A Glycemic Status Classification Model Using a Radiofrequency Noninvasive Blood Glucose Monitor
Authors' conclusion
Our findings show that the model correctly classified glycemic status 93.37% of the time as high, normal, or low.
Study context
- Population
- Participants aged 18–65 with prediabetes or T2D and no other significant medical history; control and OGTT sessions
- Participants
- 31 participants
- Comparison
- Noninvasive radiofrequency (RF) glucose sensor vs venous blood draw on Food and Drug Administration (FDA)-cleared hospital glucose meter
- Outcome
- Correct classification of glycemic status as high, normal or low
Methodological detailsmachine learning model (time series forest), 80/20 train–test split
- Machine learning model (time series forest)
- 80/20 train–test split
Performance
As reported in the abstract
Correct classification of glycemic status (high, normal, low)
| Test or model | Value | Correctly classified |
|---|---|---|
| RF sensor | 93.37% | 93.37% |
RF sensor
Value93.37%
Correctly classified93.37%
Original publication
A Glycemic Status Classification Model Using a Radiofrequency Noninvasive Blood Glucose Monitor. Diabetes Technol Ther. Published 8 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →