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

IF 9.3 1区 医学 Q1 SPORT SCIENCES Sports Medicine Pub Date : 2024-09-17 DOI:10.1007/s40279-024-02112-2
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}
引用次数: 0

摘要

背景识别脑震荡风险因素(如可见体征和损伤机制)可提高脑震荡识别率。本研究的主要目的是利用机器学习技术开发一种全面的、前瞻性编码的脑震荡风险模型,该模型适用于表现出明显体征的职业冰球运动员。方法从 2018-2019 至 2021-2022 赛季的美国国家曲棍球联盟(NHL)观测员计划中提取数据,包括与可能的脑震荡事件相关的编码可见体征和损伤机制。每个独特的观察者事件都与从医疗记录中提取的数据进行了匹配,以确定该事件是否与随后医生诊断的脑震荡有关。我们比较了三种基于机器学习的方法识别医生诊断为脑震荡的可能性的能力:条件推理树、条件推理随机森林和逻辑回归。随机选取的训练样本有 1250 个事件(146 例脑震荡),其余的预留测试样本有 313 个事件(37 例脑震荡)。所获得的模型在训练数据(接收者操作特征曲线下面积(AUC)= 0.79)和预留测试数据(AUC = 0.82)中具有较高的效果。在树型和逻辑回归模型中保留了脑震荡病史,每增加一次脑震荡病史,脑震荡诊断几率就会增加 1.32 倍。我们的研究结果表明,球员的脑震荡病史可以在可见体征和受伤机制所能解释的风险之外解释更多的风险。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
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.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Sports Medicine
Sports Medicine 医学-运动科学
CiteScore
18.40
自引率
5.10%
发文量
165
审稿时长
6-12 weeks
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.
期刊最新文献
DyNamic Interactive Anticipation-Time for a Paradigmatic Shift. Professional Male Soccer Players' Perspectives of the Nutrition Culture Within an English Premier League Football Club: A Qualitative Exploration Using Bourdieu's Concepts of Habitus, Capital and Field. Low Energy Availability and Relative Energy Deficiency in Sport: A Systematic Review and Meta-analysis A Novel Method to Predict Carbohydrate and Energy Expenditure During Endurance Exercise Using Measures of Training Load Relationship between Cognitive Demands and Biomechanical Indicators Associated with Anterior Cruciate Ligament Injury: A Systematic Review
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1