{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T13:03:07Z","timestamp":1789131787827,"version":"build-2803163510"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:00:00Z","timestamp":1775260800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:00:00Z","timestamp":1775260800000},"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 Radiol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Approximately 6.9% of children in the United Kingdom have suffered physical abuse. Fractures are a common sign and must not be overlooked due to high recurrence and mortality rates. We aimed to train and assess the diagnostic accuracy of a deep learning-based artificial intelligence model (BoneView) in detecting inflicted fractures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>This pragmatic retrospective diagnostic accuracy pilot study focuses on children under 5 years old who underwent skeletal survey examinations for suspected physical abuse at a single tertiary centre between 1st January 2000 and 31st December 2023. Radiographs were extracted from the Picture Archiving and Communication System and divided to retrain and test the model. Radiology reports and retrospective review by one observer were used as the reference standard.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our total dataset included 1740 patients (mean age, 8.77 months\u2009\u00b1\u20098.343 [standard deviation], 1026 males). The model\u2019s baseline performance recorded an area under the receiver operating curve (AUC) of 0.46 (95% CI: 0.38, 0.57), with a sensitivity of 44% (95% CI: 35%, 58%) and a specificity of 61% (95% CI: 52%, 71%). For preliminary model training, 329 of 1227 positive studies were annotated, yielding a revised AUC of 0.55 (95% CI: 0.48, 0.66), sensitivity of 52% (95% CI: 43%, 64%), and specificity of 67% (95% CI: 58%, 78%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Preliminary training of a novel AI tool for detecting inflicted fractures yielded improved results from baseline performance. This justifies the completion of annotation and further training of this AI tool to potentially achieve clinically acceptable performance.<\/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>Double reporting of skeletal surveys is vital for identifying fractures caused by physical abuse, but some departments lack the expertise to double report these investigations<\/jats:italic>\n                      .\n                    <\/jats:p>\n                    <jats:p>\n                      <jats:bold>\n                        <jats:italic>Findings<\/jats:italic>\n                      <\/jats:bold>\n                      <jats:italic>Preliminary retraining of a commercially available deep learning algorithm using radiographic skeletal surveys led to improved inflicted fracture detection accuracy<\/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>Training this deep learning algorithm using relevant imaging enhances its performance. An accurate tool for automated skeletal survey interpretation may improve outcomes for physically abused children by offering an additional diagnostic opinion<\/jats:italic>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00330-026-12513-8","type":"journal-article","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T07:12:33Z","timestamp":1775286753000},"page":"6274-6281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Developing an artificial intelligence tool for detecting fractures of child abuse: preliminary findings"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4644-9950","authenticated-orcid":false,"given":"Samuel","family":"Evans","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nihal","family":"Chanian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esther","family":"Bezzina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amaka C.","family":"Offiah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,4]]},"reference":[{"key":"12513_CR1","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/j.chiabu.2013.02.004","volume":"37","author":"L Radford","year":"2013","unstructured":"Radford L, Corral S, Bradley C, Fisher HL (2013) The prevalence and impact of child maltreatment and other types of victimization in the UK: findings from a population survey of caregivers, children and young people and young adults. Child Abuse Negl 37:801\u2013813","journal-title":"Child Abuse Negl"},{"key":"12513_CR2","doi-asserted-by":"publisher","first-page":"143","DOI":"10.2214\/ajr.121.1.143","volume":"121","author":"MS Kogutt","year":"1974","unstructured":"Kogutt MS, Swischuk LE, Fagan CJ (1974) Patterns of injury and significance of uncommon fractures in the battered child syndrome. AJR Am J Roentgenol 121:143\u2013149","journal-title":"AJR Am J Roentgenol"},{"key":"12513_CR3","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1136\/adc.2005.085639","volume":"91","author":"N Hindley","year":"2006","unstructured":"Hindley N (2006) Risk factors for recurrence of maltreatment: a systematic review. Arch Dis Child 91:744\u2013752","journal-title":"Arch Dis Child"},{"key":"12513_CR4","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/s11999-010-1578-z","volume":"469","author":"NK Pandya","year":"2011","unstructured":"Pandya NK, Baldwin K, Kamath AF, Wenger DR, Hosalkar HS (2011) Unexplained fractures: Child abuse or bone disease? A systematic review. Clin Orthop Relat Res 469:805\u2013812","journal-title":"Clin Orthop Relat Res"},{"key":"12513_CR5","unstructured":"The Royal College of Radiologists, The Society & College of Radiographers (2018) The radiological investigation of suspected physical abuse in children. SCoR, London, pp 5\u20139"},{"key":"12513_CR6","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.chiabu.2007.06.011","volume":"32","author":"SL Wootton-Gorges","year":"2008","unstructured":"Wootton-Gorges SL, Stein-Wexler R, Walton JW, Rosas AJ, Coulter KP, Rogers KK (2008) Comparison of computed tomography and chest radiography in the detection of rib fractures in abused infants. Child Abuse Negl 32:659\u2013663","journal-title":"Child Abuse Negl"},{"key":"12513_CR7","doi-asserted-by":"publisher","first-page":"e26","DOI":"10.1016\/j.crad.2019.09.102","volume":"74","author":"C Gladwell","year":"2019","unstructured":"Gladwell C, Simpson E (2019) Audit to assess compliance with the RCR\/SCoR guideline: the radiological investigation of suspected physical abuse in children. Clin Radiol 74:e26\u2013e27","journal-title":"Clin Radiol"},{"key":"12513_CR8","unstructured":"U.S. Food and Drug Administration (2023) Artificial intelligence and machine learning (AI\/ML)-enabled medical devices. Available via FDA. https:\/\/www.fda.gov\/medical-devices\/software-medical-device-samd\/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices. Accessed 11 Feb 2024"},{"key":"12513_CR9","unstructured":"Hourquet C (2023) BoneView is the first AI solution to receive FDA clearance for pediatric use in fracture detection. Available via Gleamer. https:\/\/www.gleamer.ai\/insights\/fda2023. Accessed 28 Sept 2024"},{"key":"12513_CR10","unstructured":"U.S. Department of Health and Human Services (2023) Children\u2019s Bureau: an office of the Administration for Children and Families. U.S. Department of Health & Human Services, Washington, DC, pp 21\u201322"},{"key":"12513_CR11","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.diii.2021.10.007","volume":"103","author":"M Dupuis","year":"2022","unstructured":"Dupuis M, Delbos L, Veil R, Adamsbaum C (2022) External validation of a commercially available deep learning algorithm for fracture detection in children. Diagn Interv Imaging 103:151\u2013159","journal-title":"Diagn Interv Imaging"},{"key":"12513_CR12","doi-asserted-by":"publisher","first-page":"1675","DOI":"10.1007\/s00247-023-05621-w","volume":"53","author":"I Gasmi","year":"2023","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 53:1675\u20131684","journal-title":"Pediatr Radiol"},{"key":"12513_CR13","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. Skeletal Radiol 51:2129\u20132139","journal-title":"Skeletal Radiol"},{"key":"12513_CR14","doi-asserted-by":"crossref","unstructured":"Montagnon E, Cerny M, Cadrin-Ch\u00eanevert A et al (2020) Deep learning workflow in radiology: a primer. Insights Imaging 11:22","DOI":"10.1186\/s13244-019-0832-5"},{"key":"12513_CR15","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 A-L 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","journal-title":"Pediatr Radiol"},{"key":"12513_CR16","doi-asserted-by":"publisher","first-page":"2386","DOI":"10.1007\/s00247-023-05754-y","volume":"53","author":"JR Zech","year":"2023","unstructured":"Zech JR, Jaramillo D, Altosaar J, Popkin CA, Wong TT (2023) Artificial intelligence to identify fractures on pediatric and young adult upper extremity radiographs. Pediatr Radiol 53:2386\u20132397","journal-title":"Pediatr Radiol"},{"key":"12513_CR17","doi-asserted-by":"publisher","first-page":"20220778","DOI":"10.1259\/bjr.20220778","volume":"96","author":"A Ghosh","year":"2023","unstructured":"Ghosh A, Bose S, Patton D et al (2023) Deep learning-based prediction of rib fracture presence in frontal radiographs of children under two years of age: a proof-of-concept study. Br J Radiol 96:20220778","journal-title":"Br J Radiol"},{"key":"12513_CR18","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1007\/s10278-023-00793-1","volume":"36","author":"A Ghosh","year":"2023","unstructured":"Ghosh A, Patton D, Bose S et al (2023) A patch-based deep learning approach for detecting rib fractures on frontal radiographs in young children. J Digit Imaging 36:1302\u20131313","journal-title":"J Digit Imaging"},{"key":"12513_CR19","doi-asserted-by":"publisher","first-page":"196","DOI":"10.4258\/hir.2013.19.3.196","volume":"19","author":"J Kim","year":"2013","unstructured":"Kim J, Kim S, Kim YJ, Kim KG, Park J (2013) Quantitative measurement method for possible rib fractures in chest radiographs. Healthc Inform Res 19:196","journal-title":"Healthc Inform Res"},{"key":"12513_CR20","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1007\/s00247-022-05287-w","volume":"52","author":"A Tsai","year":"2022","unstructured":"Tsai A, Kleinman PK (2022) Machine learning to identify distal tibial classic metaphyseal lesions of infant abuse: a pilot study. Pediatr Radiol 52:1095\u20131103","journal-title":"Pediatr Radiol"},{"key":"12513_CR21","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1136\/ip.6.3.203","volume":"6","author":"T Faelker","year":"2000","unstructured":"Faelker T, Pickett W, Brison RJ (2000) Socioeconomic differences in childhood injury: a population based epidemiologic study in Ontario, Canada. Inj Prev 6:203\u2013208","journal-title":"Inj Prev"},{"key":"12513_CR22","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S0033-3506(99)00182-1","volume":"113","author":"GJ Laing","year":"1999","unstructured":"Laing GJ, Logan S (1999) Patterns of unintentional injury in childhood and their relation to socio-economic factors. Public Health 113:291\u2013294","journal-title":"Public Health"}],"container-title":["European Radiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12513-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00330-026-12513-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00330-026-12513-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T12:06:24Z","timestamp":1788869184000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00330-026-12513-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":22,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["12513"],"URL":"https:\/\/doi.org\/10.1007\/s00330-026-12513-8","relation":{},"ISSN":["1432-1084"],"issn-type":[{"value":"1432-1084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"18 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The scientific guarantor of this publication is Professor Amaka C. Offiah.","order":1,"name":"Ethics","label":"Guarantor","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors of this manuscript declare relationships with the following companies: Visiana.","order":2,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"No complex statistical methods were necessary for this paper.","order":3,"name":"Ethics","label":"Statistics and biometry","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Written informed consent was waived by the Institutional Review Board.","order":4,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"Institutional Review Board approval was obtained.","order":5,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"None.","order":6,"name":"Ethics","label":"Study subjects or cohorts overlap","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"order":7,"name":"Ethics","label":"Methodology","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}}]}}