An experimental high-speed video camera powered by artificial intelligence provided quick, no-contact screenings for high blood pressure and type 1 or type 2 diabetes without blood tests or blood pressure cuffs in a preliminary study, Japanese researchers say.

Blood pressure and diabetes subtly alter blood flow. The researchers' AI algorithm detects high blood pressure and diabetes by analyzing blood flow features in face and palm skin as captured in the video camera's 150 images per second.

In 215 volunteers, including 62 with hypertension and 44 with diabetes, the video imaging/algorithm combination was 94% accurate in detecting stage 1 hypertension, or blood pressure of 130/80 mm Hg or higher.

Compared with the standard hemoglobin A1c blood test, which reflects blood sugar levels over several months, the video/algorithm combo was 75% accurate in identifying people with diabetes.

“Some of the major complications of diabetes are peripheral neuropathy - weakness, pain and numbness, usually in the hands and feet - and other diseases related to blood vessel damage,” study leader Ryoko Uchida, B.Sc. (Pharm.), of the University of Tokyo said in a statement.

“It makes sense that changes in blood flow would be a hallmark of diabetes,” said Uchida, who will present the data at the upcoming AHA scientific meeting.

The researchers still need to teach the algorithm to adjust for irregular heartbeats and test it in larger, more diverse populations, they said.