The objective of this workgroup was to design and implement hybrid empirical/simulated experiments to compare the performance of methods for (1) disease risk score (DRS) development; and (2) incorporating DRSs for multiple outcomes into the analysis to improve inference. The workgroup evaluated different approaches for developing DRSs and used a novel ‘dry run’ analysis approach to compare multiple analytic methods. Understanding the optimal approaches to DRS development and application in the distributed data and multiple outcome setting is critical for moving forward with DRS analyses in Sentinel.
Rishi J. Desai, PhD, MS; Division of Pharmacoepidemiology and Pharmacoeconomics, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA
Justin Bohn, SD, SM; Yinzhu Jin, MS, MPH; Joshua J. Gagne, PharmD, ScD; Shirley V. Wang, PhD; Richie Wyss, PhD; Division of Pharmacoepidemiology and Pharmacoeconomics, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA
Austin Cosgrove, BS; Adee Kennedy, MPH, MS; Sengwee Toh, ScD; Department of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA
Sara Karami, PhD, MPH; Clara Y. Kim, PhD; Jessica Kim, PhD; Aaron Niman, MPH; Rita Ouellet-Hellstrom, PhD; Jacqueline M. Puigbo, PhD, MS; Center for Drug Evaluation and Research, FDA, Silver Spring, MD