{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T00:03:59Z","timestamp":1776211439876,"version":"3.50.1"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":33,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Beijing Natural Science Foundation","award":["L256048"],"award-info":[{"award-number":["L256048"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["3332024146"],"award-info":[{"award-number":["3332024146"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Science and Technology Innovation Action Plan","award":["23Y11905100"],"award-info":[{"award-number":["23Y11905100"]}]},{"name":"National clinical key specialty construction project","award":["23003"],"award-info":[{"award-number":["23003"]}]},{"name":"Plastic Medicine Research Fund of Chinese Academy of Medical Sciences","award":["2024-ZX-1-01"],"award-info":[{"award-number":["2024-ZX-1-01"]}]},{"name":"National Major Disease Multidisciplinary Diagnosis and Treatment Cooperation Project","award":["No.1112320139"],"award-info":[{"award-number":["No.1112320139"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02382-2","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T13:45:00Z","timestamp":1769607900000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Human\u2013large language model collaboration in clinical medicine: a systematic review and meta-analysis"],"prefix":"10.1038","volume":"9","author":[{"given":"Guoyong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Kaijun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jiyue","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Chaonan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hui","family":"Bi","sequence":"additional","affiliation":[]},{"given":"Haojun","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Zuoliang","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaonan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"2382_CR1","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1038\/s41586-025-08869-4","volume":"642","author":"D McDuff","year":"2025","unstructured":"McDuff, D. et al. Towards accurate differential diagnosis with large language models. Nature 642, 451\u2013457 (2025).","journal-title":"Nature"},{"key":"2382_CR2","doi-asserted-by":"publisher","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh, E. et al. Large language model influence on diagnostic reasoning: a randomized clinical trial. JAMA Netw. Open 7, e2440969 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR3","volume":"45","author":"J Qiu","year":"2024","unstructured":"Qiu, J., Yuan, W. & Lam, K. The application of multimodal large language models in medicine. Lancet Reg. Health West Pac. 45, 101048 (2024).","journal-title":"Lancet Reg. Health West Pac."},{"key":"2382_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109713","volume":"27","author":"X Meng","year":"2024","unstructured":"Meng, X. et al. The application of large language models in medicine: a scoping review. iScience 27, 109713 (2024).","journal-title":"iScience"},{"key":"2382_CR5","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1038\/s41746-023-00958-w","volume":"6","author":"C Peng","year":"2023","unstructured":"Peng, C. et al. A study of generative large language model for medical research and healthcare. NPJ Digit Med. 6, 210 (2023).","journal-title":"NPJ Digit Med."},{"key":"2382_CR6","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","volume":"388","author":"P Lee","year":"2023","unstructured":"Lee, P., Bubeck, S. & Petro, J. Benefits, limits, and risks of GPT-4 as an AI Chatbot for Medicine. N. Engl. J. Med. 388, 1233\u20131239 (2023).","journal-title":"N. Engl. J. Med."},{"key":"2382_CR7","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356 (2019).","journal-title":"Nat. Med."},{"key":"2382_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":"2382_CR9","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":"2382_CR10","doi-asserted-by":"publisher","first-page":"e248895","DOI":"10.1001\/jamanetworkopen.2024.8895","volume":"7","author":"CYK Williams","year":"2024","unstructured":"Williams, C. Y. K. et al. Use of a large language model to assess clinical acuity of adults in the emergency department. JAMA Netw. Open 7, e248895 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR11","doi-asserted-by":"publisher","first-page":"e2460637","DOI":"10.1001\/jamanetworkopen.2024.60637","volume":"8","author":"MJ Duggan","year":"2025","unstructured":"Duggan, M. J. et al. Clinician experiences with ambient scribe technology to assist with documentation burden and efficiency. JAMA Netw. Open 8, e2460637 (2025).