Tech to defeat hypoglycemia

Researchers looked to identify if non- invasive machine learning could be used to identify early signs of hypoglycaemia (low blood glucose) in people with Type 1 Diabetes while they were driving a car.

Driving a vehicle involves the complex management of speed, braking and steering. High levels of cognitive, executive and psychomotor functions are required, all of which are affected negatively by hypoglycaemia. The researchers looked at combined driving (CAN) and eye tracking (ET) data. A Controller Area Network

(CAN) is a communication system made for vehicle intercommunication. Eye tracking is the process of measuring either the point of gaze (where one is looking) or the motion of an eye relative to the head.

The researchers studied active drivers between the ages of 21-50 years. For the study, participants familiarised themselves with the driving simulator during a test drive. They were fitted with the Dexcom G6 continuous glucose monitoring system. Eye gaze was recorded with a consumer eye tracker. Data was collected when the participants experience mild hypoglycaemia and pronounced hypoglycaemia. The study showed that the machine learning approach based on CAN and ET data, could detect hypoglycaemia while driving. The researchers concluded that this finding could pave the way for alternative and non- invasive detection methods of hypoglycaemia.