Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter April 8, 2021

A clinical set-up for noninvasive blood pressure monitoring using two photoplethysmograms and based on convolutional neural networks

  • Jamal Esmaelpoor EMAIL logo , Zahra Momayez Sanat and Mohammad Hassan Moradi

Abstract

Blood pressure is a reliable indicator of many cardiac arrhythmias and rheological problems. This study proposes a clinical set-up using conventional monitoring systems to estimate systolic and diastolic blood pressures continuously based on two photoplethysmogram signals (PPG) taken from the earlobe and toe. Several amendments were applied to conventional clinical monitoring devices to construct our project plan. We used two monitors to acquire two PPGs, one ECG, and invasive blood pressure as the reference to evaluate the estimation accuracy. One of the most critical requirements was the synchronization of the acquired signals that was accomplished by using ECG as the time reference. Following data acquisition and preparation procedures, the performance of each PPG signal alone and together was investigated using deep convolutional neural networks. The proposed architecture was evaluated on 32 records acquired from 14 patients after cardiovascular surgery. The results showed a better performance for toe PPG in comparison with earlobe PPG. Moreover, they indicated the algorithm accuracy improves if both signals are applied together to the network. According to the British Hypertension Society standards, the results achieved grade A for both blood pressure measurements. The mean and standard deviation of estimation errors were +0.3 ± 4.9 and +0.1 ± 3.2 mmHg for systolic and diastolic BPs, respectively. Since the method is based on conventional monitoring equipment and provides a high estimation consistency, it can be considered as a possible alternative for inconvenient invasive BP monitoring in clinical environments.


Corresponding author: Jamal Esmaelpoor, Department of Electrical Engineering, Islamic Azad University, Boukan Branch, Boukan, Iran, E-mail:

Acknowledgments

We gratefully thank Pooyandegan Rahe Saadat Company and also Shahid Rajayie Heart Hospital and Shariati Hospital for their assistance while acquiring the research data. This research would not have been possible without their cooperation.

References

1. Jamison, DT, Breman, JG, Measham, AR, Alleyne, G, Claeson, M, Evans, DB, editors, et al.. Disease control priorities in developing countries. Washington, DC: The World Bank; 2006.10.1596/978-0-8213-6179-5Search in Google Scholar

2. Chen, Y, Wen, C, Tao, G, Bi, M. Continuous and noninvasive measurement of systolic and diastolic blood pressure by one mathematical model with the same model parameters and two separate pulse wave velocities. Ann Biomed Eng 2012;40:871–82.10.1007/s10439-011-0467-2Search in Google Scholar PubMed

3. Hill, DW. The direct and indirect measurement of blood pressure. Med Biol Eng 1970;8:605. https://doi.org/10.1007/BF02478236.Search in Google Scholar

4. Fortin, J, Wellisch, A, Maier, K. CNAP--evolution of continuous non-invasive arterial blood pressure monitoring. Biomed Eng Tech 2013;58.10.1515/bmt-2013-4179Search in Google Scholar PubMed

5. Chrubasik, S, Droste, C, Glimm, E, Black, A. Comparison of different methods of blood pressure measurements. Blood Pres Monit 2007;12:157–66.10.1097/MBP.0b013e3280ad4073Search in Google Scholar PubMed

6. Webster, J, Clark, J. Medical instrumentation: application and design; 1995. Available from: http://www.just.edu.jo/CoursesAndLabs/BIOMEDICAL INSTRUMENTATION II_BME442/biomedical Instrumentation II-SYLLABUS.doc [Accessed 2 Jan 2020].10.1097/00004669-197807000-00017Search in Google Scholar

7. Mattu, GS, Perry, TLJr., Wright, JM. Comparison of the oscillometric blood pressure monitor (BPM-100 Beta) with the auscultatory mercury sphygmomanometer. Blood Pres Monit 2001;6:153–9.10.1097/00126097-200106000-00007Search in Google Scholar PubMed

8. Mackay, RS. The application of physical transducers to intracavity pressure measurement, with special reference to tonometry. Med Electron Biol Eng 1964;2:3–19.10.1007/BF02474356Search in Google Scholar PubMed

9. Lin, W-H, Wang, H, Samuel, OW, Liu, G, Huang, Z, Li, G. New photoplethysmogram indicators for improving cuffless and continuous blood pressure estimation accuracy. Physiol Meas 2018;39:25005.10.1088/1361-6579/aaa454Search in Google Scholar PubMed

10. Weber, S, Scharfschwerdt, P, Schauer, T, Seel, T, Kertzscher, U, Affeld, K. Continuous wrist blood pressure measurement with ultrasound. Biomed Eng Tech 2013;1.10.1515/bmt-2013-4124Search in Google Scholar PubMed

