{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,21]],"date-time":"2026-11-21T03:29:20Z","timestamp":1795231760683,"version":"4.10.3"},"reference-count":27,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"6","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":["J Trauma Acute Care Surg"],"published-print":{"date-parts":[[2021,6]]},"abstract":"<jats:sec>\n            <jats:title>BACKGROUND<\/jats:title>\n            <jats:p>In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in the first hours after traumatic injury.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>METHODS<\/jats:title>\n            <jats:p>Using an American College of Surgeons Trauma Quality Improvement Program\u2013derived database of truncal and junctional gunshot wound (GSW) patients (aged 16\u201360 years), we trained an information-aware Dirichlet deep neural network (field artificial intelligence triage). Using supervised training, field artificial intelligence triage was trained to predict shock and the need for major hemorrhage control procedures or early massive transfusion (MT) using GSW anatomical locations, vital signs, and patient information available in the field. In parallel, a confidence model was developed to predict the true-class probability (scale of 0\u20131), indicating the likelihood that the prediction made was correct, based on the values and interconnectivity of input variables.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>RESULTS<\/jats:title>\n            <jats:p>A total of 29,816 patients met all the inclusion criteria. Shock, major surgery, and early MT were identified in 13.0%, 22.4%, and 6.3% of the included patients, respectively. Field artificial intelligence triage achieved mean areas under the receiver operating characteristic curve of 0.89, 0.86, and 0.82 for prediction of shock, early MT, and major surgery, respectively, for 80\/20 train-test splits over 1,000 epochs. Mean predicted true-class probability for errors\/correct predictions was 0.25\/0.87 for shock, 0.30\/0.81 for MT, and 0.24\/0.69 for major surgery.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>CONCLUSION<\/jats:title>\n            <jats:p>Field artificial intelligence triage accurately identifies potential shock in truncal GSW patients and predicts their need for MT and major surgery, with a high degree of certainty. The presented model is an important proof of concept. Future iterations will use an expansion of databases to refine and validate the model, further adding to its potential to improve triage in the field, both in civilian and military settings.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>LEVEL OF EVIDENCE<\/jats:title>\n            <jats:p>Prognostic, Level III.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/ta.0000000000003155","type":"journal-article","created":{"date-parts":[[2021,4,2]],"date-time":"2021-04-02T08:16:06Z","timestamp":1617351366000},"page":"1054-1060","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":49,"title":["Development of a field artificial intelligence triage tool: Confidence in the prediction of shock, transfusion, and definitive surgical therapy in patients with truncal gunshot wounds"],"prefix":"10.1097","volume":"90","author":[{"given":"Charlie J.","family":"Nederpelt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ava K.","family":"Mokhtari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osaid","family":"Alser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodoros","family":"Tsiligkaridis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay","family":"Roberts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miriam","family":"Cha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason A.","family":"Fawley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan J.","family":"Parks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"April E.","family":"Mendoza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter J.","family":"Fagenholz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haytham M.A.","family":"Kaafarani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David R.","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George C.","family":"Velmahos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Noelle","family":"Saillant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2021,4,2]]},"reference":[{"issue":"2","key":"bib1-20250806","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1017\/S1049023X0004276X","article-title":"Disaster triage: START, then SAVE\u2014a new method of dynamic triage for victims of a catastrophic earthquake","volume":"11","year":"1996","journal-title":"Prehosp Disaster Med"},{"issue":"RR-1","key":"bib2-20250806","first-page":"1","article-title":"Guidelines for field triage of injured patients: recommendations of the National Expert Panel on Field Triage, 2011","volume":"61","year":"2012","journal-title":"MMWR Recomm Rep"},{"issue":"4","key":"bib3-20250806","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1002\/bjs.11304","article-title":"Trauma models to identify major trauma and mortality in the prehospital setting","volume":"107","year":"2020","journal-title":"Br J Surg"},{"key":"bib4-20250806","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1097\/TA.0000000000002690","article-title":"Disparities in rural versus urban field triage: risk and mitigating factors for undertriage","volume":"89","year":"2020","journal-title":"J Trauma Acute Care Surg"},{"issue":"4","key":"bib5-20250806","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1097\/TA.0000000000002393","article-title":"Undertriaged trauma patients: who are we missing?","volume":"87","year":"2019","journal-title":"J Trauma Acute Care Surg"},{"issue":"2","key":"bib6-20250806","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.annemergmed.2019.06.018","article-title":"National study of triage and access to trauma centers for older adults","volume":"75","year":"2020","journal-title":"Ann Emerg Med"},{"issue":"1","key":"bib7-20250806","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13049-020-00725-w","article-title":"Performance of pre-hospital evaluations in ruling out invasive chest stab wounds","volume":"28","year":"2020","journal-title":"Scand J Trauma Resusc Emerg