Shen Li, Wu Jiaqiang, Lu Min, Jiang Yiguo, Zhang Xiaolan, Xu Qiuyan, Ran Shuangqin
Department of Pharmacy, Suzhou Hospital, Affiliated Hospital of Medical School, Nanjing University, Suzhou, Jiangsu, China.
School of Life Sciences and Biopharmaceutical Science, Shenyang Pharmaceutical University, Shenyang, China.
Front Pediatr. 2025 Mar 7;13:1490500. doi: 10.3389/fped.2025.1490500. eCollection 2025.
Community-acquired pneumonia (CAP) is a prevalent pediatric condition, and lobar pneumonia (LP) is considered a severe subtype. Early identification of LP is crucial for appropriate management. This study aimed to develop and compare machine learning models to predict LP in children with CAP.
A total of 25 clinical and laboratory variables were collected. Missing data (<2%) were imputed, and the dataset was split into training (60%) and validation (40%) sets. Univariable logistic regression and Boruta feature selection were used to identify significant predictors. Four machine learning algorithms-Logistic Regression (LR), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Decision Tree (DT)-were compared using area under the curve (AUC), balanced accuracy, sensitivity, specificity, and F1 score. SHAP analysis was performed to interpret the best-performing model.
A total of 278 patients with CAP were included in this study, of whom 65 were diagnosed with LP. The XGBoost model demonstrated the best performance with an AUC of 0.880 (95% CI: 0.807-0.934) in the training set and 0.746 (95% CI: 0.664-0.843) in the validation set. SHAP analysis identified age, CRP, CD64 index, lymphocyte percentage, and ALB as the top five predictive factors.
The XGBoost model showed superior performance in predicting LP in children with CAP. The model enabled early diagnosis and risk assessment of LP, thereby facilitating appropriate clinical decision-making.
社区获得性肺炎（CAP）是一种常见的儿科疾病，大叶性肺炎（LP）被认为是一种严重的亚型。早期识别LP对于恰当的治疗至关重要。本研究旨在开发并比较机器学习模型以预测CAP患儿中的LP。
共收集了25个临床和实验室变量。对缺失数据（<2%）进行了插补，数据集被分为训练集（60%）和验证集（40%）。使用单变量逻辑回归和Boruta特征选择来识别显著的预测因素。使用曲线下面积（AUC）、平衡准确率、敏感性、特异性和F1分数对四种机器学习算法——逻辑回归（LR）、支持向量机（SVM）、极端梯度提升（XGBoost）和决策树（DT）——进行比较。进行SHAP分析以解释表现最佳的模型。
本研究共纳入278例CAP患儿，其中65例被诊断为LP。XGBoost模型表现最佳，训练集中的AUC为0.880（95%CI：0.807 - 0.934），验证集中的AUC为0.746（95%CI：0.664 - 0.843）。SHAP分析确定年龄、CRP、CD64指数、淋巴细胞百分比和ALB为前五个预测因素。
XGBoost模型在预测CAP患儿的LP方面表现出卓越性能。该模型能够对LP进行早期诊断和风险评估，从而促进恰当的临床决策。
