{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T11:56:31Z","timestamp":1775649391414,"version":"3.50.1"},"reference-count":40,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"unspecified","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"the National Science Foundation Graduate Research Fellowship Program","award":["DGE-1840340"],"award-info":[{"award-number":["DGE-1840340"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Trauma Surg Acute Care Open"],"accepted":{"date-parts":[[2026,3,24]]},"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Traumatic brain injury (TBI) affects 1.7\u2009million individuals annually in the USA, with cerebral edema (CE) as a critical determinant of outcomes and neurosurgical interventions. Delays in TBI diagnosis and triage in prehospital or resource-limited settings contribute to suboptimal care. This study evaluated the predictive potential of machine learning models using clinical and physiological data to detect CE on initial head CT scans, addressing this gap.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a mixed retrospective and prospective study of 1222 suspected TBI patients. Data included clinical characteristics, radiographic scores (Marshall and Rotterdam), and physiological features derived from ECG and photoplethysmography signals collected within 1\u2009hour of admission. Statistical models employed logistic regression and gradient boosting, using Shapley additive explanations for feature importance. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The models demonstrated high predictive accuracy for CE-related radiographic features, including midline shift and cisternal abnormalities (AUROC: 0.79\u20130.85). Clinical features such as Glasgow Coma Scale components and intubation status, combined with physiological variables like heart rate variability, contributed significantly to predictions. In contrast, predictions for other findings (eg, epidural hematoma) showed lower discriminatory power. Prehospital applicability was highlighted by the reliance on readily available physiological data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Machine learning models effectively predict CE prior to CT scans, offering a rapid decision support tool for triage and neurosurgical prioritization in austere and resource-limited settings. Early identification of CE could improve patient outcomes by optimizing transport and treatment strategies. Future research should focus on multicenter validation and streamlined data collection to enhance generalizability and clinical utility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of evidence<\/jats:title>\n                    <jats:p>Level III, Prognostic.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/tsaco-2025-002021","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T11:05:23Z","timestamp":1775646323000},"page":"e002021","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Rapid prediction of cerebral edema on CT scan after traumatic brain injury"],"prefix":"10.1136","volume":"11","author":[{"given":"Ryan B","family":"Felix","sequence":"first","affiliation":[{"name":"Fischell Department of Bioengineering, University of Maryland College Park, College Park, Maryland, USA"},{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jamie","family":"Podell","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathalyn","family":"Urquizo","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasmin","family":"Alamdeen","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devon","family":"Beagan","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minahil","family":"Cheema","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunjan Y","family":"Parikh","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9584-0579","authenticated-orcid":false,"given":"William","family":"Teeter","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Emergency Medicine, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Charles McC. Mathias, Jr., National Study Center for Trauma & Emergency Medical Systems, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hegang","family":"Chen","sequence":"additional","affiliation":[{"name":"Epidemiology and Public Health, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lujie Karen","family":"Chen","sequence":"additional","affiliation":[{"name":"Information Systems, University of Maryland Baltimore County, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roumen","family":"Vesselinov","sequence":"additional","affiliation":[{"name":"Charles McC. Mathias, Jr., National Study Center for Trauma & Emergency Medical Systems, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Epidemiology and Public Health, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John P","family":"Fisher","sequence":"additional","affiliation":[{"name":"Fischell Department of Bioengineering, University of Maryland College Park, College Park, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Yang","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Department of Anesthesiology, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Institute of Health Computing, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Hu","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Department of Anesthesiology, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"},{"name":"Institute of Health Computing, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1509-9034","authenticated-orcid":false,"given":"Neeraj","family":"Badjatia","sequence":"additional","affiliation":[{"name":"Program in Trauma, University of Maryland Baltimore School of Medicine, Baltimore, Maryland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"2026040804051247000_11.2.e002021.1","unstructured":"Faul M , Wald MM , Xu L , Coronado VG . Traumatic brain injury in the United States: emergency department visits, hospitalizations, and deaths, 2002-2006. 