Latent transition regression for mixed outcomes

Health status is a complex outcome, often characterized by multiple measures. When assessing changes in health status over time, multiple measures are typically collected longitudinally. Analytic challenges posed by these multivariate longitudinal data are further complicated when the outcomes are combinations of continuous, categorical, and count data. To address these challenges, we propose a fully Bayesian latent transition regression approach for jointly analyzing a mixture of longitudinal outcomes from any distribution. Health status is assumed to be a categorical latent variable, and the multiple outcomes are treated as surrogate measures of the latent health state, observed with error. Using this approach, both baseline latent health state prevalences and the probabilities of transitioning between the health states over time are modeled as functions of covariates. The observed outcomes are related to the latent health states through regression models that include subject-specific effects to account for residual correlation among repeated measures over time, and covariate effects to account for differential measurement of the latent health states. We illustrate our approach with data from a longitudinal study of back pain.     

Factor analytic models of clustered multivariate data with informative censoring

This article describes a general class of factor analytic models for the analysis of clustered multivariate data in the presence of informative missingness. We assume that there are distinct sets of cluster-level latent variables related to the primary outcomes and to the censoring process, and we account for dependency between these latent variables through a hierarchical model. A linear model is used to relate covariates and latent variables to the primary outcomes for each subunit. A generalized linear model accounts for covariate and latent variable effects on the probability of censoring for subunits within each cluster. The model accounts for correlation within clusters and within subunits through a flexible factor analytic framework that allows multiple latent variables and covariate effects on the latent variables. The structure of the model facilitates implementation of Markov chain Monte Carlo methods for posterior estimation. Data from a spermatotoxicity study are analyzed to illustrate the proposed approach.     

A Bayesian approach for joint modeling of cluster size and subunit-specific outcomes

In applications that involve clustered data, such as longitudinal studies and developmental toxicity experiments, the number of subunits within a cluster is often correlated with outcomes measured on the individual subunits. Analyses that ignore this dependency can produce biased inferences. This article proposes a Bayesian framework for jointly modeling cluster size and multiple categorical and continuous outcomes measured on each subunit. We use a continuation ratio probit model for the cluster size and underlying normal regression models for each of the subunit-specific outcomes. Dependency between cluster size and the different outcomes is accommodated through a latent variable structure. The form of the model facilitates posterior computation via a simple and computationally efficient Gibbs sampler. The approach is illustrated with an application to developmental toxicity data, and other applications, to joint modeling of longitudinal and event time data, are discussed.     

Assessing Toxicities in a Clinical Trial: Bayesian Inference for Ordinal Data Nested within Categories

Summary This article addresses modeling and inference for ordinal outcomes nested within categorical responses. We propose a mixture of normal distributions for latent variables associated with the ordinal data. This mixture model allows us to fix without loss of generality the cutpoint parameters that link the latent variable with the observed ordinal outcome. Moreover, the mixture model is shown to be more flexible in estimating cell probabilities when compared to the traditional Bayesian ordinal probit regression model with random cutpoint parameters. We extend our model to take into account possible dependence among the outcomes in different categories. We apply the model to a randomized phase III study to compare treatments on the basis of toxicities recorded by type of toxicity and grade within type. The data include the different (categorical) toxicity types exhibited in each patient. Each type of toxicity has an (ordinal) grade associated to it. The dependence among the different types of toxicity exhibited by the same patient is modeled by introducing patient‐specific random effects.     

Modeling tumor onset and multiplicity using transition models with latent variables

We describe a method for modeling carcinogenicity from animal studies where the data consist of counts of the number of tumors present over time. The research is motivated by applications to transgenic rodent studies, which have emerged as an alternative to chronic bioassays for screening possible carcinogens. In transgenic mouse studies, the endpoint of interest is frequently skin papilloma, with weekly examinations determining how many papillomas each animal has at a particular point in time. It is assumed that each animal has two unobservable latent variables at each time point. The first indicates whether or not the tumors are in a multiplying state and the second is the potential number of additional tumors if the tumors are in a multiplying state. The product of these variables follows a zero-inflated Poisson distribution, and the EM algorithm can be used to maximize the observed-data pseudo-likelihood, based on the latent variables. A generalized estimating equations robust variance estimator adjusts for dependency among outcomes within individual animals. The method is applied to testing for a dose-related trend in both tumor incidence and multiplicity in carcinogenicity studies.     

Finite mixture modeling with mixture outcomes using the EM algorithm

This paper discusses the analysis of an extended finite mixture model where the latent classes corresponding to the mixture components for one set of observed variables influence a second set of observed variables. The research is motivated by a repeated measurement study using a random coefficient model to assess the influence of latent growth trajectory class membership on the probability of a binary disease outcome. More generally, this model can be seen as a combination of latent class modeling and conventional mixture modeling. The EM algorithm is used for estimation. As an illustration, a random-coefficient growth model for the prediction of alcohol dependence from three latent classes of heavy alcohol use trajectories among young adults is analyzed.     

