Prediction of Presence of Breast Cancer Disease in the Patient using Machine Learning Algorithms and SFS

Abstract

Listen

Translate article

Breast cancer disease is recognized as the common extensive malignant tumor in between women. Identification of the initial stage of malignant growth may treatment of this disease. Early treatment helps to alleviate the disease and helps anticipate its recurrence in women. Experts have used some fact checks and different medical methods or equipment to improve the accuracy of conclusions in clinical medical service management. In this article, it extensively discussed the implementation of data mining strategies to detection as well as prediction of breast malignant tumors, including random forest (RF), support vector classifier (SVC), k-nearest neighbors (KNN), linear discriminant analysis (LDA), Gradient Boosting Classifier (GBC), Decision Tree (DT) In addition, principal component analysis (PCA) to underline changes and show strong patterns in the informational index. The connection framework is likewise used to show the level of close relationship between attributes. The sequential feature selection (SFS) method is used for comparing the accuracy of a data set with all features and the accuracy of a classifier with selected features. The results show that RF_sfs, KNN_sfs, SVC_rbf and SVC_sfs have the highest and equal accuracy, which is 97.66%. They perform well and can predict the growth of harmful malignant tumors.