Spatial Feature Extraction of Vectorcardiography via Minimum Volume Ellipsoid Enclosure in Classifying Left Ventricular Hypertrophy

The voltage criteria used to diagnose left ventricular hypertrophy (LVH) in the chest and limb leads are by no means absolute. In addition to QRS voltages, QRS axis and duration, and P wave characteristics, repolarization (STT) changes have been focused attention due to their representing left ventricular overload. Vectorcardiography (VCG) has been studied specifically on its repolarization abnormality. The present study aims to devise spatial feature extraction of VCG and assess it in the LVH classification task. A minimum volume ellipsoid enclosure was applied to six segments obtained from upstroke and downstroke of each P, QRS, and T loops of a single-beat VCG. For the evaluation, VCG and 12 lead ECG dataset along with LVH labels of 61 subjects were derived from public open data, PTB-XL. These classification performances were compared with the LVH diagnosis criteria in the standard 12 lead ECG. As a result, the Random Forest classifier trained by the proposed spatial VCG feature resulted in accuracy of 0.904 (95% confidence interval: 0.861-0.947) when the classbalanced dataset was evaluated, which slightly exceeded the feature of 12 lead ECG. The feature importance analysis provided the quantitative ranking of the spatial feature of VCG, which were practically similar to those of ECG in the LVH classification task. Since the VCG are spatially comparable with three-dimensional data of CT, MRI, or Echocardiography, VCG will shed light on the spatial behavior of electrical depolarization and repolarization abnormalities in cardiac diseases.

[1]  Radek Martinek,et al.  Comparison of Different Electrocardiography with Vectorcardiography Transformations , 2019, Sensors.

[2]  M. E. Romero-Ibarguengoitia,et al.  Improvement of electrocardiographic diagnostic accuracy of left ventricular hypertrophy using a Machine Learning approach , 2020, PloS one.

[3]  A study of the normal Frank vectorcardiogram. , 1967, The Keio journal of medicine.

[4]  E. W. Hancock,et al.  AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram: part V: electrocardiogram changes associated with cardiac chamber hypertrophy: a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinic , 2009, Journal of the American College of Cardiology.

[5]  M. P. Bonomini,et al.  Left ventricular hypertrophy index based on a combination of frontal and transverse planes in the ECG and VCG: Diagnostic utility of cardiac vectors , 2016 .

[6]  P. Rousseeuw,et al.  Minimum volume ellipsoid , 2009 .

[7]  Celso Ferreira Filho,et al.  Significance of Vectorcardiogram in the Cardiological Diagnosis of the 21st Century , 2007, Clinical cardiology.

[8]  J. M. Chapman,et al.  Electrocardiographic data recorded with Frank leads in subjects without cardiac disease and those with left ventricular overload. , 1966, The American journal of cardiology.

[9]  D. Abbott,et al.  A review of beat-to-beat vectorcardiographic (VCG) parameters for analyzing repolarization variability in ECG signals , 2016, Biomedizinische Technik. Biomedical engineering.

[10]  J. Greenfield,et al.  Vectorcardiographic Diagnosis of Left Ventricular Hypertrophy , 1968, Circulation.

[11]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[12]  L G Dahlin,et al.  Vectorcardiography is superior to conventional ECG for detection of myocardial injury after coronary surgery. , 2001, Scandinavian cardiovascular journal : SCJ.

[13]  Pablo Laguna,et al.  A wavelet-based ECG delineator: evaluation on standard databases , 2004, IEEE Transactions on Biomedical Engineering.

[14]  Wojciech Samek,et al.  PTB-XL, a large publicly available electrocardiography dataset , 2020, Scientific Data.