Faculty of Electrical Engineering, Automatic Control and Informatics, Opole University of Technology, Opole, Poland.
Faculty of Physical Education and Physiotherapy, Opole University of Technology, Opole, Poland.
PLoS One. 2024 Aug 29;19(8):e0309427. doi: 10.1371/journal.pone.0309427. eCollection 2024.
Lactate analysis plays an important role in sports science and training decisions for optimising performance, endurance, and overall success in sports. Two parameters are widely used for these goals: aerobic (AeT) and anaerobic (AnT) thresholds. However, determining AeT proves more challenging than AnT threshold due to both physiological intricacies and practical considerations. Thus, the aim of this study was to determine AeT and AnT thresholds using machine learning modelling (ML) and to compare ML-obtained results with the parameters' values determined using conventional methods. ML seems to be highly useful due to its ability to handle complex, personalised data, identify nonlinear relationships, and provide accurate predictions. The 183 results of CardioPulmonary Exercise Test (CPET) accompanied by lactate and heart ratio analyses from amateur athletes were enrolled to the study and ML models using the following algorithms: Random Forest, XGBoost (Extreme Gradient Boosting), and LightGBM (Light Gradient Boosting Machine) and metrics: R2, mean absolute error (MAE), mean squared error (MSE) and root mean square error (RMSE). The regressors used belong to the group of ensemble learning algorithms that combine the predictions of multiple base models to improve overall performance and counteract overfitting to training data. Based on evaluation metrics, the following models give the best predictions: for AeT: Random Forest has an R2 value of 0.645, MAE of 4.630, MSE of 44.450, RMSE of 6.667; and for AnT: LightGBM has an R2 of 0.803, the highest among the models, MAE of 3.439, the lowest among the models, MSE of 20.953, and RMSE of 4.577. Outlined research experiments, a comprehensive review of existing literature in the field, and obtained results suggest that ML models can be trained to make personalised predictions based on an individual athlete's unique physiological response to exercise. Athletes exhibit significant variation in their AeT and AT, and ML can capture these individual differences, allowing for tailored training recommendations and performance optimization.
乳酸分析在运动科学和训练决策中发挥着重要作用，可优化运动表现、耐力和整体成功。有两个参数广泛用于这些目标：有氧（AeT）和无氧（AnT）阈值。然而，由于生理复杂性和实际考虑因素，确定 AeT 比确定 AnT 阈值更具挑战性。因此，本研究的目的是使用机器学习模型（ML）确定 AeT 和 AnT 阈值，并将 ML 获得的结果与使用传统方法确定的参数值进行比较。由于其处理复杂、个性化数据、识别非线性关系和提供准确预测的能力，ML 似乎非常有用。该研究纳入了 183 名业余运动员的心肺运动测试（CPET）结果，以及乳酸和心率比分析结果，并使用以下算法的 ML 模型：随机森林、极端梯度提升（XGBoost）和轻梯度提升机（LightGBM）以及指标：R2、平均绝对误差（MAE）、均方误差（MSE）和均方根误差（RMSE）。所使用的回归器属于集成学习算法组，这些算法组合了多个基础模型的预测结果，以提高整体性能并抵消对训练数据的过拟合。基于评估指标，以下模型给出了最佳预测：对于 AeT：随机森林的 R2 值为 0.645，MAE 为 4.630，MSE 为 44.450，RMSE 为 6.667；对于 AnT：LightGBM 的 R2 为 0.803，是模型中最高的，MAE 为 3.439，是模型中最低的，MSE 为 20.953，RMSE 为 4.577。研究实验、该领域现有文献的综合回顾以及获得的结果表明，可以训练 ML 模型根据个体运动员对运动的独特生理反应进行个性化预测。运动员的 AeT 和 AT 存在显著差异，ML 可以捕捉这些个体差异，从而提供定制化的训练建议和性能优化。
