Predictive models of chronic kidney disease progression in pediatric patients

We read with great interest the study conducted by Ng et  al.,1 aimed to develop a suite of predictive models for time to kidney replacement therapy in children with chronic kidney disease (CKD). In this well-designed study, Ng et al.1 used robust data from the Chronic Kidney Disease in Children study2 and a combination of sophisticated strategies, incl uding both conventional statistics and machine learning methods. The authors developed 6 models of CKD progression in pediatric patients. In external validation, the elementary model, which includes the glomerular filtration rate, urine protein-creatinine ratio, and the CKD cause, showed excellent d iscrimination and calibration.
Source: Kidney International - Category: Urology & Nephrology Authors: Tags: Letter to the Editor Source Type: research