A Continuous Blood Pressure Estimation Model Based on End-to-End Neural Network

doi:10.19678/j.issn.1000-3428.0056449

Computer Engineering ›› 2020, Vol. 46 ›› Issue (12): 270-275. doi: 10.19678/j.issn.1000-3428.0056449

• Development Research and Engineering Application • Previous Articles Next Articles

A Continuous Blood Pressure Estimation Model Based on End-to-End Neural Network

WAN Pei^a, SANG Shengbo^a,b, ZHANG Chengran^a,b, ZHANG Bo^a,b

a. College of Information and Computer Science;b. Key Laboratory of Advonced Transducers and Intelligent Control System of Ministy of Education and Shanxi Province, Taiyuan University of Technology, Jinzhong, Shanxi 030600, China

Received:2019-10-30 Revised:2019-12-13 Published:2019-12-17

一种基于端到端神经网络的连续血压估计模型

万培^a, 桑胜波^a,b, 张成然^a,b, 张博^a,b

太原理工大学 a. 信息与计算机学院;b. 新型传感器与智能控制教育部和山西省重点实验室, 山西晋中 030600

作者简介:万培(1993-),男,硕士研究生,主研方向为人工智能;桑胜波,教授;张成然,硕士研究生;张博,副教授。
基金资助:
国家自然科学基金青年科学基金项目（61703298）。

Abstract

Abstract: The traditional Blood Pressure(BP) measurement model based on pulse wave transit time method and pulse wave characteristic parameter method has disadvantages such as low accuracy.This paper proposes a new continuous blood pressure estimation model.The model can automatically extract the necessary features and their time-domain changes,and reliably estimate blood pressure in a non-invasive and continuous manner.The model consists of two layers.The lower layer uses Artificial Neural Network(ANN) to extract necessary morphological features from Electrocardiogram(ECG) and photo Photoplethysmographic(PPG) waveforms.The higher layer uses the Long Short-Term Memory(LSTM) network layer to account for the time domain changes of the features extracted by the lower layer.The proposed model is evaluated on 69 subjects under the standard of the Association for the Advancement of Medical Instrumentations(AAMI).Experimental results show that the proposed model has higher prediction accuracy than Deep-RNN and other BP estimation models based on ECG and PPG feature parameters.

Key words: end-to-end neural network, Artificial Neural Network(ANN), Long Short Term Memory(LSTM), Photoplethysmography(PPG), continuous Blood Pressure(BP)

摘要： 传统基于脉搏波传导时间法及脉搏波特征参数法的血压测量模型存在精度较低及普适性差等不足。构建一种新的连续血压估计模型，通过自动提取必要的波形形态特征及其时域变化，以无创连续的方式估计血压，其由两个层次组成，较低层次使用人工神经网络从光电容积脉搏波（PPG）和心电图（ECG）波形中提取必要的形态特征，较高层次使用长短期记忆网络层来说明较低层次提取特征的时域变化。依据医疗器械发展协会标准，对69名受试者的采样数据进行模型评估，实验结果证明，与基于ECG和PPG特征参数的Deep-RNN血压估计模型相比，该模型具有更高的预测精度。

关键词: 端到端神经网络, 人工神经网络, 长短期记忆, 光电容积脉搏波, 连续血压

CLC Number:

TP183

WAN Pei, SANG Shengbo, ZHANG Chengran, ZHANG Bo. A Continuous Blood Pressure Estimation Model Based on End-to-End Neural Network[J]. Computer Engineering, 2020, 46(12): 270-275.

