An independent validation of the kidney failure risk equation in an Asian population

Abstract

Predicting the risk of end-stage renal disease (ESRD) progression facilitates appropriate nephrology care of patients with chronic kidney disease (CKD). Previously, the kidney failure risk equations (KFREs) were developed and validated in several cohorts. The purpose of this study is to validate the KFREs in a Korean population and to recalibrate the equations. A total of 38,905 adult patients, including 13,244 patients with CKD stages G3-G5, who were referred to nephrology were recruited. Using the original KFREs (4-, 6- and 8-variable equations) and recalibration equations, we predicted the risk of 2- and 5-year ESRD progression. All analyses were conducted in CKD stages G3-G5 patients as well as the total population. In CKD stages G3-G5 patients, All the original 4-, 6- and 8-variable equations showed excellent areas under the receiver operating characteristic curve of 0.87 and 0.83 for the 2- and 5-year risk of ESRD, respectively. The results of net reclassification improvement, integrated discrimination index and Brier score showed that recalibration improved the prediction models in some cases. The original KFREs showed high discrimination in both CKD stages G3-G5 patients and the total population referred to nephrology in this large Korean cohort. KFREs can be implemented in Korean health systems and can guide nephrology referrals and other CKD-related treatment decisions.

Figure 1

Diagram showing the study population.

Figure 2

Time-dependent ROC and calibration plots of 2- and 5-year risk prediction models in CKD stages G3-G5 patients. (a) 2-year risk prediction. (b) 5-year risk prediction.

Figure 3

Time-dependent ROC and calibration plots of 2- and 5-year risk prediction models in the total population. (a) 2-year risk prediction. (b) 5-year risk prediction.