2010. Available: https:\/\/stacks.cdc.gov\/view\/cdc\/5571"},{"key":"2026040804051247000_11.2.e002021.2","first-page":"549","article-title":"CDC Grand Rounds: Reducing Severe Traumatic Brain Injury in the United States","volume":"62","author":"Wright","year":"2013","journal-title":"MMWR Morb Mortal Wkly Rep"},{"key":"2026040804051247000_11.2.e002021.3","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1097\/TA.0b013e318226ed59","article-title":"Impact of secondary transfer on patients with severe traumatic brain injury","volume":"72","author":"Joosse","year":"2012","journal-title":"J Trauma Acute Care Surg"},{"key":"2026040804051247000_11.2.e002021.4","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1097\/TA.0000000000000719","article-title":"Emergent operation for isolated severe traumatic brain injury: Does time matter?","volume":"79","author":"Matsushima","year":"2015","journal-title":"J Trauma Acute Care Surg"},{"key":"2026040804051247000_11.2.e002021.5","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1177\/000313481808400225","article-title":"Head CT before Transfer Does Not Decrease Time to Craniotomy for TBI Patients","volume":"84","author":"Tonui","year":"2018","journal-title":"Am Surg"},{"key":"2026040804051247000_11.2.e002021.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jen.2008.12.010"},{"key":"2026040804051247000_11.2.e002021.7","doi-asserted-by":"publisher","DOI":"10.1007\/s13311-010-0003-3"},{"key":"2026040804051247000_11.2.e002021.8","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1111\/jon.12355","article-title":"Prehospital Imaging-Based Triage of Head Trauma with a Mobile Stroke Unit: First Evidence and Literature Review","volume":"26","author":"Schwindling","year":"2016","journal-title":"J Neuroimaging"},{"key":"2026040804051247000_11.2.e002021.9","unstructured":"Mason J . Mobile stroke units for prehospital care of ischemic stroke. In: CADTH Issues in Emerging Health Technologies. Canadian Agency for Drugs and Technologies in Health, Ottawa (ON. 2016. Available: http:\/\/www.ncbi.nlm.nih.gov\/books\/NBK481475\/"},{"key":"2026040804051247000_11.2.e002021.10","doi-asserted-by":"crossref","first-page":"2060","DOI":"10.1016\/j.injury.2022.02.020","article-title":"The diagnostic accuracy of prehospital triage tools in identifying patients with traumatic brain injury: A systematic review","volume":"53","author":"Alqurashi","year":"2022","journal-title":"Injury"},{"key":"2026040804051247000_11.2.e002021.11","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1097\/MEJ.0000000000000327","article-title":"The diagnostic accuracy of the HITSNS prehospital triage rule for identifying patients with significant traumatic brain injury: a cohort study","volume":"23","author":"Fuller","year":"2016","journal-title":"Eur J Emerg Med"},{"key":"2026040804051247000_11.2.e002021.12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3171\/2024.1.JNS232569","article-title":"Early GFAP and UCH-L1 point-of-care biomarker measurements for the prediction of traumatic brain injury and progression in patients with polytrauma and hemorrhagic shock","volume":"141","author":"Sperry","year":"2024","journal-title":"J Neurosurg"},{"key":"2026040804051247000_11.2.e002021.13","first-page":"S287","article-title":"The diagnosis of head injury requires a classification based on computed axial tomography","volume":"9 Suppl 1","author":"Marshall","year":"1992","journal-title":"J Neurotrauma"},{"key":"2026040804051247000_11.2.e002021.14","doi-asserted-by":"publisher","DOI":"10.1227\/01.NEU.0000186013.63046.6B"},{"key":"2026040804051247000_11.2.e002021.15","doi-asserted-by":"publisher","DOI":"10.1227\/NEU.0b013e3182517aa1"},{"key":"2026040804051247000_11.2.e002021.16","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1097\/PCC.0000000000000150","article-title":"Use of Rotterdam CT scores for mortality risk stratification in children with traumatic brain injury","volume":"15","author":"Liesemer","year":"2014","journal-title":"Pediatr Crit Care Med"},{"key":"2026040804051247000_11.2.e002021.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2014.01.017"},{"key":"2026040804051247000_11.2.e002021.18","unstructured":"Haut ER , Mann NC , Kotwal RS . Military trauma care\u2019s learning health system: the importance of data driven decision making. comm mil trauma care\u2019s learn heal syst its transl to civ sect. Available: https:\/\/www.nationalacademies.org\/documents\/embed\/link\/LF2255DA3DD1C41C0A42D3BEF0989ACAECE3053A6A9B\/file\/D1B3C1424D725D4E2F341FC5552C880B6FB1D68F02AA?noSaveAs=1"},{"key":"2026040804051247000_11.2.e002021.19","doi-asserted-by":"publisher","DOI":"10.1136\/emj.2007.047373"},{"key":"2026040804051247000_11.2.e002021.20","doi-asserted-by":"publisher","DOI":"10.1016\/S0196-0644(05)82288-7"},{"key":"2026040804051247000_11.2.e002021.21","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.wneu.2020.12.132","article-title":"Heart