Machine Learning Techniques for Breast Cancer Prediction

Abstract

Breast cancer is main reason for mortality in woman. Prediction of breast cancer is a challenging task in medical data analysis. Doctors and pathologist required some automated tools to take decision and to differentiate between malignant and benign tumour. A machine learning (ML) algorithm helps lot to take decisions and to perform diagnosis from the data collected by medical field. Various researches show that ML techniques are helpful for decision making in breast cancer prediction. In this paper, we used various ML Classification techniques: Naïve Bayes(NB), Logistic regression (LR),Support vector machine(SVM),K-Nearest Neighbor (KNN), Decision Tree(DT), and ensemble techniques: Random forest(RF), Adaboost, XGBoost on breast cancer dataset and evaluated by using different performance measure. It has been found that both decision tree and XGBoost classifier has highest accuracy 97% among all model and highest AUC 0.999 obtained for XGBoost classifier.