Journal of endourology
June 23, 2026 · via Europe PMC
Development of an Interpretable Machine Learning Model for Predicting Clavien-Dindo Grade ≥2 Complications after Unilateral Minimally Invasive Pyeloplasty in UPJO: A Retrospective Cohort Study.
Pan H, Wang R, Jiang M, +5 more, He D.
AI summary — for doctors, generated from the abstract only
A LightGBM machine learning model using seven preoperative features was the best of ten algorithms for predicting Clavien-Dindo grade ≥2 complications after pediatric minimally invasive pyeloplasty.
What was studied
A retrospective study of 533 children undergoing unilateral minimally invasive pyeloplasty for ureteropelvic junction obstruction (2020-2024) developed and compared ten machine learning models using preoperative clinical and ultrasound parameters, and built an online risk calculator.
Key findings
- 127 children (23.8%) developed Clavien-Dindo grade ≥2 complications
- Seven predictors were selected: age, affected-to-unaffected kidney volume ratio, increased calyx diameter, neutrophil count, cystatin C, anteroposterior pelvic diameter and WBC count
- LightGBM showed superior performance by AUC and decision curve analysis; specific AUC values not fully captured in the abstract
- SHAP analysis was used for interpretability and an online calculator was developed
Clinical relevance
The model may eventually help with postoperative risk stratification, but it is derived from a single retrospective dataset and needs external validation before clinical use.
Who should care
Limitations
Retrospective design with internal train/test splitting only; no external validation is reported and performance metrics are not given in the abstract.
An interpretable ML tool shows potential for predicting pyeloplasty complications in children, pending validation.
This is an AI-generated summary of the published abstract, not a clinical recommendation. It may not reflect the full text or subsequent updates — verify against the original source before acting on it.
Abstract
Background
Minimally invasive pyeloplasty (MIP), encompassing both conventional laparoscopy and robot-assisted approaches, has become the primary treatment for pediatric ureteropelvic junction obstruction (UPJO). However, these procedures remain associated with considerable postoperative complications that affect surgical outcomes. This study employed the Clavien-Dindo classification system and interpretable machine learning (ML) algorithms to predict Clavien-Dindo grade ≥2 complications using strictly preoperative clinical and ultrasound parameters. Furthermore, an online calculator was developed to assist clinicians in real-time risk stratification.
Methods
A retrospective analysis was conducted on 533 pediatric UPJO patients admitted between January 2020 and December 2024. Feature selection was performed using recursive feature elimination. Ten ML algorithms were developed and compared to identify the optimal predictive model.
Results
A total of 533 children undergoing unilateral minimally invasive pyeloplasty were included, among whom 127 (23.8%) developed Clavien-Dindo grade ≥2 complications. Seven preoperative clinical and imaging features were prioritized for model construction: age, affected-to-unaffected kidney volume ratio, increased calyx diameters, blood neutrophil count, cystatin C, anteroposterior pelvic diameter, and white blood cell (WBC) count. Based on comparisons of the area under the receiver operating characteristic curve and decision curve analysis in training and testing sets, the light gradient boosting machine (LightGBM) model demonstrated superior performance. SHapley Additive exPlanations (SHAP) analysis enhanced interpretability, and an online calculator was developed to improve clinical applicability.
Conclusion
The LightGBM model can effectively predict the occurrence of Clavien-Dindo grade ≥2 complications following unilateral MIP. It may assist clinicians in evaluating postoperative risks and developing personalized follow-up strategies for early intervention.
DOI
10.1177/08927790261454507
PMID
42333902
Research metadata (titles, abstracts, authors, publication dates) is sourced from Europe PMC, which aggregates content from PubMed/MEDLINE, PubMed Central, and other providers under the U.S. National Library of Medicine (NLM/NCBI). NLM does not claim copyright on abstracts; the original journal publishers or authors may hold rights to the full articles. AI-generated summaries are derived only from the abstract, never the full text, and are always labeled as AI-generated.
Want more like this?
Browse more from the feed. A free account unlocks the full feed, saving and communities.
Back to the research feed