A non-contact continuous blood pressure measurement method based on video stream_Journal of Biomedical Engineering

Authors：

YAN Hao , LI Xia , ZHU Tianyang , CHEN Xiuqiang , GONG Ning ,  ZHOU Qinwu

School of Life Science and Technology, Xi’an Jiaotong University, Xi’an 710049, P. R. China;

Corresponding author：

ZHOU Qinwu, Email: zhaozm@xjtu.edu.cn

Keywords：

Continuous blood pressure measurement; Independent component analysis; Feature selection; Machine learning; Support vector machine

DOI：

10.7507/1001-5515.202211071

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Hypertension is the primary disease that endangers human health. A convenient and accurate blood pressure measurement method can help to prevent the hypertension. This paper proposed a continuous blood pressure measurement method based on facial video signal. Firstly, color distortion filtering and independent component analysis were used to extract the video pulse wave of the region of interest in the facial video signal, and the multi-dimensional feature extraction of the pulse wave was preformed based on the time-frequency domain and physiological principles; Secondly, an integrated feature selection method was designed to extract the universal optimal feature subset; After that, we compared the single person blood pressure measurement models established by Elman neural network based on particle swarm optimization, support vector machine (SVM) and deep belief network; Finally, we used SVM algorithm to build a general blood pressure prediction model, which was compared and evaluated with the real blood pressure value. The experimental results showed that the blood pressure measurement results based on facial video were in good agreement with the standard blood pressure values. Comparing the estimated blood pressure from the video with standard blood pressure value, the mean absolute error (MAE) of systolic blood pressure was 4.9 mm Hg with a standard deviation (STD) of 5.9 mm Hg, and the MAE of diastolic blood pressure was 4.6 mm Hg with a STD of 5.0 mm Hg, which met the AAMI standards. The non-contact blood pressure measurement method based on video stream proposed in this paper can be used for blood pressure measurement.

Citation： YAN Hao, LI Xia, ZHU Tianyang, CHEN Xiuqiang, GONG Ning, ZHOU Qinwu. A non-contact continuous blood pressure measurement method based on video stream. Journal of Biomedical Engineering, 2023, 40(2): 249-256. doi: 10.7507/1001-5515.202211071 Copy