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR12","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s13045-023-01514-5","volume":"16","author":"C Zhang","year":"2023","unstructured":"Zhang, C. et al. Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment. J. Hematol. Oncol. 16, 114 (2023).","journal-title":"J. Hematol. Oncol."},{"key":"2382_CR13","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41746-024-01079-8","volume":"7","author":"J Huang","year":"2024","unstructured":"Huang, J. et al. A critical assessment of using ChatGPT for extracting structured data from clinical notes. NPJ Digit. Med. 7, 106 (2024).","journal-title":"NPJ Digit. Med."},{"key":"2382_CR14","doi-asserted-by":"publisher","first-page":"e56110","DOI":"10.2196\/56110","volume":"26","author":"JM Hoppe","year":"2024","unstructured":"Hoppe, J. M., Auer, M. K., Str\u00fcven, A., Massberg, S. & Stremmel, C. ChatGPT with GPT-4 outperforms emergency department physicians in diagnostic accuracy: retrospective analysis. J. Med. Internet Res. 26, e56110 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2382_CR15","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal, K. et al. Toward expert-level medical question answering with large language models. Nat. Med. 31, 943\u2013950 (2025).","journal-title":"Nat. Med."},{"key":"2382_CR16","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.231593","volume":"310","author":"R Doshi","year":"2024","unstructured":"Doshi, R. et al. Quantitative evaluation of large language models to streamline radiology report impressions: a multimodal retrospective analysis. Radiology 310, e231593 (2024).","journal-title":"Radiology"},{"key":"2382_CR17","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.1016\/j.jacr.2024.06.018","volume":"21","author":"K Berigan","year":"2024","unstructured":"Berigan, K. et al. The impact of large language model-generated radiology report summaries on patient comprehension: a randomized controlled trial. J. Am. Coll. Radiol. 21, 1898\u20131903 (2024).","journal-title":"J. Am. Coll. Radiol."},{"key":"2382_CR18","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1001\/jamainternmed.2025.0821","volume":"185","author":"CYK Williams","year":"2025","unstructured":"Williams, C. Y. K. et al. Physician- and large language model-generated hospital discharge summaries. JAMA Intern. Med. 185, 818\u2013825 (2025).","journal-title":"JAMA Intern. Med."},{"key":"2382_CR19","doi-asserted-by":"publisher","first-page":"e240357","DOI":"10.1001\/jamanetworkopen.2024.0357","volume":"7","author":"J Zaretsky","year":"2024","unstructured":"Zaretsky, J. et al. Generative Artificial Intelligence to transform inpatient discharge summaries to patient-friendly language and format. JAMA Netw. Open 7, e240357 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR20","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1038\/s41586-025-08866-7","volume":"642","author":"T Tu","year":"2025","unstructured":"Tu, T. et al. Towards conversational diagnostic artificial intelligence. Nature 642, 442\u2013450 (2025).","journal-title":"Nature"},{"key":"2382_CR21","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1056\/NEJMp2404691","volume":"391","author":"IS Kohane","year":"2024","unstructured":"Kohane, I. S. Compared with what? Measuring AI against the health care we have. N. Engl. J. Med. 391, 1564\u20131566 (2024).","journal-title":"N. Engl. J. Med."},{"key":"2382_CR22","doi-asserted-by":"publisher","first-page":"e243201","DOI":"10.1001\/jamanetworkopen.2024.3201","volume":"7","author":"P Garcia","year":"2024","unstructured":"Garcia, P. et al. Artificial Intelligence-generated draft replies to patient inbox messages. JAMA Netw. Open 7, e243201 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR23","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1038\/s41591-022-01772-9","volume":"28","author":"B Vasey","year":"2022","unstructured":"Vasey, B. et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nat. Med. 28, 924\u2013933 (2022).","journal-title":"Nat. Med."