School of Exercise and Nutrition Sciences, Queensland University of Technology, Kelvin Grove, Australia.
Institute of Health and Biomedical Innovation, Queensland University of Technology, Kelvin Grove, Australia.
J Sports Sci. 2021 Jun;39(12):1339-1347. doi: 10.1080/02640414.2020.1870303. Epub 2021 Jan 6.
This study aimed to identify the predictive capacity of wellness questionnaires on measures of training load using machine learning methods. The distributions of, and dose-response between, wellness and other load measures were also examined, offering insights into response patterns. Data (= 14,109) were collated from an athlete management systems platform (Catapult Sports, Melbourne, Australia) and were split across three sports (cricket, rugby league and football) with data analysis conducted in R (Version 3.4.3). Wellness (sleep quality, readiness to train, general muscular soreness, fatigue, stress, mood, recovery rating and motivation) as the dependent variable, and sRPE, sRPE-TL and markers of external load (total distance and m.min) as independent variables were included for analysis. Classification and regression tree models showed high cross-validated error rates across all sports (i.e., > 0.89) and low model accuracy (i.e., < 5% of variance explained by each model) with similar results demonstrated using random forest models. These results suggest wellness items have limited predictive capacity in relation to internal and external load measures. This result was consistent despite varying statistical approaches (regression, classification and random forest models) and transformation of wellness scores. These findings indicate practitioners should exercise caution when interpreting and applying wellness responses.
本研究旨在利用机器学习方法确定健康问卷对训练负荷测量的预测能力。还检查了健康和其他负荷测量之间的分布和剂量反应关系，为反应模式提供了深入了解。数据（= 14109）是从运动员管理系统平台（澳大利亚墨尔本的 Catapult Sports）收集的，并分为三个运动项目（板球、橄榄球联盟和足球），数据分析是在 R（版本 3.4.3）中进行的。将健康（睡眠质量、训练准备情况、一般性肌肉酸痛、疲劳、压力、情绪、恢复评分和动机）作为因变量，sRPE、sRPE-TL 和外部负荷指标（总距离和 m.min）作为自变量进行分析。分类和回归树模型显示，所有运动项目的交叉验证错误率都很高（即>0.89），模型准确性较低（即每个模型解释的方差<5%），随机森林模型也得出了类似的结果。这些结果表明，健康指标与内部和外部负荷测量相比，预测能力有限。尽管使用了不同的统计方法（回归、分类和随机森林模型）以及健康评分的转换，但结果仍然一致。这些发现表明，从业者在解释和应用健康反应时应谨慎。
