariate and multivariate survey logistic regressions and classification trees (CT) were used for analysing two response variables ‘ever used condom’ and ‘ever refused condom’. Results Eighty-three per cent of the respondents had ever used condoms, of which 38% always used them; 61% used them during the last sexual intercourse and 9% had ever refused to use them. The univariate logistic regression models and CT analysis indicated that a strong predictor of condom use was its perceived need. In the CT analysis, this variable was followed in importance by ‘knowledge of correct use of condom’, condom availability, young age, being single and higher education. ‘Perceived need’ for condoms did not remain significant in the multivariate analysis after controlling for other variables. The strongest predictor of condom refusal, as shown by the CT, was shame associated with condoms followed by the presence of sexual risk behaviour, knowing one’s HIV status, older age and lacking knowledge of condoms (i.e., ability to prevent sexually transmitted diseases and pregnancy, availability, correct and consistent use and existence of female condoms). In the multivariate logistic regression, age was not significant for condom refusal while affordability and perceived need were additional significant variables. Conclusions The use of complementary modelling techniques such as CT in addition to logistic regressions adds to a better understanding of condom use and refusal. Further improvement in correct and consistent use of condoms will require targeted interventions. In addition to existing social marketing campaigns, tailored approaches should focus on establishing the perceived need for condom-use and improving skills for correct use. They should also incorporate interventions to reduce the shame associated with condoms and individual counselling of those likely to refuse condoms. PMID:22639964

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.

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.

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.

Estimation of Recurrence of Colorectal Adenomas with Dependent Censoring Using Weighted Logistic Regression

PubMed Central

Hsu, Chiu-Hsieh; Li, Yisheng; Long, Qi; Zhao, Qiuhong; Lance, Peter

2011-01-01

In colorectal polyp prevention trials, estimation of the rate of recurrence of adenomas at the end of the trial may be complicated by dependent censoring, that is, time to follow-up colonoscopy and dropout may be dependent on time to recurrence. Assuming that the auxiliary variables capture the dependence between recurrence and censoring times, we propose to fit two working models with the auxiliary variables as covariates to define risk groups and then extend an existing weighted logistic regression method for independent censoring to each risk group to accommodate potential dependent censoring. In a simulation study, we show that the proposed method results in both a gain in efficiency and reduction in bias for estimating the recurrence rate. We illustrate the methodology by analyzing a recurrent adenoma dataset from a colorectal polyp prevention trial. PMID:22065985

Cross-national differences in the gender gap in subjective health in Europe: does country-level gender equality matter?

PubMed

Dahlin, Johanna; Härkönen, Juho

2013-12-01

Multiple studies have found that women report being in worse health despite living longer. Gender gaps vary cross-nationally, but relatively little is known about the causes of comparative differences. Existing literature is inconclusive as to whether gender gaps in health are smaller in more gender equal societies. We analyze gender gaps in self-rated health (SRH) and limiting longstanding illness (LLI) with five waves of European Social Survey data for 191,104 respondents from 28 countries. We use means, odds ratios, logistic regressions, and multilevel random slopes logistic regressions. Gender gaps in subjective health vary visibly across Europe. In many countries (especially in Eastern and Southern Europe), women report distinctly worse health, while in others (such as Estonia, Finland, and Great Britain) there are small or no differences. Logistic regressions ran separately for each country revealed that individual-level socioeconomic and demographic variables explain a majority of these gaps in some countries, but contribute little to their understanding in most countries. In yet other countries, men had worse health when these variables were controlled for. Cross-national variation in the gender gaps exists after accounting for individual-level factors. Against expectations, the remaining gaps are not systematically related to societal-level gender inequality in the multilevel analyses. Our findings stress persistent cross-national variability in gender gaps in health and call for further analysis. Copyright © 2013 Elsevier Ltd. All rights reserved.

An Investigation of the Variables Predicting Faculty of Education Students' Speaking Anxiety through Ordinal Logistic Regression Analysis

ERIC Educational Resources Information Center

Bozpolat, Ebru

2017-01-01

The purpose of this study is to determine whether Cumhuriyet University Faculty of Education students' levels of speaking anxiety are predicted by the variables of gender, department, grade, such sub-dimensions of "Speaking Self-Efficacy Scale for Pre-Service Teachers" as "public speaking," "effective speaking,"…

Predicting Teacher Value-Added Results in Non-Tested Subjects Based on Confounding Variables: A Multinomial Logistic Regression

ERIC Educational Resources Information Center

Street, Nathan Lee

2017-01-01

Teacher value-added measures (VAM) are designed to provide information regarding teachers' causal impact on the academic growth of students while controlling for exogenous variables. While some researchers contend VAMs successfully and authentically measure teacher causality on learning, others suggest VAMs cannot adequately control for exogenous…

Predicting The Type Of Pregnancy Using Flexible Discriminate Analysis And Artificial Neural Networks: A Comparison Study

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

Hooman, A.; Mohammadzadeh, M

Some medical and epidemiological surveys have been designed to predict a nominal response variable with several levels. With regard to the type of pregnancy there are four possible states: wanted, unwanted by wife, unwanted by husband and unwanted by couple. In this paper, we have predicted the type of pregnancy, as well as the factors influencing it using three different models and comparing them. Regarding the type of pregnancy with several levels, we developed a multinomial logistic regression, a neural network and a flexible discrimination based on the data and compared their results using tow statistical indices: Surface under curvemore » (ROC) and kappa coefficient. Based on these tow indices, flexible discrimination proved to be a better fit for prediction on data in comparison to other methods. When the relations among variables are complex, one can use flexible discrimination instead of multinomial logistic regression and neural network to predict the nominal response variables with several levels in order to gain more accurate predictions.« less

Alcohol and tobacco use and cognitive-motivational variables in school settings: effects on academic performance in Spanish adolescents.

PubMed

Inglés, Cándido J; Torregrosa, María S; Rodríguez-Marín, Jesús; García del Castillo, José A; Gázquez, José J; García-Fernández, José M; Delgado, Beatriz

2013-01-01

The aim of the present study was to analyze: (a) the relationship between alcohol and tobacco use and academic performance, and (b) the predictive role of psycho-educational factors and alcohol and tobacco abuse on academic performance in a sample of 352 Spanish adolescents from grades 8 to 10 of Compulsory Secondary Education. The Self-Description Questionnaire-II, the Sydney Attribution Scale, and the Achievement Goal Tendencies Questionnaire were administered in order to analyze cognitive-motivational variables. Alcohol and tobacco abuse, sex, and grade retention were also measured using self-reported questions. Academic performance was measured by school records. Frequency analyses and logistic regression analyses were used. Frequency analyses revealed that students who abuse of tobacco and alcohol show a higher rate of poor academic performance. Logistic regression analyses showed that health behaviours, and educational and cognitive-motivational variables exert a different effect on academic performance depending on the academic area analyzed. These results point out that not only academic, but also health variables should be address to improve academic performance in adolescence.

Assessing LULC changes over Chilika Lake watershed in Eastern India using Driving Force Analysis

NASA Astrophysics Data System (ADS)

Jadav, S.; Syed, T. H.

2017-12-01

Rapid population growth and industrial development has brought about significant changes in Land Use Land Cover (LULC) of many developing countries in the world. This study investigates LULC changes in the Chilika Lake watershed of Eastern India for the period of 1988 to 2016. The methodology involves pre-processing and classification of Landsat satellite images using support vector machine (SVM) supervised classification algorithm. Results reveal that `Cropland', `Emergent Vegetation' and `Settlement' has expanded over the study period by 284.61 km², 106.83 km² and 98.83 km² respectively. Contemporaneously, `Lake Area', `Vegetation' and `Scrub Land' have decreased by 121.62 km², 96.05 km² and 80.29 km² respectively. This study also analyzes five major driving force variables of socio-economic and climatological factors triggering LULC changes through a bivariate logistic regression model. The outcome gives credible relative operating characteristics (ROC) value of 0.76 that indicate goodness fit of logistic regression model. In addition, independent variables like distance to drainage network and average annual rainfall have negative regression coefficient values that represent decreased rate of dependent variable (changed LULC) whereas independent variables (population density, distance to road and distance to railway) have positive regression coefficient indicates increased rate of changed LULC . Results from this study will be crucial for planning and restoration of this vital lake water body that has major implications over the society and environment at large.

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

Religiosity and decreased risk of substance use disorders: is the effect mediated by social support or mental health status?

PubMed Central

Harris, Katherine M.; Koenig, Harold G.; Han, Xiaotong; Sullivan, Greer; Mattox, Rhonda; Tang, Lingqi

2009-01-01

Objective The negative association between religiosity (religious beliefs and church attendance) and the likelihood of substance use disorders is well established, but the mechanism(s) remain poorly understood. We investigated whether this association was mediated by social support or mental health status. Method We utilized cross-sectional data from the 2002 National Survey on Drug Use and Health (n = 36,370). We first used logistic regression to regress any alcohol use in the past year on sociodemographic and religiosity variables. Then, among individuals who drank in the past year, we regressed past year alcohol abuse/dependence on sociodemographic and religiosity variables. To investigate whether social support mediated the association between religiosity and alcohol use and alcohol abuse/dependence we repeated the above models, adding the social support variables. To the extent that these added predictors modified the magnitude of the effect of the religiosity variables, we interpreted social support as a possible mediator. We also formally tested for mediation using path analysis. We investigated the possible mediating role of mental health status analogously. Parallel sets of analyses were conducted for any drug use, and drug abuse/dependence among those using any drugs as the dependent variables. Results The addition of social support and mental health status variables to logistic regression models had little effect on the magnitude of the religiosity coefficients in any of the models. While some of the tests of mediation were significant in the path analyses, the results were not always in the expected direction, and the magnitude of the effects was small. Conclusions The association between religiosity and decreased likelihood of a substance use disorder does not appear to be substantively mediated by either social support or mental health status. PMID:19714282

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.

The association between short interpregnancy interval and preterm birth in Louisiana: a comparison of methods.

PubMed

Howard, Elizabeth J; Harville, Emily; Kissinger, Patricia; Xiong, Xu

2013-07-01

There is growing interest in the application of propensity scores (PS) in epidemiologic studies, especially within the field of reproductive epidemiology. This retrospective cohort study assesses the impact of a short interpregnancy interval (IPI) on preterm birth and compares the results of the conventional logistic regression analysis with analyses utilizing a PS. The study included 96,378 singleton infants from Louisiana birth certificate data (1995-2007). Five regression models designed for methods comparison are presented. Ten percent (10.17 %) of all births were preterm; 26.83 % of births were from a short IPI. The PS-adjusted model produced a more conservative estimate of the exposure variable compared to the conventional logistic regression method (β-coefficient: 0.21 vs. 0.43), as well as a smaller standard error (0.024 vs. 0.028), odds ratio and 95 % confidence intervals [1.15 (1.09, 1.20) vs. 1.23 (1.17, 1.30)]. The inclusion of more covariate and interaction terms in the PS did not change the estimates of the exposure variable. This analysis indicates that PS-adjusted regression may be appropriate for validation of conventional methods in a large dataset with a fairly common outcome. PS's may be beneficial in producing more precise estimates, especially for models with many confounders and effect modifiers and where conventional adjustment with logistic regression is unsatisfactory. Short intervals between pregnancies are associated with preterm birth in this population, according to either technique. Birth spacing is an issue that women have some control over. Educational interventions, including birth control, should be applied during prenatal visits and following delivery.

The relationship between venture capital investment and macro economic variables via statistical computation method

NASA Astrophysics Data System (ADS)

Aygunes, Gunes

2017-07-01

The objective of this paper is to survey and determine the macroeconomic factors affecting the level of venture capital (VC) investments in a country. The literary depends on venture capitalists' quality and countries' venture capital investments. The aim of this paper is to give relationship between venture capital investment and macro economic variables via statistical computation method. We investigate the countries and macro economic variables. By using statistical computation method, we derive correlation between venture capital investments and macro economic variables. According to method of logistic regression model (logit regression or logit model), macro economic variables are correlated with each other in three group. Venture capitalists regard correlations as a indicator. Finally, we give correlation matrix of our results.

Dysglycemia, Glycemic Variability, and Outcome After Cardiac Arrest and Temperature Management at 33°C and 36°C.

PubMed

Borgquist, Ola; Wise, Matt P; Nielsen, Niklas; Al-Subaie, Nawaf; Cranshaw, Julius; Cronberg, Tobias; Glover, Guy; Hassager, Christian; Kjaergaard, Jesper; Kuiper, Michael; Smid, Ondrej; Walden, Andrew; Friberg, Hans

2017-08-01

Dysglycemia and glycemic variability are associated with poor outcomes in critically ill patients. Targeted temperature management alters blood glucose homeostasis. We investigated the association between blood glucose concentrations and glycemic variability and the neurologic outcomes of patients randomized to targeted temperature management at 33°C or 36°C after cardiac arrest. Post hoc analysis of the multicenter TTM-trial. Primary outcome of this analysis was neurologic outcome after 6 months, referred to as "Cerebral Performance Category." Thirty-six sites in Europe and Australia. All 939 patients with out-of-hospital cardiac arrest of presumed cardiac cause that had been included in the TTM-trial. Targeted temperature management at 33°C or 36°C. Nonparametric tests as well as multiple logistic regression and mixed effects logistic regression models were used. Median glucose concentrations on hospital admission differed significantly between Cerebral Performance Category outcomes (p < 0.0001). Hyper- and hypoglycemia were associated with poor neurologic outcome (p = 0.001 and p = 0.054). In the multiple logistic regression models, the median glycemic level was an independent predictor of poor Cerebral Performance Category (Cerebral Performance Category, 3-5) with an odds ratio (OR) of 1.13 in the adjusted model (p = 0.008; 95% CI, 1.03-1.24). It was also a predictor in the mixed model, which served as a sensitivity analysis to adjust for the multiple time points. The proportion of hyperglycemia was higher in the 33°C group compared with the 36°C group. Higher blood glucose levels at admission and during the first 36 hours, and higher glycemic variability, were associated with poor neurologic outcome and death. More patients in the 33°C treatment arm had hyperglycemia.

Data mining: Potential applications in research on nutrition and health.

PubMed

Batterham, Marijka; Neale, Elizabeth; Martin, Allison; Tapsell, Linda

2017-02-01

Data mining enables further insights from nutrition-related research, but caution is required. The aim of this analysis was to demonstrate and compare the utility of data mining methods in classifying a categorical outcome derived from a nutrition-related intervention. Baseline data (23 variables, 8 categorical) on participants (n = 295) in an intervention trial were used to classify participants in terms of meeting the criteria of achieving 10 000 steps per day. Results from classification and regression trees (CARTs), random forests, adaptive boosting, logistic regression, support vector machines and neural networks were compared using area under the curve (AUC) and error assessments. The CART produced the best model when considering the AUC (0.703), overall error (18%) and within class error (28%). Logistic regression also performed reasonably well compared to the other models (AUC 0.675, overall error 23%, within class error 36%). All the methods gave different rankings of variables' importance. CART found that body fat, quality of life using the SF-12 Physical Component Summary (PCS) and the cholesterol: HDL ratio were the most important predictors of meeting the 10 000 steps criteria, while logistic regression showed the SF-12PCS, glucose levels and level of education to be the most significant predictors (P ≤ 0.01). Differing outcomes suggest caution is required with a single data mining method, particularly in a dataset with nonlinear relationships and outliers and when exploring relationships that were not the primary outcomes of the research. © 2017 Dietitians Association of Australia.

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.

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.

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.

The arcsine is asinine: the analysis of proportions in ecology.

PubMed

Warton, David I; Hui, Francis K C

2011-01-01

The arcsine square root transformation has long been standard procedure when analyzing proportional data in ecology, with applications in data sets containing binomial and non-binomial response variables. Here, we argue that the arcsine transform should not be used in either circumstance. For binomial data, logistic regression has greater interpretability and higher power than analyses of transformed data. However, it is important to check the data for additional unexplained variation, i.e., overdispersion, and to account for it via the inclusion of random effects in the model if found. For non-binomial data, the arcsine transform is undesirable on the grounds of interpretability, and because it can produce nonsensical predictions. The logit transformation is proposed as an alternative approach to address these issues. Examples are presented in both cases to illustrate these advantages, comparing various methods of analyzing proportions including untransformed, arcsine- and logit-transformed linear models and logistic regression (with or without random effects). Simulations demonstrate that logistic regression usually provides a gain in power over other methods.

Estimating the causes of traffic accidents using logistic regression and discriminant analysis.

PubMed

Karacasu, Murat; Ergül, Barış; Altin Yavuz, Arzu

2014-01-01

Factors that affect traffic accidents have been analysed in various ways. In this study, we use the methods of logistic regression and discriminant analysis to determine the damages due to injury and non-injury accidents in the Eskisehir Province. Data were obtained from the accident reports of the General Directorate of Security in Eskisehir; 2552 traffic accidents between January and December 2009 were investigated regarding whether they resulted in injury. According to the results, the effects of traffic accidents were reflected in the variables. These results provide a wealth of information that may aid future measures toward the prevention of undesired results.

Distribution of cavity trees in midwestern old-growth and second-growth forests

Treesearch

Zhaofei Fan; Stephen R. Shifley; Martin A. Spetich; Frank R. Thompson; David R. Larsen

2003-01-01

We used classification and regression tree analysis to determine the primary variables associated with the occurrence of cavity trees and the hierarchical structure among those variables. We applied that information to develop logistic models predicting cavity tree probability as a function of diameter, species group, and decay class. Inventories of cavity abundance in...

Distribution of cavity trees in midwesternold-growth and second-growth forests

Treesearch

Zhaofei Fan; Stephen R. Shifley; Martin A. Spetich; Frank R., III Thompson; David R. Larsen

2003-01-01

We used classification and regression tree analysis to determine the primary variables associated with the occurrence of cavity trees and the hierarchical structure among those variables. We applied that information to develop logistic models predicting cavity tree probability as a function of diameter, species group, and decay class. Inventories of cavity abundance in...

Assessing West Virginia NIPF owner preferred forest management assistance topics and delivery methods

Treesearch

Daniel J. Magill; Rory F. Fraser; David W. McGill

2003-01-01

Four hundred and fourteen non-industrial private forest (NIPF) owners in West Virginia responded to a mail survey questionnaire assessing their forest management assistance topics and delivery methods of interest. Logistic regression was used to analyze 39 independent variables in relation to the dependent variables of wanting a specific topic of forestry assistance or...

Escaping Poverty: Rural Low-Income Mothers' Opportunity to Pursue Post-Secondary Education

ERIC Educational Resources Information Center

Woodford, Michelle; Mammen, Sheila

2010-01-01

Using human capital theory, this paper identifies the factors that may affect the opportunity for rural low-income mothers to pursue post-secondary education or training in order to escape poverty. Dependent variables used in the logistic regression model included micro-level household variables as well as the effects of state-wide welfare…

Personality predicts time to remission and clinical status in hypochondriasis during a 6-year follow-up.

PubMed

Greeven, Anja; van Balkom, Anton J L M; Spinhoven, Philip

2014-05-01

We aimed to investigate whether personality characteristics predict time to remission and psychiatric status. The follow-up was at most 6 years and was performed within the scope of a randomized controlled trial that investigated the efficacy of cognitive behavioral therapy, paroxetine, and placebo in hypochondriasis. The Life Chart Interview was administered to investigate for each year if remission had occurred. Personality was assessed at pretest by the Abbreviated Dutch Temperament and Character Inventory. Cox's regression models for recurrent events were compared with logistic regression models. Sixteen (36.4%) of 44 patients achieved remission during the follow-up period. Cox's regression yielded approximately the same results as the logistic regression. Being less harm avoidant and more cooperative were associated with a shorter time to remission and a remitted state after the follow-up period. Personality variables seem to be relevant for describing patients with a more chronic course of hypochondriacal complaints.

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.

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

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.

A case-control study of determinants for high and low dental caries prevalence in Nevada youth

PubMed Central

2010-01-01

Background The main purpose of this study was to compare the 30% of Nevada Youth who presented with the highest Decayed Missing and Filled Teeth (DMFT) index to a cohort who were caries free and to national NHANES data. Secondly, to explore the factors associated with higher caries prevalence in those with the highest DMFT scores compared to the caries-free group. Methods Over 4000 adolescents between ages 12 and 19 (Case Group: N = 2124; Control Group: N = 2045) received oral health screenings conducted in public/private middle and high schools in Nevada in 2008/2009 academic year. Caries prevalence was computed (Untreated decay scores [D-Score] and DMFT scores) for the 30% of Nevada Youth who presented with the highest DMFT score (case group) and compared to the control group (caries-free) and to national averages. Bivariate and multivariate logistic regression was used to analyze the relationship between selected variables and caries prevalence. Results A majority of the sample was non-Hispanic (62%), non-smokers (80%), and had dental insurance (70%). With the exception of gender, significant differences in mean D-scores were found in seven of the eight variables. All variables produced significant differences between the case and control groups in mean DMFT Scores. With the exception of smoking status, there were significant differences in seven of the eight variables in the bivariate logistic regression. All of the independent variables remained in the multivariate logistic regression model contributing significantly to over 40% of the variation in the increased DMFT status. The strongest predictors for the high DMFT status were racial background, age, fluoridated community, and applied sealants respectively. Gender, second hand smoke, insurance status, and tobacco use were significant, but to a lesser extent. Conclusions Findings from this study will aid in creating educational programs and other primary and secondary interventions to help promote oral health for Nevada youth, especially focusing on the subgroup that presents with the highest mean DMFT scores. PMID:21067620

Deciphering factors controlling groundwater arsenic spatial variability in Bangladesh

NASA Astrophysics Data System (ADS)

Tan, Z.; Yang, Q.; Zheng, C.; Zheng, Y.

2017-12-01

Elevated concentrations of geogenic arsenic in groundwater have been found in many countries to exceed 10 μg/L, the WHO's guideline value for drinking water. A common yet unexplained characteristic of groundwater arsenic spatial distribution is the extensive variability at various spatial scales. This study investigates factors influencing the spatial variability of groundwater arsenic in Bangladesh to improve the accuracy of models predicting arsenic exceedance rate spatially. A novel boosted regression tree method is used to establish a weak-learning ensemble model, which is compared to a linear model using a conventional stepwise logistic regression method. The boosted regression tree models offer the advantage of parametric interaction when big datasets are analyzed in comparison to the logistic regression. The point data set (n=3,538) of groundwater hydrochemistry with 19 parameters was obtained by the British Geological Survey in 2001. The spatial data sets of geological parameters (n=13) were from the Consortium for Spatial Information, Technical University of Denmark, University of East Anglia and the FAO, while the soil parameters (n=42) were from the Harmonized World Soil Database. The aforementioned parameters were regressed to categorical groundwater arsenic concentrations below or above three thresholds: 5 μg/L, 10 μg/L and 50 μg/L to identify respective controlling factors. Boosted regression tree method outperformed logistic regression methods in all three threshold levels in terms of accuracy, specificity and sensitivity, resulting in an improvement of spatial distribution map of probability of groundwater arsenic exceeding all three thresholds when compared to disjunctive-kriging interpolated spatial arsenic map using the same groundwater arsenic dataset. Boosted regression tree models also show that the most important controlling factors of groundwater arsenic distribution include groundwater iron content and well depth for all three thresholds. The probability of a well with iron content higher than 5mg/L to contain greater than 5 μg/L, 10 μg/L and 50 μg/L As is estimated to be more than 91%, 85% and 51%, respectively, while the probability of a well from depth more than 160m to contain more than 5 μg/L, 10 μg/L and 50 μg/L As is estimated to be less than 38%, 25% and 14%, respectively.

Factor complexity of crash occurrence: An empirical demonstration using boosted regression trees.

PubMed

Chung, Yi-Shih

2013-12-01

Factor complexity is a characteristic of traffic crashes. This paper proposes a novel method, namely boosted regression trees (BRT), to investigate the complex and nonlinear relationships in high-variance traffic crash data. The Taiwanese 2004-2005 single-vehicle motorcycle crash data are used to demonstrate the utility of BRT. Traditional logistic regression and classification and regression tree (CART) models are also used to compare their estimation results and external validities. Both the in-sample cross-validation and out-of-sample validation results show that an increase in tree complexity provides improved, although declining, classification performance, indicating a limited factor complexity of single-vehicle motorcycle crashes. The effects of crucial variables including geographical, time, and sociodemographic factors explain some fatal crashes. Relatively unique fatal crashes are better approximated by interactive terms, especially combinations of behavioral factors. BRT models generally provide improved transferability than conventional logistic regression and CART models. This study also discusses the implications of the results for devising safety policies. Copyright © 2012 Elsevier Ltd. All rights reserved.

Design, innovation, and rural creative places: Are the arts the cherry on top, or the secret sauce?

PubMed

Wojan, Timothy R; Nichols, Bonnie

2018-01-01

Creative class theory explains the positive relationship between the arts and commercial innovation as the mutual attraction of artists and other creative workers by an unobserved creative milieu. This study explores alternative theories for rural settings, by analyzing establishment-level survey data combined with data on the local arts scene. The study identifies the local contextual factors associated with a strong design orientation, and estimates the impact that a strong design orientation has on the local economy. Data on innovation and design come from a nationally representative sample of establishments in tradable industries. Latent class analysis allows identifying unobserved subpopulations comprised of establishments with different design and innovation orientations. Logistic regression allows estimating the association between an establishment's design orientation and local contextual factors. A quantile instrumental variable regression allows assessing the robustness of the logistic regression results with respect to endogeneity. An estimate of design orientation at the local level derived from the survey is used to examine variation in economic performance during the period of recovery from the Great Recession (2010-2014). Three distinct innovation (substantive, nominal, and non-innovators) and design orientations (design-integrated, "design last finish," and no systematic approach to design) are identified. Innovation- and design-intensive establishments were identified in both rural and urban areas. Rural design-integrated establishments tended to locate in counties with more highly educated workforces and containing at least one performing arts organization. A quantile instrumental variable regression confirmed that the logistic regression result is robust to endogeneity concerns. Finally, rural areas characterized by design-integrated establishments experienced faster growth in wages relative to rural areas characterized by establishments using no systematic approach to design.

Design, innovation, and rural creative places: Are the arts the cherry on top, or the secret sauce?

PubMed Central

Nichols, Bonnie

2018-01-01

Objective Creative class theory explains the positive relationship between the arts and commercial innovation as the mutual attraction of artists and other creative workers by an unobserved creative milieu. This study explores alternative theories for rural settings, by analyzing establishment-level survey data combined with data on the local arts scene. The study identifies the local contextual factors associated with a strong design orientation, and estimates the impact that a strong design orientation has on the local economy. Method Data on innovation and design come from a nationally representative sample of establishments in tradable industries. Latent class analysis allows identifying unobserved subpopulations comprised of establishments with different design and innovation orientations. Logistic regression allows estimating the association between an establishment’s design orientation and local contextual factors. A quantile instrumental variable regression allows assessing the robustness of the logistic regression results with respect to endogeneity. An estimate of design orientation at the local level derived from the survey is used to examine variation in economic performance during the period of recovery from the Great Recession (2010–2014). Results Three distinct innovation (substantive, nominal, and non-innovators) and design orientations (design-integrated, “design last finish,” and no systematic approach to design) are identified. Innovation- and design-intensive establishments were identified in both rural and urban areas. Rural design-integrated establishments tended to locate in counties with more highly educated workforces and containing at least one performing arts organization. A quantile instrumental variable regression confirmed that the logistic regression result is robust to endogeneity concerns. Finally, rural areas characterized by design-integrated establishments experienced faster growth in wages relative to rural areas characterized by establishments using no systematic approach to design. PMID:29489884

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.

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

PubMed

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

2018-04-01

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

Impact of low vision on employment.

PubMed

Mojon-Azzi, Stefania M; Sousa-Poza, Alfonso; Mojon, Daniel S

2010-01-01

We investigated the influence of self-reported corrected eyesight on several variables describing the perception by employees and self-employed persons of their employment. Our study was based on data from the Survey of Health, Ageing and Retirement in Europe (SHARE). SHARE is a multidisciplinary, cross-national database of microdata on health, socioeconomic status, social and family networks, collected on 31,115 individuals in 11 European countries and in Israel. With the help of ordered logistic regressions and binary logistic regressions, we analyzed the influence of perceived visual impairment--corrected by 19 covariates capturing socioeconomic and health-related factors--on 10 variables describing the respondents' employment situation. Based on data covering 10,340 working individuals, the results of the logistic and ordered regressions indicate that respondents with lower levels of self-reported general eyesight were significantly less satisfied with their jobs, felt they had less freedom to decide, less opportunity to develop new skills, less support in difficult situations, less recognition for their work, and an inadequate salary. Respondents with a lower eyesight level more frequently reported that they feared their health might limit their ability to work before regular retirement age and more often indicated that they were seeking early retirement. Analysis of this dataset from 12 countries demonstrates the strong impact of self-reported visual impairment on individual employment, and therefore on job satisfaction, productivity, and well-being. Copyright © 2010 S. Karger AG, Basel.

Cross-Sectional and Panel Data Analyses of an Incompletely Observed Variable Derived from the Nonrandomized Method for Surveying Sensitive Questions

ERIC Educational Resources Information Center

Yamaguchi, Kazuo

2016-01-01

This article describes (1) the survey methodological and statistical characteristics of the nonrandomized method for surveying sensitive questions for both cross-sectional and panel survey data and (2) the way to use the incompletely observed variable obtained from this survey method in logistic regression and in loglinear and log-multiplicative…

Do Variables Associated with Quality Child Care Programs Predict the Inclusion of Children with Disabilities?

ERIC Educational Resources Information Center

Essa, Eva L.; Bennett, Patrick R.; Burnham, Melissa M.; Martin, Sally S.; Bingham, Ann; Allred, Keith

2008-01-01

Little research has been carried out on the inclusion of children with special needs in child care. The purpose of this study was to determine what variables predict the inclusion of children with disabilities in centers and home care. Logistic regression was used to examine the association of several indicators of quality child care and…

Cognitive and Behavioural Correlates of Non-Adherence to HIV Anti-Retroviral Therapy: Theoretical and Practical Insight for Clinical Psychology and Health Psychology

ERIC Educational Resources Information Center

Begley, Kim; McLaws, Mary-Louise; Ross, Michael W.; Gold, Julian

2008-01-01

This cross-sectional study identified variables associated with protease inhibitor (PI) non-adherence in 179 patients taking anti-retroviral therapy. Univariate analyses identified 11 variables associated with PI non-adherence. Multiple logistic regression modelling identified three predictors of PI non-adherence: low adherence self-efficacy and…

The Impact of Household Heads' Education Levels on the Poverty Risk: The Evidence from Turkey

ERIC Educational Resources Information Center

Bilenkisi, Fikret; Gungor, Mahmut Sami; Tapsin, Gulcin

2015-01-01

This study aims to analyze the relationship between the education levels of household heads and the poverty risk of households in Turkey. The logistic regression models have been estimated with the poverty risk of a household as a dependent variable and a set of educational levels as explanatory variables for all households. There are subgroups of…

Predictors of Dropout by Female Obese Patients Treated with a Group Cognitive Behavioral Therapy to Promote Weight Loss.

PubMed

Sawamoto, Ryoko; Nozaki, Takehiro; Furukawa, Tomokazu; Tanahashi, Tokusei; Morita, Chihiro; Hata, Tomokazu; Komaki, Gen; Sudo, Nobuyuki

2016-01-01

To investigate predictors of dropout from a group cognitive behavioral therapy (CBT) intervention for overweight or obese women. 119 overweight and obese Japanese women aged 25-65 years who attended an outpatient weight loss intervention were followed throughout the 7-month weight loss phase. Somatic characteristics, socioeconomic status, obesity-related diseases, diet and exercise habits, and psychological variables (depression, anxiety, self-esteem, alexithymia, parenting style, perfectionism, and eating attitude) were assessed at baseline. Significant variables, extracted by univariate statistical analysis, were then used as independent variables in a stepwise multiple logistic regression analysis with dropout as the dependent variable. 90 participants completed the weight loss phase, giving a dropout rate of 24.4%. The multiple logistic regression analysis demonstrated that compared to completers the dropouts had significantly stronger body shape concern, tended to not have jobs, perceived their mothers to be less caring, and were more disorganized in temperament. Of all these factors, the best predictor of dropout was shape concern. Shape concern, job condition, parenting care, and organization predicted dropout from the group CBT weight loss intervention for overweight or obese Japanese women. © 2016 S. Karger GmbH, Freiburg.

Predictors of Dropout by Female Obese Patients Treated with a Group Cognitive Behavioral Therapy to Promote Weight Loss

PubMed Central

Sawamoto, Ryoko; Nozaki, Takehiro; Furukawa, Tomokazu; Tanahashi, Tokusei; Morita, Chihiro; Hata, Tomokazu; Komaki, Gen; Sudo, Nobuyuki

2016-01-01

Objective To investigate predictors of dropout from a group cognitive behavioral therapy (CBT) intervention for overweight or obese women. Methods 119 overweight and obese Japanese women aged 25-65 years who attended an outpatient weight loss intervention were followed throughout the 7-month weight loss phase. Somatic characteristics, socioeconomic status, obesity-related diseases, diet and exercise habits, and psychological variables (depression, anxiety, self-esteem, alexithymia, parenting style, perfectionism, and eating attitude) were assessed at baseline. Significant variables, extracted by univariate statistical analysis, were then used as independent variables in a stepwise multiple logistic regression analysis with dropout as the dependent variable. Results 90 participants completed the weight loss phase, giving a dropout rate of 24.4%. The multiple logistic regression analysis demonstrated that compared to completers the dropouts had significantly stronger body shape concern, tended to not have jobs, perceived their mothers to be less caring, and were more disorganized in temperament. Of all these factors, the best predictor of dropout was shape concern. Conclusion Shape concern, job condition, parenting care, and organization predicted dropout from the group CBT weight loss intervention for overweight or obese Japanese women. PMID:26745715

Bayesian data fusion for spatial prediction of categorical variables in environmental sciences

NASA Astrophysics Data System (ADS)

Gengler, Sarah; Bogaert, Patrick

2014-12-01

First developed to predict continuous variables, Bayesian Maximum Entropy (BME) has become a complete framework in the context of space-time prediction since it has been extended to predict categorical variables and mixed random fields. This method proposes solutions to combine several sources of data whatever the nature of the information. However, the various attempts that were made for adapting the BME methodology to categorical variables and mixed random fields faced some limitations, as a high computational burden. The main objective of this paper is to overcome this limitation by generalizing the Bayesian Data Fusion (BDF) theoretical framework to categorical variables, which is somehow a simplification of the BME method through the convenient conditional independence hypothesis. The BDF methodology for categorical variables is first described and then applied to a practical case study: the estimation of soil drainage classes using a soil map and point observations in the sandy area of Flanders around the city of Mechelen (Belgium). The BDF approach is compared to BME along with more classical approaches, as Indicator CoKringing (ICK) and logistic regression. Estimators are compared using various indicators, namely the Percentage of Correctly Classified locations (PCC) and the Average Highest Probability (AHP). Although BDF methodology for categorical variables is somehow a simplification of BME approach, both methods lead to similar results and have strong advantages compared to ICK and logistic regression.

Myxomatosis in wild rabbit: design of control programs in Mediterranean ecosystems.

PubMed

García-Bocanegra, Ignacio; Astorga, Rafael Jesús; Napp, Sebastián; Casal, Jordi; Huerta, Belén; Borge, Carmen; Arenas, Antonio

2010-01-01

A cross-sectional study was carried out in natural wild rabbit (Oryctolagus cuniculus) populations from southern Spain to identify risk factors associated to myxoma virus infection. Blood samples from 619 wild rabbits were collected, and questionnaires which included variables related to host, disease, game management and environment were completed. A logistic regression analysis was conducted to investigate the associations between myxomatosis seropositivity (dependent variable) across 7 hunting estates and an extensive set of explanatory variables obtained from the questionnaires. The prevalence of antibodies against myxomatosis virus was 56.4% (95% CI: 52.5-60.3) and ranged between 21.4% (95% CI: 9.0-33.8) and 70.2% (95% CI: 58.3-82.1) among the different sampling areas. The logistic regression analysis showed that autumn (OR 9.0), high abundance of mosquitoes (OR 8.2), reproductive activity (OR 4.1), warren's insecticide treatment (OR 3.7), rabbit haemorrhagic disease (RHD) seropositivity (OR 2.6), high hunting pressure (OR 6.3) and sheep presence (OR 6.4) were associated with seropositivity to myxomatosis. Based on the results, diverse management measures for myxomatosis control are proposed.

To resuscitate or not to resuscitate: a logistic regression analysis of physician-related variables influencing the decision.

PubMed

Einav, Sharon; Alon, Gady; Kaufman, Nechama; Braunstein, Rony; Carmel, Sara; Varon, Joseph; Hersch, Moshe

2012-09-01

To determine whether variables in physicians' backgrounds influenced their decision to forego resuscitating a patient they did not previously know. Questionnaire survey of a convenience sample of 204 physicians working in the departments of internal medicine, anaesthesiology and cardiology in 11 hospitals in Israel. Twenty per cent of the participants had elected to forego resuscitating a patient they did not previously know without additional consultation. Physicians who had more frequently elected to forego resuscitation had practised medicine for more than 5 years (p=0.013), estimated the number of resuscitations they had performed as being higher (p=0.009), and perceived their experience in resuscitation as sufficient (p=0.001). The variable that predicted the outcome of always performing resuscitation in the logistic regression model was less than 5 years of experience in medicine (OR 0.227, 95% CI 0.065 to 0.793; p=0.02). Physicians' level of experience may affect the probability of a patient's receiving resuscitation, whereas the physicians' personal beliefs and values did not seem to affect this outcome.

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

[Associated factors in newborns with intrauterine growth retardation].

PubMed

Thompson-Chagoyán, Oscar C; Vega-Franco, Leopoldo

2008-01-01

To identify the risk factors implicated in the intrauterine growth retardation (IUGR) of neonates born in a social security institution. Case controls design study in 376 neonates: 188 with IUGR (weight < 10 percentile) and 188 without IUGR. When they born, information about 30 variables of risk for IUGR were obtained from mothers. Risk analysis and logistical regression (stepwise) were used. Odds ratios were significant for 12 of the variables. The model obtains by stepwise regression included: weight gain at pregnancy, prenatal care attendance, toxemia, chocolate ingestion, father's weight, and the environmental house. Must of the variables included in the model are related to socioeconomic disadvantages related to the risk of RCIU in the population.

Spatiotemporal variability of urban growth factors: A global and local perspective on the megacity of Mumbai

NASA Astrophysics Data System (ADS)

Shafizadeh-Moghadam, Hossein; Helbich, Marco

2015-03-01

The rapid growth of megacities requires special attention among urban planners worldwide, and particularly in Mumbai, India, where growth is very pronounced. To cope with the planning challenges this will bring, developing a retrospective understanding of urban land-use dynamics and the underlying driving-forces behind urban growth is a key prerequisite. This research uses regression-based land-use change models - and in particular non-spatial logistic regression models (LR) and auto-logistic regression models (ALR) - for the Mumbai region over the period 1973-2010, in order to determine the drivers behind spatiotemporal urban expansion. Both global models are complemented by a local, spatial model, the so-called geographically weighted logistic regression (GWLR) model, one that explicitly permits variations in driving-forces across space. The study comes to two main conclusions. First, both global models suggest similar driving-forces behind urban growth over time, revealing that LRs and ALRs result in estimated coefficients with comparable magnitudes. Second, all the local coefficients show distinctive temporal and spatial variations. It is therefore concluded that GWLR aids our understanding of urban growth processes, and so can assist context-related planning and policymaking activities when seeking to secure a sustainable urban future.

Socioeconomic and Cultural Correlates of Diet Quality in the Canadian Arctic: Results from the 2007-2008 Inuit Health Survey.

PubMed

Galloway, Tracey; Johnson-Down, Louise; Egeland, Grace M

2015-09-01

We examined the impact of socioeconomic and cultural factors on dietary quality in adult Inuit living in the Canadian Arctic. Interviews and a 24-h dietary recall were administered to 805 men and 1292 women from Inuit regions in the Canadian Arctic. We examined the effect of age, sex, education, income, employment, and cultural variables on respondents' energy, macronutrient intake, sodium/potassium ratio, and healthy eating index. Logistic regression was used to assess the impact of socioeconomic status (SES) on diet quality indicators. Age was positively associated with traditional food (TF) consumption and greater energy from protein but negatively associated with total energy and fibre intake. Associations between SES and diet quality differed considerably between men and women and there was considerable regional variability in diet quality measures. Age and cultural variables were significant predictors of diet quality in logistic regression. Increased age and use of the Inuit language in the home were the most significant predictors of TF consumption. Our findings are consistent with studies reporting a nutrition transition in circumpolar Inuit. We found considerable variability in diet quality and complex interaction between SES and cultural variables producing mixed effects that differ by age and gender.

Association Between Socio-Demographic Background and Self-Esteem of University Students.

PubMed

Haq, Muhammad Ahsan Ul

2016-12-01

The purpose of this study was to scrutinize self-esteem of university students and explore association of self-esteem with academic achievement, gender and other factors. A sample of 346 students was selected from Punjab University, Lahore Pakistan. Rosenberg self-esteem scale with demographic variables was used for data collection. Besides descriptive statistics, binary logistic regression and t test were used for analysing the data. Significant gender difference was observed, self-esteem was significantly higher in males than females. Logistic regression indicates that age, medium of instruction, family income, student monthly expenditures, GPA and area of residence has direct effect on self-esteem; while number of siblings showed an inverse effect.

Diabetic Prevalence in Bangladesh: The Role of Some Associated Demographic and Socioeconomic Characteristics

NASA Astrophysics Data System (ADS)

Imam, Tasneem

2012-12-01

The study attempts at examining the association of a few selected socio-economic and demographic characteristics on diabetic prevalence. Nationally representative data from BIRDEM 2000 have been used to meet the objectives of the study. Cross tabulation, Chi-square and logistic regression analysis have been used to portray the necessary associations. Chi- square reveals significant relationship between diabetic prevalence and all the selected demographic and socio-economic variables except ìeducationî while logistic regression analysis shows no significant contribution of ìageî and ìeducationî in diabetic prevalence. It has to be noted that, this paper dealt with all the three types of diabetes- Type 1, Type 2 and Gestational.

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.

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.

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).

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.

Methods for identifying SNP interactions: a review on variations of Logic Regression, Random Forest and Bayesian logistic regression.

PubMed

Chen, Carla Chia-Ming; Schwender, Holger; Keith, Jonathan; Nunkesser, Robin; Mengersen, Kerrie; Macrossan, Paula

2011-01-01

Due to advancements in computational ability, enhanced technology and a reduction in the price of genotyping, more data are being generated for understanding genetic associations with diseases and disorders. However, with the availability of large data sets comes the inherent challenges of new methods of statistical analysis and modeling. Considering a complex phenotype may be the effect of a combination of multiple loci, various statistical methods have been developed for identifying genetic epistasis effects. Among these methods, logic regression (LR) is an intriguing approach incorporating tree-like structures. Various methods have built on the original LR to improve different aspects of the model. In this study, we review four variations of LR, namely Logic Feature Selection, Monte Carlo Logic Regression, Genetic Programming for Association Studies, and Modified Logic Regression-Gene Expression Programming, and investigate the performance of each method using simulated and real genotype data. We contrast these with another tree-like approach, namely Random Forests, and a Bayesian logistic regression with stochastic search variable selection.

A regularization corrected score method for nonlinear regression models with covariate error.

