Evaluation of Machine Learning Approaches for Estimating Individualized Treatment Regimens for Time-to-Event Outcomes in Observational Studies

In this paper we provide an overview and evaluation of machine learning methods for estimating individualized treatment regimens (ITR) for time-to-event outcomes through maximizing restricted mean survival time (RMST) in observational studies with non-randomized treatment assignment. We present extensive simulation studies that closely mimicked real-world data under a set of scenarios representing different degrees of alignment between the observed regimen, which reflects the actual prescribing practice, and the optimal ITR. The simulation results include performance characteristics of the candidate methods in terms of their ability to recover the optimal ITR and various empirical measures of RMST gain based on the comparison between the estimated ITR and the actual prescribing practice. Direct methods for estimating ITR for survival outcomes did not show advantages over indirect methods based on predicted potential outcomes under our implementation and simulation settings. Among indirect methods, gradient boosting for estimating potential survival outcomes has an advantage over random survival forests and parametric methods. Estimating the value of estimated ITRs and associated gains over the actual prescribing practice remains a challenging problem, especially under complex confounding scenarios when either most patients do not receive optimal treatment or when the actual treatment assignments are already close to optimal.

本研究概述并评估了一类机器学习方法，该类方法用于在治疗分配非随机化的观察性研究中，通过最大化受限平均生存时间（restricted mean survival time, RMST）来估计针对事件发生时间结局的个体化治疗方案（individualized treatment regimens, ITR）。我们开展了大规模模拟研究，这些模拟严格复刻了真实世界数据场景，且场景涵盖了反映实际处方实践的观测治疗方案与最优ITR之间的不同对齐程度。模拟结果包含了候选方法的多项性能特征，具体包括其恢复最优ITR的能力，以及基于估计ITR与实际处方实践对比得到的各类受限平均生存时间增益的经验度量指标。在本次实现与模拟设置下，针对生存结局的直接ITR估计方法并未展现出优于基于预测潜在结局的间接方法的性能。在间接方法中，用于估计潜在生存结局的梯度提升算法性能优于随机生存森林与参数化方法。估计个体化治疗方案的价值及其相较于实际处方实践的增益仍是一项极具挑战性的问题，尤其是在复杂混杂场景下——当多数患者未接受最优治疗，或实际治疗分配已接近最优状态时，该问题尤为突出。