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

            AIhub is supported by:



Subscribe to AIhub newsletter on substack



Related posts :

A multi-armed robot for assisting with agricultural tasks

and   27 Mar 2026
How can a robot safely manipulate branches to reveal hidden flowers while remaining aware of interaction forces and minimizing damage?

Resource-constrained image generation and visual understanding: an interview with Aniket Roy

  26 Mar 2026
Aniket tells us about his research exploring how modern generative models can be adapted to operate efficiently while maintaining strong performance.

RWDS Big Questions: how do we highlight the role of statistics in AI?

  25 Mar 2026
Next in our series, the panel explores the statistical underpinning of AI.

A history of RoboCup with Manuela Veloso

  24 Mar 2026
Find out how RoboCup got started and how the competition has evolved, from one of the co-founders.

Information-driven design of imaging systems

  23 Mar 2026
Framework that enables direct evaluation and optimization of imaging systems based on their information content.

Machine learning framework to predict global imperilment status of freshwater fish

  20 Mar 2026
“With our model, decision makers can deploy resources in advance before a species becomes imperiled.”

Interview with AAAI Fellow Yan Liu: machine learning for time series

  19 Mar 2026
Hear from 2026 AAAI Fellow Yan Liu about her research into time series, the associated applications, and the promise of physics-informed models.

A principled approach for data bias mitigation

  18 Mar 2026
Find out more about work presented at AIES 2025 which proposes a new way to measure data bias, along with a mitigation algorithm with mathematical guarantees.



AIhub is supported by:







Subscribe to AIhub newsletter on substack




 















©2026.02 - Association for the Understanding of Artificial Intelligence