SVM Multi-classification of T2D/CVD Patients Using Biomarker Features

Abstract

Cardiovascular disease (CVD) is considered as the leading cause of morbidity and mortality in type 2 diabetes (T2D) patients. In 2008 the US FDA issued a Guidance to Industry statement, recognizing the conjoined nature of CVD and T2D and emphasizing the need to monitor cardiovascular risk during new diabetic drug trials. This led researchers to work towards identifying panels of markers that are able to distinguish subtypes of CVD in the context of T2D. Immunoassays are used to detect and quantify biomolecules in a solution. Mass spectrometric immunoassay analysis of various proteins in the blood serum of 212 subjects belonging to multiple disease groups resulted in the identification of 41 molecular species as potential biomarkers. In this paper, support vector machines are used to measure the effectiveness of using these species as a diagnosis tool. We suggest an any-vs-rest SVM multiclass classification method by dividing the problem into a series of binary SVM classification problems and using a MAP decision rule to predict the correct class. One-vs-rest and discriminant analysis approaches are also evaluated for comparison.