Sports Performance Research Institute New Zealand (SPRINZ), Auckland University of Technology, Auckland, New Zealand.
High Performance Sport New Zealand, Auckland, New Zealand.
Eur J Appl Physiol. 2024 Nov;124(11):3279-3290. doi: 10.1007/s00421-024-05530-2. Epub 2024 Jun 20.
The aim of this study was to determine if machine learning models could predict the perceived morning recovery status (AM PRS) and daily change in heart rate variability (HRV change) of endurance athletes based on training, dietary intake, sleep, HRV, and subjective well-being measures.
Self-selected nutrition intake, exercise training, sleep habits, HRV, and subjective well-being of 43 endurance athletes ranging from professional to recreationally trained were monitored daily for 12 weeks (3572 days of tracking). Global and individualized models were constructed using machine learning techniques, with the single best algorithm chosen for each model. The model performance was compared with a baseline intercept-only model.
Prediction error (root mean square error [RMSE]) was lower than baseline for the group models (11.8 vs. 14.1 and 0.22 vs. 0.29 for AM PRS and HRV change, respectively). At the individual level, prediction accuracy outperformed the baseline model but varied greatly across participants (RMSE range 5.5-23.6 and 0.05-0.44 for AM PRS and HRV change, respectively).
At the group level, daily recovery measures can be predicted based on commonly measured variables, with a small subset of variables providing most of the predictive power. However, at the individual level, the key variables may vary, and additional data may be needed to improve the prediction accuracy.
本研究旨在确定机器学习模型是否可以根据训练、饮食摄入、睡眠、心率变异性（HRV）和主观幸福感测量来预测耐力运动员的感知晨恢复状态（AM PRS）和每日 HRV 变化。
对 43 名从职业到业余训练的耐力运动员的自我选择的营养摄入、运动训练、睡眠习惯、HRV 和主观幸福感进行了为期 12 周（3572 天的跟踪）的日常监测。使用机器学习技术构建了全局和个体化模型，为每个模型选择了最佳算法。将模型性能与仅基线截距模型进行了比较。
与基线相比，组模型的预测误差（均方根误差 [RMSE]）较低（分别为 11.8 和 0.22 与 14.1 和 0.29 用于 AM PRS 和 HRV 变化）。在个体水平上，预测精度优于基线模型，但参与者之间差异很大（RMSE 范围分别为 5.5-23.6 和 0.05-0.44，用于 AM PRS 和 HRV 变化）。
在组水平上，可以根据常用变量预测每日恢复情况，其中一小部分变量提供了大部分预测能力。然而，在个体水平上，关键变量可能会有所不同，可能需要更多的数据来提高预测精度。
