Online Program Home
My Program

Abstract Details

Activity Number: 689
Type: Topic Contributed
Date/Time: Thursday, August 4, 2016 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract #320463
Title: Estimating the Optimal Treatment Regime for Time-to-Event Data
Author(s): Min Zhang* and Baqun Zhang
Companies: University of Michigan and Renmin University of China
Keywords: Personalized medicine ; restricted mean lifetime ; Survival time ; treatment regime ; censoring

A treatment regime is a rule that assigns a treatment, from among a set of possible treatments, to a patient based on his/her characteristics. The recent literature has seen much development in methodologies for estimating the optimal treatment regime. The majority of the methodological development has been focused on continuous responses. In this paper, we propose a method to estimate the optimal treatment regime for survival outcomes, where the optimal treatment regime is defined as the one that maximizes the restricted mean lifetime across all feasible regimes. We propose a direct optimization method that estimates the optimal treatment regime by optimizing the value of regimes. This direct optimization method is able to incorporate outcome-regression model (Cox model) to improve efficiency of estimation. However, as a direct optimization method as opposed to outcome-regression based method, the performance of the method is less sensitive to misspecification of the outcome regression model and enjoys certain robustness property. The method will be evaluated by extensive simulation studies and illustrated by a real data application.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association