面向个性化动态治疗方案的风险感知分位数学习
Risk-Aware Quantile Learning for Personalized Dynamic Treatment Regimes
浏览论文内容
中文总结 AI 辅助
本研究提出风险感知分位数动态治疗方案（RQDTR）框架，通过多子类设计优化治疗相关风险与分位数疗效，在模拟及真实临床数据中验证其获益-风险权衡优势。
中文摘要 AI 辅助
序贯临床决策通常不只是最大化平均疗效，临床医生可能需要同时优化结局分布中与临床相关的尾部、控制治疗相关风险，并在多种治疗方案中进行选择。现有的分位数动态治疗方案（DTR）方法虽能捕捉治疗结局的分布特征，但大多局限于仅考虑疗效的目标和二元治疗场景。为解决这些局限，我们提出风险感知分位数动态治疗方案（RQDTR），这一统一框架在优化累积潜在结局的预设分位数的同时，明确纳入治疗相关风险。我们还开发了一种基于角度的公式，用于联合学习多治疗类别的决策规则。该框架包含三个可解释的子类：仅考虑疗效的分位数学习、基于群体水平风险控制的约束学习，以及通过复合获益-风险效用的基于效用的学习。理论上，我们确立了识别性与先验等价性、平滑替代损失的Fisher一致性、估计方案的一致性，以及有限样本性能误差率。大量模拟研究及对“All of Us”重度抑郁症数据、MIMIC-III脓毒症数据的应用表明，RQDTR相比现有分位数DTR方法，能提升面向尾部的疗效，并实现更优的获益-风险权衡。
英文摘要
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, Fisher consistency of the smoothed surrogate, consistency of the estimated regime, and finite-sample performance error rates. 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.
