Bayesian generalized linear models for meta-analysis of diagnostic tests

With the recognition of the importance of evidence-based medicine, there is an emerging need for methods to systematically synthesize available data. Specifically, methods to provide accurate estimates of test characteristics for diagnostic tests are needed to help physicians make better clinical decisions. To provide more flexible approaches for meta-analysis of diagnostic tests, we developed three Bayesian generalized linear models. Two of these models, a bivariate normal and a binomial model, analyzed pairs of sensitivity and specificity values while incorporating the correlation between these two outcome variables. Noninformative independent uniform priors were used for the variance of sensitivity, specificity and correlation. We also applied an inverse Wishart prior to check the sensitivity of the results. The third model was a multinomial model where the test results were modeled as multinomial random variables. All three models can include specific imaging techniques as covariates in order to compare performance. Vague normal priors were assigned to the coefficients of the covariates. The computations were carried out using the 'Bayesian inference using Gibbs sampling' implementation of Markov chain Monte Carlo techniques. We investigated the properties of the three proposed models through extensive simulation studies. We also applied these models to a previously published meta-analysis dataset on cervical cancer as well as to an unpublished melanoma dataset. In general, our findings show that the point estimates of sensitivity and specificity were consistent among Bayesian and frequentist bivariate normal and binomial models. However, in the simulation studies, the estimates of the correlation coefficient from Bayesian bivariate models are not as good as those obtained from frequentist estimation regardless of which prior distribution was used for the covariance matrix. The Bayesian multinomial model consistently underestimated the sensitivity and specificity regardless of the sample size and correlation coefficient. In conclusion, the Bayesian bivariate binomial model provides the most flexible framework for future applications because of its following strengths: (1) it facilitates direct comparison between different tests; (2) it captures the variability in both sensitivity and specificity simultaneously as well as the intercorrelation between the two; and (3) it can be directly applied to sparse data without ad hoc correction. ^

Generalized fuzzy clustering for segmentation of multi-spectral magnetic resonance images.

An integrated approach for multi-spectral segmentation of MR images is presented. This method is based on the fuzzy c-means (FCM) and includes bias field correction and contextual constraints over spatial intensity distribution and accounts for the non-spherical cluster's shape in the feature space. The bias field is modeled as a linear combination of smooth polynomial basis functions for fast computation in the clustering iterations. Regularization terms for the neighborhood continuity of intensity are added into the FCM cost functions. To reduce the computational complexity, the contextual regularizations are separated from the clustering iterations. Since the feature space is not isotropic, distance measure adopted in Gustafson-Kessel (G-K) algorithm is used instead of the Euclidean distance, to account for the non-spherical shape of the clusters in the feature space. These algorithms are quantitatively evaluated on MR brain images using the similarity measures.

Generalized resistance resources of informal caregivers: A study of demands for care, competing demands, perception of burden and cognitive stress

This study examines the relationship among psychological resources (generalized resistance resources), care demands (demands for care, competing demands, perception of burden) and cognitive stress in a selected population of primary family caregivers. The study utilizes Antonovsky's Salutogenic Model of Health, specifically the concept of generalized resistance resources (GRRs), to analyze the relative effect of these resources on mediating cognitive stress, controlling for other care demands. The study is based on a sample of 784 eligible caregivers who (1) were relatives, (2) had the main responsibility for care, defined as a primary caregiver, and (3) provided a scaled stress score for the amount of overall care given to the care recipient (family member). The sample was drawn from the 1982 National Long-Term Care Survey (NLTCS) of individuals who assisted a given NLTCS sample person with ADL limitations.^ The study tests the following hypotheses: (a) There will be a negative relationship between generalized resistance resources (GRRs) and cognitive stress controlling for care demands (demands for care, competing demands, and perceptions of burden); (b) of the specific GRRs (material, cognitive, social, cultural-environmental) the social domain will represent the most significant factor predicting a decrease in cognitive stress; and (c) the social domain will be more significant for the female than the male primary family caregiver in decreasing cognitive stress.^ The study found that GRRs had a statistically significant mediating effect on cognitive stress, but the GRRs were a less significant predictor of stress than perception of burden and demands for care. Thus, although the analysis supported the underlying hypothesis, the specific hypothesis regarding GRRs' greater significance in buffering cognitive stress was not supported. Second, the results did not demonstrate the statistical significance or differences among the GRR domains. The hypothesis that the social GRR domain was most significant in mediating stress of family caregivers was not supported. Finally, the results confirmed that there are differences in the importance of social support help in mediating stress based on gender. It was found that gender and social support help were related to cognitive stress and gender had a statistically significant interaction effect with social support help. Implications for clinical practice, public health policy, and research are discussed. ^

