Handling dropout and clustering in longitudinal multicentre clinical trials

Abstract

Many clinical trials enrol patients from different medical centres. Multi-centre studies are particularly helpful in cancer research as they allow researchers to evaluate the efficacy of a therapy in a variety of patients and settings, making it possible to investigate the effect of treatments in those cases when it is difficult, or even impossible, for a single centre to recruit the required number of patients. It is often argued, however, that despite agreement among different centres to follow common standardized protocols, variation may occur in both baseline characteristics of the recruited patients and in treatment effects. This heterogeneity should be detected and, if present, accounted for in the data analysis. Furthermore, the longitudinal nature of these types of experimental studies raises the problem of attrition, that is, patients may dropout of the study for a number of reasons mainly death or disease progression. In this paper, we consider the health related quality of life of advanced melanoma patients in a longitudinal multi-centre randomized clinical trial comparing two different anti-tumoural treatments. We propose a Heckman type model to account for the possibility that patients dropout according to a non-ignorable mechanism. The model is extended to a multilevel setting to account both for the longitudinal nature and the multicentre structure of the design. We found a strong variation across centres in the quality of life evaluation. The effect of centres on the dropout was not found to be relevant in the considered data although dropout does depend on patient's characteristics.

Evaluating the integration of chronic disease prevention and management services into primary health care

“…However, despite the use of such patterns, heterogeneity that may be observed and documented between clinics in terms of outcomes produced, termed “center effects” is part of the pragmatic design and will reflect the clinical reality of primary health care. It has been suggested that interventions may be affected by center-specific issues and characteristics such as degree of sub-specialization within practices and provider background and experience, [52] however, we believe that delivering interventions by practitioners who evolve through the same training process will reduce clustering effects so that the experiment can be replicated across centers and over time [53]. This desired objectivity is based on the involvement of systematic recourse to the collective production of evidence and requires standardization of practices within settings in order to produce replicable findings which can then be used to standardize practice within, and across, clinical care settings [54].…”

Weather conditions, brood size and hatching order affect Common SwiftApus apusnestlings’ survival and growth

“…This type of model can be built using a Generalized Linear Mixed Model (GLMM) assuming a binomial error distribution (McDonald & Rosina 2001, Del Bianco & Borgoni 2006. Death events were modelled according to mean wind speed, a dichotomous variable accounting for occurrence of rainfall events during each interval (rainfall, hereafter), temperature residuals, nestling hatching date and age, and mean number of nestlings at a nest during each interval.…”

Copula selection models for non‐Gaussian outcomes that are missing not at random

“…Selection models have been commonly used to handle MNAR data in clinical and epidemiological research, by jointly modeling the outcome and missingness models and typically assuming bivariate normality. Heckman was one of the first to propose such model (Heckman selection model) using a simultaneous equation approach, where the error terms were assumed to follow a bivariate Gaussian.…”