Equivalence of Type 2 Diabetes Prevalence Estimates: Comparative Study of Similar Phenotyping Algorithms Using Electronic Health Record Data
The 2 independent CPs demonstrated equivalent T2D prevalence estimates, except in Hispanic individuals. Although the CPs can be considered statistically equivalent, the data driving each CP may impact accuracy and completeness. CP 1 was broader, incorporating clinical diagnoses, laboratory data, and medication, whereas CP 2 used clinical diagnostic codes alone. These results have implications for improving harmonization of CPs for public health surveillance.
Authors
- Katie Allen (ORCID: https://orcid.org/0000-0002-6058-6280)
- Brian E. Dixon (ORCID: https://orcid.org/0000-0002-1121-0607)
- John Price (ORCID: https://orcid.org/0009-0000-5042-6083)
- Muchiri E Wandai (ORCID: https://orcid.org/0000-0002-0840-2202)
- Ashley Wiensch (ORCID: https://orcid.org/0000-0001-6694-8089)
Institutions
- Regenstrief Institute (US)
- Richard M. Fairbanks Foundation (US)
- Indiana University – Purdue University Indianapolis (US)
Publication Details
- Journal
- JMIR Public Health and Surveillance
- Published
- 2025-09-24
- DOI
- https://doi.org/10.2196/79653
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00