基于GA优化的MIV-BP神经网络连续血压无创监测方法研究

Abstract
Figure/Table
References (20)
Related Citation (0)

Download: PDF (3185 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming at the shortcomings of existing blood pressure measurement models based on pulse wave transit time or pulse wave parameters, a non-invasive continuous blood pressure measurement based on GA-MIV-BP neural network model is proposed. The factors that greatly influence blood pressure from the extracted pulse wave transit time and pulse wave parameters are selected by the mean impact value (MIV) method. These factors are used as inputs, and the actual blood pressure values as outputs, to train the BP neural network model. The individual parameters are then optimized using a genetic algorithm (GA) to establish the GA-MIV-BP neural network model. Bland-Altman consistency analysis indicated that the two values were consistent and interchangeable. Therefore, this algorithm is of great significance to promote the clinical application of a non-invasive continuous blood pressure monitoring method.

Key words： pulse wave transit time pulse wave parameter non-invasive continuous blood pressure measurement GA-MIV-BP neural network model

Received: 27 October 2017 Published: 28 April 2019

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

URL:

http://jvs.sjtu.edu.cn/EN/ OR http://jvs.sjtu.edu.cn/EN/Y2019/V38/I9/71

[1] PRESSMAN GL, NEWGARD PM. A transducer for the continuous external measurement of arterial blood pressure [J]. IEEE Transaction biomedical engineering, 1963, (2): 73-81
[2] 蒋巍巍, 季忠. 无创血压测量方法的研究进展[J]. 中华高血压杂志,2015,23(07):685-689.
    Weiwei Jiang, Zhong Ji. Research progress of noninvasive blood pressure measurement methods [J]. Chinese Journal of hypertension, 2015, 23(07):685-689.
[3] Slike B, Mcauley D. Accuracy and precision of blood pressure determination with the Finapres: an overview using re-sampling statistics [J]. J Hum Hypertens, 1998, 12(6): 403-409.
[4] Simi Susan Thomas, Viswam Nathan, Chengzhi zong, et al. Bio watch: a non-invasive wrist-based blood pressure monitor that incorporates training techniques for posture and subject variability [J]. IEEE Journal of Biomedical and Health Informatics, 2016, 20(5):1291-1300.
[5] 李顶立. 基于脉搏波的无创连续血压测量方法研究[D].浙江大学,2008.
    Dingli Li. Research on non-invasive continuous blood pressure measurement based on pulse wave [D]. Zhejiang University, 2008.
[6] 焦学军,房兴业. 利用脉搏波特征参数连续测量血压的方法研究[J]. 生物医学工程学杂志,2002,(02):217-220.
     Xuejun Jiao, Xingye Fang. Research on continuous measurement of blood pressure via characteristic parameters of pulse wave [J]. Journal of Biomedical Engineering, 2002,(02):217-220.
[7] 徐可欣, 王继寸, 余辉, 等.脉搏波时域特征与血压相关性的研究[J]. 中国医疗设备, 2009, (08):42-45.
Kexin Xu, Jicun Wang, Hui Yu, et al. Research of correlation between time-domain characteristics of the pulse wave and blood pressure, China Medical Devices, 2009,(08):42-45.
[8] 董锋. 基于脉搏波特征的连续血压测量方法研究[D]. 云南大学, 2015.
Feng Dong. Study on continuous blood pressure measurement method based on pulse wave characteristics, Master degree thesis of Yunnan University, 2015.
[9] Liu Xu, Ji Zhong, Tang Yuran. Recognition of Pulse Wave Feature Points and Non-invasive Blood Pressure Measurement [J]. Journal of Signal Processing Systems, 2017, 87(2): 241-248
[10] 向海燕. 无创伤人体逐拍动脉血压测量技术[D].第四军医大学, 2005.
Haiyan Xiang. Continuous non-invasive blood pressure measurement using the pulse wave transit time, Doctoral dissertation of the Fourth Military Medical University, 2005.
[11] 梁妃学, 姚翔,于巍,等.双通道脉搏波速度测量系统的研制[J].中国医学物理学杂志,2006,23(03):209-213.
Feixue Liang, Xiang Yao, Wei Yu, et al. The development of dual channel pulse wave velocity measurement system, Chinese Journal of Medical Physics, 2006, 23(03):209-213.
[12] 何芳,王小川,肖森予,等.基于MIV-BP型网络实验的房地产项目风险识别研究[J]. 运筹与管理,2013, 22 (02):229-234.
     Fang He, Xiaochuan Wang, Senyu Xiao, et al. Research on risk recognition of real estate projects based on MIV-BP neural network test [J]. Operations Research and Management Science, 2013, 22 (02):229-234.
[13] 夏玫.BP神经网络泛化能力改进研究[D].太原科技大学,2006.
     Mei Xia. Research on improve generalization of BP neural network [D]. Taiyuan University of Science & Technology,2006.
[14] 胥永刚，赵国亮，马朝永，等. 基于双树复小波与非线性时间序列的降噪方法[J].振动与冲击, 2015, 34(16):135-140.
XU Yong Gang, ZHAO Guo Liang, MA Chao Yong, et al. New denoising method based on dual-tree complex wavelet transform and nonlinear time series [J]. Journal of Vibration and Shock, 2015, 34(16): 135-140.
[15] 查玉华,李巍,陈文霞.基于小波变换和样条插值的容积脉搏波去噪方法研究[J].中国医学装备,2015,12(10):27-29.
     Yuhua Zha, Wei Li, Wenxia Chen. A method of plethysmography wave de-noising based on wavelet transform and spline interpolation [J]. China Medical Equipment, 2015, 12(10):27-29.
[16] 罗小刚, 彭承琳, 郑小林, 等. 基于小波变换与形态学运算的ECG综合检测算法的研究[J]. 生物医学工程学杂志. 2004 .21(5):788-790.
     Xiaogang Luo, Chenglin Peng, Xiaoling Zheng, et al. A study of ECG combination detection algorithm based on wavelet transform and morphological method [J]. Journal of Biomedical Engineering, 2004, 21(5):788-790.
[17] 庄育锋,胡晓瑾,翟宇.基于BP神经网络的微量药品动态称重系统非线性补偿[J]. 仪器仪表学报, 2014, 35(8):1914-1920.
     Yufeng Zhuang, Xiaojin Hu, Yu Zhai. Nonlinear compensation of micro scale capsule dynamic condition weighing unit based on BP neural network model [J]. Chinese Journal of Scientific Instrument, 2014, 35(8):1914-1920.
[18] Hieu Trung Huynh, Yonggwan Won. Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks [J]. Pattern Recognition Letters, 2011, 32(14):1930-1935.
[19] Moller, Martin Fodslette. A scaled conjugate gradient algorithm for fast supervised learning [J]. Neural Network, 1993, 6(4):525-533.
[20] Younessi Heravi Mohammad Amin, Maghooli Keivan, Joharinia Sima. A new approach for blood pressure monitoring based on ECG and PPG signals by using Artificial Neural Networks, International Journal of Computer Applications, 2014, 103(12):36-40.