An Empirical Comparison of Machine Learning Algorithms for Predicting Breast Cancer

Abstract

According to recent statistics, breast cancer is one of the most prevalent cancers among women in the world. It represents the majority of new cancer cases and cancer-related deaths. Early diagnosis is very important, as it becomes fatal unless detected and treated in early stages. With the latest advances in artificial intelligence and machine learning (ML), there is a great potential to diagnose breast cancer by using structured data. In this paper, we conduct an empirical comparison of 10 popular machine learning models for the prediction of breast cancer. We used well known Wisconsin Breast Cancer Dataset (WBCD) to train the models and employed advanced accuracy metrics for comparison. Experimental results show that all models demonstrate superior accuracy, while Support Vector Machines (SVM) had slightly better performance than other methods. Logistic Regression, K-Nearest Neighbors and Neural Networks also proved to be strong classifiers for predicting breast cancer.