独立LLM与预定义智能体流水线解释ICU死亡率预测的可行性研究
原标题：Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset
AI 摘要
马萨诸塞大学阿默斯特分校等机构的研究人员评估了独立LLM与预定义智能体流水线在解释ICU死亡率预测方面的可行性。基于eICU演示数据集（2353例ICU住院，死亡率8.1%），XGBoost模型AUROC为0.855。在38例解释子集上，独立LLM产生1例显式结果泄漏，而四步智能体流水线无泄漏；智能体流水线在指南依据、价值特异性和合理性方面得分更高，但SHAP对齐度较低。研究表明智能体分解可提升安全相关依据和患者特定细节，但需结合归因检查。
正文节选
Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset bUniversity of Massachusetts Amherst, Amherst, United States cUniversity of Pennsylvania, Philadelphia, United States dCarnegie Mellon University, Pittsburgh, United States eNew York University, Brooklyn, United States fWake Forest University, Winston-Salem, United States gNortheastern University, Boston, United States 1These authors contributed equally. *Cor