用神经符号方法分析脓毒症治疗合规性，发现抗生素给药延迟最严重。
How Compliant is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generating Clinical Compliance Insights
- 大模型只做术语标准化，模糊推理系统处理临床规则判断
- 平均抗生素在1小时内给药率仅13%，首小时达标率36.7%
- 适合临床研究者与医疗质量评估人员参考
验证临床治疗是否符合循证指南是典型的神经符号问题，但安全关键场景下单一范式难以胜任。本文提出专家引导的管道：大语言模型仅执行语义归一化，将混乱的药物和微生物名称映射到固定临床词汇表；随后，基于Sugeno的模糊推理系统对归一化事件进行推理。该系统编码了八条生存脓毒症倡议（Surviving Sepsis Campaign）治疗包规则，将二元判断替换为[0,1]区间的评分。在2,438例MIMIC-IV v3.1脓毒症病例上的应用显示：抗生素给药时机是最大瓶颈（均值0.24，1小时内完成率仅13%），首小时达标率仅为36.7%，乳酸水平异常升高的患者中51%未及时干预，且高合规组与低合规组的重症监护住院时间差异显著（分别为3.8天与5.1天）。
原文摘要 · Abstract (English)
Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet the safety-critical setting defeats either paradigm alone. We present an expert-guided pipeline that constrains a large language model strictly to semantic normalization, mapping messy drug and microbiology strings onto a fixed clinical vocabulary, while a Sugeno fuzzy inference system reasons over the normalized events. The fuzzy layer encodes eight Surviving Sepsis Campaign bundle rules and replaces binary judgments with graded scores in [0,1]. Applied to 2,438 MIMIC-IV v3.1 sepsis episodes, it surfaces antibiotic timing as the most critical breakdown (mean 0.24, 13% within one hour), Hour-1 underperformance (mean 36.7%), a 51% elevated-lactate drop-off, and descriptive differences in ICU stay across compliance groups (3.8 versus 5.1 days).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。