Rate Variability as a Predictor of Mortality in Traumatic Brain Injury: A Systematic Review and Meta-Analysis","volume":"148","author":"Florez-Perdomo","year":"2021","journal-title":"World Neurosurg"},{"key":"2026040804051247000_11.2.e002021.22","doi-asserted-by":"publisher","DOI":"10.1089\/neu.2010.1497"},{"key":"2026040804051247000_11.2.e002021.23","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0195087","article-title":"Using support vector machines on photoplethysmographic signals to discriminate between hypovolemia and euvolemia","volume":"13","author":"Reljin","year":"2018","journal-title":"PLoS One"},{"key":"2026040804051247000_11.2.e002021.24","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-26318-4","article-title":"Rapid prediction of secondary neurologic decline after traumatic brain injury: a data analytic approach","volume":"13","author":"Podell","year":"2023","journal-title":"Sci Rep"},{"key":"2026040804051247000_11.2.e002021.25","doi-asserted-by":"crossref","DOI":"10.1007\/s10916-016-0648-5","article-title":"Reliable Collection of Real-Time Patient Physiologic Data from less Reliable Networks: a \u201cMonitor of Monitors\u201d System (MoMs)","volume":"41","author":"Hu","year":"2017","journal-title":"J Med Syst"},{"key":"2026040804051247000_11.2.e002021.26","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.93.5.1043"},{"key":"2026040804051247000_11.2.e002021.27","doi-asserted-by":"crossref","first-page":"7618","DOI":"10.1038\/s41598-024-57538-5","article-title":"Utilizing ultra-early continuous physiologic data to develop automated measures of clinical severity in a traumatic brain injury population","volume":"14","author":"Yang","year":"2024","journal-title":"Sci Rep"},{"key":"2026040804051247000_11.2.e002021.28","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1097\/TA.0000000000001047","article-title":"Automated continuous vital signs predict use of uncrossed matched blood and massive transfusion following trauma","volume":"80","author":"Parimi","year":"2016","journal-title":"J Trauma Acute Care Surg"},{"key":"2026040804051247000_11.2.e002021.29","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1097\/TA.0000000000003031","article-title":"Comparison of massive and emergency transfusion prediction scoring systems after trauma with a new Bleeding Risk Index score applied in-flight","volume":"90","author":"Yang","year":"2021","journal-title":"J Trauma Acute Care Surg"},{"key":"2026040804051247000_11.2.e002021.30","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2018.00761","article-title":"Continuous Vital Sign Analysis to Predict Secondary Neurological Decline After Traumatic Brain Injury","volume":"9","author":"Melinosky","year":"2018","journal-title":"Front Neurol"},{"key":"2026040804051247000_11.2.e002021.31","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.6.520"},{"key":"2026040804051247000_11.2.e002021.32","doi-asserted-by":"publisher","DOI":"10.1142\/S0219720005001004"},{"key":"2026040804051247000_11.2.e002021.33","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"2026040804051247000_11.2.e002021.34","doi-asserted-by":"crossref","unstructured":"van SM , Moons KG , de GJ , Collins GS , Altman DG , Eijkemans MJ , et al . Sample size for binary logistic prediction models: Beyond events per variable criteria. Stat Methods Med Res 2018. doi:10.1177\/0962280218784726","DOI":"10.1177\/0962280218784726"},{"key":"2026040804051247000_11.2.e002021.35","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . Xgboost: a scalable tree boosting system. 2016,","DOI":"10.1145\/2939672.2939785"},{"key":"2026040804051247000_11.2.e002021.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2026040804051247000_11.2.e002021.37","unstructured":"Lundberg SM , Lee SI . A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems. Curran Associates, Inc, 2017."},{"key":"2026040804051247000_11.2.e002021.38","unstructured":"Goswami M , Szafer K , Choudhry A , Cai Y , Li S , Dubrawski A . MOMENT: a family of open time-series foundation models. Available: http:\/\/arxiv.org\/abs\/2402.03885"},{"key":"2026040804051247000_11.2.e002021.39","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2020.599268","article-title":"Prehospital Detection of Life-Threatening Intracranial Pathology: An Unmet Need for Severe TBI in Austere, Rural, and Remote Areas","volume":"11","author":"Whiting","year":"2020","journal-title":"Front Neurol"},{"key":"2026040804051247000_11.2.e002021.40","article-title":"Near Infrared Spectroscopy as a Diagnostic Tool for Screening of Intracranial Hematomas; A Systematic Review and Meta-Analysis","volume":"13","author":"Zarei","year":"2025","journal-title":"Arch Acad Emerg Med"}],"container-title":["Trauma Surgery &amp; Acute Care Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/tsaco-2025-002021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T11:05:30Z","timestamp":1775646330000},"score":1,"resource":{"primary":{"URL":"https:\/\/tsaco.bmj.com\/lookup\/doi\/10.1136\/tsaco-2025-002021"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4,8]]},"published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1136\/tsaco-2025-002021"],"URL":"https:\/\/doi.org\/10.1136\/tsaco-2025-002021","relation":{},"ISSN":["2397-5776"],"issn-type":[{"value":"2397-5776","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}