Assessing the Effect of Treatment Strategies for Longitudinally Observed Outcome Data

• Activity Number: 439
• Type: Topic Contributed
• Date/Time: Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Sachiko Miyahara*+ and Abdus S. Wahed
• Companies: University of Pittsburgh and University of Pittsburgh
• Keywords: Dynamic Treatment Regimes ; Adaptive Treatment Strategies ; Longitudinal Data Analysis ; Mixed Models ; Missing Data

Abstract

Depression studies frequently adapt two-stage study designs to examine the efficacy of augmenting pharmacotherapy with psychotherapy. Initially, subjects receive one of the several treatments; if respond, they continue the same treatment; however, if they fail to respond, they move to the next stage and are randomized to other treatment options. Patients are then followed for 12 weeks during which Hamilton Depression (HAMD) score is collected repeatedly. The goal is to assess the effect of treatment regimes (consisting of initial treatment, initial response and the second stage treatment combinations) on HAMD profile. We propose several methods incorporating inverse probability weighting, mixed models, and multiple imputations to assess the effect of treatment regimes on the longitudinal HAMD scores. Methods are compared through simulation studies and application to a real data set.