CLASSIFICATION OF BREAST CANCER USING MACHINE LEARNING ALGORITHMS

Abstract

Breast Cancer is a common disease in women. Its early detection and classification using Machine Learning (ML) algorithms can effectively improve the patient's survival. In this study six Machine Learning Algorithms were applied to the dataset of Wisconsin Diagnostic Breast Cancer (WDBC) these are, Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT). The data were preprocessed and split according to their size into 0.2 and 0.3. Each algorithm was tested and evaluated using performance metrics to classify the breast cancer into Malignant or Bingen tumors. Finally, the results of the algorithms are compared to each other. The results revealed that the LR and SVM achieved high accuracy (98%) at the size of the data test 0.3, whereas the lowest accuracy was NB (92%). Reducing the size of the data test to 0.2 improved the accuracy of all algorithms except DT, The LR had the best accuracy (99%). All the work was done in the Spyder environment based on Python programming language.