Closing the Research Practice Gap in Personalized Medicine

• Activity Number: 383
• Type: Roundtables
• Date/Time: Tuesday, August 11, 2015 : 12:30 PM to 1:50 PM
• Sponsor: Mental Health Statistics Section
• Author(s): Eric Laber*
• Companies: North Carolina State University
• Keywords: Personalized medicine ; Subgroup identification ; Clinical trials ; Treatment regimes

Abstract

Individualized treatment selection has the potential to improve patient outcomes while reducing treatment burden and cost. Thus, there is keen interest among clinical and intervention scientists in estimating optimal treatment-selection strategies from observational or randomized studies. Statisticians have responded to this interest with a flurry of methodological development for individualized treatment selection in the form of (i) estimation of treatment regimes that map patient biomarkers to a recommended treatment and (ii) subgroup identification methods that identify a subset of the population likely to experience a large response to a specific treatment. Nevertheless, the translation from statistical methodology for treatment selection to actual clinical practice has been slow. The focus of this roundtable is on ways the statistics community can work to close the research practice gap in personalized medicine.