{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:55:17Z","timestamp":1787320517010,"version":"build-2736575974"},"reference-count":28,"publisher":"BMJ","issue":"6","license":[{"start":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T00:00:00Z","timestamp":1749168000000},"content-version":"unspecified","delay-in-days":5,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007687","name":"Swedish Society of Medicine","doi-asserted-by":"crossref","award":["SLS-973387"],"award-info":[{"award-number":["SLS-973387"]}],"id":[{"id":"10.13039\/501100007687","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Swedish Carnegie Hero Fund"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,5,9]]},"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop models to predict opportunities for improvement in trauma care and compare the performance of these models to the currently used audit filters.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Retrospective registry-based study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Single-centre, Scandinavian level one equivalent trauma centre.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>8220 adult trauma patients screened for opportunities for improvement between 2013 and 2022.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary and secondary outcome measures<\/jats:title>\n                    <jats:p>Two machine learning models (logistic regression and XGBoost) and the currently used audit filters were compared. Internal validation by an expanding window approach with annual updates was used for model evaluation. Performance measured by discrimination, calibration, sensitivity and false positive rate of opportunities for improvement prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 8220 patients, with a mean age of 45 years, were analysed; 69% were men with a mean injury severity score of 12. Opportunities for improvement were identified in 496 (6%) patients. Both the logistic regression and XGBoost models were well-calibrated, with intercalibration indices of 0.02 and 0.02, respectively. The models demonstrated higher areas under the receiver operating characteristic curve (AUCs) (logistic regression: 0.71; XGBoost: 0.74). The XGBoost model had a lower false positive rate at a similar sensitivity (false positive rate: 0.63). The audit filters had an AUC of 0.62 and a false positive rate of 0.67.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The logistic regression and XGBoost models outperformed audit filters in predicting opportunities for improvement among adult trauma patients and can potentially be used to improve systems for selecting patients for trauma peer review.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2025-099624","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T04:40:38Z","timestamp":1749184838000},"page":"e099624","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":5,"title":["Predicting opportunities for improvement in trauma care using machine learning: a retrospective registry-based study at a major trauma centre"],"prefix":"10.1136","volume":"15","author":[{"given":"Jonatan","family":"Attergrim","sequence":"first","affiliation":[{"name":"Department of Global Public Health, Karolinska Institutet, Stockholm, Sweden"},{"name":"Perioperative Medicine and Intensive Care, Karolinska University Hospital, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0554-1872","authenticated-orcid":false,"given":"Kelvin","family":"Szolnoky","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lovisa","family":"Str\u00f6mmer","sequence":"additional","affiliation":[{"name":"Department of Surgery, Capio S:t G\u00f6rans Hospital, Stockholm, Sweden"},{"name":"Division of Surgery, Department of Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olof","family":"Brattstr\u00f6m","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Mora Hospital, Mora, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gunilla","family":"Wihlke","sequence":"additional","affiliation":[{"name":"Perioperative Medicine and Intensive Care, Karolinska University Hospital, Stockholm, Sweden"},{"name":"Trauma and Reparative Medicine, Karolinska University Hospital, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Jacobsson","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering and Health Systems, KTH Royal Institute of Technology, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6069-4794","authenticated-orcid":false,"given":"Martin","family":"Gerdin W\u00e4rnberg","sequence":"additional","affiliation":[{"name":"Department of Global Public Health, Karolinska Institutet, Stockholm, Sweden"},{"name":"Perioperative Medicine and Intensive Care, Karolinska University Hospital, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"2025121410593912000_15.6.e099624.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(18)32203-7"},{"key":"2025121410593912000_15.6.e099624.2","unstructured":"Vos T , Lim SS , Abbafati C , et al . Global burden of 369 diseases and injuries in 204 countries and territories, 1990\u20132019: A systematic analysis for the global burden of disease study 2019. Lancet 2020. Available: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0140673620309259"},{"key":"2025121410593912000_15.6.e099624.3","unstructured":"World Health Organization . Guidelines for trauma quality improvement programmes, Available: https:\/\/www.who.int\/publications\/i\/item\/guidelines-for-trauma-quality-improvement-programmes"},{"key":"2025121410593912000_15.6.e099624.4","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1097\/SLA.0b013e31828df98e","article-title":"Development and evaluation of evidence-informed quality indicators for adult injury care","volume":"259","author":"Santana","year":"2014","journal-title":"Ann Surg"},{"key":"2025121410593912000_15.6.e099624.5","unstructured":"American College of Surgeons . Resources for optimal care of the injured patient. Chicago, IL 60611-3295: American College of Surgeons, 2022."},{"key":"2025121410593912000_15.6.e099624.