Treatment-control comparisons in platform trials including non-concurrent controls

TL;DR

This paper develops methods to incorporate non-concurrent controls in platform trials, accounting for time trends to improve power while controlling bias and type 1 error.

Contribution

It introduces frequentist and Bayesian approaches to adjust for time trends in non-concurrent controls, enhancing analysis accuracy in platform trials.

Findings

Methods effectively control type 1 error under certain conditions.

Incorporating non-concurrent controls increases statistical power.

Simulation results demonstrate improved efficiency over using only concurrent controls.

Abstract

Shared controls in platform trials comprise concurrent and non-concurrent controls. For a given experimental arm, non-concurrent controls refer to data from patients allocated to the control arm before the arm enters the trial. The use of non-concurrent controls in the analysis is attractive because it may increase the trial's power of testing treatment differences while decreasing the sample size. However, since arms are added sequentially in the trial, randomization occurs at different times, which can introduce bias in the estimates due to time trends. In this article, we present methods to incorporate non-concurrent control data in treatment-control comparisons, allowing for time trends. We focus mainly on frequentist approaches that model the time trend and Bayesian strategies that limit the borrowing level depending on the heterogeneity between concurrent and non-concurrent controls. We examine the impact of time trends, overlap between experimental treatment arms and entry times of arms in the trial on the operating characteristics of treatment effect estimators for each method under different patterns for the time trends. We argue under which conditions the methods lead to type 1 error control and discuss the gain in power compared to trials only using concurrent controls by means of a simulation study in which methods are compared.