Importance of anthropometric features to predict physical performance in elite youth soccer: a machine learning approach

Abstract

The present study aimed to determine the contribution of soccer players' anthropometric features to predict their physical performance. Sixteen players, from a professional youth soccer academy, were recruited. Several anthropometric features such as corrected arm muscle area (AMA_corr), arm muscle circumference (AMC) and right and left suprapatellar girths (RSPG and LSPG) were employed in this study. Players' physical performance was assessed by the change of direction (COD), sprint (10-m and 20-m), and vertical jump (CMJ) tests, and Yo-Yo Intermittent Recovery Test level 1 (Yo-Yo IRT1). Using an extra tree regression (ETR) model, the anthropometric features permitted to accurately predict 10-m sprint, 20-m sprint and Yo-Yo IRTL 1 performance (p < 0.05). ETR showed that upper-body features as AMA_corr, and AMC affected 10-m and 20-m sprint performances, while lower-body features as RSPG and LSPG influenced the Yo-Yo IRTL 1 (Overall Gini importance ≥ 0.22). The model predicting COD and CMJ presented a poor level of prediction, suggesting that other factors, rather than anthropometric features, may concur to predict their changes in performance. These findings demonstrated that the upper- and lower-body anthropometric features are strictly related to sprint and aerobic fitness performance in elite youth soccer.

Keywords: Body composition; aerobic fitness; anthropometry; artificial intelligence; change of direction; data mining.