Title: A review of support vector machine in cancer prediction on genomic data

Authors: L. Revathi; Ramaswami Murugesh

Addresses: Department of Computer Applications, School of Information Technology, Madurai Kamaraj University, Madurai, 625021, India ' Department of Computer Applications, School of Information Technology, Madurai Kamaraj University, Madurai, 625021, India

Abstract: Cancer is the most prevalent disease that leads to death globally. According to the World Health Organization (WHO) report, cancer claims over 10 million lives yearly. Extensive research has focused on early detection and prevention through clinical and laboratory studies. Genomic technologies enable the analysis of large cancer-related datasets, while machine learning algorithms aid in early detection. This paper explores earlier studies on supervised machine learning techniques and feature selection methods on high-dimensional gene expression data. Furthermore, this study emphasises the significance of support vector machine (SVM) in cancer prediction and diagnosis, highlighting its superior performance compared to other classification methods and in particular, the choice of kernel function strongly influences the performance of SVM. Additionally, feature selection extracts informative genes from microarray data which leads to high predictive accuracy and less computational complexity. The paper concludes that both machine learning approaches and SVM make substantial contributions to cancer prediction.

Keywords: cancer prediction; feature selection; gene expression; kernel function; machine learning; ML; supervised; support vector machine; SVM.

DOI: 10.1504/IJBRA.2024.138709

International Journal of Bioinformatics Research and Applications, 2024 Vol.20 No.2, pp.161 - 180

Received: 12 Jul 2023
Accepted: 09 Oct 2023
Published online: 29 May 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article