LLM-Based Extraction of Clinical Practice Guidelines into Structured Arguments
Abstract
Clinical Practice Guidelines CPGs are the foundation of Evidence-Based Medicine but their long, complex and unstructured format makes them difficult to integrate in Clinical Decision Support Systems CDSS. While Large Language Models LLMs are great at reading text, their tendency to hallucinate and act as black boxes makes them unsafe for autonomous medical decisions. To solve this, we propose an automated pipeline that safely turns CPGs in raw PDF format into a structured, computable database of medical evidence expressed as formal arguments. First, we use computer vision to accurately extract complex tables and preserve the document’s layout. Then, we constrain the LLM using strict clinical frameworks PICO and Toulmin to guarantee that every extracted claim is traceable and accurate. Finally, we use clustering and pruning methods to remove duplicate information and organize the data. The result is a clean, trustworthy knowledge base that lays the essential groundwork for formal argumentation graphs and reliable CDSS.
Related
- Expert Consensus-Based Clinical Practice Guidelines for Care and Weaning Procedures in Tracheostomized ICU Patients after Invasive Mechanical Ventilation: A Joint Statement by the Intensive Care Physiotherapy Society (SKR) and the French Intensive Care Society (SRLF)
- CERVICAL CANCER: NATIONAL CLINICAL PRACTICE GUIDELINES FROM THE FRENCH CERVICAL CANCER GUIDELINES GROUP
- Updated Guidelines for Best Practice in the Audiological Management of Adults with Severe and Profound Hearing Loss.
- From guidelines to practice: Operational criteria for identifying old-growth forests in northern Europe
- Implementation of evidence-based practice guidelines to prevent urinary retention in hospitals: A process evaluation in orthopaedic care
BibTeX
@article{blouin2026llmbased,
title = {{LLM-Based Extraction of Clinical Practice Guidelines into Structured Arguments}},
author = {Robin Blouin and Karima Sedki and Jean-Baptiste Lamy},
journal = {Studies in Health Technology and Informatics},
year = {2026},
month = jun,
doi = {10.3233/shti260790},
url = {https://hal.science/hal-05709881v1},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - LLM-Based Extraction of Clinical Practice Guidelines into Structured Arguments
AU - Robin Blouin
AU - Karima Sedki
AU - Jean-Baptiste Lamy
PY - 2026
DA - 2026/06/29
JO - Studies in Health Technology and Informatics
DO - 10.3233/shti260790
UR - https://hal.science/hal-05709881v1
AB - Clinical Practice Guidelines CPGs are the foundation of Evidence-Based Medicine but their long, complex and unstructured format makes them difficult to integrate in Clinical Decision Support Systems CDSS. While Large Language Models LLMs are great at reading text, their tendency to hallucinate and act as black boxes makes them unsafe for autonomous medical decisions. To solve this, we propose an automated pipeline that safely turns CPGs in raw PDF format into a structured, computable database of medical evidence expressed as formal arguments. First, we use computer vision to accurately extract complex tables and preserve the document’s layout. Then, we constrain the LLM using strict clinical frameworks PICO and Toulmin to guarantee that every extracted claim is traceable and accurate. Finally, we use clustering and pruning methods to remove duplicate information and organize the data. The result is a clean, trustworthy knowledge base that lays the essential groundwork for formal argumentation graphs and reliable CDSS.
SN - 0926-9630
SN - 1879-8365
ER -