{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T12:35:50Z","timestamp":1784118950577,"version":"3.55.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T00:00:00Z","timestamp":1776384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012774","name":"Innovationsfonden","doi-asserted-by":"publisher","award":["Clic"],"award-info":[{"award-number":["Clic"]}],"id":[{"id":"10.13039\/100012774","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To perform an in-depth evaluation of the diagnostic test accuracy of a commercially available AI tool for assistance in fracture detection on radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>This retrospective study included consecutive patients with trauma radiographs at seven Danish hospitals. The AI output was evaluated using the clinical radiologic report as a reference standard for a binary fracture outcome. The report is based on assessments by an emergency physician, a senior orthopedic surgeon, and a radiology expert. Sensitivity, specificity, positive- and negative predictive values were calculated. Sensitivity and specificity were additionally stratified for children, degenerative disease, metal, old fractures, casting, obvious fractures, and inter-hospital differences. Bone-wise sensitivity and specificity were assessed for multiple fracture cases and individual bones.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The study sample consisted of 2783 patients (median age 38 years, IQR, 21, 64, 1443 female), and 948 (34%) had the target finding. The AI tool demonstrated an overall sensitivity of 89% (95% CI: 87%\u201391%) and specificity of 88% (95% CI: 86%\u201389%). The specificity was 57% (95% CI: 49%\u201365%) in examinations with old fractures. Bone-wise sensitivity for carpal fractures ranged from other carpals 25% (95% CI: 1%\u201381%] to triquetrum 75% (95% CI: 43%\u201395%). Tarsal fractures ranged from medial cuneiform 0% (95% CI: 0%\u201360%) to talus 53% (95% CI: 27%\u201379%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The AI tool demonstrated high overall diagnostic accuracy and performed robustly across most specific situations. However, specificity was substantially reduced in the presence of old fractures. The bone-wise analysis showed great variability, with a pattern of poor accuracy for short, irregular bones.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Question<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Can a commercially available AI tool reliably detect fractures across anatomical regions, confounding factors, and individual bones -and are there patterns in diagnostic limitations<\/jats:italic>\n                      ?\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>The AI tool achieved 89% sensitivity and 88% specificity with consistent accuracy across subgroups. However, accuracy dropped for old fractures and irregular short bones<\/jats:italic>\n                      .\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Clinical relevance<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Despite broad regulatory approval, AI fracture tools may overlook clinically relevant weaknesses. Our in-depth evaluation highlights limitations, guiding responsible clinical use and future research to support safe AI implementation in radiology and informed medicolegal regulation<\/jats:italic>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-026-12489-5","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T13:03:41Z","timestamp":1776431021000},"page":"6325-6336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Independent bone-level diagnostic accuracy study of an AI tool for detecting appendicular skeletal fractures on radiographs"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9054-054X","authenticated-orcid":false,"given":"Frederik Jager","family":"Bruun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix C.","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janus Uhd","family":"Nybing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kasper Kj\u00e6rulf","family":"Gosvig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikael Ploug","family":"Boesen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias