An automatic system for the analysis and classification of human atrial fibrillation patterns from intracardiac electrograms

A Divergence-Based Approach for the Identification of Atrial Fibrillation Focal Drivers From Multipolar Mapping: A Computational Study

The expanding role of catheter ablation of atrial fibrillation (AF) has stimulated the development of novel mapping strategies to guide the procedure. We introduce a novel approach to characterize wave propagation and identify AF focal drivers from multipolar mapping data. The method reconstructs continuous activation patterns in the mapping area by a radial basis function (RBF) interpolation of multisite activation time series. Velocity vector fields are analytically determined, and the vector field divergence is used as a marker of focal drivers. The method was validated in a tissue patch cellular automaton model and in an anatomically realistic left atrial (LA) model with Courtemanche-Ramirez-Nattel ionic dynamics. Divergence analysis was effective in identifying focal drivers in a complex simulated AF pattern. Localization was reliable even with consistent reduction (47%) in the number of mapping points and in the presence of activation time misdetections (noise <10% of the cycle length). Proof-of-concept application of the method to human AF mapping data showed that divergence analysis consistently detected focal activation in the pulmonary veins and LA appendage area. These results suggest the potential of divergence analysis in combination with multipolar mapping to identify AF critical sites. Further studies on large clinical datasets may help to assess the clinical feasibility and benefit of divergence analysis for the optimization of ablation treatment.

Short-Time Estimation of Fractionation in Atrial Fibrillation with Coarse-Grained Correlation Dimension for Mapping the Atrial Substrate

Atrial fibrillation (AF) is currently the most common cardiac arrhythmia, with catheter ablation (CA) of the pulmonary veins (PV) being its first line therapy. Ablation of complex fractionated atrial electrograms (CFAEs) outside the PVs has demonstrated improved long-term results, but their identification requires a reliable electrogram (EGM) fractionation estimator. This study proposes a technique aimed to assist CA procedures under real-time settings. The method has been tested on three groups of recordings: Group 1 consisted of 24 highly representative EGMs, eight of each belonging to a different AF Type. Group 2 contained the entire dataset of 119 EGMs, whereas Group 3 contained 20 pseudo-real EGMs of the special Type IV AF. Coarse-grained correlation dimension (CGCD) was computed at epochs of 1 s duration, obtaining a classification accuracy of 100% in Group 1 and 84.0–85.7% in Group 2, using 10-fold cross-validation. The receiver operating characteristics (ROC) analysis for highly fractionated EGMs, showed 100% specificity and sensitivity in Group 1 and 87.5% specificity and 93.6% sensitivity in Group 2. In addition, 100% of the pseudo-real EGMs were correctly identified as Type IV AF. This method can consistently express the fractionation level of AF EGMs and provides better performance than previous works. Its ability to compute fractionation in short-time can agilely detect sudden changes of AF Types and could be used for mapping the atrial substrate, thus assisting CA procedures under real-time settings for atrial substrate modification.

Spiral waves characterization: Implications for an automated cardiodynamic tissue characterization

BACKGROUND AND OBJECTIVE

Spiral waves are phenomena observed in cardiac tissue especially during fibrillatory activities. Spiral waves are revealed through in-vivo and in-vitro studies using high density mapping that requires special experimental setup. Also, in-silico spiral wave analysis and classification is performed using membrane potentials from entire tissue. In this study, we report a characterization approach that identifies spiral wave behaviors using intracardiac electrogram (EGM) readings obtained with commonly used multipolar diagnostic catheters that perform localized but high-resolution readings. Specifically, the algorithm is designed to distinguish between stationary, meandering, and break-up rotors.

METHODS

The clustering and classification algorithms are tested on simulated data produced using a phenomenological 2D model of cardiac propagation. For EGM measurements, unipolar-bipolar EGM readings from various locations on tissue using two catheter types are modeled. The distance measure between spiral behaviors are assessed using normalized compression distance (NCD), an information theoretical distance. NCD is a universal metric in the sense it is solely based on compressibility of dataset and not requiring feature extraction. We also introduce normalized FFT distance (NFFTD) where compressibility is replaced with a FFT parameter.

RESULTS

Overall, outstanding clustering performance was achieved across varying EGM reading configurations. We found that effectiveness in distinguishing was superior in case of NCD than NFFTD. We demonstrated that distinct spiral activity identification on a behaviorally heterogeneous tissue is also possible.

CONCLUSIONS

This report demonstrates a theoretical validation of clustering and classification approaches that provide an automated mapping from EGM signals to assessment of spiral wave behaviors and hence offers a potential mapping and analysis framework for cardiac tissue wavefront propagation patterns.

Inflection point analysis: A machine learning approach for extraction of IEGM active intervals during atrial fibrillation

OBJECTIVE

In this paper, we propose a novel algorithm to extract the active intervals of intracardiac electrograms during atrial fibrillation.

METHODS

First, we show that the characteristics of the signal waveform at its inflection points are prominent features that are implicitly used by human annotators for distinguishing between active and inactive intervals of IEGMs. Then, we show that the natural logarithm of features corresponding to active and inactive intervals exhibits a mixture of two Gaussian distributions in three dimensional feature space. An Expectation Maximization algorithm for Gaussian mixtures is then applied for automatic clustering of the features into two categories.

RESULTS

The absolute error in onset and offset estimation of active intervals is 6.1ms and 10.7ms, respectively, guaranteeing a high resolution. The true positive rate for the proposed method is also 98.1%, proving the high reliability.

CONCLUSION

The proposed method can extract the active intervals of IEGMs during AF with a high accuracy and resolution close to manually annotated results.

SIGNIFICANCE

In contrast with some of the conventional methods, no windowing technique is required in our approach resulting in significantly higher resolution in estimating the onset and offset of active intervals. Furthermore, since the signal characteristics at inflection points are analyzed instead of signal samples, the computational time is significantly low, ensuring the real-time application of our algorithm. The proposed method is also robust to noise and baseline variations thanks to the Laplacian of Gaussian filter employed for extraction of inflection points.

Waveform Integrity in Atrial Fibrillation: The Forgotten Issue of Cardiac Electrophysiology

Atrial fibrillation (AF) is the most common arrhythmia in clinical practice with an increasing prevalence of about 15% in the elderly. Despite other alternatives, catheter ablation is currently considered as the first-line therapy for the treatment of AF. This strategy relies on cardiac electrophysiology systems, which use intracardiac electrograms (EGM) as the basis to determine the cardiac structures contributing to sustain the arrhythmia. However, the noise-free acquisition of these recordings is impossible and they are often contaminated by different perturbations. Although suppression of nuisance signals without affecting the original EGM pattern is essential for any other later analysis, not much attention has been paid to this issue, being frequently considered as trivial. The present work introduces the first thorough study on the significant fallout that regular filtering, aimed at reducing acquisition noise, provokes on EGM pattern morphology. This approach has been compared with more refined denoising strategies. Performance has been assessed both in time and frequency by well established parameters for EGM characterization. The study comprised synthesized and real EGMs with unipolar and bipolar recordings. Results reported that regular filtering altered substantially atrial waveform morphology and was unable to remove moderate amounts of noise, thus turning time and spectral characterization of the EGM notably inaccurate. Methods based on Wavelet transform provided the highest ability to preserve EGM morphology with improvements between 20 and beyond 40%, to minimize dominant atrial frequency estimation error with up to 25% reduction, as well as to reduce huge levels of noise with up to 10 dB better reduction. Consequently, these algorithms are recommended as a replacement of regular filtering to avoid significant alterations in the EGMs. This could lead to more accurate and truthful analyses of atrial activity dynamics aimed at understanding and locating the sources of AF.

Fuzzy decision tree to classify complex fractionated atrial electrograms

Catheter ablation has emerged as an effective treatment strategy for atrial fibrillation (AF) in recent years. During AF, complex fractionated atrial electrograms (CFAE) can be recorded and are known to be a potential target for ablation. Automatic algorithms have been developed to simplify CFAE detection, but they are often based on a single descriptor or a set of descriptors in combination with sharp decision classifiers. However, these methods do not reflect the progressive transition between CFAE classes. The aim of this study was to develop an automatic classification algorithm, which combines the information of a complete set of descriptors and allows for progressive and transparent decisions. We designed a method to automatically analyze CFAE based on a set of descriptors representing various aspects, such as shape, amplitude and temporal characteristics. A fuzzy decision tree (FDT) was trained and evaluated on 429 predefined electrograms. CFAE were classified into four subgroups with a correct rate of 81±3%. Electrograms with continuous activity were detected with a correct rate of 100%. In addition, a percentage of certainty is given for each electrogram to enable a comprehensive and transparent decision. The proposed FDT is able to classify CFAE with respect to their progressive transition and may allow objective and reproducible CFAE interpretation for clinical use.

