Validation of a Machine Learning Algorithm to Identify Pulmonary Vein Isolation During Ablation Procedures for the Treatment of Atrial Fibrillation: Results of the PVISION Study

Overview

Journal Europace

Publisher Oxford University Press

Specialties Cardiology & Vascular Diseases
Physiology

Date 2024 Apr 29

PMID 38682165

Authors

Jan De Pooter

Liesbeth Timmers

Serge Boveda

Stephane Combes

Sebastien Knecht

Alexandre Almorad

Carlos De Asmundis

Mattias Duytschaever

Affiliations

Soon will be listed here.

Abstract

Aims: Pulmonary vein isolation (PVI) is the cornerstone of ablation for atrial fibrillation. Confirmation of PVI can be challenging due to the presence of far-field electrograms (EGMs) and sometimes requires additional pacing manoeuvres or mapping. This prospective multicentre study assessed the agreement between a previously trained automated algorithm designed to determine vein isolation status with expert opinion in a real-world clinical setting.

Methods And Results: Consecutive patients scheduled for PVI were recruited at four centres. The ECGenius electrophysiology (EP) recording system (CathVision ApS, Copenhagen, Denmark) was connected in parallel with the existing system in the laboratory. Electrograms from a circular mapping catheter were annotated during sinus rhythm at baseline pre-ablation, time of isolation, and post-ablation. The ground truth for isolation status was based on operator opinion. The algorithm was applied to the collected PV signals off-line and compared with expert opinion. The primary endpoint was a sensitivity and specificity exceeding 80%. Overall, 498 EGMs (248 at baseline and 250 at PVI) with 5473 individual PV beats from 89 patients (32 females, 62 ± 12 years) were analysed. The algorithm performance reached an area under the curve (AUC) of 92% and met the primary study endpoint with a sensitivity and specificity of 86 and 87%, respectively (P = 0.005; P = 0.004). The algorithm had an accuracy rate of 87% in classifying the time of isolation.

Conclusion: This study validated an automated algorithm using machine learning to assess the isolation status of pulmonary veins in patients undergoing PVI with different ablation modalities. The algorithm reached an AUC of 92%, with both sensitivity and specificity exceeding the primary study endpoints.

References

Wilber D, Pappone C, Neuzil P, de Paola A, Marchlinski F, Natale A . Comparison of antiarrhythmic drug therapy and radiofrequency catheter ablation in patients with paroxysmal atrial fibrillation: a randomized controlled trial. JAMA. 2010; 303(4):333-40. DOI: 10.1001/jama.2009.2029. View

Reddy V, Sediva L, Petru J, Skoda J, Chovanec M, Chitovova Z . Durability of Pulmonary Vein Isolation with Cryoballoon Ablation: Results from the Sustained PV Isolation with Arctic Front Advance (SUPIR) Study. J Cardiovasc Electrophysiol. 2015; 26(5):493-500. DOI: 10.1111/jce.12626. View

Sroubek J, Rottmann M, Barkagan M, Leshem E, Shapira-Daniels A, Brem E . A novel octaray multielectrode catheter for high-resolution atrial mapping: Electrogram characterization and utility for mapping ablation gaps. J Cardiovasc Electrophysiol. 2019; 30(5):749-757. DOI: 10.1111/jce.13867. View

Dukkipati S, Neuzil P, Kautzner J, Petru J, Wichterle D, Skoda J . The durability of pulmonary vein isolation using the visually guided laser balloon catheter: multicenter results of pulmonary vein remapping studies. Heart Rhythm. 2012; 9(6):919-25. DOI: 10.1016/j.hrthm.2012.01.019. View

Schlageter V, Badertscher P, Luca A, Krisai P, Spies F, Kueffer T . A single-beat algorithm to discriminate farfield from nearfield bipolar voltage electrograms from the pulmonary veins. J Interv Card Electrophysiol. 2023; 66(9):2047-2054. PMC: 10694100. DOI: 10.1007/s10840-023-01535-7. View

Reddy V, Neuzil P, Koruth J, Petru J, Funosako M, Cochet H . Pulsed Field Ablation for Pulmonary Vein Isolation in Atrial Fibrillation. J Am Coll Cardiol. 2019; 74(3):315-326. DOI: 10.1016/j.jacc.2019.04.021. View

De Pooter J, Phlips T, El Haddad M, Van Heuverswyn F, Timmers L, Tavernier R . Automated verification of pulmonary vein isolation in radiofrequency- and cryoballoon-guided ablation. Pacing Clin Electrophysiol. 2017; 40(7):779-787. DOI: 10.1111/pace.13121. View

