AI and ECG could provide an alternative to finger prick tests

An adult tests a child's blood glucose levels

An alternative to finger prick tests has been successfully developed using technology that detects low blood glucose levels with a non-invasive, wearable sensor.

A team from the University of Warwick say they have found a way to avoid the conventional and painful method of checking blood sugar levels using finger prick tests. Although their new system only detects when blood glucose levels fall low, it could have positive impacts when it comes to detecting hypoglycemia.

Their approach is based around using an artificial intelligence sensor hooked up to a device that works with electrocardiogram (ECG) signals. The sensor detects low blood sugar levels by tracking the person’s heart rate. This is possible because of the way that the ECG readings change when glucose levels fall below 4 mmol/L.

The artificial intelligence system is then used to recognise low blood sugar levels compared to normal readings, and could act as an alternative to finger prick tests.

Two small pilot studies have been carried out to test the technology and found it was around 82% effective at detecting hypoglycemia.

Dr Leandro Pecchia, from the School of Engineering at the University of Warwick, said: “Finger pricks are never pleasant and in some circumstances are particularly cumbersome. Taking finger pricks during the night certainly is unpleasant, especially for patients in paediatric age.

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

“Our approach enables personalised tuning of detection algorithms and emphasise how hypoglycemic events affect ECG in individuals. Basing 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.”

The research was published in the journal Nature.

To Top