{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T18:10:12Z","timestamp":1784052612961,"version":"3.55.0"},"reference-count":27,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Supracondylar humeral fractures constitute 10\u201316% of pediatric skeletal injuries, requiring timely diagnosis to prevent neurovascular complications. Developmental variations in pediatric bone structures pose diagnostic challenges for clinicians. This study evaluated three next-generation large language models (LLMs) (ChatGPT-4o, Gemini 2.0, Claude 3.5) for detecting pediatric supracondylar humeral fractures and their classification according to the Gartland system.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective observational study included 300 pediatric patients (150 with supracondylar humeral fractures confirmed by expert consensus, 150 without fractures) aged 2\u201310 years presenting to the Emergency Department of the Bilkent City Hospital (October 2022-January 2025). Two-view elbow radiographs were presented to each LLM three times on different days. Diagnostic accuracy was evaluated using overall accuracy (all three responses correct), strict accuracy (\u22652 correct responses), and ideal accuracy (\u22651 correct response). Response consistency was assessed using Fleiss\u2019 Kappa coefficient. Fractures were classified according to modified Gartland criteria.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Gemini 2.0 demonstrated highest sensitivity (68.4%) followed by Claude 3.5 (58.7%) and ChatGPT-4o (19.3%) for fracture detection (p\u2009&lt;\u20090.001). Ideal accuracy rates were 83.3%, 78.7%, and 27.3% respectively. Although ideal accuracy rates exceeded 91% in non-fracture cases, specificity remained low (33.1\u201336.0%), indicating a high rate of false-positive classifications. Response consistency was very good for ChatGPT-4o (\u03ba\u2009=\u20090.69) and Gemini 2.0 (\u03ba\u2009=\u20090.61), good for Claude 3.5 (\u03ba\u2009=\u20090.44). For Gartland classification, Gemini 2.0 achieved highest accuracy: Type I (83.3%), Type II (62.4%), Type III (68.7%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Current LLMs demonstrate limited capability as independent diagnostic tools for pediatric supracondylar humeral fractures. Gemini 2.0\u2019s 68.4% sensitivity indicates these technologies require specialized pediatric training before clinical implementation. However, their potential as assistive tools for triage and assessment warrants further development of pediatric-specific models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0353782","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T17:34:47Z","timestamp":1784050487000},"page":"e0353782","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence meets pediatric orthopedics: A comparative analysis of ChatGPT-4o, Gemini 2.0, and Claude 3.5 in detecting supracondylar humeral fractures"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1749-8098","authenticated-orcid":true,"given":"Utku Murat","family":"Kalafat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H\u00fcseyin","family":"Mutlu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramiz","family":"Yaz\u0131c\u0131","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Murat","family":"Gen\u00e7","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bensu","family":"Bulut","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6320-9667","authenticated-orcid":true,"given":"Medine Akkan","family":"\u00d6z","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9521-1120","authenticated-orcid":true,"given":"Ay\u015fenur","family":"G\u00fcr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6744-2423","authenticated-orcid":true,"given":"Mehmet","family":"Yortanl\u0131","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"U\u011fur","family":"\u015eakar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"pone.0353782.ref001","first-page":"9892152","article-title":"Recent Development in X-Ray Imaging Technology: Future and Challenges","volume":"2021","author":"X Ou","year":"2021","journal-title":"Research (Wash