Research About Cuff-less Continuous Blood Pressure Estimation by Multi-parameter Fusion Method
XU Zhihong①② FANG Zhen①② CHEN Xianxiang① QIN Li②③ DU Lidong① ZHAO Zhan①② LIU Jiexin④
①(Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China) ②(University of Chinese Academy of Sciences, Beijing 100049, China) ③(Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China) ④(TianTan Hospital, Beijing 100050, China)
Abstract：For the problem of noninvasive continuous blood pressure algorithm with un-accuracy, a novel multi- parameter fusion algorithm based on BP neural network is proposed, according to the formation from electrocardiogram and photoplethysmograph of arterial blood pressure. The improved Pan Tompkins algorithm is used to extract the R peak of electrocardiogram, and difference-threshold algorithm is used to extract the features points of photo-plethysmograph, and the fifteen feature parameters relative to blood pressure are extracted and used to establish the model of blood pressure to estimate the beat-to-beat systolic blood pressure and diastolic blood pressure. The factor analysis method is used to analyze the weight of each parameter. The results show that the weight order is pulse transit time, time information, photoplethysmography area information, amplitude information and area ratio. The algorithm is tested in the TianTan Hospital, and the means±standard difference of single measurement errors are respectively -1.57±6.12 mmHg and -0.62±4.82 mmHg, the means± standard difference, D. of repeated measurement errors are respectively -2.12±5.10 mmHg and -2.52±4.41 mmHg, for systolic blood pressure and diastolic blood pressure. And the measurement accuracy for systolic blood pressure and diastolic blood pressure reaches Grade A of BHS standard and AAMI standard.
BUXI D, REDOUTE J M, and YUCE M R. Blood pressure estimation using pulse transit time from bioimpedance and continuous wave radar[J]. IEEE Transactions on Biomedical Engineering, 2017, 64(4): 917-927.
[2]
POON C C and ZHANG Y T. Cuff-less and noninvasive measurements of arterial blood pressure by pulse transit time[C]. International Conference of the Engineering in Medicine & Biology Society, Shanghai, China, 2005: 5877-5880.
[3]
RIBAS V. Continuous blood pressure assessment from a photoplethysmographic signal with Deep Belief Networks[J]. Faseb Journal, 2014, 28(1): Supplement LB674.
[4]
PAN J and TOMPKINS W J. A real-time QRS detection algorithm[J]. IEEE Transactions on Biomedical Engineering, 1985, 32(3): 230-236. doi: 10.1109/TBME.1985.325532.
[5]
丁有得. 基于容积脉搏波血流多参数测量的研究[D]. [博士论文], 南方医科大学, 2010.
DING Youde. Study on blood flow multi-parameters detecting based on the volume pulse wave[D]. [Ph.D. dissertation], Southern Medical University, 2010.
WU Qiuling and WU Meng, One new audio information hidden method based on wavelet transform[J]. Journal of Electronics & Information Technology, 2016, 38(4): 834-840. doi: 10.11999/JEIT150856.
WU Guangwen, WANG Changming, BAO Jiandong, et al. A wavelet threshold de-noising algorithm based on adaptive threshold function[J]. Journal of Electronics & Information Technology, 2014, 36(6): 1340-1347. doi: 10.3724/SP.J.1146. 2013.00798.
TIAN Jingjing, LI Guangjun, and LI Qiang. Hardware- efficient parallel structures for linear-phase FIR digital filter based on iterated short convolution algorithm[J]. Journal of Electronics & Information Technology, 2014, 36(5): 1151-1157. doi: 10.3724/SP.J.1146.2013.00976.
HUANG Cong and LIU Yin, Low-speed moving target detection of single frame image based on Doppler shift estimation[J]. Journal of Electronics & Information Technology, 2016, 38(7): 1638-1644. doi: 10.11999/ JEIT151078.
HUANG Xiaoxia, LUO Shengqin, and LU Mingda. A circuit of artificial neural network for implementing stable adaptive IIR filter[J]. Journal of Electronics & Information Technology, 1997, 19(4): 445-450.
XU Huajian, YANG Zhiwei, LIAO Guisheng, et al. Robust approach for clutter covariance matrix estimation with STAP in heterogeneous environment[J]. Journal of Electronics & Information Technology, 2017, 39(5): 1036-1043. doi: 10.11999/JEIT160747.
HAN Qingyang, WANG Xiaodong, LI Bingyu, et al. Using EEMD to eliminate high frequency noise and baseline drift in pulse blood-oximetry measurement simultaneously[J]. Journal of Electronics & Information Technology, 2015, 37(6): 1384-1388. doi: 10.11999/JEIT141390.
TANG Hongrong, SHEN Minfen, and LI bin. The improvement of the BEMD using compactly supported RBF[J]. Journal of Electronics & Information Technology, 2008, 30(1): 149-153. doi: 10.3724/SP.J.1146.2006.00849.
[14]
YUAN Zhaokai, HUANG Xianping, FAN Fuyuan, et al. Analysis of photoplethysmogram on different positions of 253 normal adults[J]. Journal of Hunan College of Traditional Chinese Medicine, 2000, 20(3): 1-3.
