Abstract: FR-PO0018
Applying Risk Stratification to Improve Guideline-Directed Medical Therapy Uptake and Albuminuria Testing in a Large US Nephrology Practice
Session Information
- Artificial Intelligence: Clinical Prediction, Decision Support, and Digital Kidney Care
October 23, 2026 | Location: Exhibit Hall A, Convention Center
Abstract Time: 10:00 AM - 12:00 PM
Category: Artificial Intelligence, Digital Health, and Data Science
- 300 Artificial Intelligence, Digital Health, and Data Science
Authors
- Tangri, Navdeep, University of Manitoba Max Rady College of Medicine, Winnipeg, Manitoba, Canada
- Ferguson, Thomas W., University of Manitoba Max Rady College of Medicine, Winnipeg, Manitoba, Canada
- Bhanushali, Gautam K., Nephrology Associates, Oak Park, Illinois, United States
- Sanchez, Gabriel, Nephrology Associates, Oak Park, Illinois, United States
- Dague, Heather, Nephrology Associates, Oak Park, Illinois, United States
- Cipparrone, Nancy, Nephrology Associates, Oak Park, Illinois, United States
- Udani, Suneel M., Nephrology Associates, Oak Park, Illinois, United States
Background
Chronic kidney disease (CKD) increases cardiovascular events, kidney failure, mortality, and costs. Guideline-directed medical therapies (GDMT) exist for CKD and diabetes, but uptake remains low. The Klinrisk model, validated in over 4 million patients, predicts CKD progression from routine labs. We evaluated whether Klinrisk-based risk reporting and provider feedback increased GDMT uptake and albuminuria testing in a large US nephrology practice.
Methods
All patients in a large US nephrology practice (>100 providers, >50,000 patients) with available lab data for the Klinrisk model were included in this quality improvement initiative. Patients with >=25% five-year risk of progressive CKD (40% eGFR decline or kidney failure) were flagged as high risk in electronic medical records, and providers received quarterly reports on ACR testing and GDMT use benchmarked against practice rates. Use of renin-angiotensin-aldosterone-system inhibitors (RAAS), SGLT2 inhibitors, mineralocorticoid receptor antagonists (MRA), GLP-1 receptor agonists (GLP-1 RA), and urine ACR testing were compared between a baseline period (Nov 2023 - Oct 2024) and a follow-up period (Mar 2025 - Feb 2026), separated by a four-month implementation washout, using GEE-logistic models with patient-level clustering, with post-hoc tests for effect modification by baseline risk class.
Results
51,097 patients were included at baseline and 54,257 at follow-up; 33.2% and 31.6% were high-risk, respectively. Among high-risk patients, all GDMTs increased post-implementation: SGLT2i 30.7% to 37.9% (OR 1.38, 95% CI 1.33-1.43); GLP-1 RA 14.5% to 18.2% (OR 1.31, 1.25-1.38); MRA 13.5% to 15.9% (OR 1.22, 1.16-1.28); and RAAS 61.2% to 63.5% (OR 1.11, 1.07-1.15); all p<0.001. Urine ACR testing across all patients increased from 43.0% to 50.7% (OR 1.36, 1.33-1.39, p<0.001). Increases were greater in high-risk than low and intermediate-risk patients for SGLT2i (p=0.028), MRA (p=0.021), and RAAS (p=0.040), but similar across risk strata for GLP-1 RA.
Conclusion
Risk score reporting and provider feedback were associated with increased GDMT uptake and albuminuria testing, with greater uptake among patients classified as high-risk by the Klinrisk model. These findings suggest risk stratification can direct kidney-targeted therapies to those most likely to benefit and provide a scalable template for value-based CKD care.
Funding
- Commercial Support – Klinrisk Inc, AstraZeneca Inc.