Segmentation of Holter ECG Waves Via Analysis of a Discrete Wavelet-Derived Multiple Skewness–Kurtosis Based Metric

Abstract

In this study, a simple mathematical-statistical based metric called Multiple Higher Order Moments (MHOM) is introduced enabling the electrocardiogram (ECG) detection-delineation algorithm to yield acceptable results in the cases of ambulatory holter ECG including strong noise, motion artifacts, and severe arrhythmia(s). In the MHOM measure, important geometric characteristics such as maximum value to minimum value ratio, area, extent of smoothness or being impulsive and distribution skewness degree (asymmetry), occult. In the proposed method, first three leads of high resolution 24-h holter data are extracted and preprocessed using Discrete Wavelet Transform (DWT). Next, a sample to sample sliding window is applied to preprocessed sequence and in each slid, mean value, variance, skewness, and kurtosis of the excerpted segment are superimposed called MHOM. The MHOM metric is then used as decision statistic to detect and delineate ECG events. To show advantages of the presented method, it is applied to MIT-BIH Arrhythmia Database, QT Database, and T-Wave Alternans Database and as a result, the average values of sensitivity and positive predictivity Se = 99.95% and P+ = 99.94% are obtained for the detection of QRS complexes, with the average maximum delineation error of 6.1, 4.1, and 6.5 ms for P-wave, QRS complex, and T-wave, respectively showing marginal improvement of detectiondelineation performance. In the next step, the proposed method is applied to DAY hospital high resolution holter data (more than 1,500,000 beats including Bundle Branch Blocks-BBB, Premature Ventricular Complex-PVC, and Premature Atrial Complex-PAC) and average values of Se = 99.97% and P+ = 99.95% are obtained for QRS detection. In summary, marginal performance improvement of ECG events detection-delineation process, reliable robustness against strong noise, artifacts, and probable severe arrhythmia(s) of high resolution holter data can be mentioned as important merits and capabilities of the proposed algorithm.

Optimal delineation of PCG sounds via false‐alarm bounded segmentation of a wavelet‐based principal components analyzed metric

“…To implement the à trous wavelet transform algorithm, filters H (z) and G(z) should be used according to the block diagram represented in Figure 2 [53]. According to this block diagram, each smoothing function (SMF) is obtained by sequential low-pass filtering (convolving with H (z 2k ) filters), while after high-pass filtering of an SMF (convolving with G(z 2k ) filters), the corresponding DWT at the appropriate scale is generated.…”

“…Thus, useful information can be obtained using wavelet transform in different scales. If the scale factor a and the translation parameter b are chosen as a = 2 k and b = 2 k l, the dyadic wavelet with the following basis function will be resulted [53,54] as,…”

“…The curve length of the signal x(t) in the kth slide of the analysis window can be obtained approximately as [53] …”

Optimal Delineation of Ambulatory Holter ECG Events via False-Alarm Bounded Segmentation of a Wavelet-Based Principal Components Analyzed Decision Statistic

“…The physical meaning of the M MS (k) is the average power of the events while this quantity graphically shows the dispersion of the samples around the mean value (Ghaffari et al 2010b). The M MS (k) indicates difference between absolute maximum and minimum values of an excerpted segment.…”

“…Therefore, parameterization and detection of ECG signal events using a reliable algorithm, are the first stage in the computer analysis of the ECG signal. Numerous approaches have yet been developed for the aim of detection of the ECG events including mathematical models (Sayadi and Shamsollahi 2009), Hilbert transform and the first derivative (Arzeno and Zhi-De Deng 2008;Ghaffari et al 2010a;Benitez et al 2001), multiple higher order moments (Ghaffari et al 2010b), second order derivative (Mitra and Mitra 2007), wavelet transform and the filter banks (Martinez et al 2004;Ghaffari et al 2009c, d), soft computing (Neuro-fuzzy, genetic algorithm) (Kannathal et al 2006), Hidden Markov Models (HMM) application (de Lannoy et al 2008), and etc. The performance of QRS detection algorithms can easily be verified using the standard databases such as MIT-BIH Arrhythmia Database (Moody and Mark 1990); however, validation of a proposed algorithm for the detection-delineation of P and T-waves has turned to a difficult problem due to the lack of a gold standard as universal reference (Martinez et al 2004).…”