Support Vector Machine Based Diagnosis of Breast Cancer

Abstract

In recent years, the incidence of breast cancer is constantly increasing, for the current medical incurable advanced breast cancer, early accurate diagnosis is the most important to save the lives of patients. In this paper, support vector machine (SVM) is applied to the diagnosis of breast cancer, and the performance of four commonly used kernel functions in different data sets is explored. The experimental results show that the classification accuracy of this method in the breast cancer data set is 98.25%. Compared with the original research using SVM algorithm, this method has a better effect in the auxiliary diagnosis of breast cancer and can help patients and medical institutions to detect the disease more quickly and effectively.