Classification and Diagnostic Prediction of Cancer Using Support Vector Machine

Abstract

The aim of this analysis was to develop a method for classification of cancers to specific diagnostic types
based on their gene expression signature by applying Support Vector Machine (SVM).We trained the SVM by utilizing
the small, round blue-cell tumors (SRBCTs) as the model. These cancers belong to four distinct diagnostic categories and
usually present diagnostic dilemmas in medical study. As their name implies, these cancers are difficult to distinguish by
light microscopy, and currently no single test can accurately distinguish these type of cancers. The SVM properly
classified the whole samples and identified the genes most relevant to the classification. To test the ability of the trained
SVM models to identify SRBCTs, we examined additional blinded samples that were not previously used for the training
purpose, and correctly classified them in all cases. This study demonstrates the potential applications of these methods
for tumor diagnosis and the identification of candidate targets for therapy. This paper presents architecture of Support
Vector Machine classifiers arranged in a binary tree structure for solving multi-class classification problems with
increased efficiency.