Artificial Intelligence can remotely detect dangerous hypoglycemia

Specialists from the University of Warwick introduced a new technology that allows using artificial intelligence to determine dangerously low glucose levels remotely - according to an electrocardiograph (ECG), Scientific Reports said referring to a study.

Such technology can save people with diabetes from having to do a blood test several times a day.

The team led by Dr. Leandro Pecchia conducted two pilot studies involving healthy volunteers and found that the sensitivity and specificity of the proposed technology was 82%. Similar indicators for continuous glucose monitoring systems. The new technology, however, is non-invasive, as experts emphasize.

“Fingerpricks are never pleasant and in some circumstances are particularly cumbersome. Taking fingerprick during the night certainly is unpleasant, especially for patients in paediatric age. Figure one shows the output of the algorithms over the time“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.”