The Public Health Effects of DHA Supplementation on the Joint Distribution of Birthweight and Gestational Age with Implications on Clinical Trials Design and Analysis

• Activity Number: 572
• Type: Contributed
• Date/Time: Wednesday, August 1, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Byron Gajewski*+ and C. Shane Reese and John Colombo and Susan Carlson
• Companies: University of Kansas Medical Center and Brigham Young University and University of Kansas and University of Kansas Medical Center
• Keywords: Bayesian ; co-primary outcomes ; clinical trials

Abstract

Docosahexaenoic acid (DHA) is a long-chain polyunsaturated fatty acid member of the omega-3 fatty acid family. Evidence is accumulating that DHA is particularly important in early development. A recently completed phase III trial revealed higher birthweight and gestational age were associated with DHA. Our approach takes a posterior predictive approach to assess impacts of these findings on public health. However, more complicated statistical models are needed for accurate posterior predictive distributions. Of particular interest is a paper by Schwartz who discovered that the joint distribution of BW and GA is a mixture of three normal distributions. Remarkably, our own clinical trial has a very similar distribution. Using a prior distribution from Schwartz for mean and variance-covariance matrices but weak priors for the mixing parameters, we estimate the effect of DHA supplementation on the over 4,000,000 U.S. babies born each year. We discuss the statistical issues of our model on future clinical trials design and analysis.