A comparison of Markov and generalized linear models of hospital mortality

This paper reports a comparison of three modeling strategies for the analysis of hospital mortality in a sample of general medicine inpatients in a Department of Veterans Affairs medical center. Logistic regression, a Markov chain model, and longitudinal logistic regression were evaluated on predictive performance as measured by the c-index and on accuracy of expected numbers of deaths compared to observed. The logistic regression used patient information collected at admission; the Markov model was comprised of two absorbing states for discharge and death and three transient states reflecting increasing severity of illness as measured by laboratory data collected during the hospital stay; longitudinal regression employed Generalized Estimating Equations (GEE) to model covariance structure for the repeated binary outcome. Results showed that the logistic regression predicted hospital mortality as well as the alternative methods but was limited in scope of application. The Markov chain provides insights into how day to day changes of illness severity lead to discharge or death. The longitudinal logistic regression showed that increasing illness trajectory is associated with hospital mortality. The conclusion is reached that for standard applications in modeling hospital mortality, logistic regression is adequate, but for new challenges facing health services research today, alternative methods are equally predictive, practical, and can provide new insights. ^

A nonparametric method of comparing the partial areas under two correlated receiver operating characteristic curves

A non-parametric method was developed and tested to compare the partial areas under two correlated Receiver Operating Characteristic curves. Based on the theory of generalized U-statistics the mathematical formulas have been derived for computing ROC area, and the variance and covariance between the portions of two ROC curves. A practical SAS application also has been developed to facilitate the calculations. The accuracy of the non-parametric method was evaluated by comparing it to other methods. By applying our method to the data from a published ROC analysis of CT image, our results are very close to theirs. A hypothetical example was used to demonstrate the effects of two crossed ROC curves. The two ROC areas are the same. However each portion of the area between two ROC curves were found to be significantly different by the partial ROC curve analysis. For computation of ROC curves with large scales, such as a logistic regression model, we applied our method to the breast cancer study with Medicare claims data. It yielded the same ROC area computation as the SAS Logistic procedure. Our method also provides an alternative to the global summary of ROC area comparison by directly comparing the true-positive rates for two regression models and by determining the range of false-positive values where the models differ. ^

Variance of familial dietary intake

Although many family-based genetic studies have collected dietary data, very few have used the dietary information in published findings. No single solution has been presented or discussed in the literature to deal with the problem of using factor analyses for the analyses of dietary data from several related individuals from a given household. The standard statistical approach of factor analysis cannot be applied to the VIVA LA FAMILIA Study diet data to ascertain dietary patterns since this population consists of three children from each family, thus the dietary patterns of the related children may be correlated and non-independent. Addressing this problem in this project will enable us to describe the dietary patterns in Hispanic families and to explore the relationships between dietary patterns and childhood obesity. ^ In the VIVA LA FAMILIA Study, an overweight child was first identified and then his/her siblings and parents were brought in for data collection which included 24 hour recalls and food frequency questionnaire (FFQ). Dietary intake data were collected using FFQ and 24 hour recalls on 1030 Hispanic children from 319 families. ^ The design of the VIVA LA FAMILIA Study has important and unique statistical considerations since its participants are related to each other, the majority form distinct nuclear families. Thus, the standard approach of factor analysis cannot be applied to these diet data to ascertain dietary patterns. In this project we propose to investigate whether the determinants of the correlation matrix of each family unit will allow us to adjust the original correlation matrix of the dietary intake data prior to ascertaining dietary intake patterns. If these methods are appropriate, then in the future the dietary patterns among related individuals could be assessed by standard orthogonal principal component factor analysis.^

Effects of air pollution on asthma hospitalization rates in different age groups in metropolitan cities of Korea

