“We developed this sensor to collect physiological data, information including ECG, heart rate, respiration, and body temperature,” said Jenny Tseng, Singular Wing’s marketing specialist, when New Atlas spoke with her at the expo. “And at this exhibition, we display the glucose monitoring. So, we use ECG to estimate the glucose level for high, medium, and low glucose level.”

Used to diagnose problems with heart rate or rhythm, an ECG is a non-invasive method of reading the electrical activity of the heart. In a medical setting, it might involve applying several tiny gel pads to the arms, legs, and chest and having the patient lie motionless for a minute or so. Naturally, a lot of wearable technology now continuously tracks a user's heart rhythm and rate, reports Paul McClure in New Atlas.

Research has demonstrated that both hypoglycemia and hyperglycemia impact the electrical properties of the heart, resulting in specific alterations that are visible on an electrocardiogram. In order to reliably forecast blood sugar, researchers have employed machine learning to analyze ECGs and create algorithms based on those data.

Related South Korean CGM Receives Regulatory Approval

While the product is still under development, Singular Wings has done the same with their non-invasive CGM.

“Because we use machine learning method and … the accuracy, the average accuracy, I can tell you, is about 80%,” said Dick Hsieh, PhD, account manager for Singular Wings. “But it’s about model training. We still need [a] validation stage. But the result of [the] validation stage, it is [at] the moment unknown.”