Pruning the Path to Optimal Care: Identifying Systematically Suboptimal Medical Decision-Making with Inverse Reinforcement Learning
This work addresses the problem of improving medical decision-making for clinicians and patients by identifying systematic suboptimalities, though it is incremental as it builds on existing IRL techniques.
The paper tackled the problem of identifying suboptimal medical decisions in clinical data by applying a novel two-stage Inverse Reinforcement Learning method with trajectory pruning, resulting in insights that the impact of removing suboptimal actions varies by disease and demographic groups.
In aims to uncover insights into medical decision-making embedded within observational data from clinical settings, we present a novel application of Inverse Reinforcement Learning (IRL) that identifies suboptimal clinician actions based on the actions of their peers. This approach centers two stages of IRL with an intermediate step to prune trajectories displaying behavior that deviates significantly from the consensus. This enables us to effectively identify clinical priorities and values from ICU data containing both optimal and suboptimal clinician decisions. We observe that the benefits of removing suboptimal actions vary by disease and differentially impact certain demographic groups.