Unsupervised Classification of Atrial Electrograms for Electroanatomic Mapping of Human Persistent Atrial Fibrillation

Objective: Ablation treatment for persistent atrial fibrillation (persAF) remains challenging due to the absence of a ‘ground truth’ for atrial substrate characterization and the presence of multiple mechanisms driving the arrhythmia. We implemented an unsupervised classification to identify clusters of atrial electrograms (AEGs) with similar patterns, which were then validated by AEG-derived markers. Methods: 956 bipolar AEGs were collected from 11 persAF patients. CARTO variables (Biosense Webster; ICL, ACI and SCI) were used to create a 3D space, and subsequently used to perform an unsupervised classification with k-means. The characteristics of the identified groups were investigated using nine AEG-derived markers: sample entropy (SampEn), dominant frequency, organization index (OI), determinism, laminarity, recurrence rate (RR), peak-to-peak (PP) amplitude, cycle length (CL), and wave similarity (WS). Results: Five AEG classes with distinct characteristics were identified (F = 582, P<0.0001). The presence of fractionation increased from class 1 to 5, as reflected by the nine markers. Class 1 (25%) included organized AEGs with high WS, determinism, laminarity, and RR, and low SampEn. Class 5 (20%) comprised fractionated AEGs with in low WS, OI, determinism, laminarity, and RR, and in high SampEn. Classes 2 (12%), 3 (13%) and 4 (30%) suggested different degrees of AEG organization. Conclusions: Our results expand and reinterpret the criteria used for automated AEG classification. The nine markers highlighted electrophysiological differences among the five classes found by the k-means, which could provide a more complete characterization of persAF substrate during ablation target identification in future clinical studies.

[1]  M. Chung,et al.  2017 HRS/EHRA/ECAS/APHRS/SOLAECE expert consensus statement on catheter and surgical ablation of atrial fibrillation , 2017, Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology.

[2]  M. Masè,et al.  Computational mapping in atrial fibrillation: how the integration of signal-derived maps may guide the localization of critical sources. , 2014, Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology.

[3]  F. Schlindwein,et al.  Atrial Electrogram Fractionation Distribution before and after Pulmonary Vein Isolation in Human Persistent Atrial Fibrillation—A Retrospective Multivariate Statistical Analysis , 2017, Front. Physiol..

[4]  M. Mansour,et al.  Mother rotors and fibrillatory conduction: a mechanism of atrial fibrillation. , 2002, Cardiovascular research.

[5]  G Hindricks,et al.  Fibrosis in left atrial tissue of patients with atrial fibrillation with and without underlying mitral valve disease , 2004, Heart.

[6]  Edgar Brunner,et al.  Nonparametric Tests in the Unbalanced Multivariate One-Way Design , 2000 .

[7]  Xin Li,et al.  A k-Nearest Neighbours Classifier for Predicting Catheter Ablation Responses Using Noncontact Electrograms During Persistent Atrial Fibrillation , 2018, 2018 Computing in Cardiology Conference (CinC).

[8]  Che Wun Chiou,et al.  Analyzing ECG for cardiac arrhythmia using cluster analysis , 2012, Expert Syst. Appl..

[9]  John Bustamante,et al.  Electroanatomical mapping based on discrimination of electrograms clusters for localization of critical sites in atrial fibrillation. , 2019, Progress in biophysics and molecular biology.

[10]  A. Verma,et al.  Association of Atrial Fibrillation Episode Duration With Arrhythmia Recurrence Following Ablation , 2020, JAMA network open.

[11]  Robert Ploutz-Snyder,et al.  Real-time dominant frequency mapping and ablation of dominant frequency sites in atrial fibrillation with left-to-right frequency gradients predicts long-term maintenance of sinus rhythm. , 2009, Heart rhythm.

[12]  S. Ito,et al.  New tailored approach using a revised assessment of fragmented potentials for persistent atrial fibrillation: Early area defragmentation by modified CFAE module , 2019, Journal of cardiovascular electrophysiology.

[13]  E. Prystowsky,et al.  Single‐center experience of the FIRM technique to ablate paroxysmal and persistent atrial fibrillation , 2019, Journal of cardiovascular electrophysiology.

[14]  Kalyanam Shivkumar,et al.  Long-term clinical outcomes of focal impulse and rotor modulation for treatment of atrial fibrillation: A multicenter experience. , 2016, Heart rhythm.

[15]  K. Node,et al.  Bipolar Voltage Mapping for the Evaluation of Atrial Substrate: Can We Overcome the Challenge of Directionality? , 2019, Journal of atrial fibrillation.

[16]  M. Allessie,et al.  Direct Proof of Endo-Epicardial Asynchrony of the Atrial Wall During Atrial Fibrillation in Humans , 2016, Circulation. Arrhythmia and electrophysiology.

[17]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[18]  Fahim Sufi,et al.  Diagnosis of Cardiovascular Abnormalities From Compressed ECG: A Data Mining-Based Approach , 2009, IEEE Transactions on Information Technology in Biomedicine.

[19]  K. Nademanee,et al.  A new approach for catheter ablation of atrial fibrillation: mapping of the electrophysiologic substrate. , 2004, Journal of the American College of Cardiology.

[20]  D. Haines,et al.  Assessment of Global Atrial Fibrillation Organization to Optimize Timing of Atrial Defibrillation , 2001, Circulation.

[21]  Jürgen Kurths,et al.  Recurrence plots for the analysis of complex systems , 2009 .

[22]  R. Hunter,et al.  Drivers in AF colocate to sites of electrogram organization and rapidity: Potential synergy between spectral analysis and STAR mapping approaches in prioritizing drivers for ablation , 2020, Journal of cardiovascular electrophysiology.

[23]  German Castellanos-Dominguez,et al.  Semi-supervised clustering of fractionated electrograms for electroanatomical atrial mapping , 2016, BioMedical Engineering OnLine.

[24]  Cheng Wen,et al.  Classification of ECG complexes using self-organizing CMAC , 2009 .

[25]  Xin Li,et al.  The temporal behavior and consistency of bipolar atrial electrograms in human persistent atrial fibrillation , 2017, Medical & Biological Engineering & Computing.

[26]  Xin Li,et al.  Unsupervised k-Mean Classification of Atrial Electrograms From Human Persistent Atrial Fibrillation , 2018, 2018 Computing in Cardiology Conference (CinC).

[27]  Elad Anter,et al.  Bipolar voltage amplitude: What does it really mean? , 2016, Heart rhythm.

[28]  J L Cox,et al.  Relationship between local atrial fibrillation interval and refractory period in the isolated canine atrium. , 1996, Circulation.

[29]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[30]  Rajiv Mahajan,et al.  Bipolar Electrogram Shannon Entropy at Sites of Rotational Activation: Implications for Ablation of Atrial Fibrillation , 2013, Circulation. Arrhythmia and electrophysiology.

[31]  N. Kouchoukos,et al.  Characterization of Atrial Fibrillation in Man: Studies Following Open Heart Surgery * , 1978, Pacing and clinical electrophysiology : PACE.

[32]  Kawal S. Rhode,et al.  Towards personalized clinical in-silico modeling of atrial anatomy and electrophysiology , 2012, Medical & Biological Engineering & Computing.

[33]  Alessandro Cristoforetti,et al.  The logical operator map identifies novel candidate markers for critical sites in patients with atrial fibrillation. , 2014, Progress in biophysics and molecular biology.

[34]  Wouter-Jan Rappel,et al.  Treatment of atrial fibrillation by the ablation of localized sources: CONFIRM (Conventional Ablation for Atrial Fibrillation With or Without Focal Impulse and Rotor Modulation) trial. , 2012, Journal of the American College of Cardiology.

[35]  J Clémenty,et al.  Spontaneous initiation of atrial fibrillation by ectopic beats originating in the pulmonary veins. , 1998, The New England journal of medicine.

[36]  L. Faes,et al.  Principal component analysis and cluster analysis for measuring the local organisation of human atrial fibrillation , 2001, Medical and Biological Engineering and Computing.

[37]  Esteban J. Pino,et al.  Clustering of atrial fibrillation based on surface ECG measurements , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[38]  Robert Tibshirani,et al.  Estimating the number of clusters in a data set via the gap statistic , 2000 .

[39]  M. Allessie,et al.  High-density mapping of electrically induced atrial fibrillation in humans. , 1994, Circulation.

[40]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[41]  F. Schlindwein,et al.  Characterization of human persistent atrial fibrillation electrograms using recurrence quantification analysis. , 2018, Chaos.

[42]  M. Allessie,et al.  Configuration of unipolar atrial electrograms during electrically induced atrial fibrillation in humans. , 1997, Circulation.

[43]  B. Knight,et al.  Approaches to catheter ablation of persistent atrial fibrillation. , 2009, Heart rhythm.

[44]  Xin Li,et al.  Minimizing discordances in automated classification of fractionated electrograms in human persistent atrial fibrillation , 2016, Medical & Biological Engineering & Computing.

[45]  Anil A. Bharath,et al.  Rethinking multiscale cardiac electrophysiology with machine learning and predictive modelling , 2018, Comput. Biol. Medicine.

[46]  R. L. Thorndike.  Who belongs in the family? , 1953 .