Scientists have designed an AI tool which uses driving behaviour and head/gaze motion to alert people with diabetes if their blood sugar drops while driving.
Hypoglycaemia can pose a serious risk when driving, so there are hopes this new technology will improve road safety.
Scientists led by a team from LMU Munich developed the model after collecting data from 30 people with diabetes while they were driving.
The data included speed of eye movements and car speed while their blood sugar levels were normal, and after they had been put in a hypoglycaemic state, with a medical professional in the car.
The team used the data to build a novel machine learning (ML) model that reliably recognises hypoglycaemic episodes.
Simon Schallmoser, one of the contributing researchers and doctoral candidate at the Institute of AI in Management at LMU, said: “This technology could serve as an early warning system in cars and enable drivers to take necessary precautions before hypoglycaemic symptoms impair their ability to drive safely.”
- Applying for a Driving Licence and Informing the DVLA
- Patients prefer ChatGPT responses over doctors’ responses
The model was also accurate when only head/gaze motion data was used, which will be important when it comes to self-driving cars.
Professor Stefan Feuerriegel, head of the Institute of AI in Management and project partner, said: “This study not only showcases the potential for AI to improve individual health outcomes but also its role in improving safety on public roads.”
Read the study in NEJM AI.
