Counterfactual Survival Q-learning via Buckley-James Boosting, with Applications to ACTG 175 and CALGB 8923

TL;DR

This paper introduces a Buckley James Boost Q learning method for estimating personalized treatment strategies from censored survival data, avoiding proportional hazards assumptions and improving decision accuracy.

Contribution

It develops a flexible, robust framework combining accelerated failure time modeling with boosting, tailored for dynamic treatment regime estimation in clinical trials.

Findings

Improves treatment decision accuracy in simulations.

Produces more stable counterfactual contrasts in multistage trials.

Outperforms Cox-based Q learning in nonproportional hazards scenarios.

Abstract

We propose a Buckley James (BJ) Boost Q learning framework for estimating optimal dynamic treatment regimes from right censored survival outcomes in longitudinal randomized clinical trials, motivated by the clinical need to support patient specific treatment decisions when follow up is incomplete and covariate effects may be nonlinear. The method combines accelerated failure time modeling with iterative boosting using flexible base learners, including componentwise least squares and regression trees, within a counterfactual Q learning framework. By modeling conditional survival time directly, BJ Boost Q learning avoids the proportional hazards assumption, yields clinically interpretable time scale contrasts, and enables estimation of stage specific Q functions and individualized decision rules under standard potential outcomes assumptions. In contrast to Cox based Q learning, which relies on hazard modeling and can be sensitive to nonproportional hazards and model misspecification, our approach provides a robust and flexible alternative for regime learning. Simulation studies and analyses of the ACTG175 HIV trial and the CALGB 8923 two stage leukemia trial show that BJ Boost Q learning improves treatment decision accuracy and produces more stable within participant counterfactual contrasts, particularly in multistage settings where estimation error and bias can compound across stages.