Concordance Matched Learning for Estimating Optimal Individualized Treatment Regimes with Multiple Treatments

发布时间：2020-12-07 作者：浏览次数：

Speaker:	朱文圣	DateTime:	2020年12月9日（周三）下午19:30-20:30
Brief Introduction to Speaker: 朱文圣，东北师范大学教授、博士生导师。		Place:	腾讯会议（会议号请联系左国新老师索取）
Abstract:Precision medicine has drawn tremendous attention recently to account for significant heterogeneity in the response of different patients to the same treatment. The estimation of the optimal individualized treatment regime (ITR) is of great concern to precision medicine, which is aim to recommend a treatment regime based on patient-specific characteristics by maximizing the expected clinical outcome. In recent statistical literatures, there is a large and growing body of different statistical methods to estimate optimal individualized treatment regimes. Most of the existing statistical methods are mainly focus on the estimation of optimal individualized decision rules for the two categories of treatment options and rely heavily on data from randomized controlled trials. In this talk, we propose a machine learning approach (CM-learning) to estimate optimal treatment regime from multicategorical treatment options.