Arrhythmia detection based on morphological and time-frequency features of T-wave in electrocardiogram

Abstract

The long QT syndrome (LQTs), T-wave alternans (TWA), and ventricular tachyarrhythmia (VT) are some of the common cardiac diseases which cause sudden cardiac death (SCD) in the world. [1,2] Many studies have been developed to detect an abnormal sinus ECG based on the features of ECG signal. Most of these articles use QRS complex to indentify the arrhythmia of the heart. One of the traditional methods has been performed by Jain [3] that digitized and represented each ECG lead by its z-domain modes to enhance the discrimination of the subtle changes in P, QRS, and T sections, the derivatives of the waves are employed for extraction of the modes. Lin et al. [4] used linear prediction to extract features from QRS complexes. Osowski et al. [5] applied fuzzy neural network to ECG beat recognition and classification and the features drawn from the higher order statistics have been proposed in the study. Also Engin [6] performed similar method and used autoregressive model coefficients, higher-order cumulant, and wavelet transform variances as features to enhance the performance. Jekova et al. [7] implemented four different classifiers based on 26 morphological features

The diagnostic value of electrocardiogram-based machine learning in long QT syndrome: a systematic review and meta-analysis

“…In our study, 525 articles were excluded due to inclusion and exclusion criteria. The full-text review was performed on 11 studies, and 8 of these met all criteria for inclusion ( Figure 1 ) ( 19 , 21 , 34 – 39 ).…”

“…The eight ML models included convolutional neural networks (CNNs) ( n = 5), support vector machines (SVMs) ( n = 2), and artificial neural networks (ANNs) ( n = 1). In the majority of studies ( n = 7) the ECG signals were used as inputs to the ML algorithm ( 19 , 21 , 34 – 37 , 39 ), while in the remaining study ( n = 1) the ECG signals were combined with demographic characteristics (age and gender) ( 38 ). Two studies analyzed data from multiple centers, while six studies examined data from a single center.…”

“…(5) For diagnosing LQTS, T-wave morphology is most commonly used. Most researchers in our study also implemented ML algorithms to identify the differentiation of LQTS and controls based on T-wave morphology features after calculating the length of QTc ( 19 , 21 , 34 , 35 , 37 – 39 ). They extracted features from T-wave, such as the Q to T-peak, the T-peak to T-end interval, T-wave magnitude, and T-loop slopes to differentiate LQTS from other cardiovascular diseases with similar T-wave.…”

Exploring ECG Signal Analysis Techniques for Arrhythmia Detection: A Review

“…To mitigate these sources of noise, researchers have employed various preprocessing methods are used like recursive filters [51], [56], [57], [58]and wavelets [51] are the most commonly used. Wavelet-based denoising, although effective, requires advanced levels of decomposition and is more time-consuming and complex compared to other techniques [61].…”

“…For instance, discrete wavelet transform (DWT) [59][61] is commonly used to remove baseline wander, while notch filters [7]are applied to eliminate power line interference. Butterworth filters [57]and median filters [56][60] are employed to mitigate the effects of EMG noise and baseline shift, respectively. Researchers typically focus on addressing specific types of noise and utilize corresponding denoising techniques.…”