A Minimized Measurement Scheme for Predicting Hemoglobin A1c (HbA1c) Using Discrete Self-Monitoring Blood Glucose Data Within 4 Weeks for People with Type 2 Diabetes
Authors' conclusion
A minimized calculation model for accurately and robustly predicting HbA1c using discrete self-monitoring of blood glucose data within 4 weeks for people with T2D has been established and provides a new reference for the design of a scheme for blood glucose monitoring.
Study context
- Population
- People with T2D; diabetes care clinic of Peking University First Hospital∼420,000 glucose, 10,000 HbA1c values
- Participants
- 2,432 people
- Comparison
- Multiple blood glucose monitoring schemes compared; chosen model vs previous studies
- Outcome
- Accuracy of HbA1c prediction (MAE, root mean square error, R value) from discrete SMBG values
- Follow-up
- Last 4 weeks before HbA1c prediction
Methodological detailsregularized extreme learning machine, two data sets, 2017–2022
- Regularized extreme learning machine
- Two data sets, 2017–2022
Main finding
As reported in the abstract
Data fitting of the chosen scheme
R
0.8029
P < 0.001
Mean absolute error (MAE)
0.3181%
95% CI 0.2666–0.3695%
Minimum SMBG needed in last 4 weeks: fasting and postprandial values (one each per 4 days)
7 fasting + 7 postprandial
Further findings
Comparison with previous studies
- Better accuracy and stability than previous studies, especially in the great glucose fluctuation group
- P < 0.05
Original publication
A Minimized Measurement Scheme for Predicting HbA1c Using Discrete Self-Monitoring Blood Glucose Data Within 4 Weeks for People with Type 2 Diabetes. Diabetes Technol Ther. Published 3 January 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →