Detection of Breast Cancer Using Machine Learning Approach

Abstract

Breast cancer affects a substantial portion of the global female population and ranks as the second-leading cause of female mortality. However, the potential for successful treatment increases significantly with early detection and effective intervention. Early identification not only enhances prognosis but also elevates survival rates by facilitating timely therapeutic measures. Additionally, accurate categorization of benign tumors might save patients from receiving needless therapies. This research focuses on leveraging the Wisconsin breast cancer dataset for data visualization and performance evaluations across multiple ML algorithms, specifically decision trees, SVM, random forests, and logistic regression. The primary objective is to rigorously assess the precision, recall, accuracy, and F-1 score of each algorithm, gauging their effectiveness and efficiency in accurate data classification.