Engineers have designed a system that can remotely measure blood pressure from video of a person’s forehead and using artificial intelligence algorithms to extracting cardiac signals across a range of skin tones. They describe their new technology in a new paper published in Inventions.
Using the same remote-health technology they pioneered for non-contact monitoring of vital health signs, this new technology could replace the existing uncomfortable and cumbersome method of strapping an inflatable cuff to a patient’s arm or wrist, the researchers claim.
The researchers, from the University of South Australia and Baghdad’s Middle Technical University, describe the technique, which involves filming a person from a short distance for 10 seconds and then using AI to extract cardiac signals from two regions in the forehead.
Experiments were performed on 25 people with different skin tones and under changing light conditions, overcoming the limitations reported in previous studies. Compared to a digital sphygmomanometer (itself subject to errors), the systolic and diastolic readings were around 90% accurate.
“Monitoring blood pressure is essential to detect and manage cardiovascular diseases, the leading cause of global mortality, responsible for almost 18 million deaths in 2019,” says UniSA remote sensing engineer Professor Javaan Chahl. “Furthermore, in the past 30 years, the number of adults with hypertension has risen from 650 million to 1.28 billion worldwide.”
“The health sector needs a system that can accurately measure blood pressure and assess cardiovascular risks when physical contact with patients is unsafe or difficult, such as during the recent COVID outbreak,” Prof Chahl continues. “If we can perfect this technique, it will help manage one of the most serious health challenges facing the world today.”
The cutting-edge technology has come a long way since 2017, when the UniSA and Iraqi research team demonstrated image-processing algorithms that could extract a human’s heart rate from drone video.
In the past five years the researchers have developed algorithms to measure other vital signs, including breathing rates from 50 metres away, oxygen saturation, temperature, and jaundice in newborns.
Their non-contact technology was also deployed in the United States during the pandemic for non-contact monitoring of COVID signs.
Source: University of South Australia