{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T17:30:08Z","timestamp":1785864608245,"version":"3.56.0"},"posted":{"date-parts":[[2026,6,26]]},"group-title":"Gastroenterology","reference-count":18,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T00:00:00Z","timestamp":1782432000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Large language models (LLMs) offer promise for systematic review data extraction, but performance in complex multidisciplinary domains and utility for clinical statement generation remain insufficiently described.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>To evaluate Google NotebookLM for AI-assisted data extraction and RAND\/UCLA consensus statement generation in a systematic review of IBD, obesity, and cardiometabolic comorbidities.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Studies were organized into domain-specific notebooks; structured prompts generated standardized evidence tables. Two independent reviewers validated outputs against full-text articles using a four-category error classification. Cell-level accuracy and critical accuracy (cells free of major factual errors) were the primary metrics; workflow time was compared against a published conventional extraction benchmark. Concordance between AI-generated and expert-finalized statements was assessed.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Across 57 articles, 1,710 data cells were extracted; 151 (8.83%) were flagged, yielding 91.17% cell-level accuracy. Major factual errors occurred in only 4 cells (0.23%), for a critical accuracy of 99.77%. Most errors were minor omissions (59.6%) or incomplete extractions (30.5%); domain error rates ranged from 7.08% to 11.33%. The pipeline required 17.7 versus a projected 165.1 person-hours (89.3% reduction). PICO-structured prompting generated 70 candidate statements; 58 of 112 finalized panel statements (51.8%) were AI-derived, and 85.7% were retained in the finalized set.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Google NotebookLM demonstrates feasibility as a primary extraction and synthesis tool in a multidisciplinary systematic review, with extractive incompleteness as the principal limitation and substantial time savings over conventional approaches. Its novel application to RAND\/UCLA consensus statement generation extends AI-assisted evidence synthesis to clinical consensus generation workflow.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.06.16.26355773","type":"posted-content","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T23:15:14Z","timestamp":1782515714000},"source":"Crossref","is-referenced-by-count":1,"title":["Performance of Google NotebookLM for AI-assisted data extraction and consensus statement generation in a heterogenous systematic review on inflammatory bowel disease, obesity, and cardiometabolic comorbidities: A Methodological Report"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6437-5062","authenticated-orcid":false,"given":"Sami","family":"Samaan","sequence":"first","affiliation":[{"name":"Division of Gastroenterology, WashU Medicine, Saint Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8710-2381","authenticated-orcid":false,"given":"Jalpa","family":"Devi","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, University of Nebraska Medical Center, Omaha, NE, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Vincent","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, WashU Medicine, Saint Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1591-1507","authenticated-orcid":false,"given":"Shannon","family":"Coombs","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, WashU Medicine, Saint Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2611-2767","authenticated-orcid":false,"given":"Priya","family":"Sehgal","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology and Hepatology, Thomas Jefferson University Hospital, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4761-8014","authenticated-orcid":false,"given":"Mouhand","family":"Mouhamed","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, MN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1001-9974","authenticated-orcid":false,"given":"Victoria","family":"Rai","sequence":"additional","affiliation":[{"name":"Yale School of Medicine, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2838-0538","authenticated-orcid":false,"given":"Amanda M.","family":"Johnson","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, MN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2293-5555","authenticated-orcid":false,"given":"Andres J.","family":"Yarur","sequence":"additional","affiliation":[{"name":"F. Widjaja Inflammatory Bowel Disease Institute, Cedars Sinai Medical center, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9894-8796","authenticated-orcid":false,"given":"Edward L.","family":"Barnes","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology and Hepatology, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3436-9784","authenticated-orcid":false,"given":"Parakkal","family":"Deepak","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, WashU Medicine, Saint Louis, MO, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026062904401449000_2026.06.16.26355773v1.1","doi-asserted-by":"crossref","unstructured":"Higgins JPT , T.J., Chandler J , Cumpston M , Li T , Page MJ , et al, editor(s), Cochrane Handbook for Systematic Reviews of Interventions. 