A Novel Electronic Medical Record Search Method to Identify Patients With Ketosis-Prone Diabetes: Implications for Discovery of Atypical Diabetes
Authors' conclusion
PEPPER streamlines EMR review, significantly reducing manual effort without sacrificing accuracy.
Study context
- Population
- Youth with T2D; identification of those with diabetic ketoacidosis (DKA) within 6 months of diagnosis, as first step to identify A-β+ ketosis-prone diabetes (KPD)
- Participants
- 1,660 electronic charts
- Comparison
- PEPPER automated electronic medical record (EMR) search vs manual review
- Outcome
- Chart review time per chart
Methodological detailsEMR search tool vs manual review
- EMR search tool vs manual review
Performance
As reported in the abstract
| Test or model | Value | Accuracy |
|---|---|---|
| PEPPER | mean 13.4 (SD 3.9) s | 100% |
| Manual review | mean 26.6 (SD 9.4) s |
Value
PEPPERmean 13.4 (SD 3.9) s
Manual reviewmean 26.6 (SD 9.4) s
Accuracy
PEPPER100%
Manual review— not stated in the abstract
- PEPPER vs Manual review: P < 0.001
Further findings
Youth with T2D and DKA identified by PEPPER, and those meeting full A-β+ KPD criteria
- Youth with T2D and DKA identified
- 110
- Met full A-β+ KPD criteria
- 21
Original publication
A Novel Electronic Medical Record Search Method to Identify Patients With Ketosis-Prone Diabetes: Implications for Discovery of Atypical Diabetes. Diabetes Care. Published 26 June 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →