Residual Kidney Function Decline and Mortality in Incident Hemodialysis Patients

Abstract

In patients with ESRD, residual kidney function (RKF) contributes to achievement of adequate solute clearance. However, few studies have examined RKF in patients on hemodialysis. In a longitudinal cohort of 6538 patients who started maintenance hemodialysis over a 4-year period (January 2007 through December 2010) and had available renal urea clearance (CL_urea) data at baseline and 1 year after hemodialysis initiation, we examined the association of annual change in renal CL_urea rate with subsequent survival. The median (interquartile range) baseline value and mean±SD annual change of CL_urea were 3.3 (1.9-5.0) and -1.1±2.8 ml/min per 1.73 m², respectively. Greater CL_urea rate 1 year after hemodialysis initiation associated with better survival. Furthermore, we found a gradient association between loss of RKF and all-cause mortality: changes in CL_urea rate of -6.0 and +3.0 ml/min per 1.73 m² per year associated with case mix-adjusted hazard ratios (95% confidence intervals) of 2.00 (1.55 to 2.59) and 0. 61 (0.50 to 0.74), respectively (reference: -1.5 ml/min per 1.73 m² per year). These associations remained robust against adjustment for laboratory variables and ultrafiltration rate and were consistent across strata of baseline CL_urea, age, sex, race, diabetes status, presence of congestive heart failure, and hemoglobin, serum albumin, and serum phosphorus levels. Sensitivity analyses using urine volume as another index of RKF yielded consistent associations. In conclusion, RKF decline during the first year of dialysis has a graded association with all-cause mortality among incident hemodialysis patients. The clinical benefits of RKF preservation strategies on mortality should be determined.

Keywords: chronic hemodialysis; end stage kidney disease; end-stage renal disease; hemodialysis; hemodialysis adequacy; renal function decline.

Figure 1.

Renal CL_urea and all-cause mortality risk in incident hemodialysis patients. The mortality risk associated with renal CL_urea at 1 year after initiating dialysis among 6538 incident hemodialysis patients (2007–2010) with three levels of adjustment. There was a significant trend toward lower mortality of higher renal CLurea (P for trend <0.001 across all models).

Figure 2.

Distributions and restricted cubic splines comparing the relationship of annual change in residual renal CL_urea with all-cause mortality among 6538 incident hemodialysis patients (2007–2010): (A) baseline renal CL_urea adjustment model, (B) case mix adjustment model, (C) fully adjusted model, and (D) additional adjustment for baseline ultrafiltration rate (UFr) and its annual change on the fully adjusted model. Annual changes in renal CL_urea were calculated subtracting values at year 1 (the fifth patient-quarter; the first 91 days of the second year of dialysis) from those at baseline (the first patient-quarter; the first 91 days of the first year of dialysis). Dashed and solid lines represent HR estimates and 95% CIs, respectively.

Figure 3.

Distributions and case mix–adjusted all–cause death HRs of annual change in renal CL_urea by using restricted cubic splines among 6538 incident hemodialysis patients (2007–2010) stratified by baseline CL_urea levels: (A) <1.5 ml/min per 1.73 m², (B) 1.5 to <3.0 ml/min per 1.73 m², (C) 3.0 to <6.0 ml/min per 1.73 m², and (D) ≥6.0 ml/min per 1.73 m². Annual changes in renal CL_urea were calculated subtracting values at year 1 (the fifth patient-quarter; the first 91 days of the second year of dialysis) from those at baseline (the first patient-quarter; the first 91 days of the first year of dialysis). Dashed and solid lines represent HR estimates and 95% CIs, respectively.

Figure 4.

Overall and subgroup analyses of associations between rapid decline in residual renal CL_urea >3 ml/min per 1.73 m² per year and all-cause mortality among 6538 incident hemodialysis patients (2007–2010) in the case mix adjustment model. Annual changes in renal CL_urea were calculated subtracting values at year 1 (the fifth patient-quarter; the first 91 days of the second year of dialysis) from those at baseline (the first patient-quarter; the first 91 days of the first year of dialysis). Points and bars represent HR estimates and 95% CIs, respectively. Alb, albumin; CHF, congestive heart failure; Hgb, hemoglobin; Phos, phosphorus.