AUTHOR=Udovychenko Yevhenii , Popov Anton , Chaikovsky Illya 

TITLE=Multistage Classification of Current Density Distribution Maps of Various Heart States Based on Correlation Analysis and k-NN Algorithm

JOURNAL=Frontiers in Medical Technology

VOLUME=Volume 3 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/medical-technology/articles/10.3389/fmedt.2021.779800

DOI=10.3389/fmedt.2021.779800

ISSN=2673-3129

ABSTRACT=Magnetocardiography is a modern method of registration of magnetic component of electromagnetic field, generated by heart activity. Magnetocardiography results are useful source for diagnosis of various heart diseases and states, but their usage is still undervalued in the cardiology community. In this paper 2-stage classification using correlation analysis and  k-Nearest Neighbor (k-NN) algorithm is applied for binary classification of myocardium current density distribution maps (CDDM). 14 groups of CDDMs from patients with different heart states : healthy volunteers, sportsmen, patients with negative T-peak, patients with Myocardial damage, male and female patients with microvascular disease, patients with ischemic heart disease and patients with left ventricular hypertrophy, divided into 5 and 3 different groups respectively, depending on degree of pathology were compared. Selection of best metric, used in classifier and number of neighbors was performed to define classifier with best performance for each pair of heart states. Accuracy, specificity, sensitivity and precision values dependence on number of neighbors are obtained for each class. Proposed method allows to obtain value of average accuracy equal to 96%, 70% sensitivity, 98% specificity and 70% precision.