Logistic Growth Curve Modeling for Health-Related Quality-of-Life Data

• Activity Number: 473
• Type: Contributed
• Date/Time: Wednesday, August 4, 2010 : 8:30 AM to 10:20 AM
• Sponsor: Health Policy Statistics Section
• Author(s): Zugui Zhang*+ and Paul Kolm and William S. Weintraub
• Companies: Christiana Care Health System and Christiana Care Health System and Christiana Care Health System
• Keywords: Growth curve modeling ; Repeated binary responses ; Logistic modeling ; Quality of life ; Seattle Angina Questionnaire ; RAND-36

Abstract

In health related quality of life studies, repeated binary responses frequently arise since whether clinically significant improvement from baseline within individual patients was achieved over time is one of the most important outcomes. In this study, we explored logistic growth curve in analysis of COURAGE trial for modeling systematic within-patient change across a series of repeated measurements and between-patient differences in those changes. We examined growth curves of each domain in angina-specific health status (Seattle Angina Questionnaire) and overall physical and mental function (RAND-36) as a function of coronary intervention, to compare percutaneous coronary intervention plus optimal medical therapy in providing a clinically significant incremental quality of life benefit over optimal medical therapy in patients with chronic coronary artery disease.