{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T15:00:11Z","timestamp":1788188411169,"version":"build-2803163510"},"reference-count":23,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"unspecified","delay-in-days":82,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Sport Exerc Med"],"accepted":{"date-parts":[[2025,1,6]]},"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Sportspeople suffering from mild traumatic brain injury (mTBI) who return prematurely to sport are at an increased risk of delayed recovery, repeat concussion events and, in the longer-term, the development of chronic traumatic encephalopathy. Therefore, determining the appropriate recovery time, without unnecessarily delaying return to sport, is paramount at a professional\/semi-professional level, yet notoriously difficult to predict.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To use machine learning to develop a multivariate model for the prediction of concussion recovery in sportspeople.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Demographics, injury history, Sport Concussion Assessment Tool fifth edition questionnaire and MRI head reports were collected for sportspeople who suffered mTBI and were referred to a tertiary university hospital in the West Midlands over 3 years. Random forest (RF) machine learning algorithms were trained and tuned on a 90% outcome-balanced corpus subset, with subsequent validation testing on the previously unseen 10% subset for binary prediction of greater than five missed sporting games. Confusion matrices and receiver operator curves were used to determine model discrimination.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>375 sportspeople were included. A final composite model accuracy of 94.6% based on the unseen testing subset was obtained, yielding a sensitivity of 100% and specificity of 93.8% with a positive predictive value of 71.4% and a negative predictive value of 100%. The area under the curve was 96.3%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>In this large single-centre cohort study, a composite RF machine learning algorithm demonstrated high performance in predicting sporting games missed post-mTBI injury. Validation of this novel model on larger external datasets is therefore warranted.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration number<\/jats:title>\n                    <jats:p>\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"isrctn\" xlink:href=\"ISRCTN16974791\">ISRCTN16974791<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjsem-2024-002090","type":"journal-article","created":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T02:14:30Z","timestamp":1742868870000},"page":"e002090","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":9,"title":["Developing a multivariate model for the prediction of concussion recovery in sportspeople: a machine learning approach"],"prefix":"10.1136","volume":"11","clinical-trial-number":[{"clinical-trial-number":"isrctn16974791","registry":"10.18810\/isrctn"}],"author":[{"given":"Louise C","family":"Yates","sequence":"first","affiliation":[{"name":"Department of Radiology, Worcester Acute Hospitals NHS Trust, Worcester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elliot","family":"Yates","sequence":"additional","affiliation":[{"name":"Department of Anaesthesia, Worcestershire Acute Hospitals NHS Trust, Worcester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiology, Huashan Hospital Fudan University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiping","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Huashan Hospital Fudan University, Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamal","family":"Yakoub","sequence":"additional","affiliation":[{"name":"Institute of Inflammation and Ageing, College of Medicine and Health, University of Birmingham, Birmingham, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Davies","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, University Hospitals Birmingham, Birmingham, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Belli","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK"},{"name":"Institute of Inflammation and Ageing, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6779-1255","authenticated-orcid":false,"given":"Vijay","family":"Sawlani","sequence":"additional","affiliation":[{"name":"Imaging, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"2025121106001624000_11.1.e002090.1","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2012-091941"},{"key":"2025121106001624000_11.1.e002090.2","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1001\/jama.2018.0436","article-title":"Sport-Related Concussion","volume":"319","author":"Muth","year":"2018","journal-title":"JAMA"},{"key":"2025121106001624000_11.1.e002090.3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.290.19.2549"},{"key":"2025121106001624000_11.1.e002090.4","doi-asserted-by":"publisher","DOI":"10.1177\/0363546515610537"},{"key":"2025121106001624000_11.1.e002090.5","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1146\/annurev-clinpsy-032814-112814","article-title":"Chronic traumatic encephalopathy: historical origins and current perspective","volume":"11","author":"Montenigro","year":"2015","journal-title":"Annu Rev Clin Psychol"},{"key":"2025121106001624000_11.1.e002090.6","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2017-097729"},{"key":"2025121106001624000_11.1.e002090.7","doi-asserted-by":"publisher","DOI":"10.1097\/00042752-200411000-00003"},{"key":"2025121106001624000_11.1.e002090.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.apmr.2013.06.035"},{"key":"2025121106001624000_11.1.e002090.9","doi-asserted-by":"publisher","DOI":"10.1136\/bjsports-2017-097506"},{"key":"2025121106001624000_11.1.e002090.10","doi-asserted-by":"crossref","DOI":"10.3390\/brainsci10090593","article-title":"Concussion Office Based Rehabilitation Assessment: A Novel Clinical Tool for Concussion Assessment and Management","volume":"10","author":"Katz","year":"2020","journal-title":"Brain Sci"},{"key":"2025121106001624000_11.1.e002090.11","doi-asserted-by":"crossref","first-page":"153","DOI":"10.2217\/iim.11.11","article-title":"Imaging of traumatic brain injury: current and future","volume":"3","author":"Anzai","year":"2011","journal-title":"Imaging Med"},{"key":"2025121106001624000_11.1.e002090.12","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.nicl.2014.07.010","article-title":"Multi-modal MRI of mild traumatic brain injury","volume":"7","author":"Narayana","year":"2015","journal-title":"Neuroimage Clin"},{"key":"2025121106001624000_11.1.e002090.13","doi-asserted-by":"crossref","DOI":"10.2217\/cnc-2016-0028","article-title":"White matter changes in patients with mild traumatic brain injury: MRI perspective","volume":"2","author":"Narayana","year":"2017","journal-title":"Concussion"},{"key":"2025121106001624000_11.1.e002090.14","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1814259"},{"key":"2025121106001624000_11.1.e002090.15","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2019-029883","article-title":"Investigation into repetitive concussion in sport (RECOS): study protocol of a prospective, exploratory, observational cohort study","volume":"9","author":"Yakoub","year":"2019","journal-title":"BMJ Open"},{"key":"2025121106001624000_11.1.e002090.16","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"2025121106001624000_11.1.e002090.17","unstructured":"R Core Team . R: a language and environment for statistical computing. R Foundation for Statistical Computing: Vienna, Austria; 2020. Available: https:\/\/www.R-project.org\/"},{"key":"2025121106001624000_11.1.e002090.18","unstructured":"Kuhn M . Caret: classification and regression training [R Package Version 6.0-86]. 2020. Available: https:\/\/cran.r-project.org\/web\/packages\/caret\/index.html"},{"key":"2025121106001624000_11.1.e002090.19","doi-asserted-by":"publisher","DOI":"10.1159\/000323281"},{"key":"2025121106001624000_11.1.e002090.20","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":"2025121106001624000_11.1.e002090.21","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":"2025121106001624000_11.1.e002090.22","doi-asserted-by":"publisher","DOI":"10.3171\/jns.2003.98.3.0477"},{"key":"2025121106001624000_11.1.e002090.23","doi-asserted-by":"publisher","DOI":"10.1111\/bpa.12249"}],"container-title":["BMJ Open Sport &amp; Exercise Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjsem-2024-002090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T14:00:24Z","timestamp":1765461624000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopensem.bmj.com\/lookup\/doi\/10.1136\/bmjsem-2024-002090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,3,24]]},"published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1136\/bmjsem-2024-002090"],"URL":"https:\/\/doi.org\/10.1136\/bmjsem-2024-002090","relation":{},"ISSN":["2055-7647"],"issn-type":[{"value":"2055-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}