Elite Soccer Players' Weekly Workload Assessment Through a New Training Load and Performance Score.

Abstract

Purpose: Monitoring players' training load allows practitioners to enhance physical performance while reducing injury risk. The aim of this study was to identify the key external load indicators in professional U19 soccer. Methods: Twenty-four-professional Italian young (U19) soccer players were monitored by using the rating of perceived exertion (CR-10 RPE scale) and a wearable inertial sensor during the competitive season. Three main components were detected by a Principal Component Analysis (PCA): i) volume metabolic related component, ii) intensity mechanical stimuli component, and iii) intensity metabolic/mechanical component. We hence computed two scores (i.e. Performance [PERF] and total workload [WORK]) permitting to investigate the weekly microcycle. Results: Correlation analysis showed that scores (i.e. PERF and WORK) are low correlated (r = -0.20) suggesting that they were independent. Autocorrelation analysis showed that a weekly microcycle is detectable in all the scores. Two-way ANOVA RM showed a statistical difference between match day (MD) and playing position for the three PCA components and PERF score. Conclusion: We proposed an innovative approach to assess both the players' physical performance and training load by using a machine learning approach allowing reducing a large dataset in an objective way. This approach may help practitioners to prescribe the training in the microcycle based on the two scores.