Improved measurement of blood pressure by extraction of characteristic features from the cuff oscillometric waveform

Lim, P.K. and Ng, S.C. and Jassim, W.A. and Redmond, S.J. and Zilany, M. and Avolio, A. and Lim, E. and Tan, M.P. and Lovell, N.H. (2015) Improved measurement of blood pressure by extraction of characteristic features from the cuff oscillometric waveform. Sensors, 15 (6). pp. 14142-14161. ISSN 14142-14161, DOI

PDF (Improved Measurement of Blood Pressure by Extraction of Characteristic Features from the Cuff Oscillometric Waveform)
Improved_Measurement_of_Blood_Pressure_by_Extraction_of_Characteristic_Features.pdf - Published Version

Download (1MB)
Official URL:


We present a novel approach to improve the estimation of systolic (SBP) and diastolic blood pressure (DBP) from oscillometric waveform data using variable characteristic ratios between SBP and DBP with mean arterial pressure (MAP). This was verified in 25 healthy subjects, aged 28 +/- 5 years. The multiple linear regression (MLR) and support vector regression (SVR) models were used to examine the relationship between the SBP and the DBP ratio with ten features extracted from the oscillometric waveform envelope (OWE). An automatic algorithm based on relative changes in the cuff pressure and neighbouring oscillometric pulses was proposed to remove outlier points caused by movement artifacts. Substantial reduction in the mean and standard deviation of the blood pressure estimation errors were obtained upon artifact removal. Using the sequential forward floating selection (SFFS) approach, we were able to achieve a significant reduction in the mean and standard deviation of differences between the estimated SBP values and the reference scoring (MLR: mean +/- SD = -0.3 +/- 5.8 mmHg; SVR and -0.6 +/- 5.4 mmHg) with only two features, i.e., Ratio(2) and Area(3), as compared to the conventional maximum amplitude algorithm (MAA) method (mean +/- SD = -1.6 +/- 8.6 mmHg). Comparing the performance of both MLR and SVR models, our results showed that the MLR model was able to achieve comparable performance to that of the SVR model despite its simplicity.

Item Type: Article
Funders: Ministry of Higher Education of Malaysia UM.C/HIR/MOHE/ENG/50, University of Malaya Research Grant RP028-14HTM , Australian Research Council Linkages scheme
Additional Information: ISI Document Delivery No.: CM7JX Times Cited: 0 Cited Reference Count: 37 Cited References: Anonymous, 2003, 102002 ANSIAAMI SP Antonova ML, 2013, BLOOD PRESS MONIT, V18, P32, DOI 10.1097/MBP.0b013e32835b9d5f Babbs CF, 2012, BIOMED ENG ONLINE, V11, DOI 10.1186/1475-925X-11-56 Baker PD, 1997, MED BIOL ENG COMPUT, V35, P271, DOI 10.1007/BF02530049 Barbe K, 2012, IEEE T INSTRUM MEAS, V61, P411, DOI 10.1109/TIM.2011.2161933 Barbe K, 2010, J PHYS CONF SER, V238, DOI 10.1088/1742-6596/238/1/012052 Barbe K, 2014, BIOMED SIGNAL PROCES, V11, P89, DOI 10.1016/j.bspc.2014.01.012 Basak Debasish, 2007, NEURAL INFORM PROCES, V11, P203 Brien E.O., 1993, J HYPERTENS S2, V11, pS43 Chang C.C., LIBSVM LIB SUPPORT V Charbonnier S, 2000, IEEE IMTC P, P693 Chen SL, 2011, IEEE T INSTRUM MEAS, V60, P1741, DOI 10.1109/TIM.2010.2092874 Choi HS, 2007, P ANN INT IEEE EMBS, P3285, DOI 10.1109/IEMBS.2007.4353031 Forouzanfar M, 2011, IEEE T INSTRUM MEAS, V60, P2786, DOI 10.1109/TIM.2011.2123210 Gupta V, 2007, AM J MED, V120, P841, DOI 10.1016/j.amjmed.2007.02.023 Higgins JR, 2001, LANCET, V357, P131, DOI 10.1016/S0140-6736(00)03552-2 Jazbinsek V, 2010, ANN BIOMED ENG, V38, P774, DOI 10.1007/s10439-009-9853-4 Landgraf J, 2010, AM J CARDIOL, V106, P386, DOI 10.1016/j.amjcard.2010.03.040 Lee SJ, 2011, PUBLIC DIPLOMACY AND SOFT POWER IN EAST ASIA, P1 Lee S, 2011, IEEE T INSTRUM MEAS, V60, P3405, DOI 10.1109/TIM.2011.2161926 Lee S, 2014, DIGIT SIGNAL PROCESS, V30, P154, DOI 10.1016/j.dsp.2014.04.001 Lee S, 2013, SENSORS-BASEL, V13, P13609, DOI 10.3390/s131013609 Lee S, 2013, IEEE T INSTRUM MEAS, V62, P3387, DOI 10.1109/TIM.2013.2273612 Liu JK, 2013, ANN BIOMED ENG, V41, P587, DOI 10.1007/s10439-012-0700-7 Mafi M, 2011, IEEE ENG MED BIO, P2492, DOI 10.1109/IEMBS.2011.6090691 Matthews D.E., 2005, MULTIPLE LINEAR REGR, V5, P3428 Moraes JCTB, 2000, COMPUT CARDIOL, V27, P211 PERLOFF D, 1993, CIRCULATION, V88, P2460 Pickering TG, 2005, HYPERTENSION, V45, P142, DOI 10.1161/01.HYP.0000150859.47929.8e Smola AJ, 2004, STAT COMPUT, V14, P199, DOI 10.1023/B:STCO.0000035301.49549.88 Soueidan K, 2012, PHYSIOL MEAS, V33, P881, DOI 10.1088/0967-3334/33/6/881 Sukor JA, 2012, PHYSIOL MEAS, V33, P465, DOI 10.1088/0967-3334/33/3/465 Ursino M, 1996, IEEE T BIO-MED ENG, V43, P761, DOI 10.1109/10.508540 van Popele NM, 2000, HYPERTENSION, V36, P484 World Heart Federation, HYPERTENSION Yu PS, 2006, J HYDROL, V328, P704, DOI 10.1016/j.jhydrol.2006.01.021 Zhu ZX, 2007, IEEE T SYST MAN CY B, V37, P70, DOI 10.1109/TSMCB.2006.883267 Lim, Pooi Khoon Ng, Siew-Cheok Jassim, Wissam A. Redmond, Stephen J. Zilany, Mohammad Avolio, Alberto Lim, Einly Tan, Maw Pin Lovell, Nigel H. Ministry of Higher Education of Malaysia UM.C/HIR/MOHE/ENG/50; University of Malaya Research Grant RP028-14HTM; Australian Research Council Linkages scheme Authors thank Ministry of Higher Education of Malaysia (UM.C/HIR/MOHE/ENG/50), University of Malaya Research Grant (RP028-14HTM) and the Australian Research Council Linkages scheme for financial support. 0 MDPI AG BASEL SENSORS-BASEL
Uncontrolled Keywords: Oscillometric blood pressure estimation, multiple linear regression, support vector regression, MAXIMUM AMPLITUDE ALGORITHM, SUPPORT VECTOR REGRESSION, FILTER,
Subjects: T Technology > T Technology (General)
T Technology > TA Engineering (General). Civil engineering (General)
Depositing User: Mr Jenal S
Date Deposited: 14 Apr 2016 06:53
Last Modified: 14 Apr 2016 06:53

Actions (login required)

View Item View Item