万培, 桑胜波, 张成然, 张博. 一种基于端到端神经网络的连续血压估计模型[J]. 计算机工程, 2020, 46(12): 270-275.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0056449

https://www.ecice06.com/EN/Y2020/V46/I12/270

Figures/Tables 11

References

[1] GAO Ninghua,WANG Heng,FENG Xinghua.Classification method of electrocardiogram signals based on dynamic fuzzy decision tree[J].Computer Engineering,2020,46(1):80-86.(in Chinese)高宁化,王姮,冯兴华.基于动态模糊决策树的心电信号分类方法[J].计算机工程,2020,46(1):80-86.
[2] ZHOU Linyong,XIE Xiaoyao,LIU Zhijie,et al.Research on pooling method of convolution neural network[J].Computer Engineering,2019,45(4):211-216.(in Chinese)周林勇,谢晓尧,刘志杰,等.卷积神经网络池化方法研究[J].计算机工程,2019,45(4):211-216.
[3] KACHUEE M,KIANI M M,MOHAMMADZADE H,et al.Cuffless blood pressure estimation algorithms for continuous health-care monitoring[J].IEEE Transactions on Biomedical Engineering,2017,64(4):859-869.
[4] XU Zhihong,LIU Jiexin,CHEN Xianxiang,et al.Continuous blood pressure estimation based on multiple parameters from electrocardiogram and photoplethysmogram by back-propagation neural network[J].Computers in Industry,2017,89:50-59.
[5] HALL J E.Guyton and Hall textbook of medical physiology[M].[S.1.]:Saunders Press,2010.
[6] KUMAR N,AGRAWAL A,DEB S.Cuffless BP measurement using a correlation study of pulse transient time and heart rate[C]//Proceedings of International Conference on Advances in Computing,Communications and Informatics.Washington D.C.,USA:IEEE Press,2014:1538-1541.
[7] XING Xiaomen,SUN Mingshan.Optical blood pressure estimation with photoplethysmography and FFT-based neural networks[J].Biomedical Optics Express,2016,7(8):3007-3020.
[8] MAO J,JAIN A K.Artificial neural networks for feature extraction and multivariate data projection[J].IEEE Transactions on Neural Networks,1995,6(2):296-317.
[9] GUYTON A C,COLEMAN T G,COWLEY A W,et al.Arterial pressure regulation:overriding dominance of the kidneys in long-term regulation and in hypertension[J].American Journal of the Medical Sciences,1972,52(5):584-594.
[10] CHARLTON P H,BONNICI T,TARASSENKO T,et al.An assessment of algorithms to estimate respiratory rate from theelectrocardiogram and photoplethysmogram[J].Physiological Measurement,2016,37(4):610-623.
[11] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computing,1997,9(8):1735-1780.
[12] SU Peng,DING Xiaorong,ZHANG Yuanting,et al.Long-term blood pressure prediction with deep recurrent neural networks[C]//Proceedings of 2018 IEEE EMBS International Conference on Biomedical & Health Informatics.Las Vegas,USA:IEEE Press,2017:1-19.
[13] GOLDBERGER A L,AMARAL L A,GLASS L,et al.Physio bank,physio toolkit,and physio net:components of a new research resource for complex physiologic signals[J].Circulation,2000,101(23):215-220.
[14] SELESNICK I W.Wavelet transform with tunable Q-factor[J].IEEE Transactions on Signal Processing,2011,59(8):3560-3575.
[15] UNSER M,ALDROUBI A.A review of wavelets in biomedical applications[C]//Proceedings of the IEEE,1996,84(4):626-638.
[16] DONOHO D L.De-noising by soft-thresholding[J].IEEE Transactions on Information Theory,1995,41(3):613-627.
[17] ZHAO Bo,HAO Yingdi,LI Xinzheng,et al.Human blood pressure prediction method based on support vector regression[J].Journal of Yanshan University,2017,41(5):438-443.(in Chinese)赵博,赫英迪,李信政,等.基于支持向量回归的人体血压预测方法[J].燕山大学学报,2017,41(5):438-443.
[18] PICKERING T G.Isolated diastolic hypertension[J].Journal of Clinical Hypertension,2003,5(6):411-413.
[19] SCHUSTER M,PALIWAL K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing,1997,45(11):2673-2681.
[20] ARLINGTON S.Association for the advancement of medical instrumentation[J].Journal of Clinical Engineering,2016,41(2):59-60.

Please choose a citation manager

Content to export