|
Activity Number:
|
315
- Advancements in Clinical Trial Design for Small Samples in the Age of Precision Medicine
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
|
Abstract #322075
|
View Presentation
|
|
Title:
|
The Use of Small N Sequential Multiple Assignment Randomized Trials (SnSMART) in Rare Disease Research
|
|
Author(s):
|
Roy N Tamura* and Kelley M Kidwell and Boxian Wei and Thomas Braun
|
|
Companies:
|
University of South Florida and University of Michigan and University of Michigan and University of Michigan
|
|
Keywords:
|
comparative effectiveness ;
rare disease ;
Bayes ;
bias ;
mean square error
|
|
Abstract:
|
Identifying optimal treatment for patients living with rare diseases is challenging due to the low number of individuals affected and the heterogeneity of patients within an individual type of disease. Recently, the Vasculitis Clinical Research Consortium of the NIH Rare Disease Network has designed a small n sequential multiple assignment randomized trial (snSMART) to examine three active drugs in the rare condition of isolated skin vasculitis. One of the goals of this trial is to make an overall recommendation for the best drug of those tested. This requires new statistical methodology to be developed for snSMARTs. In this talk, we will present both frequentist and Bayesian methods to help compare treatments. The link between various assumptions with potential outcomes and the resulting analyses will be highlighted. Simulations will be used to compare the statistical properties of the treatment effect estimates produced from our methods in the context of snSMARTs.
|
Authors who are presenting talks have a * after their name.