},{"key":"2382_CR24","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins, G. S. et al. TRIPOD\u2009+\u2009AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385, e078378 (2024).","journal-title":"BMJ"},{"key":"2382_CR25","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med. 30, 2613\u20132622 (2024).","journal-title":"Nat. Med."},{"key":"2382_CR26","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1093\/jamia\/ocad072","volume":"30","author":"S Liu","year":"2023","unstructured":"Liu, S. et al. Using AI-generated suggestions from ChatGPT to optimize clinical decision support. J. Am. Med. Inform. Assoc. 30, 1237\u20131245 (2023).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2382_CR27","doi-asserted-by":"publisher","first-page":"e246565","DOI":"10.1001\/jamanetworkopen.2024.6565","volume":"7","author":"M Tai-Seale","year":"2024","unstructured":"Tai-Seale, M. et al. AI-generated draft replies integrated into health records and physicians\u2019 electronic communication. JAMA Netw. Open 7, e246565 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR28","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1093\/jamia\/ocae304","volume":"32","author":"SP Ma","year":"2025","unstructured":"Ma, S. P. et al. Ambient artificial intelligence scribes: utilization and impact on documentation time. J. Am. Med. Inform. Assoc. 32, 381\u2013385 (2025).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2382_CR29","doi-asserted-by":"publisher","first-page":"e428","DOI":"10.1016\/S2589-7500(24)00061-X","volume":"6","author":"JCL Ong","year":"2024","unstructured":"Ong, J. C. L. et al. Ethical and regulatory challenges of large language models in medicine. Lancet Digit Health 6, e428\u2013e432 (2024).","journal-title":"Lancet Digit Health"},{"key":"2382_CR30","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1007\/s11606-024-09177-9","volume":"40","author":"HG Schmidt","year":"2025","unstructured":"Schmidt, H. G., Rotgans, J. I. & Mamede, S. Bias sensitivity in diagnostic decision-making: comparing ChatGPT with residents. J. Gen. Intern. Med. 40, 790\u2013795 (2025).","journal-title":"J. Gen. Intern. Med."},{"key":"2382_CR31","doi-asserted-by":"publisher","first-page":"e1002686","DOI":"10.1371\/journal.pmed.1002686","volume":"15","author":"P Rajpurkar","year":"2018","unstructured":"Rajpurkar, P. et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 15, e1002686 (2018).","journal-title":"PLoS Med."},{"key":"2382_CR32","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1148\/radiol.2019191293","volume":"294","author":"A Majkowska","year":"2020","unstructured":"Majkowska, A. et al. Chest Radiograph interpretation with deep learning models: assessment with radiologist-adjudicated reference standards and population-adjusted evaluation. Radiology 294, 421\u2013431 (2020).","journal-title":"Radiology"},{"key":"2382_CR33","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41746-024-01101-z","volume":"7","author":"X Chen","year":"2024","unstructured":"Chen, X. et al. FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer. NPJ Digit. Med. 7, 111 (2024).","journal-title":"NPJ Digit. Med."},{"key":"2382_CR34","doi-asserted-by":"publisher","first-page":"e0000341","DOI":"10.1371\/journal.pdig.0000341","volume":"3","author":"AJ Thirunavukarasu","year":"2024","unstructured":"Thirunavukarasu, A. J. et al. Large language models approach expert-level clinical knowledge and reasoning in ophthalmology: a head-to-head cross-sectional study. PLOS Digit. Health 3, e0000341 (2024).","journal-title":"PLOS Digit. Health"},{"key":"2382_CR35","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.cgh.2022.07.006","volume":"21","author":"H Xu","year":"2023","unstructured":"Xu, H. et al. Artificial Intelligence-assisted colonoscopy for colorectal cancer screening: a multicenter randomized controlled trial. Clin. Gastroenterol. Hepatol. 21, 337\u2013346.e333 (2023).","journal-title":"Clin. Gastroenterol. Hepatol."},{"key":"2382_CR36","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.1136\/gutjnl-2018-317500","volume":"68","author":"P Wang","year":"2019","unstructured":"Wang, P. et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut 68, 1813\u20131819 (2019).","journal-title":"Gut"},{"key":"2382_CR37","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1038\/s41569-020-00503-2","volume":"18","author":"KC Siontis","year":"2021","unstructured":"Siontis, K. C., Noseworthy, P. A., Attia, Z. I. & Friedman, P. A. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat. Rev. Cardiol. 