Youth Physical Development Centre, Cardiff School of Sport and Health Sciences, Cardiff Metropolitan University, UK; Sport Performance Research Institute New Zealand (SPRINZ), Auckland University of Technology, New Zealand.
Sports Research Centre, Miguel Hernadez University of Elche, Spain.
J Sci Med Sport. 2020 Nov;23(11):1044-1048. doi: 10.1016/j.jsams.2020.04.021. Epub 2020 May 18.
The purpose of this study was to examine whether the use of machine learning improved the ability of a neuromuscular screen to identify injury risk factors in elite male youth football players.
Prospective cohort study.
355 elite youth football players aged 10-18 years old completed a prospective pre-season neuromuscular screen that included anthropometric measures of size, as well as single leg countermovement jump (SLCMJ), single leg hop for distance (SLHD), 75% hop distance and stick (75%Hop), Y-balance anterior reach and tuck jump assessment. Injury incidence was monitored over one competitive season. Risk profiling was assessed using traditional regression analyses and compared to supervised machine learning algorithms constructed using decision trees.
Using continuous data, multivariate logistic analysis identified SLCMJ asymmetry as the sole significant predictor of injury (OR 0.94, 0.92-0.97, p<0.001), with a specificity of 97.7% and sensitivity of 15.2% giving an AUC of 0.661. The best performing decision tree model provided a specificity of 74.2% and sensitivity of 55.6% with an AUC of 0.663. All variables contributed to the final machine model, with asymmetry in the SLCMJ, 75%Hop and Y-balance, plus tuck jump knee valgus and anthropometrics being the most frequent contributors.
Although both statistical methods reported similar accuracy, logistic regression provided very low sensitivity and only identified a single neuromuscular injury risk factor. The machine learning model provided much improved sensitivity to predict injury and identified interactions of asymmetry, knee valgus angle and body size as contributing factors to an injurious profile in youth football players.
本研究旨在探讨机器学习的应用是否能提高神经肌肉筛查识别优秀男性青年足球运动员损伤风险因素的能力。
前瞻性队列研究。
355 名 10-18 岁的精英青年足球运动员完成了一项前瞻性的赛季前神经肌肉筛查，包括大小的人体测量学指标，以及单腿反向跳（SLCMJ）、单腿跳远（SLHD）、75%跳距和棒（75%Hop）、Y 平衡前伸和纵跳评估。在一个竞争赛季中监测损伤发生率。使用传统回归分析进行风险分析，并与使用决策树构建的监督机器学习算法进行比较。
使用连续数据，多变量逻辑分析确定 SLCMJ 不对称性是唯一显著的损伤预测因素（OR 0.94，0.92-0.97，p<0.001），特异性为 97.7%，敏感性为 15.2%，AUC 为 0.661。性能最佳的决策树模型提供了特异性为 74.2%和敏感性为 55.6%，AUC 为 0.663。所有变量都为最终的机器模型做出了贡献，其中 SLCMJ、75%Hop 和 Y 平衡的不对称性，加上纵跳膝盖外翻和人体测量学指标是最常见的贡献因素。
尽管两种统计方法报告的准确性相似，但逻辑回归提供的敏感性非常低，仅确定了一个单一的神经肌肉损伤风险因素。机器学习模型对预测损伤的敏感性有了很大提高，并确定了不对称性、膝盖外翻角和体型的相互作用是青年足球运动员受伤特征的影响因素。
