目的 分析儿童大环内酯类耐药重症肺炎支原体肺炎（SMPP）的危险因素,构建列线图预测模型。 方法 回顾性收集2023年1月—2024年9月在广州医科大学附属番禺中心医院儿科住院治疗的1 121例大环内酯类耐药肺炎支原体肺炎患儿入院初期的临床资料。按7∶3比例将患儿资料随机分为训练集（784例）和验证集（337例）。采用R4.4.1软件使用10重交叉验证最小绝对收缩与选择算法（LASSO）回归分析进行单因素变量筛选,采用Logistics回归分析建立预测模型, 绘制可视化列线图。使用受试者操作特征曲线（ROC）, 校准曲线、Hosmer-Lemeshow（HL）检验及临床决策曲线（DCA）分别评估模型的区分度、校准度和临床使用价值。 结果 在训练集中, LASSO回归结合Logistics回归分析结果显示,院前发热时间>5.5 d、谷丙转氨酶>14.5 U/L、乳酸脱氢酶>287.5 U/L、C反应蛋白>18.65 mg/L、肺实变、合并病毒感染是大环内酯类耐药SMPP发生的危险因素（P<0.05）, 根据上述危险因素构建列线图预测模型。训练集和验证集ROC曲线下面积分别为0.847和0.822; 校准曲线和HL检验显示模型具有良好的校准度; DCA显示预测模型在风险阈值为0.05~0.95时预测性能最优。 结论 院前发热时间、谷丙转氨酶、乳酸脱氢酶、C反应蛋白、肺实变、合并病毒感染是大环内酯类耐药SMPP发生的影响因素, 基于以上因素构建的列线图模型具有较好的预测效能, 有利于早期识别耐药重症病例, 及早采取有效干预,改善患者预后。

      Objective To explore the risk factors and to construct a nomogram prediction model for severe macrolide-resistant Mycoplasma pneumoniae pneumonia（MPP）in children．Methods The clinical data during the initial admission period of 1 121 children with macrolide-resistant MPP who were hospitalized in the Department of Pediatrics of the Affiliated Panyu Central Hospital of Guangzhou Medical University from January 2023 to September 2024 were retrospectively collected．The children data were randomly divided into a training set（n=784）and a validation set（n=337）at a ratio of 7∶3．With R language software（version 4.4.1）, least absolute shrinkage and selection operator（LASSO）regression analysis with tenfold cross-validation was used to screen risk factors, Logistics regression analysis was used to establish prediction model, and a visualization of the risk variables was created using a nomogram．The receiver operating characteristic（ROC）curves, calibration curves, Hosmer-Lemeshow（HL）test and clinical decision curve analysis（DCA）were used to evaluate the discrimination, calibration and clinical application value of the model．Results In the training set, LASSO regression analysis combined with Logistics regression analysis showed that prehospital fever duration > 5.5 days, alanine aminotransferase level> 14.5 U/L, lactate dehydrogenase level> 287.5 U/L, C-reactive protein > 18.65 mg/L, lung consolidation, and co-infection with virus were risk factors for severe macrolide-resistant MPP（P<0.05）．A nomogram prediction model was constructed based on the above risk factors．The area under the ROC curves of the training set and the validation set were 0.847 and 0.822, respectively．The calibration curves and HL test showed that the model had good calibration． The DCA curves showed that the prediction model had the best prediction performance when the risk threshold was between 0.05-0.95．Conclusions Prehospital fever duration, alanine aminotransferase level, lactate dehydrogenase level, C-reactive protein level, lung consolidation and co-infection with virus were risk factors for prediction of severe macrolide-resistant MPP．The nomogram model based on the above factors had a good prediction efficiency, which was conducive to early identification of severe cases with macrolide-resistant, and taking early effective interventions to improve the prognosis．