Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques

Moajjem Hossain Chowdhury, Md Nazmul Islam Shuzan, Muhammad E H Chowdhury, Zaid B Mahbub, M Monir Uddin, Amith Khandakar, Mamun Bin Ibne Reaz, Moajjem Hossain Chowdhury, Md Nazmul Islam Shuzan, Muhammad E H Chowdhury, Zaid B Mahbub, M Monir Uddin, Amith Khandakar, Mamun Bin Ibne Reaz

Abstract

Hypertension is a potentially unsafe health ailment, which can be indicated directly from the blood pressure (BP). Hypertension always leads to other health complications. Continuous monitoring of BP is very important; however, cuff-based BP measurements are discrete and uncomfortable to the user. To address this need, a cuff-less, continuous, and noninvasive BP measurement system is proposed using the photoplethysmograph (PPG) signal and demographic features using machine learning (ML) algorithms. PPG signals were acquired from 219 subjects, which undergo preprocessing and feature extraction steps. Time, frequency, and time-frequency domain features were extracted from the PPG and their derivative signals. Feature selection techniques were used to reduce the computational complexity and to decrease the chance of over-fitting the ML algorithms. The features were then used to train and evaluate ML algorithms. The best regression models were selected for systolic BP (SBP) and diastolic BP (DBP) estimation individually. Gaussian process regression (GPR) along with the ReliefF feature selection algorithm outperforms other algorithms in estimating SBP and DBP with a root mean square error (RMSE) of 6.74 and 3.59, respectively. This ML model can be implemented in hardware systems to continuously monitor BP and avoid any critical health conditions due to sudden changes.

Keywords: blood pressure; feature selection algorithm; machine learning; photoplethysmograph.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
A typical photoplethysmograph (PPG) waveform with notch, systolic peak, and diastolic peak.
Figure 2
Figure 2
Overall system block diagram.
Figure 3
Figure 3
Comparison of waveforms that are fit and unfit for the study. (a) Fit data; (b) unfit data.
Figure 4
Figure 4
PPG signal. (a) Before normalization; (b) after normalization.
Figure 5
Figure 5
Filtered signals overlaid on the raw PPG signal.
Figure 6
Figure 6
Baseline correction of PPG waveform. (a) PPG waveform with the baseline wandering and fourth degree polynomial trend; (b) PPG waveform after detrending.
Figure 7
Figure 7
Overview of feature extraction.
Figure 8
Figure 8
Algorithm of notch detection.
Figure 9
Figure 9
Demonstration of dicrotic notch detection for different age groups: Case 1 (26 years), 2 (45 years), and 3 (80 years). (a) Filtered PPG signal where we draw a line from systolic peak to diastolic peak; (b) subtract the line from the signal and find its minimum point; (c) initial notch detected; (d) adjust the notch using the fix index.
Figure 10
Figure 10
Detection of the foot of a PPG waveform. (a) Filtered PPG signal; (b) second derivative of PPG along with derivation of the zone of interest based on moving average of acceleration plethysmogram (APG) and adaptive threshold; (c) foot of the signal detected.
Figure 11
Figure 11
(a) Illustration of time-domain features in a PPG signal. (b) First and second derivatives of PPG signal.
Figure 12
Figure 12
Frequency-domain representation of PPG signal with important features.
Figure 13
Figure 13
Optimization of the Gaussian process regression (GPR) model during training.
Figure 14
Figure 14
Comparison of the predicted output vs. actual target for SBP estimation using different GPR: (a–c) Models without optimization, (d–f) models with optimization.
Figure 15
Figure 15
Comparison of the predicted output vs. actual target for DBP estimation using different GPR: (a–c) Models without optimization, (d–f) models with optimization.

