Constrained transformer network for ECG signal processing and arrhythmia classification

Abstract

Background Heart disease diagnosis is a challenging task and it is important to explore useful information from the massive amount of electrocardiogram (ECG) records of patients. The high-precision diagnostic identification of ECG can save clinicians and cardiologists considerable time while helping reduce the possibility of misdiagnosis at the same time.Currently, some deep learning-based methods can effectively perform feature selection and classification prediction, reducing the consumption of manpower. Methods In this work, an end-to-end deep learning framework based on convolutional neural network (CNN) is proposed for ECG signal processing and arrhythmia classification. In the framework, a transformer network is embedded in CNN to capture the temporal information of ECG signals and a new link constraint is introduced to the loss function to enhance the classification ability of the embedding vector. Results To evaluate the proposed method, extensive experiments based on real-world data were conducted. Experimental results show that the proposed model achieve better performance than most baselines. The experiment results also proved that the transformer network pays more attention to the temporal continuity of the data and captures the hidden deep features of the data well. The link constraint strengthens the constraint on the embedded features and effectively suppresses the effect of data imbalance on the results. Conclusions In this paper, an end-to-end model is used to process ECG signal and classify arrhythmia. The model combine CNN and Transformer network to extract temporal information in ECG signal and is capable of performing arrhythmia classification with acceptable accuracy. The model can help cardiologists perform assisted diagnosis of heart disease and improve the efficiency of healthcare delivery.

Medical Ultrasound Image Segmentation With Deep Learning Models

“…Combined with convolutional neural networks, built to repair the insensitivity of self-attention mechanisms to local features, new opportunities arise from the addition of supervised data. Che et al (2021) [39] combined a CNN and transformer network to extract temporal information in ECG signals and was able to perform arrhythmia classification with acceptable accuracy. The model can help cardiologists assist in the diagnosis of heart disease and improve the efficiency of medical services.…”

Golden Standard or Obsolete Method? Review of ECG Applications in Clinical and Experimental Context

“…Compared to the CNN, ResNet, and CNN–biLSTM, the hybrid CNN–transformer model combined with temporal ECG features achieved higher performance in recognizing nine different beat types ( Che et al, 2021 ). The transformer net—one of the most recent DL architectures—has been initially created as a compromise between the CNN (image pattern recognition) and the recurrent neural network (time-series sequence pattern recognition).…”

“…In this model, the relevant features are driven from input data using the so-called attention mechanism. Approaches, using various transformer modifications, achieve promising results in arrhythmia classification experiments on many different ECG databases (e.g., Che et al, 2021 ; Hu et al, 2021 ; Natarajan et al, 2021 ; Nonaka and Seita, 2021 ; Meng et al, 2022 ).…”

ECG signal processing by feature selection with classification based on machine learning architectures in cardiovascular disease detection

“…The automatic classification of cardiac arrhythmias served as the primary source of inspiration for the 12-lead ECG_DL method references to ECG diagnosis. Automatic multilabel arrhythmia classification using a DL model with a DNN [16] based on 1D CNN was achieved with a score of ACC = 0.94, 0.97. Authors of this study also performed single-lead ECG experiments and examined each lead's functionality individually.…”