Yung Kate K Y, Wu Paul P Y, Aus der Fünten Karen, Hecksteden Anne, Meyer Tim
Department of Orthopaedics and Traumatology, Faculty of Medicine, The Chinese University of Hong Kong, Shatin, Hong Kong.
School of Mathematical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia.
PLoS One. 2025 Mar 20;20(3):e0314184. doi: 10.1371/journal.pone.0314184. eCollection 2025.
The return-to-sport (RTS) process is multifaceted and complex, as multiple variables may interact and influence the time to RTS. These variables include intrinsic factors related the player, such as anthropometrics and playing position, or extrinsic factors, such as competitive pressure. Providing an individualised estimation of time to return to play is often challenging, and clinical decision support tools are not common in sports medicine. This study uses epidemiological data to demonstrate a Bayesian Network (BN). We applied a BN that integrated clinical, non-clinical factors, and expert knowledge to classify time day to RTS and injury severity (minimal, mild, moderate and severe) for individual players. Retrospective injury data of 3374 player seasons and 6143 time-loss injuries from seven seasons of the professional German football league (Bundesliga, 2014/2015 through 2020/2021) were collected from public databases and media resources. A total of twelve variables from three categories (player's characteristics and anthropometrics, match information and injury information) were included. The response variables were 1) days to RTS (1-3, 4-7, 8-14, 15-28, 29-60, > 60, and 2) injury severity (minimal, mild, moderate, and severe). The sensitivity of the model for days to RTS was 0.24-0.97, while for severity categories it was 0.73-1.00. The user's accuracy of the model for days to RTS was 0.52-0.83, while for severity categories, it was 0.67-1.00. The BN can help to integrate different data types to model the probability of an outcome, such as days to return to sport. In our study, the BN may support coaches and players in 1) predicting days to RTS given an injury, 2) team planning via assessment of scenarios based on players' characteristics and injury risk, and 3) understanding the relationships between injury risk factors and RTS. This study demonstrates the how a Bayesian network may aid clinical decision making for RTS.
恢复运动（RTS）过程是多方面且复杂的，因为多个变量可能相互作用并影响恢复运动的时间。这些变量包括与运动员相关的内在因素，如人体测量学和比赛位置，或外在因素，如竞争压力。提供恢复运动时间的个性化估计往往具有挑战性，并且临床决策支持工具在运动医学中并不常见。本研究使用流行病学数据来展示一个贝叶斯网络（BN）。我们应用了一个整合了临床、非临床因素和专家知识的贝叶斯网络，以对个体运动员的恢复运动天数和损伤严重程度（轻微、轻度、中度和重度）进行分类。从公共数据库和媒体资源中收集了来自德国职业足球联赛七个赛季（2014/2015至2020/2021）的3374个运动员赛季的回顾性损伤数据和6143次导致运动员缺阵的损伤数据。总共纳入了来自三个类别（运动员特征和人体测量学、比赛信息和损伤信息）的十二个变量。响应变量为：1）恢复运动天数（1 - 3天、4 - 7天、8 - 14天、15 - 28天、29 - 60天、> 60天），以及2）损伤严重程度（轻微、轻度、中度和重度）。该模型对恢复运动天数的敏感性为0.24 - 0.97，而对严重程度类别的敏感性为0.73 - 1.00。该模型对恢复运动天数的用户准确率为0.52 - 0.83，而对严重程度类别的用户准确率为0.67 - 1.00。贝叶斯网络有助于整合不同的数据类型，以对诸如恢复运动天数等结果的概率进行建模。在我们的研究中，贝叶斯网络可以在以下方面帮助教练和运动员：1）在运动员受伤的情况下预测恢复运动的天数，2）通过基于运动员特征和损伤风险评估不同情况来进行团队规划，以及3）理解损伤风险因素与恢复运动之间的关系。本研究展示了贝叶斯网络如何有助于恢复运动的临床决策。
