08Sep 2023
Predicting obstruction risk using common ultrasonography parameters in paediatric hydronephrosis with machine learning

Predicting obstruction risk using common ultrasonography parameters in paediatric hydronephrosis with machine learning

A recent study enhanced the prediction of renal obstruction risk during diuretic renography in pediatric patients using routine ultrasound (US) findings and machine learning. The study examined 304 patients with isolated hydronephrosis who underwent diuretic renograms following renal US. They developed an AI model, Evaluation of Renogram Obstruction' (AERO), outperforming the Society for Fetal Urology (SFU) grade in risk classification. AERO identified key predictors such as age, anteroposterior diameter, and SFU grade. The findings offer the potential to reduce unnecessary renograms in pediatric patients with isolated hydronephrosis safely.

  • #pediatrics

Like

Save

Share