MMA-RNN: A Multi-level Multi-task Attention-based Recurrent Neural Network for Discrimination and Localization of Atrial Fibrillation

TL;DR

This paper introduces MMA-RNN, a hierarchical multi-task neural network that simultaneously classifies atrial fibrillation types and localizes episodes from ECG signals, improving accuracy and enabling practical AF monitoring.

Contribution

The novel MMA-RNN model effectively combines multi-level feature extraction with multi-task learning for AF discrimination and localization, addressing limitations of previous stage-by-stage methods.

Findings

Achieved superior classification accuracy on CPSC 2021 dataset.

Successfully localized AF episodes with high precision.

Demonstrated potential for real-time AF monitoring on wearable devices.

Abstract

The automatic detection of atrial fibrillation based on electrocardiograph (ECG) signals has received wide attention both clinically and practically. It is challenging to process ECG signals with cyclical pattern, varying length and unstable quality due to noise and distortion. Besides, there has been insufficient research on separating persistent atrial fibrillation from paroxysmal atrial fibrillation, and little discussion on locating the onsets and end points of AF episodes. It is even more arduous to perform well on these two distinct but interrelated tasks, while avoiding the mistakes inherent from stage-by-stage approaches. This paper proposes the Multi-level Multi-task Attention-based Recurrent Neural Network for three-class discrimination on patients and localization of the exact timing of AF episodes. Our model captures three-level sequential features based on a hierarchical architecture utilizing Bidirectional Long and Short-Term Memory Network (Bi-LSTM) and attention layers, and accomplishes the two tasks simultaneously with a multi-head classifier. The model is designed as an end-to-end framework to enhance information interaction and reduce error accumulation. Finally, we conduct experiments on CPSC 2021 dataset and the result demonstrates the superior performance of our method, indicating the potential application of MMA-RNN to wearable mobile devices for routine AF monitoring and early diagnosis.