A Statistical Index for Early Diagnosis of Ventricular Arrhythmia from the Trend Analysis of ECG Phase-portraits

TL;DR

This paper introduces a statistical index based on phase-space analysis of ECG signals for early detection of ventricular arrhythmia, achieving high accuracy and predicting arrhythmia approximately 356 beats in advance.

Contribution

The paper presents a novel hybrid prediction index combining CV and kurtosis for early arrhythmia detection from ECG phase-portraits, with validated high accuracy.

Findings

Predicts arrhythmia 356 beats before onset

Achieves 96.88% sensitivity and 98.44% accuracy

Verifies effectiveness with extensive simulations

Abstract

In this paper, we propose a novel statistical index for the early diagnosis of ventricular arrhythmia (VA) using the time delay phase-space reconstruction (PSR) technique, from the electrocardiogram (ECG) signal. Patients with two classes of fatal VA - with preceding ventricular premature beats (VPBs) and with no VPBs have been analysed using extensive simulations. Three subclasses of VA with VPBs viz. ventricular tachycardia (VT), ventricular fibrillation (VF) and VT followed by VF are analyzed using the proposed technique. Measures of descriptive statistics like mean ({\mu}), standard deviation ({\sigma}), coefficient of variation (CV = {\sigma}/{\mu}), skewness ({\gamma}) and kurtosis (\{beta}) in phase-space diagrams are studied for a sliding window of 10 beats of ECG signal using the box-counting technique. Subsequently, a hybrid prediction index which is composed of a weighted sum of CV and kurtosis has been proposed for predicting the impending arrhythmia before its actual occurrence. The early diagnosis involves crossing the upper bound of a hybrid index which is capable of predicting an impending arrhythmia 356 ECG beats, on average (with 192 beats standard deviation) before its onset when tested with 32 VA patients (both with and without VPBs). The early diagnosis result is also verified using a leave out cross-validation (LOOCV) scheme with 96.88% sensitivity, 100% specificity and 98.44% accuracy.