The Role of Artificial Intelligence and Electronic Devices in Predicting Overtraining

Background: Overtraining syndrome (OTS) remains a critical challenge in sports medicine. Traditional monitoring methods often lack the sensitivity for early detection. This study investigates the role of Artificial Intelligence (AI) and wearable electronic devices in predicting OTS through advanced data analysis. Methods: A systematic review was conducted following PRISMA guidelines, analyzing studies published between ۲۰۱۴ and ۲۰۲۳. We evaluated literature involving wearable sensors (e.g., heart rate monitors, accelerometers) combined with machine learning algorithms for fatigue prediction. Data on device types, algorithms, and predictive accuracy were synthesized. Results: Fifteen relevant studies were included. AI models, particularly Long Short-Term Memory (LSTM) networks and Random Forests, demonstrated superior performance (accuracy >۸۵%) compared to traditional single-metric approaches. Multi-modal data integration—combining physiological, kinematic, and sleep data—significantly enhanced the early detection of functional overreaching. Personalized baseline modeling was identified as crucial for improving prediction reliability. Conclusion: The integration of AI and wearables offers a transformative approach to OTS prediction, enabling proactive load management. However, challenges regarding data standardization, algorithm interpretability, and privacy persist. Future research must focus on developing explainable AI frameworks and validating these technologies across diverse athletic populations to ensure clinical utility and widespread adoption.

کلیدواژه ها:

Artificial Intelligence ، Electronic Device ، Overtraining