{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T19:26:16Z","timestamp":1792524376901,"version":"4.5.0"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["NIAMS R01AR079442"],"award-info":[{"award-number":["NIAMS R01AR079442"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R01AR081344"],"award-info":[{"award-number":["R01AR081344"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R56AR081017"],"award-info":[{"award-number":["R56AR081017"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Large language models (LLMs) have shown promising abilities in text-based clinical tasks but they do not inherently interpret medical images such as knee radiographs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>To develop a human-artificial intelligence interactive diagnostic approach, named radiology generative pretrained transformer (RadGPT), aimed at assisting and synergizing with human users for the interpretation of knee radiological images.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>A total of 22\u2009512 knee roentgen ray images and reports were retrieved from Massachusetts General Hospital; 80% of these were used for model training and 10% were used for model testing and validation, respectively. Fifteen diagnostic imaging features (eg, osteoarthritis, effusion, joint space narrowing, osteophyte) were selected to label images based on their high frequency and clinical relevance in the retrieved official reports. Area under the curve scores were calculated for each feature to assess the diagnostic performance. To evaluate the quality of the generated medical text, historical clinical reports were used as the reference text. Several metrics for text generation tasks are applied, including BiLingual Evaluation Understudy, Recall-Oriented Understudy for Gisting Evaluation, Metric for Evaluation of Translation with Explicit Ordering, and Semantic Propositional Image Caption Evaluation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>RadGPT, in collaboration with human users, achieved area under the curve scores ranging from 0.76 for osteonecrosis to 0.91 for arthroplasty across 15 diagnostic categories for knee conditions. Compared with the baseline LLM method, RadGPT achieved higher scores, specifically 0.18 in BiLingual Evaluation Understudy score, 0.30 in Recall-Oriented Understudy for Gisting Evaluation-L, 0.10 in Metric for Evaluation of Translation with Explicit Ordering, and 0.15 in Semantic Propositional Image Caption Evaluation, which is significantly higher than the baseline LLM method, demonstrating good linguistic overlap and clinical consistency with the reference reports.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>RadGPT has achieved advanced results in knee roentgen ray image feature recognition, illustrating the potential of LLMs in medical image interpretation. The study establishes a training protocol for developing artificial intelligence-assisted tools specifically focusing on the diagnosis and interpretation of knee radiological images.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/radadv\/umaf027","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T11:40:52Z","timestamp":1754480452000},"source":"Crossref","is-referenced-by-count":3,"title":["Visual-language artificial intelligence system for knee radiograph diagnosis and interpretation: a collaborative system with humans"],"prefix":"10.1093","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3790-7373","authenticated-orcid":false,"given":"Xingxin","family":"He","sequence":"first","affiliation":[{"name":"Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School , Boston, MA 02129,","place":["United States"]},{"name":"Department of Radiology, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0245-1270","authenticated-orcid":false,"given":"Zachary E","family":"Stewart","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikitha","family":"Crasta","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Nukala","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Albert","family":"Jang","sequence":"additional","affiliation":[{"name":"Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School , Boston, MA 02129,","place":["United States"]},{"name":"Department of Radiology, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoye","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Radiology, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2781-2899","authenticated-orcid":false,"given":"Richard","family":"Kijowski","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York University , New York, NY 10016,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Radiology, New York University Grossman School of Medicine, New York University , New York, NY 10016,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Stanford University , Stanford, CA 94304,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6964-2536","authenticated-orcid":false,"given":"Rianne A","family":"van der Heijden","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Wisconsin-Madison , Madison, WI 53792,","place":["United States"]},{"name":"Department of Radiology & Nuclear Medicine, Erasmus MC University Medical Center , Rotterdam 3015 GD,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth S","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Wisconsin-Madison , Madison, WI 53792,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2498-6893","authenticated-orcid":false,"given":"Shasha","family":"Li","sequence":"additional","affiliation":[{"name":"Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School , Boston, MA 02129,","place":["United States"]},{"name":"Department of Radiology, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miho J","family":"Tanaka","sequence":"additional","affiliation":[{"name":"Department of Orthopaedic Surgery, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8032-6681","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School , Boston, MA 02129,","place":["United States"]},{"name":"Department of