PubMed

Zucker, David M; Gorfine, Malka; Li, Yi; Tadesse, Mahlet G; Spiegelman, Donna

2013-03-01

Many regression analyses involve explanatory variables that are measured with error, and failing to account for this error is well known to lead to biased point and interval estimates of the regression coefficients. We present here a new general method for adjusting for covariate error. Our method consists of an approximate version of the Stefanski-Nakamura corrected score approach, using the method of regularization to obtain an approximate solution of the relevant integral equation. We develop the theory in the setting of classical likelihood models; this setting covers, for example, linear regression, nonlinear regression, logistic regression, and Poisson regression. The method is extremely general in terms of the types of measurement error models covered, and is a functional method in the sense of not involving assumptions on the distribution of the true covariate. We discuss the theoretical properties of the method and present simulation results in the logistic regression setting (univariate and multivariate). For illustration, we apply the method to data from the Harvard Nurses' Health Study concerning the relationship between physical activity and breast cancer mortality in the period following a diagnosis of breast cancer. Copyright © 2013, The International Biometric Society.

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.

Country logistics performance and disaster impact.

PubMed

Vaillancourt, Alain; Haavisto, Ira

2016-04-01

The aim of this paper is to deepen the understanding of the relationship between country logistics performance and disaster impact. The relationship is analysed through correlation analysis and regression models for 117 countries for the years 2007 to 2012 with disaster impact variables from the International Disaster Database (EM-DAT) and logistics performance indicators from the World Bank. The results show a significant relationship between country logistics performance and disaster impact overall and for five out of six specific logistic performance indicators. These specific indicators were further used to explore the relationship between country logistic performance and disaster impact for three specific disaster types (epidemic, flood and storm). The findings enhance the understanding of the role of logistics in a humanitarian context with empirical evidence of the importance of country logistics performance in disaster response operations. © 2016 The Author(s). Disasters © Overseas Development Institute, 2016.

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.

Speed and Cardiac Recovery Variables Predict the Probability of Elimination in Equine Endurance Events

PubMed Central

Younes, Mohamed; Robert, Céline; Cottin, François; Barrey, Eric

2015-01-01

Nearly 50% of the horses participating in endurance events are eliminated at a veterinary examination (a vet gate). Detecting unfit horses before a health problem occurs and treatment is required is a challenge for veterinarians but is essential for improving equine welfare. We hypothesized that it would be possible to detect unfit horses earlier in the event by measuring heart rate recovery variables. Hence, the objective of the present study was to compute logistic regressions of heart rate, cardiac recovery time and average speed data recorded at the previous vet gate (n-1) and thus predict the probability of elimination during successive phases (n and following) in endurance events. Speed and heart rate data were extracted from an electronic database of endurance events (80–160 km in length) organized in four countries. Overall, 39% of the horses that started an event were eliminated—mostly due to lameness (64%) or metabolic disorders (15%). For each vet gate, logistic regressions of explanatory variables (average speed, cardiac recovery time and heart rate measured at the previous vet gate) and categorical variables (age and/or event distance) were computed to estimate the probability of elimination. The predictive logistic regressions for vet gates 2 to 5 correctly classified between 62% and 86% of the eliminated horses. The robustness of these results was confirmed by high areas under the receiving operating characteristic curves (0.68–0.84). Overall, a horse has a 70% chance of being eliminated at the next gate if its cardiac recovery time is longer than 11 min at vet gate 1 or 2, or longer than 13 min at vet gates 3 or 4. Heart rate recovery and average speed variables measured at the previous vet gate(s) enabled us to predict elimination at the following vet gate. These variables should be checked at each veterinary examination, in order to detect unfit horses as early as possible. Our predictive method may help to improve equine welfare and ethical considerations in endurance events. PMID:26322506

Speed and Cardiac Recovery Variables Predict the Probability of Elimination in Equine Endurance Events.

PubMed

Younes, Mohamed; Robert, Céline; Cottin, François; Barrey, Eric

2015-01-01

Nearly 50% of the horses participating in endurance events are eliminated at a veterinary examination (a vet gate). Detecting unfit horses before a health problem occurs and treatment is required is a challenge for veterinarians but is essential for improving equine welfare. We hypothesized that it would be possible to detect unfit horses earlier in the event by measuring heart rate recovery variables. Hence, the objective of the present study was to compute logistic regressions of heart rate, cardiac recovery time and average speed data recorded at the previous vet gate (n-1) and thus predict the probability of elimination during successive phases (n and following) in endurance events. Speed and heart rate data were extracted from an electronic database of endurance events (80-160 km in length) organized in four countries. Overall, 39% of the horses that started an event were eliminated--mostly due to lameness (64%) or metabolic disorders (15%). For each vet gate, logistic regressions of explanatory variables (average speed, cardiac recovery time and heart rate measured at the previous vet gate) and categorical variables (age and/or event distance) were computed to estimate the probability of elimination. The predictive logistic regressions for vet gates 2 to 5 correctly classified between 62% and 86% of the eliminated horses. The robustness of these results was confirmed by high areas under the receiving operating characteristic curves (0.68-0.84). Overall, a horse has a 70% chance of being eliminated at the next gate if its cardiac recovery time is longer than 11 min at vet gate 1 or 2, or longer than 13 min at vet gates 3 or 4. Heart rate recovery and average speed variables measured at the previous vet gate(s) enabled us to predict elimination at the following vet gate. These variables should be checked at each veterinary examination, in order to detect unfit horses as early as possible. Our predictive method may help to improve equine welfare and ethical considerations in endurance events.

GIS-based rare events logistic regression for mineral prospectivity mapping

NASA Astrophysics Data System (ADS)

Xiong, Yihui; Zuo, Renguang

2018-02-01

Mineralization is a special type of singularity event, and can be considered as a rare event, because within a specific study area the number of prospective locations (1s) are considerably fewer than the number of non-prospective locations (0s). In this study, GIS-based rare events logistic regression (RELR) was used to map the mineral prospectivity in the southwestern Fujian Province, China. An odds ratio was used to measure the relative importance of the evidence variables with respect to mineralization. The results suggest that formations, granites, and skarn alterations, followed by faults and aeromagnetic anomaly are the most important indicators for the formation of Fe-related mineralization in the study area. The prediction rate and the area under the curve (AUC) values show that areas with higher probability have a strong spatial relationship with the known mineral deposits. Comparing the results with original logistic regression (OLR) demonstrates that the GIS-based RELR performs better than OLR. The prospectivity map obtained in this study benefits the search for skarn Fe-related mineralization in the study area.

Sparse Logistic Regression for Diagnosis of Liver Fibrosis in Rat by Using SCAD-Penalized Likelihood

PubMed Central

Yan, Fang-Rong; Lin, Jin-Guan; Liu, Yu

2011-01-01

The objective of the present study is to find out the quantitative relationship between progression of liver fibrosis and the levels of certain serum markers using mathematic model. We provide the sparse logistic regression by using smoothly clipped absolute deviation (SCAD) penalized function to diagnose the liver fibrosis in rats. Not only does it give a sparse solution with high accuracy, it also provides the users with the precise probabilities of classification with the class information. In the simulative case and the experiment case, the proposed method is comparable to the stepwise linear discriminant analysis (SLDA) and the sparse logistic regression with least absolute shrinkage and selection operator (LASSO) penalty, by using receiver operating characteristic (ROC) with bayesian bootstrap estimating area under the curve (AUC) diagnostic sensitivity for selected variable. Results show that the new approach provides a good correlation between the serum marker levels and the liver fibrosis induced by thioacetamide (TAA) in rats. Meanwhile, this approach might also be used in predicting the development of liver cirrhosis. PMID:21716672

Impact of wearing fixed orthodontic appliances on quality of life among adolescents: Case-control study.

PubMed

Costa, Andréa A; Serra-Negra, Júnia M; Bendo, Cristiane B; Pordeus, Isabela A; Paiva, Saul M

2016-01-01

To investigate the impact of wearing a fixed orthodontic appliance on oral health-related quality of life (OHRQoL) among adolescents. A case-control study (1 ∶ 2) was carried out with a population-based randomized sample of 327 adolescents aged 11 to 14 years enrolled at public and private schools in the City of Brumadinho, southeast of Brazil. The case group (n  =  109) was made up of adolescents with a high negative impact on OHRQoL, and the control group (n  =  218) was made up of adolescents with a low negative impact. The outcome variable was the impact on OHRQoL measured by the Brazilian version of the Child Perceptions Questionnaire (CPQ 11-14) - Impact Short Form (ISF:16). The main independent variable was wearing fixed orthodontic appliances. Malocclusion and the type of school were identified as possible confounding variables. Bivariate and multiple conditional logistic regressions were employed in the statistical analysis. A multiple conditional logistic regression model demonstrated that adolescents wearing fixed orthodontic appliances had a 4.88-fold greater chance of presenting high negative impact on OHRQoL (95% CI: 2.93-8.13; P < .001) than those who did not wear fixed orthodontic appliances. A bivariate conditional logistic regression demonstrated that malocclusion was significantly associated with OHRQoL (P  =  .017), whereas no statistically significant association was found between the type of school and OHRQoL (P  =  .108). Adolescents who wore fixed orthodontic appliances had a greater chance of reporting a negative impact on OHRQoL than those who did not wear such appliances.

Prevalence of consistent condom use with various types of sex partners and associated factors among money boys in Changsha, China.

PubMed

Wang, Lian-Hong; Yan, Jin; Yang, Guo-Li; Long, Shuo; Yu, Yong; Wu, Xi-Lin

2015-04-01

Money boys with inconsistent condom use (less than 100% of the time) are at high risk of infection by human immunodeficiency virus (HIV) or sexually transmitted infection (STI), but relatively little research has examined their risk behaviors. We investigated the prevalence of consistent condom use (100% of the time) and associated factors among money boys. A cross-sectional study using a structured questionnaire was conducted among money boys in Changsha, China, between July 2012 and January 2013. Independent variables included socio-demographic data, substance abuse history, work characteristics, and self-reported HIV and STI history. Dependent variables included the consistent condom use with different types of sex partners. Among the participants, 82.4% used condoms consistently with male clients, 80.2% with male sex partners, and 77.1% with female sex partners in the past 3 months. A multiple stepwise logistic regression model identified four statistically significant factors associated with lower likelihoods of consistent condom use with male clients: age group, substance abuse, lack of an "employment" arrangement, and having no HIV test within the prior 6 months. In a similar model, only one factor associated significantly with lower likelihoods of consistent condom use with male sex partners was identified in multiple stepwise logistic regression analyses: having no HIV test within the prior six months. As for female sex partners, two significant variables were statistically significant in the multiple stepwise logistic regression analysis: having no HIV test within the prior 6 months and having STI history. Interventions which are linked with more realistic and acceptable HIV prevention methods are greatly warranted and should increase risk awareness and the behavior of consistent condom use in both commercial and personal relationship. © 2015 International Society for Sexual Medicine.

Principal component analysis-based pattern analysis of dose-volume histograms and influence on rectal toxicity.

PubMed

Söhn, Matthias; Alber, Markus; Yan, Di

2007-09-01

The variability of dose-volume histogram (DVH) shapes in a patient population can be quantified using principal component analysis (PCA). We applied this to rectal DVHs of prostate cancer patients and investigated the correlation of the PCA parameters with late bleeding. PCA was applied to the rectal wall DVHs of 262 patients, who had been treated with a four-field box, conformal adaptive radiotherapy technique. The correlated changes in the DVH pattern were revealed as "eigenmodes," which were ordered by their importance to represent data set variability. Each DVH is uniquely characterized by its principal components (PCs). The correlation of the first three PCs and chronic rectal bleeding of Grade 2 or greater was investigated with uni- and multivariate logistic regression analyses. Rectal wall DVHs in four-field conformal RT can primarily be represented by the first two or three PCs, which describe approximately 94% or 96% of the DVH shape variability, respectively. The first eigenmode models the total irradiated rectal volume; thus, PC1 correlates to the mean dose. Mode 2 describes the interpatient differences of the relative rectal volume in the two- or four-field overlap region. Mode 3 reveals correlations of volumes with intermediate doses ( approximately 40-45 Gy) and volumes with doses >70 Gy; thus, PC3 is associated with the maximal dose. According to univariate logistic regression analysis, only PC2 correlated significantly with toxicity. However, multivariate logistic regression analysis with the first two or three PCs revealed an increased probability of bleeding for DVHs with more than one large PC. PCA can reveal the correlation structure of DVHs for a patient population as imposed by the treatment technique and provide information about its relationship to toxicity. It proves useful for augmenting normal tissue complication probability modeling approaches.

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.

Individual relocation decisions after tornadoes: a multi-level analysis.

PubMed

Cong, Zhen; Nejat, Ali; Liang, Daan; Pei, Yaolin; Javid, Roxana J

2018-04-01

This study examines how multi-level factors affected individuals' relocation decisions after EF4 and EF5 (Enhanced Fujita Tornado Intensity Scale) tornadoes struck the United States in 2013. A telephone survey was conducted with 536 respondents, including oversampled older adults, one year after these two disaster events. Respondents' addresses were used to associate individual information with block group-level variables recorded by the American Community Survey. Logistic regression revealed that residential damage and homeownership are important predictors of relocation. There was also significant interaction between these two variables, indicating less difference between homeowners and renters at higher damage levels. Homeownership diminished the likelihood of relocation among younger respondents. Random effects logistic regression found that the percentage of homeownership and of higher income households in the community buffered the effect of damage on relocation; the percentage of older adults reduced the likelihood of this group relocating. The findings are assessed from the standpoint of age difference, policy implications, and social capital and vulnerability. © 2018 The Author(s). Disasters © Overseas Development Institute, 2018.

Problematic Use of Video Games and Substance Abuse in Early Adolescence: A Cross-sectional Study.

PubMed

Gallimberti, Luigi; Buja, Alessandra; Chindamo, Sonia; Rabensteiner, Andrea; Terraneo, Alberto; Marini, Elena; Pérez, Luis Javier Gómez; Baldo, Vincenzo

2016-09-01

Problematic use of video games (PUVG) is associated with substance use in middle school students. The aim of our study was to examine the association between PUVG and substance abuse in children and young adolescents. A survey was conducted during the 2014-2015 school year in Padua (northeastern Italy). The sample consisted of 1156 students in grades 6 to 8. A multivariate logistic regression model was applied to seek associations between PUVG (dependent variable) and independent variables. Logistic regression showed that lifetime drunkenness, combined energy drink and alcohol consumption (lifetime), reading comics, and disrespect for rules increased the odds of PUVG, whereas playing competitive sport, eating fruit and/or vegetables daily, finding it easy to talk with fathers and being female lowered the odds of PUVG in early adolescence. Our findings show that PUVG is more likely in young adolescents at risk of substance abuse. Prevention schemes focusing on early adolescence should be based on a multicomponent intervention strategy that takes PUVG into account.

Optimizing landslide susceptibility zonation: Effects of DEM spatial resolution and slope unit delineation on logistic regression models

NASA Astrophysics Data System (ADS)

Schlögel, R.; Marchesini, I.; Alvioli, M.; Reichenbach, P.; Rossi, M.; Malet, J.-P.

2018-01-01

We perform landslide susceptibility zonation with slope units using three digital elevation models (DEMs) of varying spatial resolution of the Ubaye Valley (South French Alps). In so doing, we applied a recently developed algorithm automating slope unit delineation, given a number of parameters, in order to optimize simultaneously the partitioning of the terrain and the performance of a logistic regression susceptibility model. The method allowed us to obtain optimal slope units for each available DEM spatial resolution. For each resolution, we studied the susceptibility model performance by analyzing in detail the relevance of the conditioning variables. The analysis is based on landslide morphology data, considering either the whole landslide or only the source area outline as inputs. The procedure allowed us to select the most useful information, in terms of DEM spatial resolution, thematic variables and landslide inventory, in order to obtain the most reliable slope unit-based landslide susceptibility assessment.

Quantitative appraisal of the Amyloid Imaging Taskforce appropriate use criteria for amyloid-PET.

PubMed

Altomare, Daniele; Ferrari, Clarissa; Festari, Cristina; Guerra, Ugo Paolo; Muscio, Cristina; Padovani, Alessandro; Frisoni, Giovanni B; Boccardi, Marina

2018-04-18

We test the hypothesis that amyloid-PET prescriptions, considered appropriate based on the Amyloid Imaging Taskforce (AIT) criteria, lead to greater clinical utility than AIT-inappropriate prescriptions. We compared the clinical utility between patients who underwent amyloid-PET appropriately or inappropriately and among the subgroups of patients defined by the AIT criteria. Finally, we performed logistic regressions to identify variables associated with clinical utility. We identified 171 AIT-appropriate and 67 AIT-inappropriate patients. AIT-appropriate and AIT-inappropriate cases did not differ in any outcomes of clinical utility (P > .05). Subgroup analysis denoted both expected and unexpected results. The logistic regressions outlined the primary role of clinical picture and clinical or neuropsychological profile in identifying patients benefitting from amyloid-PET. Contrary to our hypothesis, also AIT-inappropriate prescriptions were associated with clinical utility. Clinical or neuropsychological variables, not taken into account by the AIT criteria, may help further refine criteria for appropriateness. Copyright © 2018. Published by Elsevier Inc.

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.

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.

Contributions of sociodemographic factors to criminal behavior

PubMed Central

Mundia, Lawrence; Matzin, Rohani; Mahalle, Salwa; Hamid, Malai Hayati; Osman, Ratna Suriani

2016-01-01

We explored the extent to which prisoner sociodemographic variables (age, education, marital status, employment, and whether their parents were married or not) influenced offending in 64 randomly selected Brunei inmates, comprising both sexes. A quantitative field survey design ideal for the type of participants used in a prison context was employed to investigate the problem. Hierarchical multiple regression analysis with backward elimination identified prisoner marital status and age groups as significantly related to offending. Furthermore, hierarchical multinomial logistic regression analysis with backward elimination indicated that prisoners’ age, primary level education, marital status, employment status, and parental marital status as significantly related to stealing offenses with high odds ratios. All 29 nonrecidivists were false negatives and predicted to reoffend upon release. Similarly, all 33 recidivists were projected to reoffend after release. Hierarchical binary logistic regression analysis revealed age groups (24–29 years and 30–35 years), employed prisoner, and primary level education as variables with high likelihood trends for reoffending. The results suggested that prisoner interventions (educational, counseling, and psychotherapy) in Brunei should treat not only antisocial personality, psychopathy, and mental health problems but also sociodemographic factors. The study generated offending patterns, trends, and norms that may inform subsequent investigations on Brunei prisoners. PMID:27382342

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

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

PubMed

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

2017-08-30

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

Disorganized Symptoms Predicted Worse Functioning Outcome in Schizophrenia Patients with Established Illness.

PubMed

Ortiz, Bruno Bertolucci; Gadelha, Ary; Higuchi, Cinthia Hiroko; Noto, Cristiano; Medeiros, Daiane; Pitta, José Cássio do Nascimento; de Araújo Filho, Gerardo Maria; Hallak, Jaime Eduardo Cecílio; Bressan, Rodrigo Affonseca

Most patients with schizophrenia will have subsequent relapses of the disorder, with continuous impairments in functioning. However, evidence is lacking on how symptoms influence functioning at different phases of the disease. This study aims to investigate the relationship between symptom dimensions and functioning at different phases: acute exacerbation, nonremission and remission. Patients with schizophrenia were grouped into acutely ill (n=89), not remitted (n=89), and remitted (n=69). Three exploratory stepwise linear regression analyses were performed for each phase of schizophrenia, in which the five PANSS factors and demographic variables were entered as the independent variables and the total Global Assessment of Functioning Scale (GAF) score was entered as the dependent variable. An additional exploratory stepwise logistic regression analysis was performed to predict subsequent remission at discharge in the inpatient population. The Disorganized factor was the most significant predictor for acutely ill patients (p<0.001), while the Hostility factor was the most significant for not-remitted patients and the Negative factor was the most significant for remitted patients (p=0.001 and p<0.001, respectively). In the logistic regression, the Disorganized factor score presented a significant negative association with remission (p=0.007). Higher disorganization symptoms showed the greatest impact in functioning at acute phase, and prevented patients from achieving remission, suggesting it may be a marker of symptom severity and worse outcome in schizophrenia.

Factors affecting choice between ureterostomy, ileal conduit and continent reservoir after radical cystectomy: Japanese series.

PubMed

Sugihara, Toru; Yasunaga, Hideo; Horiguchi, Hiromasa; Fujimura, Tetsuya; Fushimi, Kiyohide; Yu, Changhong; Kattan, Michael W; Homma, Yukio

2014-12-01

Little is known about the disparity of choices between three urinary diversions after radical cystectomy, focusing on patient and institutional factors. We identified urothelial carcinoma patients who received radical cystectomy with cutaneous ureterostomy, ileal conduit or continent reservoir using the Japanese Diagnosis Procedure Combination database from 2007 to 2012. Data comprised age, sex, comorbidities (converted into the Charlson index), TNM classification (converted into oncological stage), hospitals' academic status, hospital volume, bed volume and geographical region. Multivariate ordinal logistic regression analyses fitted with the proportional odds model were performed to analyze factors affecting urinary diversion choices. For dependent variables, the three diversions were converted into an ordinal variable in order of complexity: cutaneous ureterostomy (reference), ileal conduit and continent reservoir. Geographical variations were also examined by multivariate logistic regression models. A total of 4790 patients (1131 cutaneous ureterostomies [23.6 %], 2970 ileal conduits [62.0 %] and 689 continent reservoirs [14.4 %]) were included. Ordinal logistic regression analyses showed that male sex, lower age, lower Charlson index, early tumor stage, higher hospital volume (≥3.4 cases/year) and larger bed volume (≥450 beds) were significantly associated with the preference of more complex urinary diversion. Significant geographical disparity was also found. Good patient condition and early oncological status, as well as institutional factors, including high hospital volume, large bed volume and specific geographical regions, are independently related to the likelihood of choosing complex diversions. Recognizing this disparity would help reinforce the need for clinical practice uniformity.

Relaxing the rule of ten events per variable in logistic and Cox regression.

PubMed

Vittinghoff, Eric; McCulloch, Charles E

2007-03-15

The rule of thumb that logistic and Cox models should be used with a minimum of 10 outcome events per predictor variable (EPV), based on two simulation studies, may be too conservative. The authors conducted a large simulation study of other influences on confidence interval coverage, type I error, relative bias, and other model performance measures. They found a range of circumstances in which coverage and bias were within acceptable levels despite less than 10 EPV, as well as other factors that were as influential as or more influential than EPV. They conclude that this rule can be relaxed, in particular for sensitivity analyses undertaken to demonstrate adequate control of confounding.

Predicting the probability of elevated nitrate concentrations in the Puget Sound Basin: Implications for aquifer susceptibility and vulnerability

USGS Publications Warehouse

Tesoriero, A.J.; Voss, F.D.

1997-01-01

The occurrence and distribution of elevated nitrate concentrations (≥ 3 mg/l) in ground water in the Puget Sound Basin, Washington, were determined by examining existing data from more than 3000 wells. Models that estimate the probability that a well has an elevated nitrate concentration were constructed by relating the occurrence of elevated nitrate concentrations to both natural and anthropogenic variables using logistic regression. The variables that best explain the occurrence of elevated nitrate concentrations were well depth, surficial geology, and the percentage of urban and agricultural land within a radius of 3.2 kilometers of the well. From these relations, logistic regression models were developed to assess aquifer susceptibility (relative ease with which contaminants will reach aquifer) and ground-water vulnerability (relative ease with which contaminants will reach aquifer for a given set of land-use practices). Both models performed well at predicting the probability of elevated nitrate concentrations in an independent data set. This approach to assessing aquifer susceptibility and ground-water vulnerability has the advantages of having both model variables and coefficient values determined on the basis of existing water quality information and does not depend on the assignment of variables and weighting factors based on qualitative criteria.

Learning investment indicators through data extension

NASA Astrophysics Data System (ADS)

Dvořák, Marek

2017-07-01

Stock prices in the form of time series were analysed using single and multivariate statistical methods. After simple data preprocessing in the form of logarithmic differences, we augmented this single variate time series to a multivariate representation. This method makes use of sliding windows to calculate several dozen of new variables using simple statistic tools like first and second moments as well as more complicated statistic, like auto-regression coefficients and residual analysis, followed by an optional quadratic transformation that was further used for data extension. These were used as a explanatory variables in a regularized logistic LASSO regression which tried to estimate Buy-Sell Index (BSI) from real stock market data.

Predictors of Early Termination in a University Counseling Training Clinic

ERIC Educational Resources Information Center

Lampropoulos, Georgios K.; Schneider, Mercedes K.; Spengler, Paul M.

2009-01-01

Despite the existence of counseling dropout research, there are limited predictive data for counseling in training clinics. Potential predictor variables were investigated in this archival study of 380 client files in a university counseling training clinic. Multinomial logistic regression, predictive discriminant analysis, and classification and…

Impact of Collegiate Recreation on Academic Success

ERIC Educational Resources Information Center

Sanderson, Heather; DeRousie, Jason; Guistwite, Nicole

2018-01-01

This study examined the impact of collegiate recreation participation on academic success as measured by grade point average, course credit completion, and persistence or graduation. Logistic and multiple regressions were run to explore the relationship between total recreation contact hours and outcome variables. Results indicated a positive and…

Prediction of thoracic injury severity in frontal impacts by selected anatomical morphomic variables through model-averaged logistic regression approach.

PubMed

Zhang, Peng; Parenteau, Chantal; Wang, Lu; Holcombe, Sven; Kohoyda-Inglis, Carla; Sullivan, June; Wang, Stewart

2013-11-01

This study resulted in a model-averaging methodology that predicts crash injury risk using vehicle, demographic, and morphomic variables and assesses the importance of individual predictors. The effectiveness of this methodology was illustrated through analysis of occupant chest injuries in frontal vehicle crashes. The crash data were obtained from the International Center for Automotive Medicine (ICAM) database for calendar year 1996 to 2012. The morphomic data are quantitative measurements of variations in human body 3-dimensional anatomy. Morphomics are obtained from imaging records. In this study, morphomics were obtained from chest, abdomen, and spine CT using novel patented algorithms. A NASS-trained crash investigator with over thirty years of experience collected the in-depth crash data. There were 226 cases available with occupants involved in frontal crashes and morphomic measurements. Only cases with complete recorded data were retained for statistical analysis. Logistic regression models were fitted using all possible configurations of vehicle, demographic, and morphomic variables. Different models were ranked by the Akaike Information Criteria (AIC). An averaged logistic regression model approach was used due to the limited sample size relative to the number of variables. This approach is helpful when addressing variable selection, building prediction models, and assessing the importance of individual variables. The final predictive results were developed using this approach, based on the top 100 models in the AIC ranking. Model-averaging minimized model uncertainty, decreased the overall prediction variance, and provided an approach to evaluating the importance of individual variables. There were 17 variables investigated: four vehicle, four demographic, and nine morphomic. More than 130,000 logistic models were investigated in total. The models were characterized into four scenarios to assess individual variable contribution to injury risk. Scenario 1 used vehicle variables; Scenario 2, vehicle and demographic variables; Scenario 3, vehicle and morphomic variables; and Scenario 4 used all variables. AIC was used to rank the models and to address over-fitting. In each scenario, the results based on the top three models and the averages of the top 100 models were presented. The AIC and the area under the receiver operating characteristic curve (AUC) were reported in each model. The models were re-fitted after removing each variable one at a time. The increases of AIC and the decreases of AUC were then assessed to measure the contribution and importance of the individual variables in each model. The importance of the individual variables was also determined by their weighted frequencies of appearance in the top 100 selected models. Overall, the AUC was 0.58 in Scenario 1, 0.78 in Scenario 2, 0.76 in Scenario 3 and 0.82 in Scenario 4. The results showed that morphomic variables are as accurate at predicting injury risk as demographic variables. The results of this study emphasize the importance of including morphomic variables when assessing injury risk. The results also highlight the need for morphomic data in the development of human mathematical models when assessing restraint performance in frontal crashes, since morphomic variables are more "tangible" measurements compared to demographic variables such as age and gender. Copyright © 2013 Elsevier Ltd. All rights reserved.

Effects of categorization method, regression type, and variable distribution on the inflation of Type-I error rate when categorizing a confounding variable.

PubMed

Barnwell-Ménard, Jean-Louis; Li, Qing; Cohen, Alan A

2015-03-15

The loss of signal associated with categorizing a continuous variable is well known, and previous studies have demonstrated that this can lead to an inflation of Type-I error when the categorized variable is a confounder in a regression analysis estimating the effect of an exposure on an outcome. However, it is not known how the Type-I error may vary under different circumstances, including logistic versus linear regression, different distributions of the confounder, and different categorization methods. Here, we analytically quantified the effect of categorization and then performed a series of 9600 Monte Carlo simulations to estimate the Type-I error inflation associated with categorization of a confounder under different regression scenarios. We show that Type-I error is unacceptably high (>10% in most scenarios and often 100%). The only exception was when the variable categorized was a continuous mixture proxy for a genuinely dichotomous latent variable, where both the continuous proxy and the categorized variable are error-ridden proxies for the dichotomous latent variable. As expected, error inflation was also higher with larger sample size, fewer categories, and stronger associations between the confounder and the exposure or outcome. We provide online tools that can help researchers estimate the potential error inflation and understand how serious a problem this is. Copyright © 2014 John Wiley & Sons, Ltd.

Prediction of cold and heat patterns using anthropometric measures based on machine learning.

PubMed

Lee, Bum Ju; Lee, Jae Chul; Nam, Jiho; Kim, Jong Yeol

2018-01-01

To examine the association of body shape with cold and heat patterns, to determine which anthropometric measure is the best indicator for discriminating between the two patterns, and to investigate whether using a combination of measures can improve the predictive power to diagnose these patterns. Based on a total of 4,859 subjects (3,000 women and 1,859 men), statistical analyses using binary logistic regression were performed to assess the significance of the difference and the predictive power of each anthropometric measure, and binary logistic regression and Naive Bayes with the variable selection technique were used to assess the improvement in the predictive power of the patterns using the combined measures. In women, the strongest indicators for determining the cold and heat patterns among anthropometric measures were body mass index (BMI) and rib circumference; in men, the best indicator was BMI. In experiments using a combination of measures, the values of the area under the receiver operating characteristic curve in women were 0.776 by Naive Bayes and 0.772 by logistic regression, and the values in men were 0.788 by Naive Bayes and 0.779 by logistic regression. Individuals with a higher BMI have a tendency toward a heat pattern in both women and men. The use of a combination of anthropometric measures can slightly improve the diagnostic accuracy. Our findings can provide fundamental information for the diagnosis of cold and heat patterns based on body shape for personalized medicine.

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.

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.

The effect of playing tactics and situational variables on achieving score-box possessions in a professional soccer team.

PubMed

Lago-Ballesteros, Joaquin; Lago-Peñas, Carlos; Rey, Ezequiel

2012-01-01

The aim of this study was to analyse the influence of playing tactics, opponent interaction and situational variables on achieving score-box possessions in professional soccer. The sample was constituted by 908 possessions obtained by a team from the Spanish soccer league in 12 matches played during the 2009-2010 season. Multidimensional qualitative data obtained from 12 ordered categorical variables were used. Sampled matches were registered by the AMISCO PRO system. Data were analysed using chi-square analysis and multiple logistic regression analysis. Of 908 possessions, 303 (33.4%) produced score-box possessions, 477 (52.5%) achieved progression and 128 (14.1%) failed to reach any sort of progression. Multiple logistic regression showed that, for the main variable "team possession type", direct attacks and counterattacks were three times more effective than elaborate attacks for producing a score-box possession (P < 0.05). Team possession originating from the middle zones and playing against less than six defending players (P < 0.001) registered a higher success than those started in the defensive zone with a balanced defence. When the team was drawing or winning, the probability of reaching the score-box decreased by 43 and 53 percent, respectively, compared with the losing situation (P < 0.05). Accounting for opponent interactions and situational variables is critical to evaluate the effectiveness of offensive playing tactics on producing score-box possessions.

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

Sex-related perceptions associated with sexual activity status among Japanese adolescents who heavily use text messaging.

PubMed

Kawamura, Yoko

2012-01-01

This study examines the relationship between sex-related perceptions and engagement in sexual intercourse among adolescents in Japan who were heavy users of text massaging. Using the data from the 6th National Survey on Youth Sexual Behavior of 548 high school students who heavily use text messaging, multinomial logistic regression analyses on variables constructing sexual norms and gender-role attitudes were conducted to assess the relationship with sexual activity status as the first step. A backward stepwise elimination method of multinomial logistic regression was used as the second step at which variables for each set of two factors were tested, and as the third step at which variables of two factors were simultaneously tested. The study results showed that perceptions were related to engagement in sexual intercourse among adolescents who heavily used text messaging. In particular, those who perceived that sex is an act to be engaged in at an earlier stage of a relationship and that men have a stronger sex drive tended to be sexually active or have experienced sexual intercourse. These findings could be utilized to design more effective sexual health education messages for Japanese adolescents who are at an elevated risk.

The High Prevalence of Incarceration History Among Black Men Who Have Sex With Men in the United States: Associations and Implications

PubMed Central

Magnus, Manya; Kuo, Irene; Wang, Lei; Liu, Ting-Yuan; Mayer, Kenneth H.

2014-01-01

Objectives. We examined lifetime incarceration history and its association with key characteristics among 1553 Black men who have sex with men (BMSM) recruited in 6 US cities. Methods. We conducted bivariate analyses of data collected from the HIV Prevention Trials Network 061 study from July 2009 through December 2011 to examine the relationship between incarceration history and demographic and psychosocial variables predating incarceration and multivariate logistic regression analyses to explore the associations between incarceration history and demographic and psychosocial variables found to be significant. We then used multivariate logistic regression models to explore the independent association between incarceration history and 6 outcome variables. Results. After adjusting for confounders, we found that increasing age, transgender identity, heterosexual or straight identity, history of childhood violence, and childhood sexual experience were significantly associated with incarceration history. A history of incarceration was also independently associated with any alcohol and drug use in the past 6 months. Conclusions. The findings highlight an elevated lifetime incarceration history among a geographically diverse sample of BMSM and the need to adequately assess the impact of incarceration among BMSM in the United States. PMID:24432948

Laboratory test variables useful for distinguishing upper from lower gastrointestinal bleeding.

PubMed

Tomizawa, Minoru; Shinozaki, Fuminobu; Hasegawa, Rumiko; Shirai, Yoshinori; Motoyoshi, Yasufumi; Sugiyama, Takao; Yamamoto, Shigenori; Ishige, Naoki

2015-05-28

To distinguish upper from lower gastrointestinal (GI) bleeding. Patient records between April 2011 and March 2014 were analyzed retrospectively (3296 upper endoscopy, and 1520 colonoscopy). Seventy-six patients had upper GI bleeding (Upper group) and 65 had lower GI bleeding (Lower group). Variables were compared between the groups using one-way analysis of variance. Logistic regression was performed to identify variables significantly associated with the diagnosis of upper vs lower GI bleeding. Receiver-operator characteristic (ROC) analysis was performed to determine the threshold value that could distinguish upper from lower GI bleeding. Hemoglobin (P = 0.023), total protein (P = 0.0002), and lactate dehydrogenase (P = 0.009) were significantly lower in the Upper group than in the Lower group. Blood urea nitrogen (BUN) was higher in the Upper group than in the Lower group (P = 0.0065). Logistic regression analysis revealed that BUN was most strongly associated with the diagnosis of upper vs lower GI bleeding. ROC analysis revealed a threshold BUN value of 21.0 mg/dL, with a specificity of 93.0%. The threshold BUN value for distinguishing upper from lower GI bleeding was 21.0 mg/dL.

Laboratory test variables useful for distinguishing upper from lower gastrointestinal bleeding

PubMed Central

Tomizawa, Minoru; Shinozaki, Fuminobu; Hasegawa, Rumiko; Shirai, Yoshinori; Motoyoshi, Yasufumi; Sugiyama, Takao; Yamamoto, Shigenori; Ishige, Naoki

2015-01-01

AIM: To distinguish upper from lower gastrointestinal (GI) bleeding. METHODS: Patient records between April 2011 and March 2014 were analyzed retrospectively (3296 upper endoscopy, and 1520 colonoscopy). Seventy-six patients had upper GI bleeding (Upper group) and 65 had lower GI bleeding (Lower group). Variables were compared between the groups using one-way analysis of variance. Logistic regression was performed to identify variables significantly associated with the diagnosis of upper vs lower GI bleeding. Receiver-operator characteristic (ROC) analysis was performed to determine the threshold value that could distinguish upper from lower GI bleeding. RESULTS: Hemoglobin (P = 0.023), total protein (P = 0.0002), and lactate dehydrogenase (P = 0.009) were significantly lower in the Upper group than in the Lower group. Blood urea nitrogen (BUN) was higher in the Upper group than in the Lower group (P = 0.0065). Logistic regression analysis revealed that BUN was most strongly associated with the diagnosis of upper vs lower GI bleeding. ROC analysis revealed a threshold BUN value of 21.0 mg/dL, with a specificity of 93.0%. CONCLUSION: The threshold BUN value for distinguishing upper from lower GI bleeding was 21.0 mg/dL. PMID:26034359

Factors associated with vocal fold pathologies in teachers.

PubMed

Souza, Carla Lima de; Carvalho, Fernando Martins; Araújo, Tânia Maria de; Reis, Eduardo José Farias Borges Dos; Lima, Verônica Maria Cadena; Porto, Lauro Antonio

2011-10-01

To analyze factors associated with the prevalence of the medical diagnosis of vocal fold pathologies in teachers. A census-based epidemiological, cross-sectional study was conducted with 4,495 public primary and secondary school teachers in the city of Salvador, Northeastern Brazil, between March and April 2006. The dependent variable was the self-reported medical diagnosis of vocal fold pathologies and the independent variables were sociodemographic characteristics; professional activity; work organization/interpersonal relationships; physical work environment characteristics; frequency of common mental disorders, measured by the Self-Reporting Questionnaire-20 (SRQ-20 >7); and general health conditions. Descriptive statistical, bivariate and multiple logistic regression analysis techniques were used. The prevalence of self-reported medical diagnosis of vocal fold pathologies was 18.9%. In the logistic regression analysis, the variables that remained associated with this medical diagnosis were as follows: being female, having worked as a teacher for more than seven years, excessive voice use, reporting more than five unfavorable physical work environment characteristics and presence of common mental disorders. The presence of self-reported vocal fold pathologies was associated with factors that point out the need of actions that promote teachers' vocal health and changes in their work structure and organization.

Modelling landscape change in paddy fields using logistic regression and GIS

NASA Astrophysics Data System (ADS)

Franjaya, E. E.; Syartinilia; Setiawan, Y.

2018-05-01

Paddy field in karawang district, as an important agricultural land in west java, has been decreased since 1994. From previous study, paddy fields dominantly turned into built area. The changes were almost occured in the middle area of the district where roadways, industries, settlements, and commercial buildings were existed. These were estimated as driving forces. But, we still need to prove it. This study aimed to construct the paddy field probability change model, subsequently the driving forces will be obtained. GIS combined with logistic regression using environmental variables were used as main method in this study. Ten environmental variables were elevation 0–500 m, elevation>500 m, slope<8%, slope>8%, CBD, build up area, river, irrigation, toll and national roadway, and collector and local roadway. The result indicated that four variables were significantly played as driving forces (slope>8%, CBD area, build up area, and collector and local roadway). Paddy field has high, medium, and low probability to change which covered about 27.8%, 7.8%, and 64.4% area in Karawang respectively. Based on landscape ecology, the recommendation that suitable with landscape change is adaptive management.

Quantitative Analysis of Land Loss in Coastal Louisiana Using Remote Sensing

NASA Astrophysics Data System (ADS)

Wales, P. M.; Kuszmaul, J.; Roberts, C.

2005-12-01

For the past thirty-five years the land loss along the Louisiana Coast has been recognized as a growing problem. One of the clearest indicators of this land loss is that in 2000 smooth cord grass (spartina alterniflora) was turning brown well before its normal hibernation period. Over 100,000 acres of marsh were affected by the 2000 browning. In 2001 data were collected using low altitude helicopter based transects of the coast, with 7,400 data points being collected by researchers at the USGS, National Wetlands Research Center, and Louisiana Department of Natural Resources. The surveys contained data describing the characteristics of the marsh, including latitude, longitude, marsh condition, marsh color, percent vegetated, and marsh die-back. Creating a model that combines remote sensing images, field data, and statistical analysis to develop a methodology for estimating the margin of error in measurements of coastal land loss (erosion) is the ultimate goal of the study. A model was successfully created using a series of band combinations (used as predictive variables). The most successful band combinations or predictive variables were the braud value [(Sum Visible TM Bands - Sum Infrared TM Bands)/(Sum Visible TM Bands + Sum Infrared TM Bands)], TM band 7/ TM band 2, brightness, NDVI, wetness, vegetation index, and a 7x7 autocovariate nearest neighbor floating window. The model values were used to generate the logistic regression model. A new image was created based on the logistic regression probability equation where each pixel represents the probability of finding water or non-water at that location in each image. Pixels within each image that have a high probability of representing water have a value close to 1 and pixels with a low probability of representing water have a value close to 0. A logistic regression model is proposed that uses seven independent variables. This model yields an accurate classification in 86.5% of the locations considered in the 1997 and 2001 survey locations. When the logistic regression was modeled to the satellite imagery of the entire Louisiana Coast study area a statewide loss was estimated to be 358 mi2 to 368 mi2, from 1997 to 2001, using two different methods for estimating land loss.

Comparative analysis on the probability of being a good payer

NASA Astrophysics Data System (ADS)

Mihova, V.; Pavlov, V.

2017-10-01

Credit risk assessment is crucial for the bank industry. The current practice uses various approaches for the calculation of credit risk. The core of these approaches is the use of multiple regression models, applied in order to assess the risk associated with the approval of people applying for certain products (loans, credit cards, etc.). Based on data from the past, these models try to predict what will happen in the future. Different data requires different type of models. This work studies the causal link between the conduct of an applicant upon payment of the loan and the data that he completed at the time of application. A database of 100 borrowers from a commercial bank is used for the purposes of the study. The available data includes information from the time of application and credit history while paying off the loan. Customers are divided into two groups, based on the credit history: Good and Bad payers. Linear and logistic regression are applied in parallel to the data in order to estimate the probability of being good for new borrowers. A variable, which contains value of 1 for Good borrowers and value of 0 for Bad candidates, is modeled as a dependent variable. To decide which of the variables listed in the database should be used in the modelling process (as independent variables), a correlation analysis is made. Due to the results of it, several combinations of independent variables are tested as initial models - both with linear and logistic regression. The best linear and logistic models are obtained after initial transformation of the data and following a set of standard and robust statistical criteria. A comparative analysis between the two final models is made and scorecards are obtained from both models to assess new customers at the time of application. A cut-off level of points, bellow which to reject the applications and above it - to accept them, has been suggested for both the models, applying the strategy to keep the same Accept Rate as in the current data.

A comparison of Cox and logistic regression for use in genome-wide association studies of cohort and case-cohort design.

PubMed

Staley, James R; Jones, Edmund; Kaptoge, Stephen; Butterworth, Adam S; Sweeting, Michael J; Wood, Angela M; Howson, Joanna M M

2017-06-01

Logistic regression is often used instead of Cox regression to analyse genome-wide association studies (GWAS) of single-nucleotide polymorphisms (SNPs) and disease outcomes with cohort and case-cohort designs, as it is less computationally expensive. Although Cox and logistic regression models have been compared previously in cohort studies, this work does not completely cover the GWAS setting nor extend to the case-cohort study design. Here, we evaluated Cox and logistic regression applied to cohort and case-cohort genetic association studies using simulated data and genetic data from the EPIC-CVD study. In the cohort setting, there was a modest improvement in power to detect SNP-disease associations using Cox regression compared with logistic regression, which increased as the disease incidence increased. In contrast, logistic regression had more power than (Prentice weighted) Cox regression in the case-cohort setting. Logistic regression yielded inflated effect estimates (assuming the hazard ratio is the underlying measure of association) for both study designs, especially for SNPs with greater effect on disease. Given logistic regression is substantially more computationally efficient than Cox regression in both settings, we propose a two-step approach to GWAS in cohort and case-cohort studies. First to analyse all SNPs with logistic regression to identify associated variants below a pre-defined P-value threshold, and second to fit Cox regression (appropriately weighted in case-cohort studies) to those identified SNPs to ensure accurate estimation of association with disease.

