{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:13:28Z","timestamp":1786979608457,"version":"build-2736575974"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T00:00:00Z","timestamp":1753056000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T00:00:00Z","timestamp":1753056000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur J Trauma Emerg Surg"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Convolutional Neural Networks (CNNs) have shown promise in fracture detection, but their ability to improve surgeons' inconsistent fracture classification remains unstudied. Therefore, our aim was create and (externally) validate the performance of an open-source CNN algorithm to classify DRFs according to the AO\/OTA classification system?<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients with postero-anterior, lateral and oblique radiographs were included. Radiographs were classified according to the AO\/OTA-classification and were used to train a CNN algorithm. The algorithm was tested on an internal and external validation set (two other level 1 trauma centers), with the DRFs classified by three independent surgeons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>659 radiographs were used to train the algorithm. Internal- and external validation sets contained 190 and 188 patients, respectively. Upon internal validation, the CNN had an accuracy of 62% and an area under receiving operating characteristic curve (AUC) of 0.63\u20130.93 (type 2R3A 0.84, type 2R3B 0.63, type 2R3C 0.75, and no DRF 0.93). On the external validation, the algorithm has an accuracy of 61% and an AUC of 0.56\u20130.88 (type 2R3A 0.82, type 2R3B 0.56, type 2R3C 0.75, and no DRF 0.88).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The presented algorithm has demonstrated excellent accuracy in classifying type 2R3A DRFs and excluding DRFs. However, poor to moderate accuracy is observed in classifying 2R3B and 2R3C DRFs according to the AO\/OTA system, similar to limited surgeons\u2019 inter-observer agreement. These results show that despite previous excellence in fracture detection, CNN-algorithms struggle with classifying; potentially showing the inherent problems with these classification systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00068-025-02931-6","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T16:39:36Z","timestamp":1753115976000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Open-source convolutional neural network to classify distal radial fractures according to the AO\/OTA classification on plain radiographs"],"prefix":"10.1007","volume":"51","author":[{"given":"Koen D.","family":"Oude Nijhuis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasper","family":"Prijs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Britt","family":"Barvelink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans","family":"van Luit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibin","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruurd L.","family":"Jaarsma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank F. A.","family":"IJpma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu M. E.","family":"Wijffels","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Job N.","family":"Doornberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joost W.","family":"Colaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"Machine Learning Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charlotte","family":"Laane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Canta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanne","family":"Hoeksema","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaan","family":"Aksakal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haras","family":"Mhmud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Jutte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wouter","family":"Mallee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Duckworth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niels","family":"Schep","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Hendrickx","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne-Eva","family":"Bulstra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lente","family":"Dankelman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"key":"2931_CR1","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. Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop. 2019;90:394\u2013400.","journal-title":"Acta Orthop"},{"key":"2931_CR2","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1080\/17453674.2017.1344459","volume":"88","author":"J Olczak","year":"2017","unstructured":"Olczak J, Fahlberg N, Maki A, Razavian AS, Jilert A, Stark A, et al. Artificial intelligence for analyzing orthopedic trauma radiographs: deep learning algorithms\u2014are they on par with humans for diagnosing fractures? Acta Orthop. 2017;88:581\u20136.","journal-title":"Acta Orthop"},{"key":"2931_CR3","doi-asserted-by":"crossref","unstructured":"Krogue JD, Cheng K V., Hwang KM, Toogood P, Meinberg EG, Geiger EJ, et al. Automatic hip fracture identification and functional subclassification with deep learning. Radiol Artif Intell [Internet]. 2020;2:e190023. Available from: http:\/\/pubs.rsna.org\/doi\/10.1148\/ryai.2020190023.","DOI":"10.1148\/ryai.2020190023"},{"key":"2931_CR4","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s00068-024-02731-4","volume":"51","author":"KD Oude Nijhuis","year":"2025","unstructured":"Oude Nijhuis KD, Barvelink B, Prijs J, Zhao Y, Liao Z, Jaarsma RL, et al. An open source convolutional neural network to detect and localize distal radius fractures on plain radiographs. Eur J Trauma Emerg Surg. 2025;51:26.","journal-title":"Eur J Trauma Emerg Surg"},{"key":"2931_CR5","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1080\/17453674.2018.1453714","volume":"89","author":"SW Chung","year":"2018","unstructured":"Chung SW, Han SS, Lee JW, Oh KS, Kim NR, Yoon JP, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018;89:468\u201373.","journal-title":"Acta Orthop"},{"key":"2931_CR6","doi-asserted-by":"crossref","unstructured":"Lee C, Jang J, Lee S, Kim YS, Jo HJ, Kim Y. Classification of femur fracture in pelvic X-ray images using meta-learned deep neural network. Sci Rep [Internet]. 2020;10:13694. Available from: https:\/\/www.nature.com\/articles\/s41598-020-70660-4.","DOI":"10.1038\/s41598-020-70660-4"},{"key":"2931_CR7","doi-asserted-by":"crossref","unstructured":"Mutasa S, Varada S, Goel A, Wong TT, Rasiej MJ. Advanced deep learning techniques applied to automated femoral neck fracture detection and classification. J Digit Imaging [Internet]. 2020;33:1209\u201317. Available from: https:\/\/link.springer.com\/10.1007\/s10278-020-00364-8.","DOI":"10.1007\/s10278-020-00364-8"},{"key":"2931_CR8","doi-asserted-by":"crossref","unstructured":"Lind A, Akbarian E, Olsson S, N\u00e5sell H, Sk\u00f6ldenberg O, Razavian AS, et al. Artificial intelligence for the classification of fractures around the knee in adults according to the 2018 AO\/OTA classification system. PLoS One [Internet]. 2021;16:e0248809. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/33793601.","DOI":"10.1371\/journal.pone.0248809"},{"key":"2931_CR9","doi-asserted-by":"crossref","unstructured":"Tobler P, Cyriac J, Kovacs BK, Hofmann V, Sexauer R, Paciolla F, et al. AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size. Eur Radiol [Internet]. 2021;31:6816\u201324. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/33742228.","DOI":"10.1007\/s00330-021-07811-2"},{"key":"2931_CR10","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/s13246-023-01261-4","volume":"46","author":"H Min","year":"2023","unstructured":"Min H, Rabi Y, Wadhawan A, Bourgeat P, Dowling J, White J, et al. Automatic classification of distal radius fracture using a two-stage ensemble deep learning framework. Phys Eng Sci Med. 2023;46:877\u201386.","journal-title":"Phys Eng Sci Med"},{"key":"2931_CR11","doi-asserted-by":"crossref","unstructured":"Karl JW, Olson PR, Rosenwasser MP. The epidemiology of upper extremity fractures in the United States, 2009. J Orthop Trauma [Internet]. 2015;29:e242\u20134. Available from: https:\/\/journals.lww.com\/00005131-201508000-00010.","DOI":"10.1097\/BOT.0000000000000312"},{"key":"2931_CR12","doi-asserted-by":"crossref","unstructured":"Koo KOT, Tan DMK, Chong AKS. Distal radius fractures: an epidemiological review. Orthop Surg [Internet]. 