End-Stage Kidney Disease (ESKD)
Phenotype Description
A phenotype to identify patients with end-stage kidney disease (ESKD), defined as having either chronic dialysis or kidney transplant based on a combination of kidney transplant, kidney biopsy, and kidney dialysis procedure and condition codes, and eGFR values.
Funder(s)
Provenance
Developed as part of the Preserving Kidney Function in Children with Chronic Kidney Disease (PRESERVE) study.
Algothrithm Description
The computable phenotype was developed to query patients ESKD patients (patients who had either undergone kidney chronic dialysis or kidney transplant) and was validated against a USRDS dataset and a subset of chart review patients.
The most optimal computable phenotype for identifying ESKD required one code from Group A (more specific) or two distinct codes from Group B (more sensitive) and at least five eGFR measurements ≤15 mL/min/1.73m² on different days.
This algorithm achieved:
- F1 Score: 0.92 (95% CI 0.88-0.95)
- Sensitivity: 94.6% (95% CI 92.8%-96.2%)
- PPV: 86.8.7% (95% CI 84.4%-89.3%).
Related Concept Sets
Vocabulary
Related Publications
Creative Commons license
Except where otherwised noted, this item's license is described as a CC-BY Attribution 4.0 license.