Personalized Medicine: Better Treatment for the Patient or the Right Patient for the Treatment?

• Activity Number: 587
• Type: Invited
• Date/Time: Thursday, August 7, 2014 : 8:30 AM to 10:20 AM
• Sponsor: ENAR
• Author(s): Eric B. Laber*+ and Martin Posch*+ and Stephen J. Ruberg*+ and Sandeep Menon*+ and Ilya Lipkovich*+ and Alex Dmitrienko*+
• Companies: North Carolina State University and Medical University of Vienna and Eli Lilly and Company and Pfizer and Quintiles and Quintiles
• Keywords: Dynamic treatment regimes ; Sample size formulae ; Nonregular estimation

Abstract

A personalized treatment strategy formalizes evidence-based treatment selection by mapping patient information to a recommended treatment. Personalized treatment strategies can lead to better patient outcomes while simultaneously reducing cost and treatment burden. Thus, there is a growing interest among clinical and intervention scientists in conducting randomized clinical trials with the primary aim of estimating an optimal personalized treatment strategy. At present there are no appropriate sample size formulae to assist in the design of such a trial. Furthermore, because the distribution of the estimated outcome under an estimated optimal treatment strategy can be highly sensitive to small perturbations in the generative model, sample size calculations based on standard asymptotic approximations or computer simulations may not be reliable. We offer a simple and robust method for powering a two-armed randomized clinical trial when the primary aim is estimating the optimal personalized treatment strategy. The proposed method inverts a plugin projection confidence interval and is thereby regular and robust to small perturbations of the underlying generative model.