Modelling the decline pattern in functional measures from a prevalent cohort study

In studying decline among cognitively impaired people, a prevalent cohort study design is commonly used to account for entry into the study at different levels of impairment. The data set typically consists of many short series of repeated measurements collected over time. However, the time origin, such as time of disease/impairment onset, is often uncertain. In order to model non-linear decline patterns in functional test scores and associated risk factors with such data, we propose two approaches as alternatives to Liu et al. One approach models change over adjacent visits with varying time intervals. The second models the change since baseline using a random effect for heterogeneity of change. We used these two approaches to examine the decline in cognitive test scores among special care unit (SCU) and non-SCU residents at the New York sites of the National Institute on Aging (NIA) collaborative studies of special dementia care. The analyses suggest that, controlling for several covariates, SCU residents experienced more rapid cognitive decline than did non-SCU residents. The relative advantages and disadvantages of the two models are discussed.     

Identifying interacting SNPs using Monte Carlo logic regression

Interactions are frequently at the center of interest in single-nucleotide polymorphism (SNP) association studies. When interacting SNPs are in the same gene or in genes that are close in sequence, such interactions may suggest which haplotypes are associated with a disease. Interactions between unrelated SNPs may suggest genetic pathways. Unfortunately, data sets are often still too small to definitively determine whether interactions between SNPs occur. Also, competing sets of interactions could often be of equal interest. Here we propose Monte Carlo logic regression, an exploratory tool that combines Markov chain Monte Carlo and logic regression, an adaptive regression methodology that attempts to construct predictors as Boolean combinations of binary covariates such as SNPs. The goal of Monte Carlo logic regression is to generate a collection of (interactions of) SNPs that may be associated with a disease outcome, and that warrant further investigation. As such, the models that are fitted in the Markov chain are not combined into a single model, as is often done in Bayesian model averaging procedures. Instead, the most frequently occurring patterns in these models are tabulated. The method is applied to a study of heart disease with 779 participants and 89 SNPs. A simulation study is carried out to investigate the performance of the Monte Carlo logic regression approach.     

Time-varying exposure and the impact of stressful life events on onset of affective disorder

Stressful life events are now established as risk factors for the onset of affective disorder but few studies have investigated time-varying exposure effects. Discrete (grouped) time survival methods provide a flexible framework for evaluating multiple time-dependent covariates and time-varying covariate effects. Here, we use these methods to investigate the time-varying influence of life events on the onset of affective disorder. Various straightforward time-varying exposure models are compared, involving one or more (stepped) time-dependent covariates and time-dependent covariates constructed or estimated according to exponential decay. These models are applied to data from two quite different studies. The first, a small scale interviewer-based longitudinal study (n = 180) concerned with affective disorder onset following loss (or threat of loss) event experiences. The second, a questionnaire assessment as part of an ongoing population study (n = 3353), provides a history of marital loss events and of depressive disorder onset. From the first study the initial impact of loss events was found to decay with a half-life of 5 weeks. Psychological coping strategy was found to modify vulnerability to the adverse effects of these events. The second study revealed that while men had a lower immediate risk of disorder onset following loss event experience their risk period was greater than for women. Time-varying exposure effects were well described by the appropriate use of simple time-dependent covariates.     

The onset of decline in ischemic heart disease mortality in the United States

Temporal and spatial patterns of the onset of the decline in ischemic heart disease mortality in the United States for each of the 48 contiguous US states and the District of Columbia are examined for the years 1955-1978 for age-sex-race-specific mortality. Mortality rates are derived from National Center for Health Statistics mortality data, and a polynomial interpolation is used to estimate intercensal population counts employing 1950, 1960, 1970, and 1980 US Census data. A quadratic regression equation is used to estimate the date of highest rate, which marks the beginning of the decline for each of the US states. The temporal distribution of the onset of the decline among men occurred primarily between 1960 and 1965. Among women, the onset of decline was more variable. Furthermore, strong and regular spatial patterns were seen among the groups examined and these impressions are supported by statistical analysis. California, Maryland, and the District of Columbia were early decliners in most groups studied, whereas states in the southeast were consistently among the last to experience the onset of decline. These patterns suggest the existence of an underlying phenomenon accounting for the spread or diffusion of the onset of decline in ischemic heart disease mortality.     

