A new deep learning model for assisted diagnosis on electrocardiogram

• Published in: Mathematical biosciences and engineering : MBE Vol. 16; no. 4; pp. 2481 - 2491
• Main Authors: Wang, Eric Ke, Xi, Liu, Sun, Rui Pei, Wang, Fan, Pan, Le Yun, Cheng, Cai Xia, Dimitrakopoulou-Srauss, Antonia, Zhe, Nie, Li, Yue Ping
• Format: Journal Article
• Language: English
• Published: United States AIMS Press 01-01-2019
• Subjects: Algorithms; bi-directional recurrent neural network; Cardiology; clinical medicine; convolutional neural network; Deep Learning; Diagnosis, Computer-Assisted - methods; electrocardiogram; Electrocardiography; Humans; Machine Learning; Medical Errors; Medical Informatics; Models, Cardiovascular; multi-lead; Neural Networks, Computer; Signal Processing, Computer-Assisted; Skin - pathology; clinical medicine; electrocardiogram; convolutional neural network; multi-lead; bi-directional recurrent neural network
• ISSN: 1547-1063; 1551-0018
• DOI: 10.3934/mbe.2019124

In order to enhance the accuracy of computer aided electrocardiogram analysis, we propose a deep learning model called CBRNN to assist diagnosis on electrocardiogram for clinical medical service. It combines two sub networks which are convolutional neural network (CNN) and bi-directional recurrent neural network (BRNN). In the model, CNN with one-dimension convolution is employed to extract features for each lead of ECG, and BRNN is used to fuse features of different leads to represent deeper features. In the training step, we use more than 40 thousand training data and more than 19 thousand validation data to obtain the optimal parameters of the model. Besides, by validating our model on more than CCDD 120,000 real data, it achieves an 87.69% accuracy rate, higher than popular deep learning models such as CNN and ResNet. Our model has better accuracy than state-of-the-art models and it is also slightly higher than the average accuracy of human judgement. It can be served for the first round screening of ECG examination clinical diagnosis.