Cesarean delivery rates among family physicians versus obstetricians: a population-based cohort study using instrumental variable methods

PubMed Central

Dawe, Russell Eric; Bishop, Jessica; Pendergast, Amanda; Avery, Susan; Monaghan, Kelly; Duggan, Norah; Aubrey-Bassler, Kris

2017-01-01

Background: Previous research suggests that family physicians have rates of cesarean delivery that are lower than or equivalent to those for obstetricians, but adjustments for risk differences in these analyses may have been inadequate. We used an econometric method to adjust for observed and unobserved factors affecting the risk of cesarean delivery among women attended by family physicians versus obstetricians. Methods: This retrospective population-based cohort study included all Canadian (except Quebec) hospital deliveries by family physicians and obstetricians between Apr. 1, 2006, and Mar. 31, 2009. We excluded women with multiple gestations, and newborns with a birth weight less than 500 g or gestational age less than 20 weeks. We estimated the relative risk of cesarean delivery using instrumental-variable-adjusted and logistic regression. Results: The final cohort included 776 299 women who gave birth in 390 hospitals. The risk of cesarean delivery was 27.3%, and the mean proportion of deliveries by family physicians was 26.9% (standard deviation 23.8%). The relative risk of cesarean delivery for family physicians versus obstetricians was 0.48 (95% confidence interval [CI] 0.41-0.56) with logistic regression and 1.27 (95% CI 1.02-1.57) with instrumental-variable-adjusted regression. Interpretation: Our conventional analyses suggest that family physicians have a lower rate of cesarean delivery than obstetricians, but instrumental variable analyses suggest the opposite. Because instrumental variable methods adjust for unmeasured factors and traditional methods do not, the large discrepancy between these estimates of risk suggests that clinical and/or sociocultural factors affecting the decision to perform cesarean delivery may not be accounted for in our database. PMID:29233843

Comparison of Survival Models for Analyzing Prognostic Factors in Gastric Cancer Patients

PubMed

Habibi, Danial; Rafiei, Mohammad; Chehrei, Ali; Shayan, Zahra; Tafaqodi, Soheil

2018-03-27

Objective: There are a number of models for determining risk factors for survival of patients with gastric cancer. This study was conducted to select the model showing the best fit with available data. Methods: Cox regression and parametric models (Exponential, Weibull, Gompertz, Log normal, Log logistic and Generalized Gamma) were utilized in unadjusted and adjusted forms to detect factors influencing mortality of patients. Comparisons were made with Akaike Information Criterion (AIC) by using STATA 13 and R 3.1.3 softwares. Results: The results of this study indicated that all parametric models outperform the Cox regression model. The Log normal, Log logistic and Generalized Gamma provided the best performance in terms of AIC values (179.2, 179.4 and 181.1, respectively). On unadjusted analysis, the results of the Cox regression and parametric models indicated stage, grade, largest diameter of metastatic nest, largest diameter of LM, number of involved lymph nodes and the largest ratio of metastatic nests to lymph nodes, to be variables influencing the survival of patients with gastric cancer. On adjusted analysis, according to the best model (log normal), grade was found as the significant variable. Conclusion: The results suggested that all parametric models outperform the Cox model. The log normal model provides the best fit and is a good substitute for Cox regression. Creative Commons Attribution License

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.

Predictors of Employment Outcomes for State-Federal Vocational Rehabilitation Consumers with HIV/AIDS

ERIC Educational Resources Information Center

Jung, Youngoh; Schaller, James; Bellini, James

2010-01-01

In this study, the authors investigated the effects of demographic, medical, and vocational rehabilitation service variables on employment outcomes of persons living with HIV/AIDS. Binary logistic regression analyses were conducted to determine predictors of employment outcomes using two groups drawn from Rehabilitation Services Administration…

Comparative Research of Navy Voluntary Education at Operational Commands

DTIC Science & Technology

2017-03-01

return on investment, ROI, logistic regression, multivariate analysis, descriptive statistics, Markov, time-series, linear programming 15. NUMBER...21  B.  DESCRIPTIVE STATISTICS TABLES ...............................................25  C.  PRIVACY CONSIDERATIONS...THIS PAGE INTENTIONALLY LEFT BLANK xi LIST OF TABLES Table 1.  Variables and Descriptions . Adapted from NETC (2016). .......................21

Epidemiological determinants of successful vaccine development.

PubMed

Nishiura, Hiroshi; Mizumoto, Kenji

2013-01-01

Epidemiological determinants of successful vaccine development were explored using measurable biological variables including antigenic stability and requirement of T-cell immunity. Employing a logistic regression model, we demonstrate that a high affinity with blood and immune cells and pathogen interactions (e.g. interference) would be the risk factors of failure for vaccine development.

Juvenile Offender Recidivism: An Examination of Risk Factors

ERIC Educational Resources Information Center

Calley, Nancy G.

2012-01-01

One hundred and seventy three male juvenile offenders were followed two years postrelease from a residential treatment facility to assess recidivism and factors related to recidivism. The overall recidivism rate was 23.9%. Logistic regression with stepwise and backward variable selection methods was used to examine the relationship between…

The Effect of Urban Sprawls on Timber Harvesting

Treesearch

Stephen A. Barlow; Ian A Munn; David A. Cleaves; David L. Evans

1998-01-01

In Mississippi and Alabama, urban population growth is pushing development into rural areas. To study the impact of urbanization on timber harvesting, census and forest inventory data were combined in a geographic information system, and a logistic regression model was used to estimate the relationship between several variables and harvest probabilities....

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...

Deterministic Demographic Characteristics in Tertiary Education: An Exploratory Study

ERIC Educational Resources Information Center

Morton, Lisa; Lamb, Charles

2006-01-01

This paper reports the responses of 235 tertiary commerce students to a questionnaire in relation to their learning and assessment experiences. Significant correlations between measures were used to identify underlying constructs within the overall set of variable measures. Logistic regression incorporating the factors was then used to further…

Glucose variability negatively impacts long-term functional outcome in patients with traumatic brain injury.

PubMed

Matsushima, Kazuhide; Peng, Monica; Velasco, Carlos; Schaefer, Eric; Diaz-Arrastia, Ramon; Frankel, Heidi

2012-04-01

Significant glycemic excursions (so-called glucose variability) affect the outcome of generic critically ill patients but has not been well studied in patients with traumatic brain injury (TBI). The purpose of this study was to evaluate the impact of glucose variability on long-term functional outcome of patients with TBI. A noncomputerized tight glucose control protocol was used in our intensivist model surgical intensive care unit. The relationship between the glucose variability and long-term (a median of 6 months after injury) functional outcome defined by extended Glasgow Outcome Scale (GOSE) was analyzed using ordinal logistic regression models. Glucose variability was defined by SD and percentage of excursion (POE) from the preset range glucose level. A total of 109 patients with TBI under tight glucose control had long-term GOSE evaluated. In univariable analysis, there was a significant association between lower GOSE score and higher mean glucose, higher SD, POE more than 60, POE 80 to 150, and single episode of glucose less than 60 mg/dL but not POE 80 to 110. After adjusting for possible confounding variables in multivariable ordinal logistic regression models, higher SD, POE more than 60, POE 80 to 150, and single episode of glucose less than 60 mg/dL were significantly associated with lower GOSE score. Glucose variability was significantly associated with poorer long-term functional outcome in patients with TBI as measured by the GOSE score. Well-designed protocols to minimize glucose variability may be key in improving long-term functional outcome. Copyright © 2012 Elsevier Inc. All rights reserved.

Variables Associated With Perceived Unmet Need for Mental Health Care in a Canadian Epidemiologic Catchment Area.

PubMed

Fleury, Marie-Josée; Grenier, Guy; Bamvita, Jean-Marie; Perreault, Michel; Caron, Jean

2016-01-01

This study identified variables associated with perceived partially met and unmet needs for information, medication, and counseling, as well as overall perceived unmet needs, related to mental health among 571 people in a Canadian epidemiologic catchment area. Needs were measured with the Perceived Need for Care Questionnaire and a comprehensive set of independent variables based on Andersen's behavioral model. Four models were constructed for the following dependent variables: perceived unmet needs for information, medication, and counseling (multinomial logistic regression) and overall perceived unmet needs (multiple logistic regression). The proportions reporting fully unmet need were as follows: counseling, 30%; information, 18%; and medication, 4%. Variables associated with unmet needs for information, medication, and counseling were quite distinct. Enabling factors (for example, neighborhood perception variables) were strongly associated with perceived unmet need for information. Need factors were more strongly associated with unmet need for medication, predisposing factors with unmet needs for information and medication, and health service use with unmet information and counseling needs. People whose overall needs went unmet tended to be younger, to have an addiction, and to have consulted fewer professionals. Mental health services should facilitate access to psychologists or other clinicians to better meet counseling and information needs. They should also take neighborhoods into account when assessing needs and provide more information about mental disorders and the treatments and services offered in disadvantaged areas. Finally, services should be further developed for younger people with addiction, who tend to be stigmatized and avoid using health services.

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…

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

NASA Astrophysics Data System (ADS)

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

2015-07-01

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

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

PubMed

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

2015-07-07

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

Factors associated with active commuting to work among women.

PubMed

Bopp, Melissa; Child, Stephanie; Campbell, Matthew

2014-01-01

Active commuting (AC), the act of walking or biking to work, has notable health benefits though rates of AC remain low among women. This study used a social-ecological framework to examine the factors associated with AC among women. A convenience sample of employed, working women (n = 709) completed an online survey about their mode of travel to work. Individual, interpersonal, institutional, community, and environmental influences were assessed. Basic descriptive statistics and frequencies described the sample. Simple logistic regression models examined associations with the independent variables with AC participation and multiple logistic regression analysis determined the relative influence of social ecological factors on AC participation. The sample was primarily middle-aged (44.09±11.38 years) and non-Hispanic White (92%). Univariate analyses revealed several individual, interpersonal, institutional, community and environmental factors significantly associated with AC. The multivariable logistic regression analysis results indicated that significant factors associated with AC included number of children, income, perceived behavioral control, coworker AC, coworker AC normative beliefs, employer and community supports for AC, and traffic. The results of this study contribute to the limited body of knowledge on AC participation for women and may help to inform gender-tailored interventions to enhance AC behavior and improve health.

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

Large scale landslide susceptibility assessment using the statistical methods of logistic regression and BSA - study case: the sub-basin of the small Niraj (Transylvania Depression, Romania)

NASA Astrophysics Data System (ADS)

Roşca, S.; Bilaşco, Ş.; Petrea, D.; Fodorean, I.; Vescan, I.; Filip, S.; Măguţ, F.-L.

2015-11-01

The existence of a large number of GIS models for the identification of landslide occurrence probability makes difficult the selection of a specific one. The present study focuses on the application of two quantitative models: the logistic and the BSA models. The comparative analysis of the results aims at identifying the most suitable model. The territory corresponding to the Niraj Mic Basin (87 km2) is an area characterised by a wide variety of the landforms with their morphometric, morphographical and geological characteristics as well as by a high complexity of the land use types where active landslides exist. This is the reason why it represents the test area for applying the two models and for the comparison of the results. The large complexity of input variables is illustrated by 16 factors which were represented as 72 dummy variables, analysed on the basis of their importance within the model structures. The testing of the statistical significance corresponding to each variable reduced the number of dummy variables to 12 which were considered significant for the test area within the logistic model, whereas for the BSA model all the variables were employed. The predictability degree of the models was tested through the identification of the area under the ROC curve which indicated a good accuracy (AUROC = 0.86 for the testing area) and predictability of the logistic model (AUROC = 0.63 for the validation area).

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…

Testing concordance of instrumental variable effects in generalized linear models with application to Mendelian randomization

PubMed Central

Dai, James Y.; Chan, Kwun Chuen Gary; Hsu, Li

2014-01-01

Instrumental variable regression is one way to overcome unmeasured confounding and estimate causal effect in observational studies. Built on structural mean models, there has been considerale work recently developed for consistent estimation of causal relative risk and causal odds ratio. Such models can sometimes suffer from identification issues for weak instruments. This hampered the applicability of Mendelian randomization analysis in genetic epidemiology. When there are multiple genetic variants available as instrumental variables, and causal effect is defined in a generalized linear model in the presence of unmeasured confounders, we propose to test concordance between instrumental variable effects on the intermediate exposure and instrumental variable effects on the disease outcome, as a means to test the causal effect. We show that a class of generalized least squares estimators provide valid and consistent tests of causality. For causal effect of a continuous exposure on a dichotomous outcome in logistic models, the proposed estimators are shown to be asymptotically conservative. When the disease outcome is rare, such estimators are consistent due to the log-linear approximation of the logistic function. Optimality of such estimators relative to the well-known two-stage least squares estimator and the double-logistic structural mean model is further discussed. PMID:24863158

[Optimization of diagnosis indicator selection and inspection plan by 3.0T MRI in breast cancer].

PubMed

Jiang, Zhongbiao; Wang, Yunhua; He, Zhong; Zhang, Lejun; Zheng, Kai

2013-08-01

To optimize 3.0T MRI diagnosis indicator in breast cancer and to select the best MRI scan program. Totally 45 patients with breast cancers were collected, and another 35 patients with benign breast tumor served as the control group. All patients underwent 3.0T MRI, including T1- weighted imaging (T1WI), fat suppression of the T2-weighted imaging (T2WI), diffusion weighted imaging (DWI), 1H magnetic resonance spectroscopy (1H-MRS) and dynamic contrast enhanced (DCE) sequence. With operation pathology results as the gold standard in the diagnosis of breast diseases, the pathological results of benign and malignant served as dependent variables, and the diagnostic indicators of MRI were taken as independent variables. We put all the indicators of MRI examination under Logistic regression analysis, established the Logistic model, and optimized the diagnosis indicators of MRI examination to further improve MRI scan of breast cancer. By Logistic regression analysis, some indicators were selected in the equation, including the edge feature of the tumor, the time-signal intensity curve (TIC) type and the apparent diffusion coefficient (ADC) value when b=500 s/mm2. The regression equation was Logit (P)=-21.936+20.478X6+3.267X7+ 21.488X3. Valuable indicators in the diagnosis of breast cancer are the edge feature of the tumor, the TIC type and the ADC value when b=500 s/mm2. Combining conventional MRI scan, DWI and dynamic enhanced MRI is a better examination program, while MRS is the complementary program when diagnosis is difficult.

Temperature variability during targeted temperature management is not associated with neurological outcomes following cardiac arrest.

PubMed

Nayeri, Arash; Bhatia, Nirmanmoh; Holmes, Benjamin; Borges, Nyal; Armstrong, William; Xu, Meng; Farber-Eger, Eric; Wells, Quinn S; McPherson, John A

2017-06-01

Recent studies on comatose survivors of cardiac arrest undergoing targeted temperature management (TTM) have shown similar outcomes at multiple target temperatures. However, details regarding core temperature variability during TTM and its prognostic implications remain largely unknown. We sought to assess the association between core temperature variability and neurological outcomes in patients undergoing TTM following cardiac arrest. We analyzed a prospectively collected cohort of 242 patients treated with TTM following cardiac arrest at a tertiary care hospital between 2007 and 2014. Core temperature variability was defined as the statistical variance (i.e. standard deviation squared) amongst all core temperature recordings during the maintenance phase of TTM. Poor neurological outcome at hospital discharge, defined as a Cerebral Performance Category (CPC) score>2, was the primary outcome. Death prior to hospital discharge was assessed as the secondary outcome. Multivariable logistic regression was used to examine the association between temperature variability and neurological outcome or death at hospital discharge. A poor neurological outcome was observed in 147 (61%) patients and 136 (56%) patients died prior to hospital discharge. In multivariable logistic regression, increased core temperature variability was not associated with increased odds of poor neurological outcomes (OR 0.38, 95% CI 0.11-1.38, p=0.142) or death (OR 0.43, 95% CI 0.12-1.53, p=0.193) at hospital discharge. In this study, individual core temperature variability during TTM was not associated with poor neurological outcomes or death at hospital discharge. Copyright © 2017 Elsevier Inc. All rights reserved.

Network-based regularization for matched case-control analysis of high-dimensional DNA methylation data.

PubMed

Sun, Hokeun; Wang, Shuang

2013-05-30

The matched case-control designs are commonly used to control for potential confounding factors in genetic epidemiology studies especially epigenetic studies with DNA methylation. Compared with unmatched case-control studies with high-dimensional genomic or epigenetic data, there have been few variable selection methods for matched sets. In an earlier paper, we proposed the penalized logistic regression model for the analysis of unmatched DNA methylation data using a network-based penalty. However, for popularly applied matched designs in epigenetic studies that compare DNA methylation between tumor and adjacent non-tumor tissues or between pre-treatment and post-treatment conditions, applying ordinary logistic regression ignoring matching is known to bring serious bias in estimation. In this paper, we developed a penalized conditional logistic model using the network-based penalty that encourages a grouping effect of (1) linked Cytosine-phosphate-Guanine (CpG) sites within a gene or (2) linked genes within a genetic pathway for analysis of matched DNA methylation data. In our simulation studies, we demonstrated the superiority of using conditional logistic model over unconditional logistic model in high-dimensional variable selection problems for matched case-control data. We further investigated the benefits of utilizing biological group or graph information for matched case-control data. We applied the proposed method to a genome-wide DNA methylation study on hepatocellular carcinoma (HCC) where we investigated the DNA methylation levels of tumor and adjacent non-tumor tissues from HCC patients by using the Illumina Infinium HumanMethylation27 Beadchip. Several new CpG sites and genes known to be related to HCC were identified but were missed by the standard method in the original paper. Copyright © 2012 John Wiley & Sons, Ltd.

[Prediction of histological liver damage in asymptomatic alcoholic patients by means of clinical and laboratory data].

PubMed

Iturriaga, H; Hirsch, S; Bunout, D; Díaz, M; Kelly, M; Silva, G; de la Maza, M P; Petermann, M; Ugarte, G

1993-04-01

Looking for a noninvasive method to predict liver histologic alterations in alcoholic patients without clinical signs of liver failure, we studied 187 chronic alcoholics recently abstinent, divided in 2 series. In the model series (n = 94) several clinical variables and results of common laboratory tests were confronted to the findings of liver biopsies. These were classified in 3 groups: 1. Normal liver; 2. Moderate alterations; 3. Marked alterations, including alcoholic hepatitis and cirrhosis. Multivariate methods used were logistic regression analysis and a classification and regression tree (CART). Both methods entered gamma-glutamyltransferase (GGT), aspartate-aminotransferase (AST), weight and age as significant and independent variables. Univariate analysis with GGT and AST at different cutoffs were also performed. To predict the presence of any kind of damage (Groups 2 and 3), CART and AST > 30 IU showed the higher sensitivity, specificity and correct prediction, both in the model and validation series. For prediction of marked liver damage, a score based on logistic regression and GGT > 110 IU had the higher efficiencies. It is concluded that GGT and AST are good markers of alcoholic liver damage and that, using sample cutoffs, histologic diagnosis can be correctly predicted in 80% of recently abstinent asymptomatic alcoholics.

Internalized stigma among psychiatric outpatients: Associations with quality of life, functioning, hope and self-esteem.

PubMed

Picco, Louisa; Pang, Shirlene; Lau, Ying Wen; Jeyagurunathan, Anitha; Satghare, Pratika; Abdin, Edimansyah; Vaingankar, Janhavi Ajit; Lim, Susan; Poh, Chee Lien; Chong, Siow Ann; Subramaniam, Mythily

2016-12-30

This study aimed to: (i) determine the prevalence, socio-demographic and clinical correlates of internalized stigma and (ii) explore the association between internalized stigma and quality of life, general functioning, hope and self-esteem, among a multi-ethnic Asian population of patients with mental disorders. This cross-sectional, survey recruited adult patients (n=280) who were seeking treatment at outpatient and affiliated clinics of the only tertiary psychiatric hospital in Singapore. Internalized stigma was measured using the Internalized Stigma of Mental Illness scale. 43.6% experienced moderate to high internalized stigma. After making adjustments in multiple logistic regression analysis, results revealed there were no significant socio-demographic or clinical correlates relating to internalized stigma. Individual logistic regression models found a negative relationship between quality of life, self-esteem, general functioning and internalized stigma whereby lower scores were associated with higher internalized stigma. In the final regression model, which included all psychosocial variables together, self-esteem was the only variable significantly and negatively associated with internalized stigma. The results of this study contribute to our understanding of the role internalized stigma plays in patients with mental illness, and the impact it can have on psychosocial aspects of their lives. Copyright © 2016 The Authors. Published by Elsevier Ireland Ltd.. All rights reserved.

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

NASA Technical Reports Server (NTRS)

Messer, Bradley P.

2004-01-01

Propulsion ground test facilities face the daily challenges of scheduling multiple customers into limited facility space and successfully completing their propulsion test projects. Due to budgetary and schedule constraints, NASA and industry customers are pushing to test more components, for less money, in a shorter period of time. As these new rocket engine component test programs are undertaken, the lack of technology maturity in the test articles, combined with pushing the test facilities capabilities to their limits, tends to lead to an increase in facility breakdowns and unsuccessful tests. Over the last five years Stennis Space Center's propulsion test facilities have performed hundreds of tests, collected thousands of seconds of test data, and broken numerous test facility and test article parts. While various initiatives have been implemented to provide better propulsion test techniques and improve the quality, reliability, and maintainability of goods and parts used in the propulsion test facilities, unexpected failures during testing still occur quite regularly due to the harsh environment in which the propulsion test facilities operate. Previous attempts at modeling the lifecycle of a propulsion component test project have met with little success. Each of the attempts suffered form incomplete or inconsistent data on which to base the models. By focusing on the actual test phase of the tests project rather than the formulation, design or construction phases of the test project, the quality and quantity of available data increases dramatically. A logistic regression model has been developed form the data collected over the last five years, allowing the probability of successfully completing a rocket propulsion component test to be calculated. 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. Logistic regression has primarily been used in the fields of epidemiology and biomedical research, but lends itself to many other applications. As indicated the use of logistic regression 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 the models provide project managers with insight and confidence into the affectivity of rocket engine component ground test projects. The initial success in modeling rocket propulsion ground test projects clears the way for more complex models to be developed in this area.

Variables Associated with Repeated Suicide Attempt in a Criminal Justice Population

ERIC Educational Resources Information Center

Hakansson, Anders; Bradvik, Louise; Schlyter, Frans; Berglund, Mats

2011-01-01

The aim of this study was to identify factors associated with repeated suicide attempts among criminal justice clients examined for substance abuse using the Addiction Severity Index. Among suicide attempters (n = 1,404), repeaters (two or more attempts, n = 770) were compared to nonrepeaters. In logistic regression, repetition was associated with…

Geospatial relationships of tree species damage caused by Hurricane Katrina in south Mississippi

Treesearch

Mark W. Garrigues; Zhaofei Fan; David L. Evans; Scott D. Roberts; William H. Cooke III

2012-01-01

Hurricane Katrina generated substantial impacts on the forests and biological resources of the affected area in Mississippi. This study seeks to use classification tree analysis (CTA) to determine which variables are significant in predicting hurricane damage (shear or windthrow) in the Southeast Mississippi Institute for Forest Inventory District. Logistic regressions...

Contributors to Suicidal Ideation among Bipolar Patients with and without a History of Suicide Attempts

ERIC Educational Resources Information Center

Allen, Michael H.; Chessick, Cheryl A.; Miklowitz, David J.; Goldberg, Joseph F.; Wisniewski, Stephen R.; Miyahara, Sachiko; Calabrese, Joseph R.; Marangell, Lauren; Bauer, Mark S.; Thomas, Marshall R.; Bowden, Charles L.; Sachs, Gary S.

2005-01-01

This study was designed to develop models for vulnerability to suicidal ideation in bipolar patients. Logistic regression models examined correlates of suicidal ideation in patients who had versus had not attempted suicide previously. Of 477 patients assessed, complete data on demographic, illness history, and personality variables were available…

Predicting and Managing Turnover in Human Service Agencies: A Case Study of an Organization in Crisis.

ERIC Educational Resources Information Center

Balfour, Danny L.; Neff, Donna M.

1993-01-01

A logistic regression model applied to data from 171 child service caseworkers identified variables determining job turnover during times of intense external criticism of the agency (length of service, professional commitment, level of education). A special training program did not significantly reduce the probability of turnover. (SK)

The Role of Family, Religiosity, and Behavior in Adolescent Gambling

ERIC Educational Resources Information Center

Casey, David M.; Williams, Robert J.; Mossiere, Annik M.; Schopflocher, Donald P.; el-Guebaly, Nady; Hodgins, David C.; Smith, Garry J.; Wood, Robert T.

2011-01-01

Predictors of adolescent gambling behavior were examined in a sample of 436 males and females (ages 13-16). A biopsychosocial model was used to identify key variables that differentiate between non-gambling and gambling adolescents. Logistic regression found that, as compared to adolescent male non-gamblers, adolescent male gamblers were older,…

Predictors of Success in Accelerated and Enrichment Summer Mathematics Courses for Academically Talented Adolescents

ERIC Educational Resources Information Center

Young, Adena E.; Worrell, Frank C.; Gabelko, Nina H.

2011-01-01

In this study, we used logistic regression to examine how well student background and prior achievement variables predicted success among students attending accelerated and enrichment mathematics courses at a summer program (N = 459). Socioeconomic status, grade point average (GPA), and mathematics diagnostic test scores significantly predicted…

Predictors of Employment for Youths with Visual Impairments: Findings from the Second National Longitudinal Transition Study

ERIC Educational Resources Information Center

McDonnall, Michele Capella

2011-01-01

The study reported here identified factors that predict employment for transition-age youths with visual impairments. Logistic regression was used to predict employment at two levels. Significant variables were early and recent work experiences, completion of a postsecondary program, difficulty with transportation, independent travel skills, and…

Hispanic Community College Students: Acculturation, Family Support, Perceived Educational Barriers, and Vocational Planning

ERIC Educational Resources Information Center

Fiebig, Jennifer Nepper; Braid, Barbara L.; Ross, Patricia A.; Tom, Matthew A.; Prinzo, Cara

2010-01-01

A multiple logistic regression model was used to determine the associations between the role of acculturation, perception of educational barriers, need for family kin support, vocational planning, and expectations for attaining future vocational goals against the demographic variables (gender, age, being the oldest child, the first to attend…

Transitioning Transfer Students: Interactive Factors that Influence First-Year Retention

ERIC Educational Resources Information Center

Luo, Mingchu; Williams, James E.; Vieweg, Bruce

2007-01-01

This study examined the diverse patterns of interactive factors that influence transfer students' first-year retention at a midsize four-year university. The population for this study consisted of five cohorts totaling 1,713 full-time, degree-seeking transfer students. Sequential sets of logistic regression analyses on blocks of variables were…

Competitive Employment for People with Autism: Correlates of Successful Closure in Competitive and Supported Employment

ERIC Educational Resources Information Center

Schaller, James; Yang, Nancy K.

2005-01-01

Differences in rates of case closure, case service cost, hours worked per week, and weekly wage between customers with autism closed successfully in competitive employment and supported employment were found using the Rehabilitation Service Administration national database of 2001. Using logistic regression, customer demographic variables related…

A Survival Model for Shortleaf Pine Tress Growing in Uneven-Aged Stands

Treesearch

Thomas B. Lynch; Lawrence R. Gering; Michael M. Huebschmann; Paul A. Murphy

1999-01-01

A survival model for shortleaf pine (Pinus echinata Mill.) trees growing in uneven-aged stands was developed using data from permanently established plots maintained by an industrial forestry company in western Arkansas. Parameters were fitted to a logistic regression model with a Bernoulli dependent variable in which "0" represented...

Predicting College Success: Achievement, Demographic, and Psychosocial Predictors of First-Semester College Grade Point Average

ERIC Educational Resources Information Center

Saltonstall, Margot

2013-01-01

This study seeks to advance and expand research on college student success. Using multinomial logistic regression analysis, the study investigates the contribution of psychosocial variables above and beyond traditional achievement and demographic measures to predicting first-semester college grade point average (GPA). It also investigates if…

Risk and protective factors of posttraumatic stress disorder among African American women living with HIV.

PubMed

Andu, Eaden; Wagenaar, Brad H; Kemp, Chris G; Nevin, Paul E; Simoni, Jane M; Andrasik, Michele; Cohn, Susan E; French, Audrey L; Rao, Deepa

2018-04-26

We sought to examine risk and protective factors for Posttraumatic Stress Disorder (PTSD) among African American women living with HIV. This is a cross-sectional analysis of baseline data from a randomized trial of an HIV stigma reduction intervention. We examined data from two-hundred and thirty-nine African American women living with HIV. We examined whether age, marital status, level of education, internalized HIV-related stigma, and social support as potential protective and risk factors for PTSD symptoms using logistic regression. We analyzed bi-variate associations between each variable and PTSD symptoms, and constructed a multivariate logistic regression model adjusting for all variables. We found 67% reported clinically significant PTSD symptoms at baseline. Our results suggest that age, education, and internalized stigma were found to be associated with PTSD symptoms (p < 0.001), with older age and more education as protective factors and stigma as a risk factor for PTSD. Therefore, understanding this relationship may help improve assessment and treatment through evidence- based and trauma-informed strategies.

The contribution of culture to Korean American women's cervical cancer screening behavior: the critical role of prevention orientation.

PubMed

Lee, Hee Yun; Roh, Soonhee; Vang, Suzanne; Jin, Seok Won

2011-01-01

Despite the proven benefits of Pap testing, Korean American women have one of the lowest cervical cancer screening rates in the United States. This study examined how cultural factors are associated with Pap test utilization among Korean American women participants. Quota sampling was used to recruit 202 Korean American women participants residing in New York City. Hierarchical logistic regression was used to assess the association of cultural variables with Pap test receipt. Overall, participants in our study reported significantly lower Pap test utilization; only 58% reported lifetime receipt of this screening test. Logistic regression analysis revealed one of the cultural variables--prevention orientation--was the strongest correlate of recent Pap test use. Older age and married status were also found to be significant predictors of Pap test use. Findings suggest cultural factors should be considered in interventions promoting cervical cancer screening among Korean American women. Furthermore, younger Korean American women and those not living with a spouse/partner should be targeted in cervical cancer screening efforts.

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

Demand analysis of flood insurance by using logistic regression model and genetic algorithm

NASA Astrophysics Data System (ADS)

Sidi, P.; Mamat, M. B.; Sukono; Supian, S.; Putra, A. S.

2018-03-01

Citarum River floods in the area of South Bandung Indonesia, often resulting damage to some buildings belonging to the people living in the vicinity. One effort to alleviate the risk of building damage is to have flood insurance. The main obstacle is not all people in the Citarum basin decide to buy flood insurance. In this paper, we intend to analyse the decision to buy flood insurance. It is assumed that there are eight variables that influence the decision of purchasing flood assurance, include: income level, education level, house distance with river, building election with road, flood frequency experience, flood prediction, perception on insurance company, and perception towards government effort in handling flood. The analysis was done by using logistic regression model, and to estimate model parameters, it is done with genetic algorithm. The results of the analysis shows that eight variables analysed significantly influence the demand of flood insurance. These results are expected to be considered for insurance companies, to influence the decision of the community to be willing to buy flood insurance.

[Depressive symptoms among medical intern students in a Brazilian public university].

PubMed

Costa, Edméa Fontes de Oliva; Santana, Ygo Santos; Santos, Ana Teresa Rodrigues de Abreu; Martins, Luiz Antonio Nogueira; Melo, Enaldo Vieira de; Andrade, Tarcísio Matos de

2012-01-01

To estimate, among Medical School intern students, the prevalence of depressive symptoms and their severity, as well as associated factors. Cross-sectional study in May 2008, with a representative sample of medical intern students (n = 84) from Universidade Federal de Sergipe (UFS). Beck Depression Inventory (BDI) and a structured questionnaire containing information on sociodemographic variables, teaching-learning process, and personal aspects were used. The exploratory data analysis was performed by descriptive and inferential statistics. Finally, the analysis of multiple variables by logistic regression and the calculation of simple and adjusted ORs with their respective 95% confidence intervals were performed. The general prevalence was 40.5%, with 1.2% (95% CI: 0.0-6.5) of severe depressive symptoms; 4.8% (95% CI: 1.3-11.7) of moderate depressive symptoms; and 34.5% (95% CI: 24.5-45.7) of mild depressive symptoms. The logistic regression revealed the variables with a major impact associated with the emergence of depressive symptoms: thoughts of dropping out (OR 6.24; p = 0.002); emotional stress (OR 7.43;p = 0.0004); and average academic performance (OR 4.74; p = 0.0001). The high prevalence of depressive symptoms in the study population was associated with variables related to the teaching-learning process and personal aspects, suggesting immediate preemptive measures regarding Medical School graduation and student care are required.

Induced abortion: risk factors for adolescent female students, a Brazilian study.

PubMed

Correia, Divanise S; Cavalcante, Jairo C; Maia, Eulália M C

2009-12-16

The purpose of this study was to analyze risk factors for abortion among female teenagers from 12 to 19 years of age in the city of Maceió, Brazil. This is a cross-sectional study, conducted in ten schools. The sample was calculated by considering the number of admissions for postabortion curettage, obtained from the Information System of Hospitalization. Data were obtained through a semi-structured questionnaire divided into three basic blocks of data: sociodemographic, sexual life, and pregnancy/abortion. To analyze the data, the logistic regression model was used. The Forward Method was chosen to set the final model that minimizes the number of variables and maximizes the accuracy of the model. The significant analysis between the dichotomous variables provided eight significant variables. Two of them are protective for abortion: the ages 12-14 years and talking with parents about sex. After the logistic regression, the receipt of support for abortion was the most significant variable of all. The adolescent with an active sexual life, a previous pregnancy, who is married, and has received support for an abortion has a 99.74% probability for an abortion. The results of this study, demonstrating the importance of the group in adolescence, and the statistical significance of having a partner to support and approve the pregnancy appears as a preventive factor for abortion. It shows the importance of support and companionship for adolescent women.

Statistical Methods for Quality Control of Steel Coils Manufacturing Process using Generalized Linear Models

NASA Astrophysics Data System (ADS)

García-Díaz, J. Carlos

2009-11-01

Fault detection and diagnosis is an important problem in process engineering. Process equipments are subject to malfunctions during operation. Galvanized steel is a value added product, furnishing effective performance by combining the corrosion resistance of zinc with the strength and formability of steel. Fault detection and diagnosis is an important problem in continuous hot dip galvanizing and the increasingly stringent quality requirements in automotive industry has also demanded ongoing efforts in process control to make the process more robust. When faults occur, they change the relationship among these observed variables. This work compares different statistical regression models proposed in the literature for estimating the quality of galvanized steel coils on the basis of short time histories. Data for 26 batches were available. Five variables were selected for monitoring the process: the steel strip velocity, four bath temperatures and bath level. The entire data consisting of 48 galvanized steel coils was divided into sets. The first training data set was 25 conforming coils and the second data set was 23 nonconforming coils. Logistic regression is a modeling tool in which the dependent variable is categorical. In most applications, the dependent variable is binary. The results show that the logistic generalized linear models do provide good estimates of quality coils and can be useful for quality control in manufacturing process.

[Suicidal Behavior and Attention Decifit Hyperactivity Disorder in Adolescents of Medellin (Colombia), 2011-2012].

PubMed

Restrepo-Bernal, Diana; Bonfante-Olivares, Laura; Torres de Galvis, Yolanda; Berbesi-Fernández, Dedsy; Sierra-Hincapié, Gloria

2014-01-01

Suicide is a public health problem. In Colombia, teenagers are considered a group at high risk for suicidal behavior. To explore the possible association between suicidal behavior and attention deficit hyperactivity disorder in adolescents of Medellin. Observational, cross-sectional, analytical study. The Composite International Diagnostic Interview was applied to a total of 447 adolescents and the sociodemographic, clinical, familiar, and life event variables of interest were analyzed. The descriptive analysis of qualitative variables are presented as absolute values and frequencies, and the age was described with median [interquartile range]. A logistic regression model was constructed with explanatory variables that showed statistical association. Data were analyzed with SPSS® software version 21.0. Of the total, 59.1% were female, and the median age was 16 [14-18] years. Suicidal behavior was presented in 31% of females and 23% of males. Attention deficit was present in 6.3% of adolescents. The logistic regression analysis showed that the variables that best explained the suicidal behavior of adolescents were: female sex, post-traumatic stress disorder, panic disorder, and cocaine use. The diagnosis and early intervention of attention deficit hyperactivity disorder in children may be a useful strategy in the prevention of suicidal behavior in adolescents. Copyright © 2014 Asociación Colombiana de Psiquiatría. Publicado por Elsevier España. All rights reserved.

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.

Geographic information systems and logistic regression for high-resolution malaria risk mapping in a rural settlement of the southern Brazilian Amazon.

PubMed

de Oliveira, Elaine Cristina; dos Santos, Emerson Soares; Zeilhofer, Peter; Souza-Santos, Reinaldo; Atanaka-Santos, Marina

2013-11-15

In Brazil, 99% of the cases of malaria are concentrated in the Amazon region, with high level of transmission. The objectives of the study were to use geographic information systems (GIS) analysis and logistic regression as a tool to identify and analyse the relative likelihood and its socio-environmental determinants of malaria infection in the Vale do Amanhecer rural settlement, Brazil. A GIS database of georeferenced malaria cases, recorded in 2005, and multiple explanatory data layers was built, based on a multispectral Landsat 5 TM image, digital map of the settlement blocks and a SRTM digital elevation model. Satellite imagery was used to map the spatial patterns of land use and cover (LUC) and to derive spectral indices of vegetation density (NDVI) and soil/vegetation humidity (VSHI). An Euclidian distance operator was applied to measure proximity of domiciles to potential mosquito breeding habitats and gold mining areas. The malaria risk model was generated by multiple logistic regression, in which environmental factors were considered as independent variables and the number of cases, binarized by a threshold value was the dependent variable. Out of a total of 336 cases of malaria, 133 positive slides were from inhabitants at Road 08, which corresponds to 37.60% of the notifications. The southern region of the settlement presented 276 cases and a greater number of domiciles in which more than ten cases/home were notified. From these, 102 (30.36%) cases were caused by Plasmodium falciparum and 174 (51.79%) cases by Plasmodium vivax. Malaria risk is the highest in the south of the settlement, associated with proximity to gold mining sites, intense land use, high levels of soil/vegetation humidity and low vegetation density. Mid-resolution, remote sensing data and GIS-derived distance measures can be successfully combined with digital maps of the housing location of (non-) infected inhabitants to predict relative likelihood of disease infection through the analysis by logistic regression. Obtained findings on the relation between malaria cases and environmental factors should be applied in the future for land use planning in rural settlements in the Southern Amazon to minimize risks of disease transmission.

Neuropsychological Test Selection for Cognitive Impairment Classification: A Machine Learning Approach

PubMed Central

Williams, Jennifer A.; Schmitter-Edgecombe, Maureen; Cook, Diane J.

2016-01-01

Introduction Reducing the amount of testing required to accurately detect cognitive impairment is clinically relevant. The aim of this research was to determine the fewest number of clinical measures required to accurately classify participants as healthy older adult, mild cognitive impairment (MCI) or dementia using a suite of classification techniques. Methods Two variable selection machine learning models (i.e., naive Bayes, decision tree), a logistic regression, and two participant datasets (i.e., clinical diagnosis, clinical dementia rating; CDR) were explored. Participants classified using clinical diagnosis criteria included 52 individuals with dementia, 97 with MCI, and 161 cognitively healthy older adults. Participants classified using CDR included 154 individuals CDR = 0, 93 individuals with CDR = 0.5, and 25 individuals with CDR = 1.0+. Twenty-seven demographic, psychological, and neuropsychological variables were available for variable selection. Results No significant difference was observed between naive Bayes, decision tree, and logistic regression models for classification of both clinical diagnosis and CDR datasets. Participant classification (70.0 – 99.1%), geometric mean (60.9 – 98.1%), sensitivity (44.2 – 100%), and specificity (52.7 – 100%) were generally satisfactory. Unsurprisingly, the MCI/CDR = 0.5 participant group was the most challenging to classify. Through variable selection only 2 – 9 variables were required for classification and varied between datasets in a clinically meaningful way. Conclusions The current study results reveal that machine learning techniques can accurately classifying cognitive impairment and reduce the number of measures required for diagnosis. PMID:26332171

Climate controls the distribution of a widespread invasive species: Implications for future range expansion

USGS Publications Warehouse

McDowell, W.G.; Benson, A.J.; Byers, J.E.

2014-01-01

1. Two dominant drivers of species distributions are climate and habitat, both of which are changing rapidly. Understanding the relative importance of variables that can control distributions is critical, especially for invasive species that may spread rapidly and have strong effects on ecosystems. 2. Here, we examine the relative importance of climate and habitat variables in controlling the distribution of the widespread invasive freshwater clam Corbicula fluminea, and we model its future distribution under a suite of climate scenarios using logistic regression and maximum entropy modelling (MaxEnt). 3. Logistic regression identified climate variables as more important than habitat variables in controlling Corbicula distribution. MaxEnt modelling predicted Corbicula's range expansion westward and northward to occupy half of the contiguous United States. By 2080, Corbicula's potential range will expand 25–32%, with more than half of the continental United States being climatically suitable. 4. Our combination of multiple approaches has revealed the importance of climate over habitat in controlling Corbicula's distribution and validates the climate-only MaxEnt model, which can readily examine the consequences of future climate projections. 5. Given the strong influence of climate variables on Corbicula's distribution, as well as Corbicula's ability to disperse quickly and over long distances, Corbicula is poised to expand into New England and the northern Midwest of the United States. Thus, the direct effects of climate change will probably be compounded by the addition of Corbicula and its own influences on ecosystem function.

[The role of uric acid in the insulin resistance in children and adolescents with obesity].

PubMed

de Miranda, Josiane Aparecida; Almeida, Guilherme Gomide; Martins, Raissa Isabelle Leão; Cunha, Mariana Botrel; Belo, Vanessa Almeida; dos Santos, José Eduardo Tanus; Mourão-Júnior, Carlos Alberto; Lanna, Carla Márcia Moreira

2015-12-01

To investigate the association between serum uric acid levels and insulin resistance in children and adolescents with obesity. Cross-sectional study with 245 children and adolescents (134 obese and 111 controls), aged 8 to 18 years. The anthropometric variables (weight, height and waist circumference), blood pressure and biochemical parameters were collected. The clinical characteristics of the groups were analyzed by t-test or chi-square test. To evaluate the association between uric acid levels and insulin resistance the Pearson's test and logistic regression were applied. The prevalence of insulin resistance was 26.9%. The anthropometric variables, systolic and diastolic blood pressure and biochemical variables were significantly higher in the obese group (p<0.001), except for the high-density-lipoprotein cholesterol. There was a positive and significant correlation between anthropometric variables and uric acid with HOMA-IR in the obese and in the control groups, which was higher in the obese group and in the total sample. The logistic regression model that included age, gender and obesity, showed an odds ratio of uric acid as a variable associated with insulin resistance of 1.91 (95%CI 1.40 to 2.62; p<-0.001). The increase in serum uric acid showed a positive statistical correlation with insulin resistance and it is associated with and increased risk of insulin resistance in obese children and adolescents. Copyright © 2015 Sociedade de Pediatria de São Paulo. Publicado por Elsevier Editora Ltda. All rights reserved.