2nd Edition. Chichester (UK): John Wiley & Sons, 2019. 2024.","DOI":"10.1002\/9781119536604"},{"key":"2026062904401449000_2026.06.16.26355773v1.2","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-015-0066-7"},{"key":"2026062904401449000_2026.06.16.26355773v1.3","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-017-0431-4"},{"key":"2026062904401449000_2026.06.16.26355773v1.4","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2021-069155"},{"issue":"3","key":"2026062904401449000_2026.06.16.26355773v1.5","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1002\/jrsm.1553","article-title":"Using artificial intelligence methods for systematic review in health sciences: A systematic review","volume":"13","year":"2022","journal-title":"Res Synth Methods"},{"key":"2026062904401449000_2026.06.16.26355773v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2021.12.005"},{"issue":"4","key":"2026062904401449000_2026.06.16.26355773v1.7","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1002\/jrsm.1710","article-title":"Data extraction for evidence synthesis using a large language model: A proof-of-concept study","volume":"15","year":"2024","journal-title":"Res Synth Methods"},{"key":"2026062904401449000_2026.06.16.26355773v1.8","doi-asserted-by":"crossref","first-page":"102192","DOI":"10.1016\/j.smrv.2025.102192","article-title":"Accuracy of large language models in data extraction from randomized controlled trials in sleep medicine: A proof-of-concept study","volume":"84","year":"2025","journal-title":"Sleep Med Rev"},{"key":"2026062904401449000_2026.06.16.26355773v1.9","doi-asserted-by":"crossref","unstructured":"Devi, J. , et al., Modulate Obesity and relateD metabolic complIcations For Yielding improvements in IBD outcomes (MODIFY-IBD): Consensus on Obesity and Cardiometabolic Comorbidities in Inflammatory Bowel Disease using Evidence Synthesis and the RAND\/UCLA Appropriateness Method. medRxiv, 2025.","DOI":"10.64898\/2025.12.20.25342738"},{"key":"2026062904401449000_2026.06.16.26355773v1.10","doi-asserted-by":"crossref","unstructured":"Page, M.J. , et al., The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ, 2021. 372: p. n71.","DOI":"10.1136\/bmj.n71"},{"key":"2026062904401449000_2026.06.16.26355773v1.11","unstructured":"Jalpa Devi , S.S., Matthew Vincent , Michelle Doering , Edward L. Barnes , Andres J. Yarur , Amanda M. Johnson , Parakkal Deepak , Management of Overweight, Obesity, and Cardiometabolic Comorbidities in Inflammatory Bowel Disease: A Systematic Review. PROSPERO 2025 CRD420251174653, 2025."},{"key":"2026062904401449000_2026.06.16.26355773v1.12","doi-asserted-by":"crossref","unstructured":"van Kessel, R. , et al., Omission and hallucination prevalence of clinical guidelines in diagnostic large language model outputs. BMJ Health Care Inform, 2026. 33(1).","DOI":"10.1136\/bmjhci-2025-101959"},{"key":"2026062904401449000_2026.06.16.26355773v1.13","unstructured":"Fitch, K ., et al., The RAND\/UCLA Appropriateness Method User\u2019s Manual. 2001, Santa Monica, CA: RAND Corporation."},{"issue":"1","key":"2026062904401449000_2026.06.16.26355773v1.14","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1038\/s41746-025-01457-w","article-title":"Language models for data extraction and risk of bias assessment in complementary medicine","volume":"8","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026062904401449000_2026.06.16.26355773v1.15","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","year":"2021","journal-title":"arXiv"},{"issue":"4","key":"2026062904401449000_2026.06.16.26355773v1.16","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1093\/jamia\/ocaf008","article-title":"Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines","volume":"32","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"2026062904401449000_2026.06.16.26355773v1.17","doi-asserted-by":"publisher","DOI":"10.1007\/s41669-024-00476-9"},{"issue":"12","key":"2026062904401449000_2026.06.16.26355773v1.18","doi-asserted-by":"crossref","first-page":"e0001132","DOI":"10.1371\/journal.pdig.0001132","article-title":"AI-assisted assessment of the IFSO consensus on obesity management medications in the context of metabolic bariatric surgery","volume":"4","year":"2025","journal-title":"PLOS Digit Health"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.06.16.26355773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T11:40:39Z","timestamp":1782733239000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.06.16.26355773"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,26]]},"references-count":18,"URL":"https:\/\/doi.org\/10.64898\/2026.06.16.26355773","relation":{},"subject":[],"published":{"date-parts":[[2026,6,26]]},"subtype":"preprint"}}