Skip to main content

Every penny really does count.


You are here

Artificial intelligence technology can detect low blood sugar levels without fingerpick testing

Artificial intelligence technology can detect low blood sugar levels without fingerpick testing

A new technology for detecting low glucose levels via electrocardiogram using a non-invasive wearable sensor.

Published: Jan 14, 2020
Category: Research

Researchers at the University of Warwick have developed a new technology that can detect low glucose levels in people with diabetes, using wearable technology.

Signs of hypoglycaemia (also known as a hypo, when blood sugar levels are too low) can be identified early using the latest artificial intelligence technology with electrocardiogram (ECG) signals through a non-invasive wearable sensor.

If adopted for regular use the system could replace the need for fingerpick testing of blood sugar levels, which can painful, for some people with type 1 diabetes, who may be at risk of developing a hypo.

The results of two pilot studies by researchers recently published in Nature reported a rate of 82% reliability.

Existing continuous glucose monitors (CGM) currently available from the NHS for hypoglycaemia detection measure blood sugar levels using a sensor with a little needle, which sends alarms and results to a display device.

Researchers at the University of Warwick aim to remove the need for fingerpick testing.

Dr Leandro Pecchia of the University of Warwick

Dr Leandro Pecchia, from the School of Engineering at the University of Warwick, who led the study, said: “Fingerpicks are never pleasant and in some circumstances are particularly cumbersome. Taking a fingerpick during the night certainly is unpleasant, especially for young people.

“Our innovation consisted of using artificial intelligence for the automatic detecting of hypoglycaemia via few ECG beats. This is relevant because ECG can be detected in any circumstance, including sleeping.”

Dr Pecchia added: “Our approach enables personalised tuning of detection algorithms and emphasises how hypoglycaemic events affect ECG in individuals. Based on this information, clinicians can adapt the therapy to each individual. Clearly more clinical research is required to confirm these results in wider populations. This is why we are looking for partners.”

Read the report in Nature
Spotting the signs and reducing the risk of hypoglycaemic episodes is something people with type 1 diabetes deal with every day as part of their management of the condition. The FREE DRWF Diabetes Check-up Card includes a list of symptoms of hypoglycaemia, of low blood sugar levels, to remind people with type 1 diabetes what to look out for. Order yours here
Category: Research

Share this