Advertisement

Machine Learning Techniques

  • Xiaorong DingEmail author
Chapter

Abstract

Driven by the exponential growth in the computational power and the increasing size of the collected data sets, there has been growing interest in using data-driven approaches based on machine learning techniques to resolve the problems and overcome the challenges that facing the area of cuffless blood pressure measurement. Compared with the theory-driven analytical approaches, the machine learning method is very promising with its ability to learn the function of the complex system if the model is trained well, and to address the latent affecting factors that cannot be considered in the analytical model. This chapter first addresses the motivation of employing data-driven method, then provides a brief introduction of machine learning method for cuffless blood pressure estimation. It then presents some of the state-of-the-art examples and applications of such technology and finally discusses the outlook of its future development.

Keywords

Machine learning Cuffless blood pressure Data-driven method Analytical model Pulse transit time Blood pressure indicator Learning model Deep learning 

References

  1. 1.
    Nichols W, O’Rourke M, Vlachopoulos C. McDonald’s blood flow in arteries: theoretical, experimental and clinical principles. Boca Raton, FL: CRC; 2011.Google Scholar
  2. 2.
    Hughes DJ, Babbs CF, Geddes LA, Bourland JD. Measurements of Young’s modulus of elasticity of the canine aorta with ultrasound. Ultrason Imaging. 1979;1(4):356–67.PubMedPubMedCentralCrossRefGoogle Scholar
  3. 3.
    Weltman G, Sullivan G, Bredon D. The continuous measurement of arterial pulse wave velocity. Med Biol Eng Comput. 1964;2(2):145–54.Google Scholar
  4. 4.
    Obrist PA, Light KC, McCubbin JA, Hutcheson JS, Hoffer JL. Pulse transit time: relationship to blood pressure. Behav Res Methods Instrum. 1978;10(5):623–6.CrossRefGoogle Scholar
  5. 5.
    Williams JGL, Williams B. Arterial pulse wave velocity as a psychophysiological measure, (in English). Psychosom Med. 1965;27(5):408–14.PubMedCrossRefGoogle Scholar
  6. 6.
    Gribbin B, Steptoe A, Sleight P. Pulse wave velocity as a measure of blood pressure change, (in English). Psychophysiology. 1976;13(1):86–90.PubMedCrossRefGoogle Scholar
  7. 7.
    Steptoe A, Smulyan H, Gribbin B. Pulse-wave velocity and blood-pressure change—calibration and applications, (in English). Psychophysiology. 1976;13(5):488–93.PubMedPubMedCentralCrossRefGoogle Scholar
  8. 8.
    Obrist PA, Light KC, McCubbin JA, Hutcheson J, Hoffer JL. Pulse transit time: relationship to blood pressure and myocardial performance. Psychophysiology. 1979;16(3):292–301.PubMedCrossRefGoogle Scholar
  9. 9.
    Allen RA, Schneider JA, Davidson DM, Winchester MA, Taylor CB. The covariation of blood pressure and pulse transit time in hypertensive patients, (in English). Psychophysiology. 1981;18(3):301–6.PubMedCrossRefGoogle Scholar
  10. 10.
    Geddes LA, Voelz MH, Babbs CF, Bourland JD, Tacker WA. Pulse transit time as an indicator of arterial blood pressure,(in English). Psychophysiology. 1981;18(1):71–4.CrossRefGoogle Scholar
  11. 11.
    Newlin DB. Relationships of pulse transmission times to pre-ejection period and blood pressure. Psychophysiology. 1981;18(3):316–21.PubMedCrossRefGoogle Scholar
  12. 12.
    Lane JD, Greenstadt L, Shapiro D, Rubinstein E. Pulse transit time and blood pressure—an intensive analysis, (in English). Psychophysiology. 1983;20(1):45–9.PubMedCrossRefGoogle Scholar
  13. 13.
    Pollak MH, Obrist PA. Aortic radial pulse transit time and ECG Q-wave to radial pulse wave interval as indexes of beat-by-beat blood pressure change, (in English). Psychophysiology. 1983;20(1):21–8.PubMedCrossRefGoogle Scholar
  14. 14.
    Marie GV, Lo CR, Vanjones J, Johnston DW. The relationship between arterial blood pressure and pulse transit time during dynamic and static exercise, (in English). Psychophysiology. 1984;21(5):521–7.PubMedCrossRefGoogle Scholar
