| Application of artificial intelligence in analyzing nutritional response to exercise |
| Paper ID : 1213-SPORTCONGRESS (R1) |
| Authors |
|
Ashkan Golabi *1, Vahid Talebi2 1Master's degree, Sports Physiology Department, Faculty of Sports Sciences, Guilan of University, Rasht, Iran. 2Department of Sports Sciences, Faculty of Humanities, University of Maragheh, Maragheh, Iran |
| Abstract |
| Introduction:Nutrition is a multifaceted discipline that investigates the intricate relationship between diet, health, and disease. It encompasses physiological and biochemical processes essential for energy production, tissue synthesis, and overall well-being (1, 2). With the rising global burden of diet-related non-communicable diseases, nutrition plays a critical role not only in disease prevention but also in management and treatment. The rapid integration of artificial intelligence (AI), including machine learning (ML) and deep learning (DL), has revolutionized nutritional science by enabling the analysis of large datasets to uncover hidden patterns and predict health outcomes (3,4). Methods: A systematic review was conducted to identify scientific studies published between 2019 and 2024 that applied AI, ML, and DL techniques in the field of nutrition. Research databases were systematically searched to classify studies according to their application areas, including dietary assessment, predictive modeling, personalized nutrition, food detection, and disease monitoring. Results: Fifty studies were identified and categorized into five major clusters: Smart and Personalized Nutrition (32.3%), Dietary Assessment (19.4%), Food Detection and Tracking (12.9%), Predictive Modeling for Disease (25.8%), and Disease Diagnosis and Monitoring (9.7%). The majority of studies demonstrated the potential of AI in predictive disease modeling, where nutritional, lifestyle, and clinical data were used to identify health risks such as diabetes, obesity, and cardiovascular disease. AI-based tools also supported real-time health monitoring, personalized dietary recommendations, and improved accuracy in nutritional assessment. Conclusion: AI-driven approaches are transforming nutrition science by enhancing prediction accuracy, enabling personalized interventions, and facilitating early disease detection. Despite the promising outcomes, challenges such as ethical considerations, data privacy, and model interpretability remain. Future research should emphasize interdisciplinary collaboration to develop reliable, transparent, and patient-centered AI systems that optimize nutrition and promote global health. |
| Keywords |
| Artificial intelligence; Machine learning; Deep learning; Nutrition science; Personalized nutrition; Predictive modeling; Disease prevention; Dietary assessment; Health monitoring; Data-driven healthcare |
| Status: Abstract Accepted (Oral Presentation) |
