Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Cuffless Blood Pressure Estimation Based on a Convolutional Neural Network using PPG and ECG Signals for Portable or Wearable Blood Pressure Devices

휴대용 및 웨어러블 측정기를 위한 ECG와 PPG 신호를 활용한 합성곱 신경망 알고리즘 기반의 비가압식 혈압 추정 방법

  • Received : 2019.11.18
  • Accepted : 2020.04.21
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an algorithm for estimating blood pressure using ECG (Electrocardiogram) and PPG (Photoplethysmography) signals. To estimate the BP (Blood pressure), we generate a periodic input signal, remove the noise according to the differential and threshold methods, and then estimate the systolic and diastolic blood pressures based on the convolutional neural network. We used 49 patient data of 3.1GB in the MIMIC database. As a result, it was found that the prediction error (RMSE) of systolic BP was 5.80mmHg, and the prediction error of diastolic BP was 2.78mmHg. This result confirms that the performance of class A is satisfied with the existing BP monitor evaluation method proposed by the British High Blood Pressure Association.

본 논문에서는 시계열 심전도 (Electrocardiogram: ECG) 및 광전용맥파 측정센서 (Photoplethysmography: PPG)을 이용하여 혈압을 추정하는 알고리즘을 제안한다. 혈압 (Blood pressure: BP)을 추정하기 위해 주기적 입력 신호를 생성하고 차동 및 임계값 방법에 따라 잡음을 제거한 다음 합성곱 신경망 알고리즘을 기반으로 하여 수축기 혈압과 이완기 혈압을 예측한다. 본 논문에서 사용된 데이터는 MIMIC 데이터베이스에서 총 3.1GB의 49명의 환자 데이터를 사용하였다. 실험결과 수축기 혈압의 평균 제곱근 오차는 5.80mmHg, 이완기 혈압의 예측 오차는 2.78mmHg을 나타내었다. 또한, 영국 고혈압 협회가 제안한 혈압계 평가 방법을 적용하였을 때, 최고 성능인 등급 A를 만족함을 확인할 수 있었다.

