Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes
Abstract
Sequential clinical decision-making often involves more than maximizing average efficacy. Clinicians may need to simultaneously optimize clinically relevant tails of the outcome distribution, control treatment-related risk, and choose among multiple treatment options. Existing quantile dynamic treatment regime (DTR) methods capture distributional features of treatment outcomes but remain largely restricted to efficacy-only objectives and binary treatments. To address these limitations, we propose Risk-Aware Quantile Dynamic Treatment Regimes (RQDTR), a unified framework that optimizes a prespecified quantile of the cumulative potential outcome while explicitly incorporating treatment-related risk. We also develop an angle-based formulation for jointly learning decision rules across multiple treatment categories. Our framework includes three interpretable subclasses: efficacy-only quantile learning, constraint-based learning with population-level risk control, and utility-based learning through a composite benefit-risk utility. Theoretically, we establish identification and oracle equivalence, surrogate and estimator consistency under increasing quadratic penalties, asymptotic risk feasibility, and finite-sample performance error bounds. Extensive simulation studies and applications to All of Us major depressive disorder and MIMIC-III sepsis data demonstrate that RQDTR improves tail-oriented efficacy and achieves more favorable benefit-risk trade-offs than existing quantile DTR methods.
Related
- Estimating Optimal Dynamic Treatment Regimes for Personalized Education: A Tutorial and Applications with Machine Learning
- Deformed Q-learning for High-Dimensional Dynamic Treatment Regimes
- Nonparametric Efficient Estimation of Dynamic Treatment Regimes with Competing Risks
- Sharp Causal Bounds for Dynamic Treatment Regimes
- Comparison of estimated personalized treatment rules under varying interference structures and treatment rates using dynamic weighted ordinary least squares
BibTeX
@misc{lei2026riskaware,
title = {{Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes}},
author = {Chunyin Lei and Annie Qu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2608.05434},
eprint = {2608.05434},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.05434},
}
RIS
TY - UNPB
TI - Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes
AU - Chunyin Lei
AU - Annie Qu
PY - 2026
DA - 2026/11/13
PB - arXiv
DO - 10.48550/arxiv.2608.05434
UR - https://arxiv.org/abs/2608.05434
AB - Sequential clinical decision-making often involves more than maximizing average efficacy. Clinicians may need to simultaneously optimize clinically relevant tails of the outcome distribution, control treatment-related risk, and choose among multiple treatment options. Existing quantile dynamic treatment regime (DTR) methods capture distributional features of treatment outcomes but remain largely restricted to efficacy-only objectives and binary treatments. To address these limitations, we propose Risk-Aware Quantile Dynamic Treatment Regimes (RQDTR), a unified framework that optimizes a prespecified quantile of the cumulative potential outcome while explicitly incorporating treatment-related risk. We also develop an angle-based formulation for jointly learning decision rules across multiple treatment categories. Our framework includes three interpretable subclasses: efficacy-only quantile learning, constraint-based learning with population-level risk control, and utility-based learning through a composite benefit-risk utility. Theoretically, we establish identification and oracle equivalence, surrogate and estimator consistency under increasing quadratic penalties, asymptotic risk feasibility, and finite-sample performance error bounds. Extensive simulation studies and applications to All of Us major depressive disorder and MIMIC-III sepsis data demonstrate that RQDTR improves tail-oriented efficacy and achieves more favorable benefit-risk trade-offs than existing quantile DTR methods.
ER -