Ultrasonographic length of morphologically-normal kidneys in children presented to a premier tertiary healthcare setting of Sri Lanka

Background: Accurate prediction of reference ranges of renal lengths facilitates clinical decision making. Currently a single renal-length-reference chart is used for both kidneys, which is solely based on the age of the child without adjusting for anthropometrics. Objective of the study is to assess the length of morphologically-normal kidneys ultrasonically and to build models to predict the renal lengths of children presenting at the Radiology Department of Lady Ridgeway Hospital for Children. Methods: A descriptive cross sectional study was done among 424 children with 233 males and 191 females at the study setting. Study population included children undergoing abdominal ultrasound scans for indications not related to renal disease. Children with a family history of renal diseases or with morphologically-abnormal kidneys were excluded. Bipolar-lengths of kidneys, gender and anthropometrics were documented. Having tested for assumptions, Wilcoxon-signed rank test, Mann-Whitney U test and multiple linear regression were used. Results: The mean (SD) bipor-length of right and left kidneys were 6.83 (1.43) and 7.05 (1.36) respectively (p < 0.001). Age, height and weight were significantly correlated with the renal lengths (p < 0.05). Until 16 months, there was a significant difference between the renal lengths between males and females (P < 0.05). Yet the association with gender was not significant from 17 months and in overall. Until 16 months, the best linear-regression equation (p < 0.001) for the left kidney was; 3.827 + 0.019(length in centimeters) + 0.141(weight in kilograms) - 0.023(age in months) - 0.347(for male sex). For the right kidney, it was; 3.888 + 0.020(length or height) + 0.121(weight) - 0.037(age) - 0.372 (for male sex). The respective R squares were 59.2 and 53.5% with VIF (Variance-Inflation-Factor) ranging from 1.06 to 2.08. From 17 months, best equation for left kidney (p < 0.001) was; 5.651 + 0.022(age) + 0.01(BMI). For right kidney it was; 5.336 + 0.022(age) + 0.012(BMI). The R squares were 62.5 and 66.1% with VIF being 1. Conclusions: The established models explain more variability for children above 17 months. Both renal lengths are affected significant by the body's' anthropometric parameters. For each kidney, separate normograms of renal lengths which are local-context-specific must be prepared. Further research must be promoted.