Kucukakcali Zeynep, Akbulut Sami, Colak Cemil
Department of Biostatistics and Medical Informatics, Inonu University Faculty of Medicine, 44280 Malatya, Turkey.
Department of Surgery and Liver Transplant Institute, Inonu University Faculty of Medicine, 44280 Malatya, Turkey.
J Clin Med. 2025 Jun 16;14(12):4264. doi: 10.3390/jcm14124264.
: Pediatric acute appendicitis (AAP) is a common cause of abdominal pain in children, yet accurate classification into negative, uncomplicated, and complicated forms remains clinically challenging. Misclassification may lead to unnecessary surgeries or delayed treatment. This study aims to evaluate and compare the diagnostic accuracy of five machine learning models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, and Random Forest) for classifying pediatric AAP subtypes. : In this retrospective observational study, a dataset of 590 pediatric patients was analyzed. Demographic information and laboratory parameters-including C-reactive protein (CRP), white blood cell (WBC) count, neutrophils, lymphocytes, and appendiceal diameter-were included as features. The cohort consisted of negative (19.8%), uncomplicated (49.2%), and complicated (31.0%) AAP cases. Five ensemble machine learning models (AdaBoost, XGBoost, Stochastic Gradient Boosting, Bagged CART, and Random Forest) were trained on 80% of the dataset and tested on the remaining 20%. Model performance was evaluated using accuracy, sensitivity, specificity, and F1 score, with cross-validation employed to ensure result stability. : Random Forest demonstrated the highest overall accuracy (90.7%), sensitivity (100.0%), and specificity (61.5%) for distinguishing negative and uncomplicated AAP cases. Meanwhile, XGBoost outperformed other models in identifying complicated AAP cases, achieving an accuracy of 97.3%, sensitivity of 100.0%, and specificity of 78.3%. The most influential biomarkers were neutrophil count, appendiceal diameter, and WBC levels, highlighting their predictive value in AAP classification. : ML models, particularly Random Forest and XGBoost, exhibit strong potential in aiding pediatric AAP diagnosis. Their ability to accurately classify AAP subtypes suggests that ML-based decision support tools can complement clinical judgment, improving diagnostic precision and patient outcomes. Future research should focus on multi-center validation, integrating imaging data, and enhancing model interpretability for broader clinical adoption.
小儿急性阑尾炎（AAP）是儿童腹痛的常见原因，但准确分类为阴性、非复杂性和复杂性形式在临床上仍具有挑战性。分类错误可能导致不必要的手术或治疗延迟。本研究旨在评估和比较五种机器学习模型（AdaBoost、XGBoost、随机梯度提升、袋装CART和随机森林）对小儿AAP亚型进行分类的诊断准确性。
在这项回顾性观察研究中，分析了590例儿科患者的数据集。人口统计学信息和实验室参数——包括C反应蛋白（CRP）、白细胞（WBC）计数、中性粒细胞、淋巴细胞和阑尾直径——被作为特征纳入。该队列包括阴性（19.8%）、非复杂性（49.2%）和复杂性（31.0%）AAP病例。五种集成机器学习模型（AdaBoost、XGBoost、随机梯度提升、袋装CART和随机森林）在80%的数据集上进行训练，并在其余20%上进行测试。使用准确率、灵敏度、特异性和F1分数评估模型性能，并采用交叉验证以确保结果的稳定性。
随机森林在区分阴性和非复杂性AAP病例方面表现出最高的总体准确率（90.7%）、灵敏度（100.0%）和特异性（61.5%）。同时，XGBoost在识别复杂性AAP病例方面优于其他模型，准确率达到97.3%，灵敏度为100.0%，特异性为78.3%。最具影响力的生物标志物是中性粒细胞计数、阑尾直径和白细胞水平，突出了它们在AAP分类中的预测价值。
机器学习模型，特别是随机森林和XGBoost，在辅助小儿AAP诊断方面具有强大潜力。它们准确分类AAP亚型的能力表明，基于机器学习的决策支持工具可以补充临床判断，提高诊断精度和患者预后。未来的研究应侧重于多中心验证、整合影像数据以及提高模型的可解释性，以实现更广泛的临床应用。
