Imperial College London
Alternate

DrZacharyWhinnett

Faculty of Medicine, National Heart & Lung Institute

Reader in Cardiac Electrophysiology
 
 
 
//

Contact

 

z.whinnett

 
 
//

Location

 

South- NHLI Cardiovascular ScienceBlock B Hammersmith HospitalHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Sau:2022:ehjdh/ztac042,
author = {Sau, A and Ibrahim, S and Ahmed, A and Handa, B and Kramer, DB and Waks, JW and Arnold, AD and Howard, JP and Qureshi, N and Koa-Wing, M and Keene, D and Malcolme-Lawes, L and Lefroy, DC and Linton, NWF and Lim, PB and Varnava, A and Whinnett, ZI and Kanagaratnam, P and Mandic, D and Peters, NS and Ng, FS},
doi = {ehjdh/ztac042},
journal = {European Heart Journal – Digital Health},
pages = {405--414},
title = {Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms},
url = {http://dx.doi.org/10.1093/ehjdh/ztac042},
volume = {3},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Aims:Accurately determining atrial arrhythmia mechanisms from a 12-lead electrocardiogram (ECG) can be challenging. Given the high success rate of cavotricuspid isthmus (CTI) ablation, identification of CTI-dependent typical atrial flutter (AFL) is important for treatment decisions and procedure planning. We sought to train a convolutional neural network (CNN) to classify CTI-dependent AFL vs. non-CTI dependent atrial tachycardia (AT), using data from the invasive electrophysiology (EP) study as the gold standard.Methods and results:We trained a CNN on data from 231 patients undergoing EP studies for atrial tachyarrhythmia. A total of 13 500 five-second 12-lead ECG segments were used for training. Each case was labelled CTI-dependent AFL or non-CTI-dependent AT based on the findings of the EP study. The model performance was evaluated against a test set of 57 patients. A survey of electrophysiologists in Europe was undertaken on the same 57 ECGs. The model had an accuracy of 86% (95% CI 0.77–0.95) compared to median expert electrophysiologist accuracy of 79% (range 70–84%). In the two thirds of test set cases (38/57) where both the model and electrophysiologist consensus were in agreement, the prediction accuracy was 100%. Saliency mapping demonstrated atrial activation was the most important segment of the ECG for determining model output.Conclusion:We describe the first CNN trained to differentiate CTI-dependent AFL from other AT using the ECG. Our model matched and complemented expert electrophysiologist performance. Automated artificial intelligence-enhanced ECG analysis could help guide treatment decisions and plan ablation procedures for patients with organized atrial arrhythmias.
AU  - Sau,A
AU  - Ibrahim,S
AU  - Ahmed,A
AU  - Handa,B
AU  - Kramer,DB
AU  - Waks,JW
AU  - Arnold,AD
AU  - Howard,JP
AU  - Qureshi,N
AU  - Koa-Wing,M
AU  - Keene,D
AU  - Malcolme-Lawes,L
AU  - Lefroy,DC
AU  - Linton,NWF
AU  - Lim,PB
AU  - Varnava,A
AU  - Whinnett,ZI
AU  - Kanagaratnam,P
AU  - Mandic,D
AU  - Peters,NS
AU  - Ng,FS
DO  - ehjdh/ztac042
EP  - 414
PY  - 2022///
SN  - 2634-3916
SP  - 405
TI  - Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms
T2  - European Heart Journal – Digital Health
UR  - http://dx.doi.org/10.1093/ehjdh/ztac042
UR  - http://hdl.handle.net/10044/1/99088
VL  - 3
ER  -
Download