AIPowered MultiInput Deep Learning System for NonInvasive Early Detection of Vitamin Deficiencies

This project develops a machine learning system for predicting nutrient deficiencies, including Iron, Vitamin C, Vitamin B12, and Vitamin D, by analyzing symptoms observed in individuals. The system employs algorithms such as Decision Tree, Random Forest, XGBoost, and Convolutional Neural Networks (CNN) to enhance prediction accuracy. The CNN model analyzes visual data, such as images or scans of nutritional deficiencies, alongside symptom data for a more comprehensive analysis. Additionally, a chatbot interface is integrated into the web application, providing personalized interactions to users. The chatbot helps users understand their nutritional health, explains the predictions, and suggests dietary changes based on the deficiency identified. Built with Flask for easy access, this web application aims to increase health awareness and enable individuals to make informed decisions regarding their nutrition. By combining advanced machine learning techniques with user-friendly interactions, the system ensures accuracy and provides an intuitive experience for early detection of nutritional health issues.

Keywords: Nutrient Deficiency Prediction, Machine Learning, Decision Tree, Random Forest, XGBoost, CNN, chatbot , Symptom-Based Diagnosis, Flask, Healthcare Technology, Nutritional Health Monitoring.