{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T07:55:29Z","timestamp":1790841329522,"version":"4.1.0"},"reference-count":32,"publisher":"Ovid Technologies (Wolters Kluwer Health)","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title\/>\n                    <jats:p>\n                      Accurate detection of pediatric supracondylar humerus fractures remains a diagnostic challenge in emergency settings. To address this, we developed and validated a transfer-learning model, benchmarking its performance against board-certified emergency physicians. A retrospective dataset of 1440 anonymized pediatric elbow radiographs (720 fractures and 720 normal) was preprocessed using grayscale normalization, aspect-ratio-preserving resizing, adaptive denoising, and contrast-limited adaptive histogram equalization. Data were split at the patient level into training and validation (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      \u2005=\u20051295) and a held-out test set (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      \u2005=\u2005145). A pretrained ResNet50 backbone was fine-tuned, and model stability was assessed via five-fold stratified cross-validation. Clinical applicability was evaluated in a blinded reader study where 20 emergency physicians interpreted 200 radiographs. On the held-out test set, the model achieved 90.34% accuracy, 93.5% sensitivity, and 86.8% specificity. Five-fold cross-validation yielded a mean accuracy of 91.72%, sensitivity of 92.8%, and specificity of 88.5%. In the reader study, emergency physicians achieved a mean accuracy of 87.6%, sensitivity of 90.5%, and specificity of 84.7%. Diagnostic performance differences between the model and physicians were not statistically significant (\n                      <jats:italic toggle=\"yes\">P<\/jats:italic>\n                      \u2005&gt;\u20050.05). The transfer-learning model achieved clinician-comparable performance, indicating its potential utility as an initial triage tool. However, the algorithm shares human diagnostic limitations, exhibiting lower sensitivity for nondisplaced Gartland type I fractures. Therefore, based on current data, it cannot be concluded that artificial intelligence implementation will eliminate the risk of missed fractures. Prospective multicenter validation is required before clinical deployment.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence<\/jats:title>\n                    <jats:p>Level III (retrospective diagnostic study).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/bpb.0000000000001401","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T07:00:26Z","timestamp":1790838026000},"update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence\u2013assisted diagnosis of pediatric supracondylar humerus fractures: a deep learning\u2013based clinical decision support model"],"prefix":"10.1097","author":[{"given":"Ya\u015far Samet","family":"Gokceoglu","sequence":"first","affiliation":[{"name":"Department of Orthopaedics and Traumatology, Mehmet Akif Inan Education and Research Hospital, Sanliurfa"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammed Furkan","family":"Darilmaz","sequence":"additional","affiliation":[{"name":"Department of Orthopedics and Traumatology, Training and Research Hospital, Aksaray University, Aksaray"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00d6mer Levent","family":"Karadamar","sequence":"additional","affiliation":[{"name":"Department of Orthopedics and Traumatology, D\u00f6\u015femealtI State Hospital, Antalya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harun","family":"Cig","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Engineering Faculty, Harran University, Sanliurfa, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"R1-20261001","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1007\/s00590-021-02932-2","article-title":"Overview of the contemporary management of supracondylar humeral fractures in children.","volume":"31","author":"Duffy","year":"2021","journal-title":"Eur J Orthop Surg Traumatol"},{"key":"R2-20261001","first-page":"145","article-title":"Management of supracondylar fractures of the humerus in children.","volume":"109","author":"Gartland","year":"1959","journal-title":"Surg Gynecol Obstet"},{"key":"R3-20261001","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1007\/s11999-014-4033-8","article-title":"Classifications in brief: the Gartland classification of supracondylar humerus fractures.","volume":"473","author":"Alton","year":"2015","journal-title":"Clin Orthop Relat Res"},{"key":"R4-20261001","doi-asserted-by":"crossref","first-page":"839","DOI":"10.1186\/s13018-025-06275-0","article-title":"A