Determining Glomerular Filtration Rate in Homozygous Sickle Cell Disease: Utility of Serum Creatinine Based Estimating Equations

Background: Various estimating equations have been developed to estimate glomerular filtration rate (GFR) for use in clinical practice. However, the unique renal physiological and pathological processes that occur in sickle cell disease (SCD) may invalidate these estimates in this patient population. This study aims to compare GFR estimated using common existing GFR predictive equations to actual measured GFR in persons with homozygous SCD. If the existing equations perform poorly, we propose to develop a new estimating equation for use in persons with SCD. Methods: 98 patients with the homozygous SS disease (55 females: 43 males; mean age 34 +/- 2.3 years) had serum measurements of creatinine, as well as had GFR measured using Tc-99m-DTPA nuclear renal scan. GFR was estimated using the Modification of Diet in Renal Disease (MDRD), Cockcroft-Gault (CG), and the serum creatinine based CKD-EPI equations. The Bland-Altman limit of agreement method was used to determine agreement between measured and estimated GFR values. A SCD-specific estimating equation for GFR (JSCCS-GFR equation) was generated by means of multiple regression via backward elimination. Results: The mean measured GFR +/- SD was 94.9 +/- 27.4 mls/min/1.73 m(2) BSA, with a range of 6.4-159.0 mls/min/1.73 m(2). The MDRD and CG equations both overestimated GFR, with the agreement worsening with higher GFR values. The serum creatinine based CKD-EPI equation performed relatively well, but with a systematic bias of about 45 mls/min. The new equation developed resulted in a better fit to our sickle cell disease data than the MDRD equation. Conclusion: Current estimating equations, other than the CKD-EPI equation, do not perform very accurately in persons with homozygous SS disease. A fairly accurate estimating equation, suitable for persons with GFR >60 mls/min/1.73 m(2) has been developed from our dataset and validated within a simulated dataset.