Incidence of Leading Causes of Pediatric Chronic Kidney Disease Using Electronic Health Record-Driven Computable Phenotype

Background Incidence data on pediatric chronic kidney disease (CKD) is incomplete. We developed electronic health record (EHR)-based algorithms (e-phenotypes) to identify cases and provide incidence estimates of 5 leading causes of pediatric CKD. Methods E-Phenotypes using common standardized clinical terminology were built and contained utilization, diagnostic, procedural, age, and time-period inclusion and exclusion criteria for autosomal dominant polycystic kidney disease (ADPKD), Alport Syndrome (AS), congenital anomalies of the kidney and urinary tract (CAKUT), lupus nephritis (LN), and primary childhood nephrotic syndrome (NS). Cases diagnosed between 2014 and 2023 were identified from a pediatric healthcare system that is the sole pediatric nephrology provider serving the Atlanta Metropolitan Statistical Area (MSA). The performance of the e-phenotypes was tested using a cohort of 1,000 pediatric patients. Cases identified were used to estimate incidences using population information from the Georgia Department of Health. Results The e-phenotypes demonstrated sensitivity ranging from 0.83 to 0.95, specificity 0.96 to 1.00, PPV 0.81 to 1.00, and NPV 0.98 to 1.00. All positive likelihood ratios (LR) were >20 and negative LR < 0.20. The 6,814 combined cases of ADPKD (n=107), AS (n=31), CAKUT (n=6,120), LN (n=161), and NS (n=395) had an annual incidence of 47.07 (95% CI 45.96-48.20) per 100,000 children. Annual incidence per 100,000 children (95% CI) for each condition was: ADPKD 0.74 (0.61- 0.89), AS 0.21 (0.15-0.30), CAKUT 42.28 (41.22-43.35), LN 1.11 (0.95-1.30), and NS 2.73 (2.47-3.01). Conclusions Our incidence estimates suggest CKD conditions are common among children. The e-phenotypes require validation for use at other institutions but offer opportunities to examine determinants of CKD detection, management, and outcomes.