Investigating heterogeneity in an individual patient data meta-analysis of time to event outcomes

Differences across studies in terms of design features and methodology, clinical procedures, and patient characteristics, are factors that can contribute to variability in the treatment effect between studies in a meta-analysis (statistical heterogeneity). Regression modelling can be used to examine relationships between treatment effect and covariates with the aim of explaining the variability in terms of clinical, methodological, or other factors. Such an investigation can be undertaken using aggregate data or individual patient data. An aggregate data approach can be problematic as sufficient data are rarely available and translating aggregate effects to individual patients can often be misleading. An individual patient data approach, although usually more resource demanding, allows a more thorough investigation of potential sources of heterogeneity and enables a fuller analysis of time to event outcomes in meta-analysis. Hierarchical Cox regression models are used to identify and explore the evidence for heterogeneity in meta-analysis and examine the relationship between covariates and censored failure time data in this context. Alternative formulations of the model are possible and illustrated using individual patient data from a meta-analysis of five randomized controlled trials which compare two drugs for the treatment of epilepsy. The models are further applied to simulated data examples in which the degree of heterogeneity and magnitude of treatment effect are varied. The behaviour of each model in each situation is explored and compared.     

Pseudo-likelihood methods for longitudinal binary data with non-ignorable missing responses and covariates

In this paper we consider longitudinal studies in which the outcome to be measured over time is binary, and the covariates of interest are categorical. In longitudinal studies it is common for the outcomes and any time-varying covariates to be missing due to missed study visits, resulting in non-monotone patterns of missingness. Moreover, the reasons for missed visits may be related to the specific values of the response and/or covariates that should have been obtained, i.e. missingness is non-ignorable. With non-monotone non-ignorable missing response and covariate data, a full likelihood approach is quite complicated, and maximum likelihood estimation can be computationally prohibitive when there are many occasions of follow-up. Furthermore, the full likelihood must be correctly specified to obtain consistent parameter estimates. We propose a pseudo-likelihood method for jointly estimating the covariate effects on the marginal probabilities of the outcomes and the parameters of the missing data mechanism. The pseudo-likelihood requires specification of the marginal distributions of the missingness indicator, outcome, and possibly missing covariates at each occasions, but avoids making assumptions about the joint distribution of the data at two or more occasions. Thus, the proposed method can be considered semi-parametric. The proposed method is an extension of the pseudo-likelihood approach in Troxel et al. to handle binary responses and possibly missing time-varying covariates. The method is illustrated using data from the Six Cities study, a longitudinal study of the health effects of air pollution.     

BAYESIAN IMPUTATION OF PREDICTIVE VALUES WHEN COVARIATE INFORMATION IS AVAILABLE AND GOLD STANDARD DIAGNOSIS IS UNAVAILABLE

We suggest a conceptually simple Bayesian approach to inferences about the conditional probability of a specimen being infection-free given the outcome of a diagnostic test and covariate information. The approach assumes that the infection state of a specimen is not observable but uses the outcomes of a second test in conjuction with those of the first, that is, dual testing data. Dual testing procedures are often employed in clinical laboratories to assure that positive samples are not contaminated or to increase the likelihood of correct diagnoses. Using the CD4 count and a proxy for risk behaviour as covariates, we apply the method to obtain inferences about the conditional probability of an individual being HIV-1 infection-free given the individual's covariates and a negative outcome with the standard enzyme-linked immunoadsorbent assay/Western blotting test for HIV-1 detection. Inferences combine data from two studies where specimens were tested with the standard and with the more sensitive polymerase chain reaction test.     

