|
Activity Number:
|
198
- Innovations in Patient-Focused Clinical Trials
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 8, 2022 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #322607
|
|
|
Title:
|
Innovative Basket Trails Design Using BIC (Bayesian Hierarchical Mixed Model, Patient Information, Clustering)
|
|
Author(s):
|
Chenyang Duan* and Zheyu Liu and Christoph Neumann
|
|
Companies:
|
Oregon State University and Bayer and Bayer
|
|
Keywords:
|
Basket trial;
Bayesian hierarchical mixed modeling;
Patient Information;
Clustering
|
|
Abstract:
|
Basket study is a relatively recent development in oncology clinical trials that include patients who share a specific genetic mutation independent of the origin of cancer. Investigators not only wish to know whether the drug has efficacy across different cancer types but also to determine which types of cancer are more sensitive to the drug. We propose a statistical methodology for improving such basket trials by clustering the groups with the incorporation of patient information based on the drug efficacy and using a Bayesian hierarchical mixed modeling approach for each clustering if efficacy is deemed reasonably homogeneous across the clustering. This increases the power of the study and well control type-I-error by allowing groups with similar efficacy to borrow information from each other. We compare the efficiency of our approach and the classical approach via simulation and demonstrate substantial efficiency gain from the proposed design.
|
Authors who are presenting talks have a * after their name.
