Using the VQ-VAE to improve the recognition of abnormalities in short-duration 12-lead electrocardiogram records. (November 2020)

• Record Type: Journal Article
• Authors: Liu, Han; Zhao, Zhengbo; Chen, Xiao; Yu, Rong; She, Qiang
• Is Part Of: Computer methods and programs in biomedicine. Volume 196(2020)
• Publication Date: 2020-11
• Subjects: Electrocardiogram -- Artificial intelligence -- Deep learning -- Data augmentation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105639
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Focused on the recognition of ECG morphological problems. A deep learning network is used to detect 10 classes of ECG morphological abnormalities. To address the problems with small positive samples, a data augmentation method based on VQ-VAE was proposed. 2D ECG data and 2D-CNN are employed. Reached the level of ECG specialist in the test of 1000 real clinical patients. Abstract: Background and Objective: Morphological diagnosis is a basic clinical task of the short-duration 12-lead electrocardiogram (ECG). Due to the scarcity of positive samples and other factors, there is currently no algorithm that is comparable to human experts in ECG morphological recognition. Our objective is to develop an ECG specialist-level deep learning method that can accurately identify ten ECG morphological abnormalities in real scene data. Methods: We established a short-duration 12-lead ECG image dataset that consists of approximately 200, 000 samples. To address the problems with small positive samples, a data augmentation method was proposed. We solved it by interpolating in the latent space of the vector quantized variational autoencoder (VQ-VAE) and generating new samples via sampling. The trained final classifier, general doctors, and ECG specialists evaluated the diagnostic performance on a test set that consisted of 1000 samples. Results: Relative to that of unaugmented data, the F1 score was improved by 0–6%. Compared with ECG specialists, the deep neural network achieved higher F1 scores and sensitivity in most categories. Conclusions: Our method can improve the classification performance of ECG data with insufficient positive samples and reach the level of ECG specialists. This approach can provide specialized reference opinions for ordinary clinicians and reduce the errors of ECG specialists.