ECGformer: Leveraging transformer for ECG heartbeat arrhythmia classification
This addresses automated heartbeat classification for medical diagnostics, but appears incremental as it applies an existing transformer architecture to ECG data.
The paper tackles the problem of classifying arrhythmias from ECG data by developing ECGformer, a transformer-based model, and reports that it is highly effective on MIT-BIH and PTB datasets, though no concrete numbers are provided.
An arrhythmia, also known as a dysrhythmia, refers to an irregular heartbeat. There are various types of arrhythmias that can originate from different areas of the heart, resulting in either a rapid, slow, or irregular heartbeat. An electrocardiogram (ECG) is a vital diagnostic tool used to detect heart irregularities and abnormalities, allowing experts to analyze the heart's electrical signals to identify intricate patterns and deviations from the norm. Over the past few decades, numerous studies have been conducted to develop automated methods for classifying heartbeats based on ECG data. In recent years, deep learning has demonstrated exceptional capabilities in tackling various medical challenges, particularly with transformers as a model architecture for sequence processing. By leveraging the transformers, we developed the ECGformer model for the classification of various arrhythmias present in electrocardiogram data. We assessed the suggested approach using the MIT-BIH and PTB datasets. ECG heartbeat arrhythmia classification results show that the proposed method is highly effective.