Classification of Recurrence of Breast Cancer Cells Using Machine Learning

Breast cancer is the most common cancer spreading in woman of developed and developing countries. Statistics shows the breast cancer cause so many deaths every year. Symptoms of breast cancer is lump and thickening of tissues of breast. There are many techniques including supervised and unsupervised learning methods used in medical science for prediction of breast cancer. Supervised learning methods are more popular and also used to find the type of cancer cells. They are also used for prediction of recurrence rate of cancer cells and the survival rate of woman diagnosed with breast cancer. This research study presents a comparison of machine learning (ML) classifiers: Random Forest (RF), Support Vector Machine (SVM), Naïve Bayes(NB) and Artificial Neural Network (ANN) with use of popular feature selection techniques including: Information Gain (IG), Gain Ratio (GR), Relief-F and Gini-index. The experimental results show that ANN outperforms all other classifiers with 99.6 % accuracy.