The School of Instrument Science and Engineering, Southeast University, Nanjing, China.
Computational Intelligence Group, Northumbria University, Newcastle upon Tyne, UK.
Med Biol Eng Comput. 2021 Jan;59(1):165-173. doi: 10.1007/s11517-020-02292-9. Epub 2021 Jan 2.
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.
如今，基于深度学习的模型已广泛应用于心电图（ECG）信号中的心房颤动（AF）检测。然而，由于不可避免的过拟合问题，开发的模型在应用于独立测试数据集时的分类准确性差异很大。这种情况在从动态 ECG 中检测 AF 时更为显著。在本研究中，我们探索了两种潜在的训练策略，以解决 AF 检测中的过拟合问题。第一种是使用快速傅里叶变换（FFT）和汉宁窗滤波器来抑制个体差异的影响。另一种是在可穿戴 ECG 数据上训练模型，以提高模型的鲁棒性。从 29 名心律失常患者中收集了至少 24 小时的可穿戴 ECG 数据。为了验证训练策略的有效性，提出并测试了基于长短期记忆（LSTM）和卷积神经网络（CNN）的模型。我们在独立的可穿戴 ECG 数据集以及麻省理工学院-贝思以色列医院心房颤动数据库和 PhysioNet/计算心脏病学挑战赛 2017 数据库上测试了该模型。该模型在这三个数据库上的准确率分别达到了 96.23%、95.44%和 95.28%。关于每个训练集上的准确率比较，结合所提出的训练策略训练的模型的准确率仅降低了 2%，而未采用训练策略训练的模型的准确率则降低了约 15%。因此，所提出的训练策略是设计鲁棒性 AF 检测器的有效机制，并显著提高了由此产生的深度网络的检测准确率。