11. Zhao, Y, Kullmann, WH. Determining blood pressure changes and vascular stiffness state using optical pulse pressure analysis. Biomed Eng Tech 2013;58.10.1515/bmt-2013-4188Search in Google Scholar PubMed

12. Moens, AI. Over de voortplantingssnelheid van den pols [Doctoral dissertation]. University of Leiden, Leiden; 1877.Search in Google Scholar

13. Zhang, Q. Cuff-free blood pressure estimation using signal processing techniques. Saskatoon, SK, Canada: Master thesis, University of Saskatchewan; 2010.Search in Google Scholar

14. Sondej, T, Sieczkowski, K, Olszewski, R, Dobrowolski, A. Simultaneous multi-site measurement system for the assessment of pulse wave delays. Biocybernet Biomed Eng 2019;39:488–502.10.1016/j.bbe.2019.01.001Search in Google Scholar

15. Allen, J. Photoplethysmography and its application in clinical physiological measurement. Physiol Meas 2007;28:R1.10.1088/0967-3334/28/3/R01Search in Google Scholar PubMed

16. Peltokangas, M, Vehkaoja, A, Huotari, M, Verho, J, Mattila, VM, Röning, J, et al.. Combining finger and toe photoplethysmograms for the detection of atherosclerosis. Physiol Meas 2017;38:139.10.1088/1361-6579/aa4eb0Search in Google Scholar PubMed

17. Gandhi, PG, Rao, GHR. The spectral analysis of photoplethysmography to evaluate an independent cardiovascular risk factor. Int J Gen Med 2014;7:539.10.2147/IJGM.S70892Search in Google Scholar PubMed PubMed Central

18. Geddes, LA, Voelz, MH, Babbs, CF, Bourland, JD, Tacker, WA. Pulse transit time as an indicator of arterial blood pressure. Psychophysiology 1981;18:71–4.10.1111/j.1469-8986.1981.tb01545.xSearch in Google Scholar PubMed

19. Baek, HJ, Kim, KK, Kim, JS, Lee, B, Park, KS. Enhancing the estimation of blood pressure using pulse arrival time and two confounding factors. Physiol Meas 2009;31:145.10.1088/0967-3334/31/2/002Search in Google Scholar PubMed

20. Rajala, S, Lindholm, H, Taipalus, T. Comparison of photoplethysmogram measured from wrist and finger and the effect of measurement location on pulse arrival time. Physiol Meas 2018;39:75010.10.1088/1361-6579/aac7acSearch in Google Scholar PubMed

21. Griggs, D, Sharma, M, Naghibi, A, Wallin, C, Ho, V, Barbosa, K, et al.. Design and development of continuous cuff-less blood pressure monitoring devices. In: 2016 IEEE sensors. IEEE, Orlando, FL, USA; 2016.10.1109/ICSENS.2016.7808908Search in Google Scholar

22. Thambiraj, G, Gandhi, U, Devanand, V, Umapathy, M. Noninvasive cuffless blood pressure estimation using pulse transit time, womersley number, and photoplethysmogram intensity ratio. Physiol Meas 2019;40:075001.10.1088/1361-6579/ab1f17Search in Google Scholar PubMed

23. Ding, X-R, Zhang, Y-T, Liu, J, Dai, W-X, Tsang, HK. Continuous cuffless blood pressure estimation using pulse transit time and photoplethysmogram intensity ratio. IEEE Trans Biomed Eng 2015;63:964–72.10.1109/TBME.2015.2480679Search in Google Scholar PubMed

24. Dawber, TR, THomas, HEJr., McNamara, PM. Characteristics of the dicrotic notch of the arterial pulse wave in coronary heart disease. Angiology 1973;24:244–55.10.1177/000331977302400407Search in Google Scholar PubMed

25. Tanveer, MS, Hasan, MK. Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network. Biomed Signal Process Contr 2019;51:382–92.10.1016/j.bspc.2019.02.028Search in Google Scholar

26. Xing, X, Sun, M. Optical blood pressure estimation with photoplethysmography and FFT-based neural networks. Biomed Opt Express 2016;7:3007–20.10.1364/BOE.7.003007Search in Google Scholar PubMed PubMed Central

27. Esmaelpoor, J, Moradi, MH, Kadkhodamohammadi, A. A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals. Comput Biol Med 2020;103719.10.1016/j.compbiomed.2020.103719Search in Google Scholar PubMed

28. Abayomi, EJ. The relationship between body mass and blood pressure in diverse populations. Tallahassee, Florida, USA: Dissertation of doctor of philosophy. Florida State University; 2012.Search in Google Scholar

29. Campbell, B, Richley, D, Ross, C, Eggett, CJ. Clinical Guidelines by consensus: recording a standard 12-lead electrocardiogram. An approved method by the Society for Cardiological Science and Technology (SCST). 2017. Available at: http://www.scst.org.uk/resources/SCST_ECG_Recording_Guidelines_2017.10.12968/bjca.2017.12.2.77Search in Google Scholar