2013;5:209\u201313. Available from: https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/os.12045.","DOI":"10.1111\/os.12045"},{"key":"2931_CR13","doi-asserted-by":"crossref","unstructured":"Shehovych A, Salar O, Meyer C, Ford DJ. Adult distal radius fractures classification systems: essential clinical knowledge or abstract memory testing? Ann R Coll Surg Engl [Internet]. 2016;98:525\u201331. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/27513789.","DOI":"10.1308\/rcsann.2016.0237"},{"key":"2931_CR14","doi-asserted-by":"crossref","unstructured":"Andersen DJ, Blair WF, Stevers CM, Adams BD, El-Khouri GY, Brandser EA. Classification of distal radius fractures: an analysis of interobserver reliability and intraobserver reproducibility. J Hand Surg Am [Internet]. 1996;21:574\u201382. Available from: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0363502396800062.","DOI":"10.1016\/S0363-5023(96)80006-2"},{"key":"2931_CR15","doi-asserted-by":"crossref","unstructured":"Kreder HJ, Hanel DP, McKee M, Jupiter J, McGillivary G, Swiontkowski MF. Consistency of AO fracture classification for the distal radius. J Bone Joint Surg Br [Internet]. 1996;78:726\u201331. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/8836058.","DOI":"10.1302\/0301-620X.78B5.0780726"},{"key":"2931_CR16","doi-asserted-by":"crossref","unstructured":"Macdermid JC, Richards RS, Donner A, Bellamy N, Roth JH, Hildebrand KA. Reliability of hand fellows\u2019 measurements and classifications from radiographs of distal radius fractures. Can J Plast Surg [Internet]. 2001;9:51\u20138. Available from: http:\/\/journals.sagepub.com\/doi\/10.1177\/229255030100900204.","DOI":"10.1177\/229255030100900204"},{"key":"2931_CR17","doi-asserted-by":"crossref","unstructured":"Jin W-J, Jiang L-S, Shen L, Lu H, Cui Y-M, Zhou Q, et al. The interobserver and intraobserver reliability of the cooney classification of distal radius fractures between experienced orthopaedic surgeons. J Hand Surg Eur Vol [Internet]. 2007;32:509\u201311. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/17950210.","DOI":"10.1016\/j.jhse.2007.03.002"},{"key":"2931_CR18","doi-asserted-by":"crossref","unstructured":"Ploegmakers JJW, Mader K, Pennig D, Verheyen CCPM. Four distal radial fracture classification systems tested amongst a large panel of Dutch trauma surgeons. Injury [Internet]. 2007;38:1268\u201372. Available from: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020138307001726.","DOI":"10.1016\/j.injury.2007.03.032"},{"key":"2931_CR19","doi-asserted-by":"crossref","unstructured":"Plant CE, Hickson C, Hedley H, Parsons NR, Costa ML. Is it time to revisit the AO classification of fractures of the distal radius? Bone Joint J [Internet]. 2015;97-B:818\u201323. Available from: https:\/\/online.boneandjoint.org.uk\/doi\/10.1302\/0301-620X.97B6.33844.","DOI":"10.1302\/0301-620X.97B6.33844"},{"key":"2931_CR20","doi-asserted-by":"crossref","unstructured":"van Buijtenen JM, van Tunen MLC, Zuidema WP, Heilbron EA, de Haan J, de Vet HCW, et al. Inter- and intra-observer agreement of the AO classification for operatively treated distal radius fractures. Strateg Trauma Limb Reconstr [Internet]. 2015;10:155\u20139. Available from: https:\/\/www.stlrjournal.com\/doi\/10.1007\/s11751-015-0237-z.","DOI":"10.1007\/s11751-015-0237-z"},{"key":"2931_CR21","doi-asserted-by":"crossref","unstructured":"Jayakumar P, Teunis T, Gim\u00e9nez B, Verstreken F, Di Mascio L, Jupiter J. AO distal radius fracture classification: global perspective on observer agreement. J Wrist Surg [Internet]. 2016;06:046\u201353. Available from: http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/s-0036-1587316.","DOI":"10.1055\/s-0036-1587316"},{"key":"2931_CR22","doi-asserted-by":"crossref","unstructured":"W\u00e6ver D, Madsen ML, R\u00f6lfing JHD, Borris LC, Henriksen M, Nagel LL, et al. Distal radius fractures are difficult to classify. Injury [Internet]. 2018;49:S29\u201332. Available from: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020138318302997.","DOI":"10.1016\/S0020-1383(18)30299-7"},{"key":"2931_CR23","doi-asserted-by":"crossref","unstructured":"Ilyas AM, Jupiter JB. Distal radius fractures\u2014Classification of treatment and indications for surgery. Orthop Clin North Am [Internet]. 