Publications
Publications
- April 2024
- Journal of Pediatric Urology
A Machine Learning Algorithm Predicting Risk of Dilating VUR among Infants with Hydronephrosis Using UTD Classification
By: Hsin-Hsiao Scott Wang, Michael Lingzhi Li, Dylan Cahill, John Panagides, Tanya Logvinenko, Jeanne Chow and Caleb Nelson
Abstract
Backgrounds: Urinary Tract Dilation (UTD) classification has been designed to be a more objective grading system to evaluate antenatal and post-natal UTD. Due to unclear association between UTD classifications to specific anomalies such as vesico-ureteral reflux (VUR), management recommendations tend to be subjective.
Objective: We sought to develop a model to reliably predict VUR from early post-natal ultrasound.
Study Design: Radiology records from single institution were reviewed to identify infants aged 0-90 days undergoing early ultrasound for antenatal UTD. Medical records were reviewed to confirm diagnosis of VUR. Primary outcome defined as dilating (≥Gr3) VUR. Exclusion criteria include major congenital urologic anomalies (bilateral renal agenesis, horseshoe kidney, cross fused ectopia, exstrophy) as well as patients without VCUG. Data were split into training/testing sets by 4:1 ratio. Machine learning (ML) algorithm hyperparameters were tuned by the validation set.
Results: In total, 280 patients (540 renal units) were included in the study (73 % male). Median (IQR) age at ultrasound was 27 (18–38) days. 66 renal units were found to have ≥ grade 3 VUR. The final model included gender, ureteral dilation, parenchymal appearance, parenchymal thickness, central calyceal dilation. The model predicted VUR with AUC at 0.81(0.73–0.88) on out-of-sample testing data. Model is shown in the figure.
Discussion: We developed a ML model that can predict dilating VUR among patients with hydronephrosis in early ultrasound. The study is limited by the retrospective and single institutional nature of data source. This is one of the first studies demonstrating high performance for future diagnosis prediction in early hydronephrosis cohort.
Conclusions: By predicting dilating VUR, our predictive model using machine learning algorithm provides promising performance to facilitate individualized management of children with prenatal hydronephrosis, and identify those most likely to benefit from VCUG. This would allow more selective use of this test, increasing the yield while also minimizing overutilization.
Objective: We sought to develop a model to reliably predict VUR from early post-natal ultrasound.
Study Design: Radiology records from single institution were reviewed to identify infants aged 0-90 days undergoing early ultrasound for antenatal UTD. Medical records were reviewed to confirm diagnosis of VUR. Primary outcome defined as dilating (≥Gr3) VUR. Exclusion criteria include major congenital urologic anomalies (bilateral renal agenesis, horseshoe kidney, cross fused ectopia, exstrophy) as well as patients without VCUG. Data were split into training/testing sets by 4:1 ratio. Machine learning (ML) algorithm hyperparameters were tuned by the validation set.
Results: In total, 280 patients (540 renal units) were included in the study (73 % male). Median (IQR) age at ultrasound was 27 (18–38) days. 66 renal units were found to have ≥ grade 3 VUR. The final model included gender, ureteral dilation, parenchymal appearance, parenchymal thickness, central calyceal dilation. The model predicted VUR with AUC at 0.81(0.73–0.88) on out-of-sample testing data. Model is shown in the figure.
Discussion: We developed a ML model that can predict dilating VUR among patients with hydronephrosis in early ultrasound. The study is limited by the retrospective and single institutional nature of data source. This is one of the first studies demonstrating high performance for future diagnosis prediction in early hydronephrosis cohort.
Conclusions: By predicting dilating VUR, our predictive model using machine learning algorithm provides promising performance to facilitate individualized management of children with prenatal hydronephrosis, and identify those most likely to benefit from VCUG. This would allow more selective use of this test, increasing the yield while also minimizing overutilization.
Keywords
Citation
Wang, Hsin-Hsiao Scott, Michael Lingzhi Li, Dylan Cahill, John Panagides, Tanya Logvinenko, Jeanne Chow, and Caleb Nelson. "A Machine Learning Algorithm Predicting Risk of Dilating VUR among Infants with Hydronephrosis Using UTD Classification." Journal of Pediatric Urology 20, no. 2 (April 2024): 271–278.