{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T19:28:12Z","timestamp":1793906892016,"version":"4.8.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"University of Southern Denmark","id":[{"id":"https:\/\/ror.org\/03yrrjy16","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Emerg Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To estimate diagnostic performance of a deep learning algorithm for extremity fracture detection on radiographs in patients aged\u2009\u2265\u20092 years using a refined reference standard. Secondary, to compare positive predictive value (PPV) by the algorithm\u2019s built-in confidence level (high vs. low) and diagnostic performance between adults (\u2265\u200918 years) and children.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective single-center study consecutively included patients with radiography of a suspected extremity fracture between January and December 2024. The index test was the algorithm output (bounding boxes with confidence). The reference standard was the radiology report with discordant cases adjudicated by follow-up imaging when available or specialist review. Sensitivity, specificity, PPV and negative predictive value (NPV) were calculated with 95% confidence intervals; differences were tested using the McNemar and a score test and patient-clustered logistic regression.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      There were 2,508 patients, median age 34 years (range 2\u2013105), 1,236 males; 815 patients had a total of 1,028 fractures. Per-fracture sensitivity and PPV were 92.7% (95% CI: 90.9\u201394.5) and 87.6% (95% CI: 85.5\u201389.7); Specificity and NPV were 94.4% (95% CI: 93.2-95.4) and 96.6% (95% CI: 95.6\u201397.4). PPV for high-confidence was superior to low-confidence detections (99.1% vs 59.1%,\n                      <jats:italic>p<\/jats:italic>\n                      &lt; 0.001). Children had higher per-fracture PPV than adults (91.7% vs. 86.1%;\n                      <jats:italic>p<\/jats:italic>\n                      = 0.01), with no significant difference in per-fracture sensitivity, or case-wise performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The algorithm showed good diagnostic performance for extremity fracture detection on radiographs. The AI\u2019s confidence stratification strongly influenced PPV, and higher PPV was seen among children.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s10140-026-02546-3","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T02:55:38Z","timestamp":1790045738000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Diagnostic accuracy &amp; clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0475-6254","authenticated-orcid":false,"given":"Sabine Morris","family":"Delhez","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas Breiner","family":"En\u00f8e","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oke","family":"Gerke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bjarke","family":"Viberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pia Iben","family":"Pietersen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin Schnack Brandt","family":"Rasmussen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janni","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"2546_CR1","doi-asserted-by":"publisher","DOI":"10.23970\/AHRQEPCCER258","volume-title":"AHRQ Comparative Effectiveness Reviews. Diagnostic Errors in the Emergency Department: A Systematic Review","author":"DE Newman-Toker","year":"2022","unstructured":"Newman-Toker DE, Peterson SM, Badihian S, Hassoon A, Nassery N, Parizadeh D et al (2022) AHRQ Comparative Effectiveness Reviews. Diagnostic Errors in the Emergency Department: A Systematic Review. Agency for Healthcare Research and Quality (US), Rockville (MD)"},{"issue":"10","key":"2546_CR2","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1111\/acem.13223","volume":"24","author":"CJ Dimaggio","year":"2017","unstructured":"Dimaggio CJ, Avraham JB, Lee DC, Frangos SG, Wall SP (2017) The Epidemiology of Emergency Department Trauma Discharges in the United States. Acad Emerg Med 24(10):1244\u20131256","journal-title":"Acad Emerg Med"},{"issue":"8","key":"2546_CR3","doi-asserted-by":"publisher","first-page":"e807","DOI":"10.1016\/S2214-109X(17)30222-X","volume":"5","author":"W Chen","year":"2017","unstructured":"Chen W, Lv H, Liu S, Liu B, Zhu Y, Chen X et al (2017) National incidence of traumatic fractures in China: a retrospective survey of 512 187 individuals. Lancet Global Health 5(8):e807\u2013e17","journal-title":"Lancet Global Health"},{"issue":"4","key":"2546_CR4","doi-asserted-by":"publisher","first-page":"626","DOI":"10.5811\/westjem.2019.1.41375","volume":"20","author":"M Tranovich","year":"2019","unstructured":"Tranovich M, Gooch C, Dougherty J (2019) Radiograph Interpretation Discrepancies in a Community Hospital Emergency Department. Western J Emerg Med 20(4):626\u2013632","journal-title":"Western J Emerg Med"},{"issue":"4","key":"2546_CR5","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1080\/17453674.2019.1600125","volume":"90","author":"K