1.	World Health Organization. World health statistics 2019: monitoring health for the SDGs, sustainable development goals. Geneva: World Health Organization, 2019.
2.	中华人民共和国统计局. 中国统计年鉴. 北京: 中国统计出版社, 2021.
3.	Geddes L A. The direct and indirect measurement of blood pressure. Chicago: Year Book Medical Publishers, 1970: 08000-00014.
4.	Booth J. A short history of blood pressure measurement. Proc R Soc Med, 1977, 70(11): 793-799.
5.	Penaz J. Photoelectric measurement of blood pressure, volume and flow in the finger// Dresden Conference Committee of the 10th International Conference on Medicine and Biological Engineering. Dresden: Med Biol Eng Comput, 1973: 104.
6.	Wippermann C F, Schranz D, Huth R G. Evaluation of the pulse wave arrival time as a marker for blood pressure changes in critically ill infants and children. J Clin Monit, 1995, 11(5): 324-328.
7.	Ni Yongbin, Wang Hongyu, Hu Dayi, et al. The relationship between pulse wave velocity and pulse pressure in Chinese patients with essential hypertension. Hypertens Res, 2003, 26(11): 871-874.
8.	Eom H, Lee D, Han S, et al. End-to-end deep learning architecture for continuous blood pressure estimation using attention mechanism. Sensors, 2020, 20(8): 2338.
9.	Esmaelpoor J, Moradi M H, Kadkhodamohammadi A. A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals. Comput Biol Med, 2020, 120: 103719.
10.	Da U J, Lim K M. Combined deep CNN-LSTM network-based multitasking learning architecture for noninvasive continuous blood pressure estimation using difference in ECG-PPG features. Sci Rep, 2021, 11(1): 13539.
11.	Verkruysse W, Svaasand L O, Nelson J S. Remote plethysmographic imaging using ambient light. Opt Express, 2008, 16(26): 21434-21445.
12.	Jain M, Deb S, Subramanyam A V. Face video based touchless blood pressure and heart rate estimation// 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP). Montreal: IEEE, 2016: 16599992.
13.	Luo H, Yang D, Barszczyk A, et al. Smartphone-based blood pressure measurement using transdermal optical imaging Technology. Circ Cardiovasc Imag, 2019, 12(8): e008857.
14.	Moody G B, Mark R G. Integration of real-time and off-line clinical data in the MIMIC database// Computers in Cardiology 1997. Lund: IEEE, 1997: 585-588.
15.	Escobar B, Torres R. Feasibility of non-invasive blood pressure estimation based on pulse arrival time: A MIMIC database study// Computing in Cardiology 2014. Cambridge: IEEE, 2014: 1113-1116.
16.	Prauzek M, Peterek T, Adamec O, et al. Simple data acquisition system for photopletysmography and electrocardiography// 2010 2nd International Conference on Signal Processing Systems. Dalian: IEEE, 2010: V2-377-V2-379.
17.	Kwon S, Kim J, Lee D, et al. ROI analysis for remote photoplethysmography on facial video// 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan: IEEE, 2015: 4938-4941.
18.	Wang W, Brinker A, Stuijk S, et al. Color-distortion filtering for remote photoplethysmography// 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). Washington: IEEE, 2017: 71-78.
19.	Hyvärinen A, Oja E. A fast fixed-point algorithm for independent component analysis. Neural Comput, 1997, 9(7): 1483-1492.
20.	王建雄, 张立民, 钟兆根. 基于FastICA算法的盲源分离. 计算机技术与发展, 2011, 21(12): 93-96.
21.	Alpert B S. Validation of the welch Allyn SureBP (inflation) and StepBP (deflation) algorithms by AAMI standard testing and BHS data analysis. Blood Press Monit, 2011, 16(2): 96-98.
22.	O’Brien E, Petrie J, Littler W, 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(7): 607-619.
23.	Elman J. Finding structure in time. Cognitive Sci, 1990, 14(2): 179-211.
24.	Paiva J S, Cardoso J, Pereira T. Supervised learning methods for pathological arterial pulse wave differentiation: a SVM and neural networks approach. Int J Med Inform, 2018, 109: 30-38.
25.	Chang C C, Lin C J. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol, 2007, 2(3): 1-27.
26.	Sakr G E, Mokbel M, Darwich A, et al. Comparing deep learning and support vector machines for autonomous waste sorting// 2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET). Beirut: IEEE, 2016: 207-212.
27.	Lee S, Chang J H. Deep belief networks ensemble for blood pressure estimation. IEEE Access, 2017, 5: 9962-9972.
28.	Haury A C, Gestraud P, Vert J P. The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures. PLoS One, 2011, 6(12): e28210.

