Wang Weinan, Mohseni Pedram, Kilgore Kevin L, Najafizadeh Laleh
IEEE J Biomed Health Inform. 2022 May;26(5):2075-2085. doi: 10.1109/JBHI.2021.3128383. Epub 2022 May 5.
This paper presents a new solution that enables the use of transfer learning for cuff-less blood pressure (BP) monitoring via short duration of photoplethysmogram (PPG). The proposed method estimates BP with low computational budget by 1) creating images from segments of PPG via visibility graph (VG), hence, preserving the temporal information of the PPG waveform, 2) using pre-trained deep convolutional neural network (CNN) to extract feature vectors from VG images, and 3) solving for the weights and bias between the feature vectors and the reference BPs with ridge regression. Using the University of California Irvine (UCI) database consisting of 348 records, the proposed method achieves a best error performance of 0.00±8.46 mmHg for systolic blood pressure (SBP), and -0.04±5.36 mmHg for diastolic blood pressure (DBP), respectively, in terms of the mean error (ME) and the standard deviation (SD) of error, ranking grade B for SBP and grade A for DBP under the British Hypertension Society (BHS) protocol. Our novel data-driven method offers a computationally-efficient end-to-end solution for rapid and user-friendly cuff-less PPG-based BP estimation.
本文提出了一种新的解决方案，该方案能够通过短时间的光电容积脉搏波描记图（PPG）利用迁移学习进行无袖带血压（BP）监测。所提出的方法通过以下方式以低计算量估计血压：1）通过可见性图（VG）从PPG片段创建图像，从而保留PPG波形的时间信息；2）使用预训练的深度卷积神经网络（CNN）从VG图像中提取特征向量；3）使用岭回归求解特征向量与参考血压之间的权重和偏差。使用由348条记录组成的加利福尼亚大学欧文分校（UCI）数据库，所提出的方法在收缩压（SBP）的平均误差（ME）和误差标准差（SD）方面分别达到了0.00±8.46 mmHg的最佳误差性能，舒张压（DBP）为-0.04±5.36 mmHg，根据英国高血压协会（BHS）协议，SBP等级为B，DBP等级为A。我们新颖的数据驱动方法为基于PPG的快速且用户友好的无袖带血压估计提供了一种计算高效的端到端解决方案。
