Estimation of the Optimal Regime in Treatment of Prostate Cancer Recurrence from Observational Data Using Flexible Weighting Models

• Activity Number: 530
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Jincheng Shen*+ and Lu Wang and Jeremy Taylor
• Companies: University of Michigan and Univeristy of Michigan and University of Michigan
• Keywords: Optimal Regime ; MSM ; IPCW

Abstract

In clinical prostate cancer treatment, in order to manage the recurrence, patients after the initial radiotherapy are always closely monitored for elevated prostate-specific antigen (PSA) level. Decision for salvage treatment is always made based on PSA among other longitudinal factors that are associated with the risk of recurrence. Specific guidelines such as when should a therapy be judged as a failure and when is the optimal time to start salvage therapy would be very useful in clinical practice. We here focus on how to identify the optimal salvage treatment regime from the observational data. Following Orellana et al. 2010, we employ the marginal structural models (MSM) method to extrapolate and identify the optimal treatment effect among different treatment regimes in terms of prolonging patients' recurrence-free survival. In order to accommodate for the complexity in modeling various regime rules, we proposed a nonparametric model to provide the necessary flexibility. Weighted Kaplan-Meier estimator is adopted in simulation studies to assess the performance of the weighting scheme. We also illustrate the application of this method in an observational prostate cancer dataset.