A review of support vector machine in cancer prediction on genomic data
by L. Revathi; Ramaswami Murugesh
International Journal of Bioinformatics Research and Applications (IJBRA), Vol. 20, No. 2, 2024

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.

Online publication date: Wed, 29-May-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bioinformatics Research and Applications (IJBRA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com