Using R Shiny for Bayesian Prior Determination and Clinical Trial Design

Duration: 60 minutes


Webinar Recording

**For more information, please see PharmaLex Privacy Policy.

If you do not wish to receive any communication from us, you may unsubscribe at any time.


Why watch

Summary

Bayesian methods are becoming increasingly popular in the statistical design and analysis related to drug and medical device development.  In early phases, they permit borrowing from auxiliary data and expert opinion in order to reduce trial sample sizes and save valuable development time.  Their ability to deliver exact probability statements about the likelihood of safety, efficacy, and other key quantities makes them especially well-suited to predictions of late phase success, facilitating Go/No-Go and portfolio management decisions.  However, Bayesian methods do require the user to specify a prior distribution, as a starting point for the analysis.  In this webinar, we review the role and meaning of prior distributions, and how they can be elicited from past data and expert opinion.  We then show this information can then be utilized to power a Bayesian clinical trial using a new Shiny app written in the popular R language.  The app computes the design’s Type I error and power under both the elicitee’s informative prior, and a noninformative, reference prior.  Other applications and exemplification will also be included. 
 

Key Learnings

  •    Appreciation of the role of the prior distribution in Bayesian analysis, how it can affect the results, and how it can be readily derived
  •   Understanding of how informative prior distributions drive the Type I error and power of Bayesian adaptive clinical trial designs, and how this process is viewed by regulators
  •   Illustration of a new R Shiny app to carry out these two functions, and how it informs the proper sample sizes to use in Phase I, II, and III studies


     
speakers

A full hour of inspirational speaker(s)

Brad Carlin

Senior Advisor, Data Science, PharmaLex

Brad is a statistical researcher, methodologist, consultant, and instructor.  Prior to joining PharmaLex, he spent 27 years on the faculty of the Division of Biostatistics at the University of Minnesota School of Public Health, serving as division head for 7 of those years.  He has published more than 185 papers in refereed books and journals, and has co-authored three popular textbooks on Bayesian statistical methods and their applications in spatial statistics and adaptive clinical trials.  During his spare time, Brad is a health musician and bandleader, providing keyboards and vocals in a variety of venues.  He is excited and proud to be a part of the PharmaLex data science and statistics team.

 

Thomas de Marchin

Senior Manager, Statistics & Data Science 

Thomas joined the Statistics team after having graduated with a PhD in Biochemistry and Molecular Biology. Thomas’ experience of best laboratory practices as well as knowledge of advanced statistics have proved useful in helping Top 10 pharmaceuticals companies to improve their processes in aspects related to assays and drug development, manufacturing, and drug discovery. Besides, Thomas has overseen software sales and development while in charge of the Smart Statistical Software.

 

Clément Laloux

Specialist Statistics & Data Sciences, PharmaLex 

I have a background in business engineering (bachelor and master) where I specialized myself in supply chain management. During my master, I had the opportunity to do an internship at Pharmalex Belgium where I discovered statistics in its practical aspects as support to various business activities. This experience gave me the motivation to complete my formation with a master in Statistics. 
During both my internship and this second master, I worked and specialized on models to predict the recruitment in clinical trials. For my internship, I worked on developing a tool to use information from the predictions of the model to inform the supply chain (expected demand, production information…). For my master thesis in Statistics, I worked on the influence of prior on the predictions of ongoing clinical trials.
As a Specialist Statistics & Data Sciences, I’m providing statistical support on various fields of business, such as clinical, pharmaceutical, or cosmetical activities. The projects I worked on are notably related to method validation, study of treatment effects or reporting and exploratory studies in clinical trials.