Diabetes Detection

The prevalence of diabetes is increasing globally, emphasizing the urgent need for early detection and preventive healthcare solutions. This project presents a Diabetes Detection System that leverages machine learning models integrated into a web-based application for efficient risk prediction. The system allows users to register securely, input their health data (such as glucose levels, BMI, age, and family history), and obtain real-time predictions through models including Support Vector Machine (SVM), Logistic Regression, Random Forest, and K-Nearest Neighbors (KNN). Built using Django for authentication and backend operations and Streamlit for an interactive dashboard, the application provides predictions along with model accuracy, feature importance, and graphical insights. Although the current implementation is limited to static datasets and single-user access, future enhancements aim to include real-time health data integration, advanced visualization, and improved scalability. This project contributes to the growing field of data-driven healthcare by combining technology with preventive medicine to promote timely intervention and better health outcomes.