Development of a Linguistic Approach to the Problem of the Computer Electrocardiogram’s Classifications

Abstract

Introduction. The linguistic approach, based on the transition from the observed cyclic signal to a sequence of symbols (codeword), which characterize the dynamics of indicators from cycle to cycle, makes it possible to use the procedures of mathematical linguistics to increase the reliability of decisions. The purpose of the article is to expand the diagnostic capabilities of the linguistic approach to the analysis and interpretation of electrocardiograms (ECG). Methods. Each ECG cycle is encoded with one of four symbols characterizing changes in two indicators: traditional (cycle duration) and original (symmetry of the repolarization area). Results. Based on the processing of real clinical data of verified patients and healthy volunteers, standards of patients with chronic coronary artery disease (СAD) and healthy patients. The standards are developed using computational procedures of mathematical linguistics – the Levenshtein distance, which is the minimum number of editing operations (insertion, deletion and replacement of a character), ensuring the transition from one word to another and the frequency of occurrence of substrings in the analyzed word. On the basis of these procedures, decision rules that have been developed allow making diagnostic decisions based on the Levenshtein distance to the standards and the frequency of occurrence of one-, two- and three-symbol patterns in code words. It was found that the combination of these two methods expands the diagnostic capabilities of the linguistic approach to the analysis and interpretation of the ECG. Conclusions. It has been shown that using of the developed decision rules makes it possible to increase the sensitivity and specificity of diagnostics even in cases when the ECG does not show traditional electrocardiological signs of myocardial ischemia.