Source Classification in Atrial Fibrillation Using a Machine Learning Approach

Discrimination between normal sinus rhythm (NSR), atrial fibrillation (AF) and atrial flutter (AFL) using the surface electrocardiogram (ECG) through direct Fourier analysis is not effective because ventricular activity (VA) overlaps in frequency with atrial activity (AA) and, moreover, AA frequency components present considerably lower amplitude than VA. This contribution exploits the assumption that AA and VA can be considered as generated by independent sources of cardioelectric activity. Hence, AA free from spurious VA and other disturbances can be extracted through the application of blind source separation (BSS) techniques. After the blind separation and AA identification process, it was applied a logistic regression over a group of spectral parameters extracted from the power spectral density of the AA signal that was able to discriminate between AF, AFL and NSR with a 100% accuracy considering only two spectral parameters.

The analysis and characterization of atrial tachyarrhythmias requires, in a previous step, the extraction of the atrial activity (AA) free from ventricular activity and other artefacts. This contribution adopts the blind source separation (BSS) approach to AA estimation from multilead electrocardiograms (ECGs). Previously proposed BSS methods for AA extraction--e.g., independent component analysis (ICA)--exploit only the spatial diversity introduced by the multiple spatially-separated electrodes. However, AA typically shows certain degree of temporal correlation, with a narrowband spectrum featuring a main frequency peak around 3.5-9 Hz. Taking advantage of this observation, we put forward a novel two-step BSS-based technique which exploits both spatial and temporal information contained in the recorded ECG signals. The spatiotemporal BSS algorithm is validated on simulated and real ECGs from a significant number of atrial fibrillation (AF) and atrial flutter (AFL) episodes, and proves consistently superior to a spatial-only ICA method. In simulated ECGs, a new methodology for the synthetic generation of realistic AF episodes is proposed, which includes a judicious comparison between the known AA content and the estimated AA sources. Using this methodology, the ICA technique obtains correlation indexes of 0.751, whereas the proposed approach obtains a correlation of 0.830 and an error in the estimated signal reduced by a factor of 40%. In real ECG recordings, we propose to measure performance by the spectral concentration (SC) around the main frequency peak. The spatiotemporal algorithm outperforms the ICA method, obtaining a SC of 58.8% and 44.7%, respectively.

Atrial fibrillation is the most common sustained cardiac rhythm disturbance, increasing in prevalence with age. During the past 20 years, there has been a 66% increase in hospital admissions related to atrial fibrillation. Neither the natural history of atrial fibrillation nor its response to therapy is sufficiently predictable from clinical and echocardiographic parameters. Treatment of atrial fibrillation is mainly based on trial and error. Thus, it seems appropriate to develop tests that quantify the state of the disease and guide its management. Standard 12-lead electrocardiogram recordings are commonly required for clinical evaluation. Therefore, possible prognostic information contained within the electrocardiogram provides a great interest. The goal of this thesis is to help clinicians treat atrial fibrillation by developing information from the standard 12-lead electrocardiogram on atrial fibrillation substrates, dynamics, and to predict the success of different treatments. Due to the much higher ventricular activity amplitude, the characterization of atrial fibrillation based on surface electrocardiogram signals requires that the ventricular activity first be cancelled. Average beat subtraction and independent component analysis algorithms are the most frequently used techniques in atrial activity extraction. To solve this problem with the best quality results, five different techniques were studied and compared in the first part of this thesis : the use of two different independent component analysis algorithms, a refined version of the average beat subtraction technique, a novel technique that treats each cardiac cycle in an independent manner, and a novel approach based on the use of atom dictionaries dedicated to atrial and ventricular activities. The performance of these five techniques was evaluated by using simulated and clinical electrocardiogram signals. The simulated signals were created by using models of the atria and the thorax. The refined version of the average beat subtraction technique and the technique that treats each cardiac cycle outperformed the other ones and produced high quality results on all leads. Their main advantage lies in the treatment of the ventricular depolarization and repolarization waves in an independent manner. The second part of this thesis aims at exploring the potential of the clean atrial electrocardiogram signals. So far, the complexity of the electrical atrial activity during atrial fibrillation has mainly been assessed through the analysis of the frequency spectrum or of the time-frequency analysis (spectrogram) of the electrocardiogram signal of lead V1. We propose three different approaches to characterize the atrial fibrillation that exploit the information of multiple leads in various and independent manners. Each of them considers different features that require different signal processing techniques. The first approach is based on clinician's observations on electrocardiograms, to characterize the disorganization of fibrillatory waves. We developed the processing tools to quantify these observations. Based on these clinical features, we were able to predict self-termination of atrial fibrillation with a high accuracy. We also observed an interesting correlation between the increase in the percentage of atrial fibrillations identified as non-terminating and the increase in atrial fibrillation duration. The second approach is based on dominant frequencies observed on multiple electrocardiogram signals. Firstly, two simulated cases were analyzed to understand the correspondence between the dominant frequencies observed on the thorax and the atrial fibrillation dynamics. We observed that multiple lead signals yield more information than a single lead in terms of atrial fibrillation dynamic and that lead V1 and V5 were good candidates for the observation of the left and right atrial dynamics, respectively. In order to obtain accurate dominant frequency estimation on clinical signals that contain ventricular artifacts, a recently introduced signal processing technique was tested. We observed a positive left-to-right dominant frequency gradient preference in the overall atrial fibrillations when a negative gradient preference was to be expected based on other invasive studies. These dominant frequency features also permitted us to obtain a good prediction of the response to pharmacological cardioversion attempts. Our third approach was to extract spatial information from the dipole estimated from body surface potentials. This dipole provides a global representation of the electrical atrial activity. Then, features were used to express the complexity of the atrial fibrillation dynamics. This analysis extracted spatial information that was generally lacking in typical non-invasive atrial fibrillation studies. We observed discrimination between atrial fibrillations with both single and recurrent episodes, characterized by modal and uniform dipole distributions, respectively. This discrimination could link the different atrial fibrillation types to the electrical, contractile, and structural remodelings. This approach permitted us to identify and localize stable and single atrial activity sources in the simulations. We hypothesize that this approach, together with patient's anatomical data, could have the power to help clinicians in ablation procedures ; by helping them to predict where ablation lines can be effective.

