Machine Learning Algorithms for Breast Cancer Detection: A Comparative Study

Abstract

Breast cancer is a significant cause of mortality among women. Early detection of breast cancer enhances prognosis and survival prospects while facilitating timely therapeutic intervention for patients. Support vector machines and Artificial neural network ANNs have been used in several research publications to get precise diagnoses through high classification accuracy. This study addresses breast cancer diagnosis with SVM and ANN, integrated with feature selection, and both models were evaluated on the well-recognized Kaggle Wisconsin Diagnosis Breast Cancer Dataset (WDBC) for experimental purposes. Empirical research comparing SVM and ANN revealed that ANN exhibits superior accuracy, with a classification accuracy of 98% compared to SVM's 97%.