Performance Analysis of the Classification of Breast Cancer

Abstract

In recent decades, breast cancer has increased to become the world's second leading cause of death among women. Chronic pain, genetic abnormalities, skin issues, texture of the skin, and color (redness) all appear to be indications of BC. Benign and malignant cancer is the most common binary classifications. Clinicians may discover a method of treatment that is both comprehensive and reliable. Machine Learning (ML) approaches are increasingly being employed in the classification of breast cancer. It supports with highaccuracy classifications and fast calculation skills. The proposed research work examines a supervised learning technique for classifying breast cancer that uses four different classifiers: Boosted Tree, Bagged Tree, Logistic Regression (LR) and Artificial Neural Network (ANN). Also, this research work will compare and contrast the four classifiers, as well as assess the performance. Based on the performance metrics, the above classifiers are analyzed, in which the Artificial Neural Network results with the accuracy of 97.56 % when compared to other classifiers.