For Quick Alerts
ALLOW NOTIFICATIONS  
For Daily Alerts

Blood Pressure Can Be Measured With A Video Selfie In The Near Future

What if measuring blood pressure becomes as easy as taking a selfie? That's true! If we believe the research published in Circulation: Cardiovascular Imaging [1] , video selfies can help in accurately measuring the blood pressure.

BP Can Now Be Measured By Video Selfie

Researchers from India, Canada, and China developed a technology known as transdermal optical imaging (TOI). The technology reads the facial blood flow change pattern via the video captured by a phone's camera. It then uses advanced machine learning to measure blood pressure by analyzing the received signal.

Transdermal optical imaging technology is a contactless way to measure the blood pressure and more advanced than traditional cuff-based measurement belt that lacks comfort and convenience. The digital optical sensors present in phones visualise the blood flow pattern and extract data for reading. It happens when ambient light falls on the skin's outer layer.

Ramakrishna Mukkamala, an Indian-origin researcher and professor at Michigan State University said, "This study shows that facial video can contain some information about systolic blood pressure".

The lead author of the research, Kang Lee, Professor at the University of Toronto said, "High blood pressure is a major contributor to cardiovascular disease - a leading cause of death and disability. To manage and prevent it, regular monitoring of one's blood pressure is essential".

He added, "Cuff-based blood pressure measuring devices, while highly accurate, are inconvenient and uncomfortable. Users tend not to follow American Heart Association guidelines and device manufacturers' suggestion to take multiple measurements each time".

About the Study

The study was conducted by using an iPhone containing transdermal optical imaging (TOI) software. Two-minute facial clips of the 1328 participants were recorded who were mainly Canadian and Chinese adults.

The systolic, diastolic and pulse pressure readings recorded by the smartphone were compared to the readings of the traditional cuff-based device. The researcher then used the compared data to teach TOI the accurate way to measure blood pressure through facial blood flow patterns.

It worked! On average, the accuracy of systolic blood pressure was 95% while the accuracy for diastolic blood pressure and pulse pressure was 96%.

"The technology's high accuracy is within international standards for devices used to measure blood pressure. If future studies confirm our results and show this method can be used to measure blood pressures that are clinically high or low, we will have the option of a contactless and non-invasive method to monitor blood pressures conveniently -- perhaps anytime and anywhere -- for health management purposes," said Lee who has co-founded a start-up Nuralogix to release an app based on the same principle. In future, he is planning to expand to other AI-based health data like haemoglobin check, glucose check and cholesterol check.

On this accord, Prof. Ramakrishna Mukkamala said, "If future studies could confirm this exciting result in hypertensive patients and with video camera measurements made during daily life, then obtaining blood pressure information with a click of a camera may become reality."

Drawbacks of TOI

  • The research was conducted on videos taken in a well-controlled ambience with fixed lightening. So, it is unclear whether TOI can do the accurate reading of blood pressure in a less controlled environment (home) or not.
  • As the skin tone varies with people, it is unclear whether the result would be the same across all the tones or not.
  • The video clip timing is 2 minutes that makes it time-consuming. However, the researchers are trying to decrease the video length to 30 seconds to make it more user-friendly.
View Article References
  1. [1] Kearney PM, Whelton M, Reynolds K, Muntner P, Whelton PK, He J. Global burden of hypertension: analysis of worldwide data.Lancet. 2005; 365:217-223. doi: 10.1016/S0140-6736(05)17741-1