Teaching a Machine to Feel Postoperative Pain: Combining High-Dimensional Clinical Data with Machine Learning Algorithms to Forecast Acute Postoperative Pain

PubMed Central

Tighe, Patrick J.; Harle, Christopher A.; Hurley, Robert W.; Aytug, Haldun; Boezaart, Andre P.; Fillingim, Roger B.

2015-01-01

Background Given their ability to process highly dimensional datasets with hundreds of variables, machine learning algorithms may offer one solution to the vexing challenge of predicting postoperative pain. Methods Here, we report on the application of machine learning algorithms to predict postoperative pain outcomes in a retrospective cohort of 8071 surgical patients using 796 clinical variables. Five algorithms were compared in terms of their ability to forecast moderate to severe postoperative pain: Least Absolute Shrinkage and Selection Operator (LASSO), gradient-boosted decision tree, support vector machine, neural network, and k-nearest neighbor, with logistic regression included for baseline comparison. Results In forecasting moderate to severe postoperative pain for postoperative day (POD) 1, the LASSO algorithm, using all 796 variables, had the highest accuracy with an area under the receiver-operating curve (ROC) of 0.704. Next, the gradient-boosted decision tree had an ROC of 0.665 and the k-nearest neighbor algorithm had an ROC of 0.643. For POD 3, the LASSO algorithm, using all variables, again had the highest accuracy, with an ROC of 0.727. Logistic regression had a lower ROC of 0.5 for predicting pain outcomes on POD 1 and 3. Conclusions Machine learning algorithms, when combined with complex and heterogeneous data from electronic medical record systems, can forecast acute postoperative pain outcomes with accuracies similar to methods that rely only on variables specifically collected for pain outcome prediction. PMID:26031220

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.

Comparison of multinomial logistic regression and logistic regression: which is more efficient in allocating land use?

NASA Astrophysics Data System (ADS)

Lin, Yingzhi; Deng, Xiangzheng; Li, Xing; Ma, Enjun

2014-12-01

Spatially explicit simulation of land use change is the basis for estimating the effects of land use and cover change on energy fluxes, ecology and the environment. At the pixel level, logistic regression is one of the most common approaches used in spatially explicit land use allocation models to determine the relationship between land use and its causal factors in driving land use change, and thereby to evaluate land use suitability. However, these models have a drawback in that they do not determine/allocate land use based on the direct relationship between land use change and its driving factors. Consequently, a multinomial logistic regression method was introduced to address this flaw, and thereby, judge the suitability of a type of land use in any given pixel in a case study area of the Jiangxi Province, China. A comparison of the two regression methods indicated that the proportion of correctly allocated pixels using multinomial logistic regression was 92.98%, which was 8.47% higher than that obtained using logistic regression. Paired t-test results also showed that pixels were more clearly distinguished by multinomial logistic regression than by logistic regression. In conclusion, multinomial logistic regression is a more efficient and accurate method for the spatial allocation of land use changes. The application of this method in future land use change studies may improve the accuracy of predicting the effects of land use and cover change on energy fluxes, ecology, and environment.

Logistic regression models for predicting physical and mental health-related quality of life in rheumatoid arthritis patients.

PubMed

Alishiri, Gholam Hossein; Bayat, Noushin; Fathi Ashtiani, Ali; Tavallaii, Seyed Abbas; Assari, Shervin; Moharamzad, Yashar

2008-01-01

The aim of this work was to develop two logistic regression models capable of predicting physical and mental health related quality of life (HRQOL) among rheumatoid arthritis (RA) patients. In this cross-sectional study which was conducted during 2006 in the outpatient rheumatology clinic of our university hospital, Short Form 36 (SF-36) was used for HRQOL measurements in 411 RA patients. A cutoff point to define poor versus good HRQOL was calculated using the first quartiles of SF-36 physical and mental component scores (33.4 and 36.8, respectively). Two distinct logistic regression models were used to derive predictive variables including demographic, clinical, and psychological factors. The sensitivity, specificity, and accuracy of each model were calculated. Poor physical HRQOL was positively associated with pain score, disease duration, monthly family income below 300 US$, comorbidity, patient global assessment of disease activity or PGA, and depression (odds ratios: 1.1; 1.004; 15.5; 1.1; 1.02; 2.08, respectively). The variables that entered into the poor mental HRQOL prediction model were monthly family income below 300 US$, comorbidity, PGA, and bodily pain (odds ratios: 6.7; 1.1; 1.01; 1.01, respectively). Optimal sensitivity and specificity were achieved at a cutoff point of 0.39 for the estimated probability of poor physical HRQOL and 0.18 for mental HRQOL. Sensitivity, specificity, and accuracy of the physical and mental models were 73.8, 87, 83.7% and 90.38, 70.36, 75.43%, respectively. The results show that the suggested models can be used to predict poor physical and mental HRQOL separately among RA patients using simple variables with acceptable accuracy. These models can be of use in the clinical decision-making of RA patients and to recognize patients with poor physical or mental HRQOL in advance, for better management.

Youth tobacco sales in a metropolitan county: factors associated with compliance.

PubMed

Pearson, Dave C; Song, Lin; Valdez, Roger B; Angulo, Antoinette S

2007-08-01

To describe and identify factors associated with tobacco sales in a metropolitan county. King County, Washington is the largest county in Washington State with an estimated population of 1.8 million or about 30% of the state's population. The data analysis is based on compliance checks in King County between January 2001 and March 2005. The 8879 checks were conducted by 91 youth operatives aged 14-17. Analysis of data was completed in 2006. The outcome variable for this analysis was whether "a sale was made" to a youth operative during a compliance check. Associations between independent variables and the outcome variable were examined using 2 x 2 tables, univariate (unadjusted) logistic regression, and multivariate (adjusted) logistic regression analysis. Overall tobacco sales during the 4-year and 3-month period was 7.7%. Convenience stores selling gas were significantly more likely to sell tobacco products to minors, whereas restaurants, bars, and tobacco discount stores were less likely to sell to minors. Other factors that were significantly associated with sales are described. In a county that has adopted many of the required youth access laws, opportunities still exist to reduce sales of tobacco products to minors. Asking for age and photo identification still appears to be an effective strategy in reducing sales of tobacco products to minors.

Heart rate reactivity and current post-traumatic stress disorder when data are missing.

PubMed

Jeon-Slaughter, Haekyung; Tucker, Phebe; Pfefferbaum, Betty; North, Carol S; de Andrade, Bernardo Borba; Neas, Barbara

2011-08-01

This study demonstrates that auxiliary and exclusion criteria variables increase the effectiveness of missing imputation in correcting underestimation of physiologic reactivity in relation to post-traumatic stress disorder (PTSD) caused by deleting cases with missing physiologic data. This study used data from survivors of the 1995 Oklahoma City bombing and imputed missing heart rate data using auxiliary and exclusion criteria variables. Logistic regression was used to examine heart rate reactivity in relation to current PTSD. Of 113 survivors who participated in the bombing study's 7-year follow-up interview, 42 (37%) had missing data on heart rate reactivity due to exclusion criteria (medical illness or use of cardiovascular or psychotropic medications) or non-participation. Logistic regression results based on imputed heart rate data using exclusion criteria and auxiliary (the presence of any current PTSD arousal symptoms) variables showed that survivors with current bombing-related PTSD had significantly higher heart rates at baseline and recovered more slowly back to baseline heart rate during resting periods than survivors without current PTSD, while results based on complete cases failed to show significant correlations between current PTSD and heart rates at any assessment points. Suggested methods yielded an otherwise undetectable link between physiology and current PTSD. © 2011 The Authors. Psychiatry and Clinical Neurosciences © 2011 Japanese Society of Psychiatry and Neurology.

Factors Affecting the Clinical Success Rate of Miniscrew Implants for Orthodontic Treatment.

PubMed

Jing, Zheng; Wu, Yeke; Jiang, Wenlu; Zhao, Lixing; Jing, Dian; Zhang, Nian; Cao, Xiaoqing; Xu, Zhenrui; Zhao, Zhihe

2016-01-01

The purpose of this study was to evaluate the various factors that influence the success rate of miniscrew implants used as orthodontic anchorage. Potential confounding variables examined were sex, age, vertical (FMA) and sagittal (ANB) skeletal facial pattern, site of placement (labial and buccal, palatal, and retromandibular triangle), arch of placement (maxilla and mandible), placement soft tissue type, oral hygiene, diameter and length of miniscrew implants, insertion method (predrilled or drill-free), angle of placement, onset and strength of force application, and clinical purpose. The correlations between success rate and overall variables were investigated by logistic regression analysis, and the effect of each variable on the success rate was utilized by variance analysis. One hundred fourteen patients were included with a total of 253 miniscrew implants. The overall success rate was 88.54% with an average loading period of 9.5 months in successful cases. Age, oral hygiene, vertical skeletal facial pattern (FMA), and general placement sites (maxillary and mandibular) presented significant differences in success rates both by logistic regression analysis and variance analysis (P < .05). To minimize the failure of miniscrew implants, proper oral hygiene instruction and effective supervision should be given for patients, especially young (< 12 years) high-angle patients with miniscrew implants placed in the mandible.

Factors associated with utilization of long-acting and permanent contraceptive methods among women who have decided not to have more children in Gondar city.

PubMed

Zenebe, Chernet Baye; Adefris, Mulat; Yenit, Melaku Kindie; Gelaw, Yalemzewod Assefa

2017-09-06

Despite the fact that long acting family planning methods reduce population growth and improve maternal health, their utilization remains poor. Therefore, this study assessed the prevalence of long acting and permanent family planning method utilization and associated factors among women in reproductive age groups who have decided not to have more children in Gondar city, northwest Ethiopia. An institution based cross-sectional study was conducted from August to October, 2015. Three hundred seventeen women who have decided not to have more children were selected consecutively into the study. A structured and pretested questionnaire was used to collect data. Both bivariate and multi-variable logistic regressions analyses were used to identify factors associated with utilization of long acting and permanent family planning methods. The multi-variable logistic regression analysis was used to investigate factors associated with the utilization of long acting and permanent family planning methods. The Adjusted Odds Ratio (AOR) with the corresponding 95% Confidence Interval (CI) was used to show the strength of associations, and variables with a P-value of <0.05 were considered statistically significant. In this study, the overall prevalence of long acting and permanent contraceptive (LAPCM) method utilization was 34.7% (95% CI: 29.5-39.9). According to the multi-variable logistic regression analysis, utilization of long acting and permanent contraceptive methods was significantly associated with women who had secondary school, (AOR: 2279, 95% CI: 1.17, 4.44), college, and above education (AOR: 2.91, 95% CI: 1.36, 6.24), history of previous utilization (AOR: 3.02, 95% CI: 1.69, 5.38), and information about LAPCM (AOR: 8.85, 95% CI: 2.04, 38.41). In this study the prevalence of long acting and permanent family planning method utilization among women who have decided not to have more children was high compared with previous studies conducted elsewhere. Advanced educational status, previous utilization of LAPCM, and information on LAPCM were significantly associated with the utilization of LAPCM. As a result, strengthening behavioral change communication channels to make information accessible is highly recommended.

Datamining approaches for modeling tumor control probability.

PubMed

Naqa, Issam El; Deasy, Joseph O; Mu, Yi; Huang, Ellen; Hope, Andrew J; Lindsay, Patricia E; Apte, Aditya; Alaly, James; Bradley, Jeffrey D

2010-11-01

Tumor control probability (TCP) to radiotherapy is determined by complex interactions between tumor biology, tumor microenvironment, radiation dosimetry, and patient-related variables. The complexity of these heterogeneous variable interactions constitutes a challenge for building predictive models for routine clinical practice. We describe a datamining framework that can unravel the higher order relationships among dosimetric dose-volume prognostic variables, interrogate various radiobiological processes, and generalize to unseen data before when applied prospectively. Several datamining approaches are discussed that include dose-volume metrics, equivalent uniform dose, mechanistic Poisson model, and model building methods using statistical regression and machine learning techniques. Institutional datasets of non-small cell lung cancer (NSCLC) patients are used to demonstrate these methods. The performance of the different methods was evaluated using bivariate Spearman rank correlations (rs). Over-fitting was controlled via resampling methods. Using a dataset of 56 patients with primary NCSLC tumors and 23 candidate variables, we estimated GTV volume and V75 to be the best model parameters for predicting TCP using statistical resampling and a logistic model. Using these variables, the support vector machine (SVM) kernel method provided superior performance for TCP prediction with an rs=0.68 on leave-one-out testing compared to logistic regression (rs=0.4), Poisson-based TCP (rs=0.33), and cell kill equivalent uniform dose model (rs=0.17). The prediction of treatment response can be improved by utilizing datamining approaches, which are able to unravel important non-linear complex interactions among model variables and have the capacity to predict on unseen data for prospective clinical applications.

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.

Systolic blood pressure variability in patients with early severe sepsis or septic shock: a prospective cohort study.

PubMed

Tang, Yi; Sorenson, Jeff; Lanspa, Michael; Grissom, Colin K; Mathews, V J; Brown, Samuel M

2017-06-17

Severe sepsis and septic shock are often lethal syndromes, in which the autonomic nervous system may fail to maintain adequate blood pressure. Heart rate variability has been associated with outcomes in sepsis. Whether systolic blood pressure (SBP) variability is associated with clinical outcomes in septic patients is unknown. The propose of this study is to determine whether variability in SBP correlates with vasopressor independence and mortality among septic patients. We prospectively studied patients with severe sepsis or septic shock, admitted to an intensive care unit (ICU) with an arterial catheter. We analyzed SBP variability on the first 5-min window immediately following ICU admission. We performed principal component analysis of multidimensional complexity, and used the first principal component (PC 1 ) as input for Firth logistic regression, controlling for mean systolic pressure (SBP) in the primary analyses, and Acute Physiology and Chronic Health Evaluation (APACHE) II score or NEE dose in the ancillary analyses. Prespecified outcomes were vasopressor independence at 24 h (primary), and 28-day mortality (secondary). We studied 51 patients, 51% of whom achieved vasopressor independence at 24 h. Ten percent died at 28 days. PC 1 represented 26% of the variance in complexity measures. PC 1 was not associated with vasopressor independence on Firth logistic regression (OR 1.04; 95% CI: 0.93-1.16; p = 0.54), but was associated with 28-day mortality (OR 1.16, 95% CI: 1.01-1.35, p = 0.040). Early SBP variability appears to be associated with 28-day mortality in patients with severe sepsis and septic shock.

Study of relationship between clinical factors and velopharyngeal closure in cleft palate patients

PubMed Central

Chen, Qi; Zheng, Qian; Shi, Bing; Yin, Heng; Meng, Tian; Zheng, Guang-ning

2011-01-01

BACKGROUND: This study was carried out to analyze the relationship between clinical factors and velopharyngeal closure (VPC) in cleft palate patients. METHODS: Chi-square test was used to compare the postoperative velopharyngeal closure rate. Logistic regression model was used to analyze independent variables associated with velopharyngeal closure. RESULTS: Difference of postoperative VPC rate in different cleft types, operative ages and surgical techniques was significant (P=0.000). Results of logistic regression analysis suggested that when operative age was beyond deciduous dentition stage, or cleft palate type was complete, or just had undergone a simple palatoplasty without levator veli palatini retropositioning, patients would suffer a higher velopharyngeal insufficiency rate after primary palatal repair. CONCLUSIONS: Cleft type, operative age and surgical technique were the contributing factors influencing VPC rate after primary palatal repair of cleft palate patients. PMID:22279464

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…

Producing landslide susceptibility maps by utilizing machine learning methods. The case of Finikas catchment basin, North Peloponnese, Greece.

NASA Astrophysics Data System (ADS)

Tsangaratos, Paraskevas; Ilia, Ioanna; Loupasakis, Constantinos; Papadakis, Michalis; Karimalis, Antonios

2017-04-01

The main objective of the present study was to apply two machine learning methods for the production of a landslide susceptibility map in the Finikas catchment basin, located in North Peloponnese, Greece and to compare their results. Specifically, Logistic Regression and Random Forest were utilized, based on a database of 40 sites classified into two categories, non-landslide and landslide areas that were separated into a training dataset (70% of the total data) and a validation dataset (remaining 30%). The identification of the areas was established by analyzing airborne imagery, extensive field investigation and the examination of previous research studies. Six landslide related variables were analyzed, namely: lithology, elevation, slope, aspect, distance to rivers and distance to faults. Within the Finikas catchment basin most of the reported landslides were located along the road network and within the residential complexes, classified as rotational and translational slides, and rockfalls, mainly caused due to the physical conditions and the general geotechnical behavior of the geological formation that cover the area. Each landslide susceptibility map was reclassified by applying the Geometric Interval classification technique into five classes, namely: very low susceptibility, low susceptibility, moderate susceptibility, high susceptibility, and very high susceptibility. The comparison and validation of the outcomes of each model were achieved using statistical evaluation measures, the receiving operating characteristic and the area under the success and predictive rate curves. The computation process was carried out using RStudio an integrated development environment for R language and ArcGIS 10.1 for compiling the data and producing the landslide susceptibility maps. From the outcomes of the Logistic Regression analysis it was induced that the highest b coefficient is allocated to lithology and slope, which was 2.8423 and 1.5841, respectively. From the estimation of the mean decrease in Gini coefficient performed during the application of Random Forest and the mean decrease in accuracy the most important variable is slope followed by lithology, aspect, elevation, distance from river network, and distance from faults, while the most used variables during the training phase were the variable aspect (21.45%), slope (20.53%) and lithology (19.84%). The outcomes of the analysis are consistent with previous studies concerning the area of research, which have indicated the high influence of lithology and slope in the manifestation of landslides. High percentage of landslide occurrence has been observed in Plio-Pleistocene sediments, flysch formations, and Cretaceous limestone. Also the presences of landslides have been associated with the degree of weathering and fragmentation, the orientation of the discontinuities surfaces and the intense morphological relief. The most accurate model was Random Forest which identified correctly 92.00% of the instances during the training phase, followed by the Logistic Regression 89.00%. The same pattern of accuracy was calculated during the validation phase, in which the Random Forest achieved a classification accuracy of 93.00%, while the Logistic Regression model achieved an accuracy of 91.00%. In conclusion, the outcomes of the study could be a useful cartographic product to local authorities and government agencies during the implementation of successful decision-making and land use planning strategies. Keywords: Landslide Susceptibility, Logistic Regression, Random Forest, GIS, Greece.

Risk factors for low birth weight according to the multiple logistic regression model. A retrospective cohort study in José María Morelos municipality, Quintana Roo, Mexico.

PubMed

Franco Monsreal, José; Tun Cobos, Miriam Del Ruby; Hernández Gómez, José Ricardo; Serralta Peraza, Lidia Esther Del Socorro

2018-01-17

Low birth weight has been an enigma for science over time. There have been many researches on its causes and its effects. Low birth weight is an indicator that predicts the probability of a child surviving. In fact, there is an exponential relationship between weight deficit, gestational age, and perinatal mortality. Multiple logistic regression is one of the most expressive and versatile statistical instruments available for the analysis of data in both clinical and epidemiology settings, as well as in public health. To assess in a multivariate fashion the importance of 17 independent variables in low birth weight (dependent variable) of children born in the Mayan municipality of José María Morelos, Quintana Roo, Mexico. Analytical observational epidemiological cohort study with retrospective temporality. Births that met the inclusion criteria occurred in the "Hospital Integral Jose Maria Morelos" of the Ministry of Health corresponding to the Maya municipality of Jose Maria Morelos during the period from August 1, 2014 to July 31, 2015. The total number of newborns recorded was 1,147; 84 of which (7.32%) had low birth weight. To estimate the independent association between the explanatory variables (potential risk factors) and the response variable, a multiple logistic regression analysis was performed using the IBM SPSS Statistics 22 software. In ascending numerical order values of odds ratio > 1 indicated the positive contribution of explanatory variables or possible risk factors: "unmarried" marital status (1.076, 95% confidence interval: 0.550 to 2.104); age at menarche ≤ 12 years (1.08, 95% confidence interval: 0.64 to 1.84); history of abortion(s) (1.14, 95% confidence interval: 0.44 to 2.93); maternal weight < 50 kg (1.51, 95% confidence interval: 0.83 to 2.76); number of prenatal consultations ≤ 5 (1.86, 95% confidence interval: 0.94 to 3.66); maternal age ≥ 36 years (3.5, 95% confidence interval: 0.40 to 30.47); maternal age ≤ 19 years (3.59, 95% confidence interval: 0.43 to 29.87); number of deliveries = 1 (3.86, 95% confidence interval: 0.33 to 44.85); personal pathological history (4.78, 95% confidence interval: 2.16 to 10.59); pathological obstetric history (5.01, 95% confidence interval: 1.66 to 15.18); maternal height < 150 cm (5.16, 95% confidence interval: 3.08 to 8.65); number of births ≥ 5 (5.99, 95% confidence interval: 0.51 to 69.99); and smoking (15.63, 95% confidence interval: 1.07 to 227.97). Four of the independent variables (personal pathological history, obstetric pathological history, maternal stature <150 centimeters and smoking) showed a significant positive contribution, thus they can be considered as clear risk factors for low birth weight. The use of the logistic regression model in the Mayan municipality of José María Morelos, will allow estimating the probability of low birth weight for each pregnant woman in the future, which will be useful for the health authorities of the region.

Exploring Student Characteristics of Retention That Lead to Graduation in Higher Education Using Data Mining Models

ERIC Educational Resources Information Center

Raju, Dheeraj; Schumacker, Randall

2015-01-01

The study used earliest available student data from a flagship university in the southeast United States to build data mining models like logistic regression with different variable selection methods, decision trees, and neural networks to explore important student characteristics associated with retention leading to graduation. The decision tree…

Background or Experience? Using Logistic Regression to Predict College Retention

ERIC Educational Resources Information Center

Synco, Tracee M.

2012-01-01

Tinto, Astin and countless others have researched the retention and attrition of students from college for more than thirty years. However, the six year graduation rate for all first-time full-time freshmen for the 2002 cohort was 57%. This study sought to determine the retention variables that predicted continued enrollment of entering freshmen…

Persistence of Allegheny woodrats Neotoma magister across the mid-Atlantic Appalachian Highlands landscape, USA

Treesearch

W. Mark Ford; Steven B. Castleberry; Michael T. Mengak; Jane L. Rodrigue; Daniel J. Feller; Kevin R. Russell

2006-01-01

We examined a suite of macro-habitat and landscape variables around active and inactive Allegheny woodrat Neotoma magister colony sites in the Appalachian Mountains of the mid-Atlantic Highlands of Maryland, Virginia, and West Virginia using an information-theoretic modeling approach. Logistic regression analyses suggested that Allegheny woodrat presence was related...

Different Pathways to Juvenile Delinquency: Characteristics of Early and Late Starters in a Sample of Previously Incarcerated Youth

ERIC Educational Resources Information Center

Alltucker, Kevin W.; Bullis, Michael; Close, Daniel; Yovanoff, Paul

2006-01-01

We examined the differences between early and late start juvenile delinquents in a sample of 531 previously incarcerated youth in Oregon's juvenile justice system. Data were analyzed with logistic regression to predict early start delinquency based on four explanatory variables: foster care experience, family criminality, special education…

Using multinomial logistic regression analysis to understand anglers willingness to substitute other fishing locations

Treesearch

Woo-Yong Hyun; Robert B. Ditton

2007-01-01

The concept of recreation substitutability has been a continuing research topic for outdoor recreation researchers. This study explores the relationships among variables regarding the willingness to substitute one location for another location. The objectives of the study are 1) to ascertain and predict the extent to which saltwater anglers were willing to substitute...

Modeling ozone bioindicator injury with microscale and landscape-scale explanatory variables: A logistic regression approach

Treesearch

John W. Coulston

2011-01-01

Tropospheric ozone occurs at phytotoxic levels in the United States (Lefohn and Pinkerton 1988). Several plant species, including commercially important timber species, are sensitive to elevated ozone levels. Exposure to elevated ozone can cause growth reduction and foliar injury and make trees more susceptible to secondary stressors such as insects and pathogens (...

Determining the Factors of Social Phobia Levels of University Students: A Logistic Regression Analysis

ERIC Educational Resources Information Center

Ozen, Hamit

2016-01-01

Experiencing social phobia is an important factor which can hinder academic success during university years. In this study, research of social phobia with several variables is conducted among university students. The research group of the study consists of total 736 students studying at various departments at universities in Turkey. Students are…

Multi scale habitat relationships of Martes americana in northern Idaho, U.S.A.

Treesearch

Tzeidle N. Wasserman; Samuel A. Cushman; David O. Wallin; Jim Hayden

2012-01-01

We used bivariate scaling and logistic regression to investigate multiple-scale habitat selection by American marten (Martes americana). Bivariate scaling reveals dramatic differences in the apparent nature and strength of relationships between marten occupancy and a number of habitat variables across a range of spatial scales. These differences include reversals in...

Psychosocial Correlates of AUDIT-C Hazardous Drinking Risk Status: Implications for Screening and Brief Intervention in College Settings

ERIC Educational Resources Information Center

Wahesh, Edward; Lewis, Todd F.

2015-01-01

The current study identified psychosocial variables associated with AUDIT-C hazardous drinking risk status for male and female college students. Logistic regression analysis revealed that AUDIT-C risk status was associated with alcohol-related negative consequences, injunctive norms, and descriptive norms for both male and female participants.…

Post-fire tree establishment patterns at the alpine treeline ecotone: Mount Rainier National Park, Washington, USA

Treesearch

Kirk M. Stueve; Dawna L. Cerney; Regina M. Rochefort; Laurie L. Kurth

2009-01-01

We performed classification analysis of 1970 satellite imagery and 2003 aerial photography to delineate establishment. Local site conditions were calculated from a LIDAR-based DEM, ancillary climate data, and 1970 tree locations in a GIS. We used logistic regression on a spatially weighted landscape matrix to rank variables.

Predictors of Attrition and Achievement in a Tertiary Bridging Program

ERIC Educational Resources Information Center

Whannell, Robert

2013-01-01

This study examines the attrition and achievement of a sample of 295 students in an on-campus tertiary bridging program at a regional university. A logistic regression analysis using enrolment status, age and the number of absences from scheduled classes at week three of the semester as predictor variables correctly predicted 92.8 percent of…

Individual Differences in Toddlers' Prosociality: Experiences in Early Relationships Explain Variability in Prosocial Behavior

ERIC Educational Resources Information Center

Newton, Emily K.; Thompson, Ross A.; Goodman, Miranda

2016-01-01

Latent class logistic regression analysis was used to investigate sources of individual differences in profiles of prosocial behavior. Eighty-seven 18-month-olds were observed in tasks assessing sharing with a neutral adult, instrumentally helping a neutral adult, and instrumentally helping a sad adult. Maternal mental state language (MSL) and…

HIV Risk Behaviors among Rural Stimulant Users: Variation by Gender and Race/Ethnicity

ERIC Educational Resources Information Center

Wright, Patricia B.; Stewart, Katharine E.; Fischer, Ellen P.; Carlson, Robert G.; Falck, Russel; Wang, Jichuan; Leukefeld, Carl G.; Booth, Brenda M.

2007-01-01

We examined data from a community sample of rural stimulant users (n = 691) in three diverse states to identify gender and racial/ethnic differences in HIV risk behaviors. Bivariate and logistic regression analyses were conducted with six risk behaviors as dependent variables: injecting drugs, trading sex to obtain money or drugs, trading money or…

Propensity score estimation: machine learning and classification methods as alternatives to logistic regression

PubMed Central

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-01-01

Summary Objective Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this Review was to assess machine learning alternatives to logistic regression which may accomplish the same goals but with fewer assumptions or greater accuracy. Study Design and Setting We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. Results We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (CART), and meta-classifiers (in particular, boosting). Conclusion While the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and to a lesser extent decision trees (particularly CART) appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. PMID:20630332

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.

Fungible weights in logistic regression.

PubMed

Jones, Jeff A; Waller, Niels G

2016-06-01

In this article we develop methods for assessing parameter sensitivity in logistic regression models. To set the stage for this work, we first review Waller's (2008) equations for computing fungible weights in linear regression. Next, we describe 2 methods for computing fungible weights in logistic regression. To demonstrate the utility of these methods, we compute fungible logistic regression weights using data from the Centers for Disease Control and Prevention's (2010) Youth Risk Behavior Surveillance Survey, and we illustrate how these alternate weights can be used to evaluate parameter sensitivity. To make our work accessible to the research community, we provide R code (R Core Team, 2015) that will generate both kinds of fungible logistic regression weights. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

Interpreting the concordance statistic of a logistic regression model: relation to the variance and odds ratio of a continuous explanatory variable.

PubMed

Austin, Peter C; Steyerberg, Ewout W

2012-06-20

When outcomes are binary, the c-statistic (equivalent to the area under the Receiver Operating Characteristic curve) is a standard measure of the predictive accuracy of a logistic regression model. An analytical expression was derived under the assumption that a continuous explanatory variable follows a normal distribution in those with and without the condition. We then conducted an extensive set of Monte Carlo simulations to examine whether the expressions derived under the assumption of binormality allowed for accurate prediction of the empirical c-statistic when the explanatory variable followed a normal distribution in the combined sample of those with and without the condition. We also examine the accuracy of the predicted c-statistic when the explanatory variable followed a gamma, log-normal or uniform distribution in combined sample of those with and without the condition. Under the assumption of binormality with equality of variances, the c-statistic follows a standard normal cumulative distribution function with dependence on the product of the standard deviation of the normal components (reflecting more heterogeneity) and the log-odds ratio (reflecting larger effects). Under the assumption of binormality with unequal variances, the c-statistic follows a standard normal cumulative distribution function with dependence on the standardized difference of the explanatory variable in those with and without the condition. In our Monte Carlo simulations, we found that these expressions allowed for reasonably accurate prediction of the empirical c-statistic when the distribution of the explanatory variable was normal, gamma, log-normal, and uniform in the entire sample of those with and without the condition. The discriminative ability of a continuous explanatory variable cannot be judged by its odds ratio alone, but always needs to be considered in relation to the heterogeneity of the population.

Serum Irisin Predicts Mortality Risk in Acute Heart Failure Patients.

PubMed

Shen, Shutong; Gao, Rongrong; Bei, Yihua; Li, Jin; Zhang, Haifeng; Zhou, Yanli; Yao, Wenming; Xu, Dongjie; Zhou, Fang; Jin, Mengchao; Wei, Siqi; Wang, Kai; Xu, Xuejuan; Li, Yongqin; Xiao, Junjie; Li, Xinli

2017-01-01

Irisin is a peptide hormone cleaved from a plasma membrane protein fibronectin type III domain containing protein 5 (FNDC5). Emerging studies have indicated association between serum irisin and many major chronic diseases including cardiovascular diseases. However, the role of serum irisin as a predictor for mortality risk in acute heart failure (AHF) patients is not clear. AHF patients were enrolled and serum was collected at the admission and all patients were followed up for 1 year. Enzyme-linked immunosorbent assay was used to measure serum irisin levels. To explore predictors for AHF mortality, the univariate and multivariate logistic regression analysis, and receiver-operator characteristic (ROC) curve analysis were used. To determine the role of serum irisin levels in predicting survival, Kaplan-Meier survival analysis was used. In this study, 161 AHF patients were enrolled and serum irisin level was found to be significantly higher in patients deceased in 1-year follow-up. The univariate logistic regression analysis identified 18 variables associated with all-cause mortality in AHF patients, while the multivariate logistic regression analysis identified 2 variables namely blood urea nitrogen and serum irisin. ROC curve analysis indicated that blood urea nitrogen and the most commonly used biomarker, NT-pro-BNP, displayed poor prognostic value for AHF (AUCs ≤ 0.700) compared to serum irisin (AUC = 0.753). Kaplan-Meier survival analysis demonstrated that AHF patients with higher serum irisin had significantly higher mortality (P<0.001). Collectively, our study identified serum irisin as a predictive biomarker for 1-year all-cause mortality in AHF patients though large multicenter studies are highly needed. © 2017 The Author(s). Published by S. Karger AG, Basel.

Developing logistic regression models using purchase attributes and demographics to predict the probability of purchases of regular and specialty eggs.

PubMed

Bejaei, M; Wiseman, K; Cheng, K M

2015-01-01

Consumers' interest in specialty eggs appears to be growing in Europe and North America. The objective of this research was to develop logistic regression models that utilise purchaser attributes and demographics to predict the probability of a consumer purchasing a specific type of table egg including regular (white and brown), non-caged (free-run, free-range and organic) or nutrient-enhanced eggs. These purchase prediction models, together with the purchasers' attributes, can be used to assess market opportunities of different egg types specifically in British Columbia (BC). An online survey was used to gather data for the models. A total of 702 completed questionnaires were submitted by BC residents. Selected independent variables included in the logistic regression to develop models for different egg types to predict the probability of a consumer purchasing a specific type of table egg. The variables used in the model accounted for 54% and 49% of variances in the purchase of regular and non-caged eggs, respectively. Research results indicate that consumers of different egg types exhibit a set of unique and statistically significant characteristics and/or demographics. For example, consumers of regular eggs were less educated, older, price sensitive, major chain store buyers, and store flyer users, and had lower awareness about different types of eggs and less concern regarding animal welfare issues. However, most of the non-caged egg consumers were less concerned about price, had higher awareness about different types of table eggs, purchased their eggs from local/organic grocery stores, farm gates or farmers markets, and they were more concerned about care and feeding of hens compared to consumers of other eggs types.

Correlates of consistent condom use among men who have sex with men recruited through the Internet in Huzhou city: a cross-sectional survey.

PubMed

Jin, Meihua; Yang, Zhongrong; Dong, Zhengquan; Han, Jiankang

2013-12-01

There is growing evidence that men who have sex with men (MSM) are currently a group at high risk of HIV infection in China. Our study aims to know the factors affecting consistent condom use among MSM recruited through the internet in Huzhou city. An anonymous cross-sectional study was conducted by recruiting 410 MSM living in Huzhou city via the Internet. The socio-demographic profiles (age, education level, employment status, etc.) and sexual risk behaviors of the respondents were investigated. Bivariate logistic regression analyses were performed to compare the differences between consistent condom users and inconsistent condom users. Variables with significant bivariate between groups' differences were used as candidate variables in a stepwise multivariate logistic regression model. All statistical analyses were performed using SPSS for Windows 17.0, and a p value < 0.05 was considered to be statistically significant. According to their condom use, sixty-eight respondents were classified into two groups. One is consistent condom users, and the other is inconsistent condom users. Multivariate logistic regression showed that respondents who had a comprehensive knowledge of HIV (OR = 4.08, 95% CI: 1.85-8.99), who had sex with male sex workers (OR = 15.30, 95% CI: 5.89-39.75) and who had not drunk alcohol before sex (OR = 3.10, 95% CI: 1.38-6.95) were more likely to be consistent condom users. Consistent condom use among MSM was associated with comprehensive knowledge of HIV and a lack of alcohol use before sexual contact. As a result, reducing alcohol consumption and enhancing education regarding the risks of HIV among sexually active MSM would be effective in preventing of HIV transmission.

Development of the Sydney Falls Risk Screening Tool in brain injury rehabilitation: A multisite prospective cohort study.

PubMed

McKechnie, Duncan; Fisher, Murray J; Pryor, Julie; Bonser, Melissa; Jesus, Jhoven De

2018-03-01

To develop a falls risk screening tool (FRST) sensitive to the traumatic brain injury rehabilitation population. Falls are the most frequently recorded patient safety incident within the hospital context. The inpatient traumatic brain injury rehabilitation population is one particular population that has been identified as at high risk of falls. However, no FRST has been developed for this patient population. Consequently in the traumatic brain injury rehabilitation population, there is the real possibility that nurses are using falls risk screening tools that have a poor clinical utility. Multisite prospective cohort study. Univariate and multiple logistic regression modelling techniques (backward elimination, elastic net and hierarchical) were used to examine each variable's association with patients who fell. The resulting FRST's clinical validity was examined. Of the 140 patients in the study, 41 (29%) fell. Through multiple logistic regression modelling, 11 variables were identified as predictors for falls. Using hierarchical logistic regression, five of these were identified for inclusion in the resulting falls risk screening tool: prescribed mobility aid (such as, wheelchair or frame), a fall since admission to hospital, impulsive behaviour, impaired orientation and bladder and/or bowel incontinence. The resulting FRST has good clinical validity (sensitivity = 0.9; specificity = 0.62; area under the curve = 0.87; Youden index = 0.54). The tool was significantly more accurate (p = .037 on DeLong test) in discriminating fallers from nonfallers than the Ontario Modified STRATIFY FRST. A FRST has been developed using a comprehensive statistical framework, and evidence has been provided of this tool's clinical validity. The developed tool, the Sydney Falls Risk Screening Tool, should be considered for use in brain injury rehabilitation populations. © 2017 John Wiley & Sons Ltd.

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.

Obesity and hypomagnesemia.

PubMed

Guerrero-Romero, Fernando; Flores-García, Araceli; Saldaña-Guerrero, Stephanie; Simental-Mendía, Luis E; Rodríguez-Morán, Martha

2016-10-01

Whether low serum magnesium is an epiphenomenon related with obesity or, whether obesity per se is cause of hypomagnesemia, remains to be clarified. To examine the relationship between body weight status and hypomagnesemia in apparently healthy subjects. A total of 681 healthy individuals aged 30 to 65years were enrolled in A cross-sectional study. Extreme exercise, chronic diarrhea, alcohol intake, use of diuretics, smoking, oral magnesium supplementation, diabetes, malnutrition, hypertension, liver disease, thyroid disorders, and renal damage were exclusion criteria. Based in the Body Mass Index (BMI), body weight status was defined as follows: normal weight (BMI <25kg/m 2 ); overweight (BMI ≥25<30 BMIkg/m 2 ); and obesity (BMI ≥30kg/m 2 ). Hypomagnesemia was defined by serum magnesium concentration ≤0.74mmol/L. A multiple logistic regression analysis was used to compute the odds ratio (OR) between body weight status (independent variables) and hypomagnesemia (dependent variable). The multivariate logistic regression analysis showed that dietary magnesium intake (OR 2.11; 95%CI 1.4-5.7) but no obesity (OR 1.53; 95%CI 0.9-2.5), overweight (OR 1.40; 95%CI 0.8-2.4), and normal weight (OR 0.78; 95%CI 0.6-2.09) were associated with hypomagnesemia. A subsequent logistic regression analysis adjusted by body mass index, waist circumference, total body fat, systolic and diastolic blood pressure, and triglycerides levels showed that hyperglycemia (2.19; 95%CI 1.1-7.0) and dietary magnesium intake (2.21; 95%CI 1.1-8.9) remained associated with hypomagnesemia. Our results show that body weight status is not associated with hypomagnesemia and that, irrespective of obesity, hyperglycemia is cause of hypomagnesemia in non-diabetic individuals. Copyright © 2016 European Federation of Internal Medicine. Published by Elsevier B.V. All rights reserved.

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.

Breast arterial calcification is associated with reproductive factors in asymptomatic postmenopausal women.

PubMed

Bielak, Lawrence F; Whaley, Dana H; Sheedy, Patrick F; Peyser, Patricia A

2010-09-01

The etiology of breast arterial calcification (BAC) is not well understood. We examined reproductive history and cardiovascular disease (CVD) risk factor associations with the presence of detectable BAC in asymptomatic postmenopausal women. Reproductive history and CVD risk factors were obtained in 240 asymptomatic postmenopausal women from a community-based research study who had a screening mammogram within 2 years of their participation in the study. The mammograms were reviewed for the presence of detectable BAC. Age-adjusted logistic regression models were fit to assess the association between each risk factor and the presence of BAC. Multiple variable logistic regression models were used to identify the most parsimonious model for the presence of BAC. The prevalence of BAC increased with increased age (p < 0.0001). The most parsimonious logistic regression model for BAC presence included age at time of examination, increased parity (p = 0.01), earlier age at first birth (p = 0.002), weight, and an age-by-weight interaction term (p = 0.004). Older women with a smaller body size had a higher probability of having BAC than women of the same age with a larger body size. The presence or absence of BAC at mammography may provide an assessment of a postmenopausal woman's lifetime estrogen exposure and indicate women who could be at risk for hormonally related conditions.

Logistic Regression and Path Analysis Method to Analyze Factors influencing Students’ Achievement

NASA Astrophysics Data System (ADS)

Noeryanti, N.; Suryowati, K.; Setyawan, Y.; Aulia, R. R.

2018-04-01

Students' academic achievement cannot be separated from the influence of two factors namely internal and external factors. The first factors of the student (internal factors) consist of intelligence (X1), health (X2), interest (X3), and motivation of students (X4). The external factors consist of family environment (X5), school environment (X6), and society environment (X7). The objects of this research are eighth grade students of the school year 2016/2017 at SMPN 1 Jiwan Madiun sampled by using simple random sampling. Primary data are obtained by distributing questionnaires. The method used in this study is binary logistic regression analysis that aims to identify internal and external factors that affect student’s achievement and how the trends of them. Path Analysis was used to determine the factors that influence directly, indirectly or totally on student’s achievement. Based on the results of binary logistic regression, variables that affect student’s achievement are interest and motivation. And based on the results obtained by path analysis, factors that have a direct impact on student’s achievement are students’ interest (59%) and students’ motivation (27%). While the factors that have indirect influences on students’ achievement, are family environment (97%) and school environment (37).

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.

Immortal time bias in observational studies of time-to-event outcomes.

PubMed

Jones, Mark; Fowler, Robert

2016-12-01

The purpose of the study is to show, through simulation and example, the magnitude and direction of immortal time bias when an inappropriate analysis is used. We compare 4 methods of analysis for observational studies of time-to-event outcomes: logistic regression, standard Cox model, landmark analysis, and time-dependent Cox model using an example data set of patients critically ill with influenza and a simulation study. For the example data set, logistic regression, standard Cox model, and landmark analysis all showed some evidence that treatment with oseltamivir provides protection from mortality in patients critically ill with influenza. However, when the time-dependent nature of treatment exposure is taken account of using a time-dependent Cox model, there is no longer evidence of a protective effect of treatment. The simulation study showed that, under various scenarios, the time-dependent Cox model consistently provides unbiased treatment effect estimates, whereas standard Cox model leads to bias in favor of treatment. Logistic regression and landmark analysis may also lead to bias. To minimize the risk of immortal time bias in observational studies of survival outcomes, we strongly suggest time-dependent exposures be included as time-dependent variables in hazard-based analyses. Copyright © 2016 Elsevier Inc. All rights reserved.

Development and validation of a mortality risk model for pediatric sepsis.

PubMed

Chen, Mengshi; Lu, Xiulan; Hu, Li; Liu, Pingping; Zhao, Wenjiao; Yan, Haipeng; Tang, Liang; Zhu, Yimin; Xiao, Zhenghui; Chen, Lizhang; Tan, Hongzhuan

2017-05-01

Pediatric sepsis is a burdensome public health problem. Assessing the mortality risk of pediatric sepsis patients, offering effective treatment guidance, and improving prognosis to reduce mortality rates, are crucial.We extracted data derived from electronic medical records of pediatric sepsis patients that were collected during the first 24 hours after admission to the pediatric intensive care unit (PICU) of the Hunan Children's hospital from January 2012 to June 2014. A total of 788 children were randomly divided into a training (592, 75%) and validation group (196, 25%). The risk factors for mortality among these patients were identified by conducting multivariate logistic regression in the training group. Based on the established logistic regression equation, the logit probabilities for all patients (in both groups) were calculated to verify the model's internal and external validities.According to the training group, 6 variables (brain natriuretic peptide, albumin, total bilirubin, D-dimer, lactate levels, and mechanical ventilation in 24 hours) were included in the final logistic regression model. The areas under the curves of the model were 0.854 (0.826, 0.881) and 0.844 (0.816, 0.873) in the training and validation groups, respectively.The Mortality Risk Model for Pediatric Sepsis we established in this study showed acceptable accuracy to predict the mortality risk in pediatric sepsis patients.

