Individualized treatment rules (ITRs) tailor medical treatments according to patient-specific characteristics in order to optimize patient outcomes. Data from randomized controlled trials (RCTs) are used to infer valid ITRs using statistical and machine learning methods. However, RCTs are usually conducted under specific inclusion/exclusion criteria, thus limiting their generalizability to a broader patient population in real-world practice settings. Because electronic health records (EHRs) document treatment prescriptions in the real world, transferring information in EHRs to RCTs, if done appropriately, could potentially improve the performance of ITRs, in terms of precision and generalizability. In this work, we propose a new domain adaptation method to learn ITRs by incorporating information from EHRs. Unless we assume that there is no unmeasured confounding in EHRs, we cannot directly learn the optimal ITR from the combined EHR and RCT data. Instead, we first pre-train "super" features from EHRs that summarize physician treatment decisions and patient observed benefits in the real world, as these are likely to be informative of the optimal ITRs. We then augment the feature space of the RCT and learn the optimal ITRs by stratifying by super features using subjects enrolled in RCT. We adopt Q-learning and a modified matched-learning algorithm for estimation. We present heuristic justification of our method and conduct simulation studies to demonstrate the performance of super features. Finally, we apply our method to transfer information learned from EHRs of patients with type 2 diabetes to learn individualized insulin therapies from RCT data. This article is protected by copyright. All rights reserved.

中文翻译：

---

关于使用电子健康记录改进随机试验中的最佳治疗规则


个体化治疗规则（ITR）根据患者的具体特征定制医疗治疗，以优化患者的治疗结果。随机对照试验 (RCT) 的数据用于通过统计和机器学习方法推断有效的 ITR。然而，随机对照试验通常是在特定的纳入/排除标准下进行的，因此限制了它们在现实世界实践环境中对更广泛患者群体的普遍性。由于电子健康记录 (EHR) 记录了现实世界中的治疗处方，因此，如果处理得当，将 EHR 中的信息转移到随机对照试验中，可能会提高 ITR 的准确性和普遍性方面的性能。在这项工作中，我们提出了一种新的领域适应方法，通过合并来自 EHR 的信息来学习 ITR。除非我们假设 EHR 中不存在无法测量的混杂因素，否则我们无法直接从 EHR 和 RCT 数据组合中了解最佳 ITR。相反，我们首先预训练来自 EHR 的“超级”特征，这些特征总结了医生的治疗决策和患者在现实世界中观察到的益处，因为这些可能为最佳 ITR 提供信息。然后，我们扩大 RCT 的特征空间，并通过使用 RCT 中注册的受试者按超级特征进行分层来学习最佳 ITR。我们采用 Q 学习和改进的匹配学习算法进行估计。我们提出了我们的方法的启发式论证，并进行模拟研究来证明超级特征的性能。最后，我们应用我们的方法将从 2 型糖尿病患者的 EHR 中学到的信息转移到从 RCT 数据中学习个体化胰岛素治疗。本文受版权保护。版权所有。