{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T21:31:20Z","timestamp":1793309480901,"version":"4.5.0"},"reference-count":39,"publisher":"American Medical Association (AMA)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"Importance<\/jats:title>Under austere prehospital conditions, rapid classification of injured patients for intervention or transport is essential for providing lifesaving care. Discerning which patients need care most urgently further allows for optimal allocation of limited resources. These triage processes are hindered by the limited diagnostic resources and modalities available in the prehospital environment.<\/jats:p><\/jats:sec>Objective<\/jats:title>To develop a triage model for prehospital use in patients with traumatic injury supported by machine learning (ML) analysis of continuous physiological waveform signals and derived patterns of vital signs.<\/jats:p><\/jats:sec>Design, Setting, and Participants<\/jats:title>This retrospective cohort study used data from January 1, 2018, to November 18, 2021, from critically ill patients with trauma transported by a large critical care air transport system serving Pennsylvania and surrounding states. Patients were included if classified as a trauma case by treating prehospital clinicians during a scene run by the transport service. Data were analyzed from May to November of 2024.<\/jats:p><\/jats:sec>Exposures<\/jats:title>Metrics derived from physiological waveform signal and vital sign patterns during the first 15 minutes following initiation of patient care and transport.<\/jats:p><\/jats:sec>Main Outcomes and Measures<\/jats:title>Administration of a lifesaving intervention (LSI) occurring within a 2-minute epoch during patient care. An ensemble ML approach was applied to predict LSI occurrence from physiological features recorded in the 2-minute epoch immediately preceding the LSI epoch.<\/jats:p><\/jats:sec>Results<\/jats:title>A total of 2809 participants were included in the analysis (mean [SD] age, 47.7 [19.5] years; 1981 [70.5%] men). These participants had 15\u202f088 two-minute epochs that yielded physiological data recording, of which 910 (6.0%) included an LSI. Good model performance was observed for predicting overall LSI, with an area under the receiver operating characteristics curve of 0.810 (95% CI, 0.782-0.842); sensitivity, 0.268 (95% CI, 0.193-0.357); positive predictive value, 0.301 (95% CI, 0.228-0.356); positive likelihood ratio, 6.793 (95% CI, 4.887-8.795); specificity, 0.960 (95% CI, 0.947-0.972); negative predictive value, 0.953 (95% CI, 0.943-0.964); and negative likelihood ratio, 0.763 (95% CI, 0.680-0.837). Performance was equivalent or better when predicting several LSI subcategories (eg, airway intervention, blood transfusion, vasopressor medication), when using physiological features captured up to 15 minutes prior to LSI administration, when predicting only the first LSI occurrence for each patient, and across mechanism of injury.<\/jats:p><\/jats:sec>Conclusions and Relevance<\/jats:title>In this cohort study of critically ill patients with trauma in the prehospital setting, an ML-based triage model using physiological features provided accurate predictions of lifesaving intervention delivery to single patients. Modeling approaches could be deployed in the field to help streamline and augment prehospital triage.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2025.9639","type":"journal-article","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T11:00:28Z","timestamp":1749466828000},"page":"e259639","source":"Crossref","is-referenced-by-count":26,"title":["A Machine Learning Trauma Triage Model for Critical Care Transport"],"prefix":"10.1001","volume":"8","author":[{"given":"Aaron C.","family":"Weidman","sequence":"first","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salim","family":"Malakouti","sequence":"additional","affiliation":[{"name":"NOMA AI Inc, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David D.","family":"Salcido","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chase","family":"Zikmund","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi","family":"Patel","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonard S.","family":"Weiss","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael R.","family":"Pinsky","sequence":"additional","affiliation":[{"name":"Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gilles","family":"Clermont","sequence":"additional","affiliation":[{"name":"NOMA AI Inc, Pittsburgh, Pennsylvania"},{"name":"Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Elmer","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronald K.","family":"Poropatich","sequence":"additional","affiliation":[{"name":"Center for Military Medicine Research, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua B.","family":"Brown","sequence":"additional","affiliation":[{"name":"Department of Surgery, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francis X.","family":"Guyette","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2025,6,9]]},"reference":[{"issue":"S2","key":"zoi250351r1","doi-asserted-by":"publisher","first-page":"1423","DOI":"10.1111\/trf.15161","article-title":"Outcomes of traumatic hemorrhagic shock and the epidemiology of preventable death from injury.","volume":"59","author":"Eastridge","year":"2019","journal-title":"Transfusion"},{"issue":"5-6","key":"zoi250351r2","doi-asserted-by":"publisher","first-page":"e154","DOI":"10.1093\/milmed\/usy252","article-title":"Prehospital resuscitation performed on hypotensive trauma patients in Afghanistan: the Prehospital Trauma Registry experience.","volume":"184","author":"Schauer","year":"2019","journal-title":"Mil Med"},{"issue":"2S","key":"zoi250351r3","doi-asserted-by":"publisher","first-page":"S186","DOI":"10.1097\/TA.0000000000003252","article-title":"Case-control analysis of prehospital death and prolonged field care survival during recent US military combat operations.","volume":"91","author":"Shackelford","year":"2021","journal-title":"J Trauma Acute Care Surg"},{"issue":"1","key":"zoi250351r4","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3109\/10903127.2015.1025157","article-title":"Prehospital trauma triage decision-making: a model of what happens between the 9-1-1 call and the hospital.","volume":"20","author":"Jones","year":"2016","journal-title":"Prehosp Emerg Care"},{"issue":"RR-1","key":"zoi250351r5","first-page":"1","article-title":"Guidelines for field triage of injured patients: recommendations of the National Expert Panel on Field Triage, 2011.","volume":"61","author":"Sasser","year":"2012","journal-title":"MMWR Recomm Rep"},{"issue":"6","key":"zoi250351r6","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1097\/SHK.0000000000001567","article-title":"Prehospital point of care testing for the early detection of shock and prediction of lifesaving interventions.","volume":"54","author":"Galvagno","year":"2020","journal-title":"Shock"},{"issue":"2","key":"zoi250351r7","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.jamcollsurg.2015.10.016","article-title":"Prospective validation of the national field triage guidelines for identifying seriously injured persons.","volume":"222","author":"Newgard","year":"2016","journal-title":"J Am Coll Surg"},{"issue":"1","key":"zoi250351r8","doi-asserted-by":"publisher","first-page":"S98","DOI":"10.1097\/TA.0000000000001482","article-title":"Inefficacy of standard vital signs for predicting mortality and the need for prehospital life-saving interventions in blunt trauma patients transported via helicopter: a repeated call for new measures.","volume":"83","author":"Liu","year":"2017","journal-title":"J Trauma Acute Care Surg"},{"issue":"2S","key":"zoi250351r9","doi-asserted-by":"publisher","first-page":"S146","DOI":"10.1097\/TA.0000000000002649","article-title":"Combat medic testing of a novel monitoring capability for early detection of hemorrhage.","volume":"89","author":"Koons","year":"2020","journal-title":"J Trauma Acute Care Surg"},{"key":"zoi250351r10","first-page":"318","article-title":"Automatic pre-hospital vital signs waveform and trend data capture fills quality management, triage and outcome prediction gaps.","volume":"2008","author":"Mackenzie","year":"2008","journal-title":"AMIA Annu Symp Proc"},{"issue":"3","key":"zoi250351r11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1097\/TA.0b013e3181ad67de","article-title":"Heart rate variability as a triage tool in patients with trauma during prehospital helicopter transport.","volume":"67","author":"King","year":"2009","journal-title":"J Trauma"},{"issue":"11","key":"zoi250351r12","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1016\/j.compbiomed.2013.09.012","article-title":"The impact of noise on the reliability of heart-rate variability and complexity