Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69229
Volume:
10 |
11 |
Nov 2026
Pages:
1-11
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology

Department of Artificial Intelligence and Data Science
East West Institute of Technology
Existing diet applications frequently separate meal planning, health-risk assessment, progress tracking, and conversational assistance, forcing users to interpret information manually. This paper presents NutriGuardian AI, an integrated web-based system that combines machine learning, Generative AI, and an agentic feedback mechanism for sustainable nutrition and preventive healthcare. The system provides secure user registration and profiles, health-risk prediction for diabetes, heart disease, hypertension, and obesity, personalized meal-plan generation, AI-based nutrition conversation, progress monitoring, and sustainability-oriented insights. A React and Tailwind CSS frontend communicates with a FastAPI/Python backend, while MySQL provzdes persistent storage. Disease models are developed using machine-learning algorithms and serialized for API-based inference. The Generative AI layer uses contextual user information to create meal guidance and explanations, while the agentic layer observes progress and can update recommendation context when user state changes. The system is designed around Sustainable Development Goal 2 (Zero Hunger) and SDG 3 (Good Health and Well- being), with emphasis on accessible, affordable, region-friendly, and preventive nutrition support. The proposed architecture connects prediction, generation, tracking, and adaptation into a single workflow rather than treating them as independent features. The paper describes the system architecture, methodology, database design, implementation, evaluation strategy, limitations, and future enhancements.
KEYWORDS
NutriGuardian AI presents an integrated approach to personalized nutrition and preventive healthcare by combining machine-learning-based health-risk prediction, Generative AI, agentic monitoring, progress tracking, and sustainability-oriented guidance. The system is designed as a modular web application in which user information is maintained as shared context across multiple services. The inclusion of diabetes, heart disease, hypertension, and obesity risk prediction extends the system beyond a conventional meal planner, while the Generative AI and agentic layers provide conversational and adaptive capabilities. The proposed architecture demonstrates how prediction, generation, tracking, and feedback can be connected within one platform. Although the system is not a replacement for medical professionals and requires further validation, it provides a foundation for accessible and personalized nutrition support. Future research can strengthen model validation, nutritional verification, agentic decision policies, sustainability measurement, privacy, and user evaluation to improve reliability and practical usefulness.
[1] D. Tanwar, T. Nobari, P. Chaparro, and A. Panangadan, “Quantitative Evaluation of AI-generated Recipes for Health Recommender Systems,” Proc. 2025 IEEE Int. Conf. Information Reuse and Integration and Data Science (IRI), 2025, DOI: 10.1109/IRI66576.2025.00074. [2] S. Shobana, S. Subitsha, R. Priscilla, and J. Gold Beulah Patturose, “Smart Diet Planner: An AI-Powered Web Application for Personalized Nutrition Management,” Proc. 2025 Int. Conf. Future Technologies (ICFT), 2025, DOI: 10.1109/ICFT66708.2025.11336451. [3] K. Samy, A. Osheba, H. Shams El-Din, R. M. Sallam, and M. Abd Elaziz, “Personalized Nutrition Recommendations Using Machine Learning,” Proc. 2024 Int. Conf. Smart-Digital-Green Technologies and Artificial Intelligence Sciences (CSDGAIS), 2024, DOI: 10.1109/CSDGAIS64098.2024.11064829. [4] M. Ge, F. Ricci, and D. Massimo, “Health-aware food recommender system,” Proc. 9th ACM Conf. Recommender Systems, 2015, pp. 333–334. [5] P. Chavan, B. Thoms, and J. Isaacs, “A recommender system for healthy food choices: building a hybrid model for recipe recommendations using big data sets,” Proc. 54th Hawaii Int. Conf. System Sciences, 2021. [6] Y. Tian, C. Zhang, Z. Guo, C. Huang, R. Metoyer, and N. V. Chawla, “RecipeRec: A heterogeneous graph learning model for recipe recommendation,” arXiv:2205.14005, 2022. [7] R. Yera, A. A. Alzahrani, and L. Martínez, “Exploring post-hoc agnostic models for explainable cooking recipe recommendations,” Knowledge-Based Systems, vol. 251, p. 109216, 2022. [8] Y. Chen, A. Subburathinam, C.-H. Chen, and M. J. Zaki, “Personalized food recommendation as constrained question answering over a large-scale food knowledge graph,” Proc. 14th ACM Int. Conf. Web Search and Data Mining, 2021, pp. 544–552. [9] M. Chen, X. Jia, E. Gorbonos, C. T. Hoang, X. Yu, and Y. Liu, “Eating healthier: Exploring nutrition information for healthier recipe recommendation,” Information Processing & Management, vol. 57, no. 6, p. 102051, 2020. [10] W. Wang, L.-Y. Duan, H. Jiang, P. Jing, X. Song, and L. Nie, “Market2Dish: Health-aware food recommendation,” ACM TOMM, vol. 17, no. 1, pp. 1–19, 2021.
Publication Date
11/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...