Early detection of chronic diseases is crucial for improving patient health outcomes and reducing mortality rates. This project presents an AI-based system for the detection of breast cancer and diabetes using machine learning techniques. The system utilizes publicly available medical datasets containing clinical and physiological parameters for accurate prediction. Breast cancer detection is performed using features such as cell radius, texture, perimeter, and concavity measurements, while diabetes prediction uses health indicators including age, BMI, blood glucose level, and HbA1c level. Data preprocessing methods such as normalization and feature selection are applied to enhance model performance. Multiple machine learning algorithms including Decision Tree, Random Forest, Support Vector Machine, XGBoost and Hybrid model (CNN + Random Forest) are implemented and evaluated to identify the most accurate model. The system generates binary classification results indicating the presence or absence of disease. A user-friendly web interface is developed using HTML, CSS, and JavaScript, while the backend is implemented using Python with the Django framework for seamless model integration. This project demonstrates the effectiveness of artificial intelligence in improving healthcare diagnostics and supporting clinical decision-making.

Keywords: Artificial Intelligence, Machine Learning, Breast Cancer Detection, Diabetes Prediction, Medical Data Analysis, Decision Tree, Random Forest, Support Vector Machine, XGBoost, Flask Framework.