时间✧：2019年8月15日上午9:30

地点🚴🏻‍♀️：学术会堂606会议室

报告题目🟪：Statistical methods for precisionmedicine with survival outcomes

报告人🤙🏽：Lihui Zhao, Associate Professor of Biostatistics, Department of PreventiveMedicine; Feinberg School of Medicine, Northwestern University

报告摘要💬：When comparing a new treatment to a control with a time-to-event endpoint in arandomized clinical study, the treatment effect is generally assessed byevaluating a summary measure over a specific study population. The success ofthe trial heavily depends on the choice of such a population. Furthermore,standard methods of summarizing the treatment difference are based onKaplan-Meier curves, the logrank test and the point and interval estimates via Cox's proportional hazards model. However, when the proportional hazardsassumption is violated, the logrank test may not have sufficient power todetect the difference between two event time distributions, and the resultinghazard ratio estimate is difficult, if not impossible, to interpret as atreatment contrast. In this research, we propose a systematic, effective way toidentify a promising subpopulation, for which the new treatment is expected tohave a desired survival benefit, using the data from a current study involvingsimilar comparator treatments. We illustrate the methods with the data from arandomized clinical trial.