Abstract:
|
In personalized medicine development, the patient population is thought of as a mixture of two or more subgroups that may derive differential treatment efficacy. In order to find the right patient population for the treatment to target, it is necessary to infer treatment efficacy in subgroups and combinations of subgroups through randomized clinical trials. How to correctly assess treatment efficacy in subgroups and their combinations can be nontrivial. It depends on the nature of efficacy measure as well as the estimation procedure. Focusing on the oncology trials with time-to-event outcomes, we show that the commonly used Hazard Ratio (between treatment and control) is not suitable to measure the efficacy in a mixture population. We also show that the current statistical practice of estimating the treatment efficacy in a mixture population has serious flaws. By proposing a subgroup mixable estimation principle, we develop a simultaneous inference procedure, with appropriate efficacy measures, to correctly infer treatment efficacy in a mixture population.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.