Peer-reviewed article
Predicting Postoperative Outcomes in Pediatric Ureteroscopy Using Machine Learning and Explainable AI-EAU Endourology Vision-AI Study.
Carlotta Nedbal, Vineet Gauhar, Maria Florencia Frascheri, Shilpa Gite, Het Sevalia et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study uses machine learning and artificial intelligence to predict surgical complications after ureteroscopy (a kidney stone removal procedure) in children. Researchers analyzed data from 391 pediatric patients across 8 hospitals to develop algorithms that could identify which children are at higher risk of fever, bleeding, infection, stone fragments, or need for repeat surgery. The models achieved high accuracy rates, with some reaching over 90%. The study concludes that these AI tools could help doctors plan better individualized treatment, though real-world testing is still needed.
Key points
- 15 machine learning models were trained to predict 5 postoperative outcomes: fever, hematuria, sepsis, residual fragments, and reintervention
- Ensemble models performed best, with Gradient Boosting achieving 92.4% accuracy for fever prediction and XGBoost reaching 96.0% for sepsis
- Key predictors identified included preoperative infections, stone burden, operative duration, and anatomical anomalies
- Explainable AI techniques made the models transparent and aligned with medical reasoning for clinical use
- Authors note that prospective validation is needed before tools can be deployed clinically
Limitations
This is a retrospective study of historical data from 2017-2021, which cannot establish causation or real-world clinical utility. The study does not evaluate whether using these predictions actually improves patient outcomes or clinical decision-making in practice.
Abstract
AIM OF THE STUDY: This study aimed to evaluate the performance of machine learning (ML) algorithms integrated with explainable artificial intelligence (XAI) techniques in predicting outcomes following flexible ureteroscopy (fURSL) in children. By identifying significant preoperative predictors, the goal was to improve individualized surgical risk assessment and planning. MATERIALS AND METHODS: A retrospective analysis was conducted on 391 pediatric patients treated with fURSL for urolithiasis across 8 high-volume centers (2017-2021). Preoperative, intraoperative, and postoperative data were collected. 15 ML models were trained to predict five postoperative outcomes: fever, hematuria, sepsis, residual fragments (RF), and reintervention. A multitask artificial neural network (ANN) was also developed. Performance was evaluated using validation accuracy, confusion matrices, and classification reports. SHapley Additive exPlanations values and decision trees were used for model interpretability. RESULTS: Ensemble models outperformed others, with Gradient Boosting achieving 92.4% validation accuracy in predicting postoperative fever, Extra Trees achieving 91.1% for hematuria, and XGBoost reaching 96.0% for sepsis. Predictors included preoperative infections, stone burden, operative duration, and anatomical anomalies. For RF, Gradient Boost and Random Forest yielded strong results with up to 93.7% accuracy. Reintervention was best predicted by Random Forest, with RF as the strongest predictor. XAI techniques provided transparent, clinically interpretable models that aligned with medical reasoning. CONCLUSION: ML models demonstrated high accuracy in predicting adverse postoperative outcomes in pediatric ureteroscopy, with ensemble methods showing the best performance. Integration with XAI enhanced interpretability, supporting clinical decision-making. These findings underscore the potential of ML and XAI to inform personalized treatment strategies, though further prospective validation is needed to develop robust, generalizable predictive tools.