Machine learning techniques for early detection and diagnosis of breast cancer prediction

Abstract

Currently breast cancer is considering very serious disease of death among women. The main reason for this cause is late of detected and diagnosis. The early detected and diagnosis help women for longer on live. Machine learning techniques is providing a best technique for early detected, diagnosis and predication of breast cancer. The objective of this study applied and compare two different techniques of machine learning (ML) to determent which give superior performance for predication for breast cancer. The method focuses on to achieve the objectives of this study, there are many steps has been done such as: Data collection and data preprocessing, design the proposed model. Two techniques have been used traditional and ensemble machine learning techniques. The traditional includes several algorithm such as Support vector machine (SVM), Na�ve Bayes(NB), Logistic Regression (LR), K-Nearest Neighbor (KNN), and decision tree(DT) while the ensemble ML techniques covers several algorithm such as Random frost (RF), XGBoost and Adaboot.� To evaluate the performance of these techniques, this study used several measurements such as accuracy, precision, recall, Fl scores for evaluation the performance . The results show that the ensemble ML technique gives superior classification than traditional ML technique. However, the average accuracy of the ensemble ML technique is 0.97, while the average accuracy of Traditional ML techniques is 0.96.Conclusion: The ensemble machine learning techniques outperform than traditional ML technique for detection diagnosis and prediction of breast cancer.