|
Activity Number:
|
280
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #305432 |
|
Title:
|
A Bayesian Approach for Safety Monitoring in Clincal Trials
|
|
Author(s):
|
Gang Jia*+ and Xiaoming Li and Xin Zhao
|
|
Companies:
|
Merck & Co., Inc. and Merck Research Laboratories and Merck & Co., Inc.
|
|
Address:
|
351 N. Sumneytown Pike, North Wales, PA, 19454,
|
|
Keywords:
|
Clinical trial ; Safety monitoring ; Posterior predictive probability ; Serious adverse events ; interim analysis ; Data Monitoring Committee
|
|
Abstract:
|
Consider a trial in which subjects receive either an active treatment or a control and are followed for serious adverse events (SAE). An independent Data Monitoring Committee (DMC) provides continuous safety oversight throughout the study. To help the DMC to evaluate interim safety data, conditional power approach is often used to predict safety outcome based on pre-specified decision criteria. We propose a Bayesian method based on the concept of posterior predictive probability (PPP) to incorporate prior safety information obtained through previous research or other sources. The method will be evaluated under various scenarios in which different underlining distributions, choice of priors and other parameters will be assumed.
|