Willadsen","family":"Brejneb\u00f8l","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,17]]},"reference":[{"key":"12489_CR1","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1007\/s00330-021-08214-z","volume":"32","author":"L Yang","year":"2022","unstructured":"Yang L, Ene IC, Arabi Belaghi R, Koff D, Stein N, Santaguida P (2022) Stakeholders\u2019 perspectives on the future of artificial intelligence in radiology: a scoping review. Eur Radiol 32:1477\u20131495. https:\/\/doi.org\/10.1007\/s00330-021-08214-z","journal-title":"Eur Radiol"},{"key":"12489_CR2","doi-asserted-by":"publisher","first-page":"e230513","DOI":"10.1148\/ryai.230513","volume":"6","author":"AP Brady","year":"2024","unstructured":"Brady AP, Allen B, Chong J et al (2024) Developing, purchasing, implementing and monitoring ai tools in radiology: practical considerations. a multi-society statement from the ACR, CAR, ESR, RANZCR and RSNA. Radiol Artif Intell 6:e230513. https:\/\/doi.org\/10.1148\/ryai.230513","journal-title":"Radiol Artif Intell"},{"key":"12489_CR3","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210064","volume":"4","author":"AC Yu","year":"2022","unstructured":"Yu AC, Mohajer B, Eng J (2022) External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell 4:e210064. https:\/\/doi.org\/10.1148\/ryai.210064","journal-title":"Radiol Artif Intell"},{"key":"12489_CR4","doi-asserted-by":"publisher","first-page":"tzae011","DOI":"10.1093\/bjro\/tzae011","volume":"6","author":"R Bachmann","year":"2023","unstructured":"Bachmann R, Gunes G, Hangaard S et al (2023) Improving traumatic fracture detection on radiographs with artificial intelligence support: a multi-reader study. BJR Open 6:tzae011. https:\/\/doi.org\/10.1093\/bjro\/tzae011","journal-title":"BJR Open"},{"key":"12489_CR5","doi-asserted-by":"publisher","unstructured":"Gasmi I, Calinghen A, Parienti J-J, Belloy F, Fohlen A, Pelage J-P (2023) Comparison of diagnostic performance of a deep learning algorithm, emergency physicians, junior radiologists and senior radiologists in the detection of appendicular fractures in children. Pediatr Radiol. https:\/\/doi.org\/10.1007\/s00247-023-05621-w","DOI":"10.1007\/s00247-023-05621-w"},{"key":"12489_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2023.100482","volume":"10","author":"A Parpaleix","year":"2023","unstructured":"Parpaleix A, Parsy C, Cordari M, Mejdoubi M (2023) Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting. Eur J Radiol Open 10:100482. https:\/\/doi.org\/10.1016\/j.ejro.2023.100482","journal-title":"Eur J Radiol Open"},{"key":"12489_CR7","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1007\/s00256-022-04070-0","volume":"51","author":"D Hayashi","year":"2022","unstructured":"Hayashi D, Kompel AJ, Ventre J et al (2022) Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning. Skelet Radiol 51:2129\u20132139. https:\/\/doi.org\/10.1007\/s00256-022-04070-0","journal-title":"Skelet Radiol"},{"key":"12489_CR8","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1148\/radiol.210937","volume":"302","author":"A Guermazi","year":"2022","unstructured":"Guermazi A, Tannoury C, Kompel AJ et al (2022) Improving radiographic fracture recognition performance and efficiency using artificial intelligence. Radiology 302:627\u2013636. https:\/\/doi.org\/10.1148\/radiol.210937","journal-title":"Radiology"},{"key":"12489_CR9","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1148\/radiol.2021203886","volume":"300","author":"L Duron","year":"2021","unstructured":"Duron L, Ducarouge A, Gillibert A et al (2021) Assessment of an AI aid in detection of adult appendicular skeletal fractures by emergency physicians and radiologists: a multicenter cross-sectional diagnostic study. Radiology 300:120\u2013129. https:\/\/doi.org\/10.1148\/radiol.2021203886.","journal-title":"Radiology"},{"key":"12489_CR10","doi-asserted-by":"publisher","first-page":"2215","DOI":"10.1007\/s00247-022-05496-3","volume":"52","author":"T Nguyen","year":"2022","unstructured":"Nguyen T, Maarek R, Hermann AL et al (2022) Assessment of an artificial intelligence aid for the detection of appendicular skeletal fractures in children and young adults by senior and junior radiologists. Pediatr Radiol 52:2215\u20132226. https:\/\/doi.org\/10.1007\/s00247-022-05496-3","journal-title":"Pediatr Radiol"},{"key":"12489_CR11","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1016\/j.diii.2022.06.004","volume":"103","author":"L