A Semiparametric Approach for Meta-Analysis of Survival Curves from Orthopedic Registries

• Activity Number: 53
• Type: Invited
• Date/Time: Sunday, August 3, 2014 : 4:00 PM to 5:50 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Samprit Banerjee*+
• Companies: Weill Medical College of Cornell University
• Keywords: Meta-analysis ; Gaussian process ; survival

Abstract

Meta-analysis has received a lot of attention in the past few decades particularly in the health care sector where individual studies are smaller in size and it is useful to combine information from related but independent studies to conduct inference. Combining summary information from independent studies in a meta-analysis provides increased power to detect overall treatment effect, estimates the degree of benefit from a particular treatment and assesses the amount of variability between studies. My motivating example is a study of comparative effectiveness of medical devices used in hip-replacement and knee-replacement surgeries. The FDA initiative Medical Devices Epidemiology Network (MDEpiNet) including the International Consortium of Orthopedic Registries (ICOR) is being developed by world-wide registries with a team of researchers with Cornell as the Science and Infrastructure center. In this study, time to revision surgery, post hip-replacement surgery, is being examined as a survival outcome and data from 30+ US and international registries is being aggregated in a meta-analytic framework to conduct inference. Weighted average of hazard ratios is the most common method for