Description: This study describes the development of an automated algorithm to accurately identify children and adolescents with diabetes using electronic health records. By analyzing lab results, diagnosis codes, and medication data, the algorithm distinguishes between type 1 and type 2 diabetes with high sensitivity and specificity. It provides a reliable, scalable method for using EHR data to support pediatric diabetes research and improve disease surveillance.

Citation: Li, P., Spector, E., Alkhuzam, K., Patel, R., Donahoo, W. T., Bost, S., Lyu, T., Wu, Y., Hogan, W., Prosperi, M., Dixon, B. E., Dabelea, D., Utidjian, L. H., Crume, T. L., Thorpe, L., Liese, A. D., Schatz, D. A., Atkinson, M. A., Haller, M. J., Shenkman, E. A., … Shao, H. (2025). Developing an automated algorithm for identification of children and adolescents with diabetes using electronic health records from the OneFlorida+ clinical research network. Diabetes, obesity & metabolism, 27(1), 102–110. https://doi.org/10.1111/dom.15987