{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T01:26:12Z","timestamp":1794878772068,"version":"4.9.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"vor","delay-in-days":39,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Sports Sci Med Rehabil"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Large language models (LLMs) have shown increasing relevance in clinically supervised decision-support frameworks; however, their performance in orthopedic sports injury scenarios remains unclear. This study aimed to comparatively evaluate the diagnostic, treatment, and rehabilitation recommendations generated by GPT-4o and GPT-5 using standardized clinical scenarios assessed by orthopedic specialists.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Fifteen sports injury\u2013based clinical scenarios were developed and validated by orthopedic specialists with subspecialty expertise in sports traumatology. Each scenario was scored for clinical realism, adequacy of physical examination findings, and adequacy of radiological information using a 7-point Likert scale adapted from AGREE II domains. Both GPT-4o and GPT-5 were prompted using standardized zero-shot instructions, with each scenario submitted three times to assess internal consistency. Two blinded orthopedic specialists evaluated content-level consistency, and five independent orthopedic specialists scored the expert-rated clinical adequacy of AI-generated responses on a 0\u20135 scale. Inter-rater reliability was assessed using the intraclass correlation coefficient (ICC) and Cohen\u2019s kappa.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Specialists rated the clinical scenarios favorably, with 69\u201372% agreement across domains and ICC values indicating good reliability for clinical realism (ICC\u2009=\u20090.725) and moderate reliability for physical examination (ICC\u2009=\u20090.634) and radiological adequacy (ICC\u2009=\u20090.512). GPT-4o produced consistent outputs in 93.3% of cases, with one scenario showing clinically relevant inconsistency (\u03ba\u2009=\u20090.82). Comparative expert evaluation demonstrated significantly higher scores for GPT-5 (median\u2009=\u20094.60) than GPT-4o (median\u2009=\u20094.00) (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.007). Inter-rater reliability for AI response scoring was high for both models (ICC\u2009=\u20090.888 for GPT-4o; ICC\u2009=\u20090.895 for GPT-5).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GPT-4o and GPT-5 generated responses with generally high expert-rated clinical adequacy and strong consistency in standardized sports injury\u2013related clinical scenarios, with GPT-5 achieving higher scores in expert evaluations. By providing a structured, specialty-specific expert assessment under controlled conditions, this study adds comparative insight into how contemporary large language models are perceived in orthopedic sports injury contexts, without implying objective diagnostic accuracy or autonomous clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13102-026-01675-z","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T02:33:54Z","timestamp":1774838034000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Large language models in sports injury care: a comparative expert evaluation of GPT-4o and GPT-5"],"prefix":"10.1186","volume":"18","author":[{"given":"Onur","family":"Kaya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gazi","family":"Huri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emre An\u0131l","family":"\u00d6zbek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nevzat","family":"G\u00f6nder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u0130brahim Halil","family":"Demir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaan Ali","family":"Dalk\u0131r","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"issue":"6","key":"1675_CR1","doi-asserted-by":"publisher","first-page":"2534","DOI":"10.1016\/j.jseint.2023.07.018","volume":"7","author":"M Daher","year":"2023","unstructured":"Daher M, Koa J, Boufadel P, Singh J, Fares MY, Abboud JA. Breaking barriers: can ChatGPT compete with a shoulder and elbow specialist in diagnosis and management? JSES Int. 2023;7(6):2534\u201341.","journal-title":"JSES Int"},{"issue":"6","key":"1675_CR2","doi-asserted-by":"publisher","first-page":"100323","DOI":"10.1016\/j.jisako.2024.100323","volume":"9","author":"BT Lack","year":"2024","unstructured":"Lack BT, Mouhawasse E, Childers JT, Jackson GR, Daji SV, Yerke-Hansen P, et al. Can ChatGPT answer patient questions regarding reverse shoulder arthroplasty? J ISAKOS. 