2007;38:167\u201373. Available from: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003058980700003X.","DOI":"10.1016\/j.ocl.2007.01.002"},{"key":"2931_CR24","doi-asserted-by":"crossref","unstructured":"Olczak J, Pavlopoulos J, Prijs J, Ijpma FFA, Doornberg JN, Lundstr\u00f6m C, et al. Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: an introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal. Acta Orthop [Internet]. 2021;92:513\u201325. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/33988081.","DOI":"10.1080\/17453674.2021.1918389"},{"key":"2931_CR25","unstructured":"Labelbox: The leading training data platform [Internet]. 2020 [cited 2022 Jul 18]. Available from: labelbox.com."},{"key":"2931_CR26","unstructured":"Lungren MP, Evans MRB, Ranschaert ER, Morozov S, Algra PR. Artificial Intelligence in Medical Imaging [Internet]. Ranschaert ER, Morozov S, Algra PR, editors. Cham: Springer International Publishing; 2019. Available from: http:\/\/link.springer.com\/10.1007\/978-3-319-94878-2."},{"key":"2931_CR27","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar P, Girshick R. Mask R-CNN. IEEE Trans Pattern Anal Mach Intell [Internet]. 2020;42:386\u201397. Available from: http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/29994331.","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"2931_CR28","doi-asserted-by":"crossref","unstructured":"Meinberg E, Agel J, Roberts C, Karam M, Kellam J. Fracture and dislocation classification compendium\u20142018. J Orthop Trauma [Internet]. 2018;32:S1\u201310. Available from: https:\/\/journals.lww.com\/00005131-201801001-00001.","DOI":"10.1097\/BOT.0000000000001063"},{"key":"2931_CR29","doi-asserted-by":"crossref","unstructured":"Kim DH, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol [Internet]. 2018;73:439\u201345. Available from: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0009926017305354.","DOI":"10.1016\/j.crad.2017.11.015"},{"key":"2931_CR30","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. Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A. 2018;115:11591\u20136.","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2931_CR31","doi-asserted-by":"crossref","unstructured":"Landis JR, Koch GG. The measurement of observer agreement for categorical data [Internet]. 1977. Available from: https:\/\/about.jstor.org\/terms.","DOI":"10.2307\/2529310"},{"key":"2931_CR32","doi-asserted-by":"crossref","unstructured":"Langerhuizen DWG, Janssen SJ, Mallee WH, van den Bekerom MPJ, Ring D, Kerkhoffs GMMJ, et al. What are the applications and limitations of artificial intelligence for fracture detection and classification in orthopaedic trauma imaging? A systematic review. Clin Orthop Relat Res [Internet]. 2019;477:2482\u201391. Available from: https:\/\/journals.lww.com\/10.1097\/CORR.0000000000000848.","DOI":"10.1097\/CORR.0000000000000848"}],"container-title":["European Journal of Trauma and Emergency Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00068-025-02931-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00068-025-02931-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00068-025-02931-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T11:05:42Z","timestamp":1770721542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00068-025-02931-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,21]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2931"],"URL":"https:\/\/doi.org\/10.1007\/s00068-025-02931-6","relation":{},"ISSN":["1863-9933","1863-9941"],"issn-type":[{"value":"1863-9933","type":"print"},{"value":"1863-9941","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,21]]},"assertion":[{"value":"25 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Jasper Prijs has received the following personal grants: An amount less than USD 15,000 from the Michael van Vloten Foundation (Rotterdam, The Netherlands), an amount less than USD 10,000 from ZonMw (Den Haag, The Netherlands), an amount less than USD 10,000 from the Prins Bernhard Cultuur Fonds (Amsterdam, The Netherlands).Ruurd Jaarsma is unpaid board member of the Australian Orthopaedic Association (SA\/NT) and the SOS Fracture Alliance Australia.Andrew Duckworth has received research grants, royalties, payments for lectures\/presentations, participates on multiple committees and boards and has financial interests, all not related to this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"261"}}