{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T22:50:07Z","timestamp":1777416607937,"version":"3.51.4"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T00:00:00Z","timestamp":1766361600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"the Innovation and Develop ment Special Fund of Hangzhou West Sci-Tech Innovation Corridor"},{"name":"Zhejiang Province Key Research and Development Plan","award":["No. 2024SSYS0010"],"award-info":[{"award-number":["No. 2024SSYS0010"]}]},{"name":"National Key Research and Development Program of China","award":["No.2022YFC2504605"],"award-info":[{"award-number":["No.2022YFC2504605"]}]},{"name":"National Key Research and Development Program of China","award":["No.2022YFC2504600"],"award-info":[{"award-number":["No.2022YFC2504600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82572379"],"award-info":[{"award-number":["82572379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No.226-2025-00006"],"award-info":[{"award-number":["No.226-2025-00006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAMS Innovation Fund for Medical Sciences","award":["No.2021-I2M-1-005"],"award-info":[{"award-number":["No.2021-I2M-1-005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-02273-y","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T01:52:53Z","timestamp":1766368373000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Streamlining evidence based clinical recommendations with large language models"],"prefix":"10.1038","volume":"8","author":[{"given":"Dubai","family":"Li","sequence":"first","affiliation":[]},{"given":"Nan","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Kangping","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Ruiqi","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Shuyu","family":"Ouyang","sequence":"additional","affiliation":[]},{"given":"Huayu","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Lin","family":"Qiao","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Tianshu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Danyang","family":"Tong","sequence":"additional","affiliation":[]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mengtao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiaofeng","family":"Zeng","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Xinping","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Jingsong","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,22]]},"reference":[{"key":"2273_CR1","doi-asserted-by":"publisher","unstructured":"Chen, M. et al. Evaluating Large Language Models Trained on Code. https:\/\/doi.org\/10.48550\/arXiv.2107.03374 (2021).","DOI":"10.48550\/arXiv.2107.03374"},{"key":"2273_CR2","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1038\/s41586-023-06924-6","volume":"625","author":"B Romera-Paredes","year":"2024","unstructured":"Romera-Paredes, B. et al. Mathematical discoveries from program search with large language models. Nature 625, 468\u2013475 (2024).","journal-title":"Nature"},{"key":"2273_CR3","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, S., Ding, H. & Chen, H. Large Language Models in Finance: A Survey. In Proc. Fourth ACM International Conference on AI in Finance, ICAIF \u201923, 374\u2013382 (Association for Computing Machinery, New York, NY, USA, 2023).","DOI":"10.1145\/3604237.3626869"},{"key":"2273_CR4","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":"2273_CR5","doi-asserted-by":"crossref","unstructured":"Singhal, K. et al. Toward expert-level medical question answering with large language models. Nat. Med. 31, 943\u2013950 (2025).","DOI":"10.1038\/s41591-024-03423-7"},{"key":"2273_CR6","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1038\/s41591-024-03328-5","volume":"31","author":"S Johri","year":"2025","unstructured":"Johri, S. et al. An evaluation framework for clinical use of large language models in patient interaction tasks. Nat. Med. 31, 77\u201386 (2025).","journal-title":"Nat. Med."},{"key":"2273_CR7","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01091-y","volume":"7","author":"S Kresevic","year":"2024","unstructured":"Kresevic, S. et al. Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework. npj Digit. Med. 7, 102 (2024).","journal-title":"npj Digit. Med."