Gan","year":"2019","unstructured":"Gan K, Xu D, Lin Y, Shen Y, Zhang T, Hu K et al (2019) Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop 90(4):394\u2013400","journal-title":"Acta Orthop"},{"key":"2546_CR6","doi-asserted-by":"crossref","unstructured":"Oppenheimer J, Luken S, Hamm B, Niehues SM (2023) A Prospective Approach to Integration of AI Fracture Detection Software in Radiographs into Clinical Workflow. Life (Basel Switzerland) 13(1)","DOI":"10.3390\/life13010223"},{"issue":"45","key":"2546_CR7","doi-asserted-by":"publisher","first-page":"11591","DOI":"10.1073\/pnas.1806905115","volume":"115","author":"R Lindsey","year":"2018","unstructured":"Lindsey R, Daluiski A, Chopra S, Lachapelle A, Mozer M, Sicular S et al (2018) Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A 115(45):11591\u20136","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2546_CR8","doi-asserted-by":"publisher","unstructured":"Quek JJX, Nickalls OJ, Wong BSS, Tan MO Deploying artificial intelligence in the detection of adult appendicular and pelvic fractures in the Singapore emergency department after hours: efficacy, cost savings and non-monetary benefits. Singapore Med J 9900.\u00a0https:\/\/doi.org\/10.4103\/singaporemedj.SMJ-2023-170","DOI":"10.4103\/singaporemedj.SMJ-2023-170"},{"issue":"4","key":"2546_CR9","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1007\/s10140-025-02353-2","volume":"32","author":"JT Huhtanen","year":"2025","unstructured":"Huhtanen JT, Nyman M, Blanco Sequeiros R, Koskinen SK, Pudas TK, Kajander S et al (2025) Comparative accuracy of two commercial AI algorithms for musculoskeletal trauma detection in emergency radiographs. Emerg Radiol 32(4):569\u2013580","journal-title":"Emerg Radiol"},{"key":"2546_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106120","volume":"205","author":"P Prucker","year":"2026","unstructured":"Prucker P, Lemke T, Mertens CJ, Ziegelmayer S, Graf MM, Weller D et al (2026) Real-world clinical impact of three commercial AI algorithms on musculoskeletal radiography interpretation: a prospective crossover reader study. Int J Med Inform 205:106120","journal-title":"Int J Med Inform"},{"issue":"1","key":"2546_CR11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000438","volume":"3","author":"J Jung","year":"2024","unstructured":"Jung J, Dai J, Liu B, Wu Q (2024) Artificial intelligence in fracture detection with different image modalities and data types: a systematic review and meta-analysis. PLoS Digit Health 3(1):e0000438","journal-title":"PLoS Digit Health"},{"issue":"1","key":"2546_CR12","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1148\/radiol.211785","volume":"304","author":"RYL Kuo","year":"2022","unstructured":"Kuo RYL, Harrison C, Curran TA, Jones B, Freethy A, Cussons D et al (2022) Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis. Radiology 304(1):50\u201362","journal-title":"Radiology"},{"key":"2546_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-11332-z","author":"JA Scaringi","year":"2024","unstructured":"Scaringi JA, McTaggart RA, Alvin MD, Atalay M, Bernstein MH, Jayaraman MV et al (2024) Implementing an AI algorithm in the clinical setting: a case study for the accuracy paradox. Eur Radiol. https:\/\/doi.org\/10.1007\/s00330-024-11332-z","journal-title":"Eur Radiol"},{"key":"2546_CR14","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.990604","volume":"9","author":"M Chen","year":"2022","unstructured":"Chen M, Zhang B, Cai Z, Seery S, Gonzalez MJ, Ali NM et al (2022) Acceptance of clinical artificial intelligence among physicians and medical students: a systematic review with cross-sectional survey. Front Med (Lausanne) 9:990604","journal-title":"Front Med (Lausanne)"},{"issue":"3","key":"2546_CR15","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1136\/bmjqs-2018-008370","volume":"28","author":"R Challen","year":"2019","unstructured":"Challen R, Denny J, Pitt M, Gompels L, Edwards T, Tsaneva-Atanasova K (2019) Artificial intelligence, bias and clinical safety. BMJ Quality & Safety 28(3):231\u20137","journal-title":"BMJ Quality & Safety"},{"issue":"1095","key":"2546_CR16","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20180845","volume":"92","author":"G Maskell","year":"2019","unstructured":"Maskell G (2019) Error in radiology-where are we now? Br J Radiol 92(1095):20180845","journal-title":"Br J Radiol"},{"issue":"10","key":"2546_CR17","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","volume":"31","author":"V Sounderajah","year":"2025","unstructured":"Sounderajah V, Guni A, Liu X, Collins GS, Karthikesalingam A, Markar SR et al (2025) The STARD-AI reporting guideline for diagnostic accuracy studies using artificial intelligence. Nat Med 31(10):3283\u20133289","journal-title":"Nat Med"},{"key":"2546_CR18","unstructured":"Tejani AS, Klontzas ME, Gatti AA, Mongan JT, Moy L, Park SH et al (2024) Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 Update. Radiology: Artificial Intelligence 6(4)"},{"key":"2546_CR19","unstructured":"Jensen JOL, Ludvigsen L Knoglebogen [Available from: https:\/\/knoglebogen.dk\/"},{"key":"2546_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103208","volume":"95","author":"PA