A Blood Pressure Prediction Method Based on Imaging Photoplethysmography in combination with Machine Learning

Abstract This paper proposes a non-contact blood pressure implement (NCBP) system based on imaging photoplethysmography (IPPG) The system collects facial videos through a webcam under ambient light, and extracts pulse wave signals from the videos by means of IPPG technology. From the signals (also called IPPG signals), we extracted 26 features for estimating blood pressure (BP), and trained them through four machine learning algorithms. Finally, we selected the most accurate model for blood pressure prediction. By experimenting on 191 volunteers and comparing four models, support vector regression (SVR) is the best model for predicting blood pressure. The results of SVR are that the standard deviation (STD) and mean absolute error (MAE) of systolic blood pressure (SBP) are 3.35 mmHg, 9.97 mmHg, and those of diastolic blood pressure (DBP) are 2.58 mmHg, 7.59 mmHg respectively. We conclude that through our proposed system based on IPPG technology, blood pressure can be accurately predicted in a non-contact way. In addition, this paper proposes two new methods, the region of interest (ROI) selection method based on colormaps and robust peak extraction method, which solve the key steps in IPPG technology. Finally, we discussed the influence of light intensity on the experiment, and simplified the NCBP experimental device. The system has the potential of replacing the traditional cuff-based sphygmomanometers, and has guiding significance to the future development of blood pressure measurement devices.

[1]  J. Hahn,et al.  Smartphone-based blood pressure monitoring via the oscillometric finger-pressing method , 2018, Science Translational Medicine.

[2]  Tapio Taipalus,et al.  Comparison of photoplethysmogram measured from wrist and finger and the effect of measurement location on pulse arrival time , 2018, Physiological measurement.

[3]  Enric Monte-Moreno,et al.  Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques , 2011, Artif. Intell. Medicine.

[4]  U. Bal.  Non-contact estimation of heart rate and oxygen saturation using ambient light. , 2015, Biomedical optics express.

[5]  Joonnyong Lee,et al.  Analysis of Pulse Arrival Time as an Indicator of Blood Pressure in a Large Surgical Biosignal Database: Recommendations for Developing Ubiquitous Blood Pressure Monitoring Methods , 2019, Journal of clinical medicine.

[6]  D. Mant,et al.  Normal ranges of heart rate and respiratory rate in children from birth to 18 years of age: a systematic review of observational studies , 2011, The Lancet.

[7]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[8]  Jun Xiao,et al.  Relationship between Vascular Elasticity and Human Pulse Waveform Based on FFT Analysis of Pulse Waveform with Different Age , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[9]  Guanglin Li,et al.  Towards accurate estimation of cuffless and continuous blood pressure using multi-order derivative and multivariate photoplethysmogram features , 2021, Biomed. Signal Process. Control..

[10]  Norimichi Tsumura,et al.  Non-contact method of blood pressure estimation using only facial video , 2020, Artificial Life and Robotics.

[11]  Zhong-Ping Feng,et al.  Smartphone-Based Blood Pressure Measurement Using Transdermal Optical Imaging Technology. , 2019, Circulation. Cardiovascular imaging.

[12]  Survi Kyal,et al.  Toward Ubiquitous Blood Pressure Monitoring via Pulse Transit Time: Theory and Practice , 2015, IEEE Transactions on Biomedical Engineering.

[13]  Daniel McDuff,et al.  Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam , 2011, IEEE Transactions on Biomedical Engineering.

[14]  Dietmar Stöckl,et al.  Application of the Bland-Altman plot for interpretation of method-comparison studies: a critical investigation of its practice. , 2002, Clinical chemistry.

[15]  Haiyan Wu,et al.  A Non-Invasive Continuous Blood Pressure Estimation Approach Based on Machine Learning , 2019, Sensors.

[16]  Zhan Gao,et al.  Adaptive pulse oximeter with dual-wavelength based on wavelet transforms. , 2013, Optics express.

[17]  Andrew M. Carek,et al.  Conventional pulse transit times as markers of blood pressure changes in humans , 2020, Scientific Reports.

[18]  Alfredo Vellido,et al.  Blood Pressure Assessment with Differential Pulse Transit Time and Deep Learning: A Proof of Concept , 2018, Kidney Diseases.

[19]  Makoto Yoshizawa,et al.  Techniques for estimating blood pressure variation using video images , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[20]  Zhitao Liu,et al.  A Fast Grid Search Method in Support Vector Regression Forecasting Time Series , 2006, IDEAL.

[21]  Qiao Zhang,et al.  Noninvasive cuffless blood pressure estimation using pulse transit time and Hilbert-Huang transform , 2013, Comput. Electr. Eng..

[22]  Aljo Mujcic,et al.  Blood pressure estimation using video plethysmography , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[23]  Lionel Tarassenko,et al.  Non-contact measurement of oxygen saturation with an RGB camera. , 2015, Biomedical optics express.

[24]  Joseph Finkelstein,et al.  Introducing Contactless Blood Pressure Assessment Using a High Speed Video Camera , 2016, Journal of Medical Systems.

[25]  Ahmadreza Attarpour,et al.  Cuff-less continuous measurement of blood pressure using wrist and fingertip photo-plethysmograms: Evaluation and feature analysis , 2019, Biomed. Signal Process. Control..

[26]  E. O’Brien,et al.  Recommendations on blood pressure measurement. , 1986, British medical journal.

[27]  Robert B. Dunn,et al.  Detection of transient signals using the energy operator , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[28]  V. Somers,et al.  Arterial baroreflex function and cardiovascular variability: interactions and implications. , 2002, American journal of physiology. Regulatory, integrative and comparative physiology.

[29]  Alberto Porta,et al.  Frequency-dependent baroreflex modulation of blood pressure and heart rate variability in conscious mice. , 2005, American journal of physiology. Heart and circulatory physiology.

[30]  E. O’Brien,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. , 1990, Journal of hypertension.

[31]  M. Pencina,et al.  General Cardiovascular Risk Profile for Use in Primary Care: The Framingham Heart Study , 2008, Circulation.

[32]  Norbert Noury,et al.  A review of methods for non-invasive and continuous blood pressure monitoring: Pulse transit time method is promising? , 2014 .

[33]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..