Undergraduate Research Conducted applied machine learning research on the early detection of breast cancer using Mutual Information Feature Selection and the C4.5 Decision Tree Algorithm. Engineered and preprocessed a medical dataset with demographic and tumor-specific features, boosting model robustness through data normalization and feature selection. Achieved a 93% accuracy, 100% precision, and 94% F1-score by integrating a mutual information-based feature selection pipeline with a decision tree model. Developed a responsive web interface using Python (Flask) and HTML/CSS to enable clinicians to input patient data and receive instant diagnostic predictions. Led evaluation using cross-validation and performance metrics to validate the clinical reliability of the model.