Machine Learning Model for Breast Cancer Detection and Classification

Breast cancer is still one of the prevalent diseases affecting females globally. Machine learning (ML) has come in handy in breast cancer detection by assisting doctors and other healthcare workers with accurate diagnosis in a short time period. The research aims to utilize ML technologies such as Support Vector Machines (SVM), Random Forest (RF), and Convolutional Neural Networks (CNN) to improve patient data analysis techniques, specifically differentiating cancerous tumors from non-cancerous tumors. The models have been trained using a useful dataset so that the project aims to have good sensitivity as well as specificity so as to work towards reducing chances of false calls and decreasing the number of biopsies performed. The findings suggest that ML-based approaches have the potential to significantly enhance diagnostic accuracy when compared to conventional methods. This research sheds light not only on design and anticipated model performance metrics but also on moral aspects, which in their turn demonstrate a wide potential of ML to improve breast cancer’s diagnostics and management allowing for earlier detection and therefore better treatment of patients.