Next Article in Journal
Sub-Auroral and Mid-Latitude GNSS ROTI Performance during Solar Cycle 24 Geomagnetic Disturbed Periods: Towards Storm’s Early Sensing
Previous Article in Journal
Hierarchical Tactile Sensation Integration from Prosthetic Fingertips Enables Multi-Texture Surface Recognition
Previous Article in Special Issue
Autoencoder-Based Extrasystole Detection and Modification of RRI Data for Precise Heart Rate Variability Analysis
Article

Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs

Bio-Intelligence & Data Mining Laboratory, School of Electronic and Electrical Engineering, Kyungpook National University, Daegu 41566, Korea
*
Author to whom correspondence should be addressed.
Academic Editors: Zongyuan Ge, Yingying Zhu and Xiaofeng Zhu
Sensors 2021, 21(13), 4331; https://doi.org/10.3390/s21134331
Received: 16 April 2021 / Revised: 17 June 2021 / Accepted: 21 June 2021 / Published: 24 June 2021
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
Automatic detection of abnormal heart rhythms, including atrial fibrillation (AF), using signals obtained from a single-lead wearable electrocardiogram (ECG) device, is useful for daily cardiac health monitoring. In this study, we propose a novel image-based deep learning framework to classify single-lead ECG recordings of short variable length into several different rhythms associated with arrhythmias. By transforming variable-length 1D ECG signals into fixed-size 2D time-morphology representations and feeding them to the beat–interval–texture convolutional neural network (BIT-CNN) model, we aimed to learn the comprehensible characteristics of beat shape and inter-beat patterns over time for arrhythmia classification. The proposed approach allows feature embedding vectors to provide interpretable time-morphology patterns focused at each step of the learning process. In addition, this method reduces the number of model parameters needed to be trained and aids visual interpretation, while maintaining similar performance to other CNN-based approaches to arrhythmia classification. For experiments, we used the PhysioNet/CinC Challenge 2017 dataset and achieved an overall F1_NAO of 81.75% and F1_NAOP of 76.87%, which are comparable to those of the state-of-the-art methods for variable-length ECGs. View Full-Text
Keywords: arrhythmia classification; atrial fibrillation (AF); electrocardiogram (ECG); convolutional neural network (CNN); deep learning arrhythmia classification; atrial fibrillation (AF); electrocardiogram (ECG); convolutional neural network (CNN); deep learning
Show Figures

Figure 1

MDPI and ACS Style

Lee, H.; Shin, M. Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs. Sensors 2021, 21, 4331. https://doi.org/10.3390/s21134331

AMA Style

Lee H, Shin M. Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs. Sensors. 2021; 21(13):4331. https://doi.org/10.3390/s21134331

Chicago/Turabian Style

Lee, Hyeonjeong, and Miyoung Shin. 2021. "Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs" Sensors 21, no. 13: 4331. https://doi.org/10.3390/s21134331

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop