An Arrhythmia classification approach via deep learning using single-lead ECG without QRS wave detection

Liong-Rung Liu; Ming-Yuan Huang; Shu-Tien Huang; Lu-Chih Kung; Chao-Hsiung Lee; Wen-Teng Yao; Ming-Feng Tsai; Cheng-Hung Hsu; Yu-Chang Chu; Fei-Hung Hung; Hung-Wen Chiu

doi:10.1016/j.heliyon.2024.e27200

An Arrhythmia classification approach via deep learning using single-lead ECG without QRS wave detection

Heliyon. 2024 Feb 29;10(5):e27200. doi: 10.1016/j.heliyon.2024.e27200. eCollection 2024 Mar 15.

Authors

Liong-Rung Liu^{1

2

3}, Ming-Yuan Huang^{2

3}, Shu-Tien Huang^{1

2

3}, Lu-Chih Kung^{2

3}, Chao-Hsiung Lee^{2

3}, Wen-Teng Yao^{4

3}, Ming-Feng Tsai^{1

4

3}, Cheng-Hung Hsu¹, Yu-Chang Chu¹, Fei-Hung Hung⁵, Hung-Wen Chiu^{1

6

7}

Affiliations

¹ Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.
² Department of Emergency Medicine, Mackay Memorial Hospital, Taipei, Taiwan.
³ Department of Medicine, Mackay Medical College, New Taipei City, Taiwan.
⁴ Division of Plastic Surgery, Department of Surgery, Mackay Memorial Hospital, Taipei, Taiwan.
⁵ Health Data Analytics and Statistics Center, Office of Data Science, Taipei Medical University, Taipei, Taiwan.
⁶ Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei, Taiwan.
⁷ Bioinformatics Data Science Center, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.

Abstract

Arrhythmia, a frequently encountered and life-threatening cardiac disorder, can manifest as a transient or isolated event. Traditional automatic arrhythmia detection methods have predominantly relied on QRS-wave signal detection. Contemporary research has focused on the utilization of wearable devices for continuous monitoring of heart rates and rhythms through single-lead electrocardiogram (ECG), which holds the potential to promptly detect arrhythmias. However, in this study, we employed a convolutional neural network (CNN) to classify distinct arrhythmias without QRS wave detection step. The ECG data utilized in this study were sourced from the publicly accessible PhysioNet databases. Taking into account the impact of the duration of ECG signal on accuracy, this study trained one-dimensional CNN models with 5-s and 10-s segments, respectively, and compared their results. In the results, the CNN model exhibited the capability to differentiate between Normal Sinus Rhythm (NSR) and various arrhythmias, including Atrial Fibrillation (AFIB), Atrial Flutter (AFL), Wolff-Parkinson-White syndrome (WPW), Ventricular Fibrillation (VF), Ventricular Tachycardia (VT), Ventricular Flutter (VFL), Mobitz II AV Block (MII), and Sinus Bradycardia (SB). Both 10-s and 5-s ECG segments exhibited comparable results, with an average classification accuracy of 97.31%. It reveals the feasibility of utilizing even shorter 5-s recordings for detecting arrhythmias in everyday scenarios. Detecting arrhythmias with a single lead aligns well with the practicality of wearable devices for daily use, and shorter detection times also align with their clinical utility in emergency situations.

Keywords: Arrhythmia; Computer-aided diagnosis (CAD); Convolution neural network (CNN); Deep learning; Single-lead electrocardiogram (ECG).