{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:53:47Z","timestamp":1777708427130,"version":"3.51.4"},"reference-count":48,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Early triage of trauma patients requiring massive transfusion (MT) may help to marshal appropriate resources and improve treatment and outcome. Artificial intelligence (AI) and machine learning (ML) offer theoretical advantages compared to conventional prediction algorithms but have not been thoroughly evaluated in this population. We hypothesized that AI\/ML techniques incorporating all available data in a\u00a0patient\u2019s\u00a0medical record could achieve similar, if not higher, performance in the prediction of mortality in MT patients as compared to existing models. Patients from the American College of Surgeons Trauma Quality Improvement Project database (TQIP) were retrospectively reviewed. Those receiving\u2009\u2265\u20095 units of red blood cells and\/or whole blood within the first four hours of arrival were defined as MT patients. Those receiving \u226510 units were identified as ultramassive transfusion (UMT) patients. ML models were created to predict 6-hour mortality using variables available at different time points, including patient arrival. Of 5,481,046 patients in TQIP from 2017 to 2021, 47,744 received MT and 20,337 of these received UMT. Using only variables available on arrival, MT AUROC was 0.901 [95% CI 0.895\u20130.910] which increased to 0.943 [95% CI 0.938\u20130.948] with addition of 4-hour variables. For UMT, arrival AUROC was 0.858 [95% CI 0.846\u20130.872] and increased to 0.922 [95% CI 0.914\u20130.931] at 4 hours. ML models reliably predict mortality in both MT and UMT patients. These are the only ML models trained on MT and UMT patients. Future work can focus on prospective implementation of these models with potential direct integration into the electronic medical record. Real-time utilization of comprehensive patient data may enhance clinical decision-making regarding which patients should continue receiving massive transfusion, thus optimizing the allocation of this limited resource.<\/jats:p>","DOI":"10.1371\/journal.pone.0335151","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:28:46Z","timestamp":1761326926000},"page":"e0335151","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["MIASurviveMTP: Machine learning for immediate assessment and survival prediction after massive transfusion protocol"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3864-0789","authenticated-orcid":true,"given":"Michael D.","family":"Cobler-Lichter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jessica M.","family":"Delamater","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brianna L.","family":"Collie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8338-2400","authenticated-orcid":true,"given":"Nicole B.","family":"Lyons","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luciana Tito","family":"Bustillos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Namias","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brandon M.","family":"Parker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan P.","family":"Meizoso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth G.","family":"Proctor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"issue":"11","key":"pone.0335151.ref001","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.1111\/ans.15416","article-title":"Ten-year evolution of a massive transfusion protocol in a level 1 trauma centre: have outcomes improved?","volume":"89","author":"JE van der Meij","year":"2019","journal-title":"ANZ J Surg"},{"key":"pone.0335151.ref002","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195179484.001.0001","volume-title":"The incidence and economic burden of injuries in the United States","author":"EA Finkelstein","year":"2006"},{"key":"pone.0335151.ref003"},{"issue":"1","key":"pone.0335151.ref004","first-page":"41","article-title":"Predefined massive transfusion protocols are associated with a reduction in organ failure and postinjury complications","volume":"66","author":"BA Cotton","year":"2009","journal-title":"J Trauma"},{"issue":"5","key":"pone.0335151.ref005","first-page":"1177","article-title":"Damage control hematology: the impact of a trauma exsanguination protocol on survival and blood product utilization","volume":"64","author":"BA Cotton","year":"2008","journal-title":"J Trauma"},{"issue":"2","key":"pone.0335151.ref006","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.jamcollsurg.2009.04.016","article-title":"Massive transfusion protocols: the role of aggressive resuscitation versus product ratio in mortality reduction","volume":"209","author":"DJ Riskin","year":"2009","journal-title":"J Am Coll Surg"},{"key":"pone.0335151.ref007","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1001\/archsurg.143.7.686","article-title":"A massive transfusion protocol to decrease blood component use and costs","volume":"143","author":"T O\u2019Keeffe","year":"2008","journal-title":"Arch Surg Chic Ill"},{"issue":"7","key":"pone.0335151.ref008","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1007\/s00268-017-4441-5","article-title":"Implementation of Trauma Center and Massive Transfusion Protocol Improves Outcomes for Major Trauma Patients: A Study at a Single Institution in Korea","volume":"42","author":"K Hwang","year":"2018","journal-title":"World J Surg"},{"key":"pone.0335151.ref009"},{"issue":"3","key":"pone.0335151.ref010","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1097\/TA.0000000000000914","article-title":"The Massive Transfusion Score as a decision aid for resuscitation: Learning when to turn the massive transfusion protocol on and off","volume":"80","author":"RA Callcut","year":"2016","journal-title":"J Trauma Acute Care Surg"},{"issue":"10","key":"pone.0335151.ref011","doi-asserted-by":"crossref","first-page":"2340","DOI":"10.1007\/s00268-023-07098-y","article-title":"Assessment of Machine Learning Methods to Predict Massive Blood Transfusion in Trauma","volume":"47","author":"M Strickland","year":"2023","journal-title":"World J Surg"},{"issue":"1","key":"pone.0335151.ref012","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1097\/TA.0b013e3182788b34","article-title":"Defining when to initiate massive transfusion: a validation study of individual massive transfusion triggers in PROMMTT patients","volume":"74","author":"RA Callcut","year":"2013","journal-title":"J Trauma Acute Care Surg"},{"issue":"1","key":"pone.0335151.ref013","doi-asserted-by":"crossref","first-page":"5176","DOI":"10.1038\/s41598-023-32453-3","article-title":"Assessing the utility of a sliding-windows deep neural network approach for risk prediction of trauma patients","volume":"13","author":"A Bonde","year":"2023","journal-title":"Sci Rep"},{"issue":"7","key":"pone.0335151.ref014","doi-asserted-by":"crossref","first-page":"487","DOI":"10.14744\/tjtes.2024.48074","article-title":"A method for predicting mortality in acute mesenteric ischemia: Machine learning","volume":"30","author":"AT Harmantepe","year":"2024","journal-title":"Ulus Travma Acil Cerrahi Derg"},{"issue":"11","key":"pone.0335151.ref015","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e32655","article-title":"Machine learning algorithm for predicting 30-day mortality in patients receiving rapid response system activation: A retrospective nationwide cohort study","volume":"10","author":"T Kurita","year":"2024","journal-title":"Heliyon"},{"issue":"3","key":"pone.0335151.ref016","doi-asserted-by":"crossref","DOI":"10.1097\/AS9.0000000000000314","article-title":"Early Prediction of Massive Transfusion for Patients With Traumatic Hemorrhage: Development of a Multivariable Machine Learning Model","volume":"4","author":"AJ Benjamin","year":"2023","journal-title":"Ann Surg Open"},{"key":"pone.0335151.ref017","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"GS Collins","year":"2024","journal-title":"BMJ"},{"key":"pone.0335151.ref018","first-page":"59","article-title":"Google Colaboratory.","volume-title":"Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners","author":"E Bisong"},{"key":"pone.0335151.ref019","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"pone.0335151.ref020","author":"M Abadi","year":"2015"},{"key":"pone.0335151.ref021","author":"J Yang","year":"2022"},{"key":"pone.0335151.ref022","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System.","author":"T Chen","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York (NY): ACM"},{"key":"pone.0335151.ref023","doi-asserted-by":"crossref","first-page":"106584","DOI":"10.1016\/j.cmpb.2021.106584","article-title":"Explanation of machine learning models using shapley additive explanation and application for real data in hospital","volume":"214","author":"Y Nohara","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0335151.ref024","doi-asserted-by":"crossref","first-page":"105449","DOI":"10.1016\/j.compbiomed.2022.105449","article-title":"Handling missing values in machine learning to predict patient-specific risk of adverse cardiac events: Insights from REFINE SPECT registry","volume":"145","author":"R Rios","year":"2022","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0335151.ref025","article-title":"Practical guide to building machine learning-based clinical prediction models using imbalanced datasets","volume":"9","author":"J Luu","year":"2024","journal-title":"Trauma Surg Acute Care Open"},{"issue":"16","key":"pone.0335151.ref026","doi-asserted-by":"crossref","first-page":"2244","DOI":"10.3390\/healthcare11162244","article-title":"Optimizing Clinical Decision Making with Decision Curve Analysis: Insights for Clinical Investigators","volume":"11","author":"D Piovani","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"pone.0335151.ref027","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s41512-019-0064-7","article-title":"A simple, step-by-step guide to interpreting decision curve analysis","volume":"3","author":"AJ Vickers","year":"2019","journal-title":"Diagn Progn Res"},{"key":"pone.0335151.ref028","first-page":"4768","article-title":"A unified approach to interpreting model predictions.","author":"SM Lundberg","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook (NY): Curran Associates Inc."},{"key":"pone.0335151.ref029","article-title":"Current controversies and advances in massive transfusion: Balancing evidence and practice","author":"T-L Lin","year":"2025","journal-title":"J Formos Med Assoc"},{"issue":"3","key":"pone.0335151.ref030","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1177\/0310057X20974035","article-title":"Massive transfusion experience, current practice and decision support: A survey of Australian and New Zealand anaesthetists","volume":"49","author":"BJ Sanderson","year":"2021","journal-title":"Anaesth Intensive Care"},{"issue":"2","key":"pone.0335151.ref031","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1097\/TA.0000000000003835","article-title":"When is enough enough? Odds of survival by unit transfused","volume":"94","author":"AM Loudon","year":"2023","journal-title":"J Trauma Acute Care Surg"},{"key":"pone.0335151.ref032","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jss.2023.05.028","article-title":"Data-Driven Blood Transfusion Thresholds for Severely Injured