analysis in trauma patients.","volume":"43","author":"Liu","year":"2013","journal-title":"Comput Biol Med"},{"issue":"2","key":"zoi250351r13","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1097\/SHK.0000000000000186","article-title":"Utility of vital signs, heart rate variability and complexity, and machine learning for identifying the need for lifesaving interventions in trauma patients.","volume":"42","author":"Liu","year":"2014","journal-title":"Shock"},{"issue":"6","key":"zoi250351r14","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1097\/SHK.0000000000000356","article-title":"Improving the prediction of mortality and the need for life-saving interventions in trauma patients using standard vital signs with heart-rate variability and complexity.","volume":"43","author":"Liu","year":"2015","journal-title":"Shock"},{"issue":"4","key":"zoi250351r15","doi-asserted-by":"publisher","first-page":"S93","DOI":"10.1097\/TA.0000000000000573","article-title":"Is heart-rate complexity a surrogate measure of cardiac output before, during, and after hemorrhage in a conscious sheep model of multiple hemorrhages and resuscitation?","volume":"79","author":"Liu","year":"2015","journal-title":"J Trauma Acute Care Surg"},{"issue":"4","key":"zoi250351r16","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1097\/TA.0b013e3181848241","article-title":"Heart-rate complexity for prediction of prehospital lifesaving interventions in trauma patients.","volume":"65","author":"Cancio","year":"2008","journal-title":"J Trauma"},{"issue":"2","key":"zoi250351r17","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1097\/01.ta.0000196623.48952.0e","article-title":"Heart rate variability and its association with mortality in prehospital trauma patients.","volume":"60","author":"Cooke","year":"2006","journal-title":"J Trauma"},{"issue":"5","key":"zoi250351r18","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1097\/SHK.0b013e3181dc07da","article-title":"Is respiration-induced variation in the photoplethysmogram associated with major hypovolemia in patients with acute traumatic injuries?","volume":"34","author":"Chen","year":"2010","journal-title":"Shock"},{"issue":"1","key":"zoi250351r19","doi-asserted-by":"publisher","first-page":"S25","DOI":"10.1097\/TA.0b013e3182211601","article-title":"Use of advanced machine-learning techniques for noninvasive monitoring of hemorrhage.","volume":"71","author":"Convertino","year":"2011","journal-title":"J Trauma"},{"issue":"3","key":"zoi250351r20","doi-asserted-by":"publisher","first-page":"S222","DOI":"10.1097\/TA.0000000000000198","article-title":"Early identification of uncontrolled hemorrhage after trauma: current status and future direction.","volume":"77","author":"Shackelford","year":"2014","journal-title":"J Trauma Acute Care Surg"},{"issue":"4","key":"zoi250351r21","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1097\/TA.0b013e318241c059","article-title":"Continuously recorded oxygen saturation and heart rate during prehospital transport outperform initial measurement in prediction of mortality after trauma.","volume":"72","author":"Woodford","year":"2012","journal-title":"J Trauma Acute Care Surg"},{"issue":"5","key":"zoi250351r22","doi-asserted-by":"publisher","first-page":"S111","DOI":"10.1097\/TA.0000000000000937","article-title":"Machine learning and new vital signs monitoring in civilian en route care: a systematic review of the literature and future implications for the military.","volume":"81","author":"Liu","year":"2016","journal-title":"J Trauma Acute Care Surg"},{"issue":"5","key":"zoi250351r23","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1097\/SHK.0000000000000898","article-title":"Machine learning for predicting outcomes in trauma.","volume":"48","author":"Liu","year":"2017","journal-title":"Shock"},{"issue":"1","key":"zoi250351r24","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1080\/10903127.2022.2043963","article-title":"Under-triage and over-triage using the field triage guidelines for injured patients: a systematic review.","volume":"27","author":"Lupton","year":"2023","journal-title":"Prehosp Emerg Care"},{"issue":"2","key":"zoi250351r25","doi-asserted-by":"publisher","first-page":"e49","DOI":"10.1097\/TA.0000000000003627","article-title":"National guideline for the field triage of injured patients: recommendations of the National Expert Panel on Field Triage, 