{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:47:56Z","timestamp":1777052876268,"version":"3.51.4"},"reference-count":40,"publisher":"BMJ","funder":[{"DOI":"10.13039\/100000938","name":"Robert E. Leet and Clara Guthrie Patterson Trust","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/100000938","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Inj Prev"],"accepted":{"date-parts":[[2026,4,8]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Victims of child physical abuse (CPA) disproportionately use the emergency department, yet identifying CPA remains challenging in this setting. An urgent need to develop tools that aid providers in recognising violence-related injuries in children exists. Developing a CPA predictive algorithm could improve identification and clinical familiarity with risk factors. We aimed to develop a CPA predictive algorithm and assess its performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using data from May 2017 to March 2022 involving patients aged 0\u201317 years treated at a large paediatric hospital in Connecticut, we used statistical and machine learning techniques (eg, XGBoost, lasso regression) to develop a CPA predictive algorithm. Model performance was evaluated using out-of-sample area under the receiver operating characteristic curve (AUROC), sensitivity and positive predictive value (PPV). Performance metrics were stratified by age group and gender.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 138\u2009234 patients, 298 had documented CPA. Most victims were aged 0\u20139 years, using Medicaid, and of Hispanic\/Latino ethnicity. XGBoost demonstrated the best performance. The out-of-sample AUROC was 82.6% (SE=1.6%). At 90% specificity, sensitivity was 57.7% (SE=3.1%), and PPV was 1.2% (SE=0.1%). Among high-risk patients, older children presented with behavioural health diagnoses, while young children presented with non-specific somatic symptoms; no gender differences were identified.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility of using discharge data to develop a CPA algorithm. Findings underscore the role of behavioural health professionals in recognising CPA and highlight high-risk groups that warrant further investigation. Examining the intersectionality of gender and age among children at high risk for CPA may reveal additional opportunities for clinical intervention.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/ip-2025-046076","type":"journal-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:25:35Z","timestamp":1777051535000},"page":"ip-2025-046076","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Preliminary development of a child physical abuse algorithm using emergency department records"],"prefix":"10.1136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-6090","authenticated-orcid":false,"given":"Amy A.","family":"Hunter","sequence":"first","affiliation":[{"name":"Department of Public Health Sciences, School of Medicine, UConn Health, Farmington, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shane","family":"Sacco","sequence":"additional","affiliation":[{"name":"Division of Behavioral Sciences and Community Health, UConn Health, Farmington, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Connecticut, Storrs, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Connecticut, Storrs, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Connecticut, Storrs, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"suffix":"Jr","given":"Robert H.","family":"Aseltine","sequence":"additional","affiliation":[{"name":"Division of Behavioral Sciences and Community Health, UConn Health, Farmington, Connecticut, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"2026042410252281000_ip-2025-046076v1.1","doi-asserted-by":"publisher","DOI":"10.1007\/s11606-008-0516-1"},{"key":"2026042410252281000_ip-2025-046076v1.2","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2010-2096"},{"key":"2026042410252281000_ip-2025-046076v1.3","doi-asserted-by":"crossref","first-page":"104179","DOI":"10.1016\/j.chiabu.2019.104179","article-title":"Trends in US physician diagnosis of child physical abuse and neglect injuries, 2006-2014","volume":"98","author":"Zins","year":"2019","journal-title":"Child Abuse Negl"},{"key":"2026042410252281000_ip-2025-046076v1.4","unstructured":"U.S. Department of Health & Human Services, Administration for Children and Families, Administration on Children, Youth and Families, Children\u2019s Bureau . Child maltreatment 2022. 