报告题目：Deep Learning Approaches for Individualized Causal Mediation Analysis with Survival Outcome

报告时间：2025年7月27日上午9:00

报告地点：北湖东校区激情视频 新楼216室

主办单位：激情视频 /科研处

报告人：宋心远

报告人简介：宋心远，博士生导师，香港中文大学教授，统计系系主任。获“长白山学者讲座教授”和教育部人才称号。主要研究方向为生存分析、潜变量模型、贝叶斯方法及其在医学、金融和社会学等领域内的应用。在具有国际影响力的顶级学术期刊发表SCI论文143 余篇，在Wiley出版重要英文学术专著1部，在6部英文专著中负责部分章节的编写工作。获批香港政府ECG(External Competitive Grant)-GRF(General Reach Fund)基金18项，国家自然科学基金面上项目3项。受邀参加国际会议(ICSA，COMPSTAT，IMS等)30余次，特别是2017年受德国心理测量学会年会(AMGPS)邀请，作为特邀报告人汇报潜变量在复杂数据上的应用。担任多家统计学领域顶级学术期刊如Structural Equation Modeling: A Multidisciplinary Journal(IF:4.426)、Psychometrika(IF:2.743)、Biometrics(IF:1.755)等副主编。截止2021年1月份，Google学术引用近3000次，h-index=30。

摘要：Causal mediation analysis aims to investigate the underlying mechanism of how an exposure exerts its effects on the outcome mediated by intermediate variables. However, existing methods for causal mediation analysis in the context of survival models are primarily focused on estimating average causal effects and are difficult to apply to precision medicine. Recently, machine learning has emerged as a promising tool for precisely estimating individualized causal effects without assuming specific model forms. This study proposes a novel method, conditional generative adversarial network (CGAN)-based individualized causal mediation analysis with survival outcomes (CGAN-ICMA-SO), to infer individualized causal effects with survival outcomes based on the CGAN framework. We show that the estimated distribution of the proposed inferential conditional generator converges to the true conditional distribution under mild conditions. Our numerical experiments indicate that CGAN-ICMA-SO surpasses existing state-of-the-art methods. Applying the proposed method to an Alzheimer's disease (AD) Neuroimaging Initiative dataset reveals the individualized direct and indirect effects of the APOE4 allele on time to AD onset.