Canoni-Meynet","year":"2022","unstructured":"Canoni-Meynet L, Verdot P, Danner A, Calame P, Aubry S (2022) Added value of an artificial intelligence solution for fracture detection in the radiologist\u2019s daily trauma emergencies workflow. Diagn Interv Imaging 103:594\u2013600. https:\/\/doi.org\/10.1016\/j.diii.2022.06.004","journal-title":"Diagn Interv Imaging"},{"key":"12489_CR12","doi-asserted-by":"publisher","first-page":"110447","DOI":"10.1016\/j.ejrad.2022.110447","volume":"154","author":"NE Regnard","year":"2022","unstructured":"Regnard NE, Lanseur B, Ventre J et al (2022) Assessment of performances of a deep learning algorithm for the detection of limbs and pelvic fractures, dislocations, focal bone lesions, and elbow effusions on trauma X-rays. Eur J Radiol 154:110447. https:\/\/doi.org\/10.1016\/j.ejrad.2022.110447","journal-title":"Eur J Radiol"},{"key":"12489_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2025.112113","volume":"187","author":"DV Loeffen","year":"2025","unstructured":"Loeffen DV, Zijta FM, Boymans TA, Wildberger JE, Nijssen EC (2025) AI for fracture diagnosis in clinical practice: four approaches to systematic AI-implementation and their impact on AI-effectiveness. Eur J Radiol 187:112113. https:\/\/doi.org\/10.1016\/j.ejrad.2025.112113","journal-title":"Eur J Radiol"},{"key":"12489_CR14","doi-asserted-by":"publisher","first-page":"44","DOI":"10.5334\/jbsr.3574","volume":"108","author":"A Dell\u2019Aria","year":"2024","unstructured":"Dell\u2019Aria A, Tack D, Saddiki N et al (2024) Radiographic detection of post-traumatic bone fractures: contribution of artificial intelligence software to the analysis of senior and junior radiologists. J Belg Soc Radiol 108:44. https:\/\/doi.org\/10.5334\/jbsr.3574","journal-title":"J Belg Soc Radiol"},{"key":"12489_CR15","doi-asserted-by":"publisher","first-page":"223","DOI":"10.3390\/life13010223","volume":"13","author":"J Oppenheimer","year":"2023","unstructured":"Oppenheimer J, L\u00fcken S, Hamm B, Niehues SM (2023) A prospective approach to integration of AI fracture detection software in radiographs into clinical workflow. Life 13:223. https:\/\/doi.org\/10.3390\/life13010223","journal-title":"Life"},{"key":"12489_CR16","doi-asserted-by":"publisher","unstructured":"Bousson V, Attan\u00e9 G, Benoist N et al (2023) Artificial intelligence for detecting acute fractures in patients admitted to an emergency department: real-life performance of three commercial algorithms. Acad Radiol. https:\/\/doi.org\/10.1016\/j.acra.2023.06.016","DOI":"10.1016\/j.acra.2023.06.016"},{"key":"12489_CR17","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/s00247-023-05822-3","volume":"54","author":"I Altmann-Schneider","year":"2023","unstructured":"Altmann-Schneider I, Kellenberger CJ, Pistorius S-M et al (2023) Artificial intelligence-based detection of paediatric appendicular skeletal fractures: performance and limitations for common fracture types and locations. Pediatr Radiol 54:136\u2013145. https:\/\/doi.org\/10.1007\/s00247-023-05822-3","journal-title":"Pediatr Radiol"},{"key":"12489_CR18","doi-asserted-by":"publisher","first-page":"3974","DOI":"10.1007\/s00330-022-09349-3","volume":"33","author":"M Cohen","year":"2023","unstructured":"Cohen M, Puntonet J, Sanchez J et al (2023) Artificial intelligence vs. radiologist: accuracy of wrist fracture detection on radiographs. Eur Radiol 33:3974\u20133983. https:\/\/doi.org\/10.1007\/s00330-022-09349-3","journal-title":"Eur Radiol"},{"key":"12489_CR19","doi-asserted-by":"publisher","first-page":"e012799","DOI":"10.1136\/bmjopen-2016-012799","volume":"6","author":"JF Cohen","year":"2016","unstructured":"Cohen JF, Korevaar DA, Altman DG et al (2016) STARD 2015 guidelines for reporting diagnostic accuracy studies: explanation and elaboration. BMJ Open 6:e012799. https:\/\/doi.org\/10.1136\/bmjopen-2016-012799","journal-title":"BMJ Open"},{"key":"12489_CR20","doi-asserted-by":"publisher","first-page":"103208","DOI":"10.1016\/j.jbi.2019.103208","volume":"95","author":"PA Harris","year":"2019","unstructured":"Harris PA, Taylor R, Minor BL et al (2019) The REDCap consortium: building an international community of software platform partners. J Biomed Inform 95:103208. https:\/\/doi.org\/10.1016\/j.jbi.2019.103208","journal-title":"J