Development and Validation of an Electronic Health Record–Based Risk Assessment Tool for Hypoglycemia in Patients With Type 2 Diabetes Mellitus
Authors' conclusion
We demonstrated that a hypoglycemia risk model can be successfully adapted from the ACCORD data to the EHR, with validation by a prospective study using CGM-assessed hypoglycemia. The HypoHazardScore represents a significant advancement toward implementing an EHR-based decision support system that can help reduce hypoglycemia in patients with T2DM.
Study context
- Population
- Participants with T2D, University of Minnesota; hypoglycemia assessed prospectively by continuous glucose monitoring (CGM) over 16 weeks
- Participants
- 40 participants
- Comparison
- High vs low HypoHazardScore
- High HypoHazardScoren = 21
- Low HypoHazardScoren = 19reference
- Outcome
- Prediction of ≥1 CGM-assessed hypoglycemic event (glucose <54 mg/dL for ≥15 minutes)
- Follow-up
- 16 weeks
Methodological detailsprospective validation, proof-of-concept, single-centre, HypoHazardScore translated from Action to Control Cardiovascular Risk in Diabetes (ACCORD) hypoglycemia risk model to electronic health record (EHR) data; combines 16 EHR risk factors
- Prospective validation
- Proof-of-concept
- Single-centre
- HypoHazardScore translated from ACCORD hypoglycemia risk model to EHR data; combines 16 EHR risk factors
Performance
As reported in the abstract
| Test or model | AUC |
|---|---|
| HypoHazardScore | 0.723 |
HypoHazardScore
AUC0.723
- Correlation with frequency of CGM-assessed hypoglycemic events
- r = 0.38
- Correlation with percent time in CGM-assessed hypoglycemia
- r = 0.39
Further findings
Frequency of CGM-assessed hypoglycemic events · 16-week follow-up
Percent time in CGM-assessed hypoglycemia · 16-week follow-up
Original publication
Development and Validation of an Electronic Health Record–Based Risk Assessment Tool for Hypoglycemia in Patients With Type 2 Diabetes Mellitus. J Diabetes Sci Technol. Published 28 June 2023. doi:10. 1177/ 19322968231184497
Composed by AI from the published abstract and checked against it. How Briefs are made →