AI Used to Measure Sugar in the Blood
Researchers hope this can someday replace the invasive finger prick.
Anyone suffering from diabetes knows how important tracking sugar in the blood is. Technology has improved that process but it still requires needles and finger pricks.
Researchers at the University of Warwick in the UK are trying to change that, applying artificial intelligence to the problem.
In a paper published in journal Scientific, the scientists led by Dr. Leandro Pecchia demonstrated how they could detect sugar in the blood using ECG signals and off-the-shelf-wearable sensors.
The AI system works just as well
Two pilot studies of healthy volunteers showed the system's average sensitivity and specificity was about 82% which is comparable with the current system used to detect hypoglycemia. As it stands continuous glucose monitors or CGMs are available via the NHS for detecting sugar levels in the blood. They measure the glucose in fluid using a sensor with a needle. The senor sends alarms and data to a device. The devices often need to be calibrated two times a day and include fingerprick blood glucose level tests.
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," said Dr. Pecchia in a press release announcing the work. “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.”
Subject's own data used to train the AI algorithm
What may have made the Warwick scientists' method so effective is that the AI algorithms are trained with the subject's own data. If cohort data was used the system would not give back the same results.
"Our approach enables personalised tuning of detection algorithms and emphasize how hypoglycaemic 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., Dr. Pecchia said.
Anyone suffering from diabetes knows how important tracking sugar in the blood is. Technology has improved that process but it still requires needles and finger pricks.
Researchers at the University of Warwick in the UK are trying to change that, applying artificial intelligence to the problem.
In a paper published in journal Scientific, the scientists led by Dr. Leandro Pecchia demonstrated how they could detect sugar in the blood using ECG signals and off-the-shelf-wearable sensors.
The AI system works just as well
Two pilot studies of healthy volunteers showed the system's average sensitivity and specificity was about 82% which is comparable with the current system used to detect hypoglycemia. As it stands continuous glucose monitors or CGMs are available via the NHS for detecting sugar levels in the blood. They measure the glucose in fluid using a sensor with a needle. The senor sends alarms and data to a device. The devices often need to be calibrated two times a day and include fingerprick blood glucose level tests.
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," said Dr. Pecchia in a press release announcing the work. “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.”
Subject's own data used to train the AI algorithm
What may have made the Warwick scientists' method so effective is that the AI algorithms are trained with the subject's own data. If cohort data was used the system would not give back the same results.
"Our approach enables personalised tuning of detection algorithms and emphasize how hypoglycaemic 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., Dr. Pecchia said.