  15. 15.
    Sawada Y, Yamakoshi K. A correlation analysis between pulse transit time and instantaneous blood pressure measured indirectly by the vascular unloading method, (in English). Biol Psychol. 1985;21(1):1–9.PubMedCrossRefGoogle Scholar
  16. 16.
    Zong W, Moody G, Mark R. Effects of vasoactive drugs on the relationship between ECG-pulse wave delay time and arterial blood pressure in ICU patients. In: Computers in Cardiology, IEEE; 1998. p. 673–6.Google Scholar
  17. 17.
    Nitzan M, Khanokh B, Slovik Y. The difference in pulse transit time to the toe and finger measured by photoplethysmography (in English). Physiol Meas. 2002;23(1):85–93.PubMedCrossRefGoogle Scholar
  18. 18.
    Ahlstrom C, Johansson A, Uhlin F, Länne T, Ask P. Noninvasive investigation of blood pressure changes using the pulse wave transit time: a novel approach in the monitoring of hemodialysis patients. J Artif Organs. 2005;8(3):192–7.PubMedCrossRefGoogle Scholar
  19. 19.
    Muehlsteff J, Aubert X, Schuett M. Cuffless estimation of systolic blood pressure for short effort bicycle tests: the prominent role of the pre-ejection period. In: Conf Proc IEEE Eng Med Biol Soc, New York, USA, vol. 1, 2006. p. 5088–92.Google Scholar
  20. 20.
    Payne RA, Symeonides CN, Webb DJ, Maxwell SRJ. Pulse transit time measured from the ECG: an unreliable marker of beat-to-beat blood pressure, (in English). J Appl Physiol. 2006;100(1):136–41.PubMedPubMedCentralCrossRefGoogle Scholar
  21. 21.
    Marcinkevics Z, Greve M, Aivars JI, Erts R, Zehtabi AH. Relationship between arterial pressure and pulse wave velocity using photoplethysmography during the post-exercise recovery period. Acta Univ Latviensis Biol. 2009;753:59–68.Google Scholar
  22. 22.
    Wong MYM, Poon CCY, Zhang Y-T. An evaluation of the cuffless blood pressure estimation based on pulse transit time technique: a half year study on normotensive subjects, (in English). Cardiovasc Eng. 2009;9(1):32–8.PubMedPubMedCentralCrossRefGoogle Scholar
  23. 23.
    Zheng YL, et al. Unobtrusive sensing and wearable devices for health informatics. IEEE Trans Biomed Eng. 2014;61(5):1538–54.PubMedCrossRefGoogle Scholar
  24. 24.
    Young CC, Mark JB, White W, DeBree A, Vender JS, Fleming A. Clinical evaluation of continuous noninvasive blood pressure monitoring: accuracy and tracking capabilities. J Clin Monit. 1995;11(4):245–52.PubMedCrossRefGoogle Scholar
  25. 25.
    Chen W, Kobayashi T, Ichikawa S, Takeuchi Y, Togawa T. Continuous estimation of systolic blood pressure using the pulse arrival time and intermittent calibration (in English). Med Biol Eng Comput. 2000;38(5):569–74.PubMedPubMedCentralCrossRefGoogle Scholar
  26. 26.
    Fung P, Dumont G, Ries C, Mott C, Ansermino M. Continuous noninvasive blood pressure measurement by pulse transit time. In: Conf Proc IEEE Eng Med Biol Soc, 2004, vol. 1, IEEE, 2004. p. 738–41.Google Scholar
  27. 27.
    Poon CCY, Zhang YT. Cuff-less and noninvasive measurements of arterial blood pressure by pulse transit time. In: Conf Proc IEEE Eng Med Biol Soc, Shanghai, China. IEEE; 2005. p. 5877–5880.Google Scholar
  28. 28.
    Cattivelli FS, Garudadri H. Noninvasive cuffless estimation of blood pressure from pulse arrival time and heart rate with adaptive calibration. In: Sixth international workshop on wearable and implantable body sensor networks (BSN 2009): IEEE; 2009. p. 114–9.Google Scholar
  29. 29.
    Gesche H, Grosskurth D, Küchler G, Patzak A. Continuous blood pressure measurement by using the pulse transit time: comparison to a cuff-based method. Eur J Appl Physiol. 2012;112(1):309–15.PubMedPubMedCentralCrossRefGoogle Scholar
  30. 30.
    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(4):871–82.PubMedCrossRefGoogle Scholar
  31. 31.
    Ding XR, Zhang YT, Liu J, Dai WX, Tsang HK. Continuous cuffless blood pressure estimation using pulse transit time and photoplethysmogram intensity ratio. IEEE Trans Biomed Eng. 2016;63(5):964–72.CrossRefGoogle Scholar
