Digital camera and AI check blood pressure

  • December 19, 2022
  • Steve Rogerson

Monitoring blood pressure using a digital camera and artificial intelligence (AI) could soon be the norm, thanks to a technique developed by Australian and Iraqi researchers.

Using the same remote-health technology they pioneered to monitor vital health signs from a distance, engineers from the University of South Australia (UniSA) and Baghdad’s Middle Technical University have designed a non-contact system to measure systolic and diastolic pressure accurately.

It could replace the existing uncomfortable and cumbersome method of strapping an inflatable cuff to a patient’s arm or wrist, the researchers claim.

In a paper published in Inventions, the researchers describe the technique, which involves filming a person from a short distance for ten seconds and extracting cardiac signals from two regions in the forehead, using artificial intelligence algorithms.

The systolic and diastolic readings were around 90 per cent accurate, compared with the existing instrument – a digital sphygmomanometer – used to measure blood pressure, that is itself subject to errors.

Experiments were performed on 25 people with different skin tones and under changing light conditions, overcoming the limitations reported in previous studies.

“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,” UniSA remote sensing engineer Javaan Chahl said. “Furthermore, in the past 30 years, the number of adults with hypertension has risen from 650 million to 1.28 billion worldwide.”

He said the health sector needed a system that could accurately measure blood pressure and assess cardiovascular risks when physical contact with patients was unsafe or difficult, such as during the recent Covid outbreak.

“If we can perfect this technique, it will help manage one of the most serious health challenges facing the world today,” Chahl said.

The 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 USA during the pandemic to monitor for signs of Covid-19 from a distance.

The paper was authored by Chahl and Ali Al-Naji, Ahmed Bashar Fakhri and Mustafa Mahmood from Middle Technical University, Baghdad.