Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
Authors' conclusion
Our approach may allow for noninvasive hypoglycemia detection using wearables in people with diabetes and thus complement existing methods for hypoglycemia detection and warning.
Study context
- Population
- Adults with diabetes on insulin treatment, with CGM; age 54.5 ± 15.2 years, HbA1c 6.9 ± 0.6%, 16 malesfinal analysis
- Participants
- 22 adults
- Outcome
- Detection of hypoglycemia (<3.9 mmol/L) in unseen individuals
Methodological detailsprospective, machine learning
- Prospective
- Machine learning
Performance
As reported in the abstract
Hypoglycemia detection solely from wearable data
AUC (ROC) for hypoglycemia detection solely from wearable data
0.76 ± 0.07
Further findings
Feature analysis
- Machine learning (ML) model associated increased heart rate, decreased heart rate variability and increased tonic electrodermal activity with hypoglycemia
Original publication
Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data. Diabetes Care. Published 17 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →