Machine learning for non‐invasive sensing of hypoglycaemia while driving in people with diabetes
Authors' conclusion
Our findings suggest that an ML approach based on CAN and ET data, exclusively, enables detection of hypoglycaemia while driving. This provides a promising concept for alternative and non-invasive detection of hypoglycaemia.
Study context
- Population
- Individuals with T1D driving in a simulator
- Participants
- 18 vs 9
- Comparison
- Study 1 vs Study 2
- Study 1n = 18
- Study 2n = 9
- Outcome
- Detection of hypoglycaemia by machine learning (ML) approach based on driving (CAN) and eye tracking (ET) data (AUC)
Methodological detailstwo consecutive interventional studies, driving simulator
- Two consecutive interventional studies
- Driving simulator
Performance
As reported in the abstract
Hypoglycaemia detection by ML (CAN + ET data)
| Test or model | AUC (pronounced hypoglycaemia) | AUC (mild hypoglycaemia) |
|---|---|---|
| Study 1 | 0.88 ± 0.10 | — not stated in the abstract |
| Study 2 | — not stated in the abstract | 0.83 ± 0.11 |
AUC (pronounced hypoglycaemia)
Study 10.88 ± 0.10
Study 2— not stated in the abstract
AUC (mild hypoglycaemia)
Study 1— not stated in the abstract
Study 20.83 ± 0.11
— not stated in the abstract
Original publication
Machine learning for non‐invasive sensing of hypoglycaemia while driving in people with diabetes. Diabetes Obes Metab. Published 6 March 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →