Classification of Human Ventricular Arrhythmia in High Dimensional Representation Spaces

TL;DR

This study demonstrates that high-dimensional representations of ECG signals, combined with support vector machines, can accurately classify ventricular arrhythmias using short ECG segments, improving detection speed and accuracy.

Contribution

It introduces the use of high-dimensional Fourier-based features and ensemble classifiers for rapid, accurate ventricular arrhythmia classification from short ECG segments.

Findings

Achieved over 93% sensitivity in arrhythmia detection.

Short ECG segments (2 seconds) suffice for accurate classification.

High-dimensional features improve classification accuracy.

Abstract

We studied classification of human ECGs labelled as normal sinus rhythm, ventricular fibrillation and ventricular tachycardia by means of support vector machines in different representation spaces, using different observation lengths. ECG waveform segments of duration 0.5-4 s, their Fourier magnitude spectra, and lower dimensional projections of Fourier magnitude spectra were used for classification. All considered representations were of much higher dimension than in published studies. Classification accuracy improved with segment duration up to 2 s, with 4 s providing little improvement. We found that it is possible to discriminate between ventricular tachycardia and ventricular fibrillation by the present approach with much shorter runs of ECG (2 s, minimum 86% sensitivity per class) than previously imagined. Ensembles of classifiers acting on 1 s segments taken over 5 s observation windows gave best results, with sensitivities of detection for all classes exceeding 93%.