Fractionated electrograms and rotors detection in chronic atrial fibrillation using model-based clustering

The identification of atrial fibrillation (AF) substrates is needed to improve ablation therapy guided by electrograms, although mechanisms that sustain AF are not fully understood. Detection of complex fractionated atrial electrograms (CFAE) is used for this purpose. Nonetheless, efficacy of this method is inadequate in the case of chronic AF. Recent hypothesis proposes the rotors as fibrillatory substrate. Novel approaches seek to relate CFAE with rotor; nevertheless, such methods are not able to identify the associated substrate. Furthermore, the patterns that characterize CFAE generated by rotors remain unknown. Thus, tracking of rotors is an unsolved issue. In this paper, we propose a non-supervised method to find patterns associated with fibrillatory substrates in chronic AF. We extracted two features based on local activation wave detection and one feature based on non-linear dynamics. Gaussian mixture model-based clustering was used to discriminate CFAE patterns. Resulting clusters are visualized in an electroanatomic map. We assessed the proposed method in a real database labeled according to the level of fractionation and in a simulated episode of chronic AF in which a rotor was detected. Our results indicate that the method proposed can separate different levels of fractionation in CFAE, and provide evidence that clustering can be used to locate the vortex of the rotors. Provided approach can support ablation therapy procedures by means of CFAE patterns discrimination.

Semi-supervised clustering of fractionated electrograms for electroanatomical atrial mapping

BACKGROUND

Electrogram-guided ablation procedures have been proposed as an alternative strategy consisting of either mapping and ablating focal sources or targeting complex fractionated electrograms in atrial fibrillation (AF). However, the incomplete understanding of the mechanism of AF makes difficult the decision of detecting the target sites. To date, feature extraction from electrograms is carried out mostly based on the time-domain morphology analysis and non-linear features. However, their combination has been reported to achieve better performance. Besides, most of the inferring approaches applied for identifying the levels of fractionation are supervised, which lack of an objective description of fractionation. This aspect complicates their application on EGM-guided ablation procedures.

METHODS

This work proposes a semi-supervised clustering method of four levels of fractionation. In particular, we make use of the spectral clustering that groups a set of widely used features extracted from atrial electrograms. We also introduce a new atrial-deflection-based feature to quantify the fractionated activity. Further, based on the sequential forward selection, we find the optimal subset that provides the highest performance in terms of the cluster validation. The method is tested on external validation of a labeled database. The generalization ability of the proposed training approach is tested to aid semi-supervised learning on unlabeled dataset associated with anatomical information recorded from three patients.

RESULTS

A joint set of four extracted features, based on two time-domain morphology analysis and two non-linear dynamics, are selected. To discriminate between four considered levels of fractionation, validation on a labeled database performs a suitable accuracy (77.6 %). Results show a congruence value of internal validation index among tested patients that is enough to reconstruct the patterns over the atria to located critical sites with the benefit of avoiding previous manual classification of AF types.

CONCLUSIONS

To the best knowledge of the authors, this is the first work reporting semi-supervised clustering for distinguishing patterns in fractionated electrograms. The proposed methodology provides high performance for the detection of unknown patterns associated with critical EGM morphologies. Particularly, obtained results of semi-supervised training show the advantage of demanding fewer labeled data and less training time without significantly compromising accuracy. This paper introduces a new method, providing an objective scheme that enables electro-physiologist to recognize the diverse EGM morphologies reliably.

