Using Population Crossover Trials to Improve the Decision Process Regarding Treatment Individualization in N-of-1 Trials

• Activity Number: 470 - Beyond Precision Medicine: Making It Personal with N-of-1 and Single Case Methods for Medicine, Rare Diseases, Digital Health, Behavior, and Wearables
• Type: Topic Contributed
• Date/Time: Wednesday, August 10, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Francisco J. Diaz*
• Companies: The University of Kansas Medical Center
• Keywords: Cross-over trials; Empirical Bayes; Individual Treatment Benefits; N-of-1 trials; Random effects linear models; Variance components

Abstract

There is renewed interest in N-of-1 clinical trials for the individualization of pharmacological treatments. We propose a frequentist approach to treatment individualization that we call “partial empirical Bayes.” We infer the most beneficial treatment for the patient from combining the information provided by a previously conducted population cross-over trial with individual patient data. We estimate the optimal number of treatment cycles and investigate statistical conditions under which N-of-1 trials are more beneficial than traditional clinical approaches. We represent the patient population with a random-coefficients linear model and calculate estimators of post-treatment individual disease severities. We show the estimators’ consistency under common N-of-1 designs and examine their prediction performance. Our approach is equivalent or superior to both administering the on-average best treatment to all patients and the common individualization method that simply compares average responses to the tested treatments. We conclude there are situations in which individualization with N-of-1 trials is highly beneficial while there are other situations in which it may be unfruitful.