Estimating Optimal Dynamic Treatment Regimes With Survival Outcomes

The statistical study of precision medicine is concerned with dynamic treatment regimes (DTRs) in which treatment decisions are tailored to patient-level information. Individuals are followed through multiple stages of clinical intervention, and the goal is to perform inferences on the sequence of personalized treatment decision rules to be applied in practice. Of interest is the identification of an optimal DTR, that is, the sequence of treatment decisions that yields the best expected outcome. Statistical methods for identifying optimal DTRs from observational data are theoretically complex and not easily implementable by researchers, especially when the outcome of interest is survival time. We propose a doubly robust, easy to implement method for estimating optimal DTRs with survival endpoints subject to right-censoring which requires solving a series of weighted generalized estimating equations. We provide a proof of consistency that relies on the balancing property of the weights and derive a formula for the asymptotic variance of the resulting estimators. We illustrate our novel approach with an application to the treatment of rheumatoid arthritis using observational data from the Scottish Early Rheumatoid Arthritis Inception Cohort. Our method, called dynamic weighted survival modeling, has been implemented in the DTRreg R package. Supplementary materials for this article are available online.

精准医学的统计学研究聚焦于动态治疗方案（dynamic treatment regimes, DTRs），此类方案的治疗决策会根据患者个体信息进行定制。研究对象需接受多阶段临床随访干预，核心目标为对实际应用中拟采用的个性化治疗决策规则序列开展统计推断。本研究的核心目标之一是识别最优动态治疗方案，即能够带来最优期望结局的治疗决策序列。从观察性数据中识别最优动态治疗方案的统计方法理论复杂度较高，研究者难以直接实现，尤其当关注结局为生存时间时，该问题更为突出。针对存在右删失的生存终点下的最优动态治疗方案估计问题，我们提出了一种易于实现的双稳健方法，该方法需求解一系列加权广义估计方程。我们依托权重的平衡特性证明了所得估计量的相合性，并推导了其渐近方差的计算公式。我们采用苏格兰早期类风湿关节炎起始队列的观察性数据，将所提新方法应用于类风湿关节炎的治疗场景，以验证其实际效果。我们将所提方法命名为动态加权生存建模，该方法已在DTRreg R软件包中完成实现。本文的补充材料可在线获取。