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.

翻译：为揭示临床观察数据中蕴含的医疗决策规律，本研究提出一种逆向强化学习（IRL）的创新应用，该方法通过对比临床同行行为来识别次优诊疗决策。该框架采用两阶段IRL架构，并引入中间步骤以剪除显著偏离共识行为的诊疗轨迹。基于包含最优与次优决策的重症监护室（ICU）数据，本方法能有效识别临床诊疗优先级与价值取向。研究发现：移除次优诊疗行为产生的效益存在疾病特异性，且对不同人口统计学群体产生差异化影响。