Detecting pancreaticobiliary maljunction in pediatric congenital choledochal malformation patients using machine learning methods
Related Experiment Video
Updated: Jan 16, 2026
Laparoscopic Choledochal Cyst Excision and Roux-en-Y Choledochojejunostomy in Adults
Published on: February 28, 2025
Yifeng Shao1,2, Chengyang Jiang1,2, Runmin Zhang3
1Capital Institute of Pediatrics, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.
Insights
Machine learning models effectively detect pancreaticobiliary maljunction (PBM) in children with congenital choledochal malformation using clinical data. This AI approach aids surgical planning by identifying PBM before operations.
Area of Science:
- Pediatric Surgery
- Medical Imaging and Diagnostics
- Artificial Intelligence in Medicine
Background:
- Pancreaticobiliary maljunction (PBM) presence complicates management in pediatric congenital choledochal malformation.
- Preoperative PBM detection in children is challenging, with intraoperative cholangiography often yielding suboptimal imaging.
Purpose of the Study:
- To develop and evaluate machine learning (ML) algorithms for detecting pancreaticobiliary maljunction (PBM) in pediatric patients with congenital choledochal malformation.
- To enhance preoperative diagnostic capabilities for PBM coexistence in this patient group.
Main Methods:
- Retrospective analysis of 803 pediatric patients with congenital choledochal malformation.
- Development and comparison of seven ML algorithms (LR, SVM, RF, XGBoost, AdaBoost, LightGBM, KNN) and an ensemble voting classifier.
- Performance evaluation using AUC, sensitivity, specificity, precision, recall, and F1-score; SHAP for interpretability.
Main Results:
- A significant prevalence of PBM (78.2%) was observed in the study cohort.
- An ensemble voting classifier achieved strong discriminative performance (AUC: 0.87; Recall: 0.91; F1-score: 0.91).
- Key predictive features included laboratory markers and clinical parameters.
Conclusions:
- ML algorithms integrating preoperative clinical and laboratory data show high capability in detecting PBM in pediatric congenital choledochal malformation.
- The Random Forest model demonstrated superior performance among base models.
- The developed ensemble model offers valuable preoperative guidance for surgical planning and management.
Objective:
The presence of pancreaticobiliary maljunction (PBM) in pediatric patients with congenital choledochal malformation significantly impacts clinical management and surgical decision-making. Current preoperative evaluation of PBM coexistence remains challenging in children, while intraoperative cholangiography does not consistently provide diagnostic-quality imaging. This study aims to develop machine learning-based algorithm models for detecting pancreaticobiliary maljunction (PBM) in children with congenital choledochal malformation.
Methods:
We conducted a retrospective study utilizing data from patients with congenital choledochal malformation treated at our center between January 2019 and January 2024. Demographic characteristics, clinical features, and preoperative laboratory parameters were processed through rigorous data curation and feature engineering pipelines. Cases were allocated via random sampling into training (80%) and hold-out test (20%) cohorts, maintaining strict separation between training and test cohorts. Seven machine learning algorithms - Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Light Gradient Boosting Machine (LightGBM), and K-Nearest Neighbors (KNN) - were implemented with five-fold cross-validation. An ensemble voting classifier was specifically constructed using these models. Model performance was quantified through comprehensive metrics including area under the ROC curve (AUC), sensitivity, specificity, positive/negative predictive values, accuracy, precision, recall, and F1-score. This study employed the nonparametric bootstrap method to estimate the confidence interval for the area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) was employed for model interpretability, with feature importance rankings determined by absolute SHAP value magnitudes.
Results:
In a cohort of 803 pediatric patients with congenital choledochal malformation, 628 (78.2%) demonstrated concurrent pancreaticobiliary maljunction. We developed a detection model incorporating 43 clinical features, with Random Forest showing optimal performance. An ensemble voting classifier integrating seven machine learning algorithms achieved enhanced discriminative performance (AUC: 0.87 (0.81, 0.92); Recall: 0.91 (0.85, 0.95); F1-score: 0.91 (0.87, 0.94)). Key features contributing to PBM detection included: laboratory markers and clinical parameters.
Conclusion:
By integrating preoperative clinical symptoms and laboratory parameters, machine learning algorithms demonstrated significant detection capability in identifying PBM among pediatric congenital choledochal malformation patients, with the RF model achieving superior performance metrics among all base models. The developed ensemble voting classifier provides valuable preoperative guidance for surgical planning and clinical management, enabling detection of PBM comorbidity before surgery in congenital choledochal malformation cases.
