Evaluating Ensemble-Based Machine Learning Models for Diagnosing Pediatric Acute Appendicitis: Insights from a
Zeynep Kucukakcali1, Sami Akbulut1,2, Cemil Colak1
1Department of Biostatistics and Medical Informatics, Inonu University Faculty of Medicine, 44280 Malatya, Turkey.
Journal of Clinical Medicine
|June 26, 2025
Summary
Machine learning models accurately classify pediatric acute appendicitis (AAP) subtypes. Random Forest and XGBoost show promise in improving diagnosis and patient outcomes by distinguishing between negative, uncomplicated, and complicated cases.
Area of Science:
- Computational biology and bioinformatics
- Pediatric surgery and emergency medicine
- Artificial intelligence in healthcare
Background:
- Pediatric acute appendicitis (AAP) diagnosis is challenging, with misclassification risking delayed treatment or unnecessary surgery.
- Accurate classification into negative, uncomplicated, and complicated AAP is crucial for appropriate pediatric care.
- Existing diagnostic methods for AAP require enhancement to improve precision and patient outcomes.
Purpose of the Study:
- To evaluate and compare the diagnostic accuracy of five machine learning (ML) models for classifying pediatric AAP subtypes.
- To identify the most effective ML models for distinguishing between negative, uncomplicated, and complicated pediatric appendicitis.
- To assess the role of specific laboratory biomarkers in the ML-based classification of AAP.
Main Methods:
- Retrospective analysis of 590 pediatric patients diagnosed with AAP.
- Inclusion of demographic data and laboratory parameters (CRP, WBC, neutrophils, lymphocytes, appendiceal diameter) as features.
- Training and testing of five ensemble ML models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, Random Forest) using cross-validation.
Main Results:
- Random Forest achieved 90.7% accuracy, 100% sensitivity, and 61.5% specificity for negative vs. uncomplicated AAP.
- XGBoost demonstrated superior performance for complicated AAP with 97.3% accuracy, 100% sensitivity, and 78.3% specificity.
- Neutrophil count, appendiceal diameter, and WBC levels were identified as the most influential predictive biomarkers.
Conclusions:
- Machine learning models, specifically Random Forest and XGBoost, show significant potential in aiding pediatric AAP diagnosis.
- ML-based decision support tools can enhance clinical judgment, leading to improved diagnostic accuracy and patient outcomes.
- Future research should focus on multi-center validation, integrating imaging data, and improving model interpretability for clinical adoption.
Related Concept Videos
01:29Appendicitis-II: Diagnostic Studies and Management
151
Diagnosing and managing appendicitis requires a structured and comprehensive approach that spans from initial assessment to postoperative care. Here is an overview of the process:
Diagnosing Appendicitis
It requires a multifaceted approach, starting with a detailed physical examination to pinpoint the location and nature of the pain and identify any associated symptoms. Laboratory tests play a crucial role. A complete Blood Count (CBC) typically reveals leukocytosis (an increased number of...
Diagnosing Appendicitis
It requires a multifaceted approach, starting with a detailed physical examination to pinpoint the location and nature of the pain and identify any associated symptoms. Laboratory tests play a crucial role. A complete Blood Count (CBC) typically reveals leukocytosis (an increased number of...
151
01:22Appendicitis-I: Introduction
649
The appendix, a small, narrow, blind tube extending from the inferior part of the cecum, is widely regarded as a vestigial organ, having lost much of its original function through evolution. Despite its diminished role, the appendix can become inflamed, a condition known as appendicitis.
Etiology: Appendicitis can arise from various causes, primarily rooted in the obstruction of the appendix lumen. Factors contributing to this obstruction include fecal accumulation, lymphoid hyperplasia and, in...
Etiology: Appendicitis can arise from various causes, primarily rooted in the obstruction of the appendix lumen. Factors contributing to this obstruction include fecal accumulation, lymphoid hyperplasia and, in...
649