As mentioned in our report on the FreeStyle LibreLink app, "Glucose monitoring is one of the most intrusive parts of living with diabetes", according to Diabetes Australia chief executive Professor Greg Johnson.

The University of Waterloo's approach is to use a small radar device (jointly developed with Infineon) and then apply machine learning to the data collected.

The device transmits high-frequency radio waves and receives their reflections, just as radar is used to detect aircraft in the sky.

The difference is that the digitised reflections are processed by a machine learning system that interprets 500 characteristics to determine glucose levels. Google is another collaborator on the project.

"We want to sense blood inside the body without actually having to sample any fluid," said Professor George Shaker, who leads a large team working on the project.

"Our hope is this can be realised as a smartwatch to monitor glucose continuously."

Initial tests with volunteers at the Research Institute for Aging in Waterloo achieved results that were 85% as accurate as traditional blood analysis.

"The correlation was actually amazing," said Shaker. "We have shown it is possible to use radar to look into the blood to detect changes."

The plan is to improve the system for greater accuracy, and to obtain results through the skin.

"I'm hoping we'll see a wearable device on the market within the next five years," said Shaker.

Image: Nick Youngson (CC BY-SA 3.0) via Alpha Stock Images