Methods for Time-to-Event Analysis with Changepoint

• Activity Number: 36
• Type: Contributed
• Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Sayan Dasgupta* and Ying Qing Chen
• Companies: and Fred Hutchinson Cancer Research Center
• Keywords: additive hazards ; HIV ; changepoint

Abstract

In randomized clinical trials, the additive hazards model has increasingly become an appealing alternative to the widely used proportional hazards model in treatment effectiveness assessment for censored time-to-event endpoint. It can feature an additive invariance in marginalizing over latent variables. Motivated by developing data monitoring plan for a landmark HIV/AIDS clinical trial of antiretroviral therapy management, we conduct treatment comparisons using the additive hazards model with potential latent changepoint. We also explore the ability of the proposed model in designing group sequential monitoring of a clinical trial like such, and to develop monitoring boundaries at real-time interim looks.