Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 125 - Novel Approaches for Estimating and Evaluating Treatment Rules with Applications in Mental Health Research
Type: Topic Contributed
Date/Time: Monday, August 3, 2020 : 1:00 PM to 2:50 PM
Sponsor: Mental Health Statistics Section
Abstract #312517
Title: A single index model for longitudinal outcomes to optimize individual treatment decision rules
Author(s): Lanqiu Yao* and Thaddeus Tarpey
Companies: New York University School of Medicine and NYU School of Medicine
Keywords: Single-index model; Precision medicine; Kullback-Leibler Divergence; Treatment decision rule
Abstract:

A pressing challenge in medical research is to identify optimal treatments for individual patients. This is particularly challenging in mental health settings where mean responses are often similar across multiple treatments. This talk investigates a potentially powerful precision medicine approach to this problem by examining the impact of baseline covariates on longitudinal outcome trajectories instead of scalar outcome measures. For example, on average, patients treated with an active drug versus placebo may have similar trajectories, but specific trajectory shapes may be unique to individuals treated with the active medication. We introduce a method of estimating “biosignatures” defined as linear combinations of baseline characteristics (i.e., a single index) that optimally separate longitudinal trajectories among different treatment groups. The criterion used is to maximize the Kullback-Leibler Divergences between different treatment outcome distributions. The approach is illustrated via simulation studies and a depression clinical trial. The comparison of the method with other approaches is also presented.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program