A team of researchers in the University of Warwick, UK, applied artificial intelligence (AI) technology to blood sugar testing. The scientists managed to develop an AI system that could possibly obsolete the traditional finger prick test procedures. The related pilot study results were recently published in Scientific Reports journal.
According to the report, the AI-powered system the team is currently working on is already capable of detecting low blood sugar, or hypoglycemia, with 82% accuracy, that is, at a rate similar to that of current invasive glucose testing systems and devices. The AI measures blood sugar through analyzing electrocardiogram (ECG) signals from the heart, as the heartbeat rhythm gets affected by hypoglycemia (that is, low blood sugar which may lead to diabetes).
The scientists used AI to automatically detect nocturnal hypoglycemia from just a few heartbeat signals recorded by a wearable device. The study included healthy individuals, whom the scientists monitored for 24 hours a day for 14 consecutive days.
Senior study author Leandro Pecchia, Ph.D., an associate professor of biomedical engineering at the university, commented:
“Our innovation consisted in using [AI] for automatic detecting [of] hypoglycemia via few ECG beats. This is relevant because ECG can be detected in any circumstance, including sleeping.”
Further development of the device may turn it into a real-time alarm system that would alert its bearer of significant blood sugar level fluctuations, thus shortening the amount of time that one experiences hypoglycemia and removing the inconvenience of finger prick tests.