Robust wave-feature adaptive heartbeat classification based on self-attention mechanism using a transformer model

Objective: Electrocardiography is a common method for screening cardiovascular diseases. Accurate heartbeat classification assists in diagnosis and has attracted great attention. In this paper, we proposed an automatic heartbeat classification method based on a transformer neural network using a self-attention mechanism. Approach: An adaptive heartbeat segmentation method was designed to selectively focus on the time-dependent representation of heartbeats. A one-dimensional convolution layer was used to embed wave characteristics into symbolic representations, and then, a transformer block using multi-head attention was applied to deal with the dependence of wave-embedding. The model was trained and evaluated using the MIT-BIH arrhythmia database (MIT-DB). To improve the model performance, the model pre-trained on MIT-BIH supraventricular arrhythmia database (MIT-SVDB) was used and fine-tuned on MIT-DB. Main results: The proposed method was verified using the MIT-DB for two groups. In the first group, our method attained F1 scores of 0.86 and 0.96 for the supraventricular ectopic beat (SVEB) class and ventricular ectopic beat (VEB) class, respectively. In the second group, our method achieved an average F1 value of 99.83% and better results than other state-of-the-art methods. Significance: We proposed a novel heartbeat classification method based on a transformer model. This method provides a new solution for real-time electrocardiogram heartbeat classification, which can be applied to wearable devices.

An ECG Heartbeat Classification Method Based on Deep Convolutional Neural Network

The electrocardiogram (ECG) is one of the most powerful tools used in hospitals to analyze the cardiovascular status and check health, a standard for detecting and diagnosing abnormal heart rhythms. In recent years, cardiovascular health has attracted much attention. However, traditional doctors’ consultations have disadvantages such as delayed diagnosis and high misdiagnosis rate, while cardiovascular diseases have the characteristics of early diagnosis, early treatment, and early recovery. Therefore, it is essential to reduce the misdiagnosis rate of heart disease. Our work is based on five different types of ECG arrhythmia classified according to the AAMI EC57 standard, namely, nonectopic, supraventricular ectopic, ventricular ectopic, fusion, and unknown beat. This paper proposed a high-accuracy ECG arrhythmia classification method based on convolutional neural network (CNN), which could accurately classify ECG signals. We evaluated the classification effect of this classification method on the supraventricular ectopic beat (SVEB) and ventricular ectopic beat (VEB) based on the MIT-BIH arrhythmia database. According to the results, the proposed method achieved 99.8% accuracy, 98.4% sensitivity, 99.9% specificity, and 98.5% positive prediction rate for detecting VEB. Detection of SVEB achieved 99.7% accuracy, 92.1% sensitivity, 99.9% specificity, and 96.8% positive prediction rate.

ECG-based machine-learning algorithms for heartbeat classification

Electrocardiogram (ECG) signals represent the electrical activity of the human hearts and consist of several waveforms (P, QRS, and T). The duration and shape of each waveform and the distances between different peaks are used to diagnose heart diseases. In this work, to better analyze ECG signals, a new algorithm that exploits two-event related moving-averages (TERMA) and fractional-Fourier-transform (FrFT) algorithms is proposed. The TERMA algorithm specifies certain areas of interest to locate desired peak, while the FrFT rotates ECG signals in the time-frequency plane to manifest the locations of various peaks. The proposed algorithm’s performance outperforms state-of-the-art algorithms. Moreover, to automatically classify heart disease, estimated peaks, durations between different peaks, and other ECG signal features were used to train a machine-learning model. Most of the available studies uses the MIT-BIH database (only 48 patients). However, in this work, the recently reported Shaoxing People’s Hospital (SPH) database, which consists of more than 10,000 patients, was used to train the proposed machine-learning model, which is more realistic for classification. The cross-database training and testing with promising results is the uniqueness of our proposed machine-learning model.