{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T18:42:05Z","timestamp":1787510525689,"version":"build-2736575974"},"reference-count":29,"publisher":"BMJ","issue":"10","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Emerg Med J"],"accepted":{"date-parts":[[2025,3,3]]},"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early intervention in patients with major traumatic injuries is critical. Decision support can improve clinicians\u2019 ability to identify high-risk patients. The aim of this study was to compare the performance of a machine-learning (ML) decision support system to that of expert clinicians and to assess the ML system\u2019s impact on augmenting human risk prediction after injury in the prehospital phase of care.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This early clinical evaluation study compared a ML risk prediction system to expert clinicians in assessing a patient\u2019s risk of trauma-induced coagulopathy (TIC). The study was conducted between 1 January 2019 and 31 June 2019 at two air ambulance sites in the south of England. The ML system used a Bayesian Network algorithm to predict TIC. Comparisons in predictive performance were made first between expert clinicians and the ML system and second, between expert clinicians and expert clinicians exposed to the ML system\u2019s outputs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Overall, 51 expert clinicians were enrolled in the study and 184 patient assessments from 135 patients were analysed. The median age of included patients was 31 years old (IQR 23, 47), 75% were male and median Injury Severity Score 17 (IQR 9, 34). 62 patients (46%) received blood within 4\u2009hours of injury and 26 patients (19%) developed TIC. The ML system did not outperform expert clinicians in discriminating between patients with and without TIC (area under the curve (AUC) ML: 0.87 (95% CI 0.79, 0.95) vs AUC clinician: 0.83 (95% CI 0.74, 0.92), p=0.330)). Calibration and overall accuracy of the ML system were superior. Expert clinicians\u2019 risk prediction, when augmented by the ML system, showed potential for improvement compared with unassisted human performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Early after injury, an ML system performs well compared with expert prehospital clinicians in the prediction of TIC and blood transfusion. The study suggests that ML systems may augment clinical risk prediction in trauma.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/emermed-2024-214396","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T13:20:17Z","timestamp":1744723217000},"page":"654-661","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":5,"title":["Early clinical evaluation of a machine-learning system for risk prediction of trauma-induced coagulopathy in the prehospital setting"],"prefix":"10.1136","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7147-6861","authenticated-orcid":false,"given":"Max E R","family":"Marsden","sequence":"first","affiliation":[{"name":"Centre for Trauma Sciences, Queen Mary University of London Blizard Institute, London, UK"},{"name":"Academic Department of Military Surgery and Trauma, Defence Medical Services, Lichfield, UK"},{"name":"Department of Trauma Surgery, Barts Health NHS Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zane B","family":"Perkins","sequence":"additional","affiliation":[{"name":"Centre for Trauma Sciences, Queen Mary University of London Blizard Institute, London, UK"},{"name":"Department of Trauma Surgery, Barts Health NHS Trust, London, UK"},{"name":"London\u2019s Air Ambulance, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erhan","family":"Pisirir","sequence":"additional","affiliation":[{"name":"School of Electronical Engineering and Computer Sciences, Queen Mary University of London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William","family":"Marsh","sequence":"additional","affiliation":[{"name":"School of Electronical Engineering and Computer Sciences, Queen Mary University of London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evangelia","family":"Kyrimi","sequence":"additional","affiliation":[{"name":"School of Electronical Engineering and Computer Sciences, Queen Mary University of London, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Rossetto","sequence":"additional","affiliation":[{"name":"Centre for Trauma Sciences, Queen Mary University of London Blizard Institute, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard L","family":"Lyon","sequence":"additional","affiliation":[{"name":"Air Ambulance Kent, Surrey and Sussex, Redhill, UK"},{"name":"School of Health Sciences, University of Surrey, Guildford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne","family":"Weaver","sequence":"additional","affiliation":[{"name":"London\u2019s Air Ambulance, London, UK"},{"name":"Emergency Medicine, Barts Health NHS Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8593-6582","authenticated-orcid":false,"given":"Ross","family":"Davenport","sequence":"additional","affiliation":[{"name":"Centre for Trauma Sciences, Queen Mary University of London Blizard Institute, London, UK"},{"name":"Department of Trauma