30. Addison, PS, Wang, R, Uribe, AA, Bergese, SD. Increasing signal processing sophistication in the calculation of the respiratory modulation of the photoplethysmogram (DPOP). J Clin Monit Comput 2015;29:363–72.10.1007/s10877-014-9613-3Search in Google Scholar PubMed PubMed Central

31. Ramakrishnan, AG, Prathosh, AP, Ananthapadmanabha, TV. Threshold-independent QRS detection using the dynamic plosion index. IEEE Signal Process Lett 2014;21:554–8.10.1109/LSP.2014.2308591Search in Google Scholar

32. Goodfellow, I, Bengio, Y, Courville, A. Deep learning. Cambridge, Massachusetts: MIT Press; 2016.Search in Google Scholar

33. Praveena, S, Singh, SP. Sparse-FCM and deep convolutional neural network for the segmentation and classification of acute lymphoblastic leukaemia. Biomed Tech 2020;65:759–73.10.1515/bmt-2018-0213Search in Google Scholar PubMed

34. Hubel, DH, Wiesel, TN. Receptive fields and functional architecture of monkey striate cortex. J Physiol 1968;195:215–43.10.1113/jphysiol.1968.sp008455Search in Google Scholar PubMed PubMed Central

35. Fukushima, K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 1980;36:193–202.10.1007/BF00344251Search in Google Scholar PubMed

36. Srivastava, N, Hinton, G, Krizhevsky, A, Sutskever, I, Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014;15:1929–58.Search in Google Scholar

37. Slapničar, G, Luštrek, M, Marinko, M. Continuous blood pressure estimation from PPG signal. Informatica 2018;42.Search in Google Scholar

38. Kachuee, M, Kiani, MM, Mohammadzade, H, Shabany, M. Cuffless blood pressure estimation algorithms for continuous health-care monitoring. IEEE Trans Biomed Eng 2016;64:859–69.10.1109/TBME.2016.2580904Search in Google Scholar PubMed

39. Hartmann, V, Liu, H, Chen, F, Qiu, Q, Hughes, S, Zheng, D. Quantitative comparison of photoplethysmographic waveform characteristics: effect of measurement site. Front Physiol 2019;10.10.3389/fphys.2019.00198Search in Google Scholar PubMed PubMed Central

40. Chandra, A, Neeland, IJ, Berry, JD, Ayers, CR, Rohatgi, A, Das, SR, et al.. The relationship of body mass and fat distribution with incident hypertension: observations from the Dallas Heart Study. J Am Coll Cardiol 2014;64:997–1002.10.1016/j.jacc.2014.05.057Search in Google Scholar PubMed

41. Mills, PJ, Farag, NH, Matthews, S, Nelesen, RA, Berry, CC, Dimsdale, JE. Hormone replacement therapy does not affect 24-h ambulatory blood pressure in healthy non-smoking postmenopausal women. Blood Press Monit 2003;8:57–61.10.1097/00126097-200304000-00001Search in Google Scholar PubMed

42. O’Brien, E, Petrie, J, Littler, W, Padfield, PL, O’Malley, K, Jamieson, M, et al.. The British Hypertension Society protocol for the evaluation of automated and semi-automated blood pressure measuring devices with special reference to ambulatory systems. J Hypertens 1990;8:607–19.10.1097/00004872-199007000-00004Search in Google Scholar PubMed

43. Kim, JS, Kim, KK, Baek, HJ, Park, KS. Effect of confounding factors on blood pressure estimation using pulse arrival time. Physiol Meas 2008;29:615.10.1088/0967-3334/29/5/007Search in Google Scholar PubMed

44. Lazazzera, R, Belhaj, Y, Carrault, G. A new wearable device for blood pressure estimation using photoplethysmogram. Sensors 2019;19:2557.10.3390/s19112557Search in Google Scholar PubMed PubMed Central

45. Mottaghi, S, Moradi, M, Roohisefat, L. Cuffless blood pressure estimation during exercise stress test. Int J Biosci Biochem Bioinformat 2012;2:394.10.7763/IJBBB.2012.V2.140Search in Google Scholar

46. Kamalzadeh, S. PTT-based method for noninvasive beat-to-beat estimation of systolic and diastolic blood pressure. Master thesis, Amirkabir. Tehran, Iran: University of Technology; 2016.Search in Google Scholar

Received: 2020-07-30
Accepted: 2021-03-22
Published Online: 2021-04-08
Published in Print: 2021-08-26

© 2021 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 28.3.2024 from https://www.degruyter.com/document/doi/10.1515/bmt-2020-0197/pdf
Scroll to top button