  32. 32.
    Huynh TH, Jafari R, Chung WY. Noninvasive cuffless blood pressure estimation using pulse transit time and impedance plethysmography. IEEE Trans Biomed Eng. 2018.Google Scholar
  33. 33.
    Liu J, Yan B, Zhang Y, Ding XR, Peng S, Zhao N. Multi-wavelength photoplethysmography enabling continuous blood pressure measurement with compact wearable electronics. IEEE Trans Biomed Eng. 2018.Google Scholar
  34. 34.
    LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436.PubMedCrossRefGoogle Scholar
  35. 35.
    Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT Press; 2016.Google Scholar
  36. 36.
    Kim JY, Cho BH, Im SM, Jeon MJ, Kim IY, Kim SI. Comparative study on artificial neural network with multiple regressions for continuous estimation of blood pressure. In: Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the IEEE; 2005. p. 6942–5.Google Scholar
  37. 37.
    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(2):127–38.PubMedCrossRefGoogle Scholar
  38. 38.
    Ruiz-Rodríguez JC, et al. Innovative continuous non-invasive cuffless blood pressure monitoring based on photoplethysmography technology. Intensive Care Med. 2013;39(9):1618–25.PubMedCrossRefGoogle Scholar
  39. 39.
    Duan K, Qian Z, Atef M, Wang G. A feature exploration methodology for learning based cuffless blood pressure measurement using photoplethysmography. In: Engineering in medicine and biology society (EMBC), 2016 IEEE 38th annual international conference of the IEEE; 2016. p. 6385–8.Google Scholar
  40. 40.
    Shobitha S, Amita P, Krupa BN, Beng GK. Cuffless blood pressure prediction from PPG using relevance vector machine. In: Electrical, Electronics, Communication, Computer, and Optimization Techniques (ICEECCOT), 2017 International Conference on. IEEE; 2017. p. 75–8.Google Scholar
  41. 41.
    Mousavi SS, 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.CrossRefGoogle Scholar
  42. 42.
    He R, Huang Z-P, Ji L-Y, Wu J-K, Li H, Zhang Z-Q. Beat-to-beat ambulatory blood pressure estimation based on random forest. In: Wearable and implantable body sensor networks (BSN), 2016 IEEE 13th international conference on: IEEE; 2016. p. 194–8.Google Scholar
  43. 43.
    Jain M, Kumar N, Deb S, Majumdar A. A sparse regression based approach for cuff-less blood pressure measurement. In: Acoustics, speech and signal processing (ICASSP), 2016 IEEE international conference on: IEEE; 2016. p. 789–93.Google Scholar
  44. 44.
    Sun S, Bezemer R, Long X, Muehlsteff J, Aarts R. Systolic blood pressure estimation using PPG and ECG during physical exercise. Physiol Meas. 2016;37(12):2154.PubMedCrossRefGoogle Scholar
  45. 45.
    Ertuğrul ÖF, Sezgin N. A non-invasive time-frequency based approach to estimate cuffless arterial blood pressure 2. Methods. 2018;2:18.Google Scholar
  46. 46.
    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(2):025005.PubMedPubMedCentralCrossRefGoogle Scholar
  47. 47.
    Miao F, et al. A novel continuous blood pressure estimation approach based on data mining techniques. IEEE J Biomed Health Inform. 2017;21:1730–40.CrossRefGoogle Scholar
  48. 48.
    Bose SSN, Kandaswamy S. Sparse representation of photoplethysmogram using K-SVD for cuffless estimation of arterial blood pressure. In: Advanced computing and communication systems (ICACCS), 2017 4th international conference on: IEEE; 2017. p. 1–5.Google Scholar
  49. 49.
    Pan J, Zhang Y. Improved Blood Pressure Estimation Using Photoplethysmography Based on Ensemble Method. In: Pervasive Systems, Algorithms and Networks & 2017 11th International Conference on Frontier of Computer Science and Technology & 2017 Third International Symposium of Creative Computing (ISPAN-FCST-ISCC), 2017 14th International Symposium on. IEEE; 2017. p. 105–11.Google Scholar
  50. 50.
    Su P, Ding X, Zhang Y, Li Y, Zhao N. Predicting blood pressure with deep bidirectional LSTM network, arXiv preprint. In: 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, Nevada, USA, 2018. p. 323–8.Google Scholar
