Related Experiment Video
Updated: Jun 11, 2025
A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
Published on: May 10, 2022
Developing an automated algorithm for identification of children and adolescents with diabetes using electronic
Piaopiao Li1, Eliot Spector2, Khalid Alkhuzam1
1Department of Pharmaceutical Outcomes and Policy, College of Pharmacy, University of Florida, Gainesville, Florida, USA.
Insights
We created an accurate electronic health record (EHR) computable phenotype (CP) algorithm to identify type 1 and type 2 diabetes in children and adolescents. The algorithm shows high accuracy for type 1 diabetes but faces challenges in identifying type 2 diabetes.
Area of Science:
- Pediatric Endocrinology
- Health Informatics
- Clinical Data Science
Background:
- Electronic Health Records (EHRs) are rich data sources for clinical research.
- Developing accurate computable phenotypes (CPs) is crucial for large-scale analysis of diseases in pediatric populations.
- Automated identification of diabetes in youth using EHR data is essential for timely intervention and management.
Purpose of the Study:
- To develop and validate an automated CP algorithm for identifying diabetes cases in children and adolescents.
- To leverage structured EHR data from the UF Health System for diabetes phenotyping.
- To assess the accuracy of the developed CP algorithm for different diabetes types.
Main Methods:
- An iterative CP algorithm was developed using structured EHR data (2012-2020).
- A cohort of 536 individuals under 18 years with potential diabetes indicators (lab values, diagnosis codes, medications) was randomly selected.
- Four reviewers independently validated diabetes status and type through chart review.
Main Results:
- The CP algorithm demonstrated high performance: 94% sensitivity, 98% specificity, and 96% positive predictive value for type 1 diabetes (T1D).
- For type 2 diabetes (T2D), performance metrics were 95% sensitivity, 95% specificity, and 73% positive predictive value.
- The algorithm successfully identified 159 T1D and 64 T2D cases among the reviewed cohort.
Conclusions:
- A highly accurate EHR-based CP algorithm for identifying diabetes in youth was successfully developed.
- The study highlights the effectiveness of EHR data for automated phenotyping in pediatric diabetes research.
- Identifying type 2 diabetes in youth using EHR data proved more challenging compared to type 1 diabetes, consistent with existing literature.
Aim:
To develop an automated computable phenotype (CP) algorithm for identifying diabetes cases in children and adolescents using electronic health records (EHRs) from the UF Health System.
Materials And Methods:
The CP algorithm was iteratively derived based on structured data from EHRs (UF Health System 2012-2020). We randomly selected 536 presumed cases among individuals aged <18 years who had (1) glycated haemoglobin levels ≥ 6.5%; or (2) fasting glucose levels ≥126 mg/dL; or (3) random plasma glucose levels ≥200 mg/dL; or (4) a diabetes-related diagnosis code from an inpatient or outpatient encounter; or (5) prescribed, administered, or dispensed diabetes-related medication. Four reviewers independently reviewed the patient charts to determine diabetes status and type.
Results:
Presumed cases without type 1 (T1D) or type 2 diabetes (T2D) diagnosis codes were categorized as non-diabetes/other types of diabetes. The rest were categorized as T1D if the most recent diagnosis was T1D, or otherwise categorized as T2D if the most recent diagnosis was T2D. Next, we applied a list of diagnoses and procedures that can determine diabetes type (e.g., steroid use suggests induced diabetes) to correct misclassifications from Step 1. Among the 536 reviewed cases, 159 and 64 had T1D and T2D, respectively. The sensitivity, specificity, and positive predictive values of the CP algorithm were 94%, 98% and 96%, respectively, for T1D and 95%, 95% and 73% for T2D.
Conclusion:
We developed a highly accurate EHR-based CP for diabetes in youth based on EHR data from UF Health. Consistent with prior studies, T2D was more difficult to identify using these methods.
