This paper presents a unified disease prediction system using Streamlit and Python, applying ML algorithms like Naïve Bayes, Random Forest, Decision Tree, SVM, and XGBoost to detect conditions such as heart disease, diabetes, and Parkinson’s. The system uses basic health parameters and offers real-time predictions, supporting early diagnosis and preventive care. It is scalable, user-friendly, and deployable in underserved regions, enhancing healthcare accessibility.
The proposed system demonstrates high accuracy in predicting multiple diseases using ML models. It supports healthcare professionals by automating diagnosis and handling large datasets efficiently. Future enhancements could include integration with real-time clinical systems and expansion to additional disease categories.
References
Includes 12 references from IEEE, IJCA, IJSER, and other journals covering disease prediction, ML algorithms, and healthcare analytics.
Post Comment