报  告 人:李骏 教授

报告时间:2020/6/7 10:00-10:30

报告地点:腾讯会议,会议ID:996 600 647,会议密码:112358





Talk Title: Learning survival from EMR/EHR data to estimate treatment effects using high dimensional claims codes

Speaker: Prof. Ronghui XU

Time: 2020/6/7 10:30-11:10

Tencent Meeting Info: Conference ID: 996 600 647, PIN Code: 112358

Abstract: Our work was motivated by the analysis projects using the linked US SEER-Medicare database to studying treatment effects in men of age 65 years or older who were diagnosed with prostate cancer. Such data sets contain up to 100,000 human subjects and over 20,000 claim codes. The data were obviously not randomized with regard to the treatment of interest, for example, radical prostatectomy versus conservative treatment. Informed by previous instrumental variable (IV) analysis, we know that confounding most likely exists beyond the commonly captured clinical variables in the database, and meanwhile the high dimensional claims codes have been shown to contain rich information about the patients’ survival. Hence we aim to incorporate the high dimensional claims codes into the estimation of the treatment effect. The orthogonal score method is one that can be used for treatment effect estimation and inference assuming only consistency under the high dimensional hazards outcome model and the high dimensional conditional treatment model. In addition, we show that further refinement of the approach has doubly-robust properties in high dimensions including one on sparsity.

Bio: Xu earned her Ph.D. in mathematics and a master’s in applied mathematics from UC San Diego, and her bachelor’s in math from Nankai University, China.

She was a postgraduate researcher at the UCSD Cancer Center and in the Department of Mathematics, before becoming an Assistant Professor of Biostatistics at Harvard School of Public Health and the Dana-Farber Cancer Institute. Among her academic honors are being awarded as a Fellow of the American Statistical Association (ASA), and a recipient of the ASA David P. Byar Young Investigator Award.

Applying her data science and mathematical expertise to the emergence of biomedical Big Data, Xu utilizes machine learning methods to develop predictions, as well as statistical inference for complex data types. Her interdisciplinary work includes investigating such data analysis as competing risks of cancer versus non-cancer mortality, in the presence of high dimensional covariates. Her research also includes focus on causal inference methodology, for complex data types and for rare events such as in pregnancy safety data.




报  告 人:李骏 教授

报告时间:2020/6/7 19:00-19:30

报告地点:腾讯会议,会议ID:874 776 652,会议密码:112358









报  告 人:沈维孝 教授

报告时间:2020/6/7 19:40-20:10

报告地点:腾讯会议,会议ID:874 776 652,会议密码:112358


报告人简介:沈维孝,上海数学中心、复旦大学数学科学学院教授,研究领域为动力系统。他在低维动力系统及相关领域取得了一系列突破性成果,在顶尖数学期刊Ann Math和Invent Math上发表多篇论文。他是2009年中国数学会陈省身奖获得者,2014年国际数学家大会邀请报告人。






Address: No,2005 Songhu Road, Shanghai,China

Postcode: 200438 Tel: 021-31243880 Fax:021-31244000


Copyright @2016All Aight Reserved.Shanghai Center for Mathematical Sciences