Graduate Athletic Training Program, University of Tennessee at Chattanooga, Chattanooga, TN, USA.
Department of Systems & Technology, Raymond J. Harbert College of Business, Auburn University, Auburn, AL, USA.
Risk Anal. 2018 Jul;38(7):1348-1360. doi: 10.1111/risa.12984. Epub 2018 Mar 12.
Sport injuries restrict participation, impose a substantial economic burden, and can have persisting adverse effects on health-related quality of life. The effective use of Internet of Things (IoT), when combined with analytics approaches, can improve player safety through identification of injury risk factors that can be addressed by targeted risk reduction training activities. Use of IoT devices can facilitate highly efficient quantification of relevant functional capabilities prior to sport participation, which could substantially advance the prevailing sport injury management paradigm. This study introduces a framework for using sensor-derived IoT data to supplement other data for objective estimation of each individual college football player's level of injury risk, which is an approach to injury prevention that has not been previously reported. A cohort of 45 NCAA Division I-FCS college players provided data in the form of self-ratings of persisting effects of previous injuries and single-leg postural stability test. Instantaneous change in body mass acceleration (jerk) during the test was quantified by a smartphone accelerometer, with data wirelessly transmitted to a secure cloud server. Injuries sustained from the beginning of practice sessions until the end of the 13-game season were documented, along with the number of games played by each athlete over the course of a 13-game season. Results demonstrate a strong prediction model. Our approach may have strong relevance to the estimation of injury risk for other physically demanding activities. Clearly, there is great potential for improvement of injury prevention initiatives through identification of individual athletes who possess elevated injury risk and targeted interventions.
运动损伤限制了参与度，造成了巨大的经济负担，并对与健康相关的生活质量产生持续的不良影响。物联网（IoT）的有效利用，结合分析方法，可以通过识别可以通过有针对性的降低风险培训活动解决的损伤风险因素来提高运动员的安全性。IoT 设备的使用可以在运动参与之前方便地高效量化相关功能能力，这将大大推进当前的运动损伤管理模式。本研究提出了一个使用传感器衍生的 IoT 数据来补充其他数据以客观估计每个大学生足球运动员损伤风险水平的框架，这是一种以前未报道过的损伤预防方法。一个由 45 名 NCAA 一级 FCS 大学生组成的队列以自我报告以前受伤的持续影响和单腿姿势稳定性测试的形式提供数据。智能手机加速度计量化了测试过程中身体质量加速度（急动度）的瞬时变化，数据通过无线传输到安全的云服务器。记录了从练习开始到 13 场比赛结束期间发生的伤害，以及每个运动员在 13 场比赛中的比赛场次。结果表明预测模型具有很强的预测能力。我们的方法可能与其他体力要求高的活动的损伤风险估计具有很强的相关性。显然，通过识别具有较高损伤风险的个别运动员并进行针对性干预，可以大大提高损伤预防计划的效果。