Many studies have shown relationships between air pollution and the rate of hospital admissions for asthma. A few studies have controlled for age-specific effects by adding separate smoothing functions for each age group. However, it has not yet been reported whether air pollution effects are significantly different for different age groups. This lack of information is the motivation for this study, which tests the hypothesis that air pollution effects on asthmatic hospital admissions are significantly different by age groups. Each air pollutant's effect on asthmatic hospital admissions by age groups was estimated separately. In this study, daily time-series data for hospital admission rates from seven cities in Korea from June 1999 through 2003 were analyzed. The outcome variable, daily hospital admission rates for asthma, was related to five air pollutants which were used as the independent variables, namely particulate matter <10 micrometers (μm) in aerodynamic diameter (PM10), carbon monoxide (CO), ozone (O3), nitrogen dioxide (NO2), and sulfur dioxide (SO2). Meteorological variables were considered as confounders. Admission data were divided into three age groups: children (<15 years of age), adults (ages 15-64), and elderly (≥ 65 years of age). The adult age group was considered to be the reference group for each city. In order to estimate age-specific air pollution effects, the analysis was separated into two stages. In the first stage, Generalized Additive Models (GAMs) with cubic spline for smoothing were applied to estimate the age-city-specific air pollution effects on asthmatic hospital admission rates by city and age group. In the second stage, the Bayesian Hierarchical Model with non-informative prior which has large variance was used to combine city-specific effects by age groups. The hypothesis test showed that the effects of PM10, CO and NO2 were significantly different by age groups. Assuming that the air pollution effect for adults is zero as a reference, age-specific air pollution effects were: -0.00154 (95% confidence interval(CI)= (-0.0030,-0.0001)) for children and 0.00126 (95% CI = (0.0006, 0.0019)) for the elderly for PM 10; -0.0195 (95% CI = (-0.0386,-0.0004)) for children for CO; and 0.00494 (95% CI = (0.0028, 0.0071)) for the elderly for NO2. Relative rates (RRs) were 1.008 (95% CI = (1.000-1.017)) in adults and 1.021 (95% CI = (1.012-1.030)) in the elderly for every 10 μg/m3 increase of PM10 , 1.019 (95% CI = (1.005-1.033)) in adults and 1.022 (95% CI = (1.012-1.033)) in the elderly for every 0.1 part per million (ppm) increase of CO; 1.006 (95%CI = (1.002-1.009)) and 1.019 (95%CI = (1.007-1.032)) in the elderly for every 1 part per billion (ppb) increase of NO2 and SO2, respectively. Asthma hospital admissions were significantly increased for PM10 and CO in adults, and for PM10, CO, NO2 and SO2 in the elderly.^

An exploratory analysis of variance and volatility in epileptic electroencephalograms

The electroencephalogram (EEG) is a physiological time series that measures electrical activity at different locations in the brain, and plays an important role in epilepsy research. Exploring the variance and/or volatility may yield insights for seizure prediction, seizure detection and seizure propagation/dynamics.^ Maximal Overlap Discrete Wavelet Transforms (MODWTs) and ARMA-GARCH models were used to determine variance and volatility characteristics of 66 channels for different states of an epileptic EEG – sleep, awake, sleep-to-awake and seizure. The wavelet variances, changes in wavelet variances and volatility half-lives for the four states were compared for possible differences between seizure and non-seizure channels.^ The half-lives of two of the three seizure channels were found to be shorter than all of the non-seizure channels, based on 95% CIs for the pre-seizure and awake signals. No discernible patterns were found the wavelet variances of the change points for the different signals. ^

Detecting genetic and nutritional lung cancer risk factors related to folate metabolism using Bayesian generalized linear models

