Applications of Big Data and Artificial Intelligence in Preventing Injuries in Soccer Players

Alban Gomez A.S.; Guerrero Manrique S. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2025) · DOI: 10.18687/leird2025.1.1.449

Resumen

This study analyzes the factors that make soccer players more prone to injuries, considering physical, biomechanical, psychological, and contextual variables. Risk factors such as injury history, neuromuscular fatigue, biomechanical asymmetries, training load, age, positional profile, stress, and environmental conditions are identified. It highlights tools based on Artificial Intelligence (AI) and Big Data used to integrate these factors and prevent injuries, including supervised algorithms (Random Forest, SVM, k-NN), neural networks (CNN, RNN), IoT sensors, Big Data platforms, clustering techniques, and explainable models (XAI). These models outperform traditional methods by offering continuous monitoring, analysis of multiple data sources, and adaptation to the player's condition, achieving over 90% accuracy in injury prediction and a 30% reduction in injury incidence. The methodology used follows the PICO model and the PRISMA protocol, which allowed for a rigorous systematic review. Bibliometric and content analyses are presented, along with a critical discussion of gaps in evidence and practical applicability. The conclusions summarize the key contributions and propose recommendations for future research. © LEIRD 2025.All rights reserved.

Instituciones: Universidad Tecnológica del Perú