CGBayesNets: Conditional Gaussian Bayesian Network Learning and Inference with Mixed Discrete and Continuous Data

Bayesian Networks (BN) have been a popular predictive modeling formalism in bioinformatics, but their application in modern genomics has been slowed by an inability to cleanly handle domains with mixed discrete and continuous variables. Existing free BN software packages either discretize continuous variables, which can lead to information loss, or do not include inference routines, which makes prediction with the BN impossible. We present CGBayesNets, a BN package focused around prediction of a clinical phenotype from mixed discrete and continuous variables, which fills these gaps. CGBayesNets implements Bayesian likelihood and inference algorithms for the conditional Gaussian Bayesian network (CGBNs) formalism, one appropriate for predicting an outcome of interest from, e.g., multimodal genomic data. We provide four different network learning algorithms, each making a different tradeoff between computational cost and network likelihood. CGBayesNets provides a full suite of functions for model exploration and verification, including cross validation, bootstrapping, and AUC manipulation. We highlight several results obtained previously with CGBayesNets, including predictive models of wood properties from tree genomics, leukemia subtype classification from mixed genomic data, and robust prediction of intensive care unit mortality outcomes from metabolomic profiles. We also provide detailed example analysis on public metabolomic and gene expression datasets. CGBayesNets is implemented in MATLAB and available as MATLAB source code, under an Open Source license and anonymous download at http://www.cgbayesnets.com.

This is a PLOS Computational Biology Software Article

     

A multilevel latent Markov model for the evaluation of nursing homes' performance

The periodic evaluation of health care services is a primary concern for many institutions. We consider services provided by nursing homes with the aim of ranking a set of these structures with respect to their effect on resident health status. Since the overall health status is not directly observable, and given the longitudinal and multilevel structure of the available data, we rely on latent variable models and, in particular, on a multilevel latent Markov model where residents and nursing homes are the first and the second level units, respectively. The model includes individual covariates to account for resident characteristics. The impact of nursing home membership is modelled through a pair of random effects affecting the initial distribution and the transition probabilities between different levels of health status. Through the prediction of these random effects we obtain a ranking of the nursing homes. Furthermore, the proposed model accounts for nonignorable dropout due to resident death, which typically occurs in these contexts. The motivating dataset is gathered from the Long Term Care Facilities programme, a health care protocol implemented in Umbria (Italy). Our results show that differences in performance between nursing homes are statistically significant.     

Latent variable models for longitudinal data with multiple continuous outcomes

Multiple outcomes are often used to properly characterize an effect of interest. This paper proposes a latent variable model for the situation where repeated measures over time are obtained on each outcome. These outcomes are assumed to measure an underlying quantity of main interest from different perspectives. We relate the observed outcomes using regression models to a latent variable, which is then modeled as a function of covariates by a separate regression model. Random effects are used to model the correlation due to repeated measures of the observed outcomes and the latent variable. An EM algorithm is developed to obtain maximum likelihood estimates of model parameters. Unit-specific predictions of the latent variables are also calculated. This method is illustrated using data from a national panel study on changes in methadone treatment practices.     

The Influence of Socioeconomic Factors on Health Parameters in Overweight and Obese Adults

The prevalence of being overweight and of obesity is increasing worldwide, and is associated with a high risk to health. Therefore, the aim of our study was to investigate whether normal weight, overweight and obese subjects of low, middle or high socioeconomic status (SES) differ with regard to their health behavior, health, quality of life, and the use of medical care. Data from the Austrian Health Interview Survey (ATHIS) 2006/07, comprising 3 groups of 1,077 individuals, each of whom were normal weight, overweight, or obese, respectively, and matched according to their age, sex and SES, were analyzed concerning health outcomes. The results show that subjects with a low SES differ significantly from those of high SES in terms of their health behavior, self-perceived health, levels of impairment, chronic conditions, quality of life, and health care. Additionally, obesity in adults is associated with sub-optimal dietary practices and worse health, poorer quality of life and medical care than normal weight and overweight individuals. A significant interaction between the weight class and SES was found concerning physical exercise, impairment due to health problems and chronic diseases. A low SES has a strong negative impact on health, especially in obese individuals. Therefore a continuous target group-oriented, non-discriminatory public health program is required, prioritizing obese subjects with low SES.     

