Machine Learning-Based Multi-Disease Prediction Framework for Diabetes and Heart Disease Risk Assessment

Diabetes and heart-related diseases are becoming common health issues around the world. These diseases can lead to serious health problems if they are not detected early. Therefore, early prediction and proper risk assessment are important for improving healthcare and preventing complications. This research focuses on developing a machine learning-based system to predict the risk of diabetes and heart disease using important health parameters such as Body Mass Index (BMI), blood glucose level, and blood pressure. The system is developed using publicly available healthcare datasets from Kaggle and applies different supervised machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, and K-Nearest Neighbors (KNN). The performance of these algorithms was analyzed to identify the most suitable model for disease prediction. The results showed that Random Forest achieved an accuracy of 97.03% for diabetes prediction, while K-Nearest Neighbors (KNN) achieved an accuracy of 90.16% for heart disease prediction. The trained models are integrated into a web-based application where users can enter their health details and receive quick prediction results. The system helps in identifying possible health risks at an early stage and supports preventive healthcare by making disease prediction easier and more accessible.