Surgery, Barts Health NHS Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nigel RM","family":"Tai","sequence":"additional","affiliation":[{"name":"Academic Department of Military Surgery and Trauma, Defence Medical Services, Lichfield, UK"},{"name":"Department of Trauma Surgery, Barts Health NHS Trust, London, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,4,15]]},"reference":[{"key":"2025120100551146000_42.10.654.1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1802345"},{"key":"2025120100551146000_42.10.654.2","doi-asserted-by":"publisher","DOI":"10.1186\/s13049-023-01083-z"},{"key":"2025120100551146000_42.10.654.3","doi-asserted-by":"publisher","DOI":"10.1136\/emermed-2023-213086"},{"key":"2025120100551146000_42.10.654.4","doi-asserted-by":"crossref","DOI":"10.1136\/tsaco-2023-001214","article-title":"Identification of major hemorrhage in trauma patients in the prehospital setting: diagnostic accuracy and impact on outcome","volume":"9","author":"Wohlgemut","year":"2024","journal-title":"Trauma Surg Acute Care Open"},{"key":"2025120100551146000_42.10.654.5","doi-asserted-by":"publisher","DOI":"10.1037\/a0016755"},{"key":"2025120100551146000_42.10.654.6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1038\/s41572-021-00264-3","article-title":"Trauma-induced coagulopathy","volume":"7","author":"Moore","year":"2021","journal-title":"Nat Rev Dis Primers"},{"key":"2025120100551146000_42.10.654.7","doi-asserted-by":"publisher","DOI":"10.1097\/01.TA.0000069184.82147.06"},{"key":"2025120100551146000_42.10.654.8","first-page":"22","article-title":"Validation of Point of Care INR measurement post trauma","volume":"24","author":"Mitra","year":"2012","journal-title":"EMA - Emergency Medicine Australasia"},{"key":"2025120100551146000_42.10.654.9","doi-asserted-by":"crossref","DOI":"10.3390\/medicina55100653","article-title":"Early Identification of Acute Traumatic Coagulopathy Using Clinical Prediction Tools: A Systematic Review","volume":"55","author":"Thorn","year":"2019","journal-title":"Medicina (Kaunas)"},{"key":"2025120100551146000_42.10.654.10","doi-asserted-by":"publisher","DOI":"10.1097\/TA.0000000000004385"},{"key":"2025120100551146000_42.10.654.11","doi-asserted-by":"publisher","DOI":"10.1136\/emermed-2022-212379"},{"key":"2025120100551146000_42.10.654.12","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000003771"},{"key":"2025120100551146000_42.10.654.13","unstructured":"Marsden M . The impact of a Bayesian network for pre-hospital decision-support after trauma. Queen Mary Univeristy of London, 2021."},{"key":"2025120100551146000_42.10.654.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01772-9"},{"key":"2025120100551146000_42.10.654.15","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1971.03180150059012"},{"key":"2025120100551146000_42.10.654.16","doi-asserted-by":"publisher","DOI":"10.1097\/00005373-197403000-00001"},{"key":"2025120100551146000_42.10.654.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2008.08.010"},{"key":"2025120100551146000_42.10.654.18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1538-7836.2010.03945.x"},{"key":"2025120100551146000_42.10.654.19","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0000000000002825"},{"key":"2025120100551146000_42.10.654.20","doi-asserted-by":"publisher","DOI":"10.7326\/L15-5093"},{"key":"2025120100551146000_42.10.654.21","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/26.4.404"},{"key":"2025120100551146000_42.10.654.22","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"2025120100551146000_42.10.654.23","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-024-05015-w"},{"key":"2025120100551146000_42.10.654.24","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves","volume":"12","author":"Robin","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2025120100551146000_42.10.654.25","doi-asserted-by":"crossref","unstructured":"Wickham H . Ggplot2: elegant graphics for data analysis. Springer, 2016.","DOI":"10.1007\/978-3-319-24277-4_9"},{"key":"2025120100551146000_42.10.654.26","unstructured":"Harrell FE . Package \u2018rms\u2019. 2019."},{"key":"2025120100551146000_42.10.654.27","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2025120100551146000_42.10.654.28","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(24)00047-5"},{"key":"2025120100551146000_42.10.654.29","doi-asserted-by":"publisher","DOI":"10.1097\/ACO.0b013e3283509675"}],"container-title":["Emergency Medicine Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/emermed-2024-214396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T09:18:09Z","timestamp":1764580689000},"score":1,"resource":{"primary":{"URL":"https:\/\/emj.bmj.com\/lookup\/doi\/10.1136\/emermed-2024-214396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,15]]},"references-count":29,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,9,24]]},"published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1136\/emermed-2024-214396"],"URL":"https:\/\/doi.org\/10.1136\/emermed-2024-214396","relation":{},"ISSN":["1472-0205","1472-0213"],"issn-type":[{"value":"1472-0205","type":"print"},{"value":"1472-0213","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,15]]}}}