Video-based Photoplethysmography and Machine Learning Algorithms to Achieve Pulse Wave Velocity

 
 
International Journal of Biotech Trends and Technology (IJBTT)
 
© 2021 by IJBTT Journal
Volume - 11 Issue - 1                          
Year of Publication : 2021
Authors : Pedro Henrique de Brito Souza, Israel Machado Brito Souza, Symone Gomes Soares Alcalá, Priscila Valverde de Oliveira Vitorino, Adson Ferreira da Rocha, Talles Marcelo Gonçalves de Andrade Barbosa
DOI :  10.14445/22490183/IJBTT-V11I1P602

Citation

MLA Style:Pedro Henrique de Brito Souza, Israel Machado Brito Souza, Symone Gomes Soares Alcalá, Priscila Valverde de Oliveira Vitorino, Adson Ferreira da Rocha, Talles Marcelo Gonçalves de Andrade Barbosa"Video-based Photoplethysmography and Machine Learning Algorithms to Achieve Pulse Wave Velocity" International Journal of Biotech Trends and Technology 11.1 (2021): 7-15.

APA Style:Pedro Henrique de Brito Souza, Israel Machado Brito Souza, Symone Gomes Soares Alcalá, Priscila Valverde de Oliveira Vitorino, Adson Ferreira da Rocha, Talles Marcelo Gonçalves de Andrade Barbosa(2021).Video-based Photoplethysmography and Machine Learning Algorithms to Achieve Pulse Wave Velocity. International Journal of Biotech Trends and Technology, 11(1), 7-15.

Abstract

The pulse transit time (PTT) is commonly used to monitor pulse wave velocity (PWV). In general, the instruments of signal acquisition, from which these physiological variables are estimated, require a contact surface for the sensors` installation and positioning, such as an inflatable cuff, creating a restriction or obstruction to the users` movement and ergonomics. This paper describes the development and evaluation of a contactless cardiovascular monitor, which can measure the PTT and PWV by analyzing the photoplethysmographic (PPG) signal obtained by an RGB camera`s green channel, i.e., without using sensors in contact with the skin. This monitor requires the PPG signal acquisition of two different regions of interest simultaneously: the forehead and right-hand palm. The time differences between two critical points of PPG signals were used to input machine learning algorithms, alongside other input features, such as user’s gender, height, and weight, to estimate Aortic PTT. The proposed monitor was tested by comparing its measurements of 36 healthy volunteers to the CARDIOS Dyna-MAPA+, gold standard equipment for these physiological variables measurement, showing a Pearson correlation coefficient of approximately 0.77 and a mean squared error of 0.104×10-3 for Aortic PTT.

