Electrocardiology of atrial fibrillation

Wavelet leader multifractal analysis of heart rate variability in atrial fibrillation

BACKGROUND

Accurate and timely detection of atrial fibrillation (AF) episodes is important in primarily and secondary prevention of ischemic stroke and heart-related problems. In this work, heart rate regularity of ECG inter-beat intervals was investigated in episodes of AF and other rhythms using a wavelet leader based multifractal analysis. Our aim was to improve the detectability of AF episodes.

METHODS

Inter-beat intervals from 25 ECG recordings available in the MIT-BIH atrial fibrillation database were analysed. Four types of annotated rhythms (atrial fibrillation, atrial flutter, AV junctional rhythm, and other rhythms) were available. A wavelet leader based multifractal analysis was applied to 5 min non-overlapping windows of each recording to estimate the multifractal spectrum in each window. The width of the multifractal spectrum was analysed for its discrimination power between rhythm episodes.

RESULTS

In 10 of 25 recordings, the width of multifractal spectrum was significantly lower in episodes of AF than in other rhythms indicating increased regularity during AF. High classification accuracy (95%) of AF episodes was achieved using a combination of features derived from the multifractal analysis and statistical central moment features.

CONCLUSIONS

An increase in the regularity of inter-beat intervals was observed during AF episodes by means of multifractal analysis. Multifractal features may be used to improve AF detection accuracy.

Analyzing single-lead short ECG recordings using dense convolutional neural networks and feature-based post-processing to detect atrial fibrillation

OBJECTIVE

The prevalence of atrial fibrillation (AF) in the general population is 0.5%-1%. As AF is the most common sustained cardiac arrhythmia that is associated with an increased morbidity and mortality, its timely diagnosis is clinically desirable. The main aim of this study as our contribution to the PhysioNet/CinC Challenge 2017 was to develop an automatic algorithm for classification of normal sinus rhythm (NSR), AF, other rhythm (O), and noise using a short single-channel ECG. Furthermore, the impact of changing labels/annotations on performance of the proposed algorithm was studied in this article.

APPROACH

The challenge training dataset (8528 ECG recordings) and a complementary dataset (6312 ECG recordings) from other sources were used for algorithm development. Version 3 (v3), which is an updated version of the annotations at the official phase of the challenge (v2), was used in this study. In the proposed algorithm, densely connected convolutional networks were combined with feature-based post-processing after initial signal quality analysis for the classification of ECG recordings.

MAIN RESULTS

The F1 scores for classification of NSR, AF, and O were 0.91, 0.83, and 0.72, respectively, which led to a F1 of 0.82. There was a small or no performance difference between the top entries in the official phase of the challenge and our proposed method. An increase of 2.5% in F1 score was observed when the same annotations for training and test was used (using v3 annotations) compared to using different annotations (v2 annotations for training and v3 annotations for the test).

SIGNIFICANCE

Our promising results suggest that the availability of more data with improved labeling along with improvement in signal quality analysis make our algorithm suitable for practical clinical applications.

Central tendency measure and wavelet transform combined in the non-invasive analysis of atrial fibrillation recordings

Background

Atrial fibrillation (AF) is the most common supraventricular arrhythmia in the clinical practice, being the subject of intensive research.

Methods

The present work introduces two different Wavelet Transform (WT) applications to electrocardiogram (ECG) recordings of patients in AF. The first one predicts spontaneous termination of paroxysmal AF (PAF), whereas the second one deals with the prediction of electrical cardioversion (ECV) outcome in persistent AF patients. In both cases, the central tendency measure (CTM) from the first differences scatter plot was applied to the AF wavelet decomposition. In this way, the wavelet coefficients vector CTM associated to the AF frequency scale was used to assess how atrial fibrillatory (f) waves variability can be related to AF events.

Results

Structural changes into the f waves can be assessed by combining WT and CTM to reflect atrial activity organization variation. This fact can be used to predict organization-related events in AF. To this respect, results in the prediction of PAF termination regarding sensitivity, specificity and accuracy were 100%, 91.67% and 96%, respectively. On the other hand, for ECV outcome prediction, 82.93% sensitivity, 90.91% specificity and 85.71% accuracy were obtained. Hence, CTM has reached the highest diagnostic ability as a single predictor published to date.

Conclusions

Results suggest that CTM can be considered as a promising tool to characterize non-invasive AF signals. In this sense, therapeutic interventions for the treatment of paroxysmal and persistent AF patients could be improved, thus, avoiding useless procedures and minimizing risks.

Atrial fibrillation detection by heart rate variability in Poincare plot

BACKGROUND

Atrial fibrillation (AFib) is one of the prominent causes of stroke, and its risk increases with age. We need to detect AFib correctly as early as possible to avoid medical disaster because it is likely to proceed into a more serious form in short time. If we can make a portable AFib monitoring system, it will be helpful to many old people because we cannot predict when a patient will have a spasm of AFib.

