Inverse-intensity weighted generalized estimating equations with irregularly measured longitudinal data and informative dropout

TL;DR

This paper extends inverse-intensity weighted generalized estimating equations (IIW-GEEs) to handle informative dropout in irregularly measured longitudinal data, reducing bias and improving accuracy in biomedical research analyses.

Contribution

The authors develop an extended IIW-GEE method that accounts for informative dropout, addressing bias present in existing approaches when health outcomes influence dropout.

Findings

Simulation studies show significant bias reduction with the new method.

Application to STAR*D trial data reveals overestimation of disease trajectory without accounting for dropout.

Extended method improves accuracy of longitudinal data analysis in biomedical studies.

Abstract

Longitudinal data are commonly encountered in biomedical research, including randomized trials and retrospective cohort studies. Subjects are typically followed over a period of time and may be scheduled for follow-up at pre-determined time points. However, subjects may miss their appointments or return at non-specified times, leading to irregularity in the visit process. IIW-GEEs have been developed as one method to account for this irregularity, whereby estimates from a visit intensity model are used as weights in a GEE model with an independent correlation structure. We show that currently available methods can be biased for situations in which the health outcome of interest may influence a subject's dropout from the study. We have extended the IIW-GEE framework to adjust for informative dropout and have demonstrated via simulation studies that this bias can be significantly reduced. We have illustrated this method using the STAR*D clinical trial data, and observed that the disease trajectory was generally overestimated when informative dropout was not accounted for.