<![CDATA[This study proposes a user-friendly Personalized Medical Recommendation System that integrates Artificial Intelligence (AI) and Machine Learning (ML) to improve disease prediction and healthcare accessibility, especially for non-technical users in resource-limited settings. The system is built using a Flask-based RESTful API that enables real-time predictions and delivers context-aware health recommendations through a web interface. It utilizes datasets covering symptoms, diseases, precautions, diet plans, workouts, and medication information. Data preprocessing techniques, including noise removal, normalization, missing value imputation, and synonym mapping, are applied to ensure consistency and reliability. Five classification algorithms—Support Vector Classifier (SVC), Random Forest, K-Nearest Neighbors (KNN), Gradient Boosting, and Multinomial Naive Bayes—were evaluated, with SVC achieving the highest accuracy of 95.2%. The system predicts diseases based on user-input symptoms and provides personalized recommendations. Overall, the framework offers a scalable, efficient, and practical solution for integrating AI-driven diagnosis into digital healthcare platforms.]]>
Copyrights © 2027
