The accuracy of provider diagnosed diabetes type in youth compared to an etiologic criteria in the SEARCH for Diabetes in Youth Study. Issue 8 (6th October 2020)

• Record Type: Journal Article
• Authors: Crume, Tessa L.; Hamman, Richard F.; Isom, Scott; Divers, Jasmin; Mayer‐Davis, Elizabeth J.; Liese, Angela D.; Saydah, Sharon; Lawrence, Jean M.; Pihoker, Catherine; Dabelea, Dana
• Is Part Of: Pediatric diabetes. Volume 21:Issue 8(2020)
• Page Start: 1403
• Page End: 1411
• Publication Date: 2020-10-06
• Subjects: diabetes autoantibodies -- surveillance -- type 1 diabetes -- type 2 diabetes -- validity; Diabetes in children -- Periodicals; 616.462
• DOI: 10.1111/pedi.13126
• Languages: English
• ISSNs: 1399-543X

Abstract

Abstract: Background: Although surveillance for diabetes in youth relies on provider‐assigned diabetes type from medical records, its accuracy compared to an etiologic definition is unknown. Methods: Using the SEARCH for Diabetes in Youth Registry, we evaluated the validity and accuracy of provider‐assigned diabetes type abstracted from medical records against etiologic criteria that included the presence of diabetes autoantibodies (DAA) and insulin sensitivity. Youth who were incident for diabetes in 2002‐2006, 2008, or 2012 and had complete data on key analysis variables were included (n = 4001, 85% provider diagnosed type 1). The etiologic definition for type 1 diabetes was ≥1 positive DAA titer(s) or negative DAA titers in the presence of insulin sensitivity and for type 2 diabetes was negative DAA titers in the presence of insulin resistance. Results: Provider diagnosed diabetes type correctly agreed with the etiologic definition of type for 89.9% of cases. Provider diagnosed type 1 diabetes was 96.9% sensitive, 82.8% specific, had a positive predictive value (PPV) of 97.0% and a negative predictive value (NPV) of 82.7%. Provider diagnosed type 2 diabetes was 82.8% sensitive, 96.9% specific, had a PPV and NPV of 82.7% and 97.0%, respectively. Conclusion: Provider diagnosis of diabetes type agreed with etiologic criteria for 90% of the cases. While the sensitivity and PPV were high for youth with type 1 diabetes, the lower sensitivity and PPV for type 2 diabetes highlights the value of DAA testing and assessment of insulin sensitivity status to ensure estimates are not biased by misclassification.