Accounting for Inconsistent Use of Covariate Adjustment in Group Sequential Trials

TL;DR

This paper addresses the challenges of inconsistent covariate adjustment in group sequential clinical trials, proposing methods to ensure valid interim analysis, estimation, and inference, especially for two-arm trials with continuous outcomes.

Contribution

It introduces new methods for correct covariate adjustment in group sequential trials to prevent bias and error inflation, with validation through simulation studies.

Findings

Proposed adjustment methods improve validity of interim analyses.

Simulation results show reduced bias and error inflation.

Recommendations for applying covariate adjustment in practice.

Abstract

Group sequential designs in clinical trials allow for interim efficacy and futility monitoring. Adjustment for baseline covariates can increase power and precision of estimated effects. However, inconsistently applying covariate adjustment throughout the stages of a group sequential trial can result in inflation of type I error, biased point estimates, and anti-conservative confidence intervals. We propose methods for performing correct interim monitoring, estimation, and inference in this setting that avoid these issues. We focus on two-arm trials with simple, balanced randomization and continuous outcomes. We study the performance of our boundary, estimation, and inference adjustments in simulation studies. We end with recommendations about the application of covariate adjustment in group sequential designs.