Biomed Inform"},{"key":"12489_CR21","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1080\/02841850600806340","volume":"47","author":"C-J Wei","year":"2006","unstructured":"Wei C-J, Tsai W-C, Tiu C-M, Wu H-T, Chiou H-J, Chang C-Y (2006) Systematic analysis of missed extremity fractures in emergency radiology. Acta Radiol 47:710\u2013717. https:\/\/doi.org\/10.1080\/02841850600806340","journal-title":"Acta Radiol"},{"key":"12489_CR22","doi-asserted-by":"publisher","first-page":"111","DOI":"10.23750\/abm.v89i1-S.7015","volume":"89","author":"A Pinto","year":"2018","unstructured":"Pinto A, Berritto D, Russo A et al (2018) Traumatic fractures in adults: missed diagnosis on plain radiographs in the Emergency Department. Acta Biomed 89:111\u2013123. https:\/\/doi.org\/10.23750\/abm.v89i1-S.7015","journal-title":"Acta Biomed"},{"key":"12489_CR23","doi-asserted-by":"publisher","first-page":"2885","DOI":"10.1007\/s00330-023-10380-1","volume":"34","author":"T Jacques","year":"2023","unstructured":"Jacques T, Cardot N, Ventre J, Demondion X, Cotten A (2023) Commercially-available AI algorithm improves radiologists\u2019 sensitivity for wrist and hand fracture detection on X-ray, compared to a CT-based ground truth. Eur Radiol 34:2885\u20132894. https:\/\/doi.org\/10.1007\/s00330-023-10380-1","journal-title":"Eur Radiol"},{"key":"12489_CR24","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1148\/radiol.2019192515","volume":"294","author":"DA Bluemke","year":"2020","unstructured":"Bluemke DA, Moy L, Bredella MA et al (2020) Assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers\u2014from the Radiology Editorial Board. Radiology 294:487\u2013489. https:\/\/doi.org\/10.1148\/radiol.2019192515","journal-title":"Radiology"},{"key":"12489_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1101\/2025.07.16.25331604","volume":"2025","author":"F Bruun","year":"2025","unstructured":"Bruun F, M\u00fcller FC, Nybing JU et al (2025) Diagnostic accuracy of clinical radiology reports for trauma radiographs: a retrospective validation study. medRxiv 2025:1\u201318. https:\/\/doi.org\/10.1101\/2025.07.16.25331604.","journal-title":"medRxiv"},{"key":"12489_CR26","doi-asserted-by":"publisher","unstructured":"Petersen LA, Beck MS Andersen MB (2026) Prompt engineering enables open-source LLMs to match proprietary models in diagnostic accuracy for annotation of radiology reports. Clin Radiol. https:\/\/doi.org\/10.1016\/j.crad.2026.107315","DOI":"10.1016\/j.crad.2026.107315"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12489-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-026-12489-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12489-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T13:30:17Z","timestamp":1783431017000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-026-12489-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,17]]},"references-count":26,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["12489"],"URL":"https:\/\/doi.org\/10.1007\/s00330-026-12489-5","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,17]]},"assertion":[{"value":"28 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The scientific guarantor of this publication is Frederik Jager Bruun.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Guarantor"}},{"value":"The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No complex statistical methods were necessary for this paper.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Statistics and biometry"}},{"value":"Written informed consent was waived by the Institutional Review Board.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"Institutional Review Board approval was obtained ID 22070206. The Institutional Review Board granted access to data for storage in REDcap. For analysis of the manuscript data was de-identified and exported for analysis in R.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"A subset cohort was used in a validation study of the quality of the radiological report as a reference for validation of AI [\n                      \n                      ].","order":7,"name":"Ethics","group":{"name":"EthicsHeading","label":"Study subjects or cohorts overlap"}},{"order":8,"name":"Ethics","group":{"name":"EthicsHeading","label":"Methodology"}}]}}