What is the quality of quality of medical care measures? Rashomon-like relativism and real-world applications

Much attention has been directed toward the measurement of health outcomes and the quality of medical care. Some policymakers tout outcomes measurement as a promising tool for improving health care, while others question whether current quality of care assessment is valid and of practical importance. Although significant advances have been made in the ability to measure quality of care with validity, several major methodological challenges remain. We analyze the quality of quality of medical care measures, using a conceptual framework that outlines the purpose of the measures; paradigms of the quality of care, including Donabedian's structure-process-outcome model and continuous quality improvement; and other key elements, such as scope, time, unit of analysis, and perspectives. Patient preferences and organizational contexts have been underemphasized, and should be incorporated into the framework for conceptualizing quality of care. Quality of care has relativistic and dynamic aspects. Different perspectives lead to different views of what high quality care is, and quality of care is a changing concept since medical science and treatment are constantly evolving. The most appropriate quality measures depend upon whose perspective one takes and the purpose of the measures; if the measures are chosen wisely, the current state of quality of medical care measurement is adequate for both accountability and quality improvement.     

A joint model for repeated events of different types and multiple longitudinal outcomes with application to a follow‐up study of patients after kidney transplant

This paper presents an extension of the joint modeling strategy for the case of multiple longitudinal outcomes and repeated infections of different types over time, motivated by postkidney transplantation data. Our model comprises two parts linked by shared latent terms. On the one hand is a multivariate mixed linear model with random effects, where a low‐rank thin‐plate spline function is incorporated to collect the nonlinear behavior of the different profiles over time. On the other hand is an infection‐specific Cox model, where the dependence between different types of infections and the related times of infection is through a random effect associated with each infection type to catch the within dependence and a shared frailty parameter to capture the dependence between infection types. We implemented the parameterization used in joint models which uses the fitted longitudinal measurements as time‐dependent covariates in a relative risk model. Our proposed model was implemented in OpenBUGS using the MCMC approach.     

Testing hypotheses in case-control studies--equivalence of Mantel-Haenszel statistics and logit score tests.

The two approaches in common use for the analysis of case-control studies are cross-classification by confounding variables, and modeling the logarithm of the odds ratio as a function of exposure and confounding variables. We show here that score statistics derived from the likelihood function in the latter approach are identical to the Mantel-Haenszel test statistics appropriate for the former approach. This identity holds in the most general situation considered, testing for marginal homogeneity in mK tables. This equivalence is demonstrated by a permutational argument which leads to a general likelihood expression in which the exposure variable may be a vector of discrete and/or continuous variables and in which more than two comparison groups may be considered. This likelihood can be used in analyzing studies in which there are multiple controls for each case or in which several disease categories are being compared. The possibility of including continuous variables makes this likelihood useful in situations that cannot be treated using the Mantel-Haenszel cross-classification approach.     

Estimating equations for a latent transition model with multiple discrete indicators

This paper proposes a two-part model for studying transitions between health states over time when multiple, discrete health indicators are available. The includes a measurement model positing underlying latent health states and a transition model between latent health states over time. Full maximum likelihood estimation procedures are computationally complex in this latent variable framework, making only a limited class of models feasible and estimation of standard errors problematic. For this reason, an estimating equations analogue of the pseudo-likelihood method for the parameters of interest, namely the transition model parameters, is considered. The finite sample properties of the proposed procedure are investigated through a simulation study and the importance of choosing strong indicators of the latent variable is demonstrated. The applicability of the methodology is illustrated with health survey data measuring disability in the elderly from the Longitudinal Study of Aging.     

Mitochondrial genetic effects on latent class variables associated with susceptibility to alcoholism

We report the results of statistical genetic analyses of data from the Collaborative Study on the Genetics of Alcoholism prepared for the Genetic Analysis Workshop 14 to detect and characterize maternally inherited mitochondrial genetic effects on variation in latent class psychiatric/behavioral variables employed in the diagnosis of alcoholism. Using published extensions to variance decomposition methods for statistical genetic analysis of continuous and discrete traits we: 1) estimated the proportion of the variance in each trait due to the effects of mitochondrial DNA (mtDNA), 2) tested for pleiotropy, both mitochondrial genetic and residual additive genetic, between trait pairs, and 3) evaluated whether the simultaneous estimation of mitochondrial genetic effects on these traits improves our ability to detect and localize quantitative trait loci (QTL) in the nuclear genome. After correction for multiple testing, we find significant (p < 0.009) mitochondrial genetic contributions to the variance for two latent class variables. Although we do detect significant residual additive genetic correlations between the two traits, there is no evidence of a residual mitochondrial genetic correlation between them. Evidence for autosomal QTL for these traits is improved when linkage screens are conditioned on significant mitochondrial genetic effects. We conclude that mitochondrial genes may contribute to variation in some latent class psychiatric/behavioral variables associated with alcoholism.     