18, 465\u2013478 (2021).","journal-title":"Nat. Rev. Cardiol."},{"key":"2382_CR38","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1007\/s00330-024-10902-5","volume":"35","author":"D Horiuchi","year":"2025","unstructured":"Horiuchi, D. et al. ChatGPT\u2019s diagnostic performance based on textual vs. visual information compared to radiologists\u2019 diagnostic performance in musculoskeletal radiology. Eur. Radiol. 35, 506\u2013516 (2025).","journal-title":"Eur. Radiol."},{"key":"2382_CR39","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/s41746-025-01543-z","volume":"8","author":"H Takita","year":"2025","unstructured":"Takita, H. et al. A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians. NPJ Digit. Med. 8, 175 (2025).","journal-title":"NPJ Digit. Med."},{"key":"2382_CR40","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","volume":"26","author":"X Liu","year":"2020","unstructured":"Liu, X., Cruz Rivera, S., Moher, D., Calvert, M. J. & Denniston, A. K. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat. Med. 26, 1364\u20131374 (2020).","journal-title":"Nat. Med."},{"key":"2382_CR41","doi-asserted-by":"publisher","first-page":"m3210","DOI":"10.1136\/bmj.m3210","volume":"370","author":"SC Rivera","year":"2020","unstructured":"Rivera, S. C., Liu, X., Chan, A. W., Denniston, A. K. & Calvert, M. J. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. BMJ 370, m3210 (2020).","journal-title":"BMJ"},{"key":"2382_CR42","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1038\/s41562-024-02024-1","volume":"8","author":"M Vaccaro","year":"2024","unstructured":"Vaccaro, M., Almaatouq, A. & Malone, T. When combinations of humans and AI are useful: a systematic review and meta-analysis. Nat. Hum. Behav. 8, 2293\u20132303 (2024).","journal-title":"Nat. Hum. Behav."},{"key":"2382_CR43","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-025-05468-7","volume":"29","author":"X Wu","year":"2025","unstructured":"Wu, X., Huang, Y. & He, Q. A large language model improves clinicians\u2019 diagnostic performance in complex critical illness cases. Crit. Care 29, 230 (2025).","journal-title":"Crit. Care"},{"key":"2382_CR44","doi-asserted-by":"publisher","first-page":"e2517204","DOI":"10.1001\/jamanetworkopen.2025.17204","volume":"8","author":"Q Chen","year":"2025","unstructured":"Chen, Q. et al. AI workflow, external validation, and development in eye disease diagnosis. JAMA Netw. Open 8, e2517204 (2025).","journal-title":"JAMA Netw. Open"},{"key":"2382_CR45","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/s41746-025-01559-5","volume":"8","author":"MK Wekenborg","year":"2025","unstructured":"Wekenborg, M. K., Gilbert, S. & Kather, J. N. Examining human-AI interaction in real-world healthcare beyond the laboratory. NPJ Digit. Med. 8, 169 (2025).","journal-title":"NPJ Digit. Med."},{"key":"2382_CR46","doi-asserted-by":"publisher","first-page":"e367","DOI":"10.1016\/S2589-7500(24)00047-5","volume":"6","author":"R Han","year":"2024","unstructured":"Han, R. et al. Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review. Lancet Digit. Health 6, e367\u2013e373 (2024).","journal-title":"Lancet Digit. Health"},{"key":"2382_CR47","doi-asserted-by":"publisher","first-page":"5252","DOI":"10.1007\/s00330-025-11484-6","volume":"35","author":"SH Kim","year":"2025","unstructured":"Kim, S. H. et al. Human-AI collaboration in large language model-assisted brain MRI differential diagnosis: a usability study. Eur. Radiol. 35, 5252\u20135263 (2025).","journal-title":"Eur. Radiol."},{"key":"2382_CR48","doi-asserted-by":"publisher","unstructured":"Spitzer, P. et al. The effect of medical explanations from large language models on diagnostic decisions in radiology. https:\/\/doi.org\/10.1101\/2025.03.04.25323357 (2025).","DOI":"10.1101\/2025.03.04.25323357"},{"key":"2382_CR49","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1038\/s41591-024-03456-y","volume":"31","author":"E Goh","year":"2025","unstructured":"Goh, E. et al. GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial. Nat. Med. 31, 1233\u20131238 (2025).","journal-title":"Nat. Med."