clinical study of percutaneous Kirschner wire fixation in pediatric supracondylar humeral fractures with medial column impaction: surgical technique and outcomes.","volume":"20","author":"Liang","year":"2025","journal-title":"J Orthop Surg Res"},{"key":"R5-20261001","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1007\/s00330-025-11947-w","article-title":"Diagnostic value of artificial intelligence-based software for the detection of pediatric upper extremity fractures.","volume":"36","author":"Mollica","year":"2026","journal-title":"Eur Radiol"},{"key":"R6-20261001","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.3928\/01477447-20081201-23","article-title":"Accuracy of emergency room physicians\u2019 interpretation of elbow fractures in children.","volume":"31","author":"Shrader","year":"2008","journal-title":"Orthopedics"},{"key":"R7-20261001","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1136\/emermed-2024-214047","article-title":"Black and white: how good are clinicians at diagnosing elbow injuries from paediatric elbow radiographs alone?","volume":"41","author":"Dann","year":"2024","journal-title":"Emerg Med J"},{"key":"R8-20261001","first-page":"72","article-title":"Missed elbow trauma in children: value of radiograph assessment in an emergency department. a review of 136 cases.","volume":"87-B","author":"Orsoni","year":"2005","journal-title":"Orthop Proc"},{"key":"R9-20261001","doi-asserted-by":"crossref","first-page":"e190023","DOI":"10.1148\/ryai.2020190023","article-title":"Automatic hip fracture identification and functional subclassification with deep learning.","volume":"2","author":"Krogue","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"R10-20261001","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/s12178-008-9027-2","article-title":"Pediatric supracondylar fractures of the distal humerus.","volume":"1","author":"Brubacher","year":"2008","journal-title":"Curr Rev Musculoskelet Med"},{"key":"R11-20261001","doi-asserted-by":"crossref","first-page":"112498","DOI":"10.1016\/j.ejrad.2025.112498","article-title":"Assessing deep learning artificial intelligence support for detecting elbow fractures in the pediatric emergency department.","volume":"194","author":"Costa","year":"2026","journal-title":"Eur J Radiol"},{"key":"R12-20261001","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1148\/radiol.211785","article-title":"Artificial intelligence in fracture detection: a systematic review and meta-analysis.","volume":"304","author":"Kuo","year":"2022","journal-title":"Radiology"},{"key":"R13-20261001","doi-asserted-by":"crossref","first-page":"h5527","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies.","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"R14-20261001","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.2106\/00004623-199412000-00006","article-title":"Ultrasonographic evaluation of the elbow in infants and young children after suspected trauma.","volume":"76","author":"Davidson","year":"1994","journal-title":"J Bone Joint Surg Am"},{"key":"R15-20261001","doi-asserted-by":"crossref","first-page":"W192","DOI":"10.2214\/AJR.14.12788","article-title":"Distal humeral epiphyseal separation in young children: an often-missed fracture-radiographic signs and ultrasound confirmatory diagnosis.","volume":"204","author":"Supakul","year":"2015","journal-title":"AJR Am J Roentgenol"},{"key":"R16-20261001","first-page":"235","article-title":"Short-term management outcomes of supracondylar fractures of the humerus and their associated factors in children managed at Mulago National Referral Hospital.","volume":"14","author":"Sheikdon","year":"2022","journal-title":"Orthop Res Rev"},{"key":"R17-20261001","doi-asserted-by":"crossref","first-page":"806","DOI":"10.9717\/kmms.2015.18.7.806","article-title":"The clip limit decision of contrast limited adaptive histogram equalization for X-ray images using Fuzzy logic.","volume":"18","author":"Cho","year":"2015","journal-title":"J Korea Multimed Soc"},{"key":"R18-20261001","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1148\/radiol.210937","article-title":"Improving radiographic fracture recognition performance and efficiency using artificial intelligence.","volume":"302","author":"Guermazi","year":"2022","journal-title":"Radiology"},{"key":"R19-20261001","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.3174\/ajnr.A7179","article-title":"Diagnostic accuracy and failure mode analysis of a deep learning algorithm for the detection of cervical spine fractures.","volume":"42","author":"Voter","year":"2021","journal-title":"AJNR Am J