摘要
脉搏波蕴含着许多人体生理与病理的重要信息,大量研究通过光电容积描记法(photoplethysmography,PPG)来利用脉搏波特征参数进行无创血压监测。为此,我们总结了脉搏波的特征参数及利用其进行血压测量的基本原理。然后,我们对利用脉搏波特征参数进行血压测量的有线性回归(linear regression,LR)模型、随机森林(random forest,RF)模型、支持向量机(support vector machines,SVM)模型和神经网络模型及不同模型的优缺点和研究进展进行综述。最后,对基于脉搏波信号的无创血压测量的研究进行展望。
Pulse wave contains many important physiological and pathological information of human body.A lot of studies use the characteristic parameters of pulse wave for noninvasive blood pressure monitoring through photoplethysmography(PPG).Herein,we summarize the characteristic parameters of pulse wave and the basic principle of blood pressure measurement by using them.Then the current blood pressure measurement models,include of linear regression model,random forest model,support vector machine model and neural network model are reviewed,and the current research progress,the advantages and disadvantages of various models are introduced.Finally,the prospect of non-invasive blood pressure measurement based on pulse wave signal is prospected.
作者
曹俊魏
程云章
CAO Junwei;CHENG Yunzhang(Shanghai Interventional Medical Device Engineering Technology Research center,University of Shanghai for Science and Technology,Shanghai 200093,China)
出处
《生物医学工程研究》
2021年第2期220-224,共5页
Journal Of Biomedical Engineering Research
关键词
脉搏波
血压测量
线性回归
机器学习
神经网络
Pulse wave
Blood pressure measurement
Linear regression
Machine learning
Neural network
作者简介
通讯作者:程云章,Email:cyz2008@usst.edu.cn。
