Iranian Journal of Biomedical Engineering (IJBME)
نشریه علمی مهندسی پزشکی زیستی

A Personalized Method for Cuff-less Blood Pressure Estimation from Single PPG Sensor based on Deep Transfer Learning

Document Type : Full Research Paper

Authors

Marziyeh Ghanavaty 1
Seyyedeh Fatemeh Molaeezadeh 2
Mojtaba Navidi 1

1 M.Sc. Student, Department of Electrical and Computer Engineering, Jundi-Shapur University of Technology, Dezful, Iran

2 Assistant Professor, Department of Electrical and Computer Engineering, Jundi-Shapur University of Technology, Dezful, Iran

https://doi.org/10.22041/ijbme.2024.2015090.1869
Abstract
Hypertension is the leading cause of death worldwide. Continuous blood pressure (BP) measurement is crucial for the elderly and people with myocardial infarction, cardiovascular disease, kidney disease and gestational hypertension. Cuff-based blood pressure Holters are the most common method for continuous blood pressure measurement, but due to the use of an inflatable cuff, they often cause discomfort, particularly during sleep. A solution to such problems is the optical measurement of blood pressure using the photoplethysmogram (PPG) signal. This paper introduces a transfer deep learning framework for estimating systolic BP (SBP) and diastolic BP (DBP) using a single PPG signal. The proposed framework consists of three main parts: 1) downsampling by a factor of 4 aimed at reducing model complexity, 2) designing a pre-trained model including CNN and BiLSTM layers, and 3) personalizing the pre-trained model for each patient through transfer learning. We carry out Bland-Altman and correlation analysis to compare our method to the invasive arterial catheter (the gold-standard BP measurement method). Our model was validated on a wide range of BP signals acquired from 100 patients in MIMIC-III database. Results showed that the error and Pearson correlation coefficient of our model are 0.14±7.38 mmHg (mean±standard deviation) and 0.95 for SBP, and 0.00±4.67 mmHg and 0.92 for DBP. The proposed method satisfies the requirements the AAMI and IEEE-1708a standard and receives a grade A according to the BHS standard. This research has shed light on long-term BP monitoring and the prevention of cardiovascular events.

