IMPROVED BREAST CANCER DETECTION USING MACHINE LEARNING

– This project investigated the application of machine learning to breast cancer detection. Logistic regression, K-nearest neighbors, Random Forest, and decision tree classifiers were implemented on a dataset of breast biopsy samples. Logistic regression and random forest achieved the highest accuracy (98.25% and 96.49%, respectively) in classifying malignant and benign cases. This project highlights the potential of machine learning in breast cancer detection and recognizes the need for further exploration of feature engineering and model optimization techniques. Future efforts will focus on improving the generalizability, interpretability, and verifiability of the model in clinical practice.