Integrated Anthropometric, Physiological and Biological Assessment of Elite Youth Football Players Using Machine...

Area of Science:

• Sports Science
• Exercise Physiology
• Biomechanical Analysis

Background:

• Youth football players undergo significant physical and biological changes under high training loads.
• Increased performance demands and injury risks are associated with these changes.
• Current assessments often analyze player domains in isolation, lacking integrated machine learning approaches.

Purpose of the Study:

• To conduct a multidimensional assessment of elite youth football players.
• To investigate the combined influence of anthropometric, physical, and biological markers on performance.
• To utilize classical statistics and machine learning for performance analysis.

Main Methods:

• 100 elite youth football players (14-18 years) underwent comprehensive assessments.
• Data analysis included descriptive statistics, ANOVA/MANOVA, PCA, factor analysis, and machine learning models (linear regression, SVR).
• K-means clustering was employed to identify distinct adaptation phenotypes.

Main Results:

• Older players exhibited higher weight and BMI, with consistent limb asymmetry (~5%) observed in physical tests.
• Principal Component Analysis (PCA) and factor analysis identified latent structural and metabolic domains.
• Linear regression models predicted performance (R² ≈ 0.59), and K-means clustering revealed three distinct adaptation phenotypes.

Conclusions:

• Player performance and resilience are shaped by the interplay of structural, functional, and biological factors.
• Interpretable machine learning offers potential for personalized monitoring and early injury risk detection.
• The findings support evidence-based strategies for injury prevention in young athletes.