},{"key":"2273_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01029-4","volume":"7","author":"L Wang","year":"2024","unstructured":"Wang, L. et al. Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs. npj Digit. Med. 7, 41 (2024).","journal-title":"npj Digit. Med."},{"key":"2273_CR9","doi-asserted-by":"crossref","unstructured":"Hasan, B. et al. Integrating large language models in systematic reviews: a framework and case study using ROBINS-I for risk of bias assessment. BMJ Evid. Based Med. 29, 394\u2013398 (2024).","DOI":"10.1136\/bmjebm-2023-112597"},{"key":"2273_CR10","doi-asserted-by":"publisher","first-page":"101287","DOI":"10.1016\/j.cola.2024.101287","volume":"80","author":"E Syriani","year":"2024","unstructured":"Syriani, E., David, I. & Kumar, G. Screening articles for systematic reviews with ChatGPT. J. Comput. Lang. 80, 101287 (2024).","journal-title":"J. Comput. Lang."},{"key":"2273_CR11","doi-asserted-by":"crossref","unstructured":"Liu, S., McCoy, A. B. & Wright, A. Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines. J. Am. Med. Inform. Assoc. 32, 605\u2013615 (2025).","DOI":"10.1093\/jamia\/ocaf008"},{"key":"2273_CR12","doi-asserted-by":"crossref","unstructured":"Fouladvand, S. et al. Graph-based clinical recommender: predicting specialists procedure orders using graph representation learning. J. Biomed. Inform. 143, 104407 (2023).","DOI":"10.1016\/j.jbi.2023.104407"},{"key":"2273_CR13","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1093\/jamia\/ocab270","volume":"29","author":"CA Nelson","year":"2022","unstructured":"Nelson, C. A., Bove, R., Butte, A. J. & Baranzini, S. E. Embedding electronic health records onto a knowledge network recognizes prodromal features of multiple sclerosis and predicts diagnosis. J. Am. Med. Inform. Assoc. 29, 424\u2013434 (2022).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2273_CR14","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1001\/virtualmentor.2013.15.1.mhst1-1301","volume":"15","author":"AL Zimerman","year":"2013","unstructured":"Zimerman, A. L. Evidence-based medicine: a short history of a modern medical movement. AMA J. Ethics 15, 71\u201376 (2013).","journal-title":"AMA J. Ethics"},{"key":"2273_CR15","unstructured":"Higgins, J.P.T. et al. Cochrane Handbook for Systematic Reviews of Interventions Version 6.5 (Updated August 2024) (Cochrane, Chichester, 2024)."},{"key":"2273_CR16","unstructured":"World Health Organization. WHO Handbook for Guideline Development (World Health Organization, 2014)."},{"key":"2273_CR17","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.jclinepi.2010.04.026","volume":"64","author":"G Guyatt","year":"2011","unstructured":"Guyatt, G. et al. GRADE guidelines: 1. Introduction\u2014GRADE evidence profiles and summary of findings tables. J. Clin. Epidemiol. 64, 383\u2013394 (2011).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR18","doi-asserted-by":"publisher","unstructured":"DeepSeek-AI et al. DeepSeek-V3 Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2412.19437 (2025).","DOI":"10.48550\/arXiv.2412.19437"},{"key":"2273_CR19","unstructured":"GPT-4o System Card. https:\/\/openai.com\/index\/gpt-4o-system-card\/ (2024)."},{"key":"2273_CR20","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1002\/art.41752","volume":"73","author":"L Fraenkel","year":"2021","unstructured":"Fraenkel, L. et al. 2021 American College of Rheumatology guideline for the treatment of rheumatoid arthritis. Arthritis Rheumatol. 73, 1108\u20131123 (2021).","journal-title":"Arthritis Rheumatol."},{"key":"2273_CR21","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1111\/ene.14412","volume":"27","author":"KS Frederiksen","year":"2020","unstructured":"Frederiksen, K. S. et al. A European Academy of Neurology guideline on medical management issues in dementia. Eur. J. Neurol. 27, 1805\u20131820 (2020).","journal-title":"Eur. J. Neurol."},{"key":"2273_CR22","doi-asserted-by":"publisher","first-page":"S117","DOI":"10.1016\/j.kint.2023.10.018","volume":"105","author":"PE Stevens","year":"2024","unstructured":"Stevens, P. E. et al. KDIGO 2024 Clinical Practice Guideline for the evaluation and management of chronic kidney disease. Kidney Int. 105, S117\u2013S314 (2024).","journal-title":"Kidney Int."