Monitoring Fidelity of Online Reinforcement Learning Algorithms in Clinical Trials
This addresses the problem of safe and reliable deployment of autonomous algorithms in high-stakes healthcare settings for clinical researchers and algorithm developers, but it is incremental as it builds on existing RL methods with a focus on monitoring and planning.
The paper tackles the challenge of ensuring quality control and data integrity when deploying online reinforcement learning algorithms in clinical trials, proposing algorithm fidelity as a critical requirement and presenting a framework for pre-deployment planning and real-time monitoring, with practical application demonstrated in the Oralytics trial since Spring 2023.
Online reinforcement learning (RL) algorithms offer great potential for personalizing treatment for participants in clinical trials. However, deploying an online, autonomous algorithm in the high-stakes healthcare setting makes quality control and data quality especially difficult to achieve. This paper proposes algorithm fidelity as a critical requirement for deploying online RL algorithms in clinical trials. It emphasizes the responsibility of the algorithm to (1) safeguard participants and (2) preserve the scientific utility of the data for post-trial analyses. We also present a framework for pre-deployment planning and real-time monitoring to help algorithm developers and clinical researchers ensure algorithm fidelity. To illustrate our framework's practical application, we present real-world examples from the Oralytics clinical trial. Since Spring 2023, this trial successfully deployed an autonomous, online RL algorithm to personalize behavioral interventions for participants at risk for dental disease.