The proper analysis and characterization of atrial fibrillation (AF) from surface electrocardiographic (ECG) recordings requires to cancel out the ventricular activity (VA), which is composed of the QRS complex and the T wave. Historically, for single-lead ECGs, the averaged beat subtraction (ABS) has been the most widely used technique. However, this method is very sensitive to QRST wave variations and, moreover, high-quality cancelation templates may be difficult to obtain when only short length and single-lead recordings are available. In order to overcome these limitations, a new QRST cancelation method based on adaptive singular value cancelation (ASVC) applied to each single beat is proposed. In addition, an exhaustive study about the optimal set of complexes for better cancelation of every beat is also presented for the first time. The whole study has been carried out with both simulated and real AF signals. For simulated AF, the cancelation performance was evaluated making use of a cross-correlation index and the normalized mean square error (nmse) between the estimated and the original atrial activity (AA). For real AF signals, two additional new parameters were proposed. First, the ventricular residue (VR) index estimated the presence of ventricular activity in the extracted AA. Second, the similarity (S) evaluated how the algorithm preserved the AA segments out of the QRST interval. Results indicated that for simulated AF signals, mean correlation, nmse, VR and S values were 0.945 ± 0.024, 0.332 ± 0.073, 1.552 ± 0.386 and 0.986 ± 0.012, respectively, for the ASVC method and 0.866 ± 0.042, 0.424 ± 0.120, 2.161 ± 0.564 and 0.922 ± 0.051 for ABS. In the case of real signals, the mean VR and S values were 1.725 ± 0.826 and 0.983 ± 0.038, respectively, for ASVC and 3.159 ± 1.097 and 0.951 ± 0.049 for ABS. Thus, ASVC provides a more accurate beat-to-beat ventricular QRST representation than traditional techniques. As a consequence, VA cancelation is optimized and the AA can be extracted more precisely. Finally, the study has proven that optimal VA cancelation is achieved when a number between 20 and 30 complexes is selected following a correlation-based strategy.

Development of a toolbox for electrocardiogram-based interpretation of atrial fibrillation

Atrial flutter and atrial tachycardia detection using Bayesian approach with high resolution time–frequency spectrum from ECG recordings

Atrial fibrillation is the most prevalent sustained cardiac arrhythmia encountered by clinicians. This trouble is characterized by a persisting uncoordinated atrial electrical activation, which results in a inefficient atrial mechanical function and long-term risks of stroke. Despite its incidence and risks of serious complications, the electrophysiologicalmechanisms causing AF are not yet well understood. In clinical practice, AF is mainly diagnosed on the surface electrocardiogram (ECG), where the atrial and ventricular activities appear as a linear superposition of potential fields. This renders the evaluation of the atrial activity a complex task, and calls for the design of suitable signal processing techniques for atrial activity estimation in the ECG. This chapter presents some recent advances in the estimation of atrial activity exploiting the spatial diversity of the standard ECG. We first stress the relation between the electrophysiological activity of the heart and the potential field measured by the cutaneous electrodes, including the standard linear approximation of the bioelectrical field produced by a physiological source. This connection naturally leads to the notion of source topographies and spatial filtering. Given the surface electrode recordings, spatial filters aim to isolate the potential fields of the distinct sources by means of suitable linear combination of the lead outputs. We focus on how the estimation of spatial filters is typically handled in a blind or semi-blind context. This forms the basis for the presentation of recently proposed algorithms in the estimation of atrial activity. While benefiting from prior information about the atrial activity, the proposed algorithms keep their generality so that they can be used in a wide range of electrocardiogram recordings.