METHODS

We analyzed heart beat variability from inter-beat intervals obtained by a wavelet-based detector. We made a Poincare plot using the inter-beat intervals. By analyzing the plot, we extracted three feature measures characterizing AFib and non-AFib: the number of clusters, mean stepping increment of inter-beat intervals, and dispersion of the points around a diagonal line in the plot. We divided distribution of the number of clusters into two and calculated mean value of the lower part by k-means clustering method. We classified data whose number of clusters is more than one and less than this mean value as non-AFib data. In the other case, we tried to discriminate AFib from non-AFib using support vector machine with the other feature measures: the mean stepping increment and dispersion of the points in the Poincare plot.

RESULTS

We found that Poincare plot from non-AFib data showed some pattern, while the plot from AFib data showed irregularly irregular shape. In case of non-AFib data, the definite pattern in the plot manifested itself with some limited number of clusters or closely packed one cluster. In case of AFib data, the number of clusters in the plot was one or too many. We evaluated the accuracy using leave-one-out cross-validation. Mean sensitivity and mean specificity were 91.4% and 92.9% respectively.

CONCLUSIONS

Because pulse beats of ventricles are less likely to be influenced by baseline wandering and noise, we used the inter-beat intervals to diagnose AFib. We visually displayed regularity of the inter-beat intervals by way of Poincare plot. We tried to design an automated algorithm which did not require any human intervention and any specific threshold, and could be installed in a portable AFib monitoring system.

Constrained temporal extraction of the atrial rhythm in Atrial Fibrillation episodes

The extraction of the Atrial Activity from the Ventricular Activity in Atrial Fibrillation episodes is a must for clinical analysis. We follow the semi Blind Source Extraction S-BSE approach to solve the problem. The proposed algorithm modifies the BSE contrast function to satisfy the prior knowledge about the spectral content of the atrial signal. The introduction of this prior allows obtaining a new algorithm with the following advantages: it allows the extraction of only the atrial component and it improves the quality of the recovered atrial signal in terms of spectral concentration as we show in the results.

Spatial characteristics of atrial fibrillation electrocardiograms

BACKGROUND

The present study investigates spatial properties of atrial fibrillation (AF) by analyzing vectorcardiogram loops synthesized from 12-lead electrocardiograms (ECGs).

METHODS

After atrial signal extraction, spatial properties are characterized through analysis of successive, fixed-length signal segments and expressed in loop orientation, that is, azimuth and elevation, as well as in loop morphology, that is, planarity and planar geometry. It is hypothesized that more organized AF, expressed by a lower AF frequency, is associated with decreased variability in loop morphology. Atrial fibrillation frequency is determined using spectral analysis.

RESULTS

Twenty-six patients with chronic AF were analyzed using 60-second ECG recordings. Loop orientation was similar when determined from either entire 60- or 1-second segments. For 1-second segments, the correlation between AF frequency and the parameters planarity and planar geometry were 0.608 (P < .001) and 0.543 (P < .005), respectively.

CONCLUSIONS

Quantification of AF organization based on AF frequency and spatial characteristics from the ECG is possible. The results suggested a relatively weak coupling between loop morphology and AF frequency when determined from the surface ECG.

Non-linear organization analysis of paroxysmal atrial fibrillation

Atrial fibrillation (AF) is a common supraventricular arrhythmia with episodes that, in the first stages of the disease, may terminate spontaneously. This fact is referred as paroxysmal atrial fibrillation. The analysis of its termination or maintenance could avoid unnecessary therapy and contribute to take the appropriate decisions on its management. The aim of this work is to study if an AF episode terminates spontaneously or not by analyzing the increase of atrial activity (AA) organization prior to AF termination. The organization varies as a consequence of the decrease in the number of reentries into the atrial tissue. The analysis was carried out noninvasively through the use of surface electrocardiogram (ECG) recordings. Sample entropy was selected as non-linear organization index. It was observed that noise and ventricular residues degrade AA organization estimation performance, therefore the use of selective filtering to get the main atrial wave (MAW) was necessary. Using the MAW organization analysis, that is the signal produced by the main reentry wandering the atrial tissue, 46 out of 50 of the terminating and non-terminating analyzed AF episodes were correctly classified (92%). The obtained outcomes allow to conclude that the dominant atrial frequency, and therefore, the main atrial reentry, contains the most relevant information about spontaneous AF termination.

Wavelet bidomain regularity analysis to predict spontaneous termination of atrial fibrillation

Atrial fibrillation (AF) is the most common cardiac arrhythmia. Therefore, the ability to predict if an AF episode terminates spontaneously or not is a challenging clinical problem. This work presents a robust AF prediction methodology carried out by estimating, through regularity indexes, the atrial activity (AA) organization increase prior to AF termination. This regularity variation appears as a consequence of the decrease in the number of reentries into the atrial tissue. AA was obtained from surface ECG recordings using an average QRST template cancellation technique. Wavelet transform (WT) was used in a bidomain way (time and frequency) in order to improve organization estimation. Thereafter, a more robust and reliable classification process for terminating and non-terminating AF episodes was developed making use of two different wavelet decomposition strategies. Finally, the atrial activity organization both in time and wavelet domains (bidomain) was estimated. Trougth the application of this strategy, 96% of the terminating and non-terminating analyzed AF episodes were correctly classified.