Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms

Abstract

Background Accurately determining atrial arrhythmia mechanisms from a 12-lead 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 We trained a CNN on data from 231 patients undergoing EP studies for atrial tachyarrhythmia. A total of 13500 5-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. Results 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 convolutional neural network 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 organised atrial arrhythmias.

Application of artificial intelligence in the diagnosis and treatment of cardiac arrhythmia

“…trained a 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 as well. The model matched and complemented expert electrophysiologist performance with an accuracy of 86% 58 . Sau et al.…”

“…The model matched and complemented expert electrophysiologist performance with an accuracy of 86%. 58 Sau et al also focus on distinguishing between atrioventricular re-entrant tachycardia (AVRT) and atrioventricular nodal re-entrant tachycardia (AVNRT) from the 12-lead ECG. 59 The model has a moderate accuracy and requires training in larger datasets to improve performance.…”

Diagnostic AI and Cardiac Diseases

“…Sau et al used a CNN deep learning model in 2022 in order to distinguish between atrial tachyarrhythmias that can be cured with a cavotricuspid isthmus ablation, namely atrial flutter (AFL), and others atrial tachyarrhythmias. In this binary classification endeavour, they used 5 s 12-lead ECG recordings for each patient and achieved an accuracy of 86% versus median electrophysiologist accuracy of 79% [ 30 ].…”

Principles of artificial intelligence and its application in cardiovascular medicine

“…In many fields of medicine, images from different disease entities must be classified. In cardiology, CNNs effectively classify electrocardiograms to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms 13 . Another clinically important application in cardiology is the classification of functionally significant coronary stenosis in coronary CT angiography 14 .…”

“…In cardiology, CNNs effectively classify electrocardiograms to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms. 13 Another clinically important application in cardiology is the classification of functionally significant coronary stenosis in coronary CT angiography. 14 Although CNNs were initially used in image recognition, they are also a powerful tool in other fields.…”