Development and validation of a mortality risk model for pediatric sepsis

PubMed Central

Chen, Mengshi; Lu, Xiulan; Hu, Li; Liu, Pingping; Zhao, Wenjiao; Yan, Haipeng; Tang, Liang; Zhu, Yimin; Xiao, Zhenghui; Chen, Lizhang; Tan, Hongzhuan

2017-01-01

Abstract Pediatric sepsis is a burdensome public health problem. Assessing the mortality risk of pediatric sepsis patients, offering effective treatment guidance, and improving prognosis to reduce mortality rates, are crucial. We extracted data derived from electronic medical records of pediatric sepsis patients that were collected during the first 24 hours after admission to the pediatric intensive care unit (PICU) of the Hunan Children's hospital from January 2012 to June 2014. A total of 788 children were randomly divided into a training (592, 75%) and validation group (196, 25%). The risk factors for mortality among these patients were identified by conducting multivariate logistic regression in the training group. Based on the established logistic regression equation, the logit probabilities for all patients (in both groups) were calculated to verify the model's internal and external validities. According to the training group, 6 variables (brain natriuretic peptide, albumin, total bilirubin, D-dimer, lactate levels, and mechanical ventilation in 24 hours) were included in the final logistic regression model. The areas under the curves of the model were 0.854 (0.826, 0.881) and 0.844 (0.816, 0.873) in the training and validation groups, respectively. The Mortality Risk Model for Pediatric Sepsis we established in this study showed acceptable accuracy to predict the mortality risk in pediatric sepsis patients. PMID:28514310

Propensity score estimation: neural networks, support vector machines, decision trees (CART), and meta-classifiers as alternatives to logistic regression.

PubMed

Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

2010-08-01

Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this review was to assess machine learning alternatives to logistic regression, which may accomplish the same goals but with fewer assumptions or greater accuracy. We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (classification and regression trees [CART]), and meta-classifiers (in particular, boosting). Although the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and, to a lesser extent, decision trees (particularly CART), appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. Copyright (c) 2010 Elsevier Inc. All rights reserved.

Clusters of anthropometric indicators of body fat associated with maximum oxygen uptake in adolescents

PubMed Central

2018-01-01

Introduction The aim of this study was to evaluate different clusters of anthropometric indicators (body mass index | BMI |, waist circumference | WC |, waist-to-height ratio | WHtR |, triceps skinfold |TR SF|, subscapular skinfold |SE SF|, sum of the triceps and subscapular skinfolds | ΣTR + SE |, and sum of the triceps, subscapular and suprailiac folds | ΣTR + SE + SI|) associated with the VO2max levels in adolescents. Methods The study included 1,132 adolescents (aged 14–19 years) enrolled in public schools of São José, Santa Catarina, Brazil, in the 2014 academic year. The dependent variable was the cluster of anthropometric indicators (BMI, WC, WHtR, TR SF, SE SF, SI SF, ΣTR + SE and ΣTR + SE + SI) of excess body fat. The independent variable was maximum oxygen uptake (VO2max), estimated by the modified Canadian aerobic fitness test—mCAFT. Control variables were: age, skin color, economic level, maternal education, physical activity and sexual maturation. Multinomial logistic regression was used for associations between the dependent and independent variables. Binary logistic regression was performed to identify the association between adolescents with all anthropometric indicators in excess and independent variables. Results One in ten adolescents presented all anthropometric indicators of excess body fat. Multinomial regression showed that with each increase of one VO2max unit, the odds of adolescents having three, four, five or more anthropometric indicators of excess body fat decreased by 0.92, 0.85 and 0.73 times, respectively. In the binary regression, this fact was reconfirmed, demonstrating that with each increase of one VO2max unit, the odds of adolescents having simultaneously the eight anthropometric indicators of excess body fat decreased by 0.55. Conclusion It was concluded that with each increase of one VO2max unit, adolescents decreased the odds of simultaneously presenting three or more anthropometric indicators of excess body fat, regardless of biological, economic and lifestyle factors. In addition, the present study identified that one in ten adolescents had all anthropometric indicators of excess body fat. PMID:29534098

Clusters of anthropometric indicators of body fat associated with maximum oxygen uptake in adolescents.

PubMed

Gonçalves, Eliane Cristina de Andrade; Nunes, Heloyse Elaine Gimenes; Silva, Diego Augusto Santos

2018-01-01

The aim of this study was to evaluate different clusters of anthropometric indicators (body mass index | BMI |, waist circumference | WC |, waist-to-height ratio | WHtR |, triceps skinfold |TR SF|, subscapular skinfold |SE SF|, sum of the triceps and subscapular skinfolds | ΣTR + SE |, and sum of the triceps, subscapular and suprailiac folds | ΣTR + SE + SI|) associated with the VO2max levels in adolescents. The study included 1,132 adolescents (aged 14-19 years) enrolled in public schools of São José, Santa Catarina, Brazil, in the 2014 academic year. The dependent variable was the cluster of anthropometric indicators (BMI, WC, WHtR, TR SF, SE SF, SI SF, ΣTR + SE and ΣTR + SE + SI) of excess body fat. The independent variable was maximum oxygen uptake (VO2max), estimated by the modified Canadian aerobic fitness test-mCAFT. Control variables were: age, skin color, economic level, maternal education, physical activity and sexual maturation. Multinomial logistic regression was used for associations between the dependent and independent variables. Binary logistic regression was performed to identify the association between adolescents with all anthropometric indicators in excess and independent variables. One in ten adolescents presented all anthropometric indicators of excess body fat. Multinomial regression showed that with each increase of one VO2max unit, the odds of adolescents having three, four, five or more anthropometric indicators of excess body fat decreased by 0.92, 0.85 and 0.73 times, respectively. In the binary regression, this fact was reconfirmed, demonstrating that with each increase of one VO2max unit, the odds of adolescents having simultaneously the eight anthropometric indicators of excess body fat decreased by 0.55. It was concluded that with each increase of one VO2max unit, adolescents decreased the odds of simultaneously presenting three or more anthropometric indicators of excess body fat, regardless of biological, economic and lifestyle factors. In addition, the present study identified that one in ten adolescents had all anthropometric indicators of excess body fat.

[Travel time and participation in breast cancer screening in a region with high population dispersion].

PubMed

Borda, Alfredo; Sanz, Belén; Otero, Laura; Blasco, Teresa; García-Gómez, Francisco J; de Andrés, Fuencisla

2011-01-01

To analyze the association between travel time and participation in a breast cancer screening program adjusted for contextual variables in the province of Segovia (Spain). We performed an ecological study using the following data sources: the Breast Cancer Early Detection Program of the Primary Care Management of Segovia, the Population and Housing Census for 2001 and the municipal register for 2006-2007. The study period comprised January 2006 to December 2007. Dependent variables consisted of the municipal participation rate and the desired level of municipal participation (greater than or equal to 70%). The key independent variable was travel time from the municipality to the mammography unit. Covariables consisted of the municipalities' demographic and socioeconomic factors. We performed univariate and multivariate Poisson regression analyses of the participation rate, and logistic regression of the desired participation level. The sample was composed of 178 municipalities. The mean participation rate was 75.2%. The desired level of participation (≥ 70%) was achieved in 119 municipalities (67%). In the multivariate Poisson and logistic regression analyses, longer travel time was associated with a lower participation rate and with lower participation after adjustment was made for geographic density, age, socioeconomic status and dependency ratio, with a relative risk index of 0.88 (95% CI: 0.81-0.96) and an odds ratio of 0.22 (95% CI: 0.1-0.47), respectively. Travel time to the mammography unit may help to explain participation in breast cancer screening programs. Copyright © 2010 SESPAS. Published by Elsevier Espana. All rights reserved.

Why credit risk markets are predestined for exhibiting log-periodic power law structures

NASA Astrophysics Data System (ADS)

Wosnitza, Jan Henrik; Leker, Jens

2014-01-01

Recent research has established the existence of log-periodic power law (LPPL) patterns in financial institutions’ credit default swap (CDS) spreads. The main purpose of this paper is to clarify why credit risk markets are predestined for exhibiting LPPL structures. To this end, the credit risk prediction of two variants of logistic regression, i.e. polynomial logistic regression (PLR) and kernel logistic regression (KLR), are firstly compared to the standard logistic regression (SLR). In doing so, the question whether the performances of rating systems based on balance sheet ratios can be improved by nonlinear transformations of the explanatory variables is resolved. Building on the result that nonlinear balance sheet ratio transformations hardly improve the SLR’s predictive power in our case, we secondly compare the classification performance of a multivariate SLR to the discriminative powers of probabilities of default derived from three different capital market data, namely bonds, CDSs, and stocks. Benefiting from the prompt inclusion of relevant information, the capital market data in general and CDSs in particular increasingly outperform the SLR while approaching the time of the credit event. Due to the higher classification performances, it seems plausible for creditors to align their investment decisions with capital market-based default indicators, i.e., to imitate the aggregate opinion of the market participants. Since imitation is considered to be the source of LPPL structures in financial time series, it is highly plausible to scan CDS spread developments for LPPL patterns. By establishing LPPL patterns in governmental CDS spread trajectories of some European crisis countries, the LPPL’s application to credit risk markets is extended. This novel piece of evidence further strengthens the claim that credit risk markets are adequate breeding grounds for LPPL patterns.

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

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.

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.

London Measure of Unplanned Pregnancy: guidance for its use as an outcome measure

PubMed Central

Hall, Jennifer A; Barrett, Geraldine; Copas, Andrew; Stephenson, Judith

2017-01-01

Background The London Measure of Unplanned Pregnancy (LMUP) is a psychometrically validated measure of the degree of intention of a current or recent pregnancy. The LMUP is increasingly being used worldwide, and can be used to evaluate family planning or preconception care programs. However, beyond recommending the use of the full LMUP scale, there is no published guidance on how to use the LMUP as an outcome measure. Ordinal logistic regression has been recommended informally, but studies published to date have all used binary logistic regression and dichotomized the scale at different cut points. There is thus a need for evidence-based guidance to provide a standardized methodology for multivariate analysis and to enable comparison of results. This paper makes recommendations for the regression method for analysis of the LMUP as an outcome measure. Materials and methods Data collected from 4,244 pregnant women in Malawi were used to compare five regression methods: linear, logistic with two cut points, and ordinal logistic with either the full or grouped LMUP score. The recommendations were then tested on the original UK LMUP data. Results There were small but no important differences in the findings across the regression models. Logistic regression resulted in the largest loss of information, and assumptions were violated for the linear and ordinal logistic regression. Consequently, robust standard errors were used for linear regression and a partial proportional odds ordinal logistic regression model attempted. The latter could only be fitted for grouped LMUP score. Conclusion We recommend the linear regression model with robust standard errors to make full use of the LMUP score when analyzed as an outcome measure. Ordinal logistic regression could be considered, but a partial proportional odds model with grouped LMUP score may be required. Logistic regression is the least-favored option, due to the loss of information. For logistic regression, the cut point for un/planned pregnancy should be between nine and ten. These recommendations will standardize the analysis of LMUP data and enhance comparability of results across studies. PMID:28435343

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.

Prevalence and correlates of cognitive impairment in kidney transplant recipients.

PubMed

Gupta, Aditi; Mahnken, Jonathan D; Johnson, David K; Thomas, Tashra S; Subramaniam, Dipti; Polshak, Tyler; Gani, Imran; John Chen, G; Burns, Jeffrey M; Sarnak, Mark J

2017-05-12

There is a high prevalence of cognitive impairment in dialysis patients. The prevalence of cognitive impairment after kidney transplantation is unknown. Study Design: Cross-sectional study. Single center study of prevalent kidney transplant recipients from a transplant clinic in a large academic center. Assessment of cognition using the Montreal Cognitive Assessment (MoCA). Demographic and clinical variables associated with cognitive impairment were also examined. Outcomes and Measurements: a) Prevalence of cognitive impairment defined by a MoCA score of <26. b) Multivariable linear and logistic regression to examine the association of demographic and clinical factors with cognitive impairment. Data from 226 patients were analyzed. Mean (SD) age was 54 (13.4) years, 73% were white, 60% were male, 37% had diabetes, 58% had an education level of college or above, and the mean (SD) time since kidney transplant was 3.4 (4.1) years. The prevalence of cognitive impairment was 58.0%. Multivariable linear regression demonstrated that older age, male gender and absence of diabetes were associated with lower MoCA scores (p < 0.01 for all). Estimated glomerular filtration rate (eGFR) was not associated with level of cognition. The logistic regression analysis confirmed the association of older age with cognitive impairment. Cognitive impairment is common in prevalent kidney transplant recipients, at a younger age compared to general population, and is associated with certain demographic variables, but not level of eGFR.

A simple measure of cognitive reserve is relevant for cognitive performance in MS patients.

PubMed

Della Corte, Marida; Santangelo, Gabriella; Bisecco, Alvino; Sacco, Rosaria; Siciliano, Mattia; d'Ambrosio, Alessandro; Docimo, Renato; Cuomo, Teresa; Lavorgna, Luigi; Bonavita, Simona; Tedeschi, Gioacchino; Gallo, Antonio

2018-05-04

Cognitive reserve (CR) contributes to preserve cognition despite brain damage. This theory has been applied to multiple sclerosis (MS) to explain the partial relationship between cognition and MRI markers of brain pathology. Our aim was to determine the relationship between two measures of CR and cognition in MS. One hundred and forty-seven MS patients were enrolled. Cognition was assessed using the Rao's Brief Repeatable Battery and the Stroop Test. CR was measured as the vocabulary subtest of the WAIS-R score (VOC) and the number of years of formal education (EDU). Regression analysis included raw score data on each neuropsychological (NP) test as dependent variables and demographic/clinical parameters, VOC, and EDU as independent predictors. A binary logistic regression analysis including clinical/CR parameters as covariates and absence/presence of cognitive deficits as dependent variables was performed too. VOC, but not EDU, was strongly correlated with performances at all ten NP tests. EDU was correlated with executive performances. The binary logistic regression showed that only the Expanded Disability Status Scale (EDSS) and VOC were independently correlated with the presence/absence of CD. The lower the VOC and/or the higher the EDSS, the higher the frequency of CD. In conclusion, our study supports the relevance of CR in subtending cognitive performances and the presence of CD in MS patients.

The effects of cognitive – linguistic variables and language experience on behavioural and kinematic performances in nonword learning

PubMed Central

Sasisekaran, Jayanthi; Weisberg, Sanford

2013-01-01

The aim of the present study was to investigate the effect of cognitive – linguistic variables and language experience on behavioral and kinematic measures of nonword learning in young adults. Group 1 consisted of thirteen participants who spoke American English as the first and only language. Group 2 consisted of seven participants with varying levels of proficiency in a second language. Logistic regression of the percent of correct productions revealed short-term memory to be a significant contributor. The bilingual group showed better performance compared to the monolinguals. Linear regression of the kinematic data revealed that the short – term memory variable contributed significantly to movement coordination. Differences were not observed between the bilingual and the monolingual speakers in kinematic performance. Nonword properties including syllable length and complexity influenced both behavioral and kinematic performance. The findings supported the observation that nonword repetition is multiply determined in adults. PMID:22476630

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.

[Prevalence and factors associated with peripheral artery disease in patients with type 2 diabetes mellitus in Primary Care].

PubMed

Montero-Monterroso, J L; Gascón-Jiménez, J A; Vargas-Rubio, M D; Quero-Salado, C; Villalba-Marín, P; Pérula-de Torres, L A

2015-01-01

Peripheral artery disease in the lower limbs (PAD) is a prevalent condition that entails high morbidity in diabetic patients; this study assesses PAD in these patients and its socio-demographic and clinic associated variables. Descriptive study in a systematic sample of diabetic patients (DM2) aged 50-80 years, in Primary Care settings. The dependent variable was the presence of PAD diagnosed by ankle-brachial index (ABI) ≤ 0.9; independent variables: socio-demographic, clinical and laboratory. bivariate and multiple logistic regression analyses were performed to determine the variables associated with low ABI. A sample of 251 patients, 52.6% women; mean age: 68.5 ±8.5. A low ABI was detected in 18.3% (95% Confidence Interval (95% CI):13.3-23.3%), with 6 subjets (2.4%) previously diagnosed as suffering PAD. Age (OR=1.07; 95% CI: 1.02-1.12) and retinopathy (OR=2.69; 95% CI: 1.06-6.81) were associated (multiple logistic regression analysis) with ABI. The percentage of patients diagnosed with PAD is very low, although PAD prevalence is high among DM2 patients attending Primary Care clinics, especially in older patients and those with retinopathy. We emphasize the recommendation of performing the ABI test in this population at risk. Copyright © 2014 Sociedad Española de Médicos de Atención Primaria (SEMERGEN). Publicado por Elsevier España, S.L.U. All rights reserved.

Panic anxiety, under the weather?

NASA Astrophysics Data System (ADS)

Bulbena, A.; Pailhez, G.; Aceña, R.; Cunillera, J.; Rius, A.; Garcia-Ribera, C.; Gutiérrez, J.; Rojo, C.

2005-03-01

The relationship between weather conditions and psychiatric disorders has been a continuous subject of speculation due to contradictory findings. This study attempts to further clarify this relationship by focussing on specific conditions such as panic attacks and non-panic anxiety in relation to specific meteorological variables. All psychiatric emergencies attended at a general hospital in Barcelona (Spain) during 2002 with anxiety as main complaint were classified as panic or non-panic anxiety according to strict independent and retrospective criteria. Both groups were assessed and compared with meteorological data (wind speed and direction, daily rainfall, temperature, humidity and solar radiation). Seasons and weekend days were also included as independent variables. Non-parametric statistics were used throughout since most variables do not follow a normal distribution. Logistic regression models were applied to predict days with and without the clinical condition. Episodes of panic were three times more common with the poniente wind (hot wind), twice less often with rainfall, and one and a half times more common in autumn than in other seasons. These three trends (hot wind, rainfall and autumn) were accumulative for panic episodes in a logistic regression formula. Significant reduction of episodes on weekends was found only for non-panic episodes. Panic attacks, unlike other anxiety episodes, in a psychiatric emergency department in Barcelona seem to show significant meteorotropism. Assessing specific disorders instead of overall emergencies or other variables of a more general quality could shed new light on the relationship between weather conditions and behaviour.

[Previous abstinence time as a predictive factor at 12 months follow-up in a multi-component smoking cessation program].

PubMed

Moreno-Arnedillo, J J; Morante-Benadero, M E; Sánchez-Vegazo-Sánchez, E

2014-01-01

The objective of this study is to analyze the length of the longest period of previous abstinence time as a predictor of the results of a smoking cessation program at 12 months follow-up. A cross-sectional study was conducted on a sample of 475 smokers who had participated in a multi-component smoking cessation group therapy program. The independent variable is the longest abstinence time passed, measured in weeks, before the current treatment. Success was defined as self-reported abstinence. Bivariate analyses were applied to the independent variable and to other variables in order to determine the factors that would be part of a logistic regression model using contrasts Student t or χ(2) comparisons, as appropriate. Those that showed statistical significance were entered into a multivariate logistic regression model. Within the studied variables, previous abstinence time and sex were the only predictive variables of success at 12 month follow-up. The probability of being abstinent at 12 months follow-up was significantly associated with the length of the previous longest period of abstinence, and this is the best of the predictors considered. Successful cessation programs depend more on the relationship with the consumer biographical aspects than with biological factors. The history of previous attempts is a more valuable source of information for designing treatments than others traditionally considered. Copyright © 2013 Sociedad Española de Médicos de Atención Primaria (SEMERGEN). Publicado por Elsevier España. All rights reserved.

A predictive model for diagnosing bipolar disorder based on the clinical characteristics of major depressive episodes in Chinese population.

PubMed

Gan, Zhaoyu; Diao, Feici; Wei, Qinling; Wu, Xiaoli; Cheng, Minfeng; Guan, Nianhong; Zhang, Ming; Zhang, Jinbei

2011-11-01

A correct timely diagnosis of bipolar depression remains a big challenge for clinicians. This study aimed to develop a clinical characteristic based model to predict the diagnosis of bipolar disorder among patients with current major depressive episodes. A prospective study was carried out on 344 patients with current major depressive episodes, with 268 completing 1-year follow-up. Data were collected through structured interviews. Univariate binary logistic regression was conducted to select potential predictive variables among 19 initial variables, and then multivariate binary logistic regression was performed to analyze the combination of risk factors and build a predictive model. Receiver operating characteristic (ROC) curve was plotted. Of 19 initial variables, 13 variables were preliminarily selected, and then forward stepwise exercise produced a final model consisting of 6 variables: age at first onset, maximum duration of depressive episodes, somatalgia, hypersomnia, diurnal variation of mood, irritability. The correct prediction rate of this model was 78% (95%CI: 75%-86%) and the area under the ROC curve was 0.85 (95%CI: 0.80-0.90). The cut-off point for age at first onset was 28.5 years old, while the cut-off point for maximum duration of depressive episode was 7.5 months. The limitations of this study include small sample size, relatively short follow-up period and lack of treatment information. Our predictive models based on six clinical characteristics of major depressive episodes prove to be robust and can help differentiate bipolar depression from unipolar depression. Copyright © 2011 Elsevier B.V. All rights reserved.

Factors predicting Behavior Management Problems during Initial Dental Examination in Children Aged 2 to 8 Years

PubMed Central

Kumar, Dipanshu; Anand, Ashish; Mittal, Vipula; Singh, Aparna; Aggarwal, Nidhi

2017-01-01

Aim The aim of the present study was to identify the various background variables and its influence on behavior management problems (BMP) in children. Materials and methods The study included 165 children aged 2 to 8 years. During the initial dental visit, an experienced operator obtained each child’s background variables from accompanying guardians using a standardized questionnaire. Children’s dental behavior was rated by Frankel behavior rating scale. The behavior was then analyzed in relation to the answers of the questionnaire, and a logistic regression model was used to determine the power of the variables, separately or combined, to predict BMP. Results The logistic regression analysis considering differences in background variables between children with negative or positive behavior. Four variables turned out to be as predictors: Age, the guardian’s expectation of the child’s behavior at the dental examination, the child’s anxiety when meeting unfamiliar people, and the presence and absence of toothache. Conclusion The present study concluded that by means of simple questionnaire BMP in children may be expected if one of these attributes is found. Clinical significance Information on the origin of dental fear and uncooperative behavior in a child patient prior to treatment process may help the pediatric dentist plan appropriate behavior management and treatment strategy. How to cite this article Sharma A, Kumar D, Anand A, Mittal V, Singh A, Aggarwal N. Factors predicting Behavior Management Problems during Initial Dental Examination in Children Aged 2 to 8 Years. Int J Clin Pediatr Dent 2017;10(1):5-9. PMID:28377646

Classification of Dust Days by Satellite Remotely Sensed Aerosol Products

NASA Technical Reports Server (NTRS)

Sorek-Hammer, M.; Cohen, A.; Levy, Robert C.; Ziv, B.; Broday, D. M.

2013-01-01

Considerable progress in satellite remote sensing (SRS) of dust particles has been seen in the last decade. From an environmental health perspective, such an event detection, after linking it to ground particulate matter (PM) concentrations, can proxy acute exposure to respirable particles of certain properties (i.e. size, composition, and toxicity). Being affected considerably by atmospheric dust, previous studies in the Eastern Mediterranean, and in Israel in particular, have focused on mechanistic and synoptic prediction, classification, and characterization of dust events. In particular, a scheme for identifying dust days (DD) in Israel based on ground PM10 (particulate matter of size smaller than 10 nm) measurements has been suggested, which has been validated by compositional analysis. This scheme requires information regarding ground PM10 levels, which is naturally limited in places with sparse ground-monitoring coverage. In such cases, SRS may be an efficient and cost-effective alternative to ground measurements. This work demonstrates a new model for identifying DD and non-DD (NDD) over Israel based on an integration of aerosol products from different satellite platforms (Moderate Resolution Imaging Spectroradiometer (MODIS) and Ozone Monitoring Instrument (OMI)). Analysis of ground-monitoring data from 2007 to 2008 in southern Israel revealed 67 DD, with more than 88 percent occurring during winter and spring. A Classification and Regression Tree (CART) model that was applied to a database containing ground monitoring (the dependent variable) and SRS aerosol product (the independent variables) records revealed an optimal set of binary variables for the identification of DD. These variables are combinations of the following primary variables: the calendar month, ground-level relative humidity (RH), the aerosol optical depth (AOD) from MODIS, and the aerosol absorbing index (AAI) from OMI. A logistic regression that uses these variables, coded as binary variables, demonstrated 93.2 percent correct classifications of DD and NDD. Evaluation of the combined CART-logistic regression scheme in an adjacent geographical region (Gush Dan) demonstrated good results. Using SRS aerosol products for DD and NDD, identification may enable us to distinguish between health, ecological, and environmental effects that result from exposure to these distinct particle populations.

Efficient estimation of the attributable fraction when there are monotonicity constraints and interactions.

PubMed

Traskin, Mikhail; Wang, Wei; Ten Have, Thomas R; Small, Dylan S

2013-01-01

The PAF for an exposure is the fraction of disease cases in a population that can be attributed to that exposure. One method of estimating the PAF involves estimating the probability of having the disease given the exposure and confounding variables. In many settings, the exposure will interact with the confounders and the confounders will interact with each other. Also, in many settings, the probability of having the disease is thought, based on subject matter knowledge, to be a monotone increasing function of the exposure and possibly of some of the confounders. We develop an efficient approach for estimating logistic regression models with interactions and monotonicity constraints, and apply this approach to estimating the population attributable fraction (PAF). Our approach produces substantially more accurate estimates of the PAF in some settings than the usual approach which uses logistic regression without monotonicity constraints.

Desistance from intimate partner violence: the role of legal cynicism, collective efficacy, and social disorganization in Chicago neighborhoods.

PubMed

Emery, Clifton R; Jolley, Jennifer M; Wu, Shali

2011-12-01

This paper examined the relationship between reported Intimate Partner Violence (IPV) desistance and neighborhood concentrated disadvantage, ethnic heterogeneity, residential instability, collective efficacy and legal cynicism. Data from the Project on Human Development in Chicago Neighborhoods (PHDCN) Longitudinal survey were used to identify 599 cases of IPV in Wave 1 eligible for reported desistance in Wave 2. A Generalized Boosting Model was used to determine the best proximal predictors of IPV desistance from the longitudinal data. Controlling for these predictors, logistic regression of neighborhood characteristics from the PHDCN community survey was used to predict reported IPV desistance in Wave 2. The paper finds that participants living in neighborhoods high in legal cynicism have lower odds of reporting IPV desistance, controlling for other variables in the logistic regression model. Analyses did not find that IPV desistance was related to neighborhood concentrated disadvantage, ethnic heterogeneity, residential instability and collective efficacy.

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.

Accounting for informatively missing data in logistic regression by means of reassessment sampling.

PubMed

Lin, Ji; Lyles, Robert H

2015-05-20

We explore the 'reassessment' design in a logistic regression setting, where a second wave of sampling is applied to recover a portion of the missing data on a binary exposure and/or outcome variable. We construct a joint likelihood function based on the original model of interest and a model for the missing data mechanism, with emphasis on non-ignorable missingness. The estimation is carried out by numerical maximization of the joint likelihood function with close approximation of the accompanying Hessian matrix, using sharable programs that take advantage of general optimization routines in standard software. We show how likelihood ratio tests can be used for model selection and how they facilitate direct hypothesis testing for whether missingness is at random. Examples and simulations are presented to demonstrate the performance of the proposed method. Copyright © 2015 John Wiley & Sons, Ltd.

Association of school, family, and mental health characteristics with suicidal ideation among Korean adolescents.

PubMed

Lee, Gyu-Young; Choi, Yun-Jung

2015-08-01

In a cross-sectional research design, we investigated factors related to suicidal ideation in adolescents using data from the 2013 Online Survey of Youth Health Behavior in Korea. This self-report questionnaire was administered to 72,435 adolescents aged 13-18 years in middle and high school. School characteristics, family characteristics, and mental health variables were analyzed using descriptive statistics, χ(2) tests, and logistic regression. Both suicidal ideation and behavior were more common in girls. Suicidal ideation was most common in 11th grade for boys and 8th grade for girls. Across the sample, in logistic regression, suicidal ideation was predicted by low socioeconomic status, high stress, inadequate sleep, substance use, alcohol use, and smoking. Living apart from family predicted suicidal ideation in boys but not in girls. Gender- and school-grade-specific intervention programs may be useful for reducing suicidal ideation in students. © 2015 Wiley Periodicals, Inc.

Use of antidementia drugs in frontotemporal lobar degeneration.

PubMed

López-Pousa, Secundino; Calvó-Perxas, Laia; Lejarreta, Saioa; Cullell, Marta; Meléndez, Rosa; Hernández, Erélido; Bisbe, Josep; Perkal, Héctor; Manzano, Anna; Roig, Anna Maria; Turró-Garriga, Oriol; Vilalta-Franch, Joan; Garre-Olmo, Josep

2012-06-01

Clinical evidence indicates that acetylcholinesterase inhibitors (AChEIs) are not efficacious to treat frontotemporal lobar degeneration (FTLD). The British Association for Psychopharmacology recommends avoiding the use of AChEI and memantine in patients with FTLD. Cross-sectional design using 1092 cases with Alzheimer's disease (AD) and 64 cases with FTLD registered by the Registry of Dementias of Girona. Bivariate analyses were performed, and binary logistic regressions were used to detect variables associated with antidementia drugs consumption. The AChEIs were consumed by 57.6% and 42.2% of the patients with AD and FTLD, respectively. Memantine was used by 17.2% and 10.9% of patients with AD and FTLD, respectively. Binary logistic regressions yielded no associations with antidementia drugs consumption. There is a discrepancy regarding clinical practice and the recommendations based upon clinical evidence. The increased central nervous system drug use detected in FTLD requires multicentric studies aiming at finding the best means to treat these patients.

Mortality predictions of fire-injured large Douglas-fir and ponderosa pine in Oregon and Washington, USA

Treesearch

Lisa M. Ganio; Robert A. Progar

2017-01-01

Wild and prescribed fire-induced injury to forest trees can produce immediate or delayed tree mortality but fire-injured trees can also survive. Land managers use logistic regression models that incorporate tree-injury variables to discriminate between fatally injured trees and those that will survive. We used data from 4024 ponderosa pine (Pinus ponderosa...

Validation of a Model of Extramusical Influences on Solo and Small-Ensemble Festival Ratings

ERIC Educational Resources Information Center

Bergee, Martin J.

2006-01-01

This is the fourth in a series of studies whose purpose has been to develop a theoretical model of selected extramusical variables' ability to explain solo and small-ensemble festival ratings. Authors of the second and third of these (Bergee & McWhirter, 2005; Bergee & Westfall, 2005) used logistic regression as the basis for their…

Placement Model for First-Time Freshmen in Calculus I (Math 131): University of Northern Colorado

ERIC Educational Resources Information Center

Heiny, Robert L.; Heiny, Erik L.; Raymond, Karen

2017-01-01

Two approaches, Linear Discriminant Analysis, and Logistic Regression are used and compared to predict success or failure for first-time freshmen in the first calculus course at a medium-sized public, 4-year institution prior to Fall registration. The predictor variables are high school GPA, the number, and GPA's of college prep mathematics…

A Survey of Out-of-Pocket Expenditures for Children with Autism Spectrum Disorder in Israel

ERIC Educational Resources Information Center

Raz, Raanan; Lerner-Geva, Liat; Leon, Odelia; Chodick, Gabriel; Gabis, Lidia V.

2013-01-01

We describe a survey of children with ASD aged 4-10 years. The main dependent variables were out-of-pocket expenditures for health services and hours of therapy. Multivariable logistic regression models were used in order to find independent predictors for service utilization. Parents of 178 of the children (87%) agreed to participate. The average…

Won't You Be My Neighbor? Using an Ecological Approach to Examine the Impact of Community on Revictimization

ERIC Educational Resources Information Center

Obasaju, Mayowa A.; Palin, Frances L.; Jacobs, Carli; Anderson, Page; Kaslow, Nadine J.

2009-01-01

An ecological model is used to explore the moderating effects of community-level variables on the relation between childhood sexual, physical, and emotional abuse and adult intimate partner violence (IPV) within a sample of 98 African American women from low incomes. Results from hierarchical, binary logistics regressions analyses show that…

Factors Affecting Seedling Survivorship of Blue Oak (Quercus douglasii H. & A.) in Central California

Treesearch

Frank W. Davis; Mark Borchert; L. E. Harvey; Joel C. Michaelsen

1991-01-01

Blue oak seedling mortality was studied in relation to vertebrate predators, initial acorn planting position, slope and aspect, and oak canopy cover at two sites in the Central Coast Ranges of California. Seedling survival rates (Psd) were related to treatment variables using logistic regression analysis. Analysis of 2842 seedlings for 3 years following establishment...

Analysis of the Effects of the Commander’s Battle Positioning on Unit Combat Performance

DTIC Science & Technology

1991-03-01

Analysis ......... .. 58 Logistic Regression Analysis ......... .. 61 Canonical Correlation Analysis ........ .. 62 Descriminant Analysis...entails classifying objects into two or more distinct groups, or responses. Dillon defines descriminant analysis as "deriving linear combinations of the...object given it’s predictor variables. The second objective is, through analysis of the parameters of the descriminant functions, determine those

Stability of a Model Explaining Selected Extramusical Influences on Solo and Small-Ensemble Festival Ratings

ERIC Educational Resources Information Center

Bergee, Martin J.; Westfall, Claude R.

2005-01-01

This is the third study in a line of inquiry whose purpose has been to develop a theoretical model of selected extra musical variables' influence on solo and small-ensemble festival ratings. Authors of the second of these (Bergee & McWhirter, 2005) had used binomial logistic regression as the basis for their model-formulation strategy. Their…

Prospective Associations between Youth Assets, Neighborhood Characteristics and No-Tobacco Use among Youth: Differences by Gender

ERIC Educational Resources Information Center

Tolma, Eleni L.; Oman, Roy F.; Vesely, Sara K.; Aspy, Cheryl B.; Boeckman, Lindsay

2013-01-01

The purpose of this study is to assess the relationship between youth assets and neighborhood environmental variables and future no-tobacco use among youth; examining differences by gender. Five waves of annual data were collected from 1,111 youth randomly selected to participate in the Youth Asset Study (YAS). A marginal logistic regression model…

The Use of Female Commercial Sex Workers' Services by Latino Day Laborers

ERIC Educational Resources Information Center

Galvan, Frank H.; Ortiz, Daniel J.; Martinez, Victor; Bing, Eric G.

2009-01-01

This article reports the characteristics of Latino day laborers who have sex with female commercial sex workers (CSWs). A sample of 450 day laborers in Los Angeles was used. Multivariate logistic regression was used to determine the association of independent variables with the likelihood of having sex with a CSW. Overall, 26% of the 450 day…

Can we "predict" long-term outcome for ambulatory transcutaneous electrical nerve stimulation in patients with chronic pain?

PubMed

Köke, Albère J; Smeets, Rob J E M; Perez, Roberto S; Kessels, Alphons; Winkens, Bjorn; van Kleef, Maarten; Patijn, Jacob

2015-03-01

Evidence for effectiveness of transcutaneous electrical nerve stimulation (TENS) is still inconclusive. As heterogeneity of chronic pain patients might be an important factor for this lack of efficacy, identifying factors for a successful long-term outcome is of great importance. A prospective study was performed to identify variables with potential predictive value for 2 outcome measures on long term (6 months); (1) continuation of TENS, and (2) a minimally clinical important pain reduction of ≥ 33%. At baseline, a set of risk factors including pain-related variables, psychological factors, and disability was measured. In a multiple logistic regression analysis, higher patient's expectations, neuropathic pain, no severe pain (< 80 mm visual analogue scale [VAS]) were independently related to long-term continuation of TENS. For the outcome "minimally clinical important pain reduction," the multiple logistic regression analysis indicated that no multisited pain (> 2 pain locations) and intermittent pain were positively and independently associated with a minimally clinical important pain reduction of ≥ 33%. The results showed that factors associated with a successful outcome in the long term are dependent on definition of successful outcome. © 2014 World Institute of Pain.

Multidrug-resistant pulmonary tuberculosis in Los Altos, Selva and Norte regions, Chiapas, Mexico.

PubMed

Sánchez-Pérez, H J; Díaz-Vázquez, A; Nájera-Ortiz, J C; Balandrano, S; Martín-Mateo, M

2010-01-01

To analyse the proportion of multidrug-resistant tuberculosis (MDR-TB) in cultures performed during the period 2000-2002 in Los Altos, Selva and Norte regions, Chiapas, Mexico, and to analyse MDR-TB in terms of clinical and sociodemographic indicators. Cross-sectional study of patients with pulmonary tuberculosis (PTB) from the above regions. Drug susceptibility testing results from two research projects were analysed, as were those of routine sputum samples sent in by health personnel for processing (n = 114). MDR-TB was analysed in terms of the various variables of interest using bivariate tests of association and logistic regression. The proportion of primary MDR-TB was 4.6% (2 of 43), that of secondary MDR-TB was 29.2% (7/24), while among those whose history of treatment was unknown the proportion was 14.3% (3/21). According to the logistic regression model, the variables most highly associated with MDR-TB were as follows: having received anti-tuberculosis treatment previously, cough of >3 years' duration and not being indigenous. The high proportion of MDR cases found in the regions studied shows that it is necessary to significantly improve the control and surveillance of PTB.

Education level as a predictor of condom use in jail-incarcerated women, with fundamental cause analysis.

PubMed

Emerson, Amanda M; Carroll, Hsiang-Feng; Ramaswamy, Megha

2018-05-27

To model condom usage by jail-incarcerated women incarcerated in US local jails and understand results in terms of fundamental cause theory. We surveyed 102 women in an urban jail in the Midwest United States. Chi-square tests and generalized linear modeling were used to identify factors of significance for women who used condoms during last sex compared with women who did not. Stepwise multiple logistic regression was conducted to estimate the relation between the outcome variable and variables linked to condom use in the literature. Logistic regression showed that for women who completed high school odds of reporting condom use during last sex were 2.78 times higher (p = .043) than the odds for women with less than a high school education. Among women who responded no to ever having had a sexually transmitted infection, odds of using a condom during last sex were 2.597 times (p = .03) higher than odds for women who responded that they had had a sexually transmitted infection. Education is a fundamental cause of reproductive health risk among incarcerated women. We recommend interventions that creatively target distal over proximal factors. © 2018 Wiley Periodicals, Inc.

[Malignant mesothelioma risk factors: experience in the General Hospital of Mexico].

PubMed

Hernández-Solís, Alejandro; Garcia-Hernández, Cyntia; Reding-Bernal, Arturo; Cruz-Ortiz, Humberto; Cicero-Sabido, Raúl

2013-01-01

Malignant mesothelioma is a neoplasm of bad prognosis, it is linked with asbestos contact, but there are cases without this antecedent. To investigate the relationship of asbestos exposition and other factors with malignant mesothelioma. Retrospective analysis of histologic confirmed cases of malignant mesothelioma, neoplasic familiar history, tobacco smoking, exposure to wood smoke and to asbestos, were annotated in a paired case/control study 1: 1-3 with logistic regression model to identify risk factors for OR. 61 cases of malignant mesothelioma were confirmed by histopathologic study, 41 male and 20 female. Mean age was 56 years ± 13 years; 56 cases (91.8%) correspond to epithelial malignant mesothelioma, three sarcomatous (4.9%) one desmoplastic and one biphasic. One in eight (13.1%) had exposure to asbestos. Model of logistic regression with four variables: history of familiar cancer, tobacco smoking, wood smoke and asbestos exposition, the the last one with an OR= 3.083 and p > 0.05. No other variables found to be a risk factor for malignant mesothelioma. Exposure to asbestos is a risk factor for malignant mesothelioma, which is confirmed in this study, however it is important to extend the investigation of other possible causal factors of this disease.

Factors associated with self-medication in Spain: a cross-sectional study in different age groups.

PubMed

Niclós, Gracia; Olivar, Teresa; Rodilla, Vicent

2018-06-01

The identification of factors which may influence a patient's decision to self-medicate. Descriptive, cross-sectional study of the adult population (at least 16 years old), using data from the 2009 European Health Interview Survey in Spain, which included 22 188 subjects. Logistic regression models enabled us to estimate the effect of each analysed variable on self-medication. In total, 14 863 (67%) individuals reported using medication (prescribed and non-prescribed) and 3274 (22.0%) of them self-medicated. Using logistic regression and stratifying by age, four different models have been constructed. Our results include different variables in each of the models to explain self-medication, but the one that appears on all four models is education level. Age is the other important factor which influences self-medication. Self-medication is strongly associated with factors related to socio-demographic, such as sex, educational level or age, as well as several health factors such as long-standing illness or physical activity. When our data are compared to those from previous Spanish surveys carried out in 2003 and 2006, we can conclude that self-medication is increasing in Spain. © 2017 Royal Pharmaceutical Society.

Factors associated with preventable infant death: a multiple logistic regression.

PubMed

Vidal E Silva, Sandra Maria Cunha; Tuon, Rogério Antonio; Probst, Livia Fernandes; Gondinho, Brunna Verna Castro; Pereira, Antonio Carlos; Meneghim, Marcelo de Castro; Cortellazzi, Karine Laura; Ambrosano, Glaucia Maria Bovi

2018-01-01

OBJECTIVE To identify and analyze factors associated with preventable child deaths. METHODS This analytical cross-sectional study had preventable child mortality as dependent variable. From a population of 34,284 live births, we have selected a systematic sample of 4,402 children who did not die compared to 272 children who died from preventable causes during the period studied. The independent variables were analyzed in four hierarchical blocks: sociodemographic factors, the characteristics of the mother, prenatal and delivery care, and health conditions of the patient and neonatal care. We performed a descriptive statistical analysis and estimated multiple hierarchical logistic regression models. RESULTS Approximatelly 35.3% of the deaths could have been prevented with the early diagnosis and treatment of diseases during pregnancy and 26.8% of them could have been prevented with better care conditions for pregnant women. CONCLUSIONS The following characteristics of the mother are determinant for the higher mortality of children before the first year of life: living in neighborhoods with an average family income lower than four minimum wages, being aged ≤ 19 years, having one or more alive children, having a child with low APGAR level at the fifth minute of life, and having a child with low birth weight.

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

PubMed

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

2014-06-17

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

Propensity score matching of the gymnastics for diabetes mellitus using logistic regression

NASA Astrophysics Data System (ADS)

Otok, Bambang Widjanarko; Aisyah, Amalia; Purhadi, Andari, Shofi

2017-12-01

Diabetes Mellitus (DM) is a group of metabolic diseases with characteristics shows an abnormal blood glucose level occurring due to pancreatic insulin deficiency, decreased insulin effectiveness or both. The report from the ministry of health shows that DMs prevalence data of East Java province is 2.1%, while the DMs prevalence of Indonesia is only 1,5%. Given the high cases of DM in East Java, it needs the preventive action to control factors causing the complication of DM. This study aims to determine the combination factors causing the complication of DM to reduce the bias by confounding variables using Propensity Score Matching (PSM) with the method of propensity score estimation is binary logistic regression. The data used in this study is the medical record from As-Shafa clinic consisting of 6 covariates and health complication as response variable. The result of PSM analysis showed that there are 22 of 126 DMs patients attending gymnastics paired with patients who didnt attend to diabetes gymnastics. The Average Treatment of Treated (ATT) estimation results showed that the more patients who didnt attend to gymnastics, the more likely the risk for the patients having DMs complications.

