Online Program Home
My Program

Abstract Details

Activity Number: 522 - Contributed Poster Presentations: Biometrics Section
Type: Contributed
Date/Time: Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract #304399
Title: A Bayesian Method for Preliminary Proof of Concept in Early Phase Oncology Studies with a Basket Design
Author(s): Lei Gao* and Jin Jin and Qianying Liu and Wei Zheng and Zhenming Shun and Tun Tun Lin and Yingwen Dong
Companies: Vertex Pharmaceuticals and Division of Biostatistics, University of Minnesota and Sanofi and Comprehend (Suzhou) Information Technology Inc and Daiichi Sankyo, Inc and Sanofi and Sanofi
Keywords: basket trials; Bayesian; hierarchical model; proof of concept; mixture model

In clinical development with biologics, PoC is a critical step that motivates later stage trials and profoundly impacts the CMC process. Early claim of PoC may save valuable time for the drug development. A new type of clinical trial called basket trial emerged recently. In the setting of oncology, experimental treatment targets an oncogenic pathway hypothesized to modulate the tumor growth and/or metastasis, and patients with the same genetic or molecular aberration but potentially multiple cancer types are enrolled. The problem of preliminary PoC is complicated with the early phase basket trials due to small sample size and large number of cancer types.

In this poster, we propose an approach for the assessment of preliminary PoC in early phase oncology basket trials under a Bayesian hierarchical modeling framework. We categorize cancer types into either an "active group" or an "inactive group", depending on observed response rates. We assess the preliminary PoC by the posterior probability that at least one cancer type is responsive. Simulation results are presented.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program