References

[1] M. Gao, N. B. Olivier, R. Mukkamala, Comparison of non-invasive pulse transit time estimates as markers of blood pressure using invasive pulse transit time measurements as a reference, Physiological Reports 4 (10). doi:10.14814/phy2.12768
[2] R. Mukkamala, J.-O. Hahn, Toward Ubiquitous Blood Pressure Monitoring via Pulse Transit Time: Predictions on Maximum Calibration Period and Acceptable Error Limits, IEEE Transactions Biomedical Engineering 65 (6). doi:10.1109/TBME.2017.2756018
[3] M. P. Neves, A. W. Porto Jr., P. H. Souza, T. M. Barbosa. A Photoplethysmographic Monitor for Local Pulse Wave Velocity Measurement, International Journal of Computer Applications 177(31) (2020) 62-67. doi:10.5120/ijca2020919811
[4] R. Mukkamala, J.-O. Hahn, O. T. Inan, L. K. Mestha, C.-S. Kim, H. Töreyin, S. Kyal, Towards Ubiquitous Blood Pressure Monitoring via Pulse Transit Time: Theory and Practice, IEEE Transactions on Biomedical Engineering 62 (8) (2015) 1879–1901. doi:10.1109/TBME.2015.2441951
[5] D. J. McDuff, J. Hernandez, S. Gontarek, R. W. Picard, COGCAM: Contact-free Measurement of Cognitive Stress During Computer Tasks with a Digital Camera, in 2016 Conference on Human Factors in Computing Systems, San Jose, (2016) 4000–4004. doi:10.1145/2858036.2858247
[6] D. McDuff, S. Gontarek, R. Picard, Remote measurement of cognitive stress via heart rate variability, in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 26-30 Aug. 2014, Chicago, IEEE, 2014. doi:10.1109/EMBC.2014.6944243
[7] M.-Z. Poh, D. J. McDuff, R. W. Picard, Non-contact, automated cardiac pulse measurements using video imaging and blind source separation, Optics Express 18 (10) (2010) 10762–10774. doi:10.1364/OE.18.010762
[8] M.-Z. Poh, D. J. McDuff, R. W. Picard, Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam, IEEE Transactions on Biomedical Engineering 58 (1) (2011) 7–11. doi:10.1109/TBME.2010.2086456
[9] N. Sugita, K. Obara, M. Yoshizawa, Techniques for estimating blood pressure variation using video images, in 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), (2015) 25-29, Milan, Italy, IEEE, doi:10.1109/EMBC.2015.7319325
[10] E. Dolan, A. Stanton, L. Thijs, K. Hinedi, N. Atkins, S. McClory, et al., Superiority of ambulatory over clinic blood pressure measurement in predicting mortality: the Dublin outcome study, Hypertension, 46, (2005) 156-161. doi:10.1161/01.HYP.0000170138.56903.7a
[11] Y. L. Zheng, X. R. Ding, C. C. Poon, B. P. Lo, H. Zhang, X. L. Zhou, Unobtrusive sensing wearable devices for heart informatics, IEEE Transactions on Biomedical Engineering, 61(5) (2014) 1538-54. doi:10.1109/TBME.2014.2309951
[12] B. Klaassen, B. J. F. van Beijnum, H. J. Hermens, Usability in telemedicine systems—A literature survey, International Journal of Medical Informatics, 93(9) (2016), 57-69. doi:10.1016/j.ijmedinf.2016.06.004
[13] M, Nitzan. B. Khanokh, and Y, Slovik, The difference in pulse transit time to the toe and finger measured by photoplethysmography, Physiological measurement, 23(8)5, (2001). doi:10.1088/0967-3334/23/1/308
[14] W. L. Khong, N. S. V. K. Rao, M. Mariappan, Blood pressure measurements using non-contact video imaging techniques: IEEE 2nd International Conference on Automatic Control and Intelligent Systems (I2CACIS), Kota Kinabalu, Malaysia, IEEE, 2017. doi:10.1109/I2CACIS.2017.8239029
[15] S. Laurent, J. Cockcroft, L. Van Bortel, P. Boutouyrie, C. Giannattasio, D. Hayoz, B. Pannier, C. Vlachopoulos, I. Wilkinson, H. Struijker-Boudier, Expert consensus document on arterial stiffness: methodological issues and clinical applications, European Heart Journal, 27(21) 2588-2605, 2006. doi:10.1093/eurheartj/ehl254
[16] X. R. Ding, N. Zhao, G. Z. Yang, R. I. Pettigrew, B. Lo, F. Miao, Y. Li, J. Liu, Y. T. Zhang, Continuous Blood Pressure Measurement from Invasive to Unobtrusive: Celebration of 200th Birth Anniversary of Carl Ludwig, IEEE Journal of Biomedical and Health Informatics, 20, 1455-1465, 2016. doi:10.1109/JBHI.2016.2620995
[17] T. P. Sacramento, I. M. B. Souza, P. V. O. Vitorino, T. M. G. A. Barbosa, A real-time software to the acquisition of heart rate and photoplethysmography signal using two regions of interest simultaneously via webcam, in 2017 IEEE MIT Undergraduate Research Technology Conference (URTC), (2017) 3-5 , Cambridge, MA, IEEE, 2018. doi:10.1109/URTC.2017.8284207
[18] M. P. Tarvainen, P. O. Ranta-aho, P. A. Karjalainen, An advanced detrending method with application to HRV analysis, IEEE Transactions on Biomedical Engineering 49 (2) (2002) 172–175. doi:10.1109/10.979357
[19] S. Kwon, H. Kim, K. S. Park, Validation of heart rate extraction using video imaging on a smartphone`s built-in camera system, in 2012 Annual International Conference of the IEEE Engineering in Medicine Biology Society, 28 (1) 2012, San Diego, IEEE, doi:10.1109/EMBC.2012.6346392
[20] P. H. B. Souza, J. O. Ferreira, T. M. G. de A. Barbosa, A. F. da Rocha, HRVCam: A software for real-time feedback of heart rate and HRV, in 2016 IEEE 6th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS), (2016) 13-15, Atlanta, IEEE, 2017. doi:10.1109/ICCABS.2016.7802767
[21] P. H. de B. Souza, I. M. B. Souza, T. P. Sacramento, P. C. de Matos Lima Martins, P. V. de Oliveira Vitorino, G. C. Ramos, T. M. G. de Andrade Barbosa, A. F. da Rocha, Contributions to the Acquisition of Heart Rate and Photoplethysmography Signal Using a Real-Time Software, in 2018 IEEE International Conference on Healthcare Informatics (ICHI), (2018) 4-7, 332–337. doi:10.1109/ICHI.2018.00046
[22] Gupta, R. K. Agrawal, B. Kaur, Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods, Methodologies, and Applications 19 (10) (2015) 2799–2812. doi:10.1007/s00500-014-1443-1
[23] S. G. Soares, R. Araújo, An Adaptive Ensemble of On-line Extreme Learning Machines with Variable Forgetting Factor for Dynamic System Prediction, Neurocomputing 171 (2016) 693–707. doi:10.1016/j.neucom.2015.07.035
[24] W. C. Tsai, J.Y. Chen, M.C. Wang, H.T. Wu, C.K. Chi, Y.K. Chen, J. H. Chen, L. J Lin, Association of risk factors with increased pulse wave velocity detected by a novel method using dual-channel photoplethysmography, American Journal of Hypertension, 18, 1118-1122, 2005. doi:10.1016/j.amjhyper.2005.03.739
[25] T. B. Fitzpatrick. The validity and practicality of sun-reactive skin types I through VI. Archives of Dermatology. 1988 Jun;124(6):869-871. doi:10.1001/archderm.1988.01670060015008
[26] L. M. da Silva, P. H. de B. Souza, A. F. da Rocha, T. M. G. de A. Barbosa. Contactless Cardio Monitor: a Contactless Cardiovascular Monitoring Software, International Journal of Biotech Trends and Technology 10(4) (2020) 30-37. doi: 10.14445/22490183/IJBTT-V10I4P604

Keywords
Blood Pressure, Camera, Machine Learning, Pulse Transit Time, Pulse Wave Velocity, Contactless.