TY - JOUR
T1 - Over-fitting suppression training strategies for deep learning-based atrial fibrillation detection
AU - Zhang, Xiangyu
AU - Li, Jianqing
AU - Cai, Zhipeng
AU - Zhang, Li
AU - Chen, Zhenghua
AU - Liu, Chengyu
N1 - Funding Information:
This study was supported by the National Key Research and Development Program of China (2019YFE0113800), the Distinguished Young Scholars of Jiangsu Province (BK20190014), the National Natural Science Foundation of China (81871444, 62001105 and 62071241), the Primary Research & Development Plan of Jiangsu Province (BE2017735), and the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX19_0068).
Publisher Copyright:
© 2021, International Federation for Medical and Biological Engineering.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2021/1
Y1 - 2021/1
N2 - Nowadays, deep learning-based models have been widely developed for atrial fibrillation (AF) detection in electrocardiogram (ECG) signals. However, owing to the inevitable over-fitting problem, classification accuracy of the developed models severely differed when applying on the independent test datasets. This situation is more significant for AF detection from dynamic ECGs. In this study, we explored two potential training strategies to address the over-fitting problem in AF detection. The first one is to use the Fast Fourier transform (FFT) and Hanning-window-based filter to suppress the influence from individual difference. Another is to train the model on the wearable ECG data to improve the robustness of model. Wearable ECG data from 29 patients with arrhythmia were collected for at least 24 h. To verify the effectiveness of the training strategies, a Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN)-based model was proposed and tested. We tested the model on the independent wearable ECG data set, as well as the MIT-BIH Atrial Fibrillation database and PhysioNet/Computing in Cardiology Challenge 2017 database. The model achieved 96.23%, 95.44%, and 95.28% accuracy rates on the three databases, respectively. Pertaining to the comparison of the accuracy rates on each training set, the accuracy of the model trained in conjunction with the proposed training strategies only reduced by 2%, while the accuracy of the model trained without the training strategies decreased by approximately 15%. Therefore, the proposed training strategies serve as effective mechanisms for devising a robust AF detector and significantly enhanced the detection accuracy rates of the resulting deep networks.
AB - Nowadays, deep learning-based models have been widely developed for atrial fibrillation (AF) detection in electrocardiogram (ECG) signals. However, owing to the inevitable over-fitting problem, classification accuracy of the developed models severely differed when applying on the independent test datasets. This situation is more significant for AF detection from dynamic ECGs. In this study, we explored two potential training strategies to address the over-fitting problem in AF detection. The first one is to use the Fast Fourier transform (FFT) and Hanning-window-based filter to suppress the influence from individual difference. Another is to train the model on the wearable ECG data to improve the robustness of model. Wearable ECG data from 29 patients with arrhythmia were collected for at least 24 h. To verify the effectiveness of the training strategies, a Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN)-based model was proposed and tested. We tested the model on the independent wearable ECG data set, as well as the MIT-BIH Atrial Fibrillation database and PhysioNet/Computing in Cardiology Challenge 2017 database. The model achieved 96.23%, 95.44%, and 95.28% accuracy rates on the three databases, respectively. Pertaining to the comparison of the accuracy rates on each training set, the accuracy of the model trained in conjunction with the proposed training strategies only reduced by 2%, while the accuracy of the model trained without the training strategies decreased by approximately 15%. Therefore, the proposed training strategies serve as effective mechanisms for devising a robust AF detector and significantly enhanced the detection accuracy rates of the resulting deep networks.
KW - Atrial fibrillation (AF)
KW - Deep learning
KW - Electrocardiogram (ECG)
KW - Wearable ECG
UR - http://www.scopus.com/inward/record.url?scp=85098695340&partnerID=8YFLogxK
U2 - 10.1007/s11517-020-02292-9
DO - 10.1007/s11517-020-02292-9
M3 - Article
C2 - 33387183
SN - 0140-0118
VL - 59
SP - 165
EP - 173
JO - Medical & Biological Engineering & Computing
JF - Medical & Biological Engineering & Computing
IS - 1
ER -