Deep Learning Approach to Transformer-Based Arrhythmia Classification using Scalogram of Single-Lead ECG

Arrhythmia is the heartbeat losing its regularity or deviating from its average number. Among the types of arrhythmia is atrial fibrillation (AF) and atrial flutter (AFL), which are considered risk factors for development due to high morbidity and mortality. The early detection of AF/AFL is essential because their effects on the heart or complications appear after a considerable time. Electrocardiography (ECG) is a widely used screening method in primary care because of its low cost and convenience. ECG records the heart's electrical activity for a period of time via electrodes attached to the body. Owing to the development of computing power and interest in big data, attempts at deep learning (DL) have increased. The transformer was proposed by Google in 2017 and has achieved state-of-the-art performance in natural language processing. Various transformer-based models have been applied to various tasks beyond natural language processing and have shown promising prospects. However, there have been few cases of vision transformer (ViT) applications in ECG domain. It was difficult to determine whether ViT had sufficient influence in ECG domain. This study determined whether our extensive ECG dataset could make an AF/AFL diagnosis. We also confirmed whether the recently proposed ViT has AF/AFL diagnostic power.