Response-Adaptive Repeated Measurement Designs for Clinical Trials

In a response-adaptive design (RAD), we review and update the trial on the basis of outcomes in order to achieve a specific goal. Optimal designs for clinical trials are usually constructed under a single objective. In this paper, we develop a new adaptive allocation rule to improve the current strategies of building response adaptive designs to construct multiple-objective designs. The purpose of this new rule is to increase both estimation precision and treatment benefits by assigning more patients to a better treatment. We demonstrate that the designs constructed under the new proposed allocation rule are more efficient than fixed optimal designs in terms of both the mean squared error and improved patient care.