A comparative study of the performance of methods for f-wave extraction

Objective.This study proposes a novel technique for atrial fibrillatory waves (f-waves) extraction and investigates the performance of the proposed method comparing with different f-wave extraction methods.Approach.We propose a novel technique combining a periodic component analysis (PiCA) and echo state network (ESN) for f-waves extraction, denoted PiCA-ESN. PiCA-ESN benefits from the advantages of using both source separation and nonlinear adaptive filtering. PiCA-ESN is evaluated by comparing with other state-of-the-art approaches, which include template subtraction technique based on principal component analysis, spatiotemporal cancellation, nonlinear adaptive filtering using an echo state neural network, and a source separation technique based on PiCA. Quality assessment is performed on a recently published reference database including a large number of simulated ECG signals in atrial fibrillation (AF). The performance of the f-wave extraction methods is evaluated in terms of signal quality metrics (SNR, ΔSNR) and robustness of f-wave features.Main results.The proposed method offers the best signal quality performance, with a ΔSNR of approximately 22 dB across all 8 sets of the reference database, as well as the most robust extraction of f-wave features, with 75% of all estimates of dominant atrial frequency well below 1 Hz.

F-Wave Extraction from Single-Lead Electrocardiogram Signals with Atrial Fibrillation by Utilizing an Optimized Resonance-Based Signal Decomposition Method

(1) Background: A typical cardiac cycle consists of a P-wave, a QRS complex, and a T-wave, and these waves are perfectly shown in electrocardiogram signals (ECG). When atrial fibrillation (AF) occurs, P-waves disappear, and F-waves emerge. F-waves contain information on the cause of atrial fibrillation. Therefore it is essential to extract F-waves from the ECG signal. However, F-waves overlap the QRS complex and T-waves in both the time and frequency domain, causing this matter to be a difficult one. (2) Methods: This paper presents an optimized resonance-based signal decomposition method for detecting F-waves in single-lead ECG signals with atrial fibrillation (AF). It represents the ECG signal utilizing morphological component analysis as a linear combination of a finite number of components selected from the high-resonance and low-resonance dictionaries, respectively. The linear combination of components in the low-resonance dictionary reconstructs the oscillatory part (F-wave) of the ECG signal. In contrast, the linear combination of components in the high-resonance dictionary reconstructs the transient components part (QRST wave). The tunable Q-factor wavelet transform generates the high and low resonance dictionaries, with a high Q-factor producing a high resonance dictionary and a low Q-factor producing a low resonance dictionary. The different Q-factor settings affect the dictionaries’ characteristics, hence the F-wave extraction. A genetic algorithm was used to optimize the Q-factor selection to select the optimal Q-factor. (3) Results: The presented method helps reduce RMSE between the extracted and the simulated F-waves compared to average beat subtraction (ABS) and principal component analysis (PCA). According to the amplitude of the F-wave, RMSE is reduced by 0.24–0.32. Moreover, the dominant frequency of F-waves extracted by the presented method is clearer and more resistant to interference. The presented method outperforms the other two methods, ABS and PCA, in F-wave extraction from AF-ECG signals with the ventricular premature heartbeat. (4) Conclusion: The proposed method can potentially improve the accuracy of F-wave extraction for mobile ECG monitoring equipment, especially those with fewer leads.

Non-invasive characterisation of macroreentrant atrial tachycardia types from a vectorcardiographic approach with the slow conduction region as a cornerstone

BACKGROUND AND OBJECTIVES

Macroreentrant atrial tachyarrhythmias (MRATs) can be caused by different reentrant circuits. The treatment for each MRAT type may require ablation at different sites, either at the right or left atria. Unfortunately, the reentrant circuit that drives the arrhythmia cannot be ascertained previous to the electrophysiological intervention.

METHODS

A noninvasive approach based on the comparison of atrial vectorcardiogram (VCG) loops is proposed. An archetype for each group was created, which served as a reference to measure the similarity between loops. Methods were tested in a variety of simulations and real data obtained from the most common right (peritricuspid) and left (perimitral) macroreentrant circuits, each divided into clockwise and counterclockwise subgroups. Adenosine was administered to patients to induce transient AV block, allowing the recording of the atrial signal without the interference of ventricular signals. From the vectorcardiogram, we measured intrapatient loop consistence, similarity of the pathway to archetypes, characterisation of slow velocity regions and pathway complexity.

RESULTS

Results show a considerably higher similarity with the loop of its corresponding archetype, in both simulations and real data. We found the capacity of the vectorcardiogram to reflect a slow velocity region, consistent with the mechanisms of MRAT, and the role that it plays in the characterisation of the reentrant circuit. The intra-patient loop consistence was over 0.85 for all clinical cases while the similarity of the pathway to archetypes was found to be 0.85 ± 0.03, 0.95 ± 0.03, 0.87 ± 0.04 and 0.91 ± 0.02 for the different MRAT types (and p<0.02 for 3 of the 4 groups), and pathway complexity also allowed to discriminate among cases (with p<0.05).

CONCLUSIONS

We conclude that the presented methodology allows us to differentiate between the most common forms of right and left MRATs and predict the existence and location of a slow conduction zone. This approach may be useful in planning ablation procedures in advance.

