Prevalence of low glomerular filtration rate, proteinuria and associated risk factors in North India using Cockcroft-Gault and Modification of Diet in Renal Disease equation: an observational, cross-sectional study

Abstract

Background: Chronic kidney disease (CKD) is increasingly being recognized as an emerging public health problem in India. However, community based estimates of low glomerular filtration rate (GFR) and proteinuria are few. Validity of traditional serum creatinine based GFR estimating equations in South Asian subjects is also debatable. We intended to estimate and compare the prevalence of low GFR, proteinuria and associated risk factors in North India using Cockcroft-Gault (CG) and Modification of Diet In Renal Disease (MDRD) equation.

Methods: A community based, cross-sectional study involving multistage random cluster sampling was done in Delhi and its surrounding regions. Adults > or = 20 years were surveyed. CG and MDRD equations were used to estimate GFR (eGFR). Low GFR was defined as eGFR < 60 ml/min/1.73 m2. Proteinuria (> or = 1+) was assessed using visually read dipsticks. Odds ratios, crude and adjusted, were calculated to ascertain associations between renal impairment, proteinuria and risk factors.

Results: The study population had 3,155 males and 2,097 females. The mean age for low eGFR subjects was 54 years. The unstandardized prevalence of low eGFR was 13.3% by CG equation and 4.2% by MDRD equation. The prevalence estimates of MDRD equation were lower across gender and age groups when compared with CG equation estimates. There was a strong correlation but poor agreement between GFR estimates of two equations. The survey population had a 2.25% prevalence of proteinuria. In a multivariate logistic regression analysis; age above 60 years, female gender, low educational status, increased waist circumference, hypertension and diabetes were associated with low eGFR. Similar factors were also associated with proteinuria. Only 3.3% of subjects with renal impairment were aware of their disease.

Conclusion: The prevalence of low eGFR in North India is probably higher than previous estimates. There is a significant difference between GFR estimates derived from CG and MDRD equations. These equations may not be useful in epidemiological research. GFR estimating equations validated for South Asian populations are needed before reliable estimates of CKD prevalence can be obtained. Till then, primary prevention and management targeted at CKD risk factors must play a critical role in controlling rising CKD magnitude. Cost-benefit analysis of targeted screening programs is needed.

Figure 1

Median eGFR and prevalence of low eGR across age groups in study population. The median eGFR progressively decreased across age groups and was lower for females than males. Low eGFR was defined as eGFR < 60 ml/min/1.73 m². Elderly (aged above 60 years) and females had highest prevalence of low eGFR. eGFR, estimated glomerular filtration rate; CG/BSA, Cockcroft-Gault equation corrected for body surface area; MDRD, modification of diet in renal disease equation.

Figure 2

Bland-Altman plot of the eGFR measurements by CG and MDRD equations. Differences between eGFR measurements by CG/BSA and MDRD equation were plotted against the mean of two. The solid horizontal line represents the mean difference or the estimated bias. The MDRD equation had a positive bias as compared to CG/BSA equation, suggesting that MDRD equation overestimated GFR in the study population. The limits of agreement between two equations were broad (Males: -4.27 to 45.95 ml/min/1.73 m², Females: -11.88 to 28.82 ml/min/1.73 m²). The thin dotted line represents a linear fit of data point. There was an increase in variance of MDRD eGFR estimates across eGFR range. eGFR, estimated glomerular filtration rate; CG/BSA, Cockcroft-Gault equation corrected for body surface area; MDRD, modification of diet in renal disease equation.