{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T07:38:43Z","timestamp":1789198723574,"version":"build-2803163510"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:00:00Z","timestamp":1772496000000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Med"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1038\/s41591-026-04229-5","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T10:05:10Z","timestamp":1772532310000},"page":"1152-1159","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["LLM-assisted systematic review of large language models in clinical medicine"],"prefix":"10.1038","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7719-469X","authenticated-orcid":false,"given":"Sully F.","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anton","family":"Alyakin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0624-1254","authenticated-orcid":false,"given":"Andreas","family":"Seas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunice","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joanne J.","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8961-0125","authenticated-orcid":false,"given":"Jin Vivian","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amelia L.","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranav I.","family":"Warman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3662-6745","authenticated-orcid":false,"given":"Rochelle T.","family":"Bitolas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert J.","family":"Steele","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7957-5170","authenticated-orcid":false,"given":"Daniel A.","family":"Alber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1876-5963","authenticated-orcid":false,"given":"Eric K.","family":"Oermann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,3]]},"reference":[{"key":"4229_CR1","doi-asserted-by":"publisher","unstructured":"Bommasani, R. et al. On the opportunities and risks of foundation models. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2108.07258 (2021).","DOI":"10.48550\/arXiv.2108.07258"},{"key":"4229_CR2","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41746-023-00896-7","volume":"6","author":"L Tang","year":"2023","unstructured":"Tang, L. et al. Evaluating large language models on medical evidence summarization. NPJ Digit. Med. 6, 158 (2023).","journal-title":"NPJ Digit. Med."},{"key":"4229_CR3","doi-asserted-by":"publisher","unstructured":"McDuff, D. et al. Towards accurate differential diagnosis with large language models. Nature https:\/\/doi.org\/10.1038\/s41586-025-08869-4 (2025).","DOI":"10.1038\/s41586-025-08869-4"},{"key":"4229_CR4","doi-asserted-by":"publisher","unstructured":"Tu, T. et al. Towards conversational diagnostic artificial intelligence. Nature https:\/\/doi.org\/10.1038\/s41586-025-08866-7 (2025).","DOI":"10.1038\/s41586-025-08866-7"},{"key":"4229_CR5","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1093\/postmj\/qgae065","volume":"100","author":"YS K\u0131yak","year":"2024","unstructured":"K\u0131yak, Y. S. & Emekli, E. ChatGPT prompts for generating multiple-choice questions in medical education and evidence on their validity: a literature review. Postgrad. Med. J. 100, 858\u2013865 (2024).","journal-title":"Postgrad. Med. J."},{"key":"4229_CR6","unstructured":"Alyakin, A. et al. Repurposing the scientific literature with vision-language models. Preprint at arXiv https:\/\/arxiv.org\/abs\/2502.19546 (2025)."},{"key":"4229_CR7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-023-06160-y","volume":"619","author":"LY Jiang","year":"2023","unstructured":"Jiang, L. Y. et al. Health system-scale language models are all-purpose prediction engines. Nature 619, 357\u2013362 (2023).","journal-title":"Nature"},{"key":"4229_CR8","doi-asserted-by":"publisher","first-page":"e0000198","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"TH Kung","year":"2023","unstructured":"Kung, T. H. et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit. Health 2, e0000198 (2023).","journal-title":"PLOS Digit. Health"},{"key":"4229_CR9","doi-asserted-by":"publisher","DOI":"10.2196\/45312","volume":"9","author":"A Gilson","year":"2023","unstructured":"Gilson, A. et al. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med. Educ. 9, e45312 (2023).","journal-title":"JMIR Med. Educ."},{"key":"4229_CR10","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"4229_CR11","doi-asserted-by":"publisher","first-page":"105175","DOI":"10.1016\/j.ijmedinf.2023.105175","volume":"178","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Song, Y., Ma, Z. & Han, X. Multidisciplinary considerations of fairness in medical AI: a scoping review. Int. J. Med. Inform. 178, 105175 (2023).","journal-title":"Int. J. Med. Inform."},{"key":"4229_CR12","doi-asserted-by":"publisher","first-page":"e26297","DOI":"10.1016\/j.heliyon.2024.e26297","volume":"10","author":"C Mennella","year":"2024","unstructured":"Mennella, C., Maniscalco, U., De Pietro, G. & Esposito, M. Ethical and regulatory challenges of AI technologies in healthcare: a narrative review. Heliyon 10, e26297 (2024).","journal-title":"Heliyon"},{"key":"4229_CR13","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/s00701-024-06372-9","volume":"166","author":"A Patil","year":"2024","unstructured":"Patil, A. et al. Large language models in neurosurgery: a systematic review and meta-analysis. Acta Neurochir. (Wien) 166, 475 (2024).","journal-title":"Acta Neurochir. (Wien)"},{"key":"4229_CR14","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","volume":"333","author":"S Bedi","year":"2025","unstructured":"Bedi, S. et al. Testing and evaluation of health care applications of large language models: a systematic review. JAMA 333, 319\u2013328 (2025).","journal-title":"JAMA"},{"key":"4229_CR15","doi-asserted-by":"publisher","first-page":"n71","DOI":"10.1136\/bmj.n71","volume":"372","author":"MJ Page","year":"2021","unstructured":"Page, M. J. et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 372, n71 (2021).","journal-title":"BMJ"},{"key":"4229_CR16","first-page":"156","volume":"289","author":"G Danilov","year":"2022","unstructured":"Danilov, G. et al. Length of stay prediction in neurosurgery with Russian GPT-3 language model compared to human expectations. Stud. Health Technol. Inform. 289, 156\u2013159 (2022).","journal-title":"Stud. Health Technol. Inform."},{"key":"4229_CR17","first-page":"555","volume":"295","author":"G Danilov","year":"2022","unstructured":"Danilov, G. et al. Predicting the length of stay in neurosurgery with RuGPT-3 language model. Stud. Health Technol. Inform. 295, 555\u2013558 (2022).","journal-title":"Stud. Health Technol. Inform."},{"key":"4229_CR18","doi-asserted-by":"publisher","first-page":"e57318","DOI":"10.2196\/57318","volume":"12","author":"JB Bricker","year":"2024","unstructured":"Bricker, J. B., Sullivan, B., Mull, K., Santiago-Torres, M. & Lavista Ferres, J. M. Conversational chatbot for cigarette smoking cessation: results from the 11-step user-centered design development process and randomized controlled trial. JMIR MHealth UHealth 12, e57318 (2024).","journal-title":"JMIR MHealth UHealth"},{"key":"4229_CR19","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","volume":"31","author":"J Gallifant","year":"2025","unstructured":"Gallifant, J. et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nat. Med. 31, 60\u201369 (2025).","journal-title":"Nat. Med."},{"key":"4229_CR20","doi-asserted-by":"publisher","unstructured":"Chen, S. nyuolab\/llms-in-clinical-medicine-systematic-review: Initial release. Zenodo https:\/\/doi.org\/10.5281\/zenodo.17393576 (2025).","DOI":"10.5281\/zenodo.17393576"}],"container-title":["Nature Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04229-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04229-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04229-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:03:04Z","timestamp":1774018984000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41591-026-04229-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":20,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["4229"],"URL":"https:\/\/doi.org\/10.1038\/s41591-026-04229-5","relation":{},"ISSN":["1078-8956","1546-170X"],"issn-type":[{"value":"1078-8956","type":"print"},{"value":"1546-170X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"3 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"E.K.O. reports consulting with Sofinnova Partners and Google, income from Merck & Co. and Mirati Therapeutics, and equity in Artisight. S.F.C. reports equity in OpenAI. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}