Jared M. Bruce, Kaitlin E. Riegler, Willem Meeuwisse, Paul Comper, Michael G. Hutchison, J. Scott Delaney, Ruben J. Echemendia
{"title":"用机器学习方法估算职业冰球运动员出现明显体征的脑震荡风险","authors":"Jared M. Bruce, Kaitlin E. Riegler, Willem Meeuwisse, Paul Comper, Michael G. Hutchison, J. Scott Delaney, Ruben J. Echemendia","doi":"10.1007/s40279-024-02112-2","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Background</h3><p>The identification of concussion risk factors, such as visible signs and mechanisms of injury, improves concussion identification. Exploring individual risk factors, such as concussion history, may help to improve existing concussion risk models and algorithms.</p><h3 data-test=\"abstract-sub-heading\">Objectives</h3><p>The primary aim of the current study was to use machine learning techniques to develop a comprehensive, prospectively coded concussion risk model in professional hockey among players exhibiting visible signs. The secondary aim was to examine whether including concussion history improves model performance.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Data from the National Hockey League (NHL) spotter program, including coded visible signs and mechanisms of injury associated with possible concussive events, were extracted from the 2018–2019 to the 2021–2022 seasons. Each unique spotter event was matched with data extracted from the medical record to determine whether the event was associated with a subsequent physician diagnosed concussion. We compared the ability of three machine learning-based approaches to identify the likelihood of physician diagnosed concussion: conditional inference tree, conditional inference random forest, and logistic regression.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>A total of 1563 unique events with visible signs were identified by spotters (183 leading to a concussion diagnosis). A randomly selected training sample had 1250 events (146 concussions) and the remaining set-aside test sample had 313 events (37 concussions). The obtained models performed at a high level with large effects in the training [area under the receiver operating characteristic curve (AUC) = 0.79] and set-aside test data (AUC = 0.82). Concussion history was retained in the tree and logistic regression models, with each additional prior concussion associated with a 1.32 times increased odds of concussion diagnosis.</p><h3 data-test=\"abstract-sub-heading\">Conclusions</h3><p>We present simple tree and logistic algorithms for concussion screening and as diagnostic aids. Our results show that player concussion history can explain additional risk above and beyond that explained by visible signs and mechanisms of injury alone.</p>","PeriodicalId":21969,"journal":{"name":"Sports Medicine","volume":null,"pages":null},"PeriodicalIF":9.3000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Machine Learning Approach to Concussion Risk Estimation Among Players Exhibiting Visible Signs in Professional Hockey\",\"authors\":\"Jared M. Bruce, Kaitlin E. Riegler, Willem Meeuwisse, Paul Comper, Michael G. Hutchison, J. Scott Delaney, Ruben J. Echemendia\",\"doi\":\"10.1007/s40279-024-02112-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<h3 data-test=\\\"abstract-sub-heading\\\">Background</h3><p>The identification of concussion risk factors, such as visible signs and mechanisms of injury, improves concussion identification. Exploring individual risk factors, such as concussion history, may help to improve existing concussion risk models and algorithms.</p><h3 data-test=\\\"abstract-sub-heading\\\">Objectives</h3><p>The primary aim of the current study was to use machine learning techniques to develop a comprehensive, prospectively coded concussion risk model in professional hockey among players exhibiting visible signs. The secondary aim was to examine whether including concussion history improves model performance.</p><h3 data-test=\\\"abstract-sub-heading\\\">Methods</h3><p>Data from the National Hockey League (NHL) spotter program, including coded visible signs and mechanisms of injury associated with possible concussive events, were extracted from the 2018–2019 to the 2021–2022 seasons. Each unique spotter event was matched with data extracted from the medical record to determine whether the event was associated with a subsequent physician diagnosed concussion. We compared the ability of three machine learning-based approaches to identify the likelihood of physician diagnosed concussion: conditional inference tree, conditional inference random forest, and logistic regression.