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

arXiv: https://arxiv.org/abs/2508.11060 · HTML: https://mlsanity.com/paper/2508.11060/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 25 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Builds on (most cited first, 2 of 2)

- [Multi-stage optimal dynamic treatment regimes for survival outcomes with dependent censoring](https://mlsanity.com/paper/2012.03294/) (2020)
- [Counterfactual Q Learning via the Linear Buckley James Method for Longitudinal Survival Data](https://mlsanity.com/paper/2505.12159/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bayesian fusion forests for heterogeneous treatment effects on survival from randomised and real-world data](https://mlsanity.com/paper/2607.29295/) (2026)

## Abstract (arXiv)

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.