D C)"},{"issue":"5","key":"pone.0353782.ref002","doi-asserted-by":"crossref","first-page":"633","DOI":"10.5152\/dir.2021.20497","article-title":"Chest X-ray in intensive care unit patients: what there is to know about thoracic devices","volume":"27","author":"E Baratella","year":"2021","journal-title":"Diagn Interv Radiol"},{"issue":"11","key":"pone.0353782.ref003","doi-asserted-by":"crossref","first-page":"1036","DOI":"10.1001\/archinternmed.2011.234","article-title":"Effect of computerized physician order entry on radiologic examination order indication quality","volume":"171","author":"E Schneider","year":"2011","journal-title":"Arch Intern Med"},{"issue":"2","key":"pone.0353782.ref004","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.acra.2005.10.017","article-title":"Evaluation of the quality of radiology requisitions for intensive care unit patients","volume":"13","author":"MD Cohen","year":"2006","journal-title":"Acad Radiol"},{"issue":"6","key":"pone.0353782.ref005","doi-asserted-by":"crossref","first-page":"3197","DOI":"10.1007\/s11845-023-03377-8","article-title":"GPT-4: a new era of artificial intelligence in medicine","volume":"192","author":"E Waisberg","year":"2023","journal-title":"Ir J Med Sci"},{"issue":"7","key":"pone.0353782.ref006","doi-asserted-by":"crossref","first-page":"4096","DOI":"10.1097\/JS9.0000000000001359","article-title":"Step into the era of large multimodal models: a pilot study on ChatGPT-4V(ision)\u2019s ability to interpret radiological images","volume":"110","author":"L Zhu","year":"2024","journal-title":"Int J Surg"},{"issue":"8","key":"pone.0353782.ref007","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology","volume":"18","author":"A Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"issue":"3","key":"pone.0353782.ref008","doi-asserted-by":"crossref","first-page":"471","DOI":"10.52312\/jdrs.2024.57923","article-title":"The main goal of ChatGPT is not to replace healthcare professionals","volume":"35","author":"O\u015e Atik","year":"2024","journal-title":"Jt Dis Relat Surg"},{"issue":"2","key":"pone.0353782.ref009","doi-asserted-by":"crossref","first-page":"484","DOI":"10.52312\/jdrs.2022.57906","article-title":"Artificial intelligence, machine learning, and deep learning in orthopedic surgery","volume":"33","author":"O\u015e Atik","year":"2022","journal-title":"Jt Dis Relat Surg"},{"issue":"1","key":"pone.0353782.ref010","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s11604-018-0795-3","article-title":"Technical and clinical overview of deep learning in radiology","volume":"37","author":"D Ueda","year":"2019","journal-title":"Jpn J Radiol"},{"issue":"1","key":"pone.0353782.ref011","doi-asserted-by":"crossref","first-page":"1108","DOI":"10.21037\/qims-23-892","article-title":"The role of large language models in medical image processing: a narrative review","volume":"14","author":"D Tian","year":"2024","journal-title":"Quant Imaging Med Surg"},{"issue":"5","key":"pone.0353782.ref012","doi-asserted-by":"crossref","first-page":"194","DOI":"10.3390\/jpm15050194","article-title":"The Accuracy of ChatGPT-4o in Interpreting Chest and Abdominal X-Ray Images","volume":"15","author":"PG Lacaita","year":"2025","journal-title":"J Pers Med"},{"key":"pone.0353782.ref013","doi-asserted-by":"crossref","DOI":"10.2196\/55627","article-title":"Evaluating ChatGPT-4\u2019s Diagnostic Accuracy: Impact of Visual Data Integration","volume":"12","author":"T Hirosawa","year":"2024","journal-title":"JMIR Med Inform"},{"key":"pone.0353782.ref014","doi-asserted-by":"crossref","unstructured":"Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM. ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 3462\u201371. https:\/\/doi.org\/10.1109\/cvpr.2017.369","DOI":"10.1109\/CVPR.2017.369"},{"issue":"4","key":"pone.0353782.ref015","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1001\/jamaophthalmol.2024.0017","article-title":"Accuracy of an Artificial Intelligence Chatbot\u2019s Interpretation of Clinical Ophthalmic Images","volume":"142","author":"A Mihalache","year":"2024","journal-title":"JAMA Ophthalmol"},{"issue":"6","key":"pone.0353782.ref016","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1097\/RLU.0000000000005207","article-title":"Keeping Up With ChatGPT: Evaluating Its Recognition and Interpretation of Nuclear Medicine Images","volume":"49","author":"JMM Rogasch","year":"2024","journal-title":"Clin Nucl Med"},{"issue":"2","key":"pone.0353782.ref017","article-title":"Evaluating GPT-V4 (GPT-4 with Vision) on Detection of Radiologic Findings on Chest Radiographs","volume":"311","author":"Y Zhou","year":"2024","journal-title":"Radiology"},{"issue":"1","key":"pone.0353782.ref018","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1007\/s00330-024-10902-5","article-title":"ChatGPT\u2019s diagnostic performance based on textual vs. visual information compared to radiologists\u2019 diagnostic performance in musculoskeletal radiology","volume":"35","author":"D Horiuchi","year":"2025","journal-title":"Eur Radiol"},{"issue":"3","key":"pone.0353782.ref019","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1007\/s00330-024-11115-6","article-title":"Revolution or risk?-Assessing the potential and challenges of GPT-4V in radiologic image interpretation","volume":"35","author":"MS Huppertz","year":"2025","journal-title":"Eur Radiol"},{"issue":"10","key":"pone.0353782.ref020","doi-asserted-by":"crossref","first-page":"987","DOI":"10.14744\/tjtes.2025.98680","article-title":"Diagnostic capabilities of large language models in the detection of scaphoid fractures in the emergency department","volume":"31","author":"B Bulut","year":"2025","journal-title":"Ulus Travma Acil Cerrahi Derg"},{"issue":"16","key":"pone.0353782.ref021","doi-asserted-by":"crossref","DOI":"10.5435\/JAAOS-D-24-01049","article-title":"Comparison of ChatGPT\u2019s Diagnostic and Management Accuracy of Foot and Ankle Bone-Related Pathologies to Orthopaedic Surgeons","volume":"33","author":"MD Essis","year":"2025","journal-title":"J Am Acad Orthop Surg"},{"issue":"8","key":"pone.0353782.ref022","article-title":"GPT-4: The Future of Cosmetic Procedure Consultation?","volume":"43","author":"Y-X Sun","year":"2023","journal-title":"Aesthet Surg J"},{"issue":"12","key":"pone.0353782.ref023","article-title":"Can AI Think Like a Plastic Surgeon? Evaluating GPT-4\u2019s Clinical Judgment in Reconstructive Procedures of the Upper Extremity","volume":"11","author":"T Leypold","year":"2023","journal-title":"Plast Reconstr Surg Glob Open"},{"issue":"1","key":"pone.0353782.ref024","article-title":"Evaluating ChatGPT\u2019s Performance in Classifying Pertrochanteric Fractures Based on Arbeitsgemeinschaft f\u00fcr Osteosynthesefragen\/Orthopedic Trauma Association (AO\/OTA) Standards","volume":"17","author":"M Noda","year":"2025","journal-title":"Cureus"},{"issue":"7","key":"pone.0353782.ref025","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1007\/s00247-024-05935-3","article-title":"Gartland classification concordance of supracondylar fractures among pediatric emergency medicine physicians, radiologists, and orthopedic surgeons","volume":"54","author":"RJ Schultz","year":"2024","journal-title":"Pediatr Radiol"},{"key":"pone.0353782.ref026","article-title":"Convolutional neural networks in paediatric fracture detection: pooled evidence from a systematic review and meta-analysis","author":"A Pervez","year":"2026","journal-title":"Eur Radiol"},{"issue":"2","key":"pone.0353782.ref027","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.1007\/s00068-022-02136-1","article-title":"Development and external validation of automated detection, classification, and localization of ankle fractures: inside the black box of a convolutional neural network (CNN)","volume":"49","author":"J Prijs","year":"2023","journal-title":"Eur J Trauma Emerg Surg"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T17:34:53Z","timestamp":1784050493000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353782"}},"subtitle":[],"editor":[{"given":"Lisong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":27,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353782","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]}}}