2024. Available: https:\/\/www.acf.hhs.gov\/cb\/data-research\/child-maltreatment"},{"key":"2026042410252281000_ip-2025-046076v1.5","doi-asserted-by":"publisher","DOI":"10.1097\/01.pec.0000208180.94166.dd"},{"key":"2026042410252281000_ip-2025-046076v1.6","doi-asserted-by":"publisher","DOI":"10.1097\/PEC.0000000000000257"},{"key":"2026042410252281000_ip-2025-046076v1.7","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2010-0031"},{"key":"2026042410252281000_ip-2025-046076v1.8","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2020-011833","article-title":"Machine Learning for Child and Adolescent Health: A Systematic Review","volume":"147","author":"Hoodbhoy","year":"2021","journal-title":"Pediatrics"},{"key":"2026042410252281000_ip-2025-046076v1.9","doi-asserted-by":"crossref","DOI":"10.1186\/s40621-018-0176-5","article-title":"Association between emergency department utilization and the risk of child maltreatment in young children","volume":"5","author":"Kuang","year":"2018","journal-title":"Inj Epidemiol"},{"key":"2026042410252281000_ip-2025-046076v1.10","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0247404","article-title":"A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records","volume":"16","author":"Annapragada","year":"2021","journal-title":"PLoS One"},{"key":"2026042410252281000_ip-2025-046076v1.11","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/10775595221127925","article-title":"Identifying Children at Risk for Maltreatment Using Emergency Medical Services\u2019 Data: An Exploratory Study","volume":"29","author":"Bressler","year":"2024","journal-title":"Child Maltreat"},{"key":"2026042410252281000_ip-2025-046076v1.12","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocz069"},{"key":"2026042410252281000_ip-2025-046076v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.acap.2021.11.004"},{"key":"2026042410252281000_ip-2025-046076v1.14","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1016\/j.jpedsurg.2021.03.007","article-title":"Using deep learning and natural language processing models to detect child physical abuse","volume":"56","author":"Shahi","year":"2021","journal-title":"J Pediatr Surg"},{"key":"2026042410252281000_ip-2025-046076v1.15","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2021-051742","article-title":"Traumatic Head Injury and the Diagnosis of Abuse: A Cluster Analysis","volume":"149","author":"Boos","year":"2022","journal-title":"Pediatrics"},{"key":"2026042410252281000_ip-2025-046076v1.16","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1007\/s00247-022-05287-w","article-title":"Machine learning to identify distal tibial classic metaphyseal lesions of infant abuse: a pilot study","volume":"52","author":"Tsai","year":"2022","journal-title":"Pediatr Radiol"},{"key":"2026042410252281000_ip-2025-046076v1.17","doi-asserted-by":"crossref","DOI":"10.1259\/bjr.20220778","article-title":"Deep learning-based prediction of rib fracture presence in frontal radiographs of children under two years of age: a proof-of-concept study","volume":"96","author":"Ghosh","year":"2023","journal-title":"Br J Radiol"},{"key":"2026042410252281000_ip-2025-046076v1.18","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1016\/j.eswa.2017.06.035","article-title":"Identifying child abuse through text mining and machine learning","volume":"88","author":"Amrit","year":"2017","journal-title":"Expert Syst Appl"},{"key":"2026042410252281000_ip-2025-046076v1.19","unstructured":"Keyes D , Turfe H , Das J . Prevention strategies. StatPearls Treasure Island (FL): StatPearls Publishing, 2025."},{"key":"2026042410252281000_ip-2025-046076v1.20","doi-asserted-by":"crossref","DOI":"10.2196\/51003","article-title":"Use of Epic Electronic Health Record System for Health Care Research: Scoping Review","volume":"25","author":"Chishtie","year":"2023","journal-title":"J Med Internet Res"},{"key":"2026042410252281000_ip-2025-046076v1.21","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc B Stat Methodol"},{"key":"2026042410252281000_ip-2025-046076v1.22","doi-asserted-by":"crossref","DOI":"10.1038\/s41398-020-01100-0","article-title":"Machine learning for suicide risk prediction in children and adolescents with electronic health records","volume":"10","author":"Su","year":"2020","journal-title":"Transl Psychiatry"},{"key":"2026042410252281000_ip-2025-046076v1.23","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C , eds. