What is the clinical evidence from this study?

Study design: Other. Population: Arrhythmia (n=6877). Intervention: CNN_Transformer_LC model vs. Baseline deep learning models (CNN, ResNet, Multi_channelCNN, BiRNN, CNN_BiLSTM). Primary outcome: F1 score for arrhythmia classification.

June 9, 2021Open Access

Constrained transformer network for ECG signal processing and arrhythmia classification

Key Result

The proposed CNN_Transformer_LC model achieved an F1 score of 78.6% for arrhythmia classification, outperforming baseline deep learning models.

Structured PICO

Population

6,877 individuals (3,699 men, 3,178 women) with 12-lead ECG records collected from 11 hospitals.

Intervention

End-to-end deep learning framework combining Convolutional Neural Network (CNN) and Transformer network with link constraints (CNN_Transformer_LC).

Comparator

Baseline deep learning models including CNN, ResNet, Multi_channelCNN, BiRNN, and CNN_BiLSTM.

Outcome

Arrhythmia classification performance measured by F1 score across 9 categories.

A novel deep learning model combining CNNs and Transformer networks with link constraints improves the automated classification of arrhythmias from 12-lead ECGs.

Main Result

Absolute Event Rate: 0.786% vs 0.751%

Limitations

Limited data distribution for PAC, STE, and STD categories resulted in lower performance for these classes.

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.

Mark Helpful

Bookmark

Relay

View Full Paper