Meta‐analytical synthesis of regression coefficients under different categorization scheme of continuous covariates

Recently, the number of clinical prediction models sharing the same regression task has increased in the medical literature. However, evidence synthesis methodologies that use the results of these regression models have not been sufficiently studied, particularly in meta‐analysis settings where only regression coefficients are available. One of the difficulties lies in the differences between the categorization schemes of continuous covariates across different studies. In general, categorization methods using cutoff values are study specific across available models, even if they focus on the same covariates of interest. Differences in the categorization of covariates could lead to serious bias in the estimated regression coefficients and thus in subsequent syntheses. To tackle this issue, we developed synthesis methods for linear regression models with different categorization schemes of covariates. A 2‐step approach to aggregate the regression coefficient estimates is proposed. The first step is to estimate the joint distribution of covariates by introducing a latent sampling distribution, which uses one set of individual participant data to estimate the marginal distribution of covariates with categorization. The second step is to use a nonlinear mixed‐effects model with correction terms for the bias due to categorization to estimate the overall regression coefficients. Especially in terms of precision, numerical simulations show that our approach outperforms conventional methods, which only use studies with common covariates or ignore the differences between categorization schemes. The method developed in this study is also applied to a series of WHO epidemiologic studies on white blood cell counts.     

Semiparametric regression models for detecting effect modification in matched case-crossover studies

In matched case-crossover studies, it is generally accepted that covariates on which a case and associated controls are matched cannot exert a confounding effect on independent predictors included in the conditional logistic regression model because any stratum effect is removed by the conditioning on the fixed number of sets of a case and controls in the stratum. Hence, the conditional logistic regression model is not able to detect any effects associated with the matching covariates by stratum. In addition, the matching covariates may be effect modification and the methods for assessing and characterizing effect modification by matching covariates are quite limited. In this article, we propose a unified approach in its ability to detect both parametric and nonparametric relationships between the predictor and the relative risk of disease or binary outcome, as well as potential effect modifications by matching covariates. Two methods are developed using two semiparametric models: (1) the regression spline varying coefficients model and (2) the regression spline interaction model. Simulation results show that the two approaches are comparable. These methods can be used in any matched case-control study and extend to multilevel effect modification studies. We demonstrate the advantage of our approach using an epidemiological example of a 1-4 bi-directional case-crossover study of childhood aseptic meningitis associated with drinking water turbidity.     

Semiparametric regression models for repeated measures of mortal cohorts with non‐monotone missing outcomes and time‐dependent covariates

We propose a semiparametric marginal modeling approach for longitudinal analysis of cohorts with data missing due to death and non‐response to estimate regression parameters interpreted as conditioned on being alive. Our proposed method accommodates outcomes and time‐dependent covariates that are missing not at random with non‐monotone missingness patterns via inverse‐probability weighting. Missing covariates are replaced by consistent estimates derived from a simultaneously solved inverse‐probability‐weighted estimating equation. Thus, we utilize data points with the observed outcomes and missing covariates beyond the estimated weights while avoiding numerical methods to integrate over missing covariates. The approach is applied to a cohort of elderly female hip fracture patients to estimate the prevalence of walking disability over time as a function of body composition, inflammation, and age. Copyright © 2010 John Wiley & Sons, Ltd.     

A regression model for multivariate random length data

Multivariate random length data occur when we observe multiple measurements of a quantitative variable and the variable number of these measurements is also an observed outcome for each experimental unit. For example, for a patient with coronary artery disease, we may observe a number of lesions in that patient's coronary arteries, along with percentage of blockage of each lesion. Barnhart and Sampson first proposed the multiple population model to analyse multivariate random length data without covariates. This paper extends their approach to deal with multiple covariates. We propose a new multiple population regression model with covariates, and discuss the estimation issues. We analyse data from the TYPE II coronary intervention study to illustrate the methodology.     

Choice of time-scale in Cox's model analysis of epidemiologic cohort data: a simulation study

Cox's regression model is widely used for assessing associations between potential risk factors and disease occurrence in epidemiologic cohort studies. Although age is often a strong determinant of disease risk, authors have frequently used time-on-study instead of age as the time-scale, as for clinical trials. Unless the baseline hazard is an exponential function of age, this approach can yield different estimates of relative hazards than using age as the time-scale, even when age is adjusted for. We performed a simulation study in order to investigate the existence and magnitude of bias for different degrees of association between age and the covariate of interest. Age to disease onset was generated from exponential, Weibull or piecewise Weibull distributions, and both fixed and time-dependent dichotomous covariates were considered. We observed no bias upon using age as the time-scale. Upon using time-on-study, we verified the absence of bias for exponentially distributed age to disease onset. For non-exponential distributions, we found that bias could occur even when the covariate of interest was independent from age. It could be severe in case of substantial association with age, especially with time-dependent covariates. These findings were illustrated on data from a cohort of 84,329 French women followed prospectively for breast cancer occurrence. In view of our results, we strongly recommend not using time-on-study as the time-scale for analysing epidemiologic cohort data.     

