Engineers have designed a way to measure blood pressure without physical contact, using a simple camera and artificial intelligence (AI).
Researchers from University of South Australia and the Middle Technical University of Baghdad, believe that their method of measuring blood pressure with a camera and through artificial intelligence can replace existing methods that use an inflatable strap wrapped around the patient's arm or wrist.
The new technique for measuring systolic and diastolic pressure, which has been published in a full research paper, involves taking 10-second videos of two areas of the forehead, from a "short distance," with a simple camera worn by the consumer, and using AI algorithms, heart rate and blood pressure can be measured.
This method came from a demonstration first shown in 2017, when the University of South Australia and the Iraqi research team were able to extract a human's heart rate from a drone video. Since then, researchers have been able to develop multiple algorithms to measure vital signs remotely, including breathing rates (from up to 50 meters away), oxygen saturation, and temperature.
Professor Javaan Chahl, in a report from the University of South Australia, states the following:
“Blood pressure monitoring is essential for the detection and management of cardiovascular disease, the leading cause of global mortality, responsible for nearly 18 million deaths in 2019.
Furthermore, over the past 30 years, the number of adults with hypertension has increased from 650 million to 1,28 billion worldwide. The healthcare 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.
If we can perfect this technique, it will help manage one of the most serious health challenges facing the world today."
To test the system, the team used 25 people, of different skin tones and in a variety of lighting conditions, in order to overcome the limitations of this technique noted in previous studies.
According to the engineers, the experiments resulted in systolic and diastolic measurements that were 90% accurate. The team says these results are very good, especially when you consider that existing pressure measuring machines lack precision and are "prone to error".