Random survival forest models predict renal complications in antenatal hydronephrosis

David A. Ostrowski^1,2, Joseph R. Logan^3,4,5, Austin Thompson⁶, Reiley Broms³, Thomas Syphan⁶, Maria Antony³, Mandy Rickard⁷, Lauren Erdman^8,9, Dennis Head¹⁰, Jessica H. Hannick⁶, Lynn L. Woo⁶, Frederick D. Grant¹¹, Neeta D’Souza³, Satish E. Viswanath¹², Chris A. Flask¹³, Armando J. Lorenzo⁷, Yong Fan¹⁴, Gregory E. Tasian^2,3,5, John K. Weaver^6,*
1 Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
2 Division of Urology, Department of Surgery, University of Pennsylvania Health System, Philadelphia, PA, USA
3 Division of Urology, Department of Surgery, Children’s Hospital of Philadelphia, Philadelphia, PA, USA
4 Translational Research Informatics Group, Children’s Hospital of Philadelphia, Philadelphia, PA, USA
5 Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
6 Center for Pediatric Urology, Glickman Urological and Kidney Institute, Cleveland Clinic, Cleveland, OH, USA
7 Division of Urology, Hospital for Sick Children, Toronto, ON, Canada
8 James M. Anderson Center for Health Systems Excellence, Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, USA
9 Department of Pediatrics, University of Cincinnati School of Medicine, Cincinnati, OH, USA
10 Department of Urology, Northeast Ohio Medical University, Rootstown, OH, USA
11 Department of Radiology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA
12 Department of Pediatrics and Biomedical Engineering, Emory University, Atlanta, GA, USA
13 Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA
14 Department of Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA
* Corresponding Author: John K. Weaver. Email: email , email
(This article belongs to the Special Issue: Advancing the Diagnosis and Treatment of Urological Diseases through Big Data)

Canadian Journal of Urology https://doi.org/10.32604/cju.2026.077246

Received 05 December 2025; Accepted 31 March 2026; Published online 03 June 2026

Download PDF

Abstract

Objectives: This study aims to build machine learning models to analyze Technetium-99m mercaptoacetyltriglycine (MAG3) renal scans and clinical variables from patients with antenatal hydronephrosis (ANH) with concern for ureteropelvic junction obstruction (UPJO) and equivocal initial MAG3 renal scans to predict the risk of renal complication development. Methods: A retrospective cohort of patients under 1-year-old with ANH concerning for UPJO with an equivocal MAG3 renal scan evaluated at our institution from January 2009 to June 2021 was identified. Equivocal renal scans were defined as studies where the affected kidney demonstrated split function greater than 39%, and subsequent clinical recommendation was continued surveillance instead of surgery. Random survival forest models were c onstructed to predict the risk of renal complications (decreased function, increased parenchymal thinning, worsening hydronephrosis) using clinical variables (Clinical Model), or numerical features extracted from MAG3 renal scans (Imaging Model), or clinical and numeric renal scan features (Ensemble Model). Results: One-hundred fifty-two patients were included; 62 patients developed a renal complication, and 90 did not develop a renal complication with a minimum of 3-year follow-up. The Imaging Model (C-index 0.74; 95% CI: 0.68–0.79) and the Clinical Model (C-index 0.70; 95% CI: 0.66–0.75) performed similarly, while the Ensemble Model (C-index 0.76; 95% CI: 0.75–0.86) demonstrated improved performance compared to either individually. Differential function per unit volume of the affected kidney was the most important driver of the Clinical Model’s predictions. All models identified high-risk patients at significantly higher risk of renal complications on Kaplan-Meier log-rank analysis (p < 0.0001). Conclusion: Random survival forest models using clinical and/or renal scan features may improve the prediction of renal complication risk in patients with ANH, with concern for UPJO and an equivocal initial MAG3 renal scan.