Keywords

Bidirectional Long Short-Term Memory (BiLSTM)
Personalizing
Convolutional Neural Network (CNN)
Blood Pressure
Photoplethysmography
Transfer Learning
Subjects
  1. W. Loh, Sh. Xu, O. Faust, Ch. P. Ooi et al. "Application of Photoplethysmography Signals for Healthcare Systems: An In-depth Review", Computer Methods and Programs in Biomedicine, vol. 216, 2022.
  2. Yin, G. Li, Y. Luo and L. Lin, "Cuff-less Continuous Blood Pressure Measurement Based on MultipleTypes of Information Fusion", Biomedical Signal Processing and Control, vol. 68, 2021.
  3. A. Younessi Heravi, K. Maghooli, S. Joharinia, "A New Approach for Blood Pressure Monitoring based on ECG and PPG Signals by using Artificial Neural Networks", International Journal of Computer Applications, vol. 103, pp. 36-40, 2014.
  4. Figini, S. Galici, D. Russo, I. Centoze, M. Visintin and G. Pagana, "Improving Cuff-Less Continuous Blood Pressure Estimation with Linear Regression Analysis", electronics, vol. 11, no. 9, 2022.
  5. Maher, G. A. Elshikh et al. "Non-invasive Calibration-Free Blood Pressure Estimation Based on Artificial Neural Network", International Conference on Advanced Machine Learning Technologies and Applications (AMLTA2019), vol. 921, pp. 701-711, 2020.
  6. Kachuee et al. "Cuff-less High-accuracy Calibration-free Blood Pressure Estimation Using Pulse Transit Time", 2015 IEEE International Symposium on Circuits and Systems (ISCAS), Lisbon, pp. 1006-1009, 2015, doi: 10.1109/ISCAS.2015.7168806.
  7. A. Younessi Heravi, E. Golmakani and Sima Joharinia, "A New Approach for Detecting Sudden Hypotension in Hemodialysis by Using Dual-channel Optical System", Innovative Optical Health Sciences, vol. 10, pp. 1-9, 2016.
  8. م. شهابی، و. نفیسی، «تخمین بدون کاف فشار خون مبتنی بر ویژگی‎های زمانی سیگنال نبض»، پردازش علائم وداده‎ها، صفحه 113-103، 1397.
  9. Panwar et al. "PP-Net: A Deep Learning Framework for PPG-Based Blood Pressure and Heart Rate Estimation", IEEE Sensors, vol. 20, no. 17, pp. 10000 - 10011, 2020.
  10. Gaurav et al. "Cuff-less PPG based continuous blood pressure monitoring — A smartphone based approach", 38th annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, pp. 607-610, 2016, doi: 10.1109/EMBC.2016.7590775.
  11. Slapničar, N. Malkar et al. "Blood Pressure Estimation from Photoplethysmogram Using a Spectro-Temporal Deep Neural Network", Sensors, vol. 19, no. 15, p. 3420, 2019.
  12. Yao et al. "Multi-Dimensional Feature Combination Method for Continuous Blood Pressure Measurement Based on Wrist PPG Sensor", Biomedical and Health Informatics, vol. 26, no. 8, pp. 3708-3719, 2022.
  13. Kurylyak, "A Neural Network-based Method for Continuous Blood Pressure Estimation from a PPG Signal", in 2013 IEEE International instrumentation and measurement technology conference (I2MTC), Calabria, 2013.
  14. W. Chen et al. "A Data-Driven Model with Feedback Calibration Embedded Blood Pressure Estimator Using Reflective Photoplethysmography", Sensors, vol. 22, 2022, doi: https://doi.org/10.3390/s22051873.
  15. El-Hajj and P.A Kyriaco, "Cuffless blood pressure estimation from PPG signals and its derivatives using deep learning models", Biomedical Signal Processing and Control, vol. 70, 2021.
  16. Samimi and H. R. Dajani, "A PPG-Based Calibration-Free Cuffless Blood Pressure Estimation Method Using Cardiovascular Dynamics", Sensors, vol.23,no.8, pp.1-22, 2023.
  17. S. Mousavi et al. "Blood Pressure Estimation from Appropriate and Inappropriate PPG Signals using A Whole-based Method," Biomedical Signal Processing and Control, vol. 47, pp. 196-206, 2020.
  18. Esmaelpoor et al. "A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals", Computers in Biology and Medicine, vol. 120, 2020.
  19. ج. اسماعیل پور، م. ح. مرادی، «بهبود تخمین ضربان به ضربان فشار خون‎های سیستولیک و دیاستولیک بر اساس سیگنال‎های ECG و PPG»، پایان‎نامه کارشناسی ارشد، دانشگاه صنعتی امیرکبیر، تهران، 1398.
  20. Leitner, P. H. Chiang et al. "Personalized Blood Pressure Estimation Using Photoplethysmography: A Transfer Learning Approach," IEEE Journal of Biomedical and Health Informatics, vol. 26, 2022.
  21. J. Pan and Q. Yang, "A Survey on Transfer Learning", IEEE Transactions on Knowledge and data, vol. 22, pp. 1345-1359, 2010.
  22. م. قنواتی، س. ف. مولایی زاده، م. نویدی، «یک روش شخصی‎سازی شده برای تخمین فشار خون بدون کاف از یک سنسور PPG مبتنی بر یادگیری انتقالی عمیق»، سی‎امین کنفرانس ملی و هشتمین کنفرانس بین‎المللی مهندسی زیست پزشکی ایران، تهران، 1402.
  23. E. W. Johnson et al., MIMIC-III, a freely accessible critical care database. Sci. Data 3:160035 doi: 10.1038/sdata.2016.35 (2016).
  24. Liang, M. Elgendi et al. "Analysis: An optimal filter for short photoplethysmogram signals", Scientific Data, vol. 5, no. 1, pp. 1-12, 2018.
  25. Panwar, D. Biswas et al. "Rehab-Net: Deep Learning Framework for Arm Movement Classification Using Wearable Sensors for Stroke Rehabilitation", IEEE Transactions on Biomedical Engineering, vol. 66, no. 11, pp. 3026-3037.
  26. G. Altman and J. M. Bland, "Measurement in Medicine: The Analysis of Method Comparison Studies", Royal Statistical Society: Series D (The Statistician), vol. 32, pp. 307-317, 1983.
  27. "IEEE Standard for Wearable, Cuffless Blood Pressure Measuring Devices - Amendment 1", in IEEE Std 1708a-2019 (Amendment to IEEE Std 1708-2014), pp.1-35, 4 Oct. 2019, doi: 10.1109/IEEESTD.2019.8859685.
  28. Free Printable Medical Forms, "Blood pressure range chart", Blood pressure range chart. [Online]. Available: https://isipaper.org/.post/sbk-rfrns-noisi-aai-tripl-ai-ieeeobyc.
  29. O’Brien, Th. Pickering et al. "Working Group on BP Monitoring of the ESH International Protocol for Validation of BP Measuring Devices in Ddults", Blood pressure monitoring, vol. 7, pp. 3-17, 2002.
  30. O'Brien, J. Petrie, W. Littler 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," Hypertension, vol. 8, pp. 607-619, 1990.
Iranian Journal of Biomedical Engineering (IJBME)
Volume 17, Issue 2
Summer 2023
Pages 153-164

  • Receive Date 06 November 2023
  • Revise Date 09 January 2024
  • Accept Date 13 January 2024

Home

Contact Us