Activity Number:
|
624
- Trial Design and Analysis Issues in Medical Devices
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 3, 2017 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Medical Devices and Diagnostics
|
Abstract #324954
|
View Presentation
|
Title:
|
Bayesian Design Applications for Medical Devices Trials Using Power Prior
|
Author(s):
|
Songtao Jiang* and Peter Lam and Hong Wang
|
Companies:
|
Boston Scientific Corporation and Boston Scientific Corporation and Boston Scientific Corporation
|
Keywords:
|
Bayesian Statistics ;
Power Prior ;
Medical Device
|
Abstract:
|
In medical device trials, good prior information is often available because of similar mechanism of device action and evolutionary development of medical devices from generation to generation. The Power Prior method provides a mean to incorporate historical data into the analysis of current trials. In this paper, we retrospectively design an existing trial with the intention of borrowing historical data from previous studies. We lay out the borrowing strategies using the power prior discounting parameter through simulations, which are based on the existing trial assumptions. Then the trial results from the existing trial are presented for both designs. The potential benefits and risks are studied while comparing Bayesian trial design to this existing trial design. Different aspects of both designs are discussed and recommendations are made as a reference for future studies.
|
Authors who are presenting talks have a * after their name.