},{"key":"2273_CR23","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"},{"key":"2273_CR24","unstructured":"GRADE handbook. https:\/\/gdt.gradepro.org\/app\/handbook\/handbook.html#h.m9385o5z3li7."},{"key":"2273_CR25","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1515\/rir-2024-0028","volume":"5","author":"X Tian","year":"2024","unstructured":"Tian, X. et al. Chinese guidelines for the diagnosis and treatment of rheumatoid arthritis: 2024 update. Rheumatol. Immunol. Res. 5, 189\u2013208 (2024).","journal-title":"Rheumatol. Immunol. Res."},{"key":"2273_CR26","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1136\/ard-2022-223356","volume":"82","author":"JS Smolen","year":"2023","unstructured":"Smolen, J. S. et al. EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs: 2022 update. Ann. Rheum. Dis. 82, 3\u201318 (2023).","journal-title":"Ann. Rheum. Dis."},{"key":"2273_CR27","doi-asserted-by":"publisher","unstructured":"Nori, H., King, N., McKinney, S. M., Carignan, D. & Horvitz, E. Capabilities of GPT-4 on medical challenge problems. https:\/\/doi.org\/10.48550\/arXiv.2303.13375 (2023).","DOI":"10.48550\/arXiv.2303.13375"},{"key":"2273_CR28","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1016\/j.chest.2025.02.029","volume":"168","author":"AC Yataco","year":"2025","unstructured":"Yataco, A. C. et al. Transfusion of fresh frozen plasma and platelets in critically ill adults: an American College of Chest Physicians clinical practice guideline. CHEST 168, 661\u2013676 (2025).","journal-title":"CHEST"},{"key":"2273_CR29","doi-asserted-by":"publisher","first-page":"100443","DOI":"10.1016\/j.conctc.2019.100443","volume":"16","author":"M Michelson","year":"2019","unstructured":"Michelson, M. & Reuter, K. The significant cost of systematic reviews and meta-analyses: a call for greater involvement of machine learning to assess the promise of clinical trials. Contemp. Clin. Trials Commun. 16, 100443 (2019).","journal-title":"Contemp. Clin. Trials Commun."},{"key":"2273_CR30","doi-asserted-by":"publisher","first-page":"e1000326","DOI":"10.1371\/journal.pmed.1000326","volume":"7","author":"H Bastian","year":"2010","unstructured":"Bastian, H., Glasziou, P. & Chalmers, I. Seventy-five trials and eleven systematic reviews a day: how will we ever keep up? PLoS Med. 7, e1000326 (2010).","journal-title":"PLoS Med."},{"key":"2273_CR31","doi-asserted-by":"publisher","DOI":"10.1186\/s40001-022-00717-9","volume":"27","author":"X Zhao","year":"2022","unstructured":"Zhao, X. et al. Changing trends in clinical research literature on PubMed database from 1991 to 2020. Eur. J. Med. Res. 27, 95 (2022).","journal-title":"Eur. J. Med. Res."},{"key":"2273_CR32","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.jclinepi.2020.01.008","volume":"121","author":"J Clark","year":"2020","unstructured":"Clark, J. et al. A full systematic review was completed in 2 weeks using automation tools: a case study. J. Clin. Epidemiol. 121, 81\u201390 (2020).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR33","doi-asserted-by":"publisher","first-page":"e012545","DOI":"10.1136\/bmjopen-2016-012545","volume":"7","author":"R Borah","year":"2017","unstructured":"Borah, R., Brown, A. W., Capers, P. L. & Kaiser, K. A. Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the PROSPERO registry. BMJ Open 7, e012545 (2017).","journal-title":"BMJ Open"},{"key":"2273_CR34","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.jclinepi.2021.05.019","volume":"139","author":"B Nussbaumer-Streit","year":"2021","unstructured":"Nussbaumer-Streit, B. et al. Resource use during systematic review production varies widely: a scoping review. J. Clin. Epidemiol. 139, 287\u2013296 (2021).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR35","doi-asserted-by":"publisher","first-page":"219","DOI":"10.5455\/aim.2008.16.219-225","volume":"16","author":"I Masic","year":"2008","unstructured":"Masic, I., Miokovic, M. & Muhamedagic, B. Evidence based medicine\u2014new approaches and challenges. Acta Inform. Med. 16, 219\u2013225 (2008).","journal-title":"Acta Inform. Med."