Artificial intelligence (AI) and radar technology can help people with diabetes manage their conditions without drawing blood. Researchers at the University of Waterloo in Canada have developed a small non-invasive device by combining radar and AI to help people manage blood glucose levels without having to traumatically poke the skin or draw blood.
“We want to sense blood inside the body without actually having to sample any fluid,” said lead author George Shaker, professor at the University of Waterloo.
The scientists carried out the research using Google’s Soli alpha kit. The Soli system, co-developed by Google and a German hardware firm Infineon, is a 60 GHz mm-wave radar that promises a small, mobile, and wearable platform intended for gesture recognition. The device works by sending high-frequency radio waves into liquids that contain various levels of glucose. The radio waves then reflect back to the device. Data on the reflected waves is then converted into digital data for analysis by AI algorithms developed by the researchers.
The software can detect glucose changes based on more than 500 wave features or characteristics, including how long it takes for them to bounce back to the device.
After conducting initial tests with volunteers at the Research Institute for Aging in Waterloo, researchers found that it was 85% accurate as conventional traditional, invasive blood analysis.
“The correlation was actually amazing. We have shown it is possible to use radar to look into the blood to detect changes,” said Shaker.
The potential applications of this radar-AI system are far-reaching, essentially allowing diabetics to monitor glucose levels non-invasively, and with a high level of precision.
The researchers are now planning to step up their work by boosting the precision of the system and looking at ways to shrink the device so it consumes less power and is more affordable. They are also looking at ways to integrate smartwatch technology to make it more accessible to everyone.
“I’m hoping we’ll see a wearable device on the market within the next five years. There are challenges, but the research has been going at a really good rate,” Prof. Shaker concluded.
The findings were published online in the International Journal of Mobile Human-Computer Interaction.