</p><h3 data-test=\\\"abstract-sub-heading\\\">Results</h3><p>A total of 1563 unique events with visible signs were identified by spotters (183 leading to a concussion diagnosis). A randomly selected training sample had 1250 events (146 concussions) and the remaining set-aside test sample had 313 events (37 concussions). The obtained models performed at a high level with large effects in the training [area under the receiver operating characteristic curve (AUC) = 0.79] and set-aside test data (AUC = 0.82). Concussion history was retained in the tree and logistic regression models, with each additional prior concussion associated with a 1.32 times increased odds of concussion diagnosis.</p><h3 data-test=\\\"abstract-sub-heading\\\">Conclusions</h3><p>We present simple tree and logistic algorithms for concussion screening and as diagnostic aids. Our results show that player concussion history can explain additional risk above and beyond that explained by visible signs and mechanisms of injury alone.</p>\",\"PeriodicalId\":21969,\"journal\":{\"name\":\"Sports Medicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":9.3000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Sports Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s40279-024-02112-2\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"SPORT SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sports Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s40279-024-02112-2","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SPORT SCIENCES","Score":null,"Total":0}
A Machine Learning Approach to Concussion Risk Estimation Among Players Exhibiting Visible Signs in Professional Hockey
Background
The identification of concussion risk factors, such as visible signs and mechanisms of injury, improves concussion identification. Exploring individual risk factors, such as concussion history, may help to improve existing concussion risk models and algorithms.
Objectives
The primary aim of the current study was to use machine learning techniques to develop a comprehensive, prospectively coded concussion risk model in professional hockey among players exhibiting visible signs. The secondary aim was to examine whether including concussion history improves model performance.
Methods
Data from the National Hockey League (NHL) spotter program, including coded visible signs and mechanisms of injury associated with possible concussive events, were extracted from the 2018–2019 to the 2021–2022 seasons. Each unique spotter event was matched with data extracted from the medical record to determine whether the event was associated with a subsequent physician diagnosed concussion. We compared the ability of three machine learning-based approaches to identify the likelihood of physician diagnosed concussion: conditional inference tree, conditional inference random forest, and logistic regression.
Results
A total of 1563 unique events with visible signs were identified by spotters (183 leading to a concussion diagnosis). A randomly selected training sample had 1250 events (146 concussions) and the remaining set-aside test sample had 313 events (37 concussions). The obtained models performed at a high level with large effects in the training [area under the receiver operating characteristic curve (AUC) = 0.79] and set-aside test data (AUC = 0.82). Concussion history was retained in the tree and logistic regression models, with each additional prior concussion associated with a 1.32 times increased odds of concussion diagnosis.
Conclusions
We present simple tree and logistic algorithms for concussion screening and as diagnostic aids. Our results show that player concussion history can explain additional risk above and beyond that explained by visible signs and mechanisms of injury alone.
期刊介绍:
Sports Medicine focuses on providing definitive and comprehensive review articles that interpret and evaluate current literature, aiming to offer insights into research findings in the sports medicine and exercise field. The journal covers major topics such as sports medicine and sports science, medical syndromes associated with sport and exercise, clinical medicine's role in injury prevention and treatment, exercise for rehabilitation and health, and the application of physiological and biomechanical principles to specific sports.
Types of Articles:
Review Articles: Definitive and comprehensive reviews that interpret and evaluate current literature to provide rationale for and application of research findings.
Leading/Current Opinion Articles: Overviews of contentious or emerging issues in the field.
Original Research Articles: High-quality research articles.
Enhanced Features: Additional features like slide sets, videos, and animations aimed at increasing the visibility, readership, and educational value of the journal's content.
Plain Language Summaries: Summaries accompanying articles to assist readers in understanding important medical advances.
Peer Review Process:
All manuscripts undergo peer review by international experts to ensure quality and rigor. The journal also welcomes Letters to the Editor, which will be considered for publication.