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 #312943
|
|
Title:
|
A Tree-Based Method for Discovering Response Trajectory Subgroups Based on Scalar and Functional Variables
|
Author(s):
|
Adam Ciarleglio*
|
Companies:
|
George Washington University
|
Keywords:
|
personalized medicine;
trees;
functional data;
depression
|
Abstract:
|
Antidepressant treatment effects are heterogeneous among people with depression. The ability to identify subgroups of depressed subjects who will benefit most from a particular treatment would be a step towards optimizing antidepressant treatment delivery. While the treatment effect in many antidepressant clinical studies is defined by a subject’s response at the end of the study relative to their baseline value, it may be more appropriate to assess the subject’s complete treatment response trajectory over the course of the study. We propose a tree-based method with nodes corresponding to baseline scalar and functional data for discovery of easily interpretable subgroups of subjects whose treatment responses over the course of a study follow similar trajectories. We evaluate the proposed method in a simulation study and apply it to data from a randomized, placebo-controlled antidepressant treatment study with a large collection of baseline clinical and neuroimaging measures available.
|
Authors who are presenting talks have a * after their name.