August 25, 2021Frontiers in PhysiologyOpen Access

Detection of Brief Episodes of Atrial Fibrillation Based on Electrocardiomatrix and Convolutional Neural Network

View Full Paper

Ask AI

Bookmark

Why the study?

Brief AF episodes carry risk of thrombus and stroke, but some deep learning detection approaches do not provide analysis of features used for classification.

Can a convolutional neural network based on electrocardiomatrix-images accurately detect brief episodes of atrial fibrillation?

Structured PICO

Can a convolutional neural network based on electrocardiomatrix-images accurately detect brief episodes of atrial fibrillation?

Population

ECG records from five databases: Long-Term Atrial Fibrillation, MIT-BIH Normal Sinus Rhythm, MIT-BIH Atrial Fibrillation, MIT-BIH Arrhythmia, and Monzino-AF

Intervention

Convolutional neural network (CNN) approach based on electrocardiomatrix-images (ECM-images) using a sliding window of 10 beats plus 3 s

Outcome

Detection of brief AF episodes quantified using standard classification metrics and the EC57 standard for arrhythmia detectionsurrogate

A convolutional neural network based on electrocardiomatrix-images can accurately detect brief episodes of atrial fibrillation, linking deep learning to clinical ECG characteristics.

Implication

Supports interpretable CNN detection of brief AF via ECM-images; leaves open clinical adoption pending prospective validation.

Abstract

Background: Brief episodes of atrial fibrillation (AF) may evolve into longer AF episodes increasing the chances of thrombus formation, stroke, and death. Classical methods for AF detection investigate rhythm irregularity or P-wave absence in the ECG, while deep learning approaches profit from the availability of annotated ECG databases to learn discriminatory features linked to different diagnosis. However, some deep learning approaches do not provide analysis of the features used for classification. This paper introduces a convolutional neural network (CNN) approach for automatic detection of brief AF episodes based on electrocardiomatrix-images (ECM-images) aiming to link deep learning to features with clinical meaning. Materials and Methods: The CNN is trained using two databases: the Long-Term Atrial Fibrillation and the MIT-BIH Normal Sinus Rhythm, and tested on three databases: the MIT-BIH Atrial Fibrillation, the MIT-BIH Arrhythmia, and the Monzino-AF. Detection of AF is done using a sliding window of 10 beats plus 3 s. Performance is quantified using both standard classification metrics and the EC57 standard for arrhythmia detection. Layer-wise relevance propagation analysis was applied to link the decisions made by the CNN to clinical characteristics in the ECG. Results: For all three testing databases, episode sensitivity was greater than 80.22, 89.66, and 97.45% for AF episodes shorter than 15, 30 s, and for all episodes, respectively. Conclusions: Rhythm and morphological characteristics of the electrocardiogram can be learned by a CNN from ECM-images for the detection of brief episodes of AF.