English

Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death

Machine Learning 2025-10-10 v1 Machine Learning Methodology

Abstract

Truncation by death, a prevalent challenge in critical care, renders traditional dynamic treatment regime (DTR) evaluation inapplicable due to ill-defined potential outcomes. We introduce a principal stratification-based method, focusing on the always-survivor value function. We derive a semiparametrically efficient, multiply robust estimator for multi-stage DTRs, demonstrating its robustness and efficiency. Empirical validation and an application to electronic health records showcase its utility for personalized treatment optimization.

Keywords

Cite

@article{arxiv.2510.07501,
  title  = {Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death},
  author = {Sihyung Park and Wenbin Lu and Shu Yang},
  journal= {arXiv preprint arXiv:2510.07501},
  year   = {2025}
}

Comments

30 pages, 5 figures, 6 tables, The Thirty-Ninth Annual Conference on Neural Information Processing Systems

R2 v1 2026-07-01T06:25:09.587Z