Examining the relationship between adolescent sexual risk-taking and perceptions of monitoring, communication, and parenting styles.

PubMed

Huebner, Angela J; Howell, Laurie W

2003-08-01

To examine the relationship between adolescent sexual risk-taking and perception of parental monitoring, frequency of parent-adolescent communication, and parenting style. The influences of gender, age, and ethnicity are also of interest. Data were collected from 7th-12th grade students in six rural, ethnically diverse school located in adjacent counties in a Southeastern state. A 174-item instrument assessed adolescent perceptions, behaviors and attitudes. Youth who had engaged in sexual intercourse (n = 1160) were included in the analyses. Logistic regression analyses were conducted to identify parenting practices that predicted high versus low-risk sex (defined by number of partners and use of condoms). Variables included parental monitoring, parent-adolescent communication, parenting style, parenting process interaction effects and interaction effects among these three parenting processes and gender, age and ethnicity. Analyses included frequencies, cross-tabulations and logistic regression. Parental monitoring, parental monitoring by parent-adolescent communication and parenting style by ethnicity were significant predictors of sexual risk-taking. No gender or age interactions were noted. Parental monitoring, parent-adolescent communication and parenting style are all important variables to consider when examining sexual risk-taking among adolescents.

Association between developmental enamel defects in the primary and permanent dentitions.

PubMed

Casanova-Rosado, A J; Medina-Solís, C E; Casanova-Rosado, J F; Vallejos-Sánchez, A A; Martinez-Mier, E A; Loyola-Rodríguez, J P; Islas-Márquez, A J; Maupomé, G

2011-09-01

To determine if the presence of developmental enamel defects (DED) in the primary dentition is a risk indicator for the presence of DED in the permanent dentition in children with mixed dentition, as well as others factors. A cross-sectional study was undertaken in 1296 school children ages six to 72 years. The DED [FDI; 1982] in both dentitions were identified by means of an oral exam scoring enamel opacities [classified as demarcated or diffused], and enamel hypoplasia. Sociodemographic and socioeconomic variables were collected through a questionnaire. Socioeconomic status (SES) was determined based on the occupation and maximum level of education of parents. Statistical analysis included logistic regression. Mean age of participants was 8.40 +/- 1.68; 51.6% were boys. DED prevalence was 7.5% in the permanent dentition and 10.0% in the primary dentition. The logistic regression model, adjusting for sociodemographic and socioeconomic variables, showed that for each primary tooth with DED, the odds of observing DED in the permanent dentition increased 7.38 times [95% CI = 1.17-1.64; p < 0.001]. An association between DED presence in both permanent and primary dentitions was observed. Further studies are necessary to fully characterise such relationship.

A multiscaled model of southwestern willow flycatcher breeding habitat

USGS Publications Warehouse

Hatten, J.R.; Paradzick, C.E.

2003-01-01

The southwestern willow flycatcher (SWFL; Empidonax traillii extimus) is an endangered songbird whose habitat has declined dramatically over the last century. Understanding habitat selection patterns and the ability to identify potential breeding areas for the SWFL is crucial to the management and conservation of this species. We developed a multiscaled model of SWTL breeding habitat with a Geographic Information System (GIS), survey data, GIS variables, and multiple logistic regressions. We obtained presence and absence survey data from a riverine ecosystem and a reservoir delta in south-central Arizona, USA, in 1999. We extracted the GIS variables from satellite imagery and digital elevation models to characterize vegetation and floodplain within the project area. We used multiple logistic regressions within a cell-based (30 X 30 m) modeling environment to (1) determine associations between GIS variables and breeding-site occurrence at different spatial scales (0.09-72 ha), and (2) construct a predictive model. Our best model explained 54% of the variability in breeding-site occurrence with the following variables: vegetation density at the site (0.09 ha), proportion of dense vegetation and variability in vegetation density within a 4.5-ha neighborhood, and amount of floodplain or flat terrain within a 41-ha neighborhood. The density of breeding sites was highest in areas that the model predicted to be most suitable within the project area and at an external test site 200 km away. Conservation efforts must focus on protecting not only occupied patches, but also surrounding riparian forests and floodplain to ensure long-term viability of SWTL. We will use the multiscaled model to map SWTL breeding habitat in Arizona, prioritize future survey effort, and examine changes in habitat abundance and quality over time.

Prediction of first episode of panic attack among white-collar workers.

PubMed

Watanabe, Akira; Nakao, Kazuhisa; Tokuyama, Madoka; Takeda, Masatoshi

2005-04-01

The purpose of the present study was to elucidate a longitudinal matrix of the etiology for first-episode panic attack among white-collar workers. A path model was designed for this purpose. A 5-year, open-cohort study was carried out in a Japanese company. To evaluate the risk factors associated with the onset of a first episode of panic attack, the odds ratios of a new episode of panic attack were calculated by logistic regression. The path model contained five predictor variables: gender difference, overprotection, neuroticism, lifetime history of major depression, and recent stressful life events. The logistic regression analysis indicated that a person with a lifetime history of major depression and recent stressful life events had a fivefold and a threefold higher risk of panic attacks at follow up, respectively. The path model for the prediction of a first episode of panic attack fitted the data well. However, this model presented low accountability for the variance in the ultimate dependent variables, the first episode of panic attack. Three predictors (neuroticism, lifetime history of major depression, and recent stressful life events) had a direct effect on the risk for a first episode of panic attack, whereas gender difference and overprotection had no direct effect. The present model could not fully predict first episodes of panic attack in white-collar workers. To make a path model for the prediction of the first episode of panic attack, other strong predictor variables, which were not surveyed in the present study, are needed. It is suggested that genetic variables are among the other strong predictor variables. A new path model containing genetic variables (e.g. family history etc.) will be needed to predict the first episode of panic attack.

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.

Applicability of the Ricketts' posteroanterior cephalometry for sex determination using logistic regression analysis in Hispano American Peruvians.

PubMed

Perez, Ivan; Chavez, Allison K; Ponce, Dario

2016-01-01

The Ricketts' posteroanterior (PA) cephalometry seems to be the most widely used and it has not been tested by multivariate statistics for sex determination. The objective was to determine the applicability of Ricketts' PA cephalometry for sex determination using the logistic regression analysis. The logistic models were estimated at distinct age cutoffs (all ages, 11 years, 13 years, and 15 years) in a database from 1,296 Hispano American Peruvians between 5 years and 44 years of age. The logistic models were composed by six cephalometric measurements; the accuracy achieved by resubstitution varied between 60% and 70% and all the variables, with one exception, exhibited a direct relationship with the probability of being classified as male; the nasal width exhibited an indirect relationship. The maxillary and facial widths were present in all models and may represent a sexual dimorphism indicator. The accuracy found was lower than the literature and the Ricketts' PA cephalometry may not be adequate for sex determination. The indirect relationship of the nasal width in models with data from patients of 12 years of age or less may be a trait related to age or a characteristic in the studied population, which could be better studied and confirmed.

Predictors of the number of under-five malnourished children in Bangladesh: application of the generalized poisson regression model

PubMed Central

2013-01-01

Background Malnutrition is one of the principal causes of child mortality in developing countries including Bangladesh. According to our knowledge, most of the available studies, that addressed the issue of malnutrition among under-five children, considered the categorical (dichotomous/polychotomous) outcome variables and applied logistic regression (binary/multinomial) to find their predictors. In this study malnutrition variable (i.e. outcome) is defined as the number of under-five malnourished children in a family, which is a non-negative count variable. The purposes of the study are (i) to demonstrate the applicability of the generalized Poisson regression (GPR) model as an alternative of other statistical methods and (ii) to find some predictors of this outcome variable. Methods The data is extracted from the Bangladesh Demographic and Health Survey (BDHS) 2007. Briefly, this survey employs a nationally representative sample which is based on a two-stage stratified sample of households. A total of 4,460 under-five children is analysed using various statistical techniques namely Chi-square test and GPR model. Results The GPR model (as compared to the standard Poisson regression and negative Binomial regression) is found to be justified to study the above-mentioned outcome variable because of its under-dispersion (variance < mean) property. Our study also identify several significant predictors of the outcome variable namely mother’s education, father’s education, wealth index, sanitation status, source of drinking water, and total number of children ever born to a woman. Conclusions Consistencies of our findings in light of many other studies suggest that the GPR model is an ideal alternative of other statistical models to analyse the number of under-five malnourished children in a family. Strategies based on significant predictors may improve the nutritional status of children in Bangladesh. PMID:23297699

[Possibility and predictors of successful cigarette purchase attempts by 201 primary school students in Guangzhou, China].

PubMed

Wen, Xiao-zhong; Huang, Jian-hua; Chen, Wei-qing; Liang, Cai-hua; Han, Ke; Ling, Wen-hua

2007-01-01

To explore the access to tobacco and exam the predictors of successful tobacco purchase attempts among Chinese minors. A simulative trial of purchasing cigarettes was participated by 201 sixth grade students to assess the prevalence of illegal cigarette sales to minors in Guangzhou. Methods of Chi-square and unconditional logistic regression were used to identify the significant predictors,with the result of tobacco purchase as the dependent variable and the characteristics of stores, retailers and minors as the independent variables. A total of 165 students succeeded in purchasing cigarettes but 36 failed, and the percentage of successful purchase attempts was 82. 1% . Data from univariate analysis indicated that 9 factors were significantly associated with students' success in purchasing cigarettes. They were age and height of the purchasers, types of stores, seller's gender and age, posting cigarette advertisements,showing warning signs of 'no cigarette selling to minors' ,asking buyer's age,and asking whom you buy the cigarettes for. The results of multivariable analysis showed that only three variables entering the final logistic regression: the age of students, the type of stores, and showing warning signs of 'no cigarette selling to minors'. Chinese minors have easy access to purchasing cigarettes, especially in groceries and small markets. Selling cigarettes by sellers to minors should be monitored and managed in the future.

Association between Violent Crime and Psychosis in Men Serving Prison Terms.

PubMed

Saavedra, Javier; López, Marcelino; Trigo, M Eva

2017-06-27

Psychosis has been associated with committing violent crimes. However, it has been reported that the association is mediated by toxin consumption, personality disorders, and positive symptoms. This study will examine the relationship between different psychological disorders and sociodemographic variables, and violent crime perpetration in a sample of 472 men serving prison terms in Andalusia, Spain. A correlation-based, retrospective study was conducted and data were analyzed through logistic regression. The sample is representative of the Andalusian prison population, with a 95% level of confidence and .02% precision. Inmates were sampled and diagnosed by expert clinicians using the SCID-I and the IPDE-II. We computed bivariate correlations between the aforementioned variables and perpetration of violent crimes (murder, homicide, attempted murder, and injury) to later apply logistic regression and find adjusted odds ratios. We confirmed the association between diagnosis of functional psychoses and violent crime, with a significant adjusted odds ratio in the last model (OR = 3.71; p = .010). Other significant variables that acted like risk factors include suicide attempts (OR = 2.04; p = .046), having received care at a mental health facility in the year before imprisonment (OR = 3.83; p = .008), and more strongly than the psychosis diagnosis, low level of education (OR = 10.32; p = .029). Toxin consumption and personality disorders were not significant in the final model.

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

An appraisal of convergence failures in the application of logistic regression model in published manuscripts.

PubMed

Yusuf, O B; Bamgboye, E A; Afolabi, R F; Shodimu, M A

2014-09-01

Logistic regression model is widely used in health research for description and predictive purposes. Unfortunately, most researchers are sometimes not aware that the underlying principles of the techniques have failed when the algorithm for maximum likelihood does not converge. Young researchers particularly postgraduate students may not know why separation problem whether quasi or complete occurs, how to identify it and how to fix it. This study was designed to critically evaluate convergence issues in articles that employed logistic regression analysis published in an African Journal of Medicine and medical sciences between 2004 and 2013. Problems of quasi or complete separation were described and were illustrated with the National Demographic and Health Survey dataset. A critical evaluation of articles that employed logistic regression was conducted. A total of 581 articles was reviewed, of which 40 (6.9%) used binary logistic regression. Twenty-four (60.0%) stated the use of logistic regression model in the methodology while none of the articles assessed model fit. Only 3 (12.5%) properly described the procedures. Of the 40 that used the logistic regression model, the problem of convergence occurred in 6 (15.0%) of the articles. Logistic regression tends to be poorly reported in studies published between 2004 and 2013. Our findings showed that the procedure may not be well understood by researchers since very few described the process in their reports and may be totally unaware of the problem of convergence or how to deal with it.

Associations between physical activity parenting practices and adolescent girls' self-perceptions and physical activity intentions.

PubMed

Sebire, Simon J; Haase, Anne M; Montgomery, Alan A; McNeill, Jade; Jago, Russ

2014-05-01

The current study investigated cross-sectional associations between maternal and paternal logistic and modeling physical activity support and the self-efficacy, self-esteem, and physical activity intentions of 11- to 12-year-old girls. 210 girls reported perceptions of maternal and paternal logistic and modeling support and their self-efficacy, self-esteem and intention to be physically active. Data were analyzed using multivariable regression models. Maternal logistic support was positively associated with participants' self-esteem, physical activity self-efficacy, and intention to be active. Maternal modeling was positively associated with self-efficacy. Paternal modeling was positively associated with self-esteem and self-efficacy but there was no evidence that paternal logistic support was associated with the psychosocial variables. Activity-related parenting practices were associated with psychosocial correlates of physical activity among adolescent girls. Logistic support from mothers, rather than modeling support or paternal support may be a particularly important target when designing interventions aimed at preventing the age-related decline in physical activity among girls.

The impact of meteorology on the occurrence of waterborne outbreaks of vero cytotoxin-producing Escherichia coli (VTEC): a logistic regression approach.

PubMed

O'Dwyer, Jean; Morris Downes, Margaret; Adley, Catherine C

2016-02-01

This study analyses the relationship between meteorological phenomena and outbreaks of waterborne-transmitted vero cytotoxin-producing Escherichia coli (VTEC) in the Republic of Ireland over an 8-year period (2005-2012). Data pertaining to the notification of waterborne VTEC outbreaks were extracted from the Computerised Infectious Disease Reporting system, which is administered through the national Health Protection Surveillance Centre as part of the Health Service Executive. Rainfall and temperature data were obtained from the national meteorological office and categorised as cumulative rainfall, heavy rainfall events in the previous 7 days, and mean temperature. Regression analysis was performed using logistic regression (LR) analysis. The LR model was significant (p < 0.001), with all independent variables: cumulative rainfall, heavy rainfall and mean temperature making a statistically significant contribution to the model. The study has found that rainfall, particularly heavy rainfall in the preceding 7 days of an outbreak, is a strong statistical indicator of a waterborne outbreak and that temperature also impacts waterborne VTEC outbreak occurrence.

Neck-focused panic attacks among Cambodian refugees; a logistic and linear regression analysis.

PubMed

Hinton, Devon E; Chhean, Dara; Pich, Vuth; Um, Khin; Fama, Jeanne M; Pollack, Mark H

2006-01-01

Consecutive Cambodian refugees attending a psychiatric clinic were assessed for the presence and severity of current--i.e., at least one episode in the last month--neck-focused panic. Among the whole sample (N=130), in a logistic regression analysis, the Anxiety Sensitivity Index (ASI; odds ratio=3.70) and the Clinician-Administered PTSD Scale (CAPS; odds ratio=2.61) significantly predicted the presence of current neck panic (NP). Among the neck panic patients (N=60), in the linear regression analysis, NP severity was significantly predicted by NP-associated flashbacks (beta=.42), NP-associated catastrophic cognitions (beta=.22), and CAPS score (beta=.28). Further analysis revealed the effect of the CAPS score to be significantly mediated (Sobel test [Baron, R. M., & Kenny, D. A. (1986). The moderator-mediator variable distinction in social psychological research: conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51, 1173-1182]) by both NP-associated flashbacks and catastrophic cognitions. In the care of traumatized Cambodian refugees, NP severity, as well as NP-associated flashbacks and catastrophic cognitions, should be specifically assessed and treated.

Spatial Distribution of Dorylaimid and Mononchid Nematodes from the Southeast Iberian Peninsula: Environmental Characterization of Chorotypes

PubMed Central

Liébanas, G.; Guerrero, P.; Martín-García, J.-M.; Peña-Santiago, R.

2004-01-01

The aim of this study was to determine the incidence of 18 environmental variables in the spatial distribution of 30 chorotypes (species groups with significantly similar distribution patterns) of dorylaimid and mononchid nematodes by means of logistic regression in a natural area in the southeastern Iberian Peninsula. Six variables (elevation, color chroma, clay content, nitrogen content, CaCO₃, and plant community associated) were the most important environmental factors that helped explain the distribution of chorotypes. The distribution of most chorotypes was characterized by some (one to three) environmental variables; only two chorotypes were characterized by five or more variables, and four have not been characterized. PMID:19262795

Relations that affect the probability and prediction of nitrate concentration in private wells in the glacial aquifer system in the United States

USGS Publications Warehouse

Warner, Kelly L.; Arnold, Terri L.

2010-01-01

Nitrate in private wells in the glacial aquifer system is a concern for an estimated 17 million people using private wells because of the proximity of many private wells to nitrogen sources. Yet, less than 5 percent of private wells sampled in this study contained nitrate in concentrations that exceeded the U.S. Environmental Protection Agency (USEPA) Maximum Contaminant Level (MCL) of 10 mg/L (milligrams per liter) as N (nitrogen). However, this small group with nitrate concentrations above the USEPA MCL includes some of the highest nitrate concentrations detected in groundwater from private wells (77 mg/L). Median nitrate concentration measured in groundwater from private wells in the glacial aquifer system (0.11 mg/L as N) is lower than that in water from other unconsolidated aquifers and is not strongly related to surface sources of nitrate. Background concentration of nitrate is less than 1 mg/L as N. Although overall nitrate concentration in private wells was low relative to the MCL, concentrations were highly variable over short distances and at various depths below land surface. Groundwater from wells in the glacial aquifer system at all depths was a mixture of old and young water. Oxidation and reduction potential changes with depth and groundwater age were important influences on nitrate concentrations in private wells. A series of 10 logistic regression models was developed to estimate the probability of nitrate concentration above various thresholds. The threshold concentration (1 to 10 mg/L) affected the number of variables in the model. Fewer explanatory variables are needed to predict nitrate at higher threshold concentrations. The variables that were identified as significant predictors for nitrate concentration above 4 mg/L as N included well characteristics such as open-interval diameter, open-interval length, and depth to top of open interval. Environmental variables in the models were mean percent silt in soil, soil type, and mean depth to saturated soil. The 10-year mean (1992-2001) application rate of nitrogen fertilizer applied to farms was included as the potential source variable. A linear regression model also was developed to predict mean nitrate concentrations in well networks. The model is based on network averages because nitrate concentrations are highly variable over short distances. Using values for each of the predictor variables averaged by network (network mean value) from the logistic regression models, the linear regression model developed in this study predicted the mean nitrate concentration in well networks with a 95 percent confidence in predictions.

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.

The use of auxiliary variables in capture-recapture and removal experiments

USGS Publications Warehouse

Pollock, K.H.; Hines, J.E.; Nichols, J.D.

1984-01-01

The dependence of animal capture probabilities on auxiliary variables is an important practical problem which has not been considered in the development of estimation procedures for capture-recapture and removal experiments. In this paper the linear logistic binary regression model is used to relate the probability of capture to continuous auxiliary variables. The auxiliary variables could be environmental quantities such as air or water temperature, or characteristics of individual animals, such as body length or weight. Maximum likelihood estimators of the population parameters are considered for a variety of models which all assume a closed population. Testing between models is also considered. The models can also be used when one auxiliary variable is a measure of the effort expended in obtaining the sample.

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

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.

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.

Short-term quality of life after subthalamic stimulation depends on non-motor symptoms in Parkinson's disease.

PubMed

Dafsari, Haidar Salimi; Weiß, Luisa; Silverdale, Monty; Rizos, Alexandra; Reddy, Prashanth; Ashkan, Keyoumars; Evans, Julian; Reker, Paul; Petry-Schmelzer, Jan Niklas; Samuel, Michael; Visser-Vandewalle, Veerle; Antonini, Angelo; Martinez-Martin, Pablo; Ray-Chaudhuri, K; Timmermann, Lars

2018-02-24

Subthalamic nucleus (STN) deep brain stimulation (DBS) improves quality of life (QoL), motor, and non-motor symptoms (NMS) in advanced Parkinson's disease (PD). However, considerable inter-individual variability has been observed for QoL outcome. We hypothesized that demographic and preoperative NMS characteristics can predict postoperative QoL outcome. In this ongoing, prospective, multicenter study (Cologne, Manchester, London) including 88 patients, we collected the following scales preoperatively and on follow-up 6 months postoperatively: PDQuestionnaire-8 (PDQ-8), NMSScale (NMSS), NMSQuestionnaire (NMSQ), Scales for Outcomes in PD (SCOPA)-motor examination, -complications, and -activities of daily living, levodopa equivalent daily dose. We dichotomized patients into "QoL responders"/"non-responders" and screened for factors associated with QoL improvement with (1) Spearman-correlations between baseline test scores and QoL improvement, (2) step-wise linear regressions with baseline test scores as independent and QoL improvement as dependent variables, (3) logistic regressions using aforementioned "responders/non-responders" as dependent variable. All outcomes improved significantly on follow-up. However, approximately 44% of patients were categorized as "QoL non-responders". Spearman-correlations, linear and logistic regression analyses were significant for NMSS and NMSQ but not for SCOPA-motor examination. Post-hoc, we identified specific NMS (flat moods, difficulties experiencing pleasure, pain, bladder voiding) as significant contributors to QoL outcome. Our results provide evidence that QoL improvement after STN-DBS depends on preoperative NMS characteristics. These findings are important in the advising and selection of individuals for DBS therapy. Future studies investigating motor and non-motor PD clusters may enable stratifying QoL outcomes and help predict patients' individual prospects of benefiting from DBS. Copyright © 2018. Published by Elsevier Inc.

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.

Breast Arterial Calcification Is Associated with Reproductive Factors in Asymptomatic Postmenopausal Women

PubMed Central

Whaley, Dana H.; Sheedy, Patrick F.; Peyser, Patricia A.

2010-01-01

Abstract Objective The etiology of breast arterial calcification (BAC) is not well understood. We examined reproductive history and cardiovascular disease (CVD) risk factor associations with the presence of detectable BAC in asymptomatic postmenopausal women. Methods Reproductive history and CVD risk factors were obtained in 240 asymptomatic postmenopausal women from a community-based research study who had a screening mammogram within 2 years of their participation in the study. The mammograms were reviewed for the presence of detectable BAC. Age-adjusted logistic regression models were fit to assess the association between each risk factor and the presence of BAC. Multiple variable logistic regression models were used to identify the most parsimonious model for the presence of BAC. Results The prevalence of BAC increased with increased age (p < 0.0001). The most parsimonious logistic regression model for BAC presence included age at time of examination, increased parity (p = 0.01), earlier age at first birth (p = 0.002), weight, and an age-by-weight interaction term (p = 0.004). Older women with a smaller body size had a higher probability of having BAC than women of the same age with a larger body size. Conclusions The presence or absence of BAC at mammography may provide an assessment of a postmenopausal woman's lifetime estrogen exposure and indicate women who could be at risk for hormonally related conditions. PMID:20629578

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

PubMed

Duncan, Ian; Huynh, Nhan

2017-11-17

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

Early warnings for suicide attempt among Chinese rural population.

PubMed

Lyu, Juncheng; Wang, Yingying; Shi, Hong; Zhang, Jie

2018-06-05

This study was to explore the main influencing factors of attempted suicide and establish an early warning model, so as to put forward prevention strategies for attempted suicide. Data came from a large-scale case-control epidemiological survey. A sample of 659 serious suicide attempters was randomly recruited from 13 rural counties in China. Each case was matched by a community control for gender, age, and residence location. Face to face interviews were conducted for all the cases and controls with the same structured questionnaire. Univariate logistic regression was applied to screen the factors and multivariate logistic regression was used to excavate the predictors. There were no statistical differences between suicide attempters and the community controls in gender, age, and residence location. The Cronbach`s coefficients for all the scales used were above 0.675. The multivariate logistic regressions have revealed 12 statistically significant variables predicting attempted suicide, including less education, family history of suicide, poor health, mental problem, aspiration strain, hopelessness, impulsivity, depression, negative life events. On the other hand, social support, coping skills, and healthy community protected the rural residents from suicide attempt. The excavated warning predictors are significant clinical meaning for the clinical psychiatrist. Crisis intervention strategies in rural China should be informed by the findings from this research. Education, social support, healthy community, and strain reduction are all measures to decrease the likelihood of crises. Copyright © 2018. Published by Elsevier B.V.

Colorectal cancer stage at diagnosis in migrants versus non-migrants (KoMigra): study protocol of a cross-sectional study in Germany

PubMed Central

2014-01-01

Background In Germany, about 20% of the total population have a migration background. Differences exist between migrants and non-migrants in terms of health care access and utilisation. Colorectal cancer is the second most common malignant tumour in Germany, and incidence, staging and survival chances depend, amongst other things, on ethnicity and lifestyle. The current study investigates whether stage at diagnosis differs between migrants and non-migrants with colorectal cancer in an area of high migration and attempts to identify factors that can explain any differences. Methods/Design Data on tumour and migration status will be collected for 1,200 consecutive patients that have received a new, histologically verified diagnosis of colorectal cancer in a high migration area in Germany in the previous three months. The recruitment process is expected to take 16 months and will include gastroenterological private practices and certified centres for intestinal diseases. Descriptive and analytical analysis will be performed: the distribution of variables for migrants versus non-migrants and participants versus non-participants will be analysed using appropriate χ2-, t-, F- or Wilcoxon tests. Multivariable, logistic regression models will be performed, with the dependent variable being the dichotomized stage of the tumour (UICC stage I versus more advanced than UICC stage I). Odds ratios and associated 95%-confidence intervals will be calculated. Furthermore, ordered logistic regression models will be estimated, with the exact stage of the tumour at diagnosis as the dependent variable. Predictors used in the ordered logistic regression will be patient characteristics that are specific to migrants as well as patient characteristics that are not. Interaction models will be estimated in order to investigate whether the effects of patient characteristics on stage of tumour at the time of the initial diagnosis is different in migrants, compared to non-migrants. Discussion An association of migration status or other socioeconomic variables with stage at diagnosis of colorectal cancer would be an important finding with respect to equal health care access among migrants. It would point to access barriers or different symptom appraisal and, in the long term, could contribute to the development of new health care concepts for migrants. Trial registration German Clinical Trials Register DRKS00005056. PMID:24559172

Investigation of the Self-Regulated Learning Strategies of Students from the Faculty of Education Using Ordinal Logistic Regression Analysis

ERIC Educational Resources Information Center

Bozpolat, Ebru

2016-01-01

The purpose of this study was to reveal whether the low, medium, and high level self-regulated learning strategies of third year students at the Education Faculty of Cumhuriyet University can be predicted by the variables of gender, academic self-efficacy, and general academic average. The study uses the Relational Screening Model. The dependent…

Analysis of Variables to Predict First Year Persistence Using Logistic Regression Analysis at the University of South Florida

ERIC Educational Resources Information Center

Miller, T. E.; Herreid, C. H.

2008-01-01

This article presents a project intended to produce a model for predicting the risk of attrition of individual students enrolled at the University of South Florida. The project is premised upon the principle that college student attrition is as highly individual and personal as any other aspect of the college-going experience. Students make…

Risk factors for lesions of the knee menisci among workers in South Korea's national parks.

PubMed

Shin, Donghee; Youn, Kanwoo; Lee, Eunja; Lee, Myeongjun; Chung, Hweemin; Kim, Deokweon

2016-01-01

This study was designed to investigate the prevalence of the menisci lesions in national park workers and work factors affecting this prevalence. The study subjects were 698 workers who worked in 20 Korean national parks in 2014. An orthopedist visited each national park and performed physical examinations. Knee MRI was performed if the McMurray test or Apley test was positive and there was a complaint of pain in knee area. An orthopedist and a radiologist respectively read these images of the menisci using a grading system based on the MRI signals. To calculate the cumulative intensity of trekking of the workers, the mean trail distance, the difficulty of the trail, the tenure at each national parks, and the number of treks per month for each worker from the start of work until the present were investigated. Chi-square tests was performed to see if there were differences in the menisci lesions grade according to the variables. The variables used in the Chi-square test were evaluated using simple logistic regression analysis to get crude odds ratios, and adjusted odds ratios and 95 % confidence intervals were calculated using multivariate logistic regression analysis after establishing three different models according to the adjusted variables. According to the MRI signal grades of menisci, 29 % were grade 0, 11.3 % were grade 1, 46.0 % were grade 2, and 13.7 % were grade 3. The differences in the MRI signal grades of menisci according to age and the intensity of trekking as calculated by the three different methods were statistically significant. Multiple logistic regression analysis was performed for three models. In model 1, there was no statistically significant factor affecting the menisci lesions. In model 2, among the factors affecting the menisci lesions, the OR of a high cumulative intensity of trekking was 4.08 (95 % CI 1.00-16.61), and in model 3, the OR of a high cumulative intensity of trekking was 5.84 (95 % CI 1.09-31.26). The factor that most affected the menisci lesions among the workers in Korean national park was a high cumulative intensity of trekking.

Is parenting style a predictor of suicide attempts in a representative sample of adolescents?

PubMed

Donath, Carolin; Graessel, Elmar; Baier, Dirk; Bleich, Stefan; Hillemacher, Thomas

2014-04-26

Suicidal ideation and suicide attempts are serious but not rare conditions in adolescents. However, there are several research and practical suicide-prevention initiatives that discuss the possibility of preventing serious self-harm. Profound knowledge about risk and protective factors is therefore necessary. The aim of this study is a) to clarify the role of parenting behavior and parenting styles in adolescents' suicide attempts and b) to identify other statistically significant and clinically relevant risk and protective factors for suicide attempts in a representative sample of German adolescents. In the years 2007/2008, a representative written survey of N = 44,610 students in the 9th grade of different school types in Germany was conducted. In this survey, the lifetime prevalence of suicide attempts was investigated as well as potential predictors including parenting behavior. A three-step statistical analysis was carried out: I) As basic model, the association between parenting and suicide attempts was explored via binary logistic regression controlled for age and sex. II) The predictive values of 13 additional potential risk/protective factors were analyzed with single binary logistic regression analyses for each predictor alone. Non-significant predictors were excluded in Step III. III) In a multivariate binary logistic regression analysis, all significant predictor variables from Step II and the parenting styles were included after testing for multicollinearity. Three parental variables showed a relevant association with suicide attempts in adolescents - (all protective): mother's warmth and father's warmth in childhood and mother's control in adolescence (Step I). In the full model (Step III), Authoritative parenting (protective: OR: .79) and Rejecting-Neglecting parenting (risk: OR: 1.63) were identified as significant predictors (p < .001) for suicidal attempts. Seven further variables were interpreted to be statistically significant and clinically relevant: ADHD, female sex, smoking, Binge Drinking, absenteeism/truancy, migration background, and parental separation events. Parenting style does matter. While children of Authoritative parents profit, children of Rejecting-Neglecting parents are put at risk - as we were able to show for suicide attempts in adolescence. Some of the identified risk factors contribute new knowledge and potential areas of intervention for special groups such as migrants or children diagnosed with ADHD.

Variability in the prescription of non-biologic disease-modifying antirheumatic drugs for the treatment of spondyloarthritis in Spain.

PubMed

Silva-Fernández, Lucía; Pérez-Vicente, Sabina; Martín-Martínez, María Auxiliadora; López-González, Ruth

2015-06-01

To describe the variability in the prescription of non-biologic disease-modifying antirheumatic drugs (nbDMARDs) for the treatment of spondyloarthritis (SpA) in Spain and to explore which factors relating to the disease, patient, physician, and/or center contribute to these variations. A retrospective medical record review was performed using a probabilistic sample of 1168 patients with SpA from 45 centers distributed in 15/19 regions in Spain. The sociodemographic and clinical features and the use of drugs were recorded following a standardized protocol. Logistic regression, with nbDMARDs prescriptions as the dependent variable, was used for bivariable analysis. A multilevel logistic regression model was used to study variability. The probability of receiving an nbDMARD was higher in female patients [OR = 1.548; 95% confidence interval (CI): 1.208-1.984], in those with elevated C-reactive protein (OR = 1.039; 95% CI: 1.012-1.066) and erythrocyte sedimentation rate (OR = 1.012; 95% CI: 1.003-1.021), in those with a higher number of affected peripheral joints (OR = 12.921; 95% CI: 2.911-57.347), and in patients with extra-articular manifestations like dactylitis (OR = 2.997; 95% CI: 1.868-4.809), psoriasis (OR = 2.601; 95% CI: 1.870-3.617), and enthesitis (OR = 1.717; 95% CI: 1.224-2.410). There was a marked variability in the prescription of nbDMARDs for SpA patients, depending on the center (14.3%; variance 0.549; standard error 0.161; median odds ratio 2.366; p < 0.001). After adjusting for patient and center variables, this variability fell to 3.8%. A number of factors affecting variability in clinical practice, and which are independent of disease characteristics, are associated with the probability of SpA patients receiving nbDMARDs in Spain. Copyright © 2015 Elsevier Inc. All rights reserved.

Variability in the prescription of biological drugs in rheumatoid arthritis in Spain: a multilevel analysis.

PubMed

López-Longo, Francisco Javier; Seoane-Mato, Daniel; Martín-Martínez, María A; Sánchez-Alonso, Fernando

2018-04-01

To describe variability in the prescription of biologics (B-DMARDs) for patients with rheumatoid arthritis (RA) in hospitals in Spain, and to explore which characteristics of the patient, the doctor and the hospital are associated with this variability. Cross-sectional multicentric study in 46 rheumatology services of the National Health System. Medical records of 1188 randomly selected patients were reviewed. The association of each variable with B-DMARD prescription was analyzed using simple logistic regressions. Multilevel logistic regression models were created to analyze variability among centers. 36.8% of patients had received B-DMARD. The proportion of patients being treated with B-DMARDs varied between 3.6 and 71.4% depending on the center. Association of prescription of B-DMARD with patient age (OR = 0.958, 95% CI = 0.947-0.968, p < 0.001), longer disease duration (OR = 1.05, 95% CI = 1.032-1.069, p < 0.001), higher CRP levels (OR = 1.022, 95% CI = 1.003-1.042, p = 0.023), and higher number of hospitalizations (OR = 1.286, 95% CI = 1.145-1.446, p < 0.001) was observed. With regard to the center characteristics, the existence of telephone consultations (OR = 1.438, 95% CI = 1.037-1.994, p = 0.03) and the number of beds (OR = 1.045, 95% CI = 1.001-1.091, p = 0.044) were positively associated with prescription of B-DMARDs. Patient variables explained 34.04% of the variability among centers. By adjusting for patient and hospital characteristics, it went up to 83.71%. There is variability in the prescription of B-DMARDs for patients with RA among hospitals which is associated, to a greater extent, with the center characteristics. B-DMARDs prescription could be partly explained by other factors not covered by the current study including the provider's attitudes towards biologics and other hospital characteristics.

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.…

A Methodology for Generating Placement Rules that Utilizes Logistic Regression

ERIC Educational Resources Information Center

Wurtz, Keith

2008-01-01

The purpose of this article is to provide the necessary tools for institutional researchers to conduct a logistic regression analysis and interpret the results. Aspects of the logistic regression procedure that are necessary to evaluate models are presented and discussed with an emphasis on cutoff values and choosing the appropriate number of…

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...

Periodontal disease in Chinese patients with systemic lupus erythematosus.

PubMed

Zhang, Qiuxiang; Zhang, Xiaoli; Feng, Guijaun; Fu, Ting; Yin, Rulan; Zhang, Lijuan; Feng, Xingmei; Li, Liren; Gu, Zhifeng

2017-08-01

Disease of systemic lupus erythematosus (SLE) and periodontal disease (PD) shares the common multiple characteristics. The aims of the present study were to evaluate the prevalence and severity of periodontal disease in Chinese SLE patients and to determine the association between SLE features and periodontal parameters. A cross-sectional study of 108 SLE patients together with 108 age- and sex-matched healthy controls was made. Periodontal status was conducted by two dentists independently. Sociodemographic characteristics, lifestyle factors, medication use, and clinical parameters were also assessed. The periodontal status was significantly worse in SLE patients compared to controls. In univariate logistic regression, SLE had a significant 2.78-fold [95% confidence interval (CI) 1.60-4.82] increase in odds of periodontitis compared to healthy controls. Adjusted for potential risk factors, patients with SLE had 13.98-fold (95% CI 5.10-38.33) increased odds against controls. In multiple linear regression model, the independent variable negatively and significantly associated with gingival index was education (P = 0.005); conversely, disease activity (P < 0.001) and plaque index (P = 0.002) were positively associated; Age was the only variable independently associated with periodontitis of SLE in multivariate logistic regression (OR 1.348; 95% CI: 1.183-1.536, P < 0.001). Chinese SLE patients were likely to suffer from higher odds of PD. These findings confirmed the importance of early interventions in combination with medical therapy. It is necessary for a close collaboration between dentists and clinicians when treating those patients.

Estimating the Probability of Elevated Nitrate Concentrations in Ground Water in Washington State

USGS Publications Warehouse

Frans, Lonna M.

2008-01-01

Logistic regression was used to relate anthropogenic (manmade) and natural variables to the occurrence of elevated nitrate concentrations in ground water in Washington State. Variables that were analyzed included well depth, ground-water recharge rate, precipitation, population density, fertilizer application amounts, soil characteristics, hydrogeomorphic regions, and land-use types. Two models were developed: one with and one without the hydrogeomorphic regions variable. The variables in both models that best explained the occurrence of elevated nitrate concentrations (defined as concentrations of nitrite plus nitrate as nitrogen greater than 2 milligrams per liter) were the percentage of agricultural land use in a 4-kilometer radius of a well, population density, precipitation, soil drainage class, and well depth. Based on the relations between these variables and measured nitrate concentrations, logistic regression models were developed to estimate the probability of nitrate concentrations in ground water exceeding 2 milligrams per liter. Maps of Washington State were produced that illustrate these estimated probabilities for wells drilled to 145 feet below land surface (median well depth) and the estimated depth to which wells would need to be drilled to have a 90-percent probability of drawing water with a nitrate concentration less than 2 milligrams per liter. Maps showing the estimated probability of elevated nitrate concentrations indicated that the agricultural regions are most at risk followed by urban areas. The estimated depths to which wells would need to be drilled to have a 90-percent probability of obtaining water with nitrate concentrations less than 2 milligrams per liter exceeded 1,000 feet in the agricultural regions; whereas, wells in urban areas generally would need to be drilled to depths in excess of 400 feet.

A comparison of logistic regression analysis and an artificial neural network using the BI-RADS lexicon for ultrasonography in conjunction with introbserver variability.

PubMed

Kim, Sun Mi; Han, Heon; Park, Jeong Mi; Choi, Yoon Jung; Yoon, Hoi Soo; Sohn, Jung Hee; Baek, Moon Hee; Kim, Yoon Nam; Chae, Young Moon; June, Jeon Jong; Lee, Jiwon; Jeon, Yong Hwan

2012-10-01

To determine which Breast Imaging Reporting and Data System (BI-RADS) descriptors for ultrasound are predictors for breast cancer using logistic regression (LR) analysis in conjunction with interobserver variability between breast radiologists, and to compare the performance of artificial neural network (ANN) and LR models in differentiation of benign and malignant breast masses. Five breast radiologists retrospectively reviewed 140 breast masses and described each lesion using BI-RADS lexicon and categorized final assessments. Interobserver agreements between the observers were measured by kappa statistics. The radiologists' responses for BI-RADS were pooled. The data were divided randomly into train (n = 70) and test sets (n = 70). Using train set, optimal independent variables were determined by using LR analysis with forward stepwise selection. The LR and ANN models were constructed with the optimal independent variables and the biopsy results as dependent variable. Performances of the models and radiologists were evaluated on the test set using receiver-operating characteristic (ROC) analysis. Among BI-RADS descriptors, margin and boundary were determined as the predictors according to stepwise LR showing moderate interobserver agreement. Area under the ROC curves (AUC) for both of LR and ANN were 0.87 (95% CI, 0.77-0.94). AUCs for the five radiologists ranged 0.79-0.91. There was no significant difference in AUC values among the LR, ANN, and radiologists (p > 0.05). Margin and boundary were found as statistically significant predictors with good interobserver agreement. Use of the LR and ANN showed similar performance to that of the radiologists for differentiation of benign and malignant breast masses.

Predicting the onset of smoking in boys and girls.

PubMed

Charlton, A; Blair, V

1989-01-01

The problem of the high prevalence of smoking among girls and young women is of great concern. In an attempt to identify the factors which influence girls and boys respectively to attempt smoking, the study examines social background, advertising and brand awareness, knowledge, teaching and personal beliefs in conjunction as predictors of smoking. In this study which involved the administration of identical pre- and post-test questionnaires to a sample of boys and girls aged 12 and 13 years, nine variables expressed by never-smokers at pre-test stage were assessed as predictors of immediate future smoking. The two tests were administered 4 months apart to 1125 boys and 1213 girls in northern England. The nine variables included were parental smoking, best friends' smoking, perceived positive values of smoking, perceived negative values of smoking, correct health knowledge, cigarette-brand awareness, having a favourite cigarette advertisement, having a cigarette-brand sponsored sport in four top favourites on television. One group received teaching about smoking between the pre- and post-tests and this was also included as a variable. For boys, no variable investigated had any consistently statistically significant correlation with the uptake of smoking. The most important predictor of smoking for boys, having a best friend who smoked, was significant on application of the chi 2 test (P 0.037), although it was non-significant when included singly in a logistic regression model (0.094); the discrepancy was probably due to the small number of best friends known to smoke. For girls, four variables were found to be significant predictors of smoking when included singly in a logistic regression.(ABSTRACT TRUNCATED AT 250 WORDS)

Factors Associated with HIV Testing Among Participants from Substance Use Disorder Treatment Programs in the US: A Machine Learning Approach.

PubMed

Pan, Yue; Liu, Hongmei; Metsch, Lisa R; Feaster, Daniel J

2017-02-01

HIV testing is the foundation for consolidated HIV treatment and prevention. In this study, we aim to discover the most relevant variables for predicting HIV testing uptake among substance users in substance use disorder treatment programs by applying random forest (RF), a robust multivariate statistical learning method. We also provide a descriptive introduction to this method for those who are unfamiliar with it. We used data from the National Institute on Drug Abuse Clinical Trials Network HIV testing and counseling study (CTN-0032). A total of 1281 HIV-negative or status unknown participants from 12 US community-based substance use disorder treatment programs were included and were randomized into three HIV testing and counseling treatment groups. The a priori primary outcome was self-reported receipt of HIV test results. Classification accuracy of RF was compared to logistic regression, a standard statistical approach for binary outcomes. Variable importance measures for the RF model were used to select the most relevant variables. RF based models produced much higher classification accuracy than those based on logistic regression. Treatment group is the most important predictor among all covariates, with a variable importance index of 12.9%. RF variable importance revealed that several types of condomless sex behaviors, condom use self-efficacy and attitudes towards condom use, and level of depression are the most important predictors of receipt of HIV testing results. There is a non-linear negative relationship between count of condomless sex acts and the receipt of HIV testing. In conclusion, RF seems promising in discovering important factors related to HIV testing uptake among large numbers of predictors and should be encouraged in future HIV prevention and treatment research and intervention program evaluations.