2021.","volume":"93","author":"Newgard","year":"2022","journal-title":"J Trauma Acute Care Surg"},{"key":"zoi250351r26","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.jelectrocard.2020.10.002","article-title":"An optimization study of the ultra-short period for HRV analysis at rest and post-exercise.","volume":"63","author":"Wu","year":"2020","journal-title":"J Electrocardiol"},{"issue":"1","key":"zoi250351r28","doi-asserted-by":"publisher","first-page":"7","DOI":"10.7205\/MILMED.170.1.7","article-title":"Prehospital physiologic data and lifesaving interventions in trauma patients.","volume":"170","author":"Holcomb","year":"2005","journal-title":"Mil Med"},{"key":"zoi250351r29","first-page":"2825","article-title":"Scikit-learn: machine learning in Python.","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"issue":"2","key":"zoi250351r31","doi-asserted-by":"publisher","first-page":"135","DOI":"10.3109\/10903127.2012.749966","article-title":"Variation in prehospital use and uptake of the national Field Triage Decision Scheme.","volume":"17","author":"Barnett","year":"2013","journal-title":"Prehosp Emerg Care"},{"issue":"6","key":"zoi250351r32","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1097\/TA.0b013e3182191a1b","article-title":"Out-of-hospital decision making and factors influencing the regional distribution of injured patients in a trauma system.","volume":"70","author":"Newgard","year":"2011","journal-title":"J Trauma"},{"issue":"11","key":"zoi250351r33","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1016\/j.injury.2005.07.010","article-title":"Is paramedic judgement useful in prehospital trauma triage?","volume":"36","author":"Mulholland","year":"2005","journal-title":"Injury"},{"key":"zoi250351r34","doi-asserted-by":"publisher","DOI":"10.2196\/58740","article-title":"Enhancing performance of the National Field Triage Guidelines Using Machine Learning: development of a prehospital triage model to predict severe trauma.","volume":"26","author":"Chen","year":"2024","journal-title":"J Med Internet Res"},{"key":"zoi250351r35","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.ajem.2023.12.011","article-title":"Modified physiologic criteria for the field triage scheme: efficacy of major trauma recognition in different age groups in Asia.","volume":"77","author":"Chien","year":"2024","journal-title":"Am J Emerg Med"},{"issue":"4","key":"zoi250351r36","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1080\/10903127.2021.1958961","article-title":"Need for emergent intervention within 6 hours: a novel prediction model for hospital trauma triage.","volume":"26","author":"Morris","year":"2022","journal-title":"Prehosp Emerg Care"},{"issue":"5","key":"zoi250351r37","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1001\/jamasurg.2018.4752","article-title":"Development and validation of a prediction model for prehospital triage of trauma patients.","volume":"154","author":"van Rein","year":"2019","journal-title":"JAMA Surg"},{"issue":"2","key":"zoi250351r38","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1097\/SHK.0000000000002166","article-title":"APPRAISE-HRI: an artificial intelligence algorithm for triage of hemorrhage casualties.","volume":"60","author":"Stallings","year":"2023","journal-title":"Shock"},{"issue":"2","key":"zoi250351r39","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s11517-013-1130-x","article-title":"Development and validation of a machine learning algorithm and hybrid system to predict the need for life-saving interventions in trauma patients.","volume":"52","author":"Liu","year":"2014","journal-title":"Med Biol Eng Comput"},{"key":"zoi250351r27","unstructured":"Weidman? AC. ML trauma triage model. Open Science Framework. November 14, 2024. Accessed April 7, 2025. https:\/\/osf.io\/4m6fn\/"},{"key":"zoi250351r30","unstructured":"Wickham? H. ggplot2: Elegant graphics for data analysis. 2016. Accessed April 7, 2025. https:\/\/ggplot2.tidyverse.org"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2835117\/weidman_2025_oi_250351_1751569651.98428.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T15:00:36Z","timestamp":1752073236000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2835117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":39,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6,2]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2025.9639","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,9]]}}}