Response adaptive randomization and biomarker-based trial designs for addressing patient heterogeneity in personalized medicine
Abstract
A response-adaptive randomization (RAR) design refers to the method in which the probability of treatment assignment changes according to how well the treatments are performing in the trial. Holding the promise of treating more patients with the better treatments, RARs have been successfully implemented in clinical trials. We compared equal randomization (ER) with three RARs: Bayesian adaptive randomization, sequential maximum likelihood, and sequential posterior mean. We fixed the total number of patients, considered as patient horizon, but varied the number of patients in the trial. Among the designs, we compared the proportion of patients assigned to the superior arm, overall response rate, statistical power, and total patients enrolled in the trial with and without adding an efficacy early stopping rule. Then, we examined three variations of response RAR and compare their operating characteristics. A power transformation is applied to refine the randomization probability. The clip method is used to bound the randomization probability within specified limits. A burn-in period of ER can added before AR. Last, we developed a statistical model in the hierarchical Bayesian scheme to estimate the treatment and biomarker effects. The Bayesian framework applying the hierarchical structure with adding the prior assumptions on the model parameters could be used to provide the estimations of parameters with limited data or sparse data. Furthermore, depending on the hierarchical model, we can borrow information across different biomarker groups within a treatment. Moreover, we applied the meta-analysis to combine the single patient (N-of-1) trials to investigate the personalized treatment effects. By providing more rigorous assessment of treatments effectiveness for an individual, single patient (N-of-1) trials offer a structured approach to provide the patient-focused and evidence-based treatment designs. Generally, such single-patient trials are designed to evaluate individual patient responses to the treatment(s) and then to estimate the population treatment effects.
Subject Area
Biostatistics
Recommended Citation
Du, Yining, "Response adaptive randomization and biomarker-based trial designs for addressing patient heterogeneity in personalized medicine" (2014). Texas Medical Center Dissertations (via ProQuest). AAI3723360.
https://digitalcommons.library.tmc.edu/dissertations/AAI3723360