Poor sleep quality and nightmares are associated with non-suicidal self-injury in adolescents.

PubMed

Liu, Xianchen; Chen, Hua; Bo, Qi-Gui; Fan, Fang; Jia, Cun-Xian

2017-03-01

Non-suicidal self-injury (NSSI) is prevalent and is associated with increased risk of suicidal behavior in adolescents. This study examined which sleep variables are associated with NSSI, independently from demographics and mental health problems in Chinese adolescents. Participants consisted of 2090 students sampled from three high schools in Shandong, China and had a mean age of 15.49 years. Participants completed a sleep and health questionnaire to report their demographic and family information, sleep duration and sleep problems, impulsiveness, hopelessness, internalizing and externalizing problems, and NSSI. A series of regression analyses were conducted to examine the associations between sleep variables and NSSI. Of the sample, 12.6 % reported having ever engaged in NSSI and 8.8 % engaged during the last year. Univariate logistic analyses demonstrated that multiple sleep variables including short sleep duration, insomnia symptoms, poor sleep quality, sleep insufficiency, unrefreshed sleep, sleep dissatisfaction, daytime sleepiness, fatigue, snoring, and nightmares were associated with increased risk of NSSI. After adjusting for demographic and mental health variables, NSSI was significantly associated with sleeping <6 h per night, poor sleep quality, sleep dissatisfaction, daytime sleepiness, and frequent nightmares. Stepwise logistic regression model demonstrated that poor sleep quality (OR = 2.18, 95 % CI = 1.37-3.47) and frequent nightmares (OR = 2.88, 95 % CI = 1.45-5.70) were significantly independently associated with NSSI. In conclusion, while multiple sleep variables are associated with NSSI, poor sleep quality and frequent nightmares are independent risk factors of NSSI. These findings may have important implications for further research of sleep self-harm mechanisms and early detection and prevention of NSSI in adolescents.

Logistic regression modeling to assess groundwater vulnerability to contamination in Hawaii, USA

NASA Astrophysics Data System (ADS)

Mair, Alan; El-Kadi, Aly I.

2013-10-01

Capture zone analysis combined with a subjective susceptibility index is currently used in Hawaii to assess vulnerability to contamination of drinking water sources derived from groundwater. In this study, we developed an alternative objective approach that combines well capture zones with multiple-variable logistic regression (LR) modeling and applied it to the highly-utilized Pearl Harbor and Honolulu aquifers on the island of Oahu, Hawaii. Input for the LR models utilized explanatory variables based on hydrogeology, land use, and well geometry/location. A suite of 11 target contaminants detected in the region, including elevated nitrate (> 1 mg/L), four chlorinated solvents, four agricultural fumigants, and two pesticides, was used to develop the models. We then tested the ability of the new approach to accurately separate groups of wells with low and high vulnerability, and the suitability of nitrate as an indicator of other types of contamination. Our results produced contaminant-specific LR models that accurately identified groups of wells with the lowest/highest reported detections and the lowest/highest nitrate concentrations. Current and former agricultural land uses were identified as significant explanatory variables for eight of the 11 target contaminants, while elevated nitrate was a significant variable for five contaminants. The utility of the combined approach is contingent on the availability of hydrologic and chemical monitoring data for calibrating groundwater and LR models. Application of the approach using a reference site with sufficient data could help identify key variables in areas with similar hydrogeology and land use but limited data. In addition, elevated nitrate may also be a suitable indicator of groundwater contamination in areas with limited data. The objective LR modeling approach developed in this study is flexible enough to address a wide range of contaminants and represents a suitable addition to the current subjective approach.

Methods for estimating selected low-flow frequency statistics for unregulated streams in Kentucky

USGS Publications Warehouse

Martin, Gary R.; Arihood, Leslie D.

2010-01-01

This report provides estimates of, and presents methods for estimating, selected low-flow frequency statistics for unregulated streams in Kentucky including the 30-day mean low flows for recurrence intervals of 2 and 5 years (30Q2 and 30Q5) and the 7-day mean low flows for recurrence intervals of 5, 10, and 20 years (7Q2, 7Q10, and 7Q20). Estimates of these statistics are provided for 121 U.S. Geological Survey streamflow-gaging stations with data through the 2006 climate year, which is the 12-month period ending March 31 of each year. Data were screened to identify the periods of homogeneous, unregulated flows for use in the analyses. Logistic-regression equations are presented for estimating the annual probability of the selected low-flow frequency statistics being equal to zero. Weighted-least-squares regression equations were developed for estimating the magnitude of the nonzero 30Q2, 30Q5, 7Q2, 7Q10, and 7Q20 low flows. Three low-flow regions were defined for estimating the 7-day low-flow frequency statistics. The explicit explanatory variables in the regression equations include total drainage area and the mapped streamflow-variability index measured from a revised statewide coverage of this characteristic. The percentage of the station low-flow statistics correctly classified as zero or nonzero by use of the logistic-regression equations ranged from 87.5 to 93.8 percent. The average standard errors of prediction of the weighted-least-squares regression equations ranged from 108 to 226 percent. The 30Q2 regression equations have the smallest standard errors of prediction, and the 7Q20 regression equations have the largest standard errors of prediction. The regression equations are applicable only to stream sites with low flows unaffected by regulation from reservoirs and local diversions of flow and to drainage basins in specified ranges of basin characteristics. Caution is advised when applying the equations for basins with characteristics near the applicable limits and for basins with karst drainage features.

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.

Third and Fourth Degree Perineal Injury After Vaginal Delivery: Does Race Make a Difference?

PubMed Central

de Silva, Kanoe-Lehua; Tsai, Pai-Jong Stacy; Kon, Leanne M; Kessel, Bruce; Seto, Todd; Kaneshiro, Bliss

2014-01-01

Severe perineal injury (third and fourth degree laceration) at the time of vaginal delivery increases the risk of fecal incontinence, chronic perineal pain, and dyspareunia.1–5 Studies suggest the prevalence of severe perineal injury may vary by racial group.6 The purpose of the current study was to examine rates of severe perineal injury in different Asian and Pacific Islander subgroups. A retrospective cohort study was performed among all patients who had a vaginal delivery at Queens Medical Center in Honolulu, Hawai‘i between January 1, 2002 and December 31, 2003. Demographic and health related variables were obtained for each participant. Maternal race/ethnicity (Japanese, Filipino, Chinese, other Asian, Part-Hawaiian/Hawaiian, Micronesian, other Pacific Islander, Caucasian, multiracial [non-Hawaiian], and other) was self-reported by the patient at the time admission. The significance of associations between racial/ethnic groups and demographic and health related variables was determined using chi-square tests for categorical variables and analysis of variance for continuous factors. Multiple logistic regression was performed to adjust for potential confounders when examining severe laceration rates. A total of 1842 subjects met inclusion criteria. The proportion of severe perineal lacerations did not differ significantly between racial groups. In the multiple logistic regression analysis, operative vaginal delivery was related to both race and severe perineal laceration. However, despite adjusting for this variable, race was not associated with an increased risk of having a severe laceration (P = .70). The results of this study indicate the risk of severe perineal laceration does not differ based on maternal race/ethnicity. PMID:24660124

Prevalence of common mental disorders in mothers in the semiarid region of Alagoas and its relationship with nutritional status.

PubMed

Paffer, Adriana Toledo de; Ferreira, Haroldo da Silva; Cabral Júnior, Cyro Rego; Miranda, Claudio Torres de

2012-01-01

Compromised maternal mental health (MMH) is considered to be a risk factor for child malnutrition in low income areas. Psychosocial variables associated with MMH are potentially different between urban and rural environments. The aim here was to investigate whether associations existed between MMH and selected sociodemographic risk factors and whether specific to urban or rural settings. Cross-sectional study on a representative population sample of mothers from the semiarid region of Alagoas. Multistage sampling was used. The subjects were mothers of children aged up to 60 months. MMH was evaluated through the Self-Reporting Questionnaire-20. Mothers' nutritional status was assessed using the body mass index and waist circumference. Univariate analysis used odds ratios (OR) and chi-square. Logistic regression was performed separately for urban and rural subsamples using MMH as the dependent variable. The sample comprised 288 mothers. The prevalences of common mental disorders (CMD) in rural and urban areas were 56.2% and 43.8%, respectively (OR = 1.03; 95% CI: 0.64-1.63). In univariate analysis and logistic regression, the variable of education remained associated with MMH (OR = 2.2; 95% CI: 1.03-4.6) in urban areas. In rural areas, the variable of lack of partner remained associated (OR = 2.6; 95% CI: 1.01-6.7). The prevalence of CMD is high among mothers of children aged up to two years in the semiarid region of Alagoas. This seems to be associated with lower educational level in urban settings and lack of partner in rural settings.

Application of random forests methods to diabetic retinopathy classification analyses.

PubMed

Casanova, Ramon; Saldana, Santiago; Chew, Emily Y; Danis, Ronald P; Greven, Craig M; Ambrosius, Walter T

2014-01-01

Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects. Graded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance. Both types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables. We have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression.

Factors affecting the geographic distribution of West Nile virus in Georgia, USA: 2002-2004.

PubMed

Gibbs, Samantha E J; Wimberly, Michael C; Madden, Marguerite; Masour, Janna; Yabsley, Michael J; Stallknecht, David E

2006-01-01

The distribution of West Nile virus (WNV) is dependent on the occurrence of both susceptible avian reservoir hosts and competent mosquito vectors. Both factors can be influenced by geographic variables such as land use/landcover, elevation, human population density, physiographic region, and temperature. The current study uses geographic information systems (GIS) and logistic regression analyses to model the distribution of WNV in the state of Georgia based on a wild bird indicator system, and to identify human and environmental predictor variables that are important in the determination of WNV distribution. A database for Georgia was constructed that included (1) location points of all the avian samples tested for WNV, (2) local land use classifications, including temperature, physiographic divisions, land use/landcover, and elevation, (3) human demographic data from the U.S. Census, and (4) statistics summarizing land cover, elevation, and climate within a 1-km-radius landscape around each sample point. Logistic regression analysis was carried out using the serostatus of avian collection sites as the dependent variable. Temperature, housing density, urban/suburban land use, and mountain physiographic region were important variables in predicting the distribution of WNV in the state of Georgia. While weak, the positive correlation between WNV-antibody positive sites and the urban/suburban environment was consistent throughout the study period. The risks associated with WNV endemicity appear to be increased in urban/ suburban areas and decreased in the mountainous region of the state. This information may be used in addressing regional public health needs and mosquito control programs.

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…

Classification of sodium MRI data of cartilage using machine learning.

PubMed

Madelin, Guillaume; Poidevin, Frederick; Makrymallis, Antonios; Regatte, Ravinder R

2015-11-01

To assess the possible utility of machine learning for classifying subjects with and subjects without osteoarthritis using sodium magnetic resonance imaging data. Theory: Support vector machine, k-nearest neighbors, naïve Bayes, discriminant analysis, linear regression, logistic regression, neural networks, decision tree, and tree bagging were tested. Sodium magnetic resonance imaging with and without fluid suppression by inversion recovery was acquired on the knee cartilage of 19 controls and 28 osteoarthritis patients. Sodium concentrations were measured in regions of interests in the knee for both acquisitions. Mean (MEAN) and standard deviation (STD) of these concentrations were measured in each regions of interest, and the minimum, maximum, and mean of these two measurements were calculated over all regions of interests for each subject. The resulting 12 variables per subject were used as predictors for classification. Either Min [STD] alone, or in combination with Mean [MEAN] or Min [MEAN], all from fluid suppressed data, were the best predictors with an accuracy >74%, mainly with linear logistic regression and linear support vector machine. Other good classifiers include discriminant analysis, linear regression, and naïve Bayes. Machine learning is a promising technique for classifying osteoarthritis patients and controls from sodium magnetic resonance imaging data. © 2014 Wiley Periodicals, Inc.

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…

Self-reported work ability and work performance in workers with chronic nonspecific musculoskeletal pain.

PubMed

de Vries, Haitze J; Reneman, Michiel F; Groothoff, Johan W; Geertzen, Jan H B; Brouwer, Sandra

2013-03-01

To assess self-reported work ability and work performance of workers who stay at work despite chronic nonspecific musculoskeletal pain (CMP), and to explore which variables were associated with these outcomes. In a cross-sectional study we assessed work ability (Work Ability Index, single item scale 0-10) and work performance (Health and Work Performance Questionnaire, scale 0-10) among 119 workers who continued work while having CMP. Scores of work ability and work performance were categorized into excellent (10), good (9), moderate (8) and poor (0-7). Hierarchical multiple regression and logistic regression analysis was used to analyze the relation of socio-demographic, pain-related, personal- and work-related variables with work ability and work performance. Mean work ability and work performance were 7.1 and 7.7 (poor to moderate). Hierarchical multiple regression analysis revealed that higher work ability scores were associated with lower age, better general health perception, and higher pain self-efficacy beliefs (R(2) = 42 %). Higher work performance was associated with lower age, higher pain self-efficacy beliefs, lower physical work demand category and part-time work (R(2) = 37 %). Logistic regression analysis revealed that work ability ≥8 was significantly explained by age (OR = 0.90), general health perception (OR = 1.04) and pain self-efficacy (OR = 1.15). Work performance ≥8 was explained by pain self-efficacy (OR = 1.11). Many workers with CMP who stay at work report poor to moderate work ability and work performance. Our findings suggest that a subgroup of workers with CMP can stay at work with high work ability and performance, especially when they have high beliefs of pain self-efficacy. Our results further show that not the pain itself, but personal and work-related factors relate to work ability and work performance.

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

PubMed

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

2015-08-01

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

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.

[Effects of situational and individual variables on critical thinking expression].

PubMed

Tanaka, Yuko; Kusumi, Takashi

2016-04-01

The present study examined when people decide to choose an expression that is based on critical thinking, and how situational and individual variables affect such a decision process. Given a conversation scenario including overgeneralization with two friends, participants decided whether to follow the conversation by a critical-thinking expression or not. The authors controlled purpose and topic as situational variables, and measured critical-thinking ability, critical-thinking disposition, and self-monitoring as individual variables. We conducted an experiment in which the situational variables were counterbalanced in a within-subject design with 60 university students. The results of logistic regression analysis showed differences within individuals in the decision process whether to choose a critical-thinking expression, and that some situational factors and some subscales of the individual measurements were related to the differences.

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.

Interpreting the concordance statistic of a logistic regression model: relation to the variance and odds ratio of a continuous explanatory variable

PubMed Central

2012-01-01

Background When outcomes are binary, the c-statistic (equivalent to the area under the Receiver Operating Characteristic curve) is a standard measure of the predictive accuracy of a logistic regression model. Methods An analytical expression was derived under the assumption that a continuous explanatory variable follows a normal distribution in those with and without the condition. We then conducted an extensive set of Monte Carlo simulations to examine whether the expressions derived under the assumption of binormality allowed for accurate prediction of the empirical c-statistic when the explanatory variable followed a normal distribution in the combined sample of those with and without the condition. We also examine the accuracy of the predicted c-statistic when the explanatory variable followed a gamma, log-normal or uniform distribution in combined sample of those with and without the condition. Results Under the assumption of binormality with equality of variances, the c-statistic follows a standard normal cumulative distribution function with dependence on the product of the standard deviation of the normal components (reflecting more heterogeneity) and the log-odds ratio (reflecting larger effects). Under the assumption of binormality with unequal variances, the c-statistic follows a standard normal cumulative distribution function with dependence on the standardized difference of the explanatory variable in those with and without the condition. In our Monte Carlo simulations, we found that these expressions allowed for reasonably accurate prediction of the empirical c-statistic when the distribution of the explanatory variable was normal, gamma, log-normal, and uniform in the entire sample of those with and without the condition. Conclusions The discriminative ability of a continuous explanatory variable cannot be judged by its odds ratio alone, but always needs to be considered in relation to the heterogeneity of the population. PMID:22716998

Simple, Efficient Estimators of Treatment Effects in Randomized Trials Using Generalized Linear Models to Leverage Baseline Variables

PubMed Central

Rosenblum, Michael; van der Laan, Mark J.

2010-01-01

Models, such as logistic regression and Poisson regression models, are often used to estimate treatment effects in randomized trials. These models leverage information in variables collected before randomization, in order to obtain more precise estimates of treatment effects. However, there is the danger that model misspecification will lead to bias. We show that certain easy to compute, model-based estimators are asymptotically unbiased even when the working model used is arbitrarily misspecified. Furthermore, these estimators are locally efficient. As a special case of our main result, we consider a simple Poisson working model containing only main terms; in this case, we prove the maximum likelihood estimate of the coefficient corresponding to the treatment variable is an asymptotically unbiased estimator of the marginal log rate ratio, even when the working model is arbitrarily misspecified. This is the log-linear analog of ANCOVA for linear models. Our results demonstrate one application of targeted maximum likelihood estimation. PMID:20628636

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

PubMed

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

2017-02-01

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

Analysis of Variables to Predict First Year Persistence Using Logistic Regression Analysis at the University of South Florida: Model v2.0

ERIC Educational Resources Information Center

Herreid, Charlene H.; Miller, Thomas E.

2009-01-01

This article is the fourth in a series of articles describing an attrition prediction and intervention project at the University of South Florida (USF) in Tampa. In this article, the researchers describe the updated version of the prediction model. The original model was developed from a sample of about 900 First Time in College (FTIC) students…

Help-Seeking Intentions and Behaviors among Mainland Chinese College Students: Integrating the Theory of Planned Behavior and Behavioral Model of Health Services Use

ERIC Educational Resources Information Center

Li, Wenjing; Denson, Linley A.; Dorstyn, Diana S.

2017-01-01

This study investigated help-seeking intentions and use of mental health services within a sample of 1128 Mainland Chinese college students (630 males and 498 females; mean age = 20.01 years, SD = 1.48). Results of structural equation modeling and logistic regression analysis suggested that social-cognitive variables had significant effects both…

Binary Logistic Regression Analysis in Assessment and Identifying Factors That Influence Students' Academic Achievement: The Case of College of Natural and Computational Science, Wolaita Sodo University, Ethiopia

ERIC Educational Resources Information Center

Zewude, Bereket Tessema; Ashine, Kidus Meskele

2016-01-01

An attempt has been made to assess and identify the major variables that influence student academic achievement at college of natural and computational science of Wolaita Sodo University in Ethiopia. Study time, peer influence, securing first choice of department, arranging study time outside class, amount of money received from family, good life…

First World War and Mental Health: a retrospective comparative study of veterans admitted to a psychiatric hospital between 1915 and 1918.

PubMed

Lagonia, Paolo; Aloi, Matteo; Magliocco, Fabio; Cerminara, Gregorio; Segura-Garcia, Cristina; Del Vecchio, Valeria; Luciano, Mario; Fiorillo, Andrea; De Fazio, Pasquale

2017-01-01

The association between mental illness and war has been repeatedly investigated. Higher levels of depressive symptoms and an increased suicidal risk have been found in veterans. In this study we investigated the mental health conditions among Italian soldiers during the “Great War”, who were hospitalized in a mental health hospital in Italy. The study sample consists of 498 soldiers who were admitted during the World War I between 1915 and 1918, and 498 civilian patients admitted in two different periods (1898-1914, 1919- 1932). Psychiatric diagnoses have been recorded retrospectively by a detailed examination of clinical records. Socio-demographic informations, diagnosis at first admission, number of admissions, and deployment in war zones were collected. A logistic regression analysis was performed, the diagnosis of depression was considered as dependent variable while clinical and demographic variables as independent predictors. Soldiers deployed in war zones were more likely to have a diagnosis of depression compared to those not serving on the frontline. The logistic regression analysis showed that the diagnosis of depression is predicted by being a soldier and being deployed in a war area. Our data confirm that soldiers engaged in war are at higher risk of developing depression compared to non-deployed soldiers.

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.

Ventilator-associated pneumonia: the influence of bacterial resistance, prescription errors, and de-escalation of antimicrobial therapy on mortality rates.

PubMed

Souza-Oliveira, Ana Carolina; Cunha, Thúlio Marquez; Passos, Liliane Barbosa da Silva; Lopes, Gustavo Camargo; Gomes, Fabiola Alves; Röder, Denise Von Dolinger de Brito

2016-01-01

Ventilator-associated pneumonia is the most prevalent nosocomial infection in intensive care units and is associated with high mortality rates (14-70%). This study evaluated factors influencing mortality of patients with Ventilator-associated pneumonia (VAP), including bacterial resistance, prescription errors, and de-escalation of antibiotic therapy. This retrospective study included 120 cases of Ventilator-associated pneumonia admitted to the adult adult intensive care unit of the Federal University of Uberlândia. The chi-square test was used to compare qualitative variables. Student's t-test was used for quantitative variables and multiple logistic regression analysis to identify independent predictors of mortality. De-escalation of antibiotic therapy and resistant bacteria did not influence mortality. Mortality was 4 times and 3 times higher, respectively, in patients who received an inappropriate antibiotic loading dose and in patients whose antibiotic dose was not adjusted for renal function. Multiple logistic regression analysis revealed the incorrect adjustment for renal function was the only independent factor associated with increased mortality. Prescription errors influenced mortality of patients with Ventilator-associated pneumonia, underscoring the challenge of proper Ventilator-associated pneumonia treatment, which requires continuous reevaluation to ensure that clinical response to therapy meets expectations. Copyright © 2016. Published by Elsevier Editora Ltda.

Medication adherence among patients in a chronic disease clinic.

PubMed

Tourkmani, Ayla M; Al Khashan, Hisham I; Albabtain, Monirah A; Al Harbi, Turki J; Al Qahatani, Hala B; Bakhiet, Ahmed H

2012-12-01

To assess motivation and knowledge domains of medication adherence intention, and to determine their predictors in an ambulatory setting. We conducted a cross-sectional survey study among patients attending a chronic disease clinic at the Family and Community Medicine Department, Prince Sultan Military Medical City, Riyadh, Kingdom of Saudi Arabia between June and September 2010. Adherence intention was assessed using Modified Morisky Scale. Predictors of low motivation and/or knowledge were determined using logistic regression models. A total of 347 patients were interviewed during the study duration. Most patients (75.5%) had 2 or more chronic diseases with an average of 6.3 +/- 2.3 medications, and 6.5 +/- 2.9 pills per prescription. The frequency of adherence intention was low (4.6%), variable (37.2%), and high (58.2%). In multivariate logistic regression analysis, younger age and having asthma were significantly associated with low motivation, while male gender, single status, and not having hypertension were significantly associated with low knowledge. Single status was the only independent predictor of low adherence intention. In a population with multiple chronic diseases and high illiteracy rate, more than 40% had low/variable intention to adhere to prescribed medications. Identifying predictors of this group may help in providing group-specific interventional programs.

Factors associated with preventable infant death: a multiple logistic regression

PubMed Central

Vidal e Silva, Sandra Maria Cunha; Tuon, Rogério Antonio; Probst, Livia Fernandes; Gondinho, Brunna Verna Castro; Pereira, Antonio Carlos; Meneghim, Marcelo de Castro; Cortellazzi, Karine Laura; Ambrosano, Glaucia Maria Bovi

2018-01-01

ABSTRACT OBJECTIVE To identify and analyze factors associated with preventable child deaths. METHODS This analytical cross-sectional study had preventable child mortality as dependent variable. From a population of 34,284 live births, we have selected a systematic sample of 4,402 children who did not die compared to 272 children who died from preventable causes during the period studied. The independent variables were analyzed in four hierarchical blocks: sociodemographic factors, the characteristics of the mother, prenatal and delivery care, and health conditions of the patient and neonatal care. We performed a descriptive statistical analysis and estimated multiple hierarchical logistic regression models. RESULTS Approximatelly 35.3% of the deaths could have been prevented with the early diagnosis and treatment of diseases during pregnancy and 26.8% of them could have been prevented with better care conditions for pregnant women. CONCLUSIONS The following characteristics of the mother are determinant for the higher mortality of children before the first year of life: living in neighborhoods with an average family income lower than four minimum wages, being aged ≤ 19 years, having one or more alive children, having a child with low APGAR level at the fifth minute of life, and having a child with low birth weight. PMID:29723389

Female autonomy and reported abortion-seeking in Ghana, West Africa.

PubMed

Rominski, Sarah D; Gupta, Mira; Aborigo, Raymond; Adongo, Phillip; Engman, Cyril; Hodgson, Abraham; Moyer, Cheryl

2014-09-01

To investigate factors associated with self-reported pregnancy termination in Ghana and thereby appreciate the correlates of abortion-seeking in order to understand safe abortion care provision. In a retrospective study, data from the Ghana 2008 Demographic and Health Survey were used to investigate factors associated with self-reported pregnancy termination. Variables on an individual and household level were examined by both bivariate analyses and multivariate logistic regression. A five-point autonomy scale was created to explore the role of female autonomy in reported abortion-seeking behavior. Among 4916 women included in the survey, 791 (16.1%) reported having an abortion. Factors associated with abortion-seeking included being older, having attended school, and living in an urban versus a rural area. When entered into a logistic regression model with demographic control variables, every step up the autonomy scale (i.e. increasing autonomy) was associated with a 14.0% increased likelihood of reporting the termination of a pregnancy (P < 0.05). Although health system barriers might play a role in preventing women from seeking safe abortion services, autonomy on an individual level is also important and needs to be addressed if women are to be empowered to seek safe abortion services. Copyright © 2014 International Federation of Gynecology and Obstetrics. Published by Elsevier Ireland Ltd. All rights reserved.

Uterine fibroids at routine second-trimester ultrasound survey and risk of sonographic short cervix.

PubMed

Blitz, Matthew J; Rochelson, Burton; Augustine, Stephanie; Greenberg, Meir; Sison, Cristina P; Vohra, Nidhi

2016-11-01

To determine whether women with sonographically identified uterine fibroids are at higher risk for a short cervix. This retrospective cohort study evaluated all women with singleton gestations who had a routine second-trimester ultrasound at 17-23 weeks gestational age from 2010 to 2013. When fibroids were noted, their presence, number, location and size were recorded. Exclusion criteria included a history of cervical conization or loop electrosurgical excision procedure (LEEP), uterine anomalies, maternal age greater than 40 years, and a previously placed cerclage. The primary variable of interest was short cervix (<25 mm). Secondary variables of interest included gestational age at delivery, mode of delivery, indication for cesarean, malpresentation, birth weight, and Apgar scores. A multivariable logistic regression analysis was performed. Fibroids were identified in 522/10 314 patients (5.1%). In the final multivariable logistic regression model, short cervix was increased in women with fibroids (OR 2.29, 95% CI: 1.40, 3.74). The number of fibroids did not affect the frequency of short cervix. Fibroids were significantly associated with preterm delivery (<37 weeks), primary cesarean, breech presentation, lower birth weight infants, and lower Apgar scores. Women with uterine fibroids may be at higher risk for a short cervix. Fibroids are also associated with several adverse obstetric and neonatal outcomes.

The prevalence of postpartum depression: the relative significance of three social status indices.

PubMed

Segre, Lisa S; O'Hara, Michael W; Arndt, Stephan; Stuart, Scott

2007-04-01

Little is known about the prevalence of clinically significant postpartum depression in women of varying social status. The purpose of the present study was to examine the prevalence of postpartum depression as a function of three indices of social status: income, education and occupational prestige. A sample of 4,332 postpartum women completed a demographic interview and the Inventory to Diagnose Depression, a self-report scale developed to identify a major depressive episode in accordance with DSM diagnostic criteria. Logistic regression was used to assess the relative significance of the three social status variables as risk factors for postpartum depression controlling for the effects of correlated demographic variables. In the logistic regression, income, occupational prestige, marital status, and number of children were significant predictors of postpartum depression controlling for the effects of other related demographic characteristics. The Wald Chi Square value for each of these significant predictors indicates that income was the strongest predictor. The prevalence of postpartum depression was significantly higher in financially poor relative to financially affluent women. Maternal depression screening programs targeting women who are financially poor are well placed. Future research is needed to replicate the present findings in a more ethnically diverse sample that includes the full age range of teenage mothers.

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.

A predictive model to allocate frequent service users of community-based mental health services to different packages of care.

PubMed

Grigoletti, Laura; Amaddeo, Francesco; Grassi, Aldrigo; Boldrini, Massimo; Chiappelli, Marco; Percudani, Mauro; Catapano, Francesco; Fiorillo, Andrea; Perris, Francesco; Bacigalupi, Maurizio; Albanese, Paolo; Simonetti, Simona; De Agostini, Paola; Tansella, Michele

2010-01-01

To develop predictive models to allocate patients into frequent and low service users groups within the Italian Community-based Mental Health Services (CMHSs). To allocate frequent users to different packages of care, identifying the costs of these packages. Socio-demographic and clinical data and GAF scores at baseline were collected for 1250 users attending five CMHSs. All psychiatric contacts made by these patients during six months were recorded. A logistic regression identified frequent service users predictive variables. Multinomial logistic regression identified variables able to predict the most appropriate package of care. A cost function was utilised to estimate costs. Frequent service users were 49%, using nearly 90% of all contacts. The model classified correctly 80% of users in the frequent and low users groups. Three packages of care were identified: Basic Community Treatment (4,133 Euro per six months); Intensive Community Treatment (6,180 Euro) and Rehabilitative Community Treatment (11,984 Euro) for 83%, 6% and 11% of frequent service users respectively. The model was found to be accurate for 85% of users. It is possible to develop predictive models to identify frequent service users and to assign them to pre-defined packages of care, and to use these models to inform the funding of psychiatric care.

Patient acceptance of non-invasive testing for fetal aneuploidy via cell-free fetal DNA.

PubMed

Vahanian, Sevan A; Baraa Allaf, M; Yeh, Corinne; Chavez, Martin R; Kinzler, Wendy L; Vintzileos, Anthony M

2014-01-01

To evaluate factors associated with patient acceptance of noninvasive prenatal testing for trisomy 21, 18 and 13 via cell-free fetal DNA. This was a retrospective study of all patients who were offered noninvasive prenatal testing at a single institution from 1 March 2012 to 2 July 2012. Patients were identified through our perinatal ultrasound database; demographic information, testing indication and insurance coverage were compared between patients who accepted the test and those who declined. Parametric and nonparametric tests were used as appropriate. Significant variables were assessed using multivariate logistic regression. The value p < 0.05 was considered significant. Two hundred thirty-five patients were offered noninvasive prenatal testing. Ninety-three patients (40%) accepted testing and 142 (60%) declined. Women who accepted noninvasive prenatal testing were more commonly white, had private insurance and had more than one testing indication. There was no statistical difference in the number or the type of testing indications. Multivariable logistic regression analysis was then used to assess individual variables. After controlling for race, patients with public insurance were 83% less likely to accept noninvasive prenatal testing than those with private insurance (3% vs. 97%, adjusted RR 0.17, 95% CI 0.05-0.62). In our population, having public insurance was the factor most strongly associated with declining noninvasive prenatal testing.

Plasma Homocysteine and Asymmetrical Dimethyl-l-Arginine (ADMA) and Whole Blood DNA Methylation in Early and Neovascular Age-Related Macular Degeneration: A Pilot Study.

PubMed

Pinna, Antonio; Zinellu, Angelo; Tendas, Donatella; Blasetti, Francesco; Carru, Ciriaco; Castiglia, Paolo

2016-01-01

To compare the plasma levels of homocysteine and asymmetrical dimethyl-l-arginine (ADMA) and the degree of whole blood DNA methylation in patients with early and neovascular age-related macular degeneration (AMD) and in controls without maculopathy of any sort. This observational case-control pilot study included 39 early AMD patients, 27 neovascular AMD patients and 132 sex- and age-matched controls without maculopathy. Plasma homocysteine and ADMA concentrations and the degree of whole blood DNA methylation were measured. Quantitative variables were compared by Student's t-test or Mann-Whitney test. Logistic regression models were used to investigate the significance of the association between early or wet AMD and some variables. There were no significant differences in mean plasma homocysteine and ADMA concentrations and in the degree of whole blood DNA methylation between patients with early or neovascular AMD and their controls. Similarly, logistic regression analysis disclosed that plasma homocysteine and ADMA levels were not associated with an increased risk for early or neovascular AMD. We failed to demonstrate an association between early or neovascular AMD and increased plasma homocysteine and/or ADMA. Results also suggest that the degree of whole blood DNA methylation is not a marker of AMD.

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.

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.

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

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

A review of logistic regression models used to predict post-fire tree mortality of western North American conifers

Treesearch

Travis Woolley; David C. Shaw; Lisa M. Ganio; Stephen Fitzgerald

2012-01-01

Logistic regression models used to predict tree mortality are critical to post-fire management, planning prescribed bums and understanding disturbance ecology. We review literature concerning post-fire mortality prediction using logistic regression models for coniferous tree species in the western USA. We include synthesis and review of: methods to develop, evaluate...

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

What is the predictor of surgical mortality in adult colorectal perforation? The clinical characteristics and results of a multivariate logistic regression analysis.

PubMed

Hsu, Chao-Wen; Wang, Jui-Ho; Kung, Ya-Hsin; Chang, Min-Chi

2017-06-01

Colorectal perforations are a serious condition associated with a high mortality. The aim of this study was to describe the clinical characteristics and identify predictors for the surgical mortality in adult patients with colorectal perforation, thereby achieving better outcomes. A retrospective study of adult patients diagnosed with colorectal perforation operated was performed. The clinical variables that might influence the surgical mortality were first analyzed, and the significant variables were then analyzed using a logistic regression model. A total of 423 patients were identified, and the surgical mortality rate was 36.9 %. The most common etiology was diverticulitis (38.2 %). The highest etiology-specific mortality was for colorectal cancer (61.5 %) and ischemic proctocolitis (59.8 %). In a logistic analysis, the significant predictors for the surgical mortality were ≥3 comorbidities (p = 0.034), preoperation American Society of Anesthesiologists score ≥4 (p = 0.025), preoperative sepsis or septic shock (p < 0.001), colorectal cancer or ischemic proctocolitis (p = 0.035), reoperation (p = 0.041), and Hinchey classification grade IV (p = 0.024). We demonstrated that ≥3 comorbidities, a preoperation American Society of Anesthesiologists score ≥4, preoperative sepsis or septic shock, colorectal cancer or ischemic proctocolitis, reoperation, and Hinchey classification grade IV are predictors for the surgical mortality in the adult cases of colorectal perforation. These predictors should be taken into consideration to prevent surgical mortality and to reduce potentially unnecessary medical expenses.

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.

Prevalence and Determinants of Preterm Birth in Tehran, Iran: A Comparison between Logistic Regression and Decision Tree Methods.

PubMed

Amini, Payam; Maroufizadeh, Saman; Samani, Reza Omani; Hamidi, Omid; Sepidarkish, Mahdi

2017-06-01

Preterm birth (PTB) is a leading cause of neonatal death and the second biggest cause of death in children under five years of age. The objective of this study was to determine the prevalence of PTB and its associated factors using logistic regression and decision tree classification methods. This cross-sectional study was conducted on 4,415 pregnant women in Tehran, Iran, from July 6-21, 2015. Data were collected by a researcher-developed questionnaire through interviews with mothers and review of their medical records. To evaluate the accuracy of the logistic regression and decision tree methods, several indices such as sensitivity, specificity, and the area under the curve were used. The PTB rate was 5.5% in this study. The logistic regression outperformed the decision tree for the classification of PTB based on risk factors. Logistic regression showed that multiple pregnancies, mothers with preeclampsia, and those who conceived with assisted reproductive technology had an increased risk for PTB ( p < 0.05). Identifying and training mothers at risk as well as improving prenatal care may reduce the PTB rate. We also recommend that statisticians utilize the logistic regression model for the classification of risk groups for PTB.

Determinants of child maltreatment in Nepal: Results from the 2014 Nepal multiple indicator cluster survey (the 2014 NMICS).

PubMed

Atteraya, Madhu Sudhan; Ebrahim, Nasser B; Gnawali, Shreejana

2018-02-01

We examined the prevalence of child maltreatment as measured by the level of physical (moderate to severe) and emotional abuse and child labor, and the associated household level determinants of child maltreatment in Nepal. We used a nationally representative data set from the fifth round of the Nepal Multiple Indicator Cluster Survey (the 2014 NMICS). The main independent variables were household level characteristics. Dependent variables included child experience of moderate to severe physical abuse, emotional abuse, and child labor (domestic work and economic activities). Bivariate analyses and logistic regressions were used to examine the associations between independent and dependent variables. The results showed that nearly half of the children (49.8%) had experienced moderate physical abuse, 21.5% experienced severe physical abuse, and 77.3% experienced emotional abuse. About 27% of the children had engaged in domestic work and 46.7% in various economic activities. At bivariate level, educational level of household's head and household wealth status had shown significant statistical association with child maltreatment (p<0.001). Results from multivariate logistic regressions showed that higher education levels and higher household wealth status protected children from moderate to severe physical abuse, emotional abuse and child labor. In general, child maltreatment is a neglected social issue in Nepal and the high rates of child maltreatment calls for mass awareness programs focusing on parents, and involving all stakeholders including governments, local, and international organizations. Copyright © 2017 Elsevier Ltd. All rights reserved.

Consumption of sugar products and associated life- and school-satisfaction and self-esteem factors among schoolchildren in Kuwait.

PubMed

Honkala, Sisko; Honkala, Eino; Al-Sahli, Nameer

2006-04-01

The objective of this study was to assess how frequently schoolchildren report consuming sweets, soft drinks, and cakes, and whether life- and school-satisfaction and self-esteem factors are associated with the consumption of these sugar products. A total of 2,312 schoolchildren between the ages of 11 and 13 years from the government schools in Kuwait completed an anonymous structured questionnaire during 2002 and 2003. A representative sample of children from all six governorates of the country was drawn into the study. The questionnaire of the Health Behaviour in School-Aged Children (HBSC) survey was translated from English to Arabic and was used after modification to suit Kuwaitis. The chi-square test and logistic regression model were used in the analysis. A large proportion of children reported consuming sweets (42%), soft drinks (43%), and cakes (31%) several times a day. Almost every fourth child reported consuming all these sugar products more than once a day. All life-satisfaction and self-esteem variables and almost all school-satisfaction variables seemed to associate with more-than-once-a-day consumption of sugar products. When all the associated variables were analyzed together using the logistic regression model, the life- and school-satisfaction and self-esteem factors seemed to have a stronger association with frequent sugar consumption than did gender, grade, or nationality. Consumption of sugar products was common among schoolchildren in Kuwait, and both positive and negative life-satisfaction and self-esteem factors were associated.

Osteoporosis prediction from the mandible using cone-beam computed tomography

PubMed Central

Al Haffar, Iyad; Khattab, Razan

2014-01-01

Purpose This study aimed to evaluate the use of dental cone-beam computed tomography (CBCT) in the diagnosis of osteoporosis among menopausal and postmenopausal women by using only a CBCT viewer program. Materials and Methods Thirty-eight menopausal and postmenopausal women who underwent dual-energy X-ray absorptiometry (DXA) examination for hip and lumbar vertebrae were scanned using CBCT (field of view: 13 cm×15 cm; voxel size: 0.25 mm). Slices from the body of the mandible as well as the ramus were selected and some CBCT-derived variables, such as radiographic density (RD) as gray values, were calculated as gray values. Pearson's correlation, one-way analysis of variance (ANOVA), and accuracy (sensitivity and specificity) evaluation based on linear and logistic regression were performed to choose the variable that best correlated with the lumbar and femoral neck T-scores. Results RD of the whole bone area of the mandible was the variable that best correlated with and predicted both the femoral neck and the lumbar vertebrae T-scores; further, Pearson's correlation coefficients were 0.5/0.6 (p value=0.037/0.009). The sensitivity, specificity, and accuracy based on the logistic regression were 50%, 88.9%, and 78.4%, respectively, for the femoral neck, and 46.2%, 91.3%, and 75%, respectively, for the lumbar vertebrae. Conclusion Lumbar vertebrae and femoral neck osteoporosis can be predicted with high accuracy from the RD value of the body of the mandible by using a CBCT viewer program. PMID:25473633

Gender differences in depressive symptom profiles and patterns of psychotropic drug usage in Asian patients with depression: Findings from the Research on Asian Psychotropic Prescription Patterns for Antidepressants study.

PubMed

Park, Seon-Cheol; Lee, Min-Soo; Shinfuku, Naotaka; Sartorius, Norman; Park, Yong Chon

2015-09-01

The purpose of this study was to investigate whether there were gender-specific depressive symptom profiles or gender-specific patterns of psychotropic agent usage in Asian patients with depression. Clinical data from the Research on Asian Psychotropic Prescription Patterns for Antidepressant study (1171 depressed patients) were used to determine gender differences by analysis of covariates for continuous variables and by logistic regression analysis for discrete variables. In addition, a binary logistic regression model was fitted to identify independent clinical correlates of the gender-specific pattern on psychotropic drug usage. Men were more likely than women to have loss of interest (adjusted odds ratio = 1.379, p = 0.009), fatigue (adjusted odds ratio = 1.298, p = 0.033) and concurrent substance abuse (adjusted odds ratio = 3.793, p = 0.008), but gender differences in other symptom profiles and clinical features were not significant. Men were also more likely than women to be prescribed adjunctive therapy with a second-generation antipsychotic (adjusted odds ratio = 1.320, p = 0.044). However, men were less likely than women to have suicidal thoughts/acts (adjusted odds ratio = 0.724, p = 0.028). Binary logistic regression models revealed that lower age (odds ratio = 0.986, p = 0.027) and current hospitalization (odds ratio = 3.348, p < 0.0001) were independent clinical correlates of use of second-generation antipsychotics as adjunctive therapy for treating depressed Asian men. Unique gender-specific symptom profiles and gender-specific patterns of psychotropic drug usage can be identified in Asian patients with depression. Hence, ethnic and cultural influences on the gender preponderance of depression should be considered in the clinical psychiatry of Asian patients. © The Royal Australian and New Zealand College of Psychiatrists 2015.

Development of a real-time crash risk prediction model incorporating the various crash mechanisms across different traffic states.

PubMed

Xu, Chengcheng; Wang, Wei; Liu, Pan; Zhang, Fangwei

2015-01-01

This study aimed to identify the traffic flow variables contributing to crash risks under different traffic states and to develop a real-time crash risk model incorporating the varying crash mechanisms across different traffic states. The crash, traffic, and geometric data were collected on the I-880N freeway in California in 2008 and 2009. This study considered 4 different traffic states in Wu's 4-phase traffic theory. They are free fluid traffic, bunched fluid traffic, bunched congested traffic, and standing congested traffic. Several different statistical methods were used to accomplish the research objective. The preliminary analysis showed that traffic states significantly affected crash likelihood, collision type, and injury severity. Nonlinear canonical correlation analysis (NLCCA) was conducted to identify the underlying phenomena that made certain traffic states more hazardous than others. The results suggested that different traffic states were associated with various collision types and injury severities. The matching of traffic flow characteristics and crash characteristics in NLCCA revealed how traffic states affected traffic safety. The logistic regression analyses showed that the factors contributing to crash risks were quite different across various traffic states. To incorporate the varying crash mechanisms across different traffic states, random parameters logistic regression was used to develop a real-time crash risk model. Bayesian inference based on Markov chain Monte Carlo simulations was used for model estimation. The parameters of traffic flow variables in the model were allowed to vary across different traffic states. Compared with the standard logistic regression model, the proposed model significantly improved the goodness-of-fit and predictive performance. These results can promote a better understanding of the relationship between traffic flow characteristics and crash risks, which is valuable knowledge in the pursuit of improving traffic safety on freeways through the use of dynamic safety management systems.

