Predicting Breast Cancer using Support Vector Machine Learning Algorithm

Breast cancer is one of the main reasons for death in the world, mostly for women over the last decade. By data mining techniques, the number of tests that are conventionally required, such as MRI, mammogram, ultrasound, and biopsy, can be reduced. Here, a method is proposed that focuses on detecting the presence of risk of breast cancer as 1(Malignant), i.e., present or 0(Benign), i.e., absent. The proposed method uses dataset available in machine learning repository maintained by the University of California, Irvine. The dataset consists of the unique ID numbers of the samples with corresponding diagnosis (malignant/benign), and real-value features (parameters) that are computed from digital images of the cell nuclei of the breast. Support vector machines (SVMs) learning algorithm is used to build a predictive model to identify whether a tumor is malignant or benign. It resulted in an accuracy score of 95.6%.