},{"key":"2382_CR50","doi-asserted-by":"publisher","unstructured":"Everett, S. S. et al. From tool to teammate: a randomized controlled trial of clinician-AI collaborative workflows for diagnosis. https:\/\/doi.org\/10.1101\/2025.06.07.25329176 (2025).","DOI":"10.1101\/2025.06.07.25329176"},{"key":"2382_CR51","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1038\/s41746-025-01858-x","volume":"8","author":"YH Ke","year":"2025","unstructured":"Ke, Y. H. et al. Clinical and economic impact of a large language model in perioperative medicine: a randomized crossover trial. NPJ Digit. Med. 8, 462 (2025).","journal-title":"NPJ Digit. Med."},{"key":"2382_CR52","doi-asserted-by":"publisher","unstructured":"Castano-Villegas, N., Llano, I., Villa, M. C. & Zea, J. Real-world Validation of MedSearch: a conversational agent for real-time, evidence-based medical question-answering. https:\/\/doi.org\/10.1101\/2025.05.02.25326659 (2025).","DOI":"10.1101\/2025.05.02.25326659"},{"key":"2382_CR53","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1007\/s00415-025-13261-3","volume":"272","author":"A Gorenshtein","year":"2025","unstructured":"Gorenshtein, A. et al. AI-Based EMG reporting: a randomized controlled trial. J. Neurol. 272, 586 (2025).","journal-title":"J. Neurol."},{"key":"2382_CR54","doi-asserted-by":"publisher","first-page":"123","DOI":"10.5435\/JAAOS-D-23-00474","volume":"32","author":"HP Baker","year":"2024","unstructured":"Baker, H. P. et al. ChatGPT\u2019s ability to assist with clinical documentation: a randomized controlled trial. J. Am. Acad. Orthop. Surg. 32, 123\u2013129 (2024).","journal-title":"J. Am. Acad. Orthop. Surg."},{"key":"2382_CR55","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1001\/jamaophthalmol.2025.0351","volume":"143","author":"PD Tailor","year":"2025","unstructured":"Tailor, P. D. et al. Evaluation of AI summaries on interdisciplinary understanding of ophthalmology notes. JAMA Ophthalmol. 143, 410\u2013419 (2025).","journal-title":"JAMA Ophthalmol."},{"key":"2382_CR56","doi-asserted-by":"crossref","unstructured":"Liu, X., Cruz Rivera, S., Moher, D., Calvert, M. J. & Denniston, A. K. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Lancet Digit. Health 2, e537-e548 (2020).","DOI":"10.1136\/bmj.m3164"},{"key":"2382_CR57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2024.111533","volume":"175","author":"T Woelfle","year":"2024","unstructured":"Woelfle, T. et al. Benchmarking human-AI collaboration for common evidence appraisal tools. J. Clin. Epidemiol. 175, 111533 (2024).","journal-title":"J. Clin. Epidemiol."},{"key":"2382_CR58","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1038\/s41746-025-01670-7","volume":"8","author":"E Asgari","year":"2025","unstructured":"Asgari, E. et al. A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation. NPJ Digit. Med. 8, 274 (2025).","journal-title":"NPJ Digit. Med."},{"key":"2382_CR59","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1001\/jamainternmed.2023.2366","volume":"183","author":"DP Ly","year":"2023","unstructured":"Ly, D. P., Shekelle, P. G. & Song, Z. Evidence for anchoring bias during physician decision-making. JAMA Intern. Med. 183, 818\u2013823 (2023).","journal-title":"JAMA Intern. Med."},{"key":"2382_CR60","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-016-0377-1","volume":"16","author":"G Saposnik","year":"2016","unstructured":"Saposnik, G., Redelmeier, D., Ruff, C. C. & Tobler, P. N. Cognitive biases associated with medical decisions: a systematic review. BMC Med. Inform. Decis. Mak. 16, 138 (2016).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2382_CR61","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","volume":"630","author":"S Farquhar","year":"2024","unstructured":"Farquhar, S., Kossen, J., Kuhn, L. & Gal, Y. Detecting hallucinations in large language models using semantic entropy. Nature 630, 625\u2013630 (2024).","journal-title":"Nature"},{"key":"2382_CR62","doi-asserted-by":"publisher","first-page":"e51297","DOI":"10.2196\/51297","volume":"26","author":"K Gierend","year":"2024","unstructured":"Gierend, K. et al. Provenance information for biomedical data and workflows: scoping review. J. Med. Internet Res. 26, e51297 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2382_CR63","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2025.112406","volume":"28","author":"HS Adnan","year":"2025","unstructured":"Adnan, H. S., Shidani, A., Clifton, L., Bankhead, C. R. & Perera-Salazar, R. Implementation framework for AI deployment at scale in healthcare systems. iScience 28, 112406 (2025).","journal-title":"iScience"},{"key":"2382_CR64","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","volume":"183","author":"JW Ayers","year":"2023","unstructured":"Ayers, J. W. et al. Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern. Med. 183, 589\u2013596 (2023).","journal-title":"JAMA Intern. Med."},{"key":"2382_CR65","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2023.11.009","volume":"165","author":"S Sayfi","year":"2024","unstructured":"Sayfi, S. et al. A multimethods randomized trial found that plain language versions improved adults understanding of health recommendations. J. Clin. Epidemiol. 165, 111219 (2024).","journal-title":"J. Clin. Epidemiol."},{"key":"2382_CR66","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-017-1978-4","volume":"18","author":"PR Williamson","year":"2017","unstructured":"Williamson, P. R. et al. The COMET Handbook: version 1.0. Trials 18, 280 (2017).","journal-title":"Trials"},{"key":"2382_CR67","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1136\/amiajnl-2011-000089","volume":"19","author":"K Goddard","year":"2012","unstructured":"Goddard, K., Roudsari, A. & Wyatt, J. C. Automation bias: a systematic review of frequency, effect mediators, and mitigators. J. Am. Med. Inform. Assoc. 19, 121\u2013127 (2012).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2382_CR68","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1007\/s10462-025-11352-1","volume":"58","author":"C Natali","year":"2025","unstructured":"Natali, C., Marconi, L., Dias Duran, L. D. & Cabitza, F. AI-induced deskilling in medicine: a mixed-method review and research agenda for healthcare and beyond. Artif. Intell. Rev. 58, 356 (2025).","journal-title":"Artif. Intell. Rev."},{"key":"2382_CR69","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","volume":"28","author":"P Rajpurkar","year":"2022","unstructured":"Rajpurkar, P., Chen, E., Banerjee, O. & Topol, E. J. AI in health and medicine. Nat. Med. 28, 31\u201338 (2022).","journal-title":"Nat. Med."},{"key":"2382_CR70","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":"2382_CR71","doi-asserted-by":"publisher","first-page":"l4898","DOI":"10.1136\/bmj.l4898","volume":"366","author":"JAC Sterne","year":"2019","unstructured":"Sterne, J. A. C. et al. RoB 2: a revised tool for assessing risk of bias in randomised trials. BMJ 366, l4898 (2019).","journal-title":"BMJ"},{"key":"2382_CR72","doi-asserted-by":"publisher","first-page":"i4919","DOI":"10.1136\/bmj.i4919","volume":"355","author":"JA Sterne","year":"2016","unstructured":"Sterne, J. A. et al. ROBINS-I: a tool for assessing risk of bias in non-randomised studies of interventions. BMJ 355, i4919 (2016).","journal-title":"BMJ"},{"key":"2382_CR73","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1177\/0962280216669183","volume":"27","author":"D Luo","year":"2018","unstructured":"Luo, D., Wan, X., Liu, J. & Tong, T. Optimally estimating the sample mean from the sample size, median, mid-range, and\/or mid-quartile range. Stat. Methods Med. Res. 27, 1785\u20131805 (2018).","journal-title":"Stat. Methods Med. Res."},{"key":"2382_CR74","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-135","volume":"14","author":"X Wan","year":"2014","unstructured":"Wan, X., Wang, W., Liu, J. & Tong, T. Estimating the sample mean and standard deviation from the sample size, median, range and\/or interquartile range. BMC Med. Res. Methodol. 14, 135 (2014).","journal-title":"BMC Med. Res. Methodol."},{"key":"2382_CR75","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1136\/bmj.39489.470347.AD","volume":"336","author":"GH Guyatt","year":"2008","unstructured":"Guyatt, G. H. et al. GRADE: an emerging consensus on rating quality of evidence and strength of recommendations. BMJ 336, 924\u2013926 (2008).","journal-title":"BMJ"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02382-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02382-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02382-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T14:19:39Z","timestamp":1772461179000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02382-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":75,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2382"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02382-2","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"27 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"195"}}