Causal Survival Analysis in Platform Trials with Non-Concurrent Controls

TL;DR

This paper develops a causal survival analysis framework for platform trials with non-concurrent controls, clarifying estimand identification, assumptions for pooling, and when pooling improves precision, especially in the context of COVID-19 treatment trials.

Contribution

It introduces an estimand-first causal survival framework for platform trials, providing nonparametric identification results and conditions for valid pooling of non-concurrent controls.

Findings

Pooling NCC improves precision only under correct assumptions and models.

Pooling NCC can introduce bias if assumptions are violated.

Targeting concurrent controls with covariate-adjusted DR estimators is most robust.

Abstract

Platform trials allow treatment arms to enter and exit over time while maintaining a shared control arm, yielding concurrent and non-concurrent controls (NCC). Pooling NCC is often motivated as a strategy to improve statistical efficiency, but it is unclear which estimand is targeted, what assumptions justify identification and estimation, and when precision gains are achievable; these questions are further complicated by time-to-event/survival data. Motivated by the Adaptive COVID-19 Treatment Trial (ACTT) platform trial with time to recovery as the primary endpoint, we develop an estimand-first causal survival framework targeting the treatment-specific counterfactual survival curve in the concurrent population and the corresponding functionals including the concurrent restricted mean survival time (RMST). We give nonparametric identification results and formalize conditions that justify pooling using NCC. We study covariate-adjusted outcome-regression (OR) and doubly robust (DR) estimators for the concurrent RMST, comparing concurrent-only versions to pooled-control versions. Pooling improves precision for OR estimators only when the pooling assumption holds and parametric hazard models are correctly specified; otherwise, pooling can induce bias. Moreover, in certain settings, pooling NCC yields no efficiency gain for the DR estimator. Overall, the most robust route to improve precision is to target concurrent causal survival estimands and use a covariate-adjusted DR estimation that uses only concurrent controls. An ACTT application corroborates these results.