Harris","year":"2019","unstructured":"Harris PA, Taylor R, Minor BL, Elliott V, Fernandez M, O\u2019Neal L et al (2019) The REDCap consortium: building an international community of software platform partners. J Biomed Inform 95:103208","journal-title":"J Biomed Inform"},{"issue":"2","key":"2546_CR21","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.jbi.2008.08.010","volume":"42","author":"PA Harris","year":"2009","unstructured":"Harris PA, Taylor R, Thielke R, Payne J, Gonzalez N, Conde JG (2009) Research electronic data capture (REDCap)--a metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inf 42(2):377\u2013381","journal-title":"J Biomed Inf"},{"issue":"2","key":"2546_CR22","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1111\/j.0006-341X.2000.00345.x","volume":"56","author":"W Leisenring","year":"2004","unstructured":"Leisenring W, Alono T, Pepe MS (2004) Comparisons of Predictive Values of Binary Medical Diagnostic Tests for Paired Designs. Biometrics 56(2):345\u2013351","journal-title":"Biometrics"},{"issue":"8","key":"2546_CR23","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1016\/j.crad.2024.04.009","volume":"79","author":"A Nowroozi","year":"2024","unstructured":"Nowroozi A, Salehi MA, Shobeiri P, Agahi S, Momtazmanesh S, Kaviani P et al (2024) Artificial intelligence diagnostic accuracy in fracture detection from plain radiographs and comparing it with clinicians: a systematic review and meta-analysis. Clin Radiol 79(8):579\u2013588","journal-title":"Clin Radiol"},{"issue":"2","key":"2546_CR24","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2025-111127","volume":"16","author":"JZT Sim","year":"2026","unstructured":"Sim JZT, Lin J, Fong QW, Soon AYQ, Khin LW, Balakrishnan S et al (2026) How threshold customisation affects the performance of a multiclass X-ray AI model for primary care triage: a retrospective study. BMJ Open 16(2):e111127","journal-title":"BMJ Open"},{"key":"2546_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/s00247-025-06461-6","author":"I Altmann-Schneider","year":"2025","unstructured":"Altmann-Schneider I, Geiger LS, Kellenberger CJ, Callaghan F, Seiler M (2025) Multivendor comparison study of artificial intelligence software for automated fracture detection in paediatric patients. Pediatr Radiol. https:\/\/doi.org\/10.1007\/s00247-025-06461-6","journal-title":"Pediatr Radiol"},{"issue":"8","key":"2546_CR26","doi-asserted-by":"publisher","first-page":"5041","DOI":"10.1007\/s00330-023-10559-6","volume":"34","author":"GJ Van Den Wittenboer","year":"2024","unstructured":"Van Den Wittenboer GJ, Van Der Kolk BYM, Nijholt IM, Langius-Wiffen E, Van Dijk RA, Van Hasselt BAAM et al (2024) Diagnostic accuracy of an artificial intelligence algorithm versus radiologists for fracture detection on cervical spine CT. Eur Radiol 34(8):5041\u20138","journal-title":"Eur Radiol"},{"issue":"10","key":"2546_CR27","doi-asserted-by":"publisher","first-page":"5881","DOI":"10.1007\/s00330-025-11554-9","volume":"35","author":"M Ziegner","year":"2025","unstructured":"Ziegner M, Pape J, Lacher M, Brandau A, Kelety T, Mayer S et al (2025) Real-life benefit of artificial intelligence-based fracture detection in a pediatric em ergency department. Eur Radiol 35(10):5881\u20135890","journal-title":"Eur Radiol"},{"issue":"20","key":"2546_CR28","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1001\/jama.2013.281053","volume":"310","author":"World Medical","year":"2013","unstructured":"World Medical (2013) Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA 310(20):2191\u20132194","journal-title":"JAMA"}],"container-title":["Emergency Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10140-026-02546-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10140-026-02546-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10140-026-02546-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T19:02:34Z","timestamp":1793905354000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10140-026-02546-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":28,"alternative-id":["2546"],"URL":"https:\/\/doi.org\/10.1007\/s10140-026-02546-3","relation":{},"ISSN":["1438-1435"],"issn-type":[{"value":"1438-1435","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"assertion":[{"value":"28 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The study was approved by the Danish National Committee on Health Research Ethics (Project-ID: 2403794) and registered with the Regional Health Authorities (Project-ID: 25\/27740). Written informed consent was waived by the Danish National Committee on Health Research Ethics and the Regional Health Authorities.","order":1,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Author Jensen J. previously worked as an annotator for Radiobotics, whose product is evaluated in this study. This role was not related to the conduct of the present study. The remaining authors declare that they have no relationships with any companies whose products or services may be related to the subject matter of this article.","order":2,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}