Patients During Blood Shortages","volume":"291","author":"D Ang","year":"2023","journal-title":"J Surg Res"},{"key":"pone.0335151.ref033","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1213\/ANE.0000000000006504","article-title":"Narrative review: Is there a transfusion cutoff value after which nonsurvivability is inevitable in trauma patients receiving ultramassive transfusion?","volume":"137","author":"JS Kim","year":"2023","journal-title":"Anesth Analg"},{"issue":"5","key":"pone.0335151.ref034","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1097\/TA.0000000000003980","article-title":"The reports of my death are greatly exaggerated: An evaluation of futility cut points in massive transfusion","volume":"95","author":"TW Clements","year":"2023","journal-title":"J Trauma Acute Care Surg"},{"issue":"3","key":"pone.0335151.ref035","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.jen.2005.03.004","article-title":"Variables predicting trauma patient survival following massive transfusion","volume":"31","author":"LM Criddle","year":"2005","journal-title":"J Emerg Nurs"},{"issue":"1","key":"pone.0335151.ref036","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1097\/TA.0000000000003121","article-title":"Outcomes after ultramassive transfusion in the modern era: An Eastern Association for the Surgery of Trauma multicenter study","volume":"91","author":"ZA Matthay","year":"2021","journal-title":"J Trauma Acute Care Surg"},{"issue":"1","key":"pone.0335151.ref037","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1097\/TA.0000000000003641","article-title":"Cresting mortality: Defining a plateau in ongoing massive transfusion","volume":"93","author":"MT Quintana","year":"2022","journal-title":"J Trauma Acute Care Surg"},{"key":"pone.0335151.ref038","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.jss.2020.03.004","article-title":"Death by Decade: Establishing a Transfusion Ceiling for Futility in Massive Transfusion","volume":"252","author":"MC Morris","year":"2020","journal-title":"J Surg Res"},{"issue":"5","key":"pone.0335151.ref039","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1097\/TA.0000000000004206","article-title":"Association between transfusion volume and survival outcome following trauma: Insight into the limit of transfusion from an analysis of nationwide trauma registry in Japan","volume":"96","author":"K Shibahashi","year":"2024","journal-title":"J Trauma Acute Care Surg"},{"key":"pone.0335151.ref040","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1001\/archsurg.133.9.947","article-title":"Is There a Limit to Massive Blood Transfusion After Severe Trauma?","volume":"133","author":"GC Velmahos","year":"1998","journal-title":"Arch Surg"},{"issue":"4","key":"pone.0335151.ref041","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1097\/TA.0b013e3182a12ba6","article-title":"Let technology do the work: Improving prediction of massive transfusion with the aid of a smartphone application","volume":"75","author":"MJ Mina","year":"2013","journal-title":"J Trauma Acute Care Surg"},{"issue":"2","key":"pone.0335151.ref042","first-page":"346","article-title":"Early prediction of massive transfusion in trauma: simple as ABC (assessment of blood consumption)?","volume":"66","author":"TC Nunez","year":"2009","journal-title":"J Trauma"},{"issue":"1150","key":"pone.0335151.ref043","doi-asserted-by":"crossref","first-page":"20220878","DOI":"10.1259\/bjr.20220878","article-title":"Data drift in medical machine learning: implications and potential remedies","volume":"96","author":"B Sahiner","year":"2023","journal-title":"Br J Radiol"},{"issue":"1","key":"pone.0335151.ref044","doi-asserted-by":"crossref","DOI":"10.1136\/tsaco-2023-001346","article-title":"Missingness matters: a secondary analysis of thromboelastography measurements from a recent prehospital randomized tranexamic acid clinical trial","volume":"9","author":"JK Donohue","year":"2024","journal-title":"Trauma Surg Acute Care Open"},{"issue":"2","key":"pone.0335151.ref045","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2019.20733","article-title":"Prospective and External Evaluation of a Machine Learning Model to Predict In-Hospital Mortality of Adults at Time of Admission","volume":"3","author":"N Brajer","year":"2020","journal-title":"JAMA Netw Open"},{"key":"pone.0335151.ref046","first-page":"104956","article-title":"Performance of machine learning algorithms for surgical site infection case detection and prediction: A systematic review and meta-analysis","volume":"84","author":"G Wu","year":"2022","journal-title":"Ann Med Surg (Lond)"},{"key":"pone.0335151.ref047","doi-asserted-by":"crossref","first-page":"100118","DOI":"10.1016\/j.pdisas.2020.100118","article-title":"Understanding end-users\u2019 perspectives: Towards developing usability guidelines for disaster apps","volume":"7","author":"ML Tan","year":"2020","journal-title":"Progress in Disaster Science"},{"issue":"1","key":"pone.0335151.ref048","doi-asserted-by":"crossref","DOI":"10.2196\/mhealth.8851","article-title":"Health Information Technology Usability Evaluation Scale (Health-ITUES) for Usability Assessment of Mobile Health Technology: Validation Study","volume":"6","author":"R Schnall","year":"2018","journal-title":"JMIR Mhealth Uhealth"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:28:54Z","timestamp":1761326934000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0335151"}},"subtitle":[],"editor":[{"given":"Laila","family":"Cure","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":48,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0335151","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]}}}