[15]
WAMER H R, SWAN H J, CONNOLLY D C, et al. Quantitation of beat-to-beat changes in stroke volume from the aortic pulse contour in man[J]. Journal of Applied Physiology, 1953, 5(9): 495-507.
[16]
ELGENDI M. On the analysis of fingertip photoplethysmogram signals[J]. Current Cardiology Reviews, 2012, 8(1): 14-25.
[17]
CHANDRARATNA P A, SAN P S, SCHNEIDER R, et al. Implications of changes in amplitude and contour of the mercury strain gauge plethysmograph pulse tracing[J]. Heart, 1978, 40(8): 907-910.
[18]
De S G, DEVEREUX R B, CHINALI M, et al. Association of blood pressure with blood viscosity in american indians: The strong heart study[J]. Hypertension, 2005, 45(4): 625-30.
[19]
KOUNALAKIS S N and GELADAS N D. The role of pulse transit time as an index of arterial stiffness during exercise[J]. Cardiovascular Engineering, 2009, 9(3): 92-97.
[20]
SAITO M, MATSUKAWAM, ASADA T, et al. Noninvasive assessment of arterial stiffness by pulse wave analysis[J]. IEEE Transactions on Ultrasonics, Ferroelectronics, and Freqency Control, 2012, 59(11): 2411-2419.
[21]
SHI P, HU S, ZHU Y, et al. Insight into the dicrotic notch in photoplethysmographic pulses from the finger tip of young adults[J]. Journal of Medical Engineering & Technology, 2009, 33(8): 628-633.
[22]
LAX H, FEINBERG A W, and COHEN B M. Studies of the arterial pulse wave. I. The normal pulse wave and its modification in the presence of human arteriosclerosis[J]. Journal of Chronic Diseases, 1956, 3(6): 618-631.
[23]
BABCHCHENKO A, DAVIDSON E, GINOSAR Y, et al. Photoplethysmographic measurement of changes in total and pulsatile tissue blood volume, following sympathetic blockade [J]. Physiological Measurement, 2001, 22(2): 389-397.
[24]
AWAD A A, HADDADIN A S, TANTAWY H, et al. The relationship between the photoplethysmographic waveform and systemic vascular resistance[J]. Journal of Clinical Monitoring and Computing, 2007, 21(6): 365-372.
[25]
LI J, JIN J, CHEN X, et al. Comparison of respiratory- induced variations in photoplethysmographic signals[J]. Physiological Measurement, 2010, 31(3): 415-425.
[26]
HØISETH LØ, HOFF I E, HAGEN O A, et al. Respiratory variations in the photoplethysmographic waveform amplitude depend on type of pulse oximetry device[J]. Journal of Clinical Monitoring and Computing, 2016, 30(3): 317-325.
[27]
FOO J Y, LIM C S, and WILSON S J. Photoplethy smographic assessment of hemodynamic variations using pulsatile tissue blood volume[J]. Angiology, 2009, 59(6): 745-752. doi: 10.1177/0003319708314245.
[28]
JOHANSSON A. Neural network for photoplethysmographic respiratory rate monitoring[J]. Medical & Biological Engineering & Computing, 2003, 41(3): 242-248.
[29]
SZTAJZEL J. Heart rate variability: A noninvasive electrocardiographic method to measure the autonomic nervous system[J]. Swiss Medical Weekly, 2004, 134(35/36): 514-522.
[30]
LACKNER P, GUENGOER E, BEER R, et al. Photoplethy smography pulse rate variability as a surrogate measurement of heart rate variability during non-stationary conditions[J]. Physiological Measurement, 2010, 31(9): 1271-1290.
[31]
GU W B, POON C C Y, and ZHANG Y T. A novel parameter from PPG dicrotic notch for estimation of systolic blood pressure using pulse transit time[C]. International Summer School and Symposium on Medical Devices and Biosensors, HKSAR, 2008: 86-88.
[32]
SHALTIS P, REISNER A, and ASADA H. Calibration of the photoplethysmogram to arterial blood pressure: Capabilities and limitations for continuous pressure monitoring[J]. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Shanghai, China, 2005, 4: 3970-3973. doi: 10.1109/IEMBS.2005. 1615331.
[33]
GU G, YANG L, LIU C, et al. Age and blood pressure associated changes in the Gaussian modeling characteristics of the photoplethysmographic pulse[J]. Experimental & Clinical Cardiology, 2014, 20(9): 4943-4951.
XU Kexin, WANG Jicun, YU Hui, et al. The research about the correlation between the pulse wave time-domain characteristics and blood pressure[J]. China Medical Devices, 2009, 24(8): 42-45.
LUO Zhichang, ZHANG Song, YANG Wenming, et al. The research about pulse wave characteristic information[J]. Journal of Beijing Polytechnic University, 1996, 22(1): 71-79.
ZENG Yong, SHU Hua, HU Jiangping, et al. Adaptive pseudo nearest neighbor classification based on BP neural network[J]. Journal of Electronics & Information Technology, 2016, 38(11): 2774-2779. doi: 10.11999/JEIT160133.
