Ingrelyze: Intelligent Nutrition Monitoring and Health Risk Prediction Using Machine Learning and AI Assistance

Abstract

TIn recent years, maintaining a balanced diet and monitoring nutritional intake has become increasingly important due to the rise in lifestyle-related diseases. This paper presents Ingrelyze, a web-based intelligent nutrition analysis and health monitoring system that leverages artificial intelligence and machine learning to evaluate user dietary patterns and provide personalized health insights. The system enables users to log daily food consumption through natural language input, from which nutritional attributes such as calories, proteins, carbohydrates, fats, and fiber are automatically extracted. ARandom Forest machine learning model then analyzes these nutritional attributes to classify the health impact of dietary intake. An AI-powered conversational assistant allows users to interact with the platform using natural language queries and receive dietary recommendations. The system further supports medical certificate uploads to automatically detect and track health conditions such as cholesterol levels and blood pressure. A calendar- based visualization interface and weekly report generator enhance the usability of the platform. The system is deployed as a web application accessible across desktop and mobile browsers. Experimental evaluation demonstrates that the proposed system effectively assists users in monitoring dietary intake and maintaining healthier eating patterns through automated analysis and intelligent recommendations.

Introduction

This research introduces Ingrelyze, an AI-powered nutrition monitoring system designed to help users maintain healthy dietary habits and prevent lifestyle-related diseases such as obesity, diabetes, and cardiovascular disorders. Traditional diet-tracking applications often require manual food logging and database searches, making them time-consuming, error-prone, and unable to provide personalized dietary insights. Ingrelyze addresses these limitations by combining artificial intelligence, machine learning, natural language processing (NLP), and health analytics into a unified web-based platform.

The system's primary objectives include:

• Automated nutritional analysis of daily food intake using NLP.
• Health impact prediction through a Random Forest machine learning model.
• Integration of an AI-based conversational assistant for dietary guidance.
• Calendar-based visualization of nutritional trends.
• Medical certificate upload for personalized health analysis.
• Cross-device accessibility through a responsive web application.

The literature review highlights the limitations of existing nutrition monitoring systems such as MyFitnessPal and Cronometer, which mainly focus on calorie tracking and require significant manual effort. It also discusses the growing role of machine learning in healthcare, particularly for disease prediction and health monitoring, and the benefits of AI-powered conversational assistants in improving user engagement and accessibility.

The proposed system follows a modular architecture consisting of:

1. Frontend (React.js) – User interface, dashboard, and calendar visualization.
2. Backend (Python/Node.js) – Data processing, nutritional calculations, and API management.
3. AI Module – Nutrition analysis, health scoring, and conversational assistance.

Users enter food consumption details in natural language, which are processed using NLP techniques to identify food items and quantities. The system retrieves nutritional information, calculates calories and macronutrients (protein, carbohydrates, fats, and fiber), and stores the data for further analysis.

A Random Forest classifier evaluates dietary patterns and categorizes them into:

• Healthy Diet
• Moderate Diet
• Unhealthy Diet

The system also implements a color-coded health scoring mechanism:

• Green: Healthy dietary intake.
• Yellow: Moderate deviations from recommended nutrition.
• Red: Significant nutritional imbalance.

An AI-powered conversational assistant enables users to ask questions such as calorie consumption, diet quality, and food recommendations based on their health records. Additionally, a calendar-based interface provides daily and weekly nutrition tracking, while weekly reports summarize calorie intake, macronutrient trends, and health assessments.

A unique feature of Ingrelyze is its ability to process uploaded medical certificates and health reports. The system identifies conditions such as high cholesterol or abnormal blood pressure and adjusts dietary recommendations accordingly, making health monitoring more personalized.

Experimental evaluation demonstrated strong performance, achieving 92% prediction accuracy and an average response time of less than two seconds. Users found the visual dashboards, color-coded feedback system, and calendar tracking particularly useful for monitoring dietary habits and identifying unhealthy patterns.

The study concludes that Ingrelyze provides an effective, user-friendly, and intelligent solution for nutrition monitoring by integrating dietary analysis, machine learning, AI assistance, health risk prediction, and personalized recommendations into a single platform. Future enhancements include wearable device integration, image-based food recognition, facial recognition for secure authentication, mobile app deployment, cloud-based infrastructure, and advanced AI recommendation systems for real-time health management.

Conclusion

This paper presented Ingrelyze, an intelligent web-based nutrition monitoring and health risk prediction system designed to improve dietary awareness and support healthier lifestyle choices. The system effectively integrates natural language food input processing, Random Forest-based health impact classification, an AI conversational assistant,calendar-based dietary visualization, medical certificate uploads, and weekly report generation into a unified, accessible platform.

References

[1] WorldHealthOrganization,“HealthyDietGuidelines,” WHO Publications, 2023. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/healthy-diet [2] J. Smith, R. Lee, and A. Kumar, “Machine Learning Approaches for Nutrition Analysis and Health Monitoring,” IEEEJournalofHealthInformatics,vol.25,no.4,pp.1123–1134, Apr. 2022. [3] P. Kumar, S. Nair, and M. Raj, “AI-Based Conversational Assistants in Healthcare Applications,” Springer Journal of Medical Systems, vol. 45, no. 7, pp. 89–98, Jul. 2021. [4] React.js Official Documentation, “Building User InterfaceswithReact,”MetaOpenSource.[Online]. Available:https://reactjs.org [5] Firebase Documentation, “Firebase Realtime Database and Authentication,” Google LLC. [Online]. Available: https://firebase.google.com/docs [6] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001. [7] A. Esteva et al., “A Guide to Deep Learning in Healthcare,”NatureMedicine,vol.25,pp.24–29,Jan.2019.

Copyright

Copyright © 2026 Sidharth S, Harichandana H S, Albin Tom Thomas , Saniya Jackson, Akhilesh P A, Ms. Sagara M R . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.