# Predicting vesicoureteral reflux outcomes using artificial intelligence: A critical appraisal using APPRAISE-AI

## TL;DR

AI shows promise in predicting outcomes for vesicoureteral reflux in children but needs better quality and collaboration to be widely adopted.

## Contribution

A critical appraisal of AI applications for VUR outcomes using the APPRAISE-AI framework, highlighting quality gaps and potential.

## Key findings

- AI models can predict VUR grading, UTI recurrence, and treatment outcomes but often lack robustness.
- Most studies used neural networks and tree-based algorithms with moderate quality ratings.
- Standardized reporting and multi-institutional collaboration are needed to improve AI reliability in VUR care.

## Abstract

Vesicoureteral reflux (VUR) is a common congenital urinary tract anomaly in children, associated with recurrent urinary tract infections (UTIs) and long-term sequelae such as renal scarring and chronic kidney disease. Artificial intelligence (AI) has recently emerged as a promising approach for improving VUR diagnosis, prognosis, and treatment stratification. This narrative review identified studies from the AI-PEDURO repository, a living database of AI applications in pediatric urology, most recently updated in June 2024. Eligible studies employed machine learning methods to predict clinically relevant outcomes of VUR or UTI. Seventeen studies met the inclusion criteria, with common applications including VUR grading from voiding cystourethrograms, prediction of UTI recurrence, spontaneous resolution of VUR, and outcomes following antibiotic prophylaxis or endoscopic injection therapy. Neural networks, tree-based algorithms, and support vector machines were the most frequently used approaches. Using the APPRAISE-AI tool, the median overall study quality was moderate, with strengths in clinical relevance and reporting quality, but persistent weaknesses in methodological conduct, robustness, and reproducibility. AI applications in VUR demonstrate strong potential to enhance diagnostic accuracy, personalize treatment, and predict outcomes; however, most published models remain of low to moderate quality. Adoption of standardized reporting frameworks and multi-institutional collaboration will be essential for improving rigour and accelerating clinical translation.

Vesicoureteral reflux (VUR) is a condition in children where urine flows backwards from the bladder toward the kidneys. This can increase the risk of urinary tract infections and, in severe cases, lead to kidney damage later in life. Doctors often face challenges in deciding which children need treatment and how best to monitor the condition. Recently, artificial intelligence (AI) has been explored as a tool to improve diagnosis and guide care. In this review, we examined all available studies that applied AI to VUR, including its use in interpreting imaging, predicting which children might benefit from specific treatments, and identifying those at higher risk for complications. We found that while many studies show promising results, most were small in size, not tested across different hospitals, and often lacked the detail needed for other researchers to reproduce the work. Despite these challenges, AI has the potential to make VUR diagnosis more consistent and treatment more personalized. Future research should focus on larger, collaborative studies and clearer reporting to determine how AI can best support children, families, and clinicians in managing this condition.