Creatinine-based GFR-estimating equations in children with overweight and obesity

Abstract

Background: With the increasing prevalence of childhood obesity and related development of chronic kidney disease (CKD), there is a critical need to understand how best to assess kidney function in children with obesity. Since serum creatinine (SCr) is recommended as marker of first choice for GFR estimation, we evaluated and compared creatinine-based GFR equations in children with overweight and obesity.

Methods: Six hundred children with overweight and obesity (53.5% female; mean age 12.20 ± 3.28 years; mean BMI z-score 3.31 ± 0.75) were included from the Centre for Overweight Adolescent and Children's Healthcare (COACH).

Results: Serum creatinine (SCr), normalized using Q-age polynomials obtained from reference values, results in median and mean SCr/Q value close to "1" for all age groups, and 96.5% of the children have a SCr/Q within the reference band [0.67-1.33], corresponding to the 2.5th and 97.5th percentile. eGFR CKiD (bedside Schwartz equation) and Schwartz-Lyon decreased with age, whereas eGFR EKFC and modified CKD-EPI40 showed no age-dependency, but the distribution of eGFR values was not symmetrical. eGFR CKiD under 25 (CKiDU25) demonstrated no age-dependency but major sex differences were observed. eGFR FAS age, FAS height, and adjusted-creatinine revised Lund-Malmö (LMR18) showed a relatively symmetrical distribution and no age-dependency.

Conclusions: Serum creatinine (SCr) values of children with overweight and obesity are mostly within the reference range for children. Normalization of SCr using reference Q-age polynomials works very well in this cohort. After evaluation of the different equations, we suggest that FAS age, FAS height, and LMR18 are the preferred creatinine-based GFR-estimating equations in children with overweight and obesity.

Clinicaltrial: gov; Registration Number: NCT02091544. A higher resolution version of the Graphical abstract is available as Supplementary information.

Keywords: Childhood obesity; Creatinine; Pediatrics; eGFR.

Fig. 1

Serum creatinine (SCr, in mg/dL) against age for males and females. The band represents the reference interval for SCr based on the Hoste polynomials [20]

Fig. 2

SCr/Q against age with the reference band [0.67–1.33] as described by Pottel et al. [21]. 96.5% of the children have a SCr/Q within this reference band

Fig. 3

Histogram with normal density function overlaid for normalized or rescaled SCr. The vertical reference lines correspond with the lower and upper limits of 0.67 and 1.33 (left). Linear quantile regression lines for percentiles 2.5, 50, and 97.5 are shown (right)

Fig. 4

Histograms and linear quantile regression of eGFR FAS age (a); FAS height (b); EKFC (c); CKiD (bedside Schwartz) (d); Schwartz-Lyon (e); CKiDU25 (f); LMR18 (g); CKD-EPI40 (h). The vertical lines in the histograms correspond to 80.7 (lower limit), 107.3 (median), 133.9 (= symmetrical to 80.7), and 160.1 (upper limit) corresponding to the FAS-eGFR limits calculated from SCr/Q = 0.67, 1, and 1.33 as defined by Pottel et al. [21]

Fig. 4

Histograms and linear quantile regression of eGFR FAS age (a); FAS height (b); EKFC (c); CKiD (bedside Schwartz) (d); Schwartz-Lyon (e); CKiDU25 (f); LMR18 (g); CKD-EPI40 (h). The vertical lines in the histograms correspond to 80.7 (lower limit), 107.3 (median), 133.9 (= symmetrical to 80.7), and 160.1 (upper limit) corresponding to the FAS-eGFR limits calculated from SCr/Q = 0.67, 1, and 1.33 as defined by Pottel et al. [21]