{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T03:37:19Z","timestamp":1789961839665,"version":"4.0.1"},"reference-count":13,"publisher":"Springer Science and Business Media LLC","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,5]]},"DOI":"10.7759\/cureus.100845","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T17:46:06Z","timestamp":1767635166000},"source":"Crossref","is-referenced-by-count":5,"title":["Accuracy Is Not Enough: Reasoning and Reference Reliability in Orthopaedic Large Language Model (LLM) Applications"],"prefix":"10.7759","author":[{"given":"Shashwat","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pranav","family":"Chandrasekhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2196\/50945","article-title":"The role of large language models in medical education: applications and implications","volume":"9","author":"Safranek CW","year":"2023","unstructured":"Safranek CW, Sidamon-Eristoff AE, Gilson A, Chartash D. The role of large language models in medical education: applications and implications. JMIR Med Educ. 2023, 9:e50945. 10.2196\/50945","journal-title":"JMIR Med Educ"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40561-024-00313-w","article-title":"Large language models and medical education: a paradigm shift in educator roles","volume":"11","author":"Li Z","year":"2024","unstructured":"Li Z, Li F, Fu Q, Wang X, Liu H, Zhao Y, Ren W. Large language models and medical education: a paradigm shift in educator roles. Smart Learn Environ. 2024, 11:26. 10.1186\/s40561-024-00313-w","journal-title":"Smart Learn Environ"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5435\/JAAOS-D-20-01019","article-title":"Do Orthopaedic In-Training Examination scores predict the likelihood of passing the American Board of Orthopaedic Surgery Part I examination? An update with 2014 to 2018 data","volume":"29","author":"Fritz E","year":"2021","unstructured":"Fritz E, Bednar M, Harrast J, et al.. Do Orthopaedic In-Training Examination scores predict the likelihood of passing the American Board of Orthopaedic Surgery Part I examination? An update with 2014 to 2018 data. J Am Acad Orthop Surg. 2021, 29:e1370-7. 10.5435\/JAAOS-D-20-01019","journal-title":"J Am Acad Orthop Surg"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2106\/JBJS.OA.23.00056","article-title":"Evaluating ChatGPT performance on the Orthopaedic In-Training Examination","volume":"8","author":"Kung JE","year":"2023","unstructured":"Kung JE, Marshall C, Gauthier C, Gonzalez TA, Jackson JB 3rd. Evaluating ChatGPT performance on the Orthopaedic In-Training Examination. JB JS Open Access. 2023, 8:e23.00056. 10.2106\/JBJS.OA.23.00056","journal-title":"JB JS Open Access"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3928\/01477447-20240304-02","article-title":"Performance of two artificial intelligence generative language models on the Orthopaedic In-Training Examination","volume":"47","author":"Lubitz M","year":"2024","unstructured":"Lubitz M, Latario L. Performance of two artificial intelligence generative language models on the Orthopaedic In-Training Examination. Orthopedics. 2024, 47:e146-50. 10.3928\/01477447-20240304-02","journal-title":"Orthopedics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/10225536241268789","article-title":"Comparitive performance of artificial intelligence-based large language models on the Orthopedic In-Training Examination","volume":"33","author":"Xu AY","year":"2025","unstructured":"Xu AY, Singh M, Balmaceno-Criss M, et al.. Comparitive performance of artificial intelligence-based large language models on the Orthopedic In-Training Examination. J Orthop Surg (Hong Kong). 2025, 33:10225536241268789. 10.1177\/10225536241268789","journal-title":"J Orthop Surg (Hong Kong)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0","article-title":"Detecting hallucinations in large language models using semantic entropy","volume":"630","author":"Farquhar S","year":"2024","unstructured":"Farquhar S, Kossen J, Kuhn L, Gal Y. Detecting hallucinations in large language models using semantic entropy. Nature. 2024, 630:625-30. 10.1038\/s41586-024-07421-0","journal-title":"Nature"},{"key":"ref8","unstructured":"Orthopaedic In-Training Examination (OITE) technical report 2024. (2024). Accessed. October 29, 2025: https:\/\/www.aaos.org\/globalassets\/education\/product-pages\/oite\/oite-2024-technical-report-eds.pdf."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2196\/50174","article-title":"ChatGPT in medical education: a precursor for automation bias?","volume":"10","author":"Nguyen T","year":"2024","unstructured":"Nguyen T. ChatGPT in medical education: a precursor for automation bias?. JMIR Med Educ. 2024, 10:e50174. 10.2196\/50174","journal-title":"JMIR Med Educ"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.39238","article-title":"High rates of fabricated and inaccurate references in ChatGPT-generated medical content","volume":"15","author":"Bhattacharyya M","year":"2023","unstructured":"Bhattacharyya M, Miller VM, Bhattacharyya D, Miller LE. High rates of fabricated and inaccurate references in ChatGPT-generated medical content. Cureus. 2023, 15:e39238. 10.7759\/cureus.39238","journal-title":"Cureus"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2196\/53164","article-title":"Hallucination rates and reference accuracy of ChatGPT and Bard for systematic reviews: comparative analysis","volume":"26","author":"Chelli M","year":"2024","unstructured":"Chelli M, Descamps J, Lavou\u00e9 V, et al.. Hallucination rates and reference accuracy of ChatGPT and Bard for systematic reviews: comparative analysis. J Med Internet Res. 2024, 26:e53164. 10.2196\/53164","journal-title":"J Med Internet Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.55945","article-title":"Evaluating ChatGPT's capabilities on orthopedic training examinations: an analysis of new image processing features","volume":"16","author":"Posner KM","year":"2024","unstructured":"Posner KM, Bakus C, Basralian G, Chester G, Zeiman M, O'Malley GR, Klein GR. Evaluating ChatGPT's capabilities on orthopedic training examinations: an analysis of new image processing features. Cureus. 2024, 16:e55945. 10.7759\/cureus.55945","journal-title":"Cureus"},{"key":"ref13","unstructured":"Ethics and Governance of Artificial Intelligence for Health. WHO Guidance. (2021). Accessed: October 13, 2025: https:\/\/www.who.int\/publications\/i\/item\/9789240029200."}],"container-title":["Cureus"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cureus.com\/articles\/430887-accuracy-is-not-enough-reasoning-and-reference-reliability-in-orthopaedic-large-language-model-llm-applications","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T17:46:07Z","timestamp":1767635167000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cureus.com\/articles\/430887-accuracy-is-not-enough-reasoning-and-reference-reliability-in-orthopaedic-large-language-model-llm-applications"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":13,"URL":"https:\/\/doi.org\/10.7759\/cureus.100845","relation":{},"ISSN":["2168-8184"],"issn-type":[{"value":"2168-8184","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1,5]]}}}