A comparative study of decision tree and support vector machine for breast cancer prediction
1 Department of Research and Development, Communication Towers Nigeria Limited, Nigeria.
2 Department of Electrical Engineering, George Washington University, District of Columbia, USA.
3 Department of Physics, Olusegun Agagu University of Science and Technology, Ondo State, Nigeria.
4 Centre for Clinical Trials, Research and Implementation Science, College of Medicine, University of Lagos, Nigeria.
5 Department of Computer Science, Federal University Oye Ekiti, Ekiti State, Nigeria.
6 Department of Civil Engineering, Federal University of Technology Akure, Ondo State, Nigeria.
7 Department of Biochemistry, Olusegun Agagu University of Science and Technology, Okitipupa, Ondo State, Nigeria.
8 Department of Computer Science, Federal University of Technology, Lokoja, Kogi State, Nigeria.
9 Department of Medicine and Surgery, Obafemi Awolowo University, Ife, Osun State, Nigeria.
Research Article
World Journal of Advanced Research and Reviews, 2024, 23(01), 746–752
Article DOI: 10.30574/wjarr.2024.23.1.2024
Publication history:
Received on 25 May 2024; revised on 01 July 2024; accepted on 04 July 2024
Abstract:
Breast cancer remains a leading cause of mortality among women globally, necessitating accurate and early diagnosis techniques. This study explores the effectiveness of Support Vector Machine (SVM) techniques for diagnosing breast cancer, utilizing the Object-Oriented Analysis and Design Method (OOADM) for system development. The research employed the Wisconsin Breast Cancer Dataset from the UCI Machine Learning Repository, comprising ten features. The dataset was divided into 80% for training and 20% for testing the SVM model. Performance metrics such as classification accuracy, Area Under the Curve (AUC), sensitivity, specificity, and precision were used to evaluate the SVM model, which was also compared against a Decision Tree (DT) model. The results indicated that the SVM model achieved superior performance with an accuracy of 94%, AUC of 98%, sensitivity of 95%, specificity of 87%, and precision of 93%. In comparison, the DT model showed an accuracy of 89%, AUC of 95%, sensitivity of 90%, specificity of 85%, and precision of 90%. The findings underscore the potential of SVM in enhancing breast cancer diagnostic accuracy, thereby supporting early detection and treatment.
Keywords:
Support Vector Machine (SVM); Breast Cancer Diagnosis; Machine Learning; Wisconsin Breast Cancer Dataset; Classification Accuracy; Data Mining
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0