Abstract: TH-PO1081
Prognostic Enrichment Using the Klinrisk Model: Insights from Landmark Kidney Disease Clinical Trials
Session Information
- CKD: Therapeutic Advances
October 24, 2024 | Location: Exhibit Hall, Convention Center
Abstract Time: 10:00 AM - 12:00 PM
Category: CKD (Non-Dialysis)
- 2302 CKD (Non-Dialysis): Clinical, Outcomes, and Trials
Authors
- Neuen, Brendon Lange, Royal North Shore Hospital, St Leonards, New South Wales, Australia
- Ferguson, Thomas W., University of Manitoba Department of Internal Medicine, Winnipeg, Manitoba, Canada
- Jardine, Meg, NHMRC Clinical Trials Centre, Camperdown, New South Wales, Australia
- Neal, Bruce, University of New South Wales Medicine & Health, Sydney, New South Wales, Australia
- Perkovic, Vlado, University of New South Wales, Sydney, New South Wales, Australia
- Bakris, George L., University of Chicago Pritzker School of Medicine, Chicago, Illinois, United States
- Agarwal, Rajiv, Indiana University School of Medicine, Indianapolis, Indiana, United States
- Schloemer, Patrick, Bayer AG, Leverkusen, Nordrhein-Westfalen, Germany
- Farjat, Alfredo E., Bayer AG, Leverkusen, Nordrhein-Westfalen, Germany
- Jongs, Niels, Universitair Medisch Centrum Groningen, Groningen, Groningen, Netherlands
- Heerspink, Hiddo Jan L., Universitair Medisch Centrum Groningen, Groningen, Groningen, Netherlands
- Wheeler, David C., University College London, London, United Kingdom
- Chertow, Glenn M., Stanford University School of Medicine, Stanford, California, United States
- Tangri, Navdeep, University of Manitoba Department of Internal Medicine, Winnipeg, Manitoba, Canada
Background
Patients with macroalbuminuria (KDIGO stage A3) experience high rates of CKD progression and cardiovascular events. Identifying patients with lesser degrees of albuminuria who also experience high kidney and cardiovascular event rates could enhance access to, and improve efficiency of, CKD-focused clinical trials.
Methods
We applied the Klinrisk model, a validated machine learning model incorporating routinely collected laboratory data, to patients with uACR ≥30 mg/g who were evaluated for participation in the CANVAS Program, CREDENCE, FIDELIO, FIGARO and DAPA-CKD trials but who failed screening due to albuminuria levels below the randomization threshold. We examined 2-year incidence of CKD progression (40% decline in eGFR or kidney failure) in different uACR categories, stratified by Klinrisk score (low, intermediate, and high risk indicating <2%, 2–10%, and >10% 2-year risk of CKD progression, respectively). We subsequently reviewed screen failure data from the CREDENCE, FIDELIO and DAPA-CKD trials to determine what proportion of individuals with uACR 30–300 mg/g could have been enrolled using a Klinrisk-informed approach.
Results
Across the included trials, the incidence of CKD progression among participants with uACR 30–300mg/g (KDIGO stage A2) was highly variable across risk categories, ranging from 1.1 to 9.7% in those classified as low vs. high risk by the Klinrisk model, respectively. Compared to participants with uACR 300-1000 mg/g, event rates were similar or higher for participants with uACR 30-300mg/g classified as high-risk based on the Klinrisk model. 24 to 36% of participants who screen failed due to A2 albuminuria in the CREDENCE, FIDELIO and DAPA-CKD trials were classified as high risk with the Klinrisk model.
Conclusion
Extending recruitment to patients with uACR 30-300mg/g at high-risk based on the Klinrisk algorithm could facilitate recruitment for CKD progression trials without affecting event rates. Prognostic enrichment using Klinrisk has the potential to accelerate drug development in CKD by enabling more inclusive and efficient clinical trials.