VCG and ECG indexes for classification of patients with myocardial infarction

Abstract

We proposed a classification technique for patients with Myocardial Infarction (MI), based on an Electrocardiographic (ECG) and Vectorcardiographic (VCG) signals analysis. We suggest and statistically analyze two VCGs and nine orthogonal ECG indexes, i.e., a) QRS loop Perimeter, b) Angle between QRS and T loops, c-e) the area under the QRS, T-wave and ST segment in X, Y and Z leads. For classification, the population was divided into two groups according to the infarcted area, that is, anterior or inferior sectors (MI-ant and MI-inf, respectively). The results indicate that combining eight indexes, we could separate out the MI patients in MI-ant vs MI-inf with a sensitivity = 89.8%, 84.8%, respectively, and an accuracy = 89.8%. We conclude that the proposed technique could be suitable to estimatethe infarcted area localization.