Innovative Design Team Posters

Inno Background.png

Wearable Blood Pressure Monitor

Team Members: Adrian Yabut, Andrew Luo, Jordan Van Wyk, Nathan Duarte

School: University of Waterloo (Team A)

Video Link:

Hypertension, defined as having a systolic blood pressure (SBP) above 130 mmHg or a diastolic blood pressure (DBP) above 80 mmHg, is a global issue [1]. Worldwide, it affects over 1 billion people and contributes to over 7.5 million cardiovascular-related deaths annually [2].

To help hypertensive patients better understand and manage their condition, we formed Pascal Labs at the University of Waterloo. Our members are building a wearable blood pressure monitor to this end.

Traditional cuff-based blood pressure monitors are bulky, uncomfortable, and cannot take measurements throughout the day. In response, companies have tried to develop wearables capable of measuring blood pressure, but these devices face various issues including high costs and a lack of clinical accuracy [3]–[5].

We aim to address issues with existing blood pressure measurement systems by analyzing the transit time and morphology of pulse waveforms. We collect these signals by integrating two low-cost, low-footprint optical sensors into a sleek wearable form factor. Pulse transit time (PTT) is an established correlate of blood pressure, but frequent calibration is required to use it for estimation [6]. To circumvent this and ensure our product is convenient for users, we simultaneously analyze pulse morphology using a technique called pulse wave analysis [7]–[10]. By extracting features which describe a pulse’s shape and analyzing them using trained machine learning models, it is possible to predict blood pressure with far less calibration. Altogether, by combining analysis of PTT and morphology, enabled by our innovative hardware design, our wearable device will be able to take clinically relevant blood pressure measurements and improve hypertension management.



[1] N. D. L. Fisher and G. Curfman, “Hypertension—A Public Health Challenge of Global Proportions,” JAMA, vol. 320, no. 17, p. 1757, Nov. 2018, doi: 10.1001/jama.2018.16760.

[2] “WHO | Raised blood pressure,” WHO. (accessed Oct. 07, 2020).

[3] “HeartGuide.”

[4] “The Asus VivoWatch BP is light for a blood pressure monitor, chunky for a fitness tracker.”

[5] “Measuring my Blood Pressure on my Samsung Watch | Samsung Australia.” (accessed Dec. 11, 2020).

[6] R. Lazazzera, Y. Belhaj, and G. Carrault, “A New Wearable Device for Blood Pressure Estimation Using Photoplethysmogram,” Sensors, vol. 19, no. 11, Jun. 2019, doi: 10.3390/s19112557.

[7] C. El-Hajj and P. A. Kyriacou, “A review of machine learning techniques in photoplethysmography for the non-invasive cuff-less measurement of blood pressure,” Biomed. Signal Process. Control, vol. 58, p. 101870, Apr. 2020, doi: 10.1016/j.bspc.2020.101870.

[8] Y. Kurylyak, K. Barbe, F. Lamonaca, D. Grimaldi, and W. Van Moer, “Photoplethysmogram-based Blood pressure evaluation using Kalman filtering and Neural Networks,” in 2013 IEEE International Symposium on Medical Measurements and Applications (MeMeA), May 2013, pp. 170–174, doi: 10.1109/MeMeA.2013.6549729.

[9] Md. S. Tanveer and Md. K. Hasan, “Cuffless blood pressure estimation from electrocardiogram and photoplethysmogram using waveform based ANN-LSTM network,” Biomed. Signal Process. Control, vol. 51, pp. 382–392, May 2019, doi: 10.1016/j.bspc.2019.02.028.

[10] E. Monte-Moreno, “Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques,” Artif. Intell. Med., vol. 53, no. 2, pp. 127–138, Oct. 2011, doi: 10.1016/j.artmed.2011.05.001.