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016","DOI":"10.1145\/2939672.2939785"},{"key":"2026042410252281000_ip-2025-046076v1.24","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression Shrinkage and Selection Via the Lasso","volume":"58","author":"Tibshirani","year":"1996","journal-title":"J R Stat Soc B Stat Methodol"},{"key":"2026042410252281000_ip-2025-046076v1.25","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"JMLR"},{"key":"2026042410252281000_ip-2025-046076v1.26","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2026042410252281000_ip-2025-046076v1.27","unstructured":"Lundberg SM , Lee S . SHAP (shapley additive explanations) documentation. 2025."},{"key":"2026042410252281000_ip-2025-046076v1.28","doi-asserted-by":"publisher","DOI":"10.1136\/injuryprev-2019-043579"},{"key":"2026042410252281000_ip-2025-046076v1.29","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0283595","article-title":"Target-based fusion using social determinants of health to enhance suicide prediction with electronic health records","volume":"18","author":"Sacco","year":"2023","journal-title":"PLoS One"},{"key":"2026042410252281000_ip-2025-046076v1.30","doi-asserted-by":"crossref","unstructured":"Tipton K , Leas BF , Flores E , et al . Impact of healthcare algorithms on racial and ethnic disparities in health and healthcare. 2023.","DOI":"10.23970\/AHRQEPCCER268"},{"key":"2026042410252281000_ip-2025-046076v1.31","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000278","article-title":"Bias in artificial intelligence algorithms and recommendations for mitigation","volume":"2","author":"Nazer","year":"2023","journal-title":"PLOS Digit Health"},{"key":"2026042410252281000_ip-2025-046076v1.32","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2020-049625","article-title":"Race and Bias in Child Maltreatment Diagnosis and Reporting","volume":"148","author":"Palusci","year":"2021","journal-title":"Pediatrics"},{"key":"2026042410252281000_ip-2025-046076v1.33","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2020.33710","article-title":"Racial and Ethnic Differences in Emergency Department Diagnostic Imaging at US Children\u2019s Hospitals, 2016-2019","volume":"4","author":"Marin","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2026042410252281000_ip-2025-046076v1.34","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2010-0298"},{"key":"2026042410252281000_ip-2025-046076v1.35","doi-asserted-by":"publisher","DOI":"10.1001\/jama.281.7.621"},{"key":"2026042410252281000_ip-2025-046076v1.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.chiabu.2012.04.006"},{"key":"2026042410252281000_ip-2025-046076v1.37","doi-asserted-by":"crossref","first-page":"NP12768","DOI":"10.1177\/08862605211001479","article-title":"Emergency Department Admissions for Physical Child Abuse: Evidence from the 2006-2017 Nationwide Emergency Department Sample","volume":"37","author":"Carbone","year":"2022","journal-title":"J Interpers Violence"},{"key":"2026042410252281000_ip-2025-046076v1.38","unstructured":"Centers for Disease Control and Prevention . Preventing child abuse and nelgect. n.d. Available: https:\/\/www.cdc.gov\/child-abuse-neglect\/prevention\/index.html"},{"key":"2026042410252281000_ip-2025-046076v1.39","unstructured":"Centers for Disease Control and Prevention . Data and statistics on children\u2019s mental health. n.d. Available: https:\/\/www.cdc.gov\/children-mental-health\/data-research\/index.html"},{"key":"2026042410252281000_ip-2025-046076v1.40","doi-asserted-by":"crossref","first-page":"105619","DOI":"10.1016\/j.chiabu.2022.105619","article-title":"Child maltreatment-related children\u2019s emergency department visits before and during the COVID-19 pandemic in Connecticut","volume":"128","author":"Amick","year":"2022","journal-title":"Child Abuse Negl"}],"container-title":["Injury Prevention"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/ip-2025-046076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:25:40Z","timestamp":1777051540000},"score":1,"resource":{"primary":{"URL":"https:\/\/injuryprevention.bmj.com\/lookup\/doi\/10.1136\/ip-2025-046076"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":40,"alternative-id":["10.1136\/ip-2025-046076"],"URL":"https:\/\/doi.org\/10.1136\/ip-2025-046076","relation":{},"ISSN":["1353-8047","1475-5785"],"issn-type":[{"value":"1353-8047","type":"print"},{"value":"1475-5785","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]}}}