{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:47:21Z","timestamp":1787014041983,"version":"build-2736575974"},"reference-count":28,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,4,5]],"date-time":"2026-04-05T00:00:00Z","timestamp":1775347200000},"content-version":"vor","delay-in-days":4,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100009560","name":"American Gastroenterological Association","doi-asserted-by":"publisher","award":["AGA2023\u201032\u201006"],"award-info":[{"award-number":["AGA2023\u201032\u201006"]}],"id":[{"id":"10.13039\/100009560","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Colorectal Disease"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background and Aims<\/jats:title>\n                    <jats:p>Clinical guidelines for inflammatory bowel disease (IBD) are essential for standardizing care, but synthesizing recommendations from multiple, often conflicting guidelines is a laborious task for clinicians. We developed and evaluated a proof\u2010of\u2010concept tool using a large language model (LLM) with retrieval\u2010augmented generation (RAG) to help clinicians navigate this complexity by harmonizing guidelines, identifying consensus and controversy, and generating actionable statements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>An LLM\u2010driven RAG pipeline (GPT\u20104o) was designed to segment guideline content and compare recommendations across four international guidelines (ACG, ECCO, BSG, ACPGBI). This tool was evaluated on eight common clinical questions in Crohn's disease and ulcerative colitis. Outputs were assessed against expert\u2010generated references by four independent reviewers using five\u2010point Likert scales for completeness, accuracy, relevance, coherence and conciseness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The tool reliably identified similarities and differences across guidelines, with mean scores of 4.34 (95% CI, 4.20\u20134.48) for consensus recognition and 4.61 (95% CI, 4.46\u20134.77) for disagreement detection. Completeness, accuracy and relevance consistently scored &gt;4.0, while conciseness was lower (3.84, 95% CI, 3.50\u20134.19). Outline generation performance was moderate (3.25, 95% CI, 2.85\u20133.65). In 87.5% of cases, tool\u2010generated recommendations aligned with expert conclusions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This proof\u2010of\u2010concept study demonstrates that an LLM\u2010RAG framework can systematically integrate IBD guidelines with high fidelity. This approach has the potential to improve guideline usability and support decision\u2010making at the point of care, though further refinement is needed for conciseness and comprehensive outline generation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/codi.70436","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T03:51:20Z","timestamp":1775447480000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Using large language models to integrate international\n                    <scp>IBD<\/scp>\n                    guidelines: A retrieval\u2010augmented generation approach"],"prefix":"10.1111","volume":"28","author":[{"given":"Aryan","family":"Salahi\u2010Niri","sequence":"first","affiliation":[{"name":"Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyed Amir Ahmad","family":"Safavi\u2010Naini","sequence":"additional","affiliation":[{"name":"Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences  Tehran Iran"},{"name":"Division of Data\u2010Driven and Digital Medicine Icahn School of Medicine at Mount Sinai  New York City New York USA"},{"name":"The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai  New York City New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jalpa","family":"Devi","sequence":"additional","affiliation":[{"name":"Washington University in St Louis  St Louis Missouri USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nariman","family":"Naderi","sequence":"additional","affiliation":[{"name":"Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences  Tehran Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaji","family":"Sebastian","sequence":"additional","affiliation":[{"name":"IBD Unit, Hull University Teaching Hospitals  Hull UK"},{"name":"Hull York Medical School, University of Hull  Hull UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michel","family":"Adamina","sequence":"additional","affiliation":[{"name":"Department of Visceral Surgery and Medicine, Inselspital Bern University Hospital, University of Bern  Bern Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Girish","family":"Nadkarni","sequence":"additional","affiliation":[{"name":"Division of Data\u2010Driven and Digital Medicine Icahn School of Medicine at Mount Sinai  New York City New York USA"},{"name":"The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai  New York City New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Soroush","sequence":"additional","affiliation":[{"name":"Division of Data\u2010Driven and Digital Medicine Icahn School of Medicine at Mount Sinai  New York City New York USA"},{"name":"The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai  New York City New York USA"},{"name":"Henry D. Janowitz Division of Gastroenterology Icahn School of Medicine at Mount Sinai  New York City New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alaa","family":"El\u2010Hussuna","sequence":"additional","affiliation":[{"name":"OpenSourceResearch Organization (OSRC.Network)  Aalborg Denmark"},{"name":"Helse Fona Hospital  Haugesund Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,4,5]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748-5908-7-62"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/ajg.2018.27"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-200108002-00002"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748-5908-7-67"},{"key":"e_1_2_12_6_1","doi-asserted-by":"crossref","unstructured":"BrouwersMC KerkvlietK SpithoffK NextA ConsortiumS.The AGREE Reporting Checklist: a tool to improve reporting of clinical practice guidelines checklist which was designed to improve the quality of practice guideline.2016.","DOI":"10.1136\/bmj.i1152"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjoq-2023-002595"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.2196\/55315"},{"key":"e_1_2_12_9_1","unstructured":"BrownTB MannB RyderN SubbiahM KaplanJ DhariwalP et\u00a0al.Language models are few\u2010shot learners.2020."},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf008"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01519-z"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/HEP.0000000000000834"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01091-y"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01391-3"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.14309\/ajg.0000000000000152"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/codi.14448"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/ecco-jcc\/jjab178"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/ecco-jcc\/jjab177"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/ecco-jcc\/jjz187"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/ecco-jcc\/jjz180"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2019-318484"},{"key":"e_1_2_12_22_1","unstructured":"LewisP PerezE PiktusA PetroniF KarpukhinV GoyalN et\u00a0al.Retrieval\u2010augmented generation for knowledge\u2010intensive NLP tasks. In: Advances in neural information processing systems.2020."},{"key":"e_1_2_12_23_1","article-title":"AI\u2010driven clinical decision support systems: an ongoing pursuit of potential","volume":"16","author":"Elhaddad M","year":"2024","journal-title":"Cureus"},{"key":"e_1_2_12_24_1","unstructured":"Harnessing RAG in Healthcare: Use\u2010Cases Impact & Solutions | HatchWorks AI [Internet]. Available from:https:\/\/hatchworks.com\/blog\/gen\u2010ai\/rag\u2010for\u2010healthcare\/"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00896-7"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02855-5"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01239-w"},{"key":"e_1_2_12_28_1","doi-asserted-by":"crossref","unstructured":"KruseM HuS DerbyN WuY StonbrakerS YaoB et\u00a0al.Zero\u2010shot Large Language Models for Long Clinical Text Summarization with Temporal Reasoning.2025. Available from:http:\/\/arxiv.org\/abs\/2501.18724","DOI":"10.1101\/2025.07.21.25331947"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13562"}],"container-title":["Colorectal Disease"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/codi.70436","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/codi.70436","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/codi.70436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:02:07Z","timestamp":1776747727000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/codi.70436"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/codi.70436"],"URL":"https:\/\/doi.org\/10.1111\/codi.70436","archive":["Portico"],"relation":{},"ISSN":["1462-8910","1463-1318"],"issn-type":[{"value":"1462-8910","type":"print"},{"value":"1463-1318","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"2025-10-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70436"}}