Latent class regression on latent factors

In the research of public health, psychology, and social sciences, many research questions investigate the relationship between a categorical outcome variable and continuous predictor variables. The focus of this paper is to develop a model to build this relationship when both the categorical outcome and the predictor variables are latent (i.e. not observable directly). This model extends the latent class regression model so that it can include regression on latent predictors. Maximum likelihood estimation is used and two numerical methods for performing it are described: the Monte Carlo expectation and maximization algorithm and Gaussian quadrature followed by quasi-Newton algorithm. A simulation study is carried out to examine the behavior of the model under different scenarios. A data example involving adolescent health is used for demonstration where the latent classes of eating disorders risk are predicted by the latent factor body satisfaction.     

Why is the outcome of transient ischaemic attacks different in different groups of patients?

The outcomes of each of three large cohorts of patients with transient ischaemic attacks, which were studied in the same country at much the same time with the same methods, were compared and found to be quite different from each other. The differences in outcome were related not only to different strategies of treatment but also to differences in the prevalence and level of important prognostic factors (for example, case mix) and other factors such a the time delay from transient ischaemic attack to entry into the study and the play of chance. The implications for purchasers of health care are that they cannot rely solely on non-randomised comparisons of outcome of patients treated in competing units as a measure of the quality of care (which has only rather modest effects) without accounting for other factors that may influence outcome such as the nature of the illness, the case mix, observer bias, and the play of chance.     

医院质量监测系统在医院管理及临床服务中的应用

医院质量监测系统（HQMS）作为医疗服务监管信息网络直报平台,对建立全国性医疗服务质量与效率资料库,提供医院评审评价数据支持,促进医院内部持续改进具有重要作用。文章将医院应用HQMS进行医疗质量管理和持续改进的具体实践以及取得的成效进行了总结,可以为各医院医疗质量管理提供有益参考。     

Implementation and evaluation of a clinical pathway for TRAM breast reconstruction

Among strategies recently proposed to reduce practice variation, promote quality, and control costs in health care delivery, the concept of the clinical pathway has received considerable attention. Because transverse rectus abdominis musculocutaneous (TRAM) breast reconstruction is a common and often costly intervention, this institution sought to evaluate cost and quality outcomes of a clinical pathways program for this procedure. The TRAM reconstruction clinical pathway was implemented in April of 1996 to standardize postoperative care in this patient population. Outcomes of consecutive pathway cases for the first 14 months of the program were assessed in a retrospective cohort design, by using all nonpathway TRAM cases from the 18 months immediately before pathway implementation as controls. Outcomes assessed included length of hospital stay, postoperative complications, total postoperative charges, and total postoperative costs in relative value units. Data on these dependent variables were collected from hospital charts and billing records. The effects of pathway implementation on the outcomes of interest were analyzed by using analysis of covariance to control for potential confounding by other independent variables, including surgical site (unilateral versus bilateral reconstructions), technique (pedicle versus free TRAMs), timing (immediate versus delayed reconstructions), and patient age. Finally, a comparison of variances in the outcomes of interest between the two groups was analyzed by using an Ftest. For all statistical tests, p values of < or = 0.05 were considered significant. Twenty-nine patients were treated in the TRAM pathway group, whereas the control population included 40 nonpathway patients. After implementation of the TRAM pathway, length of stay decreased from 6.0 to 5.2 days; total postoperative charges were reduced from $8587 to $7744; and total postoperative relative value unit utilization declined from 1686 to 1104. Analysis of covariance showed that the decreases in length of hospital stay and relative value units in the TRAM pathway were statistically significant (p = 0.05 and p = 0.007, respectively). By contrast, no significant increase in complications was observed after pathway implementation. Variability in the TRAM pathway group, as measured by SD, decreased significantly for both length of hospital stay (p = 0.039) and relative value units (p = 0.023). Implementation of the TRAM reconstruction clinical pathway resulted in significant declines in length of hospital stay and total costs. These decreases in resource utilization had no significant effect on postoperative complication rates. Although additional research is needed to further assess the impact of clinical pathways, this approach offers considerable promise for improving the cost-effectiveness of health care.     

A Bayesian approach to jointly modeling toxicity and biomarker expression in a phase I/II dose-finding trial

In this article, we propose a Bayesian approach to phase I/II dose-finding oncology trials by jointly modeling a binary toxicity outcome and a continuous biomarker expression outcome. We apply our method to a clinical trial of a new gene therapy for bladder cancer patients. In this trial, the biomarker expression indicates biological activity of the new therapy. For ethical reasons, the trial is conducted sequentially, with the dose for each successive patient chosen using both toxicity and activity data from patients previously treated in the trial. The modeling framework that we use naturally incorporates correlation between the binary toxicity and continuous activity outcome via a latent Gaussian variable. The dose-escalation/de-escalation decision rules are based on the posterior distributions of both toxicity and activity. A flexible state-space model is used to relate the activity outcome and dose. Extensive simulation studies show that the design reliably chooses the preferred dose using both toxicity and expression outcomes under various clinical scenarios.