Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Reliability of the Photoplethysmographic Analysis Using Deep Neural Network (DNN) Algorithm

심층신경망 알고리즘을 이용한 광용적맥파의 분석의 신뢰성

  • Kim, Jiwoon (Interdisciplinary Program in Biohealth-Machinery Convergence Engineering, Kangwon National University) ;
  • Park, Sung-Min (Institute of Medicine, Kangwon National University) ;
  • Choi, Seong-Wook (Interdisciplinary Program in Biohealth-Machinery Convergence Engineering, Kangwon National University)
  • 김지운 (강원대학교 바이오헬스기기 융합기술 협동과정) ;
  • 박성민 (강원대학교 의료기기연구소) ;
  • 최성욱 (강원대학교 바이오헬스기기 융합기술 협동과정)
  • Received : 2021.02.18
  • Accepted : 2021.03.09
  • Published : 2021.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, the waveform parameters of photoplethysmography were obtained by using a new algorithm incorporating deep neural networks (DNN) and compared data measured from electrocardiogram and parameters manually acquired by experts, to analyze the accuracy and errors of the suggested algorithm. The 6 DNNs of the algorithm had been trained to find the onset, systolic, W and Z points and to determine the start and end of non-informative regions. The algorithm inputs 3 seconds of PPG data measured in real time into DNNs, records the position of the DNNs' output. The final decision accuracy of the algorithm was improved by using repeating number of DNNs' output when overlapping the input data section and the output section. HR and HRV obtained by the algorithm showed 87.7% and 86.7% agreement compared to those determined by ECG. Aix, crest time, Pulse Propagation Time (PPT) among PPG parameters showed 0.080±0.15 mV, -0.012±0.030 sec and 0.033±0.109 sec error compared to those manually measured by human experts. The algorithm proposed in this study was able to quickly provide accurate PPG parameters with little errors even when noise and arrhythmia occurred.

Keywords

Acknowledgement

본 연구는 한국연구재단 기본연구 과제의 지원을 받아 수행하였음(No.2020R1F1A1073478).