  51. 51.
    Radha M, et al. Wrist-worn blood pressure tracking in healthy free-living individuals using neural networks. arXiv preprint arXiv:1805.09121, 2018.
  52. 52.
    Ghosh S, Banerjee A, Ray N, Wood PW, Boulanger P, Padwal R. Using accelerometric and gyroscopic data to improve blood pressure prediction from pulse transit time using recurrent neural network. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2018. p. 935–9.Google Scholar
  53. 53.
    Wu D, Xu L, Zhang R, Zhang H, Ren L, Zhang Y-T. Continuous cuff-less blood pressure estimation based on combined information using deep learning approach. J Med Imaging Health Inform. 2018;8(6):1290–9.CrossRefGoogle Scholar
  54. 54.
  55. 55.
    Chan K, Hung K, Zhang Y. Noninvasive and cuffless measurements of blood pressure for telemedicine. In: Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE, vol. 4. IEEE; 2001. p. 3592–3.Google Scholar
  56. 56.
    Payne R, Symeonides C, Webb D, Maxwell S. Pulse transit time measured from the ECG: an unreliable marker of beat-to-beat blood pressure. J Appl Physiol. 2006;100(1):136–41.PubMedPubMedCentralCrossRefGoogle Scholar
  57. 57.
    Douniama C, Sauter C, Couronne R. Blood pressure tracking capabilities of pulse transit times in different arterial segments: a clinical evaluation. In: Computers in Cardiology, 2009. IEEE; 2009. p. 201–4.Google Scholar
  58. 58.
    Wong MY-M, Poon CC-Y, Zhang Y-T. An evaluation of the cuffless blood pressure estimation based on pulse transit time technique: a half year study on normotensive subjects. Cardiovasc Eng. 2009;9(1):32–8.PubMedPubMedCentralCrossRefGoogle Scholar
  59. 59.
    Choi Y, Zhang Q, Ko S. Noninvasive cuffless blood pressure estimation using pulse transit time and Hilbert–Huang transform. Comput Electr Eng. 2013;39(1):103–11.CrossRefGoogle Scholar
  60. 60.
    Heravi MY, Khalilzadeh M, Joharinia S. Continuous and cuffless blood pressure monitoring based on ECG and SpO2 signals ByUsing Microsoft visual C sharp. J Biomed Phys Eng. 2014;4(1):27.Google Scholar
  61. 61.
    Kim JS, Kim KK, Baek HJ, Park KS. Effect of confounding factors on blood pressure estimation using pulse arrival time. Physiol Meas. 2008;29(5):615.PubMedCrossRefGoogle Scholar
  62. 62.
    Ye S-y, Kim G-R, Jung D-K, Baik S, Jeon G. Estimation of systolic and diastolic pressure using the pulse transit time. World Acad Sci Eng Technol. 2010;67:726–31.Google Scholar
  63. 63.
    Breiman L. Random forests. Mach Learn. 2001;45(1):5–32.CrossRefGoogle Scholar
  64. 64.
    Deka PC. Support vector machine applications in the field of hydrology: a review. Appl Soft Comput. 2014;19:372–86.CrossRefGoogle Scholar
  65. 65.
    Are deep neural nets “Software 2.0”?. 2018.Google Scholar
  66. 66.
    Wang G, Atef M, Lian Y. Towards a continuous non-invasive cuffless blood pressure monitoring system using PPG: systems and circuits review. IEEE Circuits Syst Mag. 2018;18(3):6–26.CrossRefGoogle Scholar
  67. 67.
    Wang L, Zhou W, Xing Y, Zhou X. A novel neural network model for blood pressure estimation using photoplethesmography without electrocardiogram. J Healthc Eng. 2018;2018Google Scholar
  68. 68.
    Xing X, Sun M. Optical blood pressure estimation with photoplethysmography and FFT-based neural networks. Biomed Opt Express. 2016;7(8):3007–20.PubMedPubMedCentralCrossRefGoogle Scholar
  69. 69.
    Poliñski A, Czuszyñski K, Kocejko T. Blood pressure estimation based on blood flow, ECG and respiratory signals using recurrent neural networks. In: 2018 11th International Conference on Human System Interaction (HSI): IEEE; 2018. p. 86–92.Google Scholar
  70. 70.
    Yu K-H, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018;2(10):719.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Institute of Biomedical Engineering, Department of Engineering ScienceUniversity of OxfordOxfordUK

Personalised recommendations