Med"},{"issue":"4","key":"bib8-20250806","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1001\/jamasurg.2017.4472","article-title":"Accuracy of prehospital triage in selecting severely injured trauma patients","volume":"153","year":"2018","journal-title":"JAMA Surg"},{"issue":"6","key":"bib9-20250806","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1097\/TA.0b013e318252510a","article-title":"The mortality benefit of direct trauma center transport in a regional trauma system: a population-based analysis","volume":"72","year":"2012","journal-title":"J Trauma Acute Care Surg"},{"issue":"6","key":"bib10-20250806","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1016\/j.jamcollsurg.2016.02.014","article-title":"Cost-effectiveness of field trauma triage among injured adults served by emergency medical services","volume":"222","year":"2016","journal-title":"J Am Coll Surg"},{"issue":"7","key":"bib11-20250806","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1001\/jamapediatrics.2019.1068","article-title":"Comparison of machine learning optimal classification trees with the pediatric emergency care applied research network head trauma decision rules","volume":"173","year":"2019","journal-title":"JAMA Pediatr"},{"issue":"4","key":"bib12-20250806","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1097\/SLA.0000000000002956","article-title":"Surgical risk is not linear: derivation and validation of a novel, user-friendly, and machine-learning-based Predictive OpTimal Trees in Emergency Surgery Risk (POTTER) Calculator","volume":"268","year":"2018","journal-title":"Ann Surg"},{"key":"bib13-20250806","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1002\/bjs.11442","article-title":"Prehospital triage of acute aortic syndrome using a machine learning algorithm","volume":"107","year":"2020","journal-title":"Br J Surg"},{"issue":"3","key":"bib14-20250806","doi-asserted-by":"crossref","first-page":"e0229331","DOI":"10.1371\/journal.pone.0229331","article-title":"Predicting intensive care unit admission among patients presenting to the emergency department using machine learning and natural language processing","volume":"15","year":"2020","journal-title":"PLoS One"},{"key":"bib15-20250806","doi-asserted-by":"crossref","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","year":"2015","journal-title":"BMJ"},{"issue":"6","key":"bib16-20250806","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1097\/01.ta.0000220386.84012.bf","article-title":"Trauma Associated Severe Hemorrhage (TASH)-Score: probability of mass transfusion as surrogate for life threatening hemorrhage after multiple trauma","volume":"60","year":"2006","journal-title":"J Trauma"},{"issue":"7494","key":"bib17-20250806","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1136\/bmj.330.7494.740","article-title":"What makes a good clinical decision support system","volume":"330","year":"2005","journal-title":"BMJ"},{"issue":"7494","key":"bib18-20250806","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1136\/bmj.38398.500764.8F","article-title":"Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success","volume":"330","year":"2005","journal-title":"BMJ"},{"issue":"6","key":"bib19-20250806","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.1007\/s00268-020-05394-5","article-title":"Multicenter validation of the Revised Assessment of Bleeding and Transfusion (RABT) score for predicting massive transfusion","volume":"44","year":"2020","journal-title":"World J Surg"},{"issue":"Suppl 2","key":"bib20-20250806","first-page":"S57","article-title":"A predictive model for massive transfusion in combat casualty patients","volume":"64","year":"2008","journal-title":"J Trauma"},{"issue":"4","key":"bib21-20250806","doi-asserted-by":"crossref","first-page":"1126","DOI":"10.1007\/s00268-019-05289-0","article-title":"The FASILA score: a novel bio-clinical score to predict massive blood transfusion in patients with abdominal trauma","volume":"44","year":"2020","journal-title":"World J Surg"},{"issue":"Suppl 1","key":"bib22-20250806","first-page":"S33","article-title":"Multicenter validation of a simplified score to predict massive transfusion in trauma","volume":"69","year":"2010","journal-title":"J Trauma"},{"issue":"2","key":"bib23-20250806","first-page":"346","article-title":"Early prediction of massive transfusion in trauma: simple as ABC (assessment of blood consumption)?","volume":"66","year":"2009","journal-title":"J Trauma"},{"issue":"4","key":"bib24-20250806","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1016\/j.jamcollsurg.2007.05.007","article-title":"Early predictors of massive transfusion in combat casualties","volume":"205","year":"2007","journal-title":"J Am Coll Surg"},{"issue":"4","key":"bib25-20250806","doi-asserted-by":"crossref","first-page":"R172","DOI":"10.1186\/cc12851","article-title":"The Shock Index revisited \u2014 a fast guide to transfusion requirement? A retrospective analysis on 21,853 patients derived from the TraumaRegister DGU","volume":"17","year":"2013","journal-title":"Crit Care"},{"issue":"4","key":"bib26-20250806","doi-asserted-by":"crossref","first-page":"R129","DOI":"10.1186\/cc11432","article-title":"Predicting on-going hemorrhage and transfusion requirement after severe trauma: a validation of six scoring systems and algorithms on the TraumaRegister DGU","volume":"16","year":"2012","journal-title":"Crit Care"},{"issue":"11","key":"bib27-20250806","doi-asserted-by":"crossref","first-page":"3560","DOI":"10.1007\/s00268-018-4674-y","article-title":"Massive transfusion: the Revised Assessment of Bleeding and Transfusion (RABT) score","volume":"42","year":"2018","journal-title":"World J Surg"}],"container-title":["Journal of Trauma and Acute Care Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/TA.0000000000003155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T16:19:22Z","timestamp":1754497162000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/TA.0000000000003155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,2]]},"references-count":27,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1097\/ta.0000000000003155","relation":{},"ISSN":["2163-0763","2163-0755"],"issn-type":[{"value":"2163-0763","type":"electronic"},{"value":"2163-0755","type":"print"}],"subject":[],"published":{"date-parts":[[2021,4,2]]}}}