Applying machine learning models to breast cancer prediction problem

Abstract

Cancer has become the number one killer of human life and health. Therefore, a model that can predict cancer is able to help doctors to diagnose whether a patient has cancer or not, which can boost the accuracy of the diagnosis and enhance diagnostic efficiency, thus reducing the chance of misdiagnosis and other situations. This paper focuses on breast cancer prediction and adopted three machine learning based methods, including logistic regression, K-Nearest Neighbor, and decision tree models to build automatic solutions and investigate which model is more suitable for such a simple prediction problem. In this study, the detailed features, data collection and pre-processing approaches are presented to better understand such medical data. Then extensive experiments show that the accuracy scores of the three models are 97.08%, 94.89%, and 93.43%, respectively. Through comparison, it is concluded that the logistic regression model achieves the best performance for the breast cancer prediction task.