AI and wearable sensors detect glucose levels without fingerprick test

A technology to detect low glucose levels via ECG using a non-invasive wearable sensor, which with the latest Artificial Intelligence can detect hypoglycaemic events from raw ECG signals, has been developed by researchers from the University of Warwick.

Currently, Continuous Glucose Monitors (CGM) are available by the UK's National Health Service (NHS) for hypoglycaemia detection (sugar levels into blood or derma). They measure glucose in interstitial fluid using an invasive sensor with a little needle, which sends alarms and data to a display device. In many cases, they require calibration twice a day with invasive finger-prick blood glucose level tests.

Dr. Leandro Pecchia's team at the University of Warwick discovered they can detect hypoglycaemic events from raw ECG signals acquired with off-the-shelf non-invasive wearable sensors. Their results are published in a paper titled 'Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG' in the Nature Springer journal Scientific Reports.

Two pilot studies with healthy volunteers found the average sensitivity and specificity approximately 82% for hypoglycaemia detection, which is comparable with the current CGM performance.

Pecchia said, "Fingerpicks are never pleasant and in some circumstances are particularly cumbersome. Taking fingerpick during the night certainly is unpleasant, especially for patients in pediatric age. Our innovation consisted in using artificial intelligence for automatic detecting hypoglycaemia via few ECG beats. This is relevant because ECG can be detected in any circumstance, including sleeping."

This result is possible because the Warwick AI model is trained with each subject's own data. Intersubjective differences are so significant that training the system using cohort data would not give the same results.

Pecchia said: "The differences highlighted above could explain why previous studies using ECG to detect hypoglycaemic events failed. The performance of AI algorithms trained over cohort ECG-data would be hindered by these inter-subject differences."