Does poor health predict moving,move quality,and desire to move?: A study examining neighborhood selection in US adolescents and adults

To date, research has rarely considered the role of health in shaping characteristics of the neighborhood, including mobility patterns. We explored whether individual health status shapes and constrains where individuals live. Using the National Longitudinal Study of Adolescent Health data, we examined whether 16 health indicators predicted moving, move quality, and desire to move. 3.8% of adolescents (n=490) reported a move in the past year. In the unadjusted models, 10 health indicators were associated with moving; the magnitude of association for these health indicators was similar to socio-demographic characteristics. 7 of these health-moving associations persisted after adjusting for covariates. Health was also associated with moving quality, with a greater number of past year health problems in the child being associated with moving to a lower income neighborhood and parent disability or poor health being associated with moving to a higher income neighborhood. Almost every poor health status indicator was associated with a greater desire to move. Findings suggest that health status influences moving, and a reciprocal framework is more appropriate for examining health-neighborhood linkages.     

Psychosis and schizophrenia-like disorders in the elderly

Non-organic, non-affective psychoses that have their first onset in late life have been the subject of diagnostic dispute for many years. Do they represent the late manifestation of more typical schizophrenia but with a delayed onset? Are they cases of "symptomatic schizophrenia" in which some organic brain change associated with ageing gives rise to schizophrenic symptoms? A recent International Consensus established that while cases of schizophrenia are sometimes delayed in their onset to 40 to 59 years of age (late-onset schizophrenia), onset after the age of 60 years is generally associated with a different symptom profile and associated risk factors (very late-onset schizophrenia-like psychosis). In this paper we review the data on the very late-onset schizophrenia-like psychosis patient group and suggest research directions for the future.     

Meta-analysis of diagnostic test studies using individual patient data and aggregate data

A meta-analysis of diagnostic test studies provides evidence-based results regarding the accuracy of a particular test, and usually involves synthesizing aggregate data (AD) from each study, such as the 2 by 2 tables of diagnostic accuracy. A bivariate random-effects meta-analysis (BRMA) can appropriately synthesize these tables, and leads to clinical results, such as the summary sensitivity and specificity across studies. However, translating such results into practice may be limited by between-study heterogeneity and that they relate to some 'average' patient across studies.In this paper we describe how the meta-analysis of individual patient data (IPD) from diagnostic studies can lead to clinical results more tailored to the individual patient. We develop IPD models that extend the BRMA framework to include study-level covariates, which help explain the between-study heterogeneity, and also patient-level covariates, which allow one to assess the effect of patient characteristics on test accuracy. We show how the inclusion of patient-level covariates requires a careful separation of within-study and across-study accuracy-covariate effects, as the latter are particularly prone to confounding. Our models are assessed through simulation and extended to allow IPD studies to be combined with AD studies, as IPD are not always available for all studies. Application is made to 23 studies assessing the accuracy of ear thermometers for diagnosing fever in children, with 16 IPD and 7 AD studies. The models reveal that between-study heterogeneity is partly explained by the use of different measurement devices, but there is no evidence that being an infant modifies diagnostic accuracy.     

Recursive partitioning for monotone missing at random longitudinal markers

The development of HIV resistance mutations reduces the efficacy of specific antiretroviral drugs used to treat HIV infection and cross‐resistance within classes of drugs is common. Recursive partitioning has been extensively used to identify resistance mutations associated with a reduced virologic response measured at a single time point; here we describe a statistical method that accommodates a large set of genetic or other covariates and a longitudinal response. This recursive partitioning approach for continuous longitudinal data uses the kernel of a U‐statistic as the splitting criterion and avoids the need for parametric assumptions regarding the relationship between observed response trajectories and covariates. We propose an extension of this approach that allows longitudinal measurements to be monotone missing at random by making use of inverse probability weights. We assess the performance of our method using extensive simulation studies and apply them to data collected by the Forum for Collaborative HIV Research as part of an investigation of the viral genetic mutations associated with reduced clinical efficacy of the drug abacavir. Copyright © 2012 John Wiley & Sons, Ltd.     