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjsurg.2014.02.006"},{"key":"2025121410593912000_15.6.e099624.7","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1007\/s40719-018-0127-1","article-title":"Quality benchmarking in trauma: from the NTDB to TQIP","volume":"4","author":"Hornor","year":"2018","journal-title":"Curr Trauma Rep"},{"key":"2025121410593912000_15.6.e099624.8","article-title":"Audit filters for improving processes of care and clinical outcomes in trauma systems","volume":"2009","author":"Evans","year":"2009","journal-title":"Cochrane Database Syst Rev"},{"key":"2025121410593912000_15.6.e099624.9","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1097\/00005373-199609000-00003","article-title":"Continuous use of standard process audit filters has limited value in an established trauma system","volume":"41","author":"Cryer","year":"1996","journal-title":"J Trauma: Injury, Infect Crit Care"},{"key":"2025121410593912000_15.6.e099624.10","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1111\/aas.13151","article-title":"Analysis of preventable deaths and errors in trauma care in a Scandinavian trauma level-I centre","volume":"62","author":"Ghorbani","year":"2018","journal-title":"Acta Anaesthesiol Scand"},{"key":"2025121410593912000_15.6.e099624.11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.anclin.2018.09.001","article-title":"Recognizing preventable death","volume":"37","author":"Radke","year":"2019","journal-title":"Anesthesiol Clin"},{"key":"2025121410593912000_15.6.e099624.12","doi-asserted-by":"crossref","first-page":"1960","DOI":"10.1016\/j.injury.2016.05.042","article-title":"Survival prediction algorithms miss significant opportunities for improvement if used for case selection in trauma quality improvement programs","volume":"47","author":"Heim","year":"2016","journal-title":"Injury"},{"key":"2025121410593912000_15.6.e099624.13","unstructured":"SweTrau . \u00c5rsrapporter, Available: http:\/\/rcsyd.se\/swetrau\/om-swetrau\/arsrapporter"},{"key":"2025121410593912000_15.6.e099624.14","doi-asserted-by":"crossref","DOI":"10.1186\/1757-7241-16-7","article-title":"The Utstein template for uniform reporting of data following major trauma: a joint revision by SCANTEM, TARN, DGU-TR and RITG","volume":"16","author":"Ringdal","year":"2008","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2025121410593912000_15.6.e099624.15","doi-asserted-by":"publisher","DOI":"10.1097\/TA.0b013e31815078ae"},{"key":"2025121410593912000_15.6.e099624.16","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":"2025121410593912000_15.6.e099624.17","doi-asserted-by":"publisher","DOI":"10.1177\/962280218784726"},{"key":"2025121410593912000_15.6.e099624.18","doi-asserted-by":"crossref","DOI":"10.1186\/s13049-023-01157-y","article-title":"Patient and process factors associated with opportunities for improvement in trauma care: a registry-based study","volume":"31","author":"Albaaj","year":"2023","journal-title":"Scand J Trauma Resusc Emerg Med"},{"key":"2025121410593912000_15.6.e099624.19","unstructured":"R Core Team . R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing, 2020. Available: https:\/\/www.R-project.org\/"},{"key":"2025121410593912000_15.6.e099624.20","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. in: proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 2016:785\u201394. doi:10.1145\/2939672.2939785 Available: https:\/\/dl.acm.org\/doi\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2025121410593912000_15.6.e099624.21","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/87.4.954"},{"key":"2025121410593912000_15.6.e099624.22","doi-asserted-by":"crossref","unstructured":"Haibo H , Yang B , Garcia EA , et al . 2008 ieee international joint conference on neural networks (ijcnn 2008 - hong kong); hong kong, china, december 17, 2008:1322\u20138. 10.1109\/ijcnn.2008.4633969. n.d. Available: http:\/\/ieeexplore.ieee.org\/document\/4633969\/","DOI":"10.1109\/IJCNN.2008.4633969"},{"key":"2025121410593912000_15.6.e099624.23","unstructured":"Kuhn M , Wickham H . Tidymodels: A collection of packages for modeling and machine learning using tidyverse principles, 2020. Available: https:\/\/www.tidymodels.org"},{"key":"2025121410593912000_15.6.e099624.24","doi-asserted-by":"crossref","first-page":"4051","DOI":"10.1002\/sim.8281","article-title":"The Integrated Calibration Index (ICI) and related metrics for quantifying the calibration of logistic regression models","volume":"38","author":"Austin","year":"2019","journal-title":"Stat Med"},{"key":"2025121410593912000_15.6.e099624.25","article-title":"All models are wrong, but many are useful: learning a variable\u2019s importance by studying an entire class of prediction models simultaneously","volume":"20","author":"Fisher","year":"2019","journal-title":"J Mach Learn Res"},{"key":"2025121410593912000_15.6.e099624.26","unstructured":"Zhang T , Nikouline A , Lightfoot D , et al . Machine learning in the prediction of trauma outcomes: A systematic review, 10.1016\/j.annemergmed.2022.05.011 Available: https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0196064422003353"},{"key":"2025121410593912000_15.6.e099624.27","first-page":"970","article-title":"Analysis of preventable trauma deaths and opportunities for trauma care improvement in Utah","volume":"70","author":"Sanddal","year":"2011","journal-title":"J Trauma"},{"key":"2025121410593912000_15.6.e099624.28","doi-asserted-by":"crossref","DOI":"10.1186\/s12913-017-2085-7","article-title":"Learning from 2523 trauma deaths in India- opportunities to prevent in-hospital deaths","volume":"17","author":"Roy","year":"2017","journal-title":"BMC Health Serv Res"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2025-099624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T18:59:52Z","timestamp":1765738792000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2025-099624"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":28,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,6]]},"published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1136\/bmjopen-2025-099624"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2025-099624","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}