The Investigation of the Success of Different Machine Learning Methods in Breast Cancer Diagnosis

Abstract

Objective: The aim of this study is to identify cancer earlier in life using machine learning methods. Methods: For this purpose, the Wisconsin Diagnostic Breast Cancer dataset was classified using Naive Bayes, decision trees, artificial neural networks algorithms and comparison of these machine learning methods was made. KNIME Analytics Platform was used for applications. Before the classification process, the dataset was preprocessed. After the preprocessing stage, three different classifier methods were applied to the dataset. Accuracy, sensitivity, specificity and confusion matrices were used to measure the success of the methods. Results: The results show that Naive Bayes and artificial neural network methods classify tumors with 96.5% accuracy. The success of the decision tree method in classification was 92.6%. Conclusions: The machine learning algorithms can be used successfully in breast cancer diagnosis to determine whether the tumors are malign or benign.