Prediction of Breast Cancer Using Machine Learning Techniques

Abstract

Breast cancer affects a large number of women around the world who are more likely to die as a result of this condition. To seek out the main cause of breast cancer, samples were collected by employing a variety of cutting-edge procedures. The most modern techniques used in this regard are logistic regression, discriminant analysis and principal component analysis (PCA), all of which are useful in determining the causes of breast cancer. The Breast Cancer Wisconsin Diagnostic Dataset collects information about breast cancer via the machine learning repository approach. As a result of the data correlation matrix, we were able to root our job positively. PCA, discriminant analysis, and logistic regression were utilized to extract the dataset features. Models such as decision tree, naive Bayes, logistic regression, support vector machine (SVM), and artificial neural networks were utilized, and their performances were rigorously examined. The results suggested that the proposed strategy works effectively and reduces the training time. These new methods will help doctors to understand the origins of breast cancer and to distinguish between tumor kinds. Data mining techniques are used extensively, especially for feature selection. Finally, it was concluded that among all models, the hybrid discriminant-logistic (DA-LR) feature selection model outperforms SVM and naive Bayes.