},{"key":"2273_CR36","doi-asserted-by":"publisher","first-page":"W352","DOI":"10.1093\/nar\/gkab326","volume":"49","author":"A Allot","year":"2021","unstructured":"Allot, A., Lee, K., Chen, Q., Luo, L. & Lu, Z. LitSuggest: a web-based system for literature recommendation and curation using machine learning. Nucleic Acids Res. 49, W352\u2013W358 (2021).","journal-title":"Nucleic Acids Res."},{"key":"2273_CR37","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.jclinepi.2018.06.011","volume":"103","author":"B Pham","year":"2018","unstructured":"Pham, B. et al. Improving the conduct of systematic reviews: a process mining perspective. J. Clin. Epidemiol. 103, 101\u2013111 (2018).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR38","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1136\/bmj.320.7240.954","volume":"320","author":"GH Guyatt","year":"2000","unstructured":"Guyatt, G. H., Meade, M. O., Jaeschke, R. Z., Cook, D. J. & Haynes, R. B. Practitioners of evidence based care. Not all clinicians need to appraise evidence from scratch but all need some skills. BMJ 320, 954\u2013955 (2000).","journal-title":"BMJ"},{"key":"2273_CR39","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1136\/qshc.2008.028043","volume":"18","author":"M Lugtenberg","year":"2009","unstructured":"Lugtenberg, M., Burgers, J. S. & Westert, G. P. Effects of evidence-based clinical practice guidelines on quality of care: a systematic review. BMJ Qual. Saf. 18, 385\u2013392 (2009).","journal-title":"BMJ Qual. Saf."},{"key":"2273_CR40","doi-asserted-by":"publisher","first-page":"36","DOI":"10.3390\/healthcare4030036","volume":"4","author":"F Fischer","year":"2016","unstructured":"Fischer, F., Lange, K., Klose, K., Greiner, W. & Kraemer, A. Barriers and strategies in guideline implementation\u2014a scoping review. Healthcare 4, 36 (2016).","journal-title":"Healthcare"},{"key":"2273_CR41","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.mayocp.2017.01.001","volume":"92","author":"MH Murad","year":"2017","unstructured":"Murad, M. H. Clinical practice guidelines: a primer on development and dissemination. Mayo Clin. Proc. 92, 423\u2013433 (2017).","journal-title":"Mayo Clin. Proc."},{"key":"2273_CR42","doi-asserted-by":"crossref","unstructured":"Bell, R. J. Evidence synthesis in the time of COVID-19. Climacteric 24, 211\u2013213 (2021).","DOI":"10.1080\/13697137.2021.1904676"},{"key":"2273_CR43","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1002\/jrsm.1314","volume":"10","author":"A Wanner","year":"2019","unstructured":"Wanner, A. & Baumann, N. Design and implementation of a tool for conversion of search strategies between PubMed and Ovid MEDLINE. Res. Synth. Methods 10, 154\u2013160 (2019).","journal-title":"Res. Synth. Methods"},{"key":"2273_CR44","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-021-01635-3","volume":"10","author":"KEK Chai","year":"2021","unstructured":"Chai, K. E. K., Lines, R. L. J., Gucciardi, D. F. & Ng, L. Research Screener: a machine learning tool to semi-automate abstract screening for systematic reviews. Syst. Rev. 10, 93 (2021).","journal-title":"Syst. Rev."},{"key":"2273_CR45","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.jclinepi.2017.12.015","volume":"96","author":"A Gates","year":"2018","unstructured":"Gates, A., Vandermeer, B. & Hartling, L. Technology-assisted risk of bias assessment in systematic reviews: a prospective cross-sectional evaluation of the RobotReviewer machine learning tool. J. Clin. Epidemiol. 96, 54\u201362 (2018).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR46","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1136\/bmjebm-2018-111126","volume":"26","author":"J Brassey","year":"2021","unstructured":"Brassey, J. et al. Developing a fully automated evidence synthesis tool for identifying, assessing and collating the evidence. BMJ Evid. -Based Med. 26, 24\u201327 (2021).","journal-title":"BMJ Evid. -Based Med."},{"key":"2273_CR47","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.jclinepi.2021.12.005","volume":"144","author":"H Khalil","year":"2022","unstructured":"Khalil, H., Ameen, D. & Zarnegar, A. Tools to support the automation of systematic reviews: a scoping review. J. Clin. Epidemiol. 144, 22\u201342 (2022).