Li_et_al_EHRA_2019_Classifications_v1.pdf (211.34 kB)
Download file

Machine learning classifiers for predicting catheter ablation responses using non-contact electrograms during persistent atrial fibrillation

Download (211.34 kB)
conference contribution
posted on 19.05.2020, 08:32 by F Schlindwein, X Li, GS Chu, TP Almeida, JL Salinet, AR Mistry, Z Vali, PJ Stafford, FS Schlindwein, GA Ng

Background:

Identification of atrial sites which are effective ablation targets remains challenging in atrial fibrillation (AF) therapy.

Purpose: We thought to test machine learning algorithm in predicting the responses of ablating electrograms (EGMs) and their effect on terminating persistent atrial fibrillation (persAF).

Methods:

A total of 3,206 non-contact electrograms (EGMs) of 51 ablation lesion sites from ten persAF patients undergoing left atrial (LA) catheter ablation (2048-channel Ensite Array) were used as training dataset. AF cycle length (AFCL) changes before and after ablating each LA site were recorded in Labsystem Pro recording system. The EGMs were labelled in four classes by AFCL changes (with 10 ms threshold) after ablation: AF termination; AFCL increase; AFCL unchanged and AFCL decrease. Dominant frequency (DF) and organisation index (OI) were calculated from all EGMs (264 seconds) and used as input features. A group of machine classifiers were trained using the training dataset to predict the ablation response and deployed. 5-fold cross-validation was considered (80% of the data for training; 20% for validation).

Results:

The accuracy of the investigated classifiers was 69.66 % ± 12.60 %. The best performing Fine k-nearest neighbour (KNN) classifier achieved 85.3% of accuracy in the classification of the four classes. For AF termination classification (Area under the curve (AUC) = 0.98) from all four classes, a sensitivity of 87% and a specificity of 98% were achieved, whilst classifying AFCL increase group (AUC = 0.96) resulted in a sensitivity of 84% and a specificity of 92%.

Conclusion:

This work presents a machine learning framework to identify EGMs that are responsible for maintenance of persAF and potential targets for catheter ablation using panoramic non-contact mapping. Supervised learning algorithms on frequency features of long EGMs showed the ability to predict ablation responses measured by AFCL changes and AF termination. Targeting atrial regions with appropriate frequency characteristics might improve ablation outcome in persAF.

History

Citation

EP Europace, Volume 21, Issue Supplement_2, March 2019, Pages ii532–ii719, https://doi.org/10.1093/europace/euz096

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Engineering

Source

Congress of the European Heart Rhythm Association - EHRA2019

Version

AM (Accepted Manuscript)

Published in

EP Europace

Volume

21

Issue

Supplement_2

Pagination

ii532–ii719

Publisher

Oxford University Press (OUP) for European Society of Cardiology (ESC), European Heart Rhythm Association [

eissn

1532-2092

Acceptance date

01/11/2018

Copyright date

2019

Available date

03/05/2019

Publisher version

https://academic.oup.com/europace/article/21/Supplement_2/ii532/5484958

Notes

Abstract only

Spatial coverage

Lisbon, Portugal

Temporal coverage: start date

17/03/2019

Temporal coverage: end date

19/03/2019

Language

en

Usage metrics

Categories

Keywords

Exports