Bayesian Clinical Trials Designed and Conducted at the University of Texas M. D. Anderson Cancer Center (MDACC)

• Activity Number: 277
• Type: Topic Contributed
• Date/Time: Tuesday, July 31, 2007 : 10:30 AM to 12:30 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Swati Biswas and Diane D. Liu*+ and J. Jack Lee and Donald A. Berry
• Companies: University of North Texas Health Science Center and The University of Texas M.D. Anderson Cancer Center and The University of Texas M.D. Anderson Cancer Center and The University of Texas M.D. Anderson Cancer Center
• Keywords: Bayesian Design ; Clinical Trials ; CRM ; Adaptive Randomization

Abstract

We reviewed 964 protocols registered in MDACC Protocol Document Online System between 2000--2005. Of these, 59% were MDACC only trials, 38% were multicenter trials and 3% were CCOP trials. The numbers of clinical trials by phases are: I: 106, I/II: 66, II: 348, II/III: 6, III: 78, IV: 7, and others: 353. Bayesian designs accounted for 20% of the trials reviewed. A majority of Bayesian designs (90%) were applied in the phase I and II settings. Most commonly used Bayesian designs conducted at MDACC include the continuous reassessment method (CRM), adaptive randomization, and designs to monitor efficacy and toxicity simultaneously. We will describe various types of innovative Bayesian trial designs that have been conducted at MDACC.