References

    1. Why is Blood Pressure Important. [(accessed on 23 January 2020)]; Available online:
    1. 24-Hour Ambulatory Blood Pressure Monitoring (ABPM) [(accessed on 23 January 2020)]; Available online:
    1. Chowdhury M.E., Alzoubi K., Khandakar A., Khallifa R., Abouhasera R., Koubaa S., Ahmed R., Hasan A. Wearable real-time heart attack detection and warning system to reduce road accidents. Sensors. 2019;19:2780. doi: 10.3390/s19122780.
    1. Chowdhury M.E., Khandakar A., Alzoubi K., Mansoor S., Tahir A.M., Reaz M.B.I., Al-Emadi N. Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring. Sensors. 2019;19:2781. doi: 10.3390/s19122781.
    1. Lee H., Kim E., Lee Y., Kim H., Lee J., Kim M., Yoo H.-J., Yoo S. Toward all-day wearable health monitoring: An ultralow-power, reflective organic pulse oximetry sensing patch. Sci. Adv. 2018;4:eaas9530. doi: 10.1126/sciadv.aas9530.
    1. Chandrasekhar A., Kim C.-S., Naji M., Natarajan K., Hahn J.-O., Mukkamala R. Smartphone-based blood pressure monitoring via the oscillometric finger-pressing method. Sci. Transl. Med. 2018;10:eaap8674. doi: 10.1126/scitranslmed.aap8674.
    1. Liang Y., Chen Z., Ward R., Elgendi M. Photoplethysmography and deep learning: Enhancing hypertension risk stratification. Biosensors. 2018;8:101. doi: 10.3390/bios8040101.
    1. Elgendi M., Fletcher R., Liang Y., Howard N., Lovell N.H., Abbott D., Lim K., Ward R. The use of photoplethysmography for assessing hypertension. NPJ Digit. Med. 2019;2:1–11. doi: 10.1038/s41746-019-0136-7.
    1. Elgendi M. On the analysis of fingertip photoplethysmogram signals. Curr. Cardiol. Rev. 2012;8:14–25. doi: 10.2174/157340312801215782.
    1. Allen J. Photoplethysmography and its application in clinical physiological measurement. Physiol. Meas. 2007;28:R1. doi: 10.1088/0967-3334/28/3/R01.
    1. Otsuka T., Kawada T., Katsumata M., Ibuki C. Utility of second derivative of the finger photoplethysmogram for the estimation of the risk of coronary heart disease in the general population. Circ. J. 2006;70:304–310. doi: 10.1253/circj.70.304.
    1. Millasseau S.C., Kelly R., Ritter J., Chowienczyk P. Determination of age-related increases in large artery stiffness by digital pulse contour analysis. Clin. Sci. 2002;103:371–377. doi: 10.1042/cs1030371.
    1. Zheng Y., Poon C.C., Yan B.P., Lau J.Y. Pulse arrival time based cuff-less and 24-H wearable blood pressure monitoring and its diagnostic value in hypertension. J. Med. Syst. 2016;40:195. doi: 10.1007/s10916-016-0558-6.
    1. Lee C., Shin H.S., Lee M. Relations between ac-dc components and optical path length in photoplethysmography. J. Biomed. Opt. 2011;16:077012. doi: 10.1117/1.3600769.
    1. Utami N., Setiawan A.W., Zakaria H., Mengko T.R., Mengko R. Extracting blood flow parameters from Photoplethysmograph signals: A review; Proceedings of the 2013 3rd International Conference on Instrumentation, Communications, Information Technology and Biomedical Engineering (ICICI-BME); Bandung, Indonesia. 7–8 November 2013; pp. 403–407.
    1. Bashkatov A., Genina E., Kochubey V., Tuchin V. Optical properties of human skin, subcutaneous and mucous tissues in the wavelength range from 400 to 2000 nm. J. Phys. D Appl. Phys. 2005;38:2543. doi: 10.1088/0022-3727/38/15/004.
    1. Van Gastel M., Stuijk S., de Haan G. New principle for measuring arterial blood oxygenation, enabling motion-robust remote monitoring. Sci. Rep. 2016;6:1–16. doi: 10.1038/srep38609.
    1. Liang Y., Elgendi M., Chen Z., Ward R. An optimal filter for short photoplethysmogram signals. Sci. Data. 2018;5:180076. doi: 10.1038/sdata.2018.76.
    1. Waugh W., Allen J., Wightman J., Sims A.J., Beale T.A. Novel signal noise reduction method through cluster analysis, applied to photoplethysmography. Comput. Math. Methods Med. 2018;2018:6812404. doi: 10.1155/2018/6812404.
    1. Lee H., Chung H., Ko H., Lee J. Wearable multichannel photoplethysmography framework for heart rate monitoring during intensive exercise. IEEE Sens. J. 2018;18:2983–2993. doi: 10.1109/JSEN.2018.2801385.
    1. Xing X., Ma Z., Zhang M., Zhou Y., Dong W., Song M. An Unobtrusive and Calibration-free Blood pressure estimation Method using photoplethysmography and Biometrics. Sci. Rep. 2019;9:1–8. doi: 10.1038/s41598-019-45175-2.