2024;9(6):100323.","journal-title":"J ISAKOS"},{"issue":"5","key":"1675_CR3","doi-asserted-by":"publisher","first-page":"100963","DOI":"10.1016\/j.asmr.2024.100963","volume":"6","author":"M Megalla","year":"2024","unstructured":"Megalla M, Hahn AK, Bauer JA, Windsor JT, Grace ZT, Gedman MA, et al. ChatGPT and Google Provide Mostly Excellent or Satisfactory Responses to the Most Frequently Asked Patient Questions Related to Rotator Cuff Repair. Arthrosc Sports Med Rehabil. 2024;6(5):100963.","journal-title":"Arthrosc Sports Med Rehabil"},{"key":"1675_CR4","doi-asserted-by":"publisher","first-page":"1504532","DOI":"10.3389\/fmed.2024.1504532","volume":"11","author":"S Maaz","year":"2024","unstructured":"Maaz S, Palaganas JC, Palaganas G, Bajwa M. A guide to prompt design: foundations and applications for healthcare simulationists. Front Med (Lausanne). 2024;11:1504532.","journal-title":"Front Med (Lausanne)"},{"issue":"10","key":"1675_CR5","doi-asserted-by":"publisher","first-page":"e1511","DOI":"10.3109\/0142159X.2013.818632","volume":"35","author":"I Motola","year":"2013","unstructured":"Motola I, Devine LA, Chung HS, Sullivan JE, Issenberg SB. Simulation in healthcare education: a best evidence practical guide. AMEE Guide 82 Med Teach. 2013;35(10):e1511\u201330.","journal-title":"AMEE Guide 82 Med Teach"},{"key":"1675_CR6","unstructured":"Cai C, Jongejan J. The effects of example-based prompts on clinical reasoning in large language models. In 24th International Conference on Intelligent User Interfaces (IUI \u201919). 2019."},{"key":"1675_CR7","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.jor.2024.12.039","volume":"66","author":"A Velasquez Garcia","year":"2025","unstructured":"Velasquez Garcia A, Minami M, Mejia-Rodriguez M, Ortiz-Morales JR, Radice F. Large language models in orthopedics: An exploratory research trend analysis and machine learning classification. J Orthop. 2025;66:110\u20138.","journal-title":"J Orthop"},{"issue":"18","key":"1675_CR8","doi-asserted-by":"publisher","first-page":"E839","DOI":"10.1503\/cmaj.090449","volume":"182","author":"MC Brouwers","year":"2010","unstructured":"Brouwers MC, Kho ME, Browman GP, Burgers JS, Cluzeau F, Feder G, et al. AGREE II: advancing guideline development, reporting and evaluation in health care. CMAJ. 2010;182(18):E839\u201342.","journal-title":"CMAJ"},{"key":"1675_CR9","doi-asserted-by":"crossref","unstructured":"Chundi G, Dawar A, Sarwar S, Prasad S, Vosbikian M. Ahmed, I. Comparative evaluation of LLMs in orthopedic surgery. J Orthop Rep. 2025.","DOI":"10.1016\/j.jorep.2025.100728"},{"issue":"3","key":"1675_CR10","doi-asserted-by":"publisher","first-page":"e076484","DOI":"10.1136\/bmjopen-2023-076484","volume":"14","author":"J Caterson","year":"2024","unstructured":"Caterson J, Ambler O, Cereceda-Monteoliva N, Horner M, Jones A, Poacher AT. Application of generative language models to orthopaedic practice. BMJ Open. 2024;14(3):e076484.","journal-title":"BMJ Open"},{"issue":"1","key":"1675_CR11","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1186\/s12911-025-03024-5","volume":"25","author":"YC Chen","year":"2025","unstructured":"Chen YC, Lee SH, Sheu H, Lin SH, Hu CC, Fu SC, et al. Enhancing responses from large language models with role-playing prompts: a comparative study on answering frequently asked questions about total knee arthroplasty. BMC Med Inf Decis Mak. 2025;25(1):196.","journal-title":"BMC Med Inf Decis Mak"},{"issue":"12","key":"1675_CR12","doi-asserted-by":"publisher","first-page":"2629","DOI":"10.1007\/s10439-023-03272-4","volume":"51","author":"L Giray","year":"2023","unstructured":"Giray L. Prompt Engineering with ChatGPT: A Guide for Academic Writers. Ann Biomed Eng. 2023;51(12):2629\u201333.","journal-title":"Ann Biomed Eng"},{"key":"1675_CR13","doi-asserted-by":"crossref","unstructured":"Comrie D. ChatGPT Decision Support System: Utility in Creating Public Policy for Concussion\/Repetitive Brain Trauma Associated With Neurodegenerative Diseases. medRxiv. 2023.","DOI":"10.1101\/2023.04.17.23288681"},{"key":"1675_CR14","doi-asserted-by":"crossref","unstructured":"Williamson A, Tavabi N, Kalepalli N, Lavoie-Gagne O, Weiss A, Bijwadia SR. Large Language Models for Zero-Shot Procedure Extraction in Orthopedic Surgery: A Comparative Evaluation. medRxiv. 2025.","DOI":"10.1101\/2025.08.19.25333995"},{"issue":"5","key":"1675_CR15","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1016\/j.arthro.2024.06.021","volume":"41","author":"KN Kunze","year":"2025","unstructured":"Kunze KN, Varady NH, Mazzucco M, Lu AZ, Chahla J, Martin RK, et al. The Large Language Model ChatGPT-4 Exhibits Excellent Triage Capabilities and Diagnostic Performance for Patients Presenting With Various Causes of Knee Pain. Arthroscopy. 