MULTIPLE DISEASE PREDICTION USING MACHINE LEARNING

Abstract- This project presents a unified disease prediction system using Streamlit and Python, employing machine learning algorithms like Naïve Bayes, Random Forest, Decision Tree, and SVM to identify conditions such as Heart Disease, Diabetes, and Parkinson’s Disease. By inputting basic health parameters like blood pressure, cholesterol, pulse rate, and heart rate, users can get real-time predictions on their health status. The most accurate model is selected and saved using pickling for deployment. Designed for scalability, the system can later include other chronic and skin diseases, helping in early diagnosis, preventive care, and potentially reducing mortality rates. It offers a simple, user-friendly interface, promoting regular health monitoring and increasing awareness about personal well-being. This model supports healthcare professionals by acting as a decision-support tool, reducing diagnostic workload and improving patient engagement. Moreover, it emphasizes the importance of accessible, AI-driven tools in preventive healthcare, especially in remote or underserved regions where early detection can be life-saving. Keywords- Diabetes, Heart, Liver, KNN, Random Forest, XG Boost., Streamlit,lung cancer ,chronic kidney disease.