Development and external validation of a machine learning-based predictive model for acute kidney injury in hospitalized children with idiopathic nephrotic syndrome.

Of the 3,390 patients with idiopathic nephrotic syndrome, 12.9% developed acute kidney injury.

It was then deployed as a web-based calculator for real-time risk assessment.

Key predictors included exposure to nephrotoxic antibiotics, exposure to cyclophosphamide, respiratory tract infection, urine H, and admission times.

In the acute kidney injury cohort, alanine transaminase, aspartate transaminase, and serum phosphate levels were primarily associated with the development of chronic kidney disease.