Monitoring Fidelity of Online Reinforcement Learning Algorithms in Clinical Trials

arXiv:2402.17003v1 Announce Type: new
Abstract: 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 …

abstract algorithm algorithms arxiv autonomous clinical clinical trials control cs.ai cs.cy cs.lg data data quality fidelity healthcare monitoring online reinforcement learning paper quality reinforcement reinforcement learning treatment type