EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Development of a machine learning model for predicting renal damage in children with closed spinal dysraphism

Yu He, Wan-Liang Guo, Ming-Chang Zhang

BMC Pediatrics · 2025

DOI: 10.1186/s12887-025-05936-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BMC Pediatrics, 2025. Verfasst von Yu He und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China. Hauptthemen laut MEDLINE: Machine Learning, Spinal Dysraphism, Kidney Diseases. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Renal damage in closed spinal dysraphism (CSD), primarily linked to neurogenic bladder dysfunction, significantly impacts long-term patient outcomes by increasing the risk of chronic kidney disease. Identifying patients at highest risk for renal damage is essential for implementing early interventions, improving bladder management strategies, and preserving renal function. This study aims to develop an effective machine learning model to predict renal damage in children with CSD. METHODS: This retrospective study included 110 children with CSD. We developed four machine learning models (logistic regression, support vector machine, decision tree, and extreme gradient boosting [XGBoost]), and compared their predictive performances. The area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis were used to evaluate predictive performance. The Shapley additive explanations (SHAP) algorithm and Local Interpretable Model-Agnostic Explanations (LIME) were used to interpret the optimal model. RESULTS: The XGBoost model showed the best predictive performance (AUC = 0.957) among the four machine learning models. Through the SHAP analysis, abnormal radiological lower urinary tract findings, female sex, and high-grade vesicoureteral reflux were identified as the three most influential features in predicting renal damage. CONCLUSION: Our study effectively developed a model that accurately predicted renal damage in children with CSD based on the XGBoost algorithm, demonstrating its potential to achieve good predictive performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningSpinal DysraphismKidney DiseasesHumansFemaleRetrospective StudiesMaleChild, PreschoolChildInfantDecision TreesVesico-Ureteral RefluxROC CurveLogistic ModelsUrinary Bladder, NeurogenicPredictive Value of TestsSupport Vector Machine

Stichwörter der Autor:innen

Closed spinal dysraphismExtreme gradient boostingMachine learningRenal damage

Autor:innen und Institutionen

  • Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China.
  • Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China. gwlsuzhou@163.com.
  • Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China. 972424678@qq.com.

Zitieren

APA

He, Y., Guo, W. L., & Zhang, M. C. (2025). Development of a machine learning model for predicting renal damage in children with closed spinal dysraphism. BMC Pediatrics. https://doi.org/10.1186/s12887-025-05936-7

Vancouver

He Y, Guo WL, Zhang MC. Development of a machine learning model for predicting renal damage in children with closed spinal dysraphism. BMC Pediatrics. 2025. doi:10.1186/s12887-025-05936-7

BibTeX
@article{He2025,
  author = {He, Yu and Guo, Wan-Liang and Zhang, Ming-Chang},
  title = {Development of a machine learning model for predicting renal damage in children with closed spinal dysraphism},
  journal = {BMC Pediatrics},
  year = {2025},
  doi = {10.1186/s12887-025-05936-7}
}
Kostenlos starten →