Comparative assessment of nonlinear metrics to quantify organization-related events in surface electrocardiograms of atrial fibrillation

Atrial fibrillation (AF) is today the most common sustained arrhythmia, its treatment being not completely satisfactory. Electrical activity organization analysis within the atria could play a key role in the improvement of current AF therapies. The application of a nonlinear regularity index, such as sample entropy (SampEn), to the atrial activity (AA) fundamental waveform has proven to be a successful noninvasive AF organization estimator. However, the use of alternative nonlinear metrics within this context is a pending issue. The present work analyzes the ability of several nonlinear indices to assess regularity of patterns and, thus, organization, in the AA signal and its fundamental waveform, defined as the main atrial wave (MAW). Precisely, Fuzzy Entropy, Spectral Entropy, Lempel-Ziv Complexity and Hurst Exponents were studied, achieving more robust and accurate AF organization estimates than SampEn. Results also provided better AF organization estimates from the MAW than from the AA signal for all the tested nonlinear metrics, which agrees with previous works only focused on SampEn. Furthermore, some of these indices reported a discriminant ability close to 95% in the classification of AF organization-dependent events, thus outperforming the diagnostic accuracy of SampEn and other widely used noninvasive estimators, such as the dominant atrial frequency (DAF). As a conclusion, these nonlinear metrics could be considered as promising estimators of noninvasive AF organization and could be helpful in making appropriate decisions on the patients' management.

Dynamic time warping applied to estimate atrial fibrillation temporal organization from the surface electrocardiogram

Atrial fibrillation (AF) is the most commonly diagnosed arrhythmia in clinical practice. However, the mechanisms responsible for its induction and maintenance still are not fully understood. To this respect, analysis of the electrical activity organization within the atria could play an important role in their proper interpretation. Although many algorithms to quantify AF organization from invasive electrograms can be found in the literature, a reduced number of indirect estimators from the standard ECG have been proposed to date. Furthermore, these surface methods can only yield a global AF organization assessment, blurring the possible information that each individual fibrillatory (f) wave may provide. To this respect, the present manuscript proposes a novel method for direct and short-time AF organization estimation from single-lead surface ECG recordings. Through the computation of morphological variations among f waves, the temporal arrhythmia organization is estimated. The f waves are individually extracted and delineated from the atrial activity signal, making use of a dynamic time warping approach. The proposed algorithm was tested on real AF surface recordings in order to discriminate atrial signals with different organization degrees, obtaining a diagnostic accuracy higher than 88%. In addition, its performance was validated by comparison with two temporal organization measures from invasive unipolar electrograms of both atria, providing statistically significant linear correlations between invasive and non-invasive estimates. As a consequence, new standpoints are opened through this work in the non-invasive analysis of AF, where the individualized study of each f wave could assess short-time AF organization, would improve the understanding of AF mechanisms and become useful for its clinical treatment.

Identification of recurring patterns in fractionated atrial electrograms using new transform coefficients

Background

Identification of recurrent patterns in complex fractionated atrial electrograms (CFAE) has been used to differentiate paroxysmal from persistent atrial fibrillation (AF). Detection of the atrial CFAE patterns might therefore be assistive in guiding radiofrequency catheter ablation to drivers of the arrhythmia. In this study a technique for robust detection and classification of recurrent CFAE patterns is described.

Method

CFAE were obtained from the four pulmonary vein ostia, and from the anterior and posterior left atrium, in 10 patients with paroxysmal AF and 10 patients with longstanding persistent AF (216 recordings in total). Sequences 8.4 s in length were analyzed (8,192 sample points, 977 Hz sampling). Among the 216 sequences, two recurrent patterns A and B were substituted for 4 and 5 of the sequences, respectively. To this data, random interference, and random interference + noise were separately added. Basis vectors were constructed using a new transform that is derived from ensemble averaging. Patterns A and B were then detected and classified using a threshold level of Euclidean distance between spectral signatures as constructed with transform coefficients.

Results

In the presence of interference, sensitivity to detect and distinguish two patterns A and B was 96.2%, while specificity to exclude nonpatterns was 98.0%. In the presence of interference + noise, sensitivity was 89.1% while specificity was 97.0%.

Conclusions

Transform coefficients computed from ensemble averages can be used to succinctly quantify synchronized patterns present in AF data. The technique is useful to automatically detect recurrent patterns in CFAE that are embedded in interference without user bias. This quantitation can be implemented in real-time to map the AF substrate prior to and during catheter ablation.