An Accelerated Failure Time Cure Model for Time-to-Event Data with Masked Cause of Failure

• Activity Number: 239
• Type: Contributed
• Date/Time: Tuesday, August 5, 2008 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Jing J. Zhang*+ and Molin Wang
• Companies: Harvard University and Dana Farber Cancer Institute and Harvard University
• Keywords: accelerated failure time model ; cure rate ; masked cause ; EM algorithm

Abstract

We consider the analysis of time-to-event data that is subject to a cure rate with masked cause of failure. Assuming an accelerated failure time model with unspecified error distribution for the time to event of interest, we propose rank-based estimating equations for the model parameters and use a generalization of the EM algorithm for parameter estimation. The motivation comes from an International Breast Cancer Study Group (IBCSG) clinical trial, where we characterize the process of treatment-induced amenorrhea (TIA), complicated by the fact that natural menopause may also occur and is indistinguishable from TIA unless a recovery of menses is observed after treatment end. Moreover, not all patients will experience TIA (cured proportion). A simulation study is conducted to evaluate the performance of the proposed method, and an application to the IBCSG data is undertaken.