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR48","doi-asserted-by":"publisher","first-page":"e56780","DOI":"10.2196\/56780","volume":"26","author":"X Luo","year":"2024","unstructured":"Luo, X. et al. Potential roles of large language models in the production of systematic reviews and meta-analyses. J. Med. Internet Res. 26, e56780 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2273_CR49","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.jclinepi.2020.06.035","volume":"126","author":"J Clark","year":"2020","unstructured":"Clark, J., Scott, A. M. & Glasziou, P. Not all systematic reviews can be completed in 2 weeks\u2014but many can be (and should be). J. Clin. Epidemiol. 126, 163 (2020).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR50","doi-asserted-by":"crossref","unstructured":"Li, J. et al. Benchmarking large language models in evidence-based medicine. IEEE J. Biomed. Health Inform. 29, 6143\u20136156 (2024).","DOI":"10.1109\/JBHI.2024.3483816"},{"key":"2273_CR51","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01840-7","volume":"8","author":"Z Wang","year":"2025","unstructured":"Wang, Z. et al. Accelerating clinical evidence synthesis with large language models. npj Digit. Med. 8, 509 (2025).","journal-title":"npj Digit. Med."},{"key":"2273_CR52","unstructured":"Jiang, P. et al. Reasoning-enhanced healthcare predictions with knowledge graph community retrieval. In Proc. of the Thirteenth International Conference on Learning Representations (2024)."},{"key":"2273_CR53","doi-asserted-by":"publisher","unstructured":"Wu, J. et al. Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation. https:\/\/doi.org\/10.48550\/arXiv.2408.04187 (2024).","DOI":"10.48550\/arXiv.2408.04187"},{"key":"2273_CR54","doi-asserted-by":"publisher","unstructured":"Lu, K. et al. Med-R$^2$: Crafting Trustworthy LLM Physicians through Retrieval and Reasoning of Evidence-Based Medicine. https:\/\/doi.org\/10.48550\/arXiv.2501.11885 (2025).","DOI":"10.48550\/arXiv.2501.11885"},{"key":"2273_CR55","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1016\/j.mcpdig.2024.05.023","volume":"2","author":"IB Riaz","year":"2024","unstructured":"Riaz, I. B., Naqvi, S. A. A., Hasan, B. & Murad, M. H. Future of evidence synthesis: automated, living, and interactive systematic reviews and meta-analyses. Mayo Clin. Proc. Digit. Health 2, 361\u2013365 (2024).","journal-title":"Mayo Clin. Proc. Digit. Health"},{"key":"2273_CR56","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.jclinepi.2020.11.005","volume":"131","author":"B Tendal","year":"2021","unstructured":"Tendal, B. et al. Weekly updates of national living evidence-based guidelines: methods for the Australian living guidelines for care of people with COVID-19. J. Clin. Epidemiol. 131, 11\u201321 (2021).","journal-title":"J. Clin. Epidemiol."},{"key":"2273_CR57","doi-asserted-by":"publisher","unstructured":"Sun, Z. et al. How good are large language models for automated data extraction from randomized trials? https:\/\/doi.org\/10.1101\/2024.02.20.24303083 (2024).","DOI":"10.1101\/2024.02.20.24303083"},{"key":"2273_CR58","doi-asserted-by":"crossref","unstructured":"Kartchner, D., Ramalingam, S., Al-Hussaini, I., Kronick, O. & Mitchell, C. Zero-shot information extraction for clinical meta-analysis using large language models. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, 396\u2013405 (Association for Computational Linguistics, Toronto, Canada, 2023).","DOI":"10.18653\/v1\/2023.bionlp-1.37"},{"key":"2273_CR59","doi-asserted-by":"publisher","first-page":"351","DOI":"10.3390\/systems11070351","volume":"11","author":"A Alshami","year":"2023","unstructured":"Alshami, A., Elsayed, M., Ali, E., Eltoukhy, A. E. E. & Zayed, T. Harnessing the power of ChatGPT for automating systematic review process: methodology, case study, limitations, and future directions. Systems 11, 351 (2023).","journal-title":"Systems"},{"key":"2273_CR60","doi-asserted-by":"publisher","first-page":"92420","DOI":"10.52202\/079017-2935","volume":"37","author":"J Dekoninck","year":"2024","unstructured":"Dekoninck, J., M\u00fcller, M. N. & Vechev, M. ConStat: performance-based contamination detection in large language models. Adv. Neural Inf. Process. Syst. 37, 92420\u201392464 (2024).