Refined Ventricular Activity Cancellation in Electrograms During Atrial Fibrillation by Combining Average Beat Subtraction and Interpolation

Many techniques have been developed to cancel the ventricular interference in atrial electrograms (AEG) during atrial fibrillation. In particular, average beat subtraction (ABS) and interpolation are among those mostly adopted. However, ABS usually leaves high power residues and discontinuity at the borders, whereas interpolation totally substitutes the residual activity with a forecasting that might fail at the center of the cancellation segment. In this study, we proposed a new algorithm to refine the ventricular estimate provided by ABS, in such a way that the residual activity should likely be distributed as the local atrial activity. Briefly, the local atrial activity is first modeled with an autoregressive (AR) process, then the estimate is refined by maximizing the log likelihood of the atrial residual activity according to the fitted AR model. We tested the new algorithm on both synthetic and real AEGs, and compared the performance with other four algorithms (two variants of ABS, interpolation and zero substitution). On synthetic data, our algorithm outperformed all the others in terms of average root mean square error (0.043 vs 0.046 for interpolation; p <; 0.05). On real data, our methodology outperformed two variants of ABS (p <; 0.05) and performed similarly to interpolation when considering the high power residues left (both <; 5%), and the log likelihood with the fitted AR model.

Reference database and performance evaluation of methods for extraction of atrial fibrillatory waves in the ECG

OBJECTIVE

This study proposes a reference database, composed of a large number of simulated ECG signals in atrial fibrillation (AF), for investigating the performance of methods for extraction of atrial fibrillatory waves (f-waves).

APPROACH

The simulated signals are produced using a recently published and validated model of 12-lead ECGs in AF. The database is composed of eight signal sets together accounting for a wide range of characteristics known to represent major challenges in f-wave extraction, including high heart rates, high morphological QRST variability, and the presence of ventricular premature beats. Each set contains 30 5 min signals with different f-wave amplitudes. The database is used for the purpose of investigating the statistical association between different indices, designed for use with either real or simulated signals.

MAIN RESULTS

Using the database, available at the PhysioNet repository of physiological signals, the performance indices unnormalized ventricular residue (uVR), designed for real signals, and the root mean square error, designed for simulated signals, were found to exhibit the strongest association, leading to the recommendation that uVR should be used when characterizing performance in real signals.

SIGNIFICANCE

The proposed database facilitates comparison of the performance of different f-wave extraction methods and makes it possible to express performance in terms of the error between simulated and extracted f-wave signals.

A novel IRBF-RVM model for diagnosis of atrial fibrillation

BACKGROUND AND OBJECTIVE

Atrial fibrillation (AF) is one of the common cardiovascular diseases, and electrocardiography (ECG) is a key indicator for the detection and diagnosis of AF and other heart diseases. In this study, an improved machine learning method is proposed for rapid modeling and accurate diagnosis of AF.

METHODS

This paper presents a novel IRBF-RVM model that combines the integrated radial basis function (IRBF) and relevance vector machine (RVM), which is utilized for the diagnosis of AF. The synchronous 12-lead ECG signals are collected from the human body surface so as to fully reflect the electrical activity of the whole heart. RR intervals of the QRS-waves in ECG signals are obtained by means of the classical Pan-Tompkins algorithm. The RR-features extracted from RR intervals are adopted as the diagnostic features for AF patients. In addition, the conventional RBF-RVM model, support vector machine (SVM) and other machine learning methods are also investigated for the diagnosis of AF so as to reflect the advantage of the proposed IRBF-RVM model. The open MIT-BIH arrhythmia database (MITDB) is also used to evaluate the predictive performance of these state-of-the-art methods.

RESULTS

Altogether 1056 AF patients and 904 healthy people are participated in this study and validate the effectiveness of each channel of the 12-lead ECG signals. Experimental results show that the classification rate of IRBF-RVM can reach up to 98.16% by recurring to Channel II of the 12-lead ECG signals.

CONCLUSIONS

IRBF-RVM absorbs the advantages of IRBF, which makes the kernel parameter of IRBF-RVM have a much larger selectable region than RBF-RVM. In addition, RVM has faster modeling and recognition speed in comparison with SVM. This work lays the foundation for the application of RVM to accurate diagnosis of AF.

Multiscaled Fusion of Deep Convolutional Neural Networks for Screening Atrial Fibrillation From Single Lead Short ECG Recordings

Atrial fibrillation (AF) is one of the most common sustained chronic cardiac arrhythmia in elderly population, associated with a high mortality and morbidity in stroke, heart failure, coronary artery disease, systemic thromboembolism, etc. The early detection of AF is necessary for averting the possibility of disability or mortality. However, AF detection remains problematic due to its episodic pattern. In this paper, a multiscaled fusion of deep convolutional neural network (MS-CNN) is proposed to screen out AF recordings from single lead short electrocardiogram (ECG) recordings. The MS-CNN employs the architecture of two-stream convolutional networks with different filter sizes to capture features of different scales. The experimental results show that the proposed MS-CNN achieves 96.99% of classification accuracy on ECG recordings cropped/padded to 5 s. Especially, the best classification accuracy, 98.13%, is obtained on ECG recordings of 20 s. Compared with artificial neural network, shallow single-stream CNN, and VisualGeometry group network, the MS-CNN can achieve the better classification performance. Meanwhile, visualization of the learned features from the MS-CNN demonstrates its superiority in extracting linear separable ECG features without hand-craft feature engineering. The excellent AF screening performance of the MS-CNN can satisfy the most elders for daily monitoring with wearable devices.