Sološenko Andrius, Paliakaitė Birutė, Marozas Vaidotas, Sörnmo Leif
Biomedical Engineering Institute, Kaunas University of Technology, Kaunas, Lithuania.
Department of Electronics Engineering, Kaunas University of Technology, Kaunas, Lithuania.
Front Physiol. 2022 Jul 18;13:928098. doi: 10.3389/fphys.2022.928098. eCollection 2022.
To develop a method for detection of bradycardia and ventricular tachycardia using the photoplethysmogram (PPG). The detector is based on a dual-branch convolutional neural network (CNN), whose input is the scalograms of the continuous wavelet transform computed in 5-s segments. Training and validation of the CNN is accomplished using simulated PPG signals generated from RR interval series extracted from public ECG databases. Manually annotated real PPG signals from the PhysioNet/CinC 2015 Challenge Database are used for performance evaluation. The performance is compared to that of a pulse-based reference detector. The sensitivity/specificity were found to be 98.1%/97.9 and 76.6%/96.8% for the CNN-based detector, respectively, whereas the corresponding results for the pulse-based detector were 94.7%/99.8 and 67.1%/93.8%, respectively. The proposed detector may be useful for continuous, long-term monitoring of bradycardia and tachycardia using wearable devices, e.g., wrist-worn devices, especially in situations where sensitivity is favored over specificity. The study demonstrates that simulated PPG signals are suitable for training and validation of a CNN.
开发一种利用光电容积脉搏波图（PPG）检测心动过缓和室性心动过速的方法。该检测器基于双分支卷积神经网络（CNN），其输入是在5秒时间段内计算得到的连续小波变换的尺度图。CNN的训练和验证使用从公共心电图数据库提取的RR间期序列生成的模拟PPG信号来完成。来自PhysioNet/CinC 2015挑战赛数据库的手动标注的真实PPG信号用于性能评估。将该性能与基于脉搏的参考检测器的性能进行比较。基于CNN的检测器的灵敏度/特异性分别为98.1%/97.9和76.6%/96.8%，而基于脉搏的检测器的相应结果分别为94.7%/99.8和67.1%/93.8%。所提出的检测器可用于使用可穿戴设备（如腕戴设备）对心动过缓和心动过速进行连续、长期监测，特别是在灵敏度比特异性更受青睐的情况下。该研究表明模拟PPG信号适用于CNN的训练和验证。
