Selecting best machine learning techniques for breast cancer prediction and diagnosis

Abstract

In this article, we will present an overview of the evolution of large data in the health system, and apply four learning algorithms to a medical data set. The aim of this research work is to predict breast cancer, which is the second leading cause of death among women worldwide, and with early detection and prevention can dramatically reduce the risk of death, using several machine-learning algorithms that are Random Forest, Naïve Bayes, Support Vector Machines SVM, and K-Nearest Neighbors K-NN, and chose the most effective. The experimental results show that SVM gives the highest accuracy 97.9%. The finding will help to select the best classification machine-learning algorithm for breast cancer prediction.