Atrial fibrillation (AF) is the most frequent cardiac arrhythmia diagnosed in clinical practice, identified by an uncoordinated and irregular atrial depolarization. However, its electrophysiological mechanisms are still not clearly understood, increasing the intensive clinical research into this challenging cardiac condition in the past few years. The noninvasive extraction of the atrial activity (AA) from multi-lead electrocardiogram (ECG) recordings by signal processing techniques has helped in better understanding this complex arrhythmia. In particular, tensor decomposition techniques have proven to be powerful tools in this task, overcoming the limitations of matrix factorization methods. Exploring the spatial as well as the temporal diversity of ECG recordings, this contribution puts forward a novel noninvasive AA extraction method that models consecutive AF ECG segments as a coupled block-term tensor decomposition, assuming that they share the same spatial signatures. Experiments on synthetic and real data, the latter acquired from persistent AF patients, validate the proposed coupled tensor approach, which provides satisfactory performance with reduced computational cost.

A novel application of sample entropy to the electrocardiogram of atrial fibrillation

The analysis and characterization of atrial tachyarrhythmias requires the previous estimation of the atrial activity (AA) free from any ventricular activity and other artefacts. This contribution considers a blind source separation (BSS) model to separate the AA from multilead electrocardiograms (ECGs). Previously proposed BSS methods for AA extraction exploit only the spatial diversity introduced by the multiple electrodes. However, AA typically shows certain degree of temporal correlation, featuring a narrowband spectrum. Taking advantage of this observation, we put forward a novel two-step BSS-based technique which exploits both spatial and temporal information. The spatiotemporal BSS algorithm is validated on real ECGs from a significant number of patients, and proves consistently superior to a spatial-only ICA method. In real ECG recordings, performance can be measured by the main frequency peak and the spectral concentration. The spatiotemporal algorithm outperforms the ICA method, obtaining a spectral concentration of 58.8% and 44.7%, respectively.KeywordsIndependent Component AnalysisBlind Source SeparationAtrial ArrhythmiaAtrial ActivitySpectral ConcentrationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Arrhythmia is not uncommon in the etiology of syncope which mimics epilepsy. Data about the epilepsy induced vagal tonus abnormalities have being increasingly reported. So we aimed to evaluate what a neurologist may gain by a simultaneous electrocardiogram (ECG) and electroencephalogram (EEG) recording in the patients who underwent EEG testing due to prediagnosis of epilepsy. We retrospectively evaluated and detected ECG abnormalities in 68 (18%) of 376 patients who underwent EEG testing. A minimum of 20 of minutes artifact-free recording were required for each patient. Standard 1-channel ECG was simultaneously recorded in conjunction with the EEG. In all, 28% of females and 14% of males had ECG abnormalities. Females (mean age 49 years, range 18-88 years) were older compared with the male group (mean age 28 years, range 16-83 years). Atrial fibrillation was more frequent in female group whereas bradycardia and respiratory sinus arrhythmia was higher in male group. One case had been detected a critical asystole indicating sick sinus syndrome in the female group and treated with a pacemaker implantation in the following period. Simultaneous ECG recording in conjunction with EEG testing is a clinical prerequisite to detect and to clarify the coexisting ECG and EEG abnormalities and their clinical relevance. Potentially rare lethal causes of syncope that mimic seizure or those that could cause resistance to antiepileptic therapy could effectively be distinguished by detecting ECG abnormalities coinciding with the signs and abnormalities during EEG recording.

Early reports suggested that some patients with "atrial fibrillation/flutter" might have atrial fibrillation in one atrium and atrial flutter in the other. However, more recent conceptions of atrial fibrillation/flutter postulate that the pattern is due to a relatively organized (type I) form of atrial fibrillation. We report the occurrence and ECG manifestations of simultaneous atrial fibrillation and flutter in patients undergoing attempted catheter ablation of atrial flutter. In patients undergoing radiofrequency ablation for atrial flutter, an attempt was made to entrain atrial flutter by pacing in the right atrium. The arrhythmias observed occurred following attempts at entrainment, or spontaneously in one case. Twelve transient episodes of simultaneous atrial fibrillation and flutter were observed in five patients. The atrial fibrillation was localized to all or a portion of one atrium, during which the other atrium maintained atrial flutter. In each case, the surface 12-lead ECG reflected the right atrial activation pattern. No patients had interatrial or intra-atrial conduction block during sinus rhythm, suggesting functional intra-atrial block as a mechanism for simultaneous atrial fibrillation/flutter. In certain patients, the occurrence of transient, simultaneous atrial fibrillation and flutter is possible. In contrast to prior studies in which it was suggested that left atrial or septal activation determines P wave morphology, the results of the present study show that P wave morphology is determined by right atrial activation. Functional interatrial block appears to be a likely mechanism for this phenomenon.

Measurement and Rate Correction of the QT Interval

Different patterns of atrial activation in idiopathic atrial fibrillation: simultaneous multisite atrial mapping in patients with paroxysmal and chronic atrial fibrillation

In the field of camera-based photoplethysmography the application of blind source separation (BSS) techniques has extensively stressed to cope with frequently occurring artifacts and noise. Although said techniques can help to extract the cardiac component from a mixture of input sources, permutation indeterminacy inherit to BSS techniques often introduces inaccuracies or requires manual intervention. The current contribution focuses on methods to automatically select the cardiac component from the output of BSS techniques applied to camera-based photoplethysmograms. To that end, we propose simple Markov models to describe and subsequently identify cardiac components. It is shown that good results can be obtained by combining different simple Markov models.