How Consistent are Clinicians? Evaluating the Predictability of Sepsis Disease Progression with Dynamics Models

arXiv:2404.07148v1 Announce Type: new
Abstract: Reinforcement learning (RL) is a promising approach to generate treatment policies for sepsis patients in intensive care. While retrospective evaluation metrics show decreased mortality when these policies are followed, studies with clinicians suggest their recommendations are often spurious. We propose that these shortcomings may be due to lack of diversity in observed actions and outcomes in the training data, and we construct experiments to investigate the feasibility of predicting sepsis disease severity changes due to …

abstract arxiv clinicians consistent cs.hc cs.lg disease dynamics evaluation evaluation metrics generate metrics mortality patients policies recommendations reinforcement reinforcement learning retrospective sepsis show studies treatment type