Neuroradiol"},{"key":"R20-20261001","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1097\/00006565-199712000-00021","article-title":"Pediatric elbow trauma.","volume":"13","author":"Skaggs","year":"1997","journal-title":"Pediatr Emerg Care"},{"key":"R21-20261001","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.diii.2023.09.008","article-title":"External validation of an artificial intelligence solution for the detection of elbow fractures and joint effusions in children.","volume":"105","author":"Dupuis","year":"2024","journal-title":"Diagn Interv Imaging"},{"key":"R22-20261001","doi-asserted-by":"crossref","first-page":"e38503","DOI":"10.1097\/MD.0000000000038503","article-title":"Automatic diagnosis of pediatric supracondylar humerus fractures using radiomics-based machine learning.","volume":"103","author":"Yao","year":"2024","journal-title":"Medicine (Baltim)"},{"key":"R23-20261001","doi-asserted-by":"crossref","first-page":"208","DOI":"10.4103\/singaporemedj.SMJ-2022-078","article-title":"Use of deep learning model for paediatric elbow radiograph binomial classification: initial experience, performance and lessons learnt.","volume":"66","author":"Tan","year":"2025","journal-title":"Singapore Med J"},{"key":"R24-20261001","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s00068-025-02779-w","article-title":"Impact of deep learning on pediatric elbow fracture detection: a systematic review and meta-analysis.","volume":"51","author":"Binh","year":"2025","journal-title":"Eur J Trauma Emerg Surg"},{"key":"R25-20261001","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1016\/j.crad.2024.04.009","article-title":"Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis.","volume":"79","author":"Nowroozi","year":"2024","journal-title":"Clin Radiol"},{"key":"R26-20261001","doi-asserted-by":"crossref","first-page":"2882","DOI":"10.3390\/diagnostics15222882","article-title":"Flexing ChatGPT-4o\u2019s diagnostic muscle: detection of fractures in the ossifying pediatric elbow on radiographs.","volume":"15","author":"Phua","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"R27-20261001","doi-asserted-by":"crossref","first-page":"e250540","DOI":"10.1148\/radiol.250540","article-title":"Impact of test set composition on AI performance for pediatric radiograph appendicular skeleton fracture detection.","volume":"318","author":"Stranger","year":"2026","journal-title":"Radiology"},{"key":"R28-20261001","doi-asserted-by":"crossref","first-page":"5469","DOI":"10.1007\/s00330-019-06167-y","article-title":"Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs.","volume":"29","author":"Cheng","year":"2019","journal-title":"Eur Radiol"},{"key":"R29-20261001","doi-asserted-by":"crossref","first-page":"e216096","DOI":"10.1001\/jamanetworkopen.2021.6096","article-title":"Development and validation of a deep learning model using convolutional neural networks to identify scaphoid fractures in radiographs.","volume":"4","author":"Yoon","year":"2021","journal-title":"JAMA Netw Open"},{"key":"R30-20261001","doi-asserted-by":"crossref","first-page":"110118","DOI":"10.1016\/j.clinimag.2024.110118","article-title":"The Gartland classification for expediting supracondylar humerus fracture triage: a collaborative approach to structured reporting between pediatric radiologists and orthopedists.","volume":"109","author":"Bridges","year":"2024","journal-title":"Clin Imaging"},{"key":"R31-20261001","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.acra.2006.10.003","article-title":"The prevalence effect in a laboratory environment: changing the confidence ratings.","volume":"14","author":"Gur","year":"2007","journal-title":"Acad Radiol"},{"key":"R32-20261001","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1037\/0096-3445.136.4.623","article-title":"Low target prevalence is a stubborn source of errors in visual search tasks.","volume":"136","author":"Wolfe","year":"2007","journal-title":"J Exp Psychol Gen"}],"container-title":["Journal of Pediatric Orthopaedics B"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1097\/BPB.0000000000001401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T07:00:31Z","timestamp":1790838031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1097\/BPB.0000000000001401"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1097\/bpb.0000000000001401","relation":{},"ISSN":["1060-152X","1473-5865"],"issn-type":[{"value":"1060-152X","type":"print"},{"value":"1473-5865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"assertion":[{"value":"2026-06-16","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-20","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}