A method to screen left ventricular dysfunction through ECG based on convolutional neural network
Autor: | Ning Wang, Ling-Feng Miao, Yue Qiu, Yang Hua, Ru-Xing Wang, Juan Lu, Zhen-Ye Zhang, Han-Lin Ding, Min Dai, Bo Shao, Yu-Cong Qiao, Jin-Yu Sun, Yan Chen, Hong-Cheng Guo, Chang-ying Zhang, Yu-Min Zhang, Jin Guo |
---|---|
Rok vydání: | 2021 |
Předmět: |
medicine.medical_specialty
030204 cardiovascular system & hematology Convolutional neural network Ventricular Function Left Set (abstract data type) 03 medical and health sciences Electrocardiography Ventricular Dysfunction Left 0302 clinical medicine Artificial Intelligence Physiology (medical) Internal medicine medicine Humans cardiovascular diseases 030212 general & internal medicine Retrospective Studies Ejection fraction business.industry Deep learning Stroke Volume Predictive value Cardiology Deep neural networks Artificial intelligence Neural Networks Computer Transthoracic echocardiogram Cardiology and Cardiovascular Medicine business Test data |
Zdroj: | Journal of cardiovascular electrophysiologyREFERENCES. 32(4) |
ISSN: | 1540-8167 |
Popis: | Objective This study aims to develop an artificial intelligence-based method to screen patients with left ventricular ejection fraction (LVEF) of 50% or lesser using electrocardiogram (ECG) data alone. Methods Convolutional neural network (CNN) is a class of deep neural networks, which has been widely used in medical image recognition. We collected standard 12-lead ECG and transthoracic echocardiogram (TTE) data including the LVEF value. Then, we paired the ECG and TTE data from the same individual. For multiple ECG-TTE pairs from a single individual, only the earliest data pair was included. All the ECG-TTE pairs were randomly divided into the training, validation, or testing data set in a ratio of 9:1:1 to create or evaluate the CNN model. Finally, we assessed the screening performance by overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. Results We retrospectively enrolled a total of 26 786 ECG-TTE pairs and randomly divided them into training (n = 21 732), validation (n = 2 530), and testing data set (n = 2 530). In the testing set, the CNN algorithm showed an overall accuracy of 73.9%, sensitivity of 69.2%, specificity of 70.5%, positive predictive value of 70.1%, and negative predictive value of 69.9%. Conclusion Our results demonstrate that a well-trained CNN algorithm may be used as a low-cost and noninvasive method to identify patients with left ventricular dysfunction. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |