{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:34:48Z","timestamp":1786696488988,"version":"build-2736575974"},"reference-count":29,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Pediatric head trauma is a common reason for emergency department presentation. Although most children have minor injuries, a small proportion harbor clinically important traumatic brain injuries requiring urgent intervention. Artificial intelligence (AI) may offer structured support in computed tomography (CT) decision making, but evidence regarding the performance of general-purpose large language models in pediatric head trauma remains limited. Objective: To evaluate the association between AI-based cranial CT recommendations and clinically meaningful outcomes in pediatric patients with blunt head trauma and to assess the diagnostic performance and clinical utility of the model. Methods: This retrospective single-center observational study included pediatric patients younger than 18 years with blunt head trauma who underwent cranial CT imaging and had complete outcome data. A general-purpose large language model generated binary CT recommendations (\u201cCT recommended\u201d or \u201cCT not recommended\u201d) using structured clinical information available at the time of emergency department presentation. The primary outcome was a composite adverse clinical outcome defined as the occurrence of at least one of the following: emergency surgical intervention, intensive care unit admission, intubation, neurological sequelae or mortality. Diagnostic performance metrics, calibration analysis and decision curve analysis were performed. Results: A total of 819 pediatric patients were included, and the AI model recommended CT in 530 patients (64.7%). The primary outcome occurred in 143 patients (17.5%) and was significantly more frequent in the CT-recommended group than in the CT-not recommended group (24.5% vs. 4.5%; OR 6.90, 95% CI 3.82\u201312.45; p &lt; 0.001). Abnormal CT findings, emergency surgery, intubation and neurological sequelae were also significantly more common in patients for whom CT was recommended by the AI system. For the primary outcome, the AI recommendation demonstrated a sensitivity of 90.9%, specificity of 40.8%, positive predictive value of 24.5% and negative predictive value of 95.5%. Calibration analysis showed acceptable agreement between predicted probabilities and observed event rates. Decision curve analysis demonstrated greater net benefit than both the \u201ctreat-all\u201d and \u201ctreat-none\u201d strategies across a range of threshold probabilities. Conclusions: In this clinically selected cohort of pediatric patients with blunt head trauma who underwent cranial CT imaging, AI-based CT recommendations were strongly associated with adverse clinical outcomes and demonstrated high sensitivity and negative predictive value for identifying children at risk of clinically important events. These findings suggest that, within a clinically selected cohort of children who underwent cranial CT imaging, AI-generated CT recommendations were associated with clinically meaningful outcomes. However, these results should not be interpreted as validation of CT decision making in the broader pediatric head trauma population and require prospective validation in unselected cohorts.<\/jats:p>","DOI":"10.3390\/diagnostics16162558","type":"journal-article","created":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:08:29Z","timestamp":1786694909000},"page":"2558","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Model Decision Support for Cranial CT in Pediatric Head Trauma"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5294-0722","authenticated-orcid":false,"given":"Ezgi","family":"Cesur","sequence":"first","affiliation":[{"name":"Emergency Medicine Department, K\u00fctahya City Hospital, 43020 K\u00fctahya, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1392-4694","authenticated-orcid":false,"given":"Ali","family":"Halici","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Faculty of Medicine, K\u00fctahya Health Sciences University, 43100 K\u00fctahya, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nursel","family":"Kurtoglu","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Faculty of Medicine, K\u00fctahya Health Sciences University, 43100 K\u00fctahya, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1001\/archpediatrics.2011.1156","article-title":"Prevalence of clinically important traumatic brain injuries in children with minor blunt head trauma and isolated severe injury mechanisms","volume":"166","author":"Nigrovic","year":"2012","journal-title":"Arch. Pediatr. Adolesc. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.wneu.2016.03.045","article-title":"Epidemiology of global pediatric traumatic brain injury: Qualitative review","volume":"91","author":"Dewan","year":"2016","journal-title":"World Neurosurg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/S0196-0644(96)70261-5","article-title":"Minor head trauma: Is computed tomography always necessary?","volume":"27","author":"Miller","year":"1996","journal-title":"Ann. Emerg. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1097\/00005373-200108000-00004","article-title":"Pediatric minor head trauma: Indications for computed tomographic scanning revisited","volume":"51","author":"Simon","year":"2001","journal-title":"J. Trauma Acute Care Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"606","DOI":"10.6061\/clinics\/2016(10)09","article-title":"Pediatric minor head trauma: Do cranial CT scans change the therapeutic approach?","volume":"71","author":"Andrade","year":"2016","journal-title":"Clinics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1016\/j.annemergmed.2018.11.011","article-title":"Implementation of a clinical decision support system for children with minor blunt head trauma who are at nonnegligible risk for traumatic brain injuries","volume":"73","author":"Ballard","year":"2019","journal-title":"Ann. Emerg. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e019","DOI":"10.1097\/pq9.0000000000000019","article-title":"Quality improvement in pediatric head trauma with PECARN rules implementation as computerized decision support","volume":"2","author":"Atabaki","year":"2017","journal-title":"Pediatr. Qual. Saf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1038\/s41390-022-02226-1","article-title":"Artificial intelligence-based clinical decision support in pediatrics","volume":"93","author":"Ramgopal","year":"2023","journal-title":"Pediatr. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1007\/s10143-024-02897-w","article-title":"Artificial intelligence in paediatric head trauma: Enhancing diagnostic accuracy for skull fractures and brain haemorrhages","volume":"47","author":"Azad","year":"2024","journal-title":"Neurosurg. Rev."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Di Sarno, L., Caroselli, A., Tonin, G., Graglia, B., Pansini, V., Causio, F.A., Gatto, A., and Chiaretti, A. (2024). Artificial intelligence in pediatric emergency medicine: Applications, challenges, and future perspectives. Biomedicines, 12.","DOI":"10.20944\/preprints202404.1642.v1"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Orenuga, S., Jordache, P., Mirzai, D., Monteros, T., Gonzalez, E., Madkoor, A., Hirani, R., Tiwari, R.K., and Etienne, M. (2025). Traumatic brain injury and artificial intelligence: Shaping the future of neurorehabilitation\u2014A review. Life, 15.","DOI":"10.3390\/life15030424"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chong, S.-L., Liu, N., Barbier, S., and Ong, M.E.H. (2015). Predictive modeling in pediatric traumatic brain injury using machine learning. BMC Med. Res. Methodol., 15.","DOI":"10.1186\/s12874-015-0015-0"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"493","DOI":"10.3340\/jkns.2023.0195","article-title":"Artificial intelligence-enhanced neurocritical care for traumatic brain injury: Past, present and future","volume":"67","author":"Kim","year":"2024","journal-title":"J. Korean Neurosurg. Soc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e182847","DOI":"10.1001\/jamapediatrics.2018.2847","article-title":"Diagnosis and management of mild traumatic brain injury in children: A systematic review","volume":"172","author":"Yeates","year":"2018","journal-title":"JAMA Pediatr."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yigit, Y., Kaynak, M.F., Alkahlout, B., Ahmed, S., G\u00fcnay, S., and Ozbek, A.E. (2025). AI-assisted decision-making in mild traumatic brain injury. BMC Emerg. Med., 25.","DOI":"10.1186\/s12873-024-01159-8"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e20162709","DOI":"10.1542\/peds.2016-2709","article-title":"Use of traumatic brain injury prediction rules with clinical decision support","volume":"139","author":"Dayan","year":"2017","journal-title":"Pediatrics"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rajaei, F., Cheng, S., Williamson, C.A., Wittrup, E., and Najarian, K. (2023). AI-based decision support system for traumatic brain injury: A survey. Diagnostics, 13.","DOI":"10.3390\/diagnostics13091640"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1038\/s41746-025-01714-y","article-title":"Predicting outcomes after moderate and severe traumatic brain injury using artificial intelligence: A systematic review","volume":"8","author":"Malhotra","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1186\/s13049-016-0287-3","article-title":"Validation of the PECARN clinical decision rule for children with minor head trauma: A French multicenter prospective study","volume":"24","author":"Lorton","year":"2016","journal-title":"Scand. J. Trauma Resusc. Emerg. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1007\/s00431-025-06345-9","article-title":"An update on paediatric traumatic brain injury in the emergency department: A narrative review","volume":"184","author":"Alsuwais","year":"2025","journal-title":"Eur. J. Pediatr."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1007\/s00068-017-0811-9","article-title":"Pediatric Emergency Care Applied Research Network (PECARN) prediction rules in identifying high risk children with mild traumatic brain injury","volume":"43","author":"Yousefifard","year":"2017","journal-title":"Eur. J. Trauma Emerg. Surg."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2147","DOI":"10.1007\/s00431-022-04424-9","article-title":"PECARN Rule in diagnostic process of pediatric patients with minor head trauma in emergency department","volume":"181","author":"Gambacorta","year":"2022","journal-title":"Eur. J. Pediatr."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.annemergmed.2014.01.030","article-title":"Comparison of PECARN, CATCH, and CHALICE rules for children with minor head injury: A prospective cohort study","volume":"64","author":"Easter","year":"2014","journal-title":"Ann. Emerg. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1177\/1024907920930510","article-title":"The comparison of PECARN, CATCH, AND CHALICE criteria in children under the age of 18 years with minor head trauma in emergency department","volume":"29","author":"Gizli","year":"2022","journal-title":"Hong Kong J. Emerg. Med."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"12454","DOI":"10.1038\/s41598-022-16313-0","article-title":"Decision effect of a deep-learning model to assist a head computed tomography order for pediatric traumatic brain injury","volume":"12","author":"Heo","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e074867","DOI":"10.1136\/bmj-2023-074867","article-title":"Reducing computed tomography (CT) imaging for adults with minor traumatic brain injuries in the emergency department","volume":"386","author":"Rowe","year":"2024","journal-title":"BMJ"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e13251","DOI":"10.1002\/emp2.13251","article-title":"Use of artificial intelligence to support prehospital traumatic injury care: A scoping review","volume":"5","author":"Toy","year":"2024","journal-title":"JACEP Open"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"106466","DOI":"10.1016\/j.ijmedinf.2026.106466","article-title":"Safety and Diagnostic Accuracy of Large-Language Model Application of PECARN Head Injury Algorithm","volume":"216","author":"Simper","year":"2026","journal-title":"Int. J. Med. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lampros, M., Romeo, E., Zagorianakou, P., Voulgaris, S., and Alexiou, G.A. (2026). Evaluation of ChatGPT-5 for CT Imaging in Canadian CT Head Rule-Positive Mild Traumatic Brain Injury: A Pilot Study. Biomedicines, 14.","DOI":"10.3390\/biomedicines14071555"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2558\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T08:25:56Z","timestamp":1786695956000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2558"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,14]]},"references-count":29,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162558"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162558","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,14]]}}}