Validation of the Klinrisk chronic kidney disease progression model in the FIDELITY population

Background:

• Chronic kidney disease (CKD) affects over 800 million globally and is often underdiagnosed.
• Early detection and intervention are crucial for slowing CKD progression.
• Klinrisk is a validated model using laboratory data to predict CKD progression risk.

Purpose of the Study:

• To externally validate the Klinrisk model's predictive accuracy for CKD progression.
• To assess Klinrisk's performance in a diverse patient population with CKD and type 2 diabetes within the FIDELITY trials.
• To investigate potential interactions between finerenone treatment and risk prediction.

Main Methods:

• The FIDELITY trial cohort, including patients with CKD and type 2 diabetes, was used for validation up to 4 years.
• Primary outcomes included a 40% or 57% decrease in estimated glomerular filtration rate (eGFR) or kidney failure.
• Model performance was evaluated using area under the receiver operating characteristic curve (AUC) and calibration plots.

Main Results:

• Klinrisk demonstrated strong predictive accuracy for the primary outcome at 2 years (AUC=0.81) and 4 years (AUC=0.86).
• The model showed appropriate calibration, with Brier scores of 0.067 (2 years) and 0.115 (4 years).
• No significant interaction was found between finerenone treatment and CKD progression risk (P=0.31).

Conclusions:

• The Klinrisk model is accurate and useful for identifying patients at high risk of CKD progression.
• Laboratory-based risk prediction facilitates early detection and management strategies for CKD.
• The findings support the use of Klinrisk in clinical practice for proactive CKD patient care.