Evaluating Bayesian adaptive randomization procedures with adaptive clip methods for multi-arm trials

Response-adaptive randomization in clinical trials: from myths to practical considerations

Response-Adaptive Randomization (RAR) is part of a wider class of data-dependent sampling algorithms, for which clinical trials are typically used as a motivating application. In that context, patient allocation to treatments is determined by randomization probabilities that change based on the accrued response data in order to achieve experimental goals. RAR has received abundant theoretical attention from the biostatistical literature since the 1930's and has been the subject of numerous debates. In the last decade, it has received renewed consideration from the applied and methodological communities, driven by well-known practical examples and its widespread use in machine learning. Papers on the subject present different views on its usefulness, and these are not easy to reconcile. This work aims to address this gap by providing a unified, broad and fresh review of methodological and practical issues to consider when debating the use of RAR in clinical trials.

Bayesian two-stage sequential enrichment design for biomarker-guided phase II trials for anticancer therapies

Biomarker-guided phase II trials have become increasingly important for personalized cancer treatment. In this paper, we propose a Bayesian two-stage sequential enrichment design for such biomarker-guided trials. We assumed that all patients were dichotomized as marker positive or marker negative based on their biomarker status; the positive patients were considered more likely to respond to the targeted drug. Early stopping rules and adaptive randomization methods were embedded in the design to control the number of patients receiving inferior treatment. At the same time, a Bayesian hierarchical model was used to borrow information between the positive and negative control arms to improve efficiency. Simulation results showed that the proposed design achieved higher empirical power while controlling the type I error and assigned more patients to the superior treatment arms. The operating characteristics suggested that the design has good performance and may be useful for biomarker-guided phase II trials for evaluating anticancer therapies.

Identification of an optimal dose of intravenous ketamine for late-life treatment-resistant depression: a Bayesian adaptive randomization trial

Evidence supporting specific therapies for late-life treatment-resistant depression (LL-TRD) is necessary. This study used Bayesian adaptive randomization to determine the optimal dose for the probability of treatment response (≥50% improvement from baseline on the Montgomery-Åsberg Depression Rating Scale) 7 days after a 40 min intravenous (IV) infusion of ketamine 0.1 mg/kg (KET 0.1), 0.25 mg/kg (KET 0.25), or 0.5 mg/kg (KET 0.5), compared to midazolam 0.03 mg/kg (MID) as an active placebo. The goal of this study was to identify the best dose to carry forward into a larger clinical trial. Response durability at day 28, safety and tolerability, and effects on cortical excitation/inhibition (E/I) ratio using resting electroencephalography gamma and alpha power, were also determined. Thirty-three medication-free US military veterans (mean age 62; range: 55-72; 10 female) with LL-TRD were randomized double-blind. The trial was terminated when dose superiority was established. All interventions were safe and well-tolerated. Pre-specified decision rules terminated KET 0.1 (N = 4) and KET 0.25 (N = 5) for inferiority. Posterior probability was 0.89 that day-seven treatment response was superior for KET 0.5 (N = 11; response rate = 70%) compared to MID (N = 13; response rate = 46%). Persistent treatment response at day 28 was superior for KET 0.5 (response rate = 82%) compared to MID (response rate = 37%). KET 0.5 had high posterior probability of increased frontal gamma power (posterior probability = 0.99) and decreased posterior alpha power (0.89) during infusion, suggesting an acute increase in E/I ratio. These results suggest that 0.5 mg/kg is an effective initial IV ketamine dose in LL-TRD, although further studies in individuals older than 75 are required.