Keywords

References

  1. Allen, R., Schneider, J., Davidson, D., Winchester, M., and Taylor, C. (1981). The Covariation of Blood Pressure and Pulse Transit Time in Hypertensive Patients, Psychophysiology, 18(3), 301-306. https://doi.org/10.1111/j.1469-8986.1981.tb03038.x
  2. Babbs, C. (2012). Oscillometric Measurement of Systolic and Diastolic Blood Pressures Validated in a Physiologic Mathematical Model, BioMedical Engineering OnLine, 11(56), 1-22. https://doi.org/10.1186/1475-925X-11-1
  3. Baker, P. (1990). Neural Network P rocessing of Oscillometric Waveforms and Blood Pressure Estimation from the Superficial Temporal Artery, Ph. D. Thesis, Graduate School of University of Utah, USA.
  4. Brien, E., Waeber, B., Parati, G., Staessen, J., and Myers, G. (2001). Blood Pressure Measuring Devices: Recommendations of the European Society of Hypertension, British Medical Journal, 322(7285), 531-536. https://doi.org/10.1136/bmj.322.7285.531
  5. Chen, W., Kobayashi, T., Ichikawa, S., Takeuchi, Y., and Togawa, T. (2000). Continuous Estimation of Systolic Blood Pressure using the Pulse Arrival Time and Intermittent Calibration, Medical and Biological Engineering and Computing, 38(5), 569-574. https://doi.org/10.1007/BF02345755
  6. Cho, Y., Kim, M., and Yoon, J. (2014). Comparison of Characteristics of P-Wave Detection in ECG with Wireless Patch Electrodes, Korea Society of Industrial Information Systems, 19(1), 43-52.
  7. Choi, S., Lee, K., Kim, K., and Kwak, S. (2019). Lane Departure Warning System using Deep Learning, Journal of the Korea Industrial Information Systems Research, 24(2), 25-31. https://doi.org/10.9723/JKSIIS.2019.24.2.025
  8. Chung, M., and Lee. J. (2018). Systemic Analysis of Research Activities and Trends Related to Artificial Intelligence (A.I.) Technology based on Latent Dirichlet Allocation (LDA) Model, Journal of the Korea Industrial Information Systems Research, 23(3), 87-95. https://doi.org/10.9723/JKSIIS.2018.23.3.087
  9. Choi, Y., Kim, K., Hong, W., and Ryu, J. (2009). Development of Blood Pressure Measuring System using Piezoelectric and Photo Sensor, Korea Society of Industrial Information Systems, 14(5), 149-154.
  10. Ding, X., Zhao, N., Yang, G., Pettigrew, R., Lo, B., Miao, F., Li, Y., Liu, J., and Zhang, Y. (2016). Continuous Blood Pressure Measurement from Invasive to Unobtrusive: Celebration of 200th Birth Anniversary of Carl Ludwig, IEEE Journal of Biomedical and Health Informatics, 20(6), 1455-1465. https://doi.org/10.1109/JBHI.2016.2620995
  11. Ding, X., Yan, B., Zhang, Y., Liu, J., Zhao, N., and Tsang, H. (2017). Pulse Transit Time Based Continuous Cufess Blood Pressure Estimation: A New Extension and A Comprehensive Evaluation, Scientific Reports, 7(11554), 1-11. https://doi.org/10.1038/s41598-016-0028-x
  12. Forouzanfar, M., Dajani, H., Groza, V., Bolic, M., and Rajan, S. (2011). Feature-based Neural Network Approach for Oscillometric Blood Pressure Estimation, IEEE Transactions on Instrumentation and Measurement, 60(8), 2786-2796. https://doi.org/10.1109/TIM.2011.2123210
  13. Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P., Mark, R., Mietus, J., Moody, G., Peng, C., and Stanley, H. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation 101(23), e215-e220.
  14. Kachuee, M., Kiani, M., Mohammadzade, H., and Shabany, M. (2016). Cuffless Blood Pressure Estimation Algorithms for Continuous Health-Care Monitoring, IEEE Transactions on Biomedical Engineering, 64(4), 859-869. https://doi.org/10.1109/TBME.2016.2580904
  15. Kim, M., Kim, Y., and Cho, Y. (2015). Electrocardiographic Characteristics of Significant Factors of Detected Atrial Fibrillation using WEMS, Korea Society of Industrial Information Systems, 20(6), 37-46.
  16. Lee, H., Lee, J., and Shin, M. (2019). Using Wearable ECG/PPG Sensors for Driver Drowsiness Detection Based on Distinguishable Pattern of Recurrence Plots, Electronics, 8(2), 192, 1-15. https://doi.org/10.3390/electronics8020192
  17. Lee, M., Nam, K., and Lee, C. (2019). Crack Detection on the Road in Aerial Image using Mask R-CNN, Journal of the Korea Industrial Information Systems Research, 24(3), 23-29. https://doi.org/10.9723/JKSIIS.2019.24.3.023
  18. Lee, S., and Chang, J. (2017). Oscillometric Blood Pressure Estimation Based on Deep Learning, IEEE Transactions on Industrial Informatics, 13(2), 461-472. https://doi.org/10.1109/TII.2016.2612640
  19. Moody, G., and Mark, R. (1996). A Database to Support Development and Evaluation of Intelligent Intensive Care Monitoring, Computers in Cardiology, 23, 657-660.
  20. Naschitz, J., Bezobchuk, S., Mussafia-Priselac, R., Sundick, S., Dreyfuss, D., Khorshidi, I., Karidis, A., Manor, H., Nagar M., Peck, E., Peck, S., Storch, S., Rosner, I., and Gaitini, L. (2004). Pulse Transit Time by R-wave-gated Infrared photoplethysmography: Review of the Literature and Personal Experience, Journal of Clinical Monitoring and Computing. 8(5), 333-342.
  21. Payne, R., Symeonides, C., Webb, D., and Maxwell, S. (2006). Pulse Transit Time Measured from the ECG: an Unreliable Marker of Beat-to-beat Blood Pressure, Jpurnal of Applied Physiology, 100(1), 136-141. https://doi.org/10.1152/japplphysiol.00657.2005
  22. Ruiz-Rodriguez, J., Ruiz-Sanmartin, A., Ribas, A., Caballero, J., Garcia-Roche, A., Riera, J., Nuvials, X., Nadal, M., SolaMorales, O., and Serra, J. (2013). Innovative Continuous Non-invasive Cuffless bBood Pressure Monitoring based on Photoplethysmography Technology, Intensive Care Medician, 39(9), 1618-1625. https://doi.org/10.1007/s00134-013-2964-2
  23. Rundo F., Conoci, S., Ortis A., and Battiato, S. (2018). An Advanced Bio-Inspired PhotoPlethysmoGraphy(PPG) and ECG Pattern Recognition System for Medical Assessment, Sensors, 18(2), 405, 1-22. https://doi.org/10.3390/s18020405
  24. Sola, J., Proenca, M., Ferrario, D., Porchet, J., Falhi, A, Grossenbacher, O, Allemann, Y., Rimoldi, S., and Sartori, C. (2013). Noninvasive and Nonocclusive Blood Pressure Estimation Via a Chest Sensor, IEEE Transactions on Biomedical Engineering, 60(12), 3505-3513. https://doi.org/10.1109/TBME.2013.2272699
  25. Sun, J., Reisner, A., and Mark, R. (2006). A Signal Abnormality Index for Arterial Blood Pressure Waveforms, Proceedings on Computers in Cardiology, Valencia, Spain, pp. 13-16.
  26. Teng, X., and Zhang, Y. (2013). Continuous and Noninvasive Estimation of Arterial Blood Pressure using a Photoplethysmographic Approach, The 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Sep. 17-21, Cancun, Mexico, pp. 3153-3156.
  27. Wang, L., Zhou, W., Xing, Y., and Zhou, X. (2018). A Novel Neural Network Model for Blood Pressure Estimation using Photoplethesmography without Electrocardiogram, Journal of Healthcare Engineering, 2018(7804243), 1-9.
  28. Wippermann, C., Schranz, D., and Huth, R. (1995). Evaluation of the Pulse Wave Arrival Time as a Marker for Blood Pressure Changes in Critically Ill Infants and Children, Journal of Clinical Monitoring, 11(5), 324-328. https://doi.org/10.1007/BF01616991
  29. Xing, X., and Sun, M. (2016). Optical Blood Pressure Estimation with Photoplethysmography and FFT-based Neural Networks, Biomedical Optics Express, 7(8), 3007-3020. https://doi.org/10.1364/BOE.7.003007
  30. Zhang, Q., Zeng, X., Hu, W., and Zhou, D. (2017). A Machine Learning-Empowered System for Long-Term Motion-Tolerant Wearable Monitoring of Blood Pressure and Heart Rate With Ear-ECG/PPG, IEEE Access, 5, 10547-10561. https://doi.org/10.1109/ACCESS.2017.2707472