| AI-Driven Biomarker Analysis for Personalized Fatigue Monitoring and Management in Sport |
| Paper ID : 1117-SPORTCONGRESS |
| Authors |
|
Hosna Soori *1, Alireza Souri2 11. Department of Biology, CT.C, Islamic Azad University, Tehran, Iran
2. Institute of Biosocial and Quantum Science and Technologies, CT.C, Islamic Azad University, Tehran, Iran 2Department of Physical Education and Sport Sciences, Science and Research Branch, Islamic Azad University, Tehran, Iran |
| Abstract |
| Introduction: Exercise-induced fatigue is a complex physiological phenomenon arising from interactions among muscular, metabolic, hormonal, and neural systems. It influences performance, recovery, and long-term athlete health. Conventional fatigue assessments—often based on subjective perception or isolated biomarkers—fail to capture this multidimensional complexity. This study highlights how Artificial Intelligence (AI), synergistically combined with targeted biomarker analysis, can reveal both peripheral and central mechanisms of fatigue and enable precision management in sports. Methods: A structured literature review was conducted across PubMed, Scopus, and Web of Science, focusing on exercise biomarkers, sports fatigue, and AI in sports science. Recent meta-analyses and experimental studies (2023–2025) employing machine learning or deep learning for fatigue-related biomarker analysis were included. Extracted data were synthesized into an integrative framework illustrating the interaction between biomarkers and AI for real-time fatigue monitoring and personalized recovery optimization. Results: AI-enhanced biomarker analysis significantly improves the sensitivity and personalization of fatigue assessment. Creatine Kinase (CK) and CKMB, indicators of muscle microtrauma, are modeled through AI to predict recovery timelines and detect overreaching. Blood lactate and metabolomic profiles help uncover metabolic fatigue signatures beyond anaerobic thresholds. Hormonal markers—cortisol, testosterone, and the T/C ratio—are dynamically analyzed to forecast overtraining risk, while inflammatory and immune markers (Interleukin-6, salivary IgA, α-amylase) enable early detection of immune suppression and systemic stress. Integrating these biochemical markers with physiological signals from wearables supports individualized fatigue prediction and adaptive recovery guidance. Conclusion: The synergy between biomarker science and Artificial Intelligence is redefining fatigue management in sport. By transforming complex biochemical and physiological data into personalized insights, AI empowers athletes and coaches to make proactive, data-driven decisions that balance performance with well-being. This human-centered precision approach represents the future of sports medicine—where intelligent systems enhance, rather than replace, human expertise. |
| Keywords |
| Sport fatigue, Biomarkers, Artificial Intelligence |
| Status: Abstract Accepted (Poster Presentation) |
