# Development of a feasible and portable electronic flag for near-real-time identification of renal replacement therapy in the Veterans Health Administration

**Authors:** Samuel W. Golenbock, Dipandita Basnet, Hillary J. Mull, Rebecca Lamkin, Kimberly Harvey, Marlena Shin, Judith M. Strymish, Sarah Leatherman, Ryan Ferguson, Westyn Branch-Elliman

PMC · DOI: 10.1017/ash.2025.10166 · Antimicrobial Stewardship & Healthcare Epidemiology : ASHE · 2025-10-23

## TL;DR

A new electronic flag was developed to identify Veterans undergoing dialysis in real-time, improving patient safety and medication management.

## Contribution

A novel electronic flag using structured EHR data was developed to accurately identify active renal replacement therapy in Veterans.

## Key findings

- The RRT flag achieved high accuracy with an AUC of 0.976 and strong sensitivity and specificity.
- The flag combines outpatient dialysis procedures, consults, and serum creatinine levels to identify active RRT.
- The flag supports patient safety and stewardship efforts in the Veterans Health Administration.

## Abstract

Chronic kidney disease (CKD) is prevalent among US Veterans. Identifying patients undergoing dialysis in real-time is crucial for implementing patient safety measures, including stewardship interventions, such as medication dosing adjustments. Limited feasible and accurate tools exist for near-real-time identification. This study aimed to develop a renal replacement therapy (RRT) flag using structured data in the Veterans Health Administration (VHA) electronic health record (EHR).

Data from Veterans who underwent cardiovascular implantable electronic device (CIED) procedures (9/2015–12/2019) were linked to US Renal Data Systems (USRDS) data. Potential identifiers included outpatient hemodialysis procedure records, community care hemodialysis consults, ICD-10 diagnoses, and serum creatinine (SCr) >4 mg/dL. USRDS served as the comparison standard, and sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Logistic regression determined the area under the curve (AUC).

Among 37,706 CIED procedures on 34,994 Veterans, 967 patients (2.6%) were identified by USRDS as ever receiving RRT (hemodialysis and peritoneal dialysis or transplant), with 520 (1.4%) actively receiving RRT at the time of CIED. The RRT flag, combining ≥4 outpatient procedures in the prior 30 days, ≥1 consult in the prior year, and/or SCr >4 mg/dL, achieved an AUC of 0.976 (95% CI: 0.97–0.98), with high sensitivity (0.96; 95% CI: 0.94–0.97) and specificity (0.99; 95% CI: 0.99–1.00). The PPV was 0.70 (95% CI: 0.67–0.74). Performance was slightly lower when consults were replaced with ICD codes.

We developed an accurate electronic flag using structured data to identify active RRT within VHA among Veterans undergoing invasive procedures, supporting patient safety and care adjustments. This flag addresses a crucial patient safety gap and supports expansion of stewardship efforts.

## Linked entities

- **Diseases:** chronic kidney disease (MONDO:0005300)

## Full-text entities

- **Diseases:** CKD (MESH:D051436), renal replacement (MESH:D006030)
- **Chemicals:** creatinine (MESH:D003404)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12571676/full.md

## Figures

2 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12571676/full.md

## References

20 references — full list in the complete paper: https://tomesphere.com/paper/PMC12571676/full.md

---
Source: https://tomesphere.com/paper/PMC12571676