Opening the Doors to Open Source Programming in Drug Development

• Activity Number: 100
• Type: Invited
• Date/Time: Monday, August 5, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Narinder K, Nangia*+ and Annie Wang
• Companies: AbbVie , Inc. and Astellas
• Keywords: Bayesian ; OpenBUGS ; BRugs ; Probability of Success ; Clinical Trial

Abstract

Testing of hypothesis of no treatment effect at the end of a learning stage study (a proof of concept or a dose-ranging study) is an inefficient approach as these studies are generally powered with little or no information on the unknown treatment effect. It is very important to exploit totality of data for characterizing the dose-response curve, estimating treatment effect and probability of success at an interim stage (or at the end of the study) to facilitate early decision-making about further development of the experimental drug candidate. A Bayesian dose-response model developed for real time monitoring of the probability of success can be implemented using R and OpenBUGS through BRugs. However, there are questions about the underlying assumptions on parameters of the reference model and the validity of the results when an important decision needs to be made about stopping or continuing development of the drug. This presentation will address the validation of the open source algorithm and the sensitivity of the parameter assumptions in the model.