analiza aiqbench
This research demonstrates how Large Language Models can automate the translation of unstructured clinical guidelines into executable, interpretable computational models. By preserving guideline structure and enabling human inspection of intermediate artifacts, the approach offers a scalable solution for generating patient-specific medical recommendations without relying on extensive manual encoding. The study validates this pipeline using NICE cancer guidelines, achieving strong alignment with expert reviews and an F1 score of 82.5% on patient vignettes.
Automatic Conversion of NICE Guidelines to an Executable Computational Model Using Large Language Models
arXiv:2608.30022v1 Announce Type: new Abstract: Introduction: NICE guidelines provide evidence-based recommendations for clinical care but remain largely in unstructured natural language. Existing approaches to converting them into computable representations often focus on individual diseases, require substantial manual encoding, and do not scale. Large language models (LLMs) may enable much of this translation to be automated. Methods: We present an end-to-end approach that converts textual clinical guidelines into executable models capable of generating explainable, patient-specific recommendations. A stepwise LLM-based transformation with in-context examples produces human-inspectable intermediate artifacts. We apply the approach to NICE pancreatic and lung cancer guidelines, use expert review to assess rule alignment, and evaluate the executable pancreatic cancer model on 20 patient vignettes. Results: Expert review showed strong alignment between the source guidelines and generated executable models. Most discrepancies were partial omissions rather than incorrect logic, while hallucinated or fundamentally incorrect rules were rare. On the patient vignettes, the executable model achieved an F1 score of 82.5%. Conclusion: LLMs can transform natural-language NICE guidelines into interpretable, executable models that preserve guideline structure, support transparent inspection and modification, and generate patient-specific recommendations. These findings demonstrate the feasibility of scalable automated generation of computable clinical guidelines.
Abstract:Introduction: NICE guidelines provide evidence-based recommendations for clinical care but remain largely in unstructured natural language. Existing approaches to converting them into computable representations often focus on individual diseases, require substantial manual encoding, and do not scale. Large language models (LLMs) may enable much of this translation to be automated. Methods: We present an end-to-end approach that converts textual clinical guidelines into executable models capable of generating explainable, patient-specific recommendations. A stepwise LLM-based transformation with in-context examples produces human-inspectable intermediate artifacts. We apply the approach to NICE pancreatic and lung cancer guidelines, use expert review to assess rule alignment, and evaluate the executable pancreatic cancer model on 20 patient vignettes. Results: Expert review showed strong alignment between the source guidelines and generated executable models. Most discrepancies were partial omissions rather than incorrect logic, while hallucinated or fundamentally incorrect rules were rare. On the patient vignettes, the executable model achieved an F1 score of 82.5%. Conclusion: LLMs can transform natural-language NICE guidelines into interpretable, executable models that preserve guideline structure, support transparent inspection and modification, and generate patient-specific recommendations. These findings demonstrate the feasibility of scalable automated generation of computable clinical guidelines.
18 pages. Published in Learning Health Systems (2026)
Artificial Intelligence (cs.AI)
arXiv:2608.30022 [cs.AI]
(or arXiv:2608.30022v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.30022 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
Learning Health Systems, 2026, 10(4):e70114. PubMed lists the article in volume 10, issue 4
https://doi.org/10.1002/lrh2.70114 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 317 cuvinte
Subiecte conexe
Honest Abacus AI Review: ChatLLM, DeepAgent, AI Studio & More
KDnuggets · 4 aug. 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026
Podcast with Stephen DiAdamo, Co-founder and CTO of Qoro Quantum
Quantum Computing Report · 7 aug. 2026
Presentation: From Consumers to Builders: Turning 200 of our Team into Agent Creators in Two Weeks
InfoQ · 28 sept. 2026