    1. Rundo F., Ortis A., Battiato S., Conoci S. Advanced bio-inspired system for noninvasive cuff-less blood pressure estimation from physiological signal analysis. Computation. 2018;6:46. doi: 10.3390/computation6030046.
    1. Kim J.Y., Cho B.H., Im S.M., Jeon M.J., Kim I.Y., Kim S.I. Comparative study on artificial neural network with multiple regressions for continuous estimation of blood pressure; Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference; Shanghai, China. 17–18 January 2006; pp. 6942–6945.
    1. Kachuee M., Kiani M.M., Mohammadzade H., Shabany M. Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time; Proceedings of the 2015 IEEE International Symposium on Circuits and Systems (ISCAS); Lisbon, Portugal. 24–27 May 2015; pp. 1006–1009.
    1. Cattivelli F.S., Garudadri H. Noninvasive cuffless estimation of blood pressure from pulse arrival time and heart rate with adaptive calibration; Proceedings of the 2009 Sixth International Workshop on Wearable and Implantable Body Sensor Networks; Berkeley, CA, USA. 3–5 June 2009; pp. 114–119.
    1. Xing X., Sun M. Optical blood pressure estimation with photoplethysmography and FFT-based neural networks. Biomed. Opt. Express. 2016;7:3007–3020. doi: 10.1364/BOE.7.003007.
    1. Zhang Y., Feng Z. A SVM method for continuous blood pressure estimation from a PPG signal; Proceedings of the 9th International Conference on Machine Learning and Computing; Singapore. 24–26 February 2017; pp. 128–132.
    1. Su P., Ding X.-R., Zhang Y.-T., Liu J., Miao F., Zhao N. Long-term blood pressure prediction with deep recurrent neural networks; Proceedings of the 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI); Las Vegas, NV, USA. 4–7 March 2018; pp. 323–328.
    1. Gotlibovych I., Crawford S., Goyal D., Liu J., Kerem Y., Benaron D., Yilmaz D., Marcus G., Li Y. End-to-end deep learning from raw sensor data: Atrial fibrillation detection using wearables. arXiv. 20181807.10707
    1. Slapničar G., Mlakar N., Luštrek M. Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network. Sensors. 2019;19:3420. doi: 10.3390/s19153420.
    1. Liang G.L.Y., Chen Z., Elgendi M. PPG-BP Database. [(accessed on 21 October 2019)];2018 Available online:
    1. Liang Y., Chen Z., Liu G., Elgendi M. A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China. Sci. Data. 2018;5:180020. doi: 10.1038/sdata.2018.20.
    1. Liang Y., Chen Z., Ward R., Elgendi M. Hypertension assessment via ECG and PPG signals: An evaluation using MIMIC database. Diagnostics. 2018;8:65. doi: 10.3390/diagnostics8030065.
    1. Liang Y., Chen Z., Ward R., Elgendi M. Hypertension assessment using photoplethysmography: A risk stratification approach. J. Clin. Med. 2019;8:12. doi: 10.3390/jcm8010012.
    1. Ferdinando H., Huotari M., Myllylä T. Photoplethysmography signal analysis to assess obesity, age group and hypertension; Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Berlin, Germany. 23–27 July 2019; pp. 5572–5575.
    1. Kavsaoğlu A.R., Polat K., Hariharan M. Non-invasive prediction of hemoglobin level using machine learning techniques with the PPG signal’s characteristics features. Appl. Soft Comput. 2015;37:983–991. doi: 10.1016/j.asoc.2015.04.008.
    1. Elgendi M., Norton I., Brearley M., Abbott D., Schuurmans D. Detection of a and b waves in the acceleration photoplethysmogram. Biomed. Eng. Online. 2014;13:139. doi: 10.1186/1475-925X-13-139.
    1. Kavsaoğlu A.R., Polat K., Bozkurt M.R. A novel feature ranking algorithm for biometric recognition with PPG signals. Comput. Biol. Med. 2014;49:1–14. doi: 10.1016/j.compbiomed.2014.03.005.
    1. Mahbub Z.B., Rabbani K. Frequency domain analysis to identify neurological disorders from evoked EMG responses. J. Biol. Phys. 2007;33:99–108. doi: 10.1007/s10867-007-9045-0.
    1. Yang S., Zhang Y., Cho S.-Y., Morgan S.P., Correia R., Wen L. Cuff-less blood pressure measurement using fingertip photoplethysmogram signals and physiological characteristics; Proceedings of the Optics in Health Care and Biomedical Optics VIII; Beijing, China. 23 October 2018; p. 1082036.
    1. Chatterjee A., Roy U.K. PPG Based Heart Rate Algorithm Improvement with Butterworth IIR Filter and Savitzky-Golay FIR Filter; Proceedings of the 2018 2nd International Conference on Electronics, Materials Engineering & Nano-Technology (IEMENTech); Kolkata, India. 4–5 May 2018; pp. 1–6.