Packer D, Kowal R, Wheelan K, Irwin J, Champagne J, Guerra P . Cryoballoon ablation of pulmonary veins for paroxysmal atrial fibrillation: first results of the North American Arctic Front (STOP AF) pivotal trial. J Am Coll Cardiol. 2013; 61(16):1713-23. DOI: 10.1016/j.jacc.2012.11.064. View

Nery P, Belliveau D, Nair G, Bernick J, Redpath C, Szczotka A . Relationship Between Pulmonary Vein Reconnection and Atrial Fibrillation Recurrence: A Systematic Review and Meta-Analysis. JACC Clin Electrophysiol. 2018; 2(4):474-483. DOI: 10.1016/j.jacep.2016.02.003. View

10.

Yamane T, Shah D, Jais P, Hocini M M, Deisenhofer I, Choi K . Electrogram polarity reversal as an additional indicator of breakthroughs from the left atrium to the pulmonary veins. J Am Coll Cardiol. 2002; 39(8):1337-44. DOI: 10.1016/s0735-1097(02)01782-5. View

11.

Park C, Lehrmann H, Keyl C, Weber R, Schiebeling J, Allgeier J . Mechanisms of pulmonary vein reconnection after radiofrequency ablation of atrial fibrillation: the deterministic role of contact force and interlesion distance. J Cardiovasc Electrophysiol. 2014; 25(7):701-8. DOI: 10.1111/jce.12396. View

12.

Hygrell T, Viberg F, Dahlberg E, Charlton P, Kemp Gudmundsdottir K, Mant J . An artificial intelligence-based model for prediction of atrial fibrillation from single-lead sinus rhythm electrocardiograms facilitating screening. Europace. 2023; 25(4):1332-1338. PMC: 10105867. DOI: 10.1093/europace/euad036. View

13.

Asirvatham S . Pulmonary vein-related maneuvers: part I. Heart Rhythm. 2007; 4(4):538-44. DOI: 10.1016/j.hrthm.2007.01.010. View

14.

El Haddad M, Houben R, Berte B, Van Heuverswyn F, Stroobandt R, Vandekerckhove Y . Bipolar electrograms characteristics at the left atrial-pulmonary vein junction: Toward a new algorithm for automated verification of pulmonary vein isolation. Heart Rhythm. 2014; 12(1):21-31. DOI: 10.1016/j.hrthm.2014.08.030. View

15.

Shade J, Ali R, Basile D, Popescu D, Akhtar T, Marine J . Preprocedure Application of Machine Learning and Mechanistic Simulations Predicts Likelihood of Paroxysmal Atrial Fibrillation Recurrence Following Pulmonary Vein Isolation. Circ Arrhythm Electrophysiol. 2020; 13(7):e008213. PMC: 7375930. DOI: 10.1161/CIRCEP.119.008213. View

16.

Budzianowski J, Hiczkiewicz J, Burchardt P, Pieszko K, Rzezniczak J, Budzianowski P . Predictors of atrial fibrillation early recurrence following cryoballoon ablation of pulmonary veins using statistical assessment and machine learning algorithms. Heart Vessels. 2018; 34(2):352-359. PMC: 6510876. DOI: 10.1007/s00380-018-1244-z. View

17.

Svennberg E, Caiani E, Bruining N, Desteghe L, Han J, Narayan S . The digital journey: 25 years of digital development in electrophysiology from an Europace perspective. Europace. 2023; 25(8). PMC: 10450797. DOI: 10.1093/europace/euad176. View

18.

Shah D, Haissaguerre M, Jais P, Hocini M, Yamane T, Macle L . Left atrial appendage activity masquerading as pulmonary vein potentials. Circulation. 2002; 105(24):2821-5. DOI: 10.1161/01.cir.0000021596.01916.35. View

19.

Providencia R, Defaye P, Lambiase P, Pavin D, Cebron J, Halimi F . Results from a multicentre comparison of cryoballoon vs. radiofrequency ablation for paroxysmal atrial fibrillation: is cryoablation more reproducible?. Europace. 2016; 19(1):48-57. DOI: 10.1093/europace/euw080. View

20.

Hindricks G, Potpara T, Dagres N, Arbelo E, Bax J, Blomstrom-Lundqvist C . 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): The Task Force for the diagnosis and management of atrial fibrillation of the.... Eur Heart J. 2020; 42(5):373-498. DOI: 10.1093/eurheartj/ehaa612. View