ΑΙhub.org
 

New device monitors blood glucose levels using radar and AI


by
15 October 2020



share this:
Researchers test a prototype of a new diabetes device for prick-free glucose monitoring.

New technology can quickly and accurately monitor glucose levels in people with diabetes without painful finger pricks to draw blood. A palm-sized device developed by researchers at the University of Waterloo uses radar and artificial intelligence (AI) to non-invasively read blood inside the human body.

“The key advantage is simply no pricking,” said George Shaker, an engineering professor at Waterloo. “That is extremely important for a lot of people, especially elderly people with very sensitive skin and children who require multiple tests throughout the day.”

About the same size as existing glucometers, the rectangular device works by sending radio waves through the skin and into blood vessels when users place the tip of their finger on a touchpad. The waves are then reflected back to the device for signal processing and analysis by a machine learning algorithm (principal component analysis), telling users within seconds whether their blood sugar has gone up, down or remained the same.

Changes are measured in relation to a baseline reading that would be obtained every few weeks with a glucometer or a laboratory blood test to ensure accuracy.

“Our safe, reusable, pain-free device would eliminate the need for implanted sensors, patches or devices that use chemical reactions or fluid transfer through the skin,” said Ala Eldin Omer, an engineering PhD student who led the project.

Researchers are now exploring commercialization of the inexpensive technology – they estimate the device would retail for less than $500 – and developing a wearable device similar to a smartwatch that would be on at all times.

“This finding paves the way for continuous monitoring,” said Shaker. “Given the current pace of progress, I expect the technology to be available in a wearable form within the next couple of years.”

Safieddin (Ali) Safavi-Naeini, also an engineering professor at Waterloo, said the science at the heart of the diabetes device potentially has several additional applications. “Since many ingredients of blood have distinct electromagnetic properties, the same technology could be extended to other types of blood analysis and medical diagnosis,” he said.

Much of the work was conducted at the Wireless Sensors and Devices Lab and the Centre for Intelligent Antenna and Radio Systems (CIARS) at Waterloo. Collaborators included several researchers at Sorbonne University in Paris.

Read the paper in full

Low‑cost portable microwave sensor for non‑invasive monitoring of blood glucose level: novel design utilizing a four‑cell CSRR hexagonal confguration
Ala Eldin Omer, George Shaker, Safeddin Safavi‑Naeini, Hamid Kokabi, Georges Alquié, Frédérique Deshours & Raed M. Shubair.




University of Waterloo

            AUAI is supported by:



Subscribe to AIhub newsletter on substack



Related posts :

Disappearing lakes and AI are helping scientists map Arctic permafrost thaw in near‑real time

  18 Sep 2026
Researchers created an interactive website to track permafrost thaw across the Arctic.

How much can fair budget-division rules resist manipulation?

The authors write about their award-winning IJCAI-ECAI paper: "Approximate Strategyproofness in Approval-based Budget Division".

AI dives into a sea of data, from plankton to pollution

  16 Sep 2026
“Faster and cheaper monitoring means problems like plankton decline, litter accumulation, oil spills and coral degradation can be picked up and acted on sooner."

Interview with Yash Saxena: how is external knowledge used in AI systems?

  15 Sep 2026
What happens to information from external sources as it moves through an AI system?

When AI art has no author: Study finds generated images often can’t be traced to training data

  14 Sep 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.

AI in nature conservation: powerful tool or dangerous shortcut?

  11 Sep 2026
AI provides opportunity for future biodiversity conservation but introduces risks .

Improving the process for large-scale recommender systems: an interview with Haruka Kiyohara

  10 Sep 2026
Credit-assigned policy gradient for early stage retrieval in two-stage ranking.

The Machine Ethics podcast: Data Collective with E.M. Lewis-Jong

Ben chats to E.M. Lewis-Jong about the promise of AI and making human connection easier, speech recognition and supporting linguistic diversity, making useful technologies that have a purpose, and more.



AUAI is supported by:







Subscribe to AIhub newsletter on substack




 















©2026.05 - Association for the Understanding of Artificial Intelligence