Effectiveness of the CANRISK tool in the identification of dysglycemia in First Nations and Métis in Canada

PubMed Central

Gina, Agarwal; Ying, Jiang; Susan, Rogers Van Katwyk; Chantal, Lemieux; Heather, Orpana; Yang, Mao; Brandan, Hanley; Karen, Davis; Laurel, Leuschen; Howard, Morrison

2018-01-01

Abstract Introduction: First Nations/Métis populations develop diabetes earlier and at higher rates than other Canadians. The Canadian diabetes risk questionnaire (CANRISK) was developed as a diabetes screening tool for Canadians aged 40 years or over. The primary aim of this paper is to assess the effectiveness of the existing CANRISK tool and risk scores in detecting dysglycemia in First Nations/Métis participants, including among those under the age of 40. A secondary aim was to determine whether alternative waist circumference (WC) and body mass index (BMI) cut-off points improved the predictive ability of logistic regression models using CANRISK variables to predict dysglycemia. Methods: Information from a self-administered CANRISK questionnaire, anthropometric measurements, and results of a standard oral glucose tolerance test (OGTT) were collected from First Nations and Métis participants (n = 1479). Sensitivity and specificity of CANRISK scores using published risk score cut-off points were calculated. Logistic regression was conducted with alternative ethnicity-specific BMI and WC cut-off points to predict dysglycemia using CANRISK variables. Results: Compared with OGTT results, using a CANRISK score cut-off point of 33, the sensitivity and specificity of CANRISK was 68% and 63% among individuals aged 40 or over; it was 27% and 87%, respectively among those under 40. Using a lower cut-off point of 21, the sensitivity for individuals under 40 improved to 77% with a specificity of 44%. Though specificity at this threshold was low, the higher level of sensitivity reflects the importance of the identification of high risk individuals in this population. Despite altered cut-off points of BMI and WC, logistic regression models demonstrated similar predictive ability. Conclusion: CANRISK functioned well as a preliminary step for diabetes screening in a broad age range of First Nations and Métis in Canada, with an adjusted CANRISK cutoff point for individuals under 40, and with no incremental improvement from using alternative BMI/WC cut-off points. PMID:29443485

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.

Could Poor Parental Recall of HPV Vaccination Contribute to Low Vaccination Rates?

PubMed

Apte, Gauri; Pierre-Joseph, Natalie; Vercruysse, Jessica L; Perkins, Rebecca B

2015-09-01

Rates of initiation and completion of the human papillomavirus (HPV) vaccine series remain below national goals. Because parents are responsible for ensuring vaccination of their children, we examined the accuracy of parental recall of the number of shots their daughters received. Parents/guardians of girls aged 11 to 17 years were asked to recall the number of HPV doses received by their daughters. Dose number was confirmed using provider-verified medical records. Logistic regression assessed variables associated with correct recall. A total of 79 (63%) parents/guardians correctly identified the number of shots their daughters received. Ninety-one (73%) were aware of whether their daughter started the series at all. The only factor significantly associated with accurate recall in logistic regression models was female gender of parent/guardian. Nearly 40% of parents/guardians inaccurately recalled the number of HPV shots their children received, which may contribute to low rates of vaccine initiation and completion. © The Author(s) 2015.

Risk Factors for Brachial Plexus Birth Injury

PubMed Central

Louden, Emily; Marcotte, Michael; Mehlman, Charles; Lippert, William; Huang, Bin; Paulson, Andrea

2018-01-01

Over the course of decades, the incidence of brachial plexus birth injury (BPBI) has increased despite advances in healthcare which would seem to assist in decreasing the rate. The aim of this study is to identify previously unknown risk factors for BPBI and the risk factors with potential to guide preventative measures. A case control study of 52 mothers who had delivered a child with a BPBI injury and 132 mothers who had delivered without BPBI injury was conducted. Univariate, multivariable and logistic regressions identified risk factors and their combinations. The odds of BPBI were 2.5 times higher when oxytocin was used and 3.7 times higher when tachysystole occurred. The odds of BPBI injury are increased when tachysystole and oxytocin occur during the mother’s labor. Logistic regression identified a higher risk for BPBI when more than three of the following variables (>30 lbs gained during the pregnancy, stage 2 labor >61.5 min, mother’s age >26.4 years, tachysystole, or fetal malpresentation) were present in any combination. PMID:29596309

Gluten-free is not enough--perception and suggestions of celiac consumers.

PubMed

do Nascimento, Amanda Bagolin; Fiates, Giovanna Medeiros Rataichesck; dos Anjos, Adilson; Teixeira, Evanilda

2014-06-01

The present study investigated the perceptions of individuals with celiac disease about gluten-free (GF) products, their consumer behavior and which product is the most desired. A survey was used to collect information. Descriptive analysis, χ² tests and Multiple Logistic Regressions were conducted. Ninety-one questionnaires were analyzed. Limited variety and availability, the high price of products and the social restrictions imposed by the diet were the factors that caused the most dissatisfaction and difficulty. A total of 71% of the participants confirmed having moderate to high difficulty finding GF products. The logistic regression identified a significant relationship between dissatisfaction, texture and variety (p < 0.05) and between variety and difficulty of finding GF products (p < 0.05). The sensory characteristics were the most important variables considered for actual purchases. Bread was the most desired product. The participants were dissatisfaction with GF products. The desire for bread with better sensory characteristics reinforces the challenge to develop higher quality baking products.

HIV testing among MSM in Bogotá, Colombia: The role of structural and individual characteristics

PubMed Central

Reisen, Carol A.; Zea, Maria Cecilia; Bianchi, Fernanda T.; Poppen, Paul J.; del Río González, Ana Maria; Romero, Rodrigo A. Aguayo; Pérez, Carolin

2014-01-01

This study used mixed methods to examine characteristics related to HIV testing among men who have sex with men (MSM) in Bogotá, Colombia. A sample of 890 MSM responded to a computerized quantitative survey. Follow-up qualitative data included 20 in-depth interviews with MSM and 12 key informant interviews. Hierarchical logistic set regression indicated that sequential sets of variables reflecting demographic characteristics, insurance coverage, risk appraisal, and social context each added to the explanation of HIV testing. Follow-up logistic regression showed that individuals who were older, had higher income, paid for their own insurance, had had a sexually transmitted infection, knew more people living with HIV, and had greater social support were more likely to have been tested for HIV at least once. Qualitative findings provided details of personal and structural barriers to testing, as well as interrelationships among these factors. Recommendations to increase HIV testing among Colombian MSM are offered. PMID:25068180

Avoiding overstating the strength of forensic evidence: Shrunk likelihood ratios/Bayes factors.

PubMed

Morrison, Geoffrey Stewart; Poh, Norman

2018-05-01

When strength of forensic evidence is quantified using sample data and statistical models, a concern may be raised as to whether the output of a model overestimates the strength of evidence. This is particularly the case when the amount of sample data is small, and hence sampling variability is high. This concern is related to concern about precision. This paper describes, explores, and tests three procedures which shrink the value of the likelihood ratio or Bayes factor toward the neutral value of one. The procedures are: (1) a Bayesian procedure with uninformative priors, (2) use of empirical lower and upper bounds (ELUB), and (3) a novel form of regularized logistic regression. As a benchmark, they are compared with linear discriminant analysis, and in some instances with non-regularized logistic regression. The behaviours of the procedures are explored using Monte Carlo simulated data, and tested on real data from comparisons of voice recordings, face images, and glass fragments. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

Cultural beliefs and clinical breast examination in Hmong American women: the crucial role of modesty.

PubMed

Lee, Hee Yun; Vang, Suzanne

2015-06-01

Despite grave cancer disparities in Hmong American women, investigation of the group's breast cancer screening behavior is sparse. This study examined how cultural factors are associated with breast cancer screening utilization, specifically clinical breast exam (CBE), in this population. One hundred and sixty-four Hmong American women between ages 18 and 67 were recruited from a large Midwestern metropolitan area with a median age of 28.0 years. Logistic regression was used to assess the association of cultural variables with receipt of CBE. Roughly 73% of Hmong American women reported ever having had a CBE. Logistic regression revealed that endorsing more modest views was the greatest barrier to ever having had a CBE. Age and language preference were also found to be significant predictors of past CBE use. Cultural factors should be considered in developing interventions aimed at promoting breast cancer screening in this population. In particular, Hmong American women who have less English proficiency and are relatively younger should be targeted in breast cancer screening efforts.

The Association between Unintended Pregnancy and Violence among Incarcerated Men and Women

PubMed Central

Kelly, Patricia J.; Ramaswamy, Megha

2018-01-01

Background In this article, we examine the association between unintended pregnancy and individual and community level indicators of violence in a population of both women and men in the criminal justice system. Methods We conducted a cross-sectional survey with 290 women and 306 men in 3 correctional facilities in Kansas City and used logistic regression models to assess relationships between key independent variables and unintended pregnancy. Findings In gender-specific logistic regression models, women with a history of intimate partner violence were 2.02 times more likely (CI 1.15, 3.56), and those with a history of sexual abuse before age 16 were 1.23 times more likely (CI 1.02–1.49) to have experienced unintended pregnancy. Men or their family members who were victimized by neighborhood violence were 1.82 times more likely to have experienced unintended pregnancy (CI 1.01, 3.28). Discussion These findings suggest the need for gender and community-specific interventions that address the relationship between violence and unintended pregnancy. PMID:23136860

Can additive measures add to an intersectional understanding? Experiences of gay and ethnic discrimination among HIV-positive Latino gay men.

PubMed

Reisen, Carol A; Brooks, Kelly D; Zea, Maria Cecilia; Poppen, Paul J; Bianchi, Fernanda T

2013-04-01

The current study investigated a methodological question of whether traditional, additive, quantitative data can be used to address intersectional issues, and illustrated such an approach with a sample of 301 HIV-positive, Latino gay men in the United States. Participants were surveyed using A-CASI. Hierarchical logistic set regression investigated the role of sets of variables reflecting demographic characteristics, gender nonconformity, and gay and ethnic discrimination in relation to depression and gay collective identity. Results showed the discrimination set was related to depression and to gay collective identity, as was gender nonconformity. Follow-up logistic regression showed that both types of discrimination were associated with greater depression, but gender nonconformity was not. Gay discrimination and gender nonconformity were positively associated with gay collective identity, whereas ethnic discrimination was negatively associated. Results are discussed in terms of the use of traditional quantitative data as a potential means of understanding intersectional issues, as well as of contributing to knowledge about individuals facing multiple structural inequalities.

Cross-sectional study of variables associated with length of stay and ICU need in open Roux-En-Y gastric bypass surgery for morbid obese patients: an exploratory analysis based on the Public Health System administrative database (Datasus) in Brazil.

PubMed

Asano, Elio Fernando; Rasera, Irineu; Shiraga, Elisabete Cristina

2012-12-01

This is an exploratory analysis of potential variables associated with open Roux-en-Y gastric bypass (RYGB) surgery hospitalization resource use pattern. Cross-sectional study based on an administrative database (DATASUS) records. Inclusion criteria were adult patients undergoing RYGB between Jan/2008 and Jun/2011. Dependent variables were length of stay (LoS) and ICU need. Independent variables were: gender, age, region, hospital volume, surgery at certified center of excellence (CoE) by the Surgical Review Corporation (SRC), teaching hospital, and year of hospitalization. Univariate and multivariate analysis (logistic regression for ICU need and linear regression for length of stay) were performed. Data from 13,069 surgeries were analyzed. In crude analysis, hospital volume was the most impactful variable associated with log-transformed LoS (1.312 ± 0.302 high volume vs. 1.670 ± 0.581 low volume, p < 0.001), whereas for ICU need it was certified CoE (odds ratio (OR), 0.016; 95% confidence interval (CI), 0.010-0.026). After adjustment by logistic regression, certified CoE remained as the strongest predictor of ICU need (OR, 0.011; 95% CI, 0.007-0.018), followed by hospital volume (OR, 3.096; 95% CI, 2.861-3.350). Age group, male gender, and teaching hospital were also significantly associated (p < 0.001). For log-transformed LoS, final model includes hospital volume (coefficient, -0.223; 95% CI, -0.250 to -0.196) and teaching hospital (coefficient, 0.375; 95% CI, 0.351-0.398). Region of Brazil was not associated with any of the outcomes. High-volume hospital was the strongest predictor for shorter LoS, whereas SRC certification was the strongest predictor of lower ICU need. Public health policies targeting an increase of efficiency and patient access to the procedure should take into account these results.

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).

Data-Science Analysis of the Macro-scale Features Governing the Corrosion to Crack Transition in AA7050-T7451

NASA Astrophysics Data System (ADS)

Co, Noelle Easter C.; Brown, Donald E.; Burns, James T.

2018-05-01

This study applies data science approaches (random forest and logistic regression) to determine the extent to which macro-scale corrosion damage features govern the crack formation behavior in AA7050-T7451. Each corrosion morphology has a set of corresponding predictor variables (pit depth, volume, area, diameter, pit density, total fissure length, surface roughness metrics, etc.) describing the shape of the corrosion damage. The values of the predictor variables are obtained from white light interferometry, x-ray tomography, and scanning electron microscope imaging of the corrosion damage. A permutation test is employed to assess the significance of the logistic and random forest model predictions. Results indicate minimal relationship between the macro-scale corrosion feature predictor variables and fatigue crack initiation. These findings suggest that the macro-scale corrosion features and their interactions do not solely govern the crack formation behavior. While these results do not imply that the macro-features have no impact, they do suggest that additional parameters must be considered to rigorously inform the crack formation location.

Exploring unobserved heterogeneity in bicyclists' red-light running behaviors at different crossing facilities.

PubMed

Guo, Yanyong; Li, Zhibin; Wu, Yao; Xu, Chengcheng

2018-06-01

Bicyclists running the red light at crossing facilities increase the potential of colliding with motor vehicles. Exploring the contributing factors could improve the prediction of running red-light probability and develop countermeasures to reduce such behaviors. However, individuals could have unobserved heterogeneities in running a red light, which make the accurate prediction more challenging. Traditional models assume that factor parameters are fixed and cannot capture the varying impacts on red-light running behaviors. In this study, we employed the full Bayesian random parameters logistic regression approach to account for the unobserved heterogeneous effects. Two types of crossing facilities were considered which were the signalized intersection crosswalks and the road segment crosswalks. Electric and conventional bikes were distinguished in the modeling. Data were collected from 16 crosswalks in urban area of Nanjing, China. Factors such as individual characteristics, road geometric design, environmental features, and traffic variables were examined. Model comparison indicates that the full Bayesian random parameters logistic regression approach is statistically superior to the standard logistic regression model. More red-light runners are predicted at signalized intersection crosswalks than at road segment crosswalks. Factors affecting red-light running behaviors are gender, age, bike type, road width, presence of raised median, separation width, signal type, green ratio, bike and vehicle volume, and average vehicle speed. Factors associated with the unobserved heterogeneity are gender, bike type, signal type, separation width, and bike volume. Copyright © 2018 Elsevier Ltd. All rights reserved.

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.

[Use of data display screens and ocular hypertension in local public sector workers].

PubMed

Abellán Torró, Rosana; Merelles Tormo, Antoni

2014-01-01

The main objective of this study is to examine the association between work with data display screens (DDS) and ocular hypertension (OHT). A cross-sectional study among local public sector workers (Diputación Provincial de Valencia). Data from 620 people were collected over 25 months, from periodic medical examinations performed at an occupational health unit. Intraocular pressure (IOP) was obtained with a portable puff tonometer validated for screening, establishing the cut-off point for OHT at 22 mmHg. Both biological characteristics and other work-related variables were taken into account as covariates. Descriptive statistics of the data were obtained, together with nonparametric tests with a level of significance of 95% and logistic regression with p 〈0.1 as the level of significance of the likelihood test. The average age of the study population is 52.8 years. The prevalence of OHT was 3.5% (5.1% among men and 1.2% among women; p=0.012). No significant associations were found between hours of DDS-related work and OHT were found (p=0.395). Logistic regression corroborated the association between gender and OHT, with women less affected (OR = 0.234; 95%CI: 0.068 - 0.799; p=0.020). In our study, no associations were found between time of exposure to data display screens and ocular hypertension. Logistic regression points to a certain association between ocular hypertension and gender, with men being more predisposed. Copyright belongs to the Societat Catalana de Salut Laboral.

Modelling Status Food Security Households Disease Sufferers Pulmonary Tuberculosis Uses the Method Regression Logistics Binary

NASA Astrophysics Data System (ADS)

Wulandari, S. P.; Salamah, M.; Rositawati, A. F. D.

2018-04-01

Food security is the condition where the food fulfilment is managed well for the country till the individual. Indonesia is one of the country which has the commitment to create the food security becomes main priority. However, the food necessity becomes common thing means that it doesn’t care about nutrient standard and the health condition of family member, so in the fulfilment of food necessity also has to consider the disease suffered by the family member, one of them is pulmonary tuberculosa. From that reasons, this research is conducted to know the factors which influence on household food security status which suffered from pulmonary tuberculosis in the coastal area of Surabaya by using binary logistic regression method. The analysis result by using binary logistic regression shows that the variables wife latest education, house density and spacious house ventilation significantly affect on household food security status which suffered from pulmonary tuberculosis in the coastal area of Surabaya, where the wife education level is University/equivalent, the house density is eligible or 8 m2/person and spacious house ventilation 10% of the floor area has the opportunity to become food secure households amounted to 0.911089. While the chance of becoming food insecure households amounted to 0.088911. The model household food security status which suffered from pulmonary tuberculosis in the coastal area of Surabaya has been conformable, and the overall percentages of those classifications are at 71.8%.

Logistic regression analysis of psychosocial correlates associated with recovery from schizophrenia in a Chinese community.

PubMed

Tse, Samson; Davidson, Larry; Chung, Ka-Fai; Yu, Chong Ho; Ng, King Lam; Tsoi, Emily

2015-02-01

More mental health services are adopting the recovery paradigm. This study adds to prior research by (a) using measures of stages of recovery and elements of recovery that were designed and validated in a non-Western, Chinese culture and (b) testing which demographic factors predict advanced recovery and whether placing importance on certain elements predicts advanced recovery. We examined recovery and factors associated with recovery among 75 Hong Kong adults who were diagnosed with schizophrenia and assessed to be in clinical remission. Data were collected on socio-demographic factors, recovery stages and elements associated with recovery. Logistic regression analysis was used to identify variables that could best predict stages of recovery. Receiver operating characteristic curves were used to detect the classification accuracy of the model (i.e. rates of correct classification of stages of recovery). Logistic regression results indicated that stages of recovery could be distinguished with reasonable accuracy for Stage 3 ('living with disability', classification accuracy = 75.45%) and Stage 4 ('living beyond disability', classification accuracy = 75.50%). However, there was no sufficient information to predict Combined Stages 1 and 2 ('overwhelmed by disability' and 'struggling with disability'). It was found that having a meaningful role and age were the most important differentiators of recovery stage. Preliminary findings suggest that adopting salient life roles personally is important to recovery and that this component should be incorporated into mental health services. © The Author(s) 2014.

Predicting the potential distribution of invasive exotic species using GIS and information-theoretic approaches: A case of ragweed (Ambrosia artemisiifolia L.) distribution in China

USGS Publications Warehouse

Hao, Chen; LiJun, Chen; Albright, Thomas P.

2007-01-01

Invasive exotic species pose a growing threat to the economy, public health, and ecological integrity of nations worldwide. Explaining and predicting the spatial distribution of invasive exotic species is of great importance to prevention and early warning efforts. We are investigating the potential distribution of invasive exotic species, the environmental factors that influence these distributions, and the ability to predict them using statistical and information-theoretic approaches. For some species, detailed presence/absence occurrence data are available, allowing the use of a variety of standard statistical techniques. However, for most species, absence data are not available. Presented with the challenge of developing a model based on presence-only information, we developed an improved logistic regression approach using Information Theory and Frequency Statistics to produce a relative suitability map. This paper generated a variety of distributions of ragweed (Ambrosia artemisiifolia L.) from logistic regression models applied to herbarium specimen location data and a suite of GIS layers including climatic, topographic, and land cover information. Our logistic regression model was based on Akaike's Information Criterion (AIC) from a suite of ecologically reasonable predictor variables. Based on the results we provided a new Frequency Statistical method to compartmentalize habitat-suitability in the native range. Finally, we used the model and the compartmentalized criterion developed in native ranges to "project" a potential distribution onto the exotic ranges to build habitat-suitability maps. ?? Science in China Press 2007.

Analysis of occlusal variables, dental attrition, and age for distinguishing healthy controls from female patients with intracapsular temporomandibular disorders.

PubMed

Seligman, D A; Pullinger, A G

2000-01-01

Confusion about the relationship of occlusion to temporomandibular disorders (TMD) persists. This study attempted to identify occlusal and attrition factors plus age that would characterize asymptomatic normal female subjects. A total of 124 female patients with intracapsular TMD were compared with 47 asymptomatic female controls for associations to 9 occlusal factors, 3 attrition severity measures, and age using classification tree, multiple stepwise logistic regression, and univariate analyses. Models were tested for accuracy (sensitivity and specificity) and total contribution to the variance. The classification tree model had 4 terminal nodes that used only anterior attrition and age. "Normals" were mainly characterized by low attrition levels, whereas patients had higher attrition and tended to be younger. The tree model was only moderately useful (sensitivity 63%, specificity 94%) in predicting normals. The logistic regression model incorporated unilateral posterior crossbite and mediotrusive attrition severity in addition to the 2 factors in the tree, but was slightly less accurate than the tree (sensitivity 51%, specificity 90%). When only occlusal factors were considered in the analysis, normals were additionally characterized by a lack of anterior open bite, smaller overjet, and smaller RCP-ICP slides. The log likelihood accounted for was similar for both the tree (pseudo R(2) = 29.38%; mean deviance = 0.95) and the multiple logistic regression (Cox Snell R(2) = 30.3%, mean deviance = 0.84) models. The occlusal and attrition factors studied were only moderately useful in differentiating normals from TMD patients.

Inferring microhabitat preferences of Lilium catesbaei (Liliaceae).

PubMed

Sommers, Kristen Penney; Elswick, Michael; Herrick, Gabriel I; Fox, Gordon A

2011-05-01

Microhabitat studies use varied statistical methods, some treating site occupancy as a dependent and others as an independent variable. Using the rare Lilium catesbaei as an example, we show why approaches to testing hypotheses of differences between occupied and unoccupied sites can lead to erroneous conclusions about habitat preferences. Predictive approaches like logistic regression can better lead to understanding of habitat requirements. Using 32 lily locations and 30 random locations >2 m from a lily (complete data: 31 lily and 28 random spots), we measured physical conditions--photosynthetically active radiation (PAR), canopy cover, litter depth, distance to and height of nearest shrub, and soil moisture--and number and identity of neighboring plants. Twelve lilies were used to estimate a photosynthetic assimilation curve. Analyses used logistic regression, discriminant function analysis (DFA), (multivariate) analysis of variance, and resampled Wilcoxon tests. Logistic regression and DFA found identical predictors of presence (PAR, canopy cover, distance to shrub, litter), but hypothesis tests pointed to a different set (PAR, litter, canopy cover, height of nearest shrub). Lilies are mainly in high-PAR spots, often close to light saturation. By contrast, PAR in random spots was often near the lily light compensation point. Lilies were near Serenoa repens less than at random; otherwise, neighbor identity had no significant effect. Predictive methods are more useful in this context than the hypothesis tests. Light availability plays a big role in lily presence, which may help to explain increases in flowering and emergence after fire and roller-chopping.

Measurements of the talus in the assessment of population affinity.

PubMed

Bidmos, Mubarak A; Dayal, Manisha R; Adegboye, Oyelola A

2018-06-01

As part of their routine work, forensic anthropologists are expected to report population affinity as part of the biological profile of an individual. The skull is the most widely used bone for the estimation of population affinity but it is not always present in a forensic case. Thus, other bones that preserve well have been shown to give a good indication of either the sex or population affinity of an individual. In this study, the potential of measurements of the talus was investigated for the purpose of estimating population affinity in South Africans. Nine measurements from two hundred and twenty tali of South African Africans (SAA) and South African Whites (SAW) from the Raymond A. Dart Collection of Human Skeletons were used. Direct and step-wise discriminant function and logistic regression analyses were carried out using SPSS and SAS. Talar length was the best single variable for discriminating between these two groups for males while in females the head height was the best single predictor. Average accuracies for correct population affinity classification using logistic regression analysis were higher than those obtained from discriminant function analysis. This study was the first of its type to employ discriminant function analyses and logistic regression analyses to estimate the population affinity of an individual from the talus. Thus these equations can now be used by South African anthropologists when estimating the population affinity of dismembered or damaged or incomplete skeletal remains of SAA and SAW. Copyright © 2018 Elsevier B.V. All rights reserved.

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.

Probability estimation with machine learning methods for dichotomous and multicategory outcome: theory.

PubMed

Kruppa, Jochen; Liu, Yufeng; Biau, Gérard; Kohler, Michael; König, Inke R; Malley, James D; Ziegler, Andreas

2014-07-01

Probability estimation for binary and multicategory outcome using logistic and multinomial logistic regression has a long-standing tradition in biostatistics. However, biases may occur if the model is misspecified. In contrast, outcome probabilities for individuals can be estimated consistently with machine learning approaches, including k-nearest neighbors (k-NN), bagged nearest neighbors (b-NN), random forests (RF), and support vector machines (SVM). Because machine learning methods are rarely used by applied biostatisticians, the primary goal of this paper is to explain the concept of probability estimation with these methods and to summarize recent theoretical findings. Probability estimation in k-NN, b-NN, and RF can be embedded into the class of nonparametric regression learning machines; therefore, we start with the construction of nonparametric regression estimates and review results on consistency and rates of convergence. In SVMs, outcome probabilities for individuals are estimated consistently by repeatedly solving classification problems. For SVMs we review classification problem and then dichotomous probability estimation. Next we extend the algorithms for estimating probabilities using k-NN, b-NN, and RF to multicategory outcomes and discuss approaches for the multicategory probability estimation problem using SVM. In simulation studies for dichotomous and multicategory dependent variables we demonstrate the general validity of the machine learning methods and compare it with logistic regression. However, each method fails in at least one simulation scenario. We conclude with a discussion of the failures and give recommendations for selecting and tuning the methods. Applications to real data and example code are provided in a companion article (doi:10.1002/bimj.201300077). © 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Evaluation of logistic regression models and effect of covariates for case-control study in RNA-Seq analysis.

PubMed

Choi, Seung Hoan; Labadorf, Adam T; Myers, Richard H; Lunetta, Kathryn L; Dupuis, Josée; DeStefano, Anita L

2017-02-06

Next generation sequencing provides a count of RNA molecules in the form of short reads, yielding discrete, often highly non-normally distributed gene expression measurements. Although Negative Binomial (NB) regression has been generally accepted in the analysis of RNA sequencing (RNA-Seq) data, its appropriateness has not been exhaustively evaluated. We explore logistic regression as an alternative method for RNA-Seq studies designed to compare cases and controls, where disease status is modeled as a function of RNA-Seq reads using simulated and Huntington disease data. We evaluate the effect of adjusting for covariates that have an unknown relationship with gene expression. Finally, we incorporate the data adaptive method in order to compare false positive rates. When the sample size is small or the expression levels of a gene are highly dispersed, the NB regression shows inflated Type-I error rates but the Classical logistic and Bayes logistic (BL) regressions are conservative. Firth's logistic (FL) regression performs well or is slightly conservative. Large sample size and low dispersion generally make Type-I error rates of all methods close to nominal alpha levels of 0.05 and 0.01. However, Type-I error rates are controlled after applying the data adaptive method. The NB, BL, and FL regressions gain increased power with large sample size, large log2 fold-change, and low dispersion. The FL regression has comparable power to NB regression. We conclude that implementing the data adaptive method appropriately controls Type-I error rates in RNA-Seq analysis. Firth's logistic regression provides a concise statistical inference process and reduces spurious associations from inaccurately estimated dispersion parameters in the negative binomial framework.

Applied Prevalence Ratio estimation with different Regression models: An example from a cross-national study on substance use research.

PubMed

Espelt, Albert; Marí-Dell'Olmo, Marc; Penelo, Eva; Bosque-Prous, Marina

2016-06-14

To examine the differences between Prevalence Ratio (PR) and Odds Ratio (OR) in a cross-sectional study and to provide tools to calculate PR using two statistical packages widely used in substance use research (STATA and R). We used cross-sectional data from 41,263 participants of 16 European countries participating in the Survey on Health, Ageing and Retirement in Europe (SHARE). The dependent variable, hazardous drinking, was calculated using the Alcohol Use Disorders Identification Test - Consumption (AUDIT-C). The main independent variable was gender. Other variables used were: age, educational level and country of residence. PR of hazardous drinking in men with relation to women was estimated using Mantel-Haenszel method, log-binomial regression models and poisson regression models with robust variance. These estimations were compared to the OR calculated using logistic regression models. Prevalence of hazardous drinkers varied among countries. Generally, men have higher prevalence of hazardous drinking than women [PR=1.43 (1.38-1.47)]. Estimated PR was identical independently of the method and the statistical package used. However, OR overestimated PR, depending on the prevalence of hazardous drinking in the country. In cross-sectional studies, where comparisons between countries with differences in the prevalence of the disease or condition are made, it is advisable to use PR instead of OR.

Health behaviours associated with indoor tanning based on the 2012/13 Manitoba Youth Health Survey

PubMed Central

Harland, E.; Griffith, J.; Lu, H.; Erickson, T.; Magsino, K.

2016-01-01

Abstract Introduction: Although indoor tanning causes cancer, it remains relatively common among adolescents. Little is known about indoor tanning prevalence and habits in Canada, and even less about associated behaviours. This study explores the prevalence of adolescent indoor tanning in Manitoba and its association with other demographic characteristics and health behaviours. Methods: We conducted secondary analyses of the 2012/13 Manitoba Youth Health Survey data collected from Grade 7 to 12 students (n = 64 174) and examined associations between indoor tanning (whether participants had ever used artificial tanning equipment) and 25 variables. Variables with statistically significant associations to indoor tanning were tested for collinearity and grouped based on strong associations. For each group of highly associated variables, the variable with the greatest effect upon indoor tanning was placed into the final logistic regression model. Separate analyses were conducted for males and females to better understand sex-based differences, and analyses were adjusted for age. Results: Overall, 4% of male and 9% of female students reported indoor tanning, and prevalence increased with age. Relationships between indoor tanning and other variables were similar for male and female students. Binary logistic regression models indicated that several variables significantly predicted indoor tanning, including having part-time work, being physically active, engaging in various risk behaviours such as driving after drinking for males and unplanned sex after alcohol/drugs for females, experiencing someone say something bad about one’s body shape/size/appearance, identifying as trans or with another gender, consuming creatine/other supplements and, for females only, never/rarely using sun protection. Conclusion: Indoor tanning among adolescents was associated with age, part-time work, physical activity and many consumption behaviours and lifestyle risk factors. Though legislation prohibiting adolescent indoor tanning is critical, health promotion to discourage indoor tanning may be most beneficial if it also addresses these associated factors. PMID:27556919

Health behaviours associated with indoor tanning based on the 2012/13 Manitoba Youth Health Survey.

PubMed

Harland, E; Griffith, J; Lu, H; Erickson, T; Magsino, K

2016-08-01

Although indoor tanning causes cancer, it remains relatively common among adolescents. Little is known about indoor tanning prevalence and habits in Canada, and even less about associated behaviours. This study explores the prevalence of adolescent indoor tanning in Manitoba and its association with other demographic characteristics and health behaviours. We conducted secondary analyses of the 2012/13 Manitoba Youth Health Survey data collected from Grade 7 to 12 students (n = 64 174) and examined associations between indoor tanning (whether participants had ever used artificial tanning equipment) and 25 variables. Variables with statistically significant associations to indoor tanning were tested for collinearity and grouped based on strong associations. For each group of highly associated variables, the variable with the greatest effect upon indoor tanning was placed into the final logistic regression model. Separate analyses were conducted for males and females to better understand sex-based differences, and analyses were adjusted for age. Overall, 4% of male and 9% of female students reported indoor tanning, and prevalence increased with age. Relationships between indoor tanning and other variables were similar for male and female students. Binary logistic regression models indicated that several variables significantly predicted indoor tanning, including having part-time work, being physically active, engaging in various risk behaviours such as driving after drinking for males and unplanned sex after alcohol/drugs for females, experiencing someone say something bad about one's body shape/size/appearance, identifying as trans or with another gender, consuming creatine/other supplements and, for females only, never/rarely using sun protection. Indoor tanning among adolescents was associated with age, part-time work, physical activity and many consumption behaviours and lifestyle risk factors. Though legislation prohibiting adolescent indoor tanning is critical, health promotion to discourage indoor tanning may be most beneficial if it also addresses these associated factors.

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.

Unintended pregnancy and sex education in Chile: a behavioural model.

PubMed

Herold, J M; Thompson, N J; Valenzuela, M S; Morris, L

1994-10-01

This study analysed factors associated with unintended pregnancy among adolescent and young adult women in Santiago, Chile. Three variations of a behavioural model were developed. Logistic regression showed that the effect of sex education on unintended pregnancy works through the use of contraception. Other significant effects were found for variables reflecting socioeconomic status and a woman's acceptance of her sexuality. The results also suggested that labelling affects measurement of 'unintended' pregnancy.

Are Students of Color More Likely to Graduate from College if They Attend More Selective Institutions? Evidence from a Cohort of Recipients and Nonrecipients of the Gates Millennium Scholarship Program

ERIC Educational Resources Information Center

Melguizo, Tatiana

2010-01-01

The study takes advantage of the nontraditional selection process of the Gates Millennium Scholars (GMS) program to test the association between selectivity of 4-year institution attended as well as other noncognitive variables on the college completion rates of a sample of students of color. The results of logistic regression and propensity score…

The impact of truant and alcohol-related behavior on educational aspirations: a study of US high school seniors.

PubMed

Barry, Adam E; Chaney, Beth; Chaney, J Don

2011-08-01

Truancy and alcohol use are quality indicators of academic achievement and success. However, there remains a paucity of substantive research articulating the impact these deviant behaviors have on an adolescent's educational aspirations. The purpose of this study is to assess whether recent alcohol use and truancy impact students' educational aspirations among a nationally representative sample of US high school seniors. This study conducted a secondary data analysis of the Monitoring the Future project data, 2006. Logistic regression was conducted to assess how alcohol use and truancy affected educational aspirations. Subsequent interaction effects were assessed in the final multivariable model. Demographic variables such as age, sex, race, and father and mother's educational level were included as covariates in the regression model. Results indicate that as students engage in increased alcohol use and/or truancy, educational aspirations decrease. Thus, students who indicated a desire to attend a 4-year college/university were less likely to engage in high-risk drinking behavior and/or truancy. Moreover, in testing the interaction between truancy and alcohol use, as it relates to educational aspirations, the logistic regression model found both of these independent variables to be statistically significant predictors of the likelihood students would attend a 4-year college/university. To ensure that adolescents further their education and maximize their potential life opportunities, school and public health officials should initiate efforts to reduce alcohol consumption and truancy among students. Furthermore, future research should examine the risk and protective factors that may influence one's educational aspirations. © 2011, American School Health Association.

Heterogeneous models for an early discrimination between sepsis and non-infective SIRS in medical ward patients: a pilot study.

PubMed

Mearelli, Filippo; Fiotti, Nicola; Altamura, Nicola; Zanetti, Michela; Fernandes, Giovanni; Burekovic, Ismet; Occhipinti, Alessandro; Orso, Daniele; Giansante, Carlo; Casarsa, Chiara; Biolo, Gianni

2014-10-01

The objective of the study was to determine the accuracy of phospholipase A2 group II (PLA2-II), interferon-gamma-inducible protein 10 (IP-10), angiopoietin-2 (Ang-2), and procalcitonin (PCT) plasma levels in early ruling in/out of sepsis among systemic inflammatory response syndrome (SIRS) patients. Biomarker levels were determined in 80 SIRS patients during the first 4 h of admission to the medical ward. The final diagnosis of sepsis or non-infective SIRS was issued according to good clinical practice. Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for sepsis diagnosis were assessed. The optimal biomarker combinations with clinical variables were investigated by logistic regression and decision tree (CART). PLA2-II, IP-10 and PCT, but not Ang-2, were significantly higher in septic (n = 60) than in non-infective SIRS (n = 20) patients (P ≤ 0.001, 0.027, and 0.002, respectively). PLA2-II PPV and NPV were 88 and 86%, respectively. The corresponding figures were 100 and 31% for IP-10, and 93 and 35% for PCT. Binary logistic regression model had 100% PPV and NPV, while manual and software-generated CART reached an overall accuracy of 95 and 98%, respectively, both with 100% NPV. PLA2-II and IP-10 associated with clinical variables in regression or decision tree heterogeneous models may be valuable biomarkers for sepsis diagnosis in SIRS patients admitted to medical ward (MW). Further studies are needed to introduce them into clinical practice.

Understanding the Personality and Behavioral Mechanisms Defining Hypersexuality in Men Who Have Sex with Men

PubMed Central

Miner, Michael H.; Romine, Rebecca Swinburne; Raymond, Nancy; Janssen, Erick; MacDonald, Angus; Coleman, Eli

2016-01-01

Objective The purpose of this study was to investigate personality factors and behavioral mechanisms that are relevant to hypersexuality in men who have sex with men. Method A sample of 242 men who have sex with men were recruited from various sites in a moderate size mid-western city. Participants were assigned to hypersexuality or control group using a SCID-type interview. Self-report inventories were administered that measured the broad band personality constructs of positive emotionality, negative emotionality and constraint, and more narrow constructs related to sexual behavioral control, behavioral activation, behavioral inhibition, sexual excitation, sexual inhibition, impulsivity, ADHD, and sexual behavior. Hierarchical logistic regression was used to determine the relationship between these personality and behavioral variables and group membership. Results A hierarchical logistic regression, controlling for age, revealed a significant positive relationship between hypersexuality and negative emotionality and a negative relationship with constraint. None of the behavioral mechanism variables entered this equation. However, a hierarchical multiple regression predicting sexual behavioral control indicated that lack of such control was positively related to sexual excitation and sexual inhibition due to the threat of performance failure and negatively related to sexual inhibition due to the threat of performance consequences and general behavioral inhibition Conclusions Hypersexuality was found to be related to two broad personality factors that are characterized by emotional reactivity, risk-taking, and impulsivity. The associated lack of sexual behavior control is influenced by both sexual excitatory and inhibitory mechanisms, but not general behavioral activation and inhibitory mechanisms. PMID:27486137

Evaluating atmospheric blocking in the global climate model EC-Earth

NASA Astrophysics Data System (ADS)

Hartung, Kerstin; Hense, Andreas; Kjellström, Erik

2013-04-01

Atmospheric blocking is a phenomenon of the midlatitudal troposphere, which plays an important role in climate variability. Therefore a correct representation of blocking in climate models is necessary, especially for evaluating the results of climate projections. In my master's thesis a validation of blocking in the coupled climate model EC-Earth is performed. Blocking events are detected based on the Tibaldi-Molteni Index. At first, a comparison with the reanalysis dataset ERA-Interim is conducted. The blocking frequency depending on longitude shows a small general underestimation of blocking in the model - a well known problem. Scaife et al. (2011) proposed the correction of model bias as a way to solve this problem. However, applying the correction to the higher resolution EC-Earth model does not yield any improvement. Composite maps show a link between blocking events and surface variables. One example is the formation of a positive surface temperature anomaly north and a negative anomaly south of the blocking anticyclone. In winter the surface temperature in EC-Earth can be reproduced quite well, but in summer a cold bias over the inner-European ocean is present. Using generalized linear models (GLMs) I want to study the connection between regional blocking and global atmospheric variables further. GLMs have the advantage of being applicable to non-Gaussian variables. Therefore the blocking index at each longitude, which is Bernoulli distributed, can be analysed statistically with GLMs. I applied a logistic regression between the blocking index and the geopotential height at 500 hPa to study the teleconnection of blocking events at midlatitudes with global geopotential height. GLMs also offer the possibility of quantifying the connections shown in composite maps. The implementation of the logistic regression can even be expanded to a search for trends in blocking frequency, for example in the scenario simulations.

Contrasting analytical and data-driven frameworks for radiogenomic modeling of normal tissue toxicities in prostate cancer.

PubMed

Coates, James; Jeyaseelan, Asha K; Ybarra, Norma; David, Marc; Faria, Sergio; Souhami, Luis; Cury, Fabio; Duclos, Marie; El Naqa, Issam

2015-04-01

We explore analytical and data-driven approaches to investigate the integration of genetic variations (single nucleotide polymorphisms [SNPs] and copy number variations [CNVs]) with dosimetric and clinical variables in modeling radiation-induced rectal bleeding (RB) and erectile dysfunction (ED) in prostate cancer patients. Sixty-two patients who underwent curative hypofractionated radiotherapy (66 Gy in 22 fractions) between 2002 and 2010 were retrospectively genotyped for CNV and SNP rs5489 in the xrcc1 DNA repair gene. Fifty-four patients had full dosimetric profiles. Two parallel modeling approaches were compared to assess the risk of severe RB (Grade⩾3) and ED (Grade⩾1); Maximum likelihood estimated generalized Lyman-Kutcher-Burman (LKB) and logistic regression. Statistical resampling based on cross-validation was used to evaluate model predictive power and generalizability to unseen data. Integration of biological variables xrcc1 CNV and SNP improved the fit of the RB and ED analytical and data-driven models. Cross-validation of the generalized LKB models yielded increases in classification performance of 27.4% for RB and 14.6% for ED when xrcc1 CNV and SNP were included, respectively. Biological variables added to logistic regression modeling improved classification performance over standard dosimetric models by 33.5% for RB and 21.2% for ED models. As a proof-of-concept, we demonstrated that the combination of genetic and dosimetric variables can provide significant improvement in NTCP prediction using analytical and data-driven approaches. The improvement in prediction performance was more pronounced in the data driven approaches. Moreover, we have shown that CNVs, in addition to SNPs, may be useful structural genetic variants in predicting radiation toxicities. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Application of Random Forests Methods to Diabetic Retinopathy Classification Analyses

PubMed Central

Casanova, Ramon; Saldana, Santiago; Chew, Emily Y.; Danis, Ronald P.; Greven, Craig M.; Ambrosius, Walter T.

2014-01-01

Background Diabetic retinopathy (DR) is one of the leading causes of blindness in the United States and world-wide. DR is a silent disease that may go unnoticed until it is too late for effective treatment. Therefore, early detection could improve the chances of therapeutic interventions that would alleviate its effects. Methodology Graded fundus photography and systemic data from 3443 ACCORD-Eye Study participants were used to estimate Random Forest (RF) and logistic regression classifiers. We studied the impact of sample size on classifier performance and the possibility of using RF generated class conditional probabilities as metrics describing DR risk. RF measures of variable importance are used to detect factors that affect classification performance. Principal Findings Both types of data were informative when discriminating participants with or without DR. RF based models produced much higher classification accuracy than those based on logistic regression. Combining both types of data did not increase accuracy but did increase statistical discrimination of healthy participants who subsequently did or did not have DR events during four years of follow-up. RF variable importance criteria revealed that microaneurysms counts in both eyes seemed to play the most important role in discrimination among the graded fundus variables, while the number of medicines and diabetes duration were the most relevant among the systemic variables. Conclusions and Significance We have introduced RF methods to DR classification analyses based on fundus photography data. In addition, we propose an approach to DR risk assessment based on metrics derived from graded fundus photography and systemic data. Our results suggest that RF methods could be a valuable tool to diagnose DR diagnosis and evaluate its progression. PMID:24940623