We develop a prediction-based prescriptive model for learning optimal personalized treatments for patients based on their Electronic Health Records (EHRs). Our approach consists of: (i) predicting future outcomes under each possible therapy using a robustified nonlinear model, and (ii) adopting a randomized prescriptive policy determined by the predicted outcomes. We show theoretical results that guarantee the out-of-sample predictive power of the model, and prove the optimality of the randomized strategy in terms of the expected true future outcome. We apply the proposed methodology to develop optimal therapies for patients with type 2 diabetes or hypertension using EHRs from a major safety-net hospital in New England, and show that our algorithm leads to a larger reduction of the HbA1c, for diabetics, or systolic blood pressure, for patients with hypertension, compared to the alternatives. We demonstrate that our approach outperforms the standard of care under the robustified nonlinear predictive model.
翻译:我们开发了一个基于预测的规范模式,以学习基于其电子健康记录(EHRs)的病人的最佳个性化治疗。我们的方法包括:(一) 使用强健的非线性模型预测每一种可能的治疗方法的未来结果,以及(二) 采用由预测结果决定的随机性规范政策。我们展示了理论结果,保证了模型的超模预测力,并证明随机化战略在预期的将来真正结果方面是最佳的。我们运用了拟议方法,利用新英格兰主要安全网医院的EHRs为2型糖尿病或高血压患者制定最佳治疗方法,并表明我们的算法导致对高血压患者的HbA1c(糖尿病)或静脉血压比替代品更大幅度削减。我们证明我们的方法超过了在强健非线性预测模型下的护理标准。