A new approach for blood pressure estimation based on phonocardiogram

다국어 초록 (Multilingual Abstract)

Continuous and non-invasive measurement of blood pressure (BP) is of great importance particularly for patients in criticalstate. To achieve continuous and cuffl ess BP monitoring, pulse transit time (PTT) has been reported as a potential parameter.
Nevertheless, this approach remains very sensitive, cumbersome and disagreeable in ambulatory measurement. This paperproposes a new approach to estimate blood pressure through PCG signal by exploring the correlation between PTT anddiastolic duration (S21). In this purpose, an artifi cial neural network was developed using as input data: (systolic duration,diastolic duration, heart rate, sex, height and weight). According to the NN decision, the mean blood pressure was measuredand consequently the systolic and the diastolic pressures were estimated. The proposed method is evaluated on 37 subjects.
The obtained results are satisfactory, where, the error in the estimation of the systolic and the diastolic pressures comparedto the commercial blood pressure device was in the order of 6 .48 ± 4.48 mmHg and 3 .91 ± 2.58 mmHg, respectively, whichare very close to the AAMI standard, 5 ± 8 mmHg. This shows the feasibility of estimating of blood pressure using PCG.

참고문헌 (Reference)

1 Perloff D, "The prognostic value of ambulatory blood pressures" 249 (249): 2792-2798, 1983

2 Nigam V, "Simplicity based gating of heart sounds" IEEE 1298-1301, 2005

3 Yang X-L, "Research progress of noninvasive continuous blood pressure measurements based on pulse wave velocity" 24 (24): 467-472, 2011

4 Obrist PA, "Pulse transit time : relationship to blood pressure" 10 (10): 623-626, 1978

5 Tahar O, "Phonocardiogram signal analysis in the aim of measuring blood pressure" Tlemcen univercity 2017

6 Dastjerdi AE, "Non-invasive blood pressure estimation using phonocardiogram" IEEE 1-4, 2017

7 Tahar O, "New parameter available in phonocardiogram for blood pressure estimation" 301-310, 2018

8 Aizenberg I, "Multilayer feedforward neural network based on multi-valued neurons(MLMVN)and a backpropagation learning algorithm" 11 (11): 169-183, 2007

9 Zhang X-Y, "Model-based analysis of eff ects of systolic blood pressure on frequency characteristics of the second heart sound" IEEE 2888-2891, 2006

10 Sakamoto T, "Hemodynamic determinants of the amplitude of the fi rst heart sound" 16 (16): 45-57, 1965

11 Tozawa M, "Evidence for elevated pulse pressure in patients on chronic hemodialysis : a case-control study" 62 (62): 2195-, 2002

12 Kario K, "Eff ect of dosing time of angiotensin II receptor blockade titrated by self-measured blood pressure recordings on cardiorenal protection in hypertensives : the japan morning surge-target organ protection(j-top)study" 28 (28): 1574-1583, 2010

13 Hsiao C-C, "Design and implementation of auscultation blood pressure measurement using vascular transit time and physiological parameters" IEEE 2996-3001, 2017

14 Fung P, "Continuous noninvasive blood pressure measurement by pulse transit time" IEEE 1 : 738-741, 2004

15 Winter DA, "Biomechanics and motor control of human movement" Wiley 2009

16 Hirose Y, "Back-propagation algorithm which varies the number of hidden units" 4 (4): 61-66, 1991

17 Yano Y, "Association of home and ambulatory blood pressure changes with changes in cardiovascular biomarkers during antihypertensive treatment" 25 (25): 306-312, 2012

18 Omari T, "An automatic wavelet denoising scheme for heart sounds" 13 (13): 1550016-, 2015

19 Association for the Advancement of Medical Instrumentation, "American national standard. manual, electronic or automated sphygmomanometers. ANSI/AAMI SP10-2002/A1"