Estimation of Treatment Policies Based on Functional Predictors

• Activity Number: 469
• Type: Topic Contributed
• Date/Time: Wednesday, August 7, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Mental Health Statistics Section
• Author(s): Ian McKeague*+ and Min Qian
• Companies: Columbia University and Columbia University
• Keywords: Empirical processes ; Functional data analysis ; Inverse treatment probability weighting ; Locally efficient estimation

Abstract

High-dimensional patient profiles based on biomedical images, mass spectrometry or gene expression might one day be used to guide treatment selection and improve outcomes. This talk discusses statistical methodology to assess the effectiveness of individualized treatment policies based on such profiles by interpreting them as functional predictors. We specify the interaction between the treatment and patient profile in terms of a parametric functional regression model. We then shown how data from randomized clinical trials can be used to simultaneously evaluate the effectiveness of the treatment policies (measured in terms of mean outcome when all patients follow the policy), and to identify features of patient profiles that optimize the interaction effect over competing treatments.