{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T11:27:17Z","timestamp":1787052437453,"version":"build-2736575974"},"reference-count":21,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/Y030974\/1"],"award-info":[{"award-number":["EP\/Y030974\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013342","name":"NIHR Imperial Biomedical Research Centre","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013342","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Learning Health Systems"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The UK National Institute for Health and Care Excellence (NICE) produce guidelines that provide evidence\u2010based recommendations to support clinical care across England and Wales, but remain available in unstructured natural language form. Converting these guidelines into computable, logically coherent representations is an active area of research yet existing approaches typically focus on individual diseases, require substantial manual encoding, and do not scale. Recent advances in large language models offer an opportunity to automate much of this translation process.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We present an end\u2010to\u2010end approach that automatically converts textual clinical guidelines into an executable model capable of generating explainable patient\u2010specific recommendations. Our approach uses a stepwise LLM\u2010based transformation with in\u2010context examples that can be customized to the guideline of your choice. Each step generates human\u2010inspectable intermediate artifacts, ensuring full transparency and modifiability. We apply the approach to both pancreatic and lung cancer NICE guidelines and use expert human review to assess the alignment of the produced rules as well as evaluating the executable model over 20 pancreatic cancer patient vignettes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Human experts review demonstrated strong alignment between the natural language guidelines and the generated executable models, with the majority of guideline recommendations translated correctly. Most discrepancies involved partial omissions of specific details rather than incorrect logic, and instances of hallucinated or fundamentally incorrect rules were rare. When executed on the vignettes, the resulting executable models produced patient\u2010specific recommendations with an\n                      <jats:italic>F<\/jats:italic>\n                      1 score of 82.5%.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This work demonstrates that LLMs can be used to automatically transform natural language NICE guidelines into interpretable and executable models. The models preserve guideline structure, allow transparent inspection and modification, and can be executed to generate patient\u2010specific recommendations. Our findings highlight the feasibility of automated guideline generation, opening the door to scalable computable guidelines.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/lrh2.70114","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T13:36:46Z","timestamp":1786714606000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Conversion of\n                    <scp>NICE<\/scp>\n                    Guidelines to an Executable Computational Model Using Large Language Models"],"prefix":"10.1002","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4966-525X","authenticated-orcid":false,"given":"Ashvin","family":"Gupta","sequence":"first","affiliation":[{"name":"Department of Computing Imperial College London  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denys","family":"Prociuk","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer and I\u2010X\/Digital Foundry Imperial College London  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandra","family":"Russo","sequence":"additional","affiliation":[{"name":"Department of Computing Imperial College London  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brendan C.","family":"Delaney","sequence":"additional","affiliation":[{"name":"Department of Surgery and Cancer and I\u2010X\/Digital Foundry Imperial College London  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjqs\u20102024\u2010017967"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjqs\u20102016\u2010005401"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169\u20102607(97)00034\u20105"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01133012"},{"key":"e_1_2_9_6_1","first-page":"645","volume-title":"Proceedings of the AMIA Symposium","author":"Peleg M.","year":"2000"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/lrh2.10394"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v37i3.2678"},{"key":"e_1_2_9_9_1","first-page":"1594","volume-title":"Proceedings of the 23rd AAAI Conference on Artificial Intelligence","author":"Lifschitz V.","year":"2008"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010024\u201001079\u20108"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci\u20102024\u2010101139"},{"key":"e_1_2_9_12_1","article-title":"Logic\u2010LM: Empowering Large Language Models With Symbolic Solvers for Faithful Logical Reasoning","author":"Pan L.","year":"2023","journal-title":"arXiv"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.24963\/kr.2024\/78"},{"key":"e_1_2_9_14_1","article-title":"LLM\u2010ARC: Enhancing LLMs With an Automated Reasoning Critic","author":"Kalyanpur A.","year":"2024","journal-title":"arXiv"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.24963\/kr.2023\/37"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1471068418000054"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl\u20102011\u2010000334"},{"key":"e_1_2_9_18_1","unstructured":"National Institute for Health and Care Excellence (NICE) \u201cPancreatic Cancer in Adults: Diagnosis and Management (NG85) \u201d7 February 2018 https:\/\/www.nice.org.uk\/guidance\/ng85."},{"key":"e_1_2_9_19_1","unstructured":"National Institute for Health and Care Excellence (NICE) \u201cSuspected Cancer: Recognition and Referral (NG12) \u201d23 June 2015 (updated January\/April 2026) https:\/\/www.nice.org.uk\/guidance\/ng12."},{"key":"e_1_2_9_20_1","unstructured":"National Institute for Health and Care Excellence (NICE) \u201cLung Cancer: Diagnosis and Management (NG122) \u201d28 March 2019 (updated 8 March 2024) https:\/\/www.nice.org.uk\/guidance\/ng122."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_2_9_22_1","unstructured":"NICE \u201cThe NICE Strategy 2021 to 2026 \u201dApril 2021 https:\/\/www.nice.org.uk\/about\/who\u2010we\u2010are\/corporate\u2010publications\/the\u2010nice\u2010strategy\u20102021\u2010to\u20102026."}],"container-title":["Learning Health Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lrh2.70114","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/lrh2.70114","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lrh2.70114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T10:31:13Z","timestamp":1787049073000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/lrh2.70114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":21,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/lrh2.70114"],"URL":"https:\/\/doi.org\/10.1002\/lrh2.70114","archive":["Portico"],"relation":{},"ISSN":["2379-6146","2379-6146"],"issn-type":[{"value":"2379-6146","type":"print"},{"value":"2379-6146","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]},"assertion":[{"value":"2025-08-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70114"}}