Radiology, Massachusetts General Hospital , Boston, MA 02114,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"issue":"4-5","key":"2025091919550933500_umaf027-B1","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.compmedimag.2007.02.002","article-title":"Computer-aided diagnosis in medical imaging: historical review, current status and future potential","volume":"31","author":"Doi","year":"2007","journal-title":"Comput Med Imaging Graph"},{"issue":"7553","key":"2025091919550933500_umaf027-B2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"issue":"3","key":"2025091919550933500_umaf027-B3","doi-asserted-by":"publisher","first-page":"e210064","DOI":"10.1148\/ryai.210064","article-title":"External validation of deep learning algorithms for radiologic diagnosis: a systematic review","volume":"4","author":"Yu","year":"2022","journal-title":"Radiol Artif Intell"},{"issue":"11","key":"2025091919550933500_umaf027-B4","doi-asserted-by":"publisher","first-page":"713","DOI":"10.21037\/atm.2020.02.44","article-title":"A review of the application of deep learning in medical image classification and segmentation","volume":"8","author":"Cai","year":"2020","journal-title":"Ann Transl Med"},{"issue":"2","key":"2025091919550933500_umaf027-B5","doi-asserted-by":"publisher","first-page":"489","DOI":"10.32604\/cmes.2021.016728","article-title":"Multi-disease prediction based on deep learning: a survey","volume":"128","author":"Xie","year":"2021","journal-title":"Comput Model Eng Sci"},{"issue":"1","key":"2025091919550933500_umaf027-B6","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"2025091919550933500_umaf027-B7","author":"Zhao","year":"2023"},{"key":"2025091919550933500_umaf027-B8","first-page":"27730","volume-title":"Advances in Neural Information Processing Systems","author":"Ouyang","year":"2022"},{"key":"2025091919550933500_umaf027-B9","author":"OpenAI","year":"2023"},{"key":"2025091919550933500_umaf027-B10","author":"Hello GPT-4o"},{"issue":"1","key":"2025091919550933500_umaf027-B11","doi-asserted-by":"publisher","first-page":"bbad493","DOI":"10.1093\/bib\/bbad493","article-title":"Opportunities and challenges for ChatGPT and large language models in biomedicine and health","volume":"25","author":"Tian","year":"2023","journal-title":"Brief Bioinform"},{"issue":"6","key":"2025091919550933500_umaf027-B12","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s10067-004-0934-3","article-title":"Knee osteoarthritis: interpretation variability of radiological signs","volume":"23","author":"Vilalta","year":"2004","journal-title":"Clin Rheumatol"},{"key":"2025091919550933500_umaf027-B13","doi-asserted-by":"publisher","author":"Dosovitskiy","year":"2021","DOI":"10.48550\/arXiv.2010.11929"},{"key":"2025091919550933500_umaf027-B14","doi-asserted-by":"publisher","author":"Touvron","year":"2023","DOI":"10.48550\/arXiv.2302.13971"},{"key":"2025091919550933500_umaf027-B15","author":"Chiang","year":"2023"},{"key":"2025091919550933500_umaf027-B16","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Proc Sys"},{"key":"2025091919550933500_umaf027-B17","author":"Dong","year":"2023"},{"key":"2025091919550933500_umaf027-B18","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","author":"Papineni","year":"2001"},{"key":"2025091919550933500_umaf027-B19","first-page":"74","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"2025091919550933500_umaf027-B20","first-page":"65","author":"Banerjee","year":"2005"},{"key":"2025091919550933500_umaf027-B21","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision\u2014ECCV 2016","author":"Anderson","year":"2016"},{"issue":"3","key":"2025091919550933500_umaf027-B22","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2025091919550933500_umaf027-B23","author":"A simple sequentially rejective multiple test procedure on JSTOR"},{"issue":"Pt 1","key":"2025091919550933500_umaf027-B24","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006X126600","article-title":"Computing inter-rater reliability and its variance in the presence of high agreement","volume":"61","author":"Gwet","year":"2008","journal-title":"Br J Math Stat Psychol"},{"issue":"1","key":"2025091919550933500_umaf027-B25","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ Psychol Meas"},{"key":"2025091919550933500_umaf027-B26","author":"Zhu","year":"2023"},{"key":"2025091919550933500_umaf027-B27","doi-asserted-by":"publisher","first-page":"37","DOI":"10.18653\/v1\/P19-3007","author":"Vig","year":"2019"},{"issue":"4","key":"2025091919550933500_umaf027-B28","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1136\/ard.16.4.494","article-title":"Radiological assessment of osteo-arthrosis","volume":"16","author":"Kellgren","year":"1957","journal-title":"Ann Rheum Dis"},{"issue":"20","key":"2025091919550933500_umaf027-B29","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.1056\/NEJMcp0804745","article-title":"Anterior cruciate ligament tear","volume":"359","author":"Spindler","year":"2008","journal-title":"N Engl J Med"},{"key":"2025091919550933500_umaf027-B30","doi-asserted-by":"publisher","author":"Huang","year":"2023","DOI":"10.48550\/arXiv.2212.10403"}],"container-title":["Radiology Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/radadv\/advance-article-pdf\/doi\/10.1093\/radadv\/umaf027\/63974835\/umaf027.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/5\/umaf027\/63974835\/umaf027.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/5\/umaf027\/63974835\/umaf027.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T23:55:15Z","timestamp":1758326115000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/radadv\/article\/doi\/10.1093\/radadv\/umaf027\/8224589"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"references-count":30,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9,4]]}},"URL":"https:\/\/doi.org\/10.1093\/radadv\/umaf027","relation":{},"ISSN":["2976-9337"],"issn-type":[{"value":"2976-9337","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,9]]},"published":{"date-parts":[[2025,8,7]]},"article-number":"umaf027"}}