|
Activity Number:
|
94
- Building Innovative Ethical Health Care Systems via Sequential Approaches
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 8, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Mental Health Statistics Section
|
|
Abstract #320327
|
|
|
Title:
|
A Bayesian Decision-Theoretic Framework to Adaptively Estimate Minimum Effective Combinations of Sedentary Breaks to Reduce Cardiometabolic Risks: A Use Case of Adaptive Trial Design
|
|
Author(s):
|
Ying Kuen Ken Cheung* and Thevaa Chandereng and Keith M Diaz
|
|
Companies:
|
Columbia University and Columbia University and Columbia University
|
|
Keywords:
|
adaptive dose-finding;
Bayesian decision-theory;
glucose monitoring;
posterior gain;
sedentary breaks
|
|
Abstract:
|
We address the problem of estimating minimum effective combinations of multi-dimensional treatment or conditions. For context, we will describe a behavioral intervention study where we introduce sedentary breaks to participants to reduce their glucose and/or blood pressure over an 8-hour period under controlled environment. Each sedentary break regimen is defined by two elements: break frequency and break duration. The trial aims to identify minimum combinations of frequency and duration that shift these cardiometabolic parameters. We will describe a novel adaptive design (AD) based on Bayesian decision-theoretic framework for this study. Briefly, the method continuously updates the target combinations and enroll new participants based on these updates--according to two AD techniques: adaptive randomization and epsilon-tapering. We will discuss improvements due to AD in terms of false discovery rate and true positive rate relative to non-adaptive balanced randomization, and how the adaptive system addresses ethical concerns in terms of maximizing benefits of trial participants. We will also outline applicability of the method in a broader and pragmatic mental health system context.
|
Authors who are presenting talks have a * after their name.
