Individual patient variability with the application of the kidney failure risk equation in advanced chronic kidney disease

Abstract

The Kidney Failure Risk Equation (KFRE) predicts the need for dialysis or transplantation using age, sex, estimated glomerular filtration rate (eGFR), and urine albumin to creatinine ratio (ACR). The eGFR and ACR have known biological and analytical variability. We examined the effect of biological and analytical variability of eGFR and ACR on the 2-year KFRE predicted kidney failure probabilities using single measure and the average of repeat measures of simulated eGFR and ACR. Previously reported values for coefficient of variation (CV) for ACR and eGFR were used to calculate day to day variability. Variation was also examined with outpatient laboratory data from patients with an eGFR between 15 and 50 mL/min/1.72 m2. A web application was developed to calculate and model day to day variation in risk. The biological and analytical variability related to ACR and eGFR lead to variation in the predicted probability of kidney failure. A male patient age 50, ACR 30 mg/mmol and eGFR 25, had a day to day variation in risk of 7% (KFRE point estimate: 17%, variability range 14% to 21%). The addition of inter laboratory variation due to different instrumentation increased the variability to 9% (KFRE point estimate 17%, variability range 13% to 22%). Averaging of repeated measures of eGFR and ACR significantly decreased the variability (KFRE point estimate 17%, variability range 15% to 19%). These findings were consistent when using outpatient laboratory data which showed that most patients had a KFRE 2-year risk variability of ≤ 5% (79% of patients). Approximately 13% of patients had variability from 5-10% and 8% had variability > 10%. The mean age (SD) of this cohort was 64 (15) years, 36% were females, the mean (SD) eGFR was 32 (10) ml/min/1.73m2 and median (IQR) ACR was 22.7 (110). Biological and analytical variation intrinsic to the eGFR and ACR may lead to a substantial degree of variability that decreases with repeat measures. Use of a web application may help physicians and patients understand individual patient's risk variability and communicate risk (https://mccudden.shinyapps.io/kfre_app/). The web application allows the user to alter age, gender, eGFR, ACR, CV (for both eGFR and ACR) as well as units of measurements for ACR (g/mol versus mg/g).

Fig 1

A. Predicted KFRE variation with eGFR. The black line represents the 2-year KFRE estimate for a 50-year old male with a fixed ACR of 30 g/mol. Upper and lower bounds (dotted lines) represent the 95% confidence interval for KFRE risk based on a biological variation in eGFR of 6.6%. B. Predicted KFRE variation with eGFR and inter-laboratory variation. Upper and lower bounds (dotted lines) represent the 95% confidence interval for KFRE risk based on a biological variation in eGFR of 6.6% combined with a reported inter-laboratory variation of 4.3%.

Fig 2

A Predicted KFRE variation with ACR concentration. The black line represents the 2-year KFRE estimate for a 50-year old male with a fixed eGFR of 30 mL/min/1.72 m². Upper and lower bounds (dotted lines) represent the 95% confidence interval for the 2-year KFRE risk based on published ACR-concentration variation from 11.3%. B. Predicted KFRE variation with ACR concentration in combination with inter-laboratory variation. Upper and lower bounds (dotted lines) represent the 95% confidence interval for KFRE risk based published ACR variation combined with a reported inter-laboratory variation of 9.6%.

Fig 3. Comparison of predicted risk variability using a single laboratory, multiple laboratory with different methods, or averaging serial values.

In all panels, the black lines represent the 2-year KFRE estimate for a 50-year old male at fixed ACRs of 3, 30, and 300 g/mol and the upper and lower dotted lines represent 95% confidence intervals. Left Panels: Predicted KFRE with combined variation in eGFR and ACR analyzed by a single method. Center Panels: Predicted KFRE with combined variation in eGFR, ACR, and laboratory method. Variation includes combined inter-laboratory variation. Right Panels: Predicted reduction in KFRE variation by using averages of serial eGFR and ACR measurement. Inter-laboratory variation was excluded to reflect use of a single laboratory.

Fig 4. Variation in KFRE using serial eGFR and ACR from patients.

A. Variation in 2-year KFRE with eGFR in patients. Variation was determined by calculating the difference in 2-year KFRE using serial eGFR and ACR values from a given patient. Each point represents the difference in KFRE calculated from two pairs of eGFR and ACR values for a single patient within a 3-month time period. B. The same patient data as panel A, except showing variation in 2-year KFRE with ACR on the x-axis.