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2273_CR61","doi-asserted-by":"publisher","first-page":"e56764","DOI":"10.2196\/56764","volume":"26","author":"A Choudhury","year":"2024","unstructured":"Choudhury, A. & Chaudhry, Z. Large language models and user trust: consequence of self-referential learning loop and the deskilling of health care professionals. J. Med. Internet Res. 26, e56764 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2273_CR62","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1038\/s41591-022-02160-z","volume":"29","author":"V Subbiah","year":"2023","unstructured":"Subbiah, V. The next generation of evidence-based medicine. Nat. Med. 29, 49\u201358 (2023).","journal-title":"Nat. Med."},{"key":"2273_CR63","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/S0140-6736(16)31592-6","volume":"390","author":"B Djulbegovic","year":"2017","unstructured":"Djulbegovic, B. & Guyatt, G. H. Progress in evidence-based medicine: a quarter century on. Lancet 390, 415\u2013423 (2017).","journal-title":"Lancet"},{"key":"2273_CR64","unstructured":"Brown, T. et al. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems Vol. 33, 1877\u20131901 (Curran Associates, Inc., 2020)."},{"key":"2273_CR65","first-page":"46534","volume":"36","author":"A Madaan","year":"2023","unstructured":"Madaan, A. et al. Self-refine: iterative refinement with self-feedback. Adv. Neural Inf. Process. Syst. 36, 46534\u201346594 (2023).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2273_CR66","unstructured":"Zhang, T. et al. In-context principle learning from mistakes. In Proc. of the 41st international conference on machine learning (eds Salakhutdinov, R. et al.) 235, 59520\u201359558 (PMLR, 2024)."},{"key":"2273_CR67","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J. et al. Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inf. Process. Syst. 35, 24824\u201324837 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2273_CR68","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0","volume":"68","author":"Z Xi","year":"2025","unstructured":"Xi, Z. et al. The rise and potential of large language model based agents: a survey. Sci. China Inf. Sci. 68, 121101 (2025).","journal-title":"Sci. China Inf. Sci."},{"key":"2273_CR69","unstructured":"Anthopic, P. B. C. Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku Anthropic. https:\/\/www.anthropic.com\/news\/3-5-models-and-computer-use (2024)."},{"key":"2273_CR70","doi-asserted-by":"publisher","unstructured":"Li, Z. et al. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2308.03281 (2023).","DOI":"10.48550\/arXiv.2308.03281"},{"key":"2273_CR71","unstructured":"Lefebvre, C. et al. Searching for and selecting studies. In Cochrane Handbook for Systematic Reviews of Interventions Version 6.5.1 (eds Higgins, J. et al.) Ch. 4 (Cochrane, Chichester, 2025)."},{"key":"2273_CR72","doi-asserted-by":"publisher","unstructured":"Lopez, P. GROBID: Combining automatic bibliographic data recognition and term extraction for scholarship publications. In Research and Advanced Technology for Digital Libraries (eds Agosti, M., Borbinha, J., Kapidakis, S., Papatheodorou, C. & Tsakonas, G.) 473\u2013474 (Springer, Berlin, Heidelberg, 2009). https:\/\/doi.org\/10.1007\/978-3-642-04346-8_62.","DOI":"10.1007\/978-3-642-04346-8_62"},{"key":"2273_CR73","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":"2273_CR74","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1136\/ard.2009.126532","volume":"69","author":"JS Smolen","year":"2010","unstructured":"Smolen, J. S. et al. EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs. Ann. Rheum. Dis. 69, 964\u2013975 (2010).","journal-title":"Ann. Rheum. Dis."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02273-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02273-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02273-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T21:02:55Z","timestamp":1767042175000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02273-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,22]]},"references-count":74,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["2273"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02273-y","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,22]]},"assertion":[{"value":"30 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2025","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":"793"}}