Scholarlink

Clinical Practice Guidelines (CPGs) are continually updated, yet translating such narrative recommendations into formal Care Pathway (CPW) processes remains labor-intensive and prone to inconsistency. We introduce a modular, end-to-end extraction pipeline that leverages Large Language Model (LLM) frameworks to automatically generate and evaluate BPMN models of CPWs from CPG text. Our system standardizes different output formats, applies LLM-based label alignment to harmonize terminology, and evaluates models against reference models using node- and structural-similarity metrics. Experiments on four stroke-related CPGs, using two state-of-the-art LLM frameworks—ProMoAI and a multi-agent orchestration approach (MAO)—shows the feasibility of automated CPW process extraction. We further observe that the multi-agent framework (MAO) demonstrates markedly higher fidelity. A web-based UI supports experiment configuration and result inspection. We released all code, prompts, and datasets as open-source to promote reproducibility and future enhancements.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An LLM Pipeline for Automatic Extraction and Evaluation of Care Pathways from Clinical Guidelines

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Alireza Houshidari,
  • William Van Woensel,
  • Daniel Amyot,
  • El Mostafa Bouattane

摘要

Clinical Practice Guidelines (CPGs) are continually updated, yet translating such narrative recommendations into formal Care Pathway (CPW) processes remains labor-intensive and prone to inconsistency. We introduce a modular, end-to-end extraction pipeline that leverages Large Language Model (LLM) frameworks to automatically generate and evaluate BPMN models of CPWs from CPG text. Our system standardizes different output formats, applies LLM-based label alignment to harmonize terminology, and evaluates models against reference models using node- and structural-similarity metrics. Experiments on four stroke-related CPGs, using two state-of-the-art LLM frameworks—ProMoAI and a multi-agent orchestration approach (MAO)—shows the feasibility of automated CPW process extraction. We further observe that the multi-agent framework (MAO) demonstrates markedly higher fidelity. A web-based UI supports experiment configuration and result inspection. We released all code, prompts, and datasets as open-source to promote reproducibility and future enhancements.