    1. Sun S., Peeters W.H., Bezemer R., Long X., Paulussen I., Aarts R.M., Noordergraaf G.J. Finger and forehead photoplethysmography-derived pulse-pressure variation and the benefits of baseline correction. J. Clin. Monit. Comput. 2019;33:65–75. doi: 10.1007/s10877-018-0140-5.
    1. Maxwell J.C. A Treatise on Electricity and Magnetism. Vol. 1 Clarendon Press; Oxford, UK: 1881.
    1. McDuff D., Gontarek S., Picard R.W. Remote detection of photoplethysmographic systolic and diastolic peaks using a digital camera. IEEE Trans. Biomed. Eng. 2014;61:2948–2954. doi: 10.1109/TBME.2014.2340991.
    1. Laurin A. BP_Annotate. [(accessed on 21 November 2019)]; Available online:
    1. Pan J., Tompkins W.J. A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 1985;32:230–236. doi: 10.1109/TBME.1985.325532.
    1. Sun J., Reisner A., Mark R. A signal abnormality index for arterial blood pressure waveforms; Proceedings of the 2006 Computers in Cardiology; Valencia, Spain. 17–20 September 2006; pp. 13–16.
    1. Monte-Moreno E. Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques. Artif. Intell. Med. 2011;53:127–138. doi: 10.1016/j.artmed.2011.05.001.
    1. Kurylyak Y., Lamonaca F., Grimaldi D. A Neural Network-based method for continuous blood pressure estimation from a PPG signal; Proceedings of the 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC); Minneapolis, MN, USA. 6–9 May 2013; pp. 280–283.
    1. Kira K., Rendell L.A. The feature selection problem: Traditional methods and a new algorithm. Aaai. 1992;2:129–134.
    1. Kononenko I., Šimec E., Robnik-Šikonja M. Overcoming the myopia of inductive learning algorithms with RELIEFF. Appl. Intell. 1997;7:39–55. doi: 10.1023/A:1008280620621.
    1. Roffo G. Ranking to learn and learning to rank: On the role of ranking in pattern recognition applications. arXiv. 20171706.05933
    1. Ding C., Peng H. Minimum redundancy feature selection from microarray gene expression data. J. Bioinform. Comput. Biol. 2005;3:185–205. doi: 10.1142/S0219720005001004.
    1. Darbellay G.A., Vajda I. Estimation of the information by an adaptive partitioning of the observation space. IEEE Trans. Inf. Theory. 1999;45:1315–1321. doi: 10.1109/18.761290.
    1. Khandakar A., Chowdhury M.E.H., Kazi M.K., Benhmed K., Touati F., Al-Hitmi M., Antonio S.P., Jr. Gonzales. Machine learning based photovoltaics (PV) power prediction using different environmental parameters of Qatar. Energies. 2019;12:2782. doi: 10.3390/en12142782.
    1. Sit H. Quick Start to Gaussian Process Regression. [(accessed on 23 January 2020)]; Available online:
    1. Ensemble Algorithms. [(accessed on 23 January 2020)]; Available online:
    1. Filion A. (1994–2020). Applied Machine Learning, Part 3: Hyperparameter Optimization. [(accessed on 23 January 2020)]; Available online:
    1. Zadi A.S., Alex R., Zhang R., Watenpaugh D.E., Behbehani K. Arterial blood pressure feature estimation using photoplethysmography. Comput. Biol. Med. 2018;102:104–111. doi: 10.1016/j.compbiomed.2018.09.013.
    1. Stergiou G.S., Alpert B., Mieke S., Asmar R., Atkins N., Eckert S., Frick G., Friedman B. A universal standard for the validation of blood pressure measuring devices: Association for the Advancement of Medical Instrumentation/European Society of Hypertension/International Organization for Standardization (AAMI/ESH/ISO) Collaboration Statement. Hypertension. 2018;71:368–374. doi: 10.1161/HYPERTENSIONAHA.117.10237.
    1. Mousavi S.S., Firouzmand M., Charmi M., Hemmati M., Moghadam M., Ghorbani Y. Blood pressure estimation from appropriate and inappropriate PPG signals using A whole-based method. Biomed. Signal Process. Control. 2019;47:196–206. doi: 10.1016/j.bspc.2018.08.022.
    1. Association for the Advancement of Medical Instrumentation . American National Standard. Manual, Electronic or Automated Sphygmomanometers. Association for the Advancement of Medical Instrumentation; Arlington, VA, USA: 2003. ANSI/AAMI SP10-2002/A1.
    1. O’brien E., Waeber B., Parati G., Staessen J., Myers M.G. Blood pressure measuring devices: Recommendations of the European Society of Hypertension. BMJ. 2001;322:531–536. doi: 10.1136/bmj.322.7285.531.

Source: PubMed

Sponsorer og samarbeidspartnere

Medisinsk tilstand

Legemiddelintervensjoner

3
Abonnere