Identifying and interpreting subgroups in health care utilization data with count mixture regression models

Inpatient care is a large share of total health care spending, making analysis of inpatient utilization patterns an important part of understanding what drives health care spending growth. Common features of inpatient utilization measures such as length of stay and spending include zero inflation, overdispersion, and skewness, all of which complicate statistical modeling. Moreover, latent subgroups of patients may have distinct patterns of utilization and relationships between that utilization and observed covariates. In this work, we apply and compare likelihood-based and parametric Bayesian mixtures of negative binomial and zero-inflated negative binomial regression models. In a simulation, we find that the Bayesian approach finds the true number of mixture components more accurately than using information criteria to select among likelihood-based finite mixture models. When we apply the models to data on hospital lengths of stay for patients with lung cancer, we find distinct subgroups of patients with different means and variances of hospital days, health and treatment covariates, and relationships between covariates and length of stay.     

Validity of using ad hoc methods to analyze secondary traits in case‐control association studies

Case‐control association studies often collect from their subjects information on secondary phenotypes. Reusing the data and studying the association between genes and secondary phenotypes provide an attractive and cost‐effective approach that can lead to discovery of new genetic associations. A number of approaches have been proposed, including simple and computationally efficient ad hoc methods that ignore ascertainment or stratify on case‐control status. Justification for these approaches relies on the assumption of no covariates and the correct specification of the primary disease model as a logistic model. Both might not be true in practice, for example, in the presence of population stratification or the primary disease model following a probit model. In this paper, we investigate the validity of ad hoc methods in the presence of covariates and possible disease model misspecification. We show that in taking an ad hoc approach, it may be desirable to include covariates that affect the primary disease in the secondary phenotype model, even though these covariates are not necessarily associated with the secondary phenotype. We also show that when the disease is rare, ad hoc methods can lead to severely biased estimation and inference if the true disease model follows a probit model instead of a logistic model. Our results are justified theoretically and via simulations. Applied to real data analysis of genetic associations with cigarette smoking, ad hoc methods collectively identified as highly significant () single nucleotide polymorphisms from over 10 genes, genes that were identified in previous studies of smoking cessation.     

A Bayesian proportional hazards regression model with non-ignorably missing time-varying covariates

Missing covariate data are common in observational studies of time to an event, especially when covariates are repeatedly measured over time. Failure to account for the missing data can lead to bias or loss of efficiency, especially when the data are non-ignorably missing. Previous work has focused on the case of fixed covariates rather than those that are repeatedly measured over the follow-up period, hence, here we present a selection model that allows for proportional hazards regression with time-varying covariates when some covariates may be non-ignorably missing. We develop a fully Bayesian model and obtain posterior estimates of the parameters via the Gibbs sampler in WinBUGS. We illustrate our model with an analysis of post-diagnosis weight change and survival after breast cancer diagnosis in the Long Island Breast Cancer Study Project follow-up study. Our results indicate that post-diagnosis weight gain is associated with lower all-cause and breast cancer-specific survival among women diagnosed with new primary breast cancer. Our sensitivity analysis showed only slight differences between models with different assumptions on the missing data mechanism yet the complete-case analysis yielded markedly different results.     

Analyzing left‐truncated and right‐censored infectious disease cohort data with interval‐censored infection onset

In an infectious disease cohort study, individuals who have been infected with a pathogen are often recruited for follow up. The period between infection and the onset of symptomatic disease, referred to as the incubation period, is of interest because of its importance on disease surveillance and control. However, the incubation period is often difficult to ascertain due to the uncertainty associated with asymptomatic infection onset time. An additional complication is that the observed infected subjects are likely to have longer incubation periods due to the prevalent sampling. In this article, we demonstrate how to estimate the distribution of the incubation period with the uncertain infection onset, subject to left‐truncation and right‐censoring. We employ a family of sufficiently general parametric models, the generalized odds‐rate class of regression models, for the underlying incubation period and its correlation with covariates. In simulation studies, we assess the finite sample performance of the model fitting and hazard function estimation. The proposed method is illustrated on data from the HIV/AIDS study on injection drug users admitted to a detoxification program in Badalona, Spain.