Complex diseases, such as cancer, are caused by various genetic and environmental factors, and their interactions. Joint analysis of these factors and their interactions would increase the power to detect risk factors but is statistically. Bayesian generalized linear models using student-t prior distributions on coefficients, is a novel method to simultaneously analyze genetic factors, environmental factors, and interactions. I performed simulation studies using three different disease models and demonstrated that the variable selection performance of Bayesian generalized linear models is comparable to that of Bayesian stochastic search variable selection, an improved method for variable selection when compared to standard methods. I further evaluated the variable selection performance of Bayesian generalized linear models using different numbers of candidate covariates and different sample sizes, and provided a guideline for required sample size to achieve a high power of variable selection using Bayesian generalize linear models, considering different scales of number of candidate covariates. ^ Polymorphisms in folate metabolism genes and nutritional factors have been previously associated with lung cancer risk. In this study, I simultaneously analyzed 115 tag SNPs in folate metabolism genes, 14 nutritional factors, and all possible genetic-nutritional interactions from 1239 lung cancer cases and 1692 controls using Bayesian generalized linear models stratified by never, former, and current smoking status. SNPs in MTRR were significantly associated with lung cancer risk across never, former, and current smokers. In never smokers, three SNPs in TYMS and three gene-nutrient interactions, including an interaction between SHMT1 and vitamin B12, an interaction between MTRR and total fat intake, and an interaction between MTR and alcohol use, were also identified as associated with lung cancer risk. These lung cancer risk factors are worthy of further investigation.^

Regression with autocorrelated data: A study of time trend of global infant mortality rate

The infant mortality rate (IMR) is considered to be one of the most important indices of a country's well-being. Countries around the world and other health organizations like the World Health Organization are dedicating their resources, knowledge and energy to reduce the infant mortality rates. The well-known Millennium Development Goal 4 (MDG 4), whose aim is to archive a two thirds reduction of the under-five mortality rate between 1990 and 2015, is an example of the commitment. ^ In this study our goal is to model the trends of IMR between the 1950s to 2010s for selected countries. We would like to know how the IMR is changing overtime and how it differs across countries. ^ IMR data collected over time forms a time series. The repeated observations of IMR time series are not statistically independent. So in modeling the trend of IMR, it is necessary to account for these correlations. We proposed to use the generalized least squares method in general linear models setting to deal with the variance-covariance structure in our model. In order to estimate the variance-covariance matrix, we referred to the time-series models, especially the autoregressive and moving average models. Furthermore, we will compared results from general linear model with correlation structure to that from ordinary least squares method without taking into account the correlation structure to check how significantly the estimates change.^

Predictors of benzodiazepine self -administration behavior in anxious patients

The purpose of this study was to examine factors that may be associated with benzodiazepine (BZ) self-administration and risks of dependence in anxious patients. Preliminary work included examination of psychosocial characteristics and subjective drug response as potential predictors of medication use. Fifty-five M, F patients with generalized anxiety or panic disorder participated in a 3-week outpatient Choice Procedure in which they self-medicated “as needed” with alprazolam (Alz) and placebo. Findings showed that a large amount of variance in alprazolam preference, frequency, and quantity of use could be predicted by measures of anxiety, drug liking, and certain personality characteristics. The primary study extended this work by examining whether individual differences in Alz sensitivity also predict patterns of use. Twenty anxious patients participated in the study, which required 11 weekly clinic visits. Ten of these also participated in a baseline assessment of HPA-axis function that involved 24-hour monitoring of cortisol and ACTH levels and a CRH Stimulation Test. This assessment was conducted on the basis of prior evidence that steroid metabolites exert neuromodulatory effects on the GABA A receptor and that HPA-axis function may be related to BZ sensitivity and long-term disability in anxious patients. Patients were classified as either HIGH or LOW users based on their p.r.n. patterns of Alz use during the first 3 weeks of the study. They then participated in a 4-week dose response trial in which they received prescribed doses of medication (placebo, 0.25, 0.5, and 1.0mg Alz), each taken TID for 1 week. The dose response trial was followed by a second 3-week Choice Procedure. Findings were not indicative of biological differences in Alz sensitivity between the HIGH and LOW users. However, the HIGH users had higher baseline anxiety and greater anxiolytic response to Alz than the LOW users. Anxiolytic benefits of p.r.n. and prescribed dosing were shown to be comparable, and patients' conservative patterns of p.r.n. medication use were not affected by the period of prescribed dosing. Although there was not strong evidence to suggest relationships between HPA-axis function and Alz use or sensitivity, interesting findings emerged about the relationship between HPA-axis function and anxiety. ^