Keywords
intelligent decision support systems
personalized diet
artificial intelligence
machine learning
big data in nutrition
food composition analysis
food additives
overeating
recommender systems
wearable devices
nutrigenomics
food databases
chronic disease prevention
visual-language models
digital health
eating behavior
metabolic profile
nutrition sensing and tracking
ethics and privacy in AI
How to Cite
Abstract
personalized nutrition does not align well with traditional disciplinary boundaries, and attempts to define it narrowly have often failed. We analyzed how artificial intelligence and nutrition intersect and found that most current approaches operate as context-specific solutions rather than coherent systems. Existing platforms draw on diverse data sources such as food composition metrics, biometric updates, meal images, and user preferences, but their effective integration remains uncertain.
We observed a shift from fixed system architectures to modular and flexible configurations. Language models, probabilistic classifiers, and computer vision algorithms are increasingly combined to enhance responsiveness, though often at the expense of structural consistency.
The body of evidence for AI-driven personalized nutrition is expanding but remains inconsistent. Reported outcomes include reductions of up to 40% in irritable bowel syndrome symptoms and partial diabetes remission in more than 70% of participants. However, these results vary considerably across studies and are often influenced by external factors unrelated to nutrition.
Despite these limitations, the field continues to advance. Personalized nutrition is emerging not only as a technical application but also as a redefinition of dietary advice in a digital, data-driven environment.
References
Limit Fat, Salt, and Sugar Intake. World Health Organization, Eastern Mediterranean Region. Режим доступа: https://www.emro.who.int/nutrition/reduce-fat-salt-and-sugar-intake/.
Huang L., Li J., Zhang Y., Chen X. The Role of Artificial Intelligence in Obesity Risk Prediction and Management: Approaches, Insights, and Recommendations. Medicina. 2025;61(2):358. DOI: 10.3390/medicina61020358.
Theodore Armand T. P., Nfor K. A., Kim J-I., Kim H.-C. Applications of Artificial Intelligence, Machine Learning, and Deep Learning in Nutrition: A Systematic Review. Nutrients. 2024;16(7):1073. DOI: 10.3390/nu16071073.
Agrawal K., Goktas P., Kumar N., Leung M.-F. Artificial Intelligence in Personalized Nutrition and Food Manufacturing: A Comprehensive Review of Methods, Applications, and Future Directions. Frontiers in Nutrition. 2025;12. DOI: 10.3389/fnut.2025.1636980.
Yang Z., Khatibi E., Nagesh N., Abbasian M., Azimi I., Jain R., Rahmani A. ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework. arXiv:2403.00781. 2024. DOI: https://doi.org/10.48550/arXiv.2403.00781.
Lee D.-S., Kwon S.-K. Amount Estimation Method for Food Intake Based on Color and Depth Images through Deep Learning. Sensors. 2024;24(7):2044. DOI: 10.3390/s24072044.
Ma P., Wu Y., Yu N., Zhang Y., Backes M., Wang Q., Wei C.-I. UMDFood: Vision-Language Models Boost Food Composition Compilation. arXiv:2306.01747. 2023. DOI: 10.48550/arXiv.2306.01747.
Arefeen A., Fessler S., Mostafavi S. M., Johnston C. S., Ghasemzadeh H. MealMeter: Using Multimodal Sensing and Machine Learning for Automatically Estimating Nutrition Intake. arXiv:2503.11683. 2025. DOI: https://doi.org/10.48550/arXiv.2503.11683.
Yang Z., Khatibi E., Nagesh N., Abbasian M., Azimi I., Jain R., Rahmani A. M. ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework. arXiv:2403.00781. 2024. DOI: https://doi.org/10.48550/arXiv.2403.00781.
Rao S., Neethirajan S. Computational Architectures for Precision Dairy Nutrition Digital Twins: A Technical Review and Implementation Framework. Sensors. 2025;25(16):4899. DOI: 10.3390/s25164899.
Xu Z., Gu Y., Xu X., Topaz M., Guo Z., Kang H., Sun L., Li J. Developing a Personalized Meal Recommendation System for Chinese Older Adults: Observational Cohort Study. JMIR Formative Research. 2024;8:e52170. DOI: 10.2196/52170.
Tunali V., Arslan N. C¸., Ermis¸ B. H. et al. A Multicenter Randomized Controlled Trial of MicrobiomeBased Artificial Intelligence-Assisted Personalized Diet vs Low-Fermentable Oligosaccharides, Disaccharides, Monosaccharides, and Polyols Diet: A Novel Approach for the Management of Irritable Bowel Syndrome. The American Journal of Gastroenterology. 2024;119(9):1901–1912. DOI: 10.14309/ajg.0000000000002862.
Tay J., Thompson C. H., Luscombe-Marsh N. D., Wycherley T. P., Noakes M., Buckley J. D., Wittert G. A., Yancy W. S. Jr., Brinkworth G. D. Effects of an Energy-Restricted Low-Carbohydrate, High Unsaturated Fat/Low Saturated Fat Diet Versus a High-Carbohydrate, Low-Fat Diet in Type 2 Diabetes: A 2-Year Randomized Clinical Trial. Diabetes, Obesity and Metabolism. 2018;20(4):858–871. DOI: 10.1111/dom.13164.
Tily H., Partridge E., Cai Y., et al. Gut Microbiome Activity Contributes to Prediction of Individual Variation in Glycemic Response in Adults. Diabetes Therapy. 2022;13(1):89–111. DOI: 10.1007/s13300021-01174-z. Режим доступа: https://pubmed.ncbi.nlm.nih.gov/PMC8776936.
Azzimani K., Bihri H., Dahmi A., Azzouzi S. An AI-Based Approach for Personalized Nutrition and Food Menu Planning. Proc. of 2022 IEEE 3rd International Conference on Electronics, Control, Optimization and Computer Science (ICECOCS). Fez, Morocco, 2022:1–5. DOI: 10.1109/ICECOCS55148.2022.9983099.