1. World Health Organization. World health statistics 2019: monitoring health for the SDGs, sustainable development goals. Geneva: World Health Organization, 2019.
2. 中华人民共和国统计局. 中国统计年鉴. 北京: 中国统计出版社, 2021.
3. Geddes L A. The direct and indirect measurement of blood pressure. Chicago: Year Book Medical Publishers, 1970: 08000-00014.
4. Booth J. A short history of blood pressure measurement. Proc R Soc Med, 1977, 70(11): 793-799.
5. Penaz J. Photoelectric measurement of blood pressure, volume and flow in the finger// Dresden Conference Committee of the 10th International Conference on Medicine and Biological Engineering. Dresden: Med Biol Eng Comput, 1973: 104.
6. Wippermann C F, Schranz D, Huth R G. Evaluation of the pulse wave arrival time as a marker for blood pressure changes in critically ill infants and children. J Clin Monit, 1995, 11(5): 324-328.
7. Ni Yongbin, Wang Hongyu, Hu Dayi, et al. The relationship between pulse wave velocity and pulse pressure in Chinese patients with essential hypertension. Hypertens Res, 2003, 26(11): 871-874.
8. Eom H, Lee D, Han S, et al. End-to-end deep learning architecture for continuous blood pressure estimation using attention mechanism. Sensors, 2020, 20(8): 2338.
9. Esmaelpoor J, Moradi M H, Kadkhodamohammadi A. A multistage deep neural network model for blood pressure estimation using photoplethysmogram signals. Comput Biol Med, 2020, 120: 103719.
10. Da U J, Lim K M. Combined deep CNN-LSTM network-based multitasking learning architecture for noninvasive continuous blood pressure estimation using difference in ECG-PPG features. Sci Rep, 2021, 11(1): 13539.
11. Verkruysse W, Svaasand L O, Nelson J S. Remote plethysmographic imaging using ambient light. Opt Express, 2008, 16(26): 21434-21445.
12. Jain M, Deb S, Subramanyam A V. Face video based touchless blood pressure and heart rate estimation// 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP). Montreal: IEEE, 2016: 16599992.
13. Luo H, Yang D, Barszczyk A, et al. Smartphone-based blood pressure measurement using transdermal optical imaging Technology. Circ Cardiovasc Imag, 2019, 12(8): e008857.
14. Moody G B, Mark R G. Integration of real-time and off-line clinical data in the MIMIC database// Computers in Cardiology 1997. Lund: IEEE, 1997: 585-588.
15. Escobar B, Torres R. Feasibility of non-invasive blood pressure estimation based on pulse arrival time: A MIMIC database study// Computing in Cardiology 2014. Cambridge: IEEE, 2014: 1113-1116.
16. Prauzek M, Peterek T, Adamec O, et al. Simple data acquisition system for photopletysmography and electrocardiography// 2010 2nd International Conference on Signal Processing Systems. Dalian: IEEE, 2010: V2-377-V2-379.
17. Kwon S, Kim J, Lee D, et al. ROI analysis for remote photoplethysmography on facial video// 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Milan: IEEE, 2015: 4938-4941.
18. Wang W, Brinker A, Stuijk S, et al. Color-distortion filtering for remote photoplethysmography// 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). Washington: IEEE, 2017: 71-78.
19. Hyvärinen A, Oja E. A fast fixed-point algorithm for independent component analysis. Neural Comput, 1997, 9(7): 1483-1492.
20. 王建雄, 张立民, 钟兆根. 基于FastICA算法的盲源分离. 计算机技术与发展, 2011, 21(12): 93-96.
21. Alpert B S. Validation of the welch Allyn SureBP (inflation) and StepBP (deflation) algorithms by AAMI standard testing and BHS data analysis. Blood Press Monit, 2011, 16(2): 96-98.
22. O’Brien E, Petrie J, Littler W, 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(7): 607-619.
23. Elman J. Finding structure in time. Cognitive Sci, 1990, 14(2): 179-211.
24. Paiva J S, Cardoso J, Pereira T. Supervised learning methods for pathological arterial pulse wave differentiation: a SVM and neural networks approach. Int J Med Inform, 2018, 109: 30-38.
25. Chang C C, Lin C J. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol, 2007, 2(3): 1-27.
26. Sakr G E, Mokbel M, Darwich A, et al. Comparing deep learning and support vector machines for autonomous waste sorting// 2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET). Beirut: IEEE, 2016: 207-212.
27. Lee S, Chang J H. Deep belief networks ensemble for blood pressure estimation. IEEE Access, 2017, 5: 9962-9972.
28. Haury A C, Gestraud P, Vert J P. The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures. PLoS One, 2011, 6(12): e28210.

Previous Article
Primary study on recognition of vascular stiffness based on wavelet scattering neural network
Next Article
A multi-behavior recognition method for macaques based on improved SlowFast network

Journal of Biomedical Engineering

A non-contact continuous blood pressure measurement method based on video stream

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content