References

  1. Mann DM, Chen J, Chunara R, Testa PA, Nov O. COVID-19 transforms health care through telemedicine: evidence from the field. Journal of the American Medical Informatics Association. 2020.
  2. Pietila J, Mehrang S, Tolonen J, Helander E, Jimison H, Pavel M, Korhonen I. Evaluation of the accuracy and reliability for photoplethysmography based heart rate and beat-to-beat detection during daily activities. EMBEC & NBC. 2017;145-8.
  3. Lu G, Yang F, Taylor JA, Stein JF. A comparison of photoplethysmography and ECG recording to analyse heart rate variability in healthy subjects, Journal of medical engineering & technology. 2009;33(8):634-41. https://doi.org/10.3109/03091900903150998
  4. Nitzan M, Babchenko A, Khanokh B. Very low frequency variability in arterial blood pressure and blood volume pulse. Medical & biological engineering & computing. 1999;37(1): 54-8. https://doi.org/10.1007/BF02513266
  5. London GM, Guerin AP. Influence of arterial pulse and reflected waves on blood pressure and cardiac function, American heart journal. 1999;138(3): S220-4. https://doi.org/10.1016/S0002-8703(99)70313-3
  6. Zhang Q, Zeng X, Hu W, Zhou D. A machine learning empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with ear-ECG/PPG. IEEE Access. 2017;5:10547-61. https://doi.org/10.1109/ACCESS.2017.2707472
  7. Blanc VF, Haig M, Troli M, Sauve B. Computerized photoplethysmography of the finger, Canadian journal of anaesthesia. 1993; 40(3):271-8. https://doi.org/10.1007/BF03037040
  8. Takazawa K, Tanaka N, Fujita M, Matsuoka O, Saiki T, Aikawa M, Ibukiyama C. Assessment of vasoactive agents and vascular aging by the second derivative of photoplethysmogram waveform. Hypertension. 1998;32(2):365-70. https://doi.org/10.1161/01.hyp.32.2.365
  9. Reuss JL, Bahr DE. Period domain analysis in fetal pulse oximetry, In Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society[Engineering in Medicine and Biology] IEEE (Houston, USA). 2002;1742-3.
  10. Shelley KH. Photoplethysmography: beyond the calculation of arterial oxygen saturation and heart rate. Anesthesia & Analgesia. 2007;105(6):S31-6. https://doi.org/10.1213/01.ane.0000269512.82836.c9
  11. Biswas D, Everson L, Liu M, Panwar M, Verhoef BE, Patki S, Van Helleputte N, CorNET: Deep learning framework for PPG-based heart rate estimation and biometric identification in ambulant environment. IEEE transactions. 2019;13(2):282- 91.
  12. Reiss A, Indlekofer I, Schmidt P, Van Laerhoven K. Deep PPG: large-scale heart rate estimation with convolutional neural networks. Sensors. 2019;19(14):3079. https://doi.org/10.3390/s19143079
  13. Senturk U, Yucedag I, Polat K. Repetitive neural network (RNN) based blood pressure estimation using PPG and ECG signals. In 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) IEEE. 2018;1-4.
  14. Reiss A, Schmidt P, Indlekofer I, Van Laerhoven K. PPG-based heart rate estimation with time-frequency spectra: A deep learning approach. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. 2018;1283-92.
  15. Jindal V, Birjandtalab J, Pouyan MB, Nourani M. An adaptive deep learning approach for PPG-based identification. In 2016 38th Annual international conference of the IEEE engineering in medicine and biology society (EMBC) IEEE. 2016; 6401-4.
  16. Everson L, Biswas D, Panwar M, Rodopoulos D. Acharyya A, Kim CH, Van Helleputte N. Biometricnet: Deep learning based biometric identification using wrist-worn PPG. In 2018 IEEE International Symposium on Circuits and Systems (ISCAS). 2018;1-5.
  17. Lee MS, Lee YK, Pae DS, Lim MT, Kim DW, Kang TK. Fast Emotion Recognition Based on Single Pulse PPG Signal with Convolutional Neural Network. Applied Sciences. 2019;9(16):3355. https://doi.org/10.3390/app9163355
  18. Yang YL, Seok HS, Noh GJ, Choi BM, Shin H. Postoperative pain assessment indices based on photoplethysmography waveform analysis. Frontiers in physiology. 2019;9:1199. https://doi.org/10.3389/fphys.2018.01199
  19. Zhou K, et al. Practical evaluation of encrypted traffic classification based on a combined method of entropy estimation and neural networks. ETRI Journal. 2020;42(3):311-23. https://doi.org/10.4218/etrij.2019-0190
  20. Rocha LG, Liu M, Biswas D, Verhoef BE, Bampi S, Kim CH, Van Helleputte N. Real-time HR Estimation from wrist PPG using Binary LSTMs. In 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS) IEEE. 2019;1-4.
  21. Lake BM, Ullman TD, Tenenbaum JB, Gershman SJ. Building machines that learn and think like people. Behavioral and brain sciences. 2017;40:E253. https://doi.org/10.1017/S0140525X16001837
  22. Cooke SF, Bliss TVP. Plasticity in the human central nervous system. Brain. 2006;129(7):1659-73. https://doi.org/10.1093/brain/awl082
  23. Kim J, Park S, Choi S. Automatic Parameter Acquisition of 12 leads ECG Using Continuous Data Processing Deep Neural Network. Journal of Biomedical Engineering Research. 2020;41(2):107-19. https://doi.org/10.9718/JBER.2020.41.2.107
  24. Karimpanal TG, Bouffanais R. Self-organizing maps for storage and transfer of knowledge in reinforcement learning. Adaptive Behavior. 2019;27(2):111-26. https://doi.org/10.1177/1059712318818568
  25. Kim J, Park S, Choi S. Real-time Photoplethysmographic Heart Rate Measurement Using Deep Neural Network Filters. ETRI journal. 2021.
  26. Elgendi M. On the analysis of fingertip photoplethysmogram signals. Current cardiology reviews. 2012;8(1):14-25. https://doi.org/10.2174/157340312801215782
  27. Elgendi M, Liang Y, Ward R. Toward generating more diagnostic features from photoplethysmogram waveforms. Diseases. 2018;6(1):20. https://doi.org/10.3390/diseases6010020
  28. Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Stanley HE. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. 2000;101(23):e215-20.
  29. Pimentel MA, Johnson AE, Charlton PH, Birrenkott D, Watkinson PJ, Tarassenko L, Clifton DA. Toward a robust estimation of respiratory rate from pulse oximeters. IEEE Transactions on Biomedical Engineering. 2016;64(8):1914-23. https://doi.org/10.1109/TBME.2016.2613124
  30. Moody GB, Mark RG. A database to support development and evaluation of intelligent intensive care monitoring. In Computers in Cardiology. 1996; 657-60.
  31. Jeyhani V, Mahdiani S, Peltokangas M, Vehkaoja A. Comparison of HRV parameters derived from photoplethysmography and electrocardiography signals. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) IEEE. 2015;5952-5.
  32. Brennan M, Palaniswami M, Kamen P. Poincare plot interpretation using a physiological model of HRV based on a network of oscillators. American Journal of Physiology-Heart and Circulatory Physiology. 2002;283(5):H1873-86. https://doi.org/10.1152/ajpheart.00405.2000
  33. Korpas D, Halek J, Dolezal L. Parameters describing the pulse wave. Physiological research, 2009;58(4):473-9. https://doi.org/10.33549/physiolres.931468
  34. Rubins U, Grabovskis A, Grube J, Kukulis I. Photoplethysmography analysis of artery properties in patients with cardiovascular diseases. In 14th Nordic-Baltic Conference on Biomedical Engineering and Medical Physics. 2008:319-22.
  35. Yoon YZ, Kang JM, Kwon Y, Park S, Noh S, Kim Y, Hwang SW. Cuff-less blood pressure estimation using pulse waveform analysis and pulse arrival time. IEEE journal of biomedical and health informatics. 2017;22(4):1068-74. https://doi.org/10.1109/jbhi.2017.2714674