2025;41(5):1438\u201347. e14.","journal-title":"Arthroscopy"},{"key":"1675_CR16","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1126\/scitranslmed.abb1655","volume":"13","author":"MBA McDermott","year":"2021","unstructured":"McDermott MBA, Wang S, Marinsek N, Ranganath R, Foschini L, Ghassemi M. Reproducibility in machine learning for health research: Still a ways to go. Sci Transl Med. 2021;13:586.","journal-title":"Sci Transl Med"},{"issue":"7","key":"1675_CR17","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1302\/2046-3758.127.BJR-2023-0111.R1","volume":"12","author":"AB Lisacek-Kiosoglous","year":"2023","unstructured":"Lisacek-Kiosoglous AB, Powling AS, Fontalis A, Gabr A, Mazomenos E, Haddad FS. Artificial intelligence in orthopaedic surgery. Bone Joint Res. 2023;12(7):447\u201354.","journal-title":"Bone Joint Res"},{"key":"1675_CR18","doi-asserted-by":"crossref","unstructured":"Hartman HMD, McGrath T, Gillaspie C, Savage-Elliott I. Can ChatGPT-4 Think Like an Orthopaedic Surgeon. Testing Clinical Judgement and Diagnostic Ability in Pathologies of the Foot and Ankle. AOFAS Annual Meeting. 2024; 12.2024: Foot & Ankle Orthopaedics,; 2024.","DOI":"10.1177\/2473011424S00172"},{"key":"1675_CR19","doi-asserted-by":"publisher","first-page":"22","DOI":"10.4103\/jehp.jehp_625_23","volume":"13","author":"AD Roy","year":"2024","unstructured":"Roy AD, Das D, Mondal H. Efficacy of ChatGPT in solving attitude, ethics, and communication case scenario used for competency-based medical education in India: A case study. J Educ Health Promot. 2024;13:22.","journal-title":"J Educ Health Promot"},{"key":"1675_CR20","doi-asserted-by":"crossref","unstructured":"Drouaud A, Stocchi C, Tang J, Gonsalves G, Cheung Z, Szatkowski J et al. Exploring the Performance of ChatGPT in an Orthopaedic Setting and Its Potential Use as an Educational Tool. JB JS Open Access. 2024;9(4).","DOI":"10.2106\/JBJS.OA.24.00081"},{"issue":"2","key":"1675_CR21","doi-asserted-by":"publisher","first-page":"86","DOI":"10.4103\/jiag.jiag_27_23","volume":"19","author":"KD Mittal","year":"2023","unstructured":"Mittal KD, Minakshi. Use of ChatGPT by Physicians to Build Rehabilitation Plans for the Elderly A Mini-Review of Case Studies. J Indian Acad Geriatr. 2023;19(2):86\u201393.","journal-title":"J Indian Acad Geriatr"},{"key":"1675_CR22","doi-asserted-by":"crossref","unstructured":"Javaid M, Haleema A, Singh RP. Chat GPT for healthcare services: An emerging stage for an innovative perspective. Bench Council Transactionson Benchmarks Stand Evaluations. 2023;3(1).","DOI":"10.1016\/j.tbench.2023.100105"},{"key":"1675_CR23","doi-asserted-by":"publisher","first-page":"e55318","DOI":"10.2196\/55318","volume":"12","author":"S Sivarajkumar","year":"2024","unstructured":"Sivarajkumar S, Kelley M, Samolyk-Mazzanti A, Visweswaran S, Wang Y. An empirical evaluation of prompting strategies for large language models in zero-shot clinical natural language processing: algorithm development and validation study. JMIR Med Inf. 2024;12:e55318.","journal-title":"JMIR Med Inf"},{"issue":"17","key":"1675_CR24","doi-asserted-by":"publisher","first-page":"5101","DOI":"10.3390\/jcm13175101","volume":"13","author":"K Shah","year":"2024","unstructured":"Shah K, Xu AY, Sharma Y, Daher M, McDonald C, Diebo BG, Daniels AH. Large language model prompting techniques for advancement in clinical medicine. J Clin Med. 2024;13(17):5101.","journal-title":"J Clin Med"}],"container-title":["BMC Sports Science, Medicine and Rehabilitation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13102-026-01675-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13102-026-01675-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13102-026-01675-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:06:16Z","timestamp":1781643976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13102-026-01675-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":24,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1675"],"URL":"https:\/\/doi.org\/10.1186\/s13102-026-01675-z","relation":{},"ISSN":["2052-1847"],"issn-type":[{"value":"2052-1847","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"17 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This study did not involve human participants, patient data, or interventions requiring institutional ethics approval. All clinical scenarios were artificially constructed and did not include identifiable patient information.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable. No individual person\u2019s data, images, or identifiable materials are included in this manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"232"}}