| 摘要: |
| ［摘要］ 目的 构建诊断儿童重症肺炎支原体肺炎（SMPP）的列线图模型，并对模型进行效能分析。方法 回顾性分析2023年5月至2024年5月新疆医科大学第一附属医院收治的966例肺炎支原体肺炎（MPP）患儿的临床资料。按照7∶3的比例将患儿随机分为建模集（680例）和验证集（286例）。根据MPP病情严重程度将患儿分为SMPP组和非SMPP组。对建模集数据进行单因素分析、Lasso回归分析及多因素logistic回归分析，筛选具有诊断SMPP意义的变量，并基于这些变量构建列线图模型。基于建模集和验证集数据，通过受试者工作特征（ROC）曲线分析、校正曲线分析以及决策曲线分析（DCA）评估列线图模型的诊断准确性以及临床应用价值。结果 Lasso回归分析获得12个有意义的指标：年龄、发热、呼吸音减弱、肺内并发症（总体）、胸腔积液、中性粒细胞/淋巴细胞比值（NLR）、血小板/淋巴细胞比值（PLR）、C-反应蛋白（CRP）、红细胞沉降率（ESR）、乳酸脱氢酶（LDH）、支气管充气征以及病变部位在左下叶。多因素logistic回归分析结果显示，年龄（OR=1.102）、呼吸音减弱（OR=4.714）、肺内并发症（OR=4.740）、LDH（OR=1.012）、ESR（OR=1.053）是SMPP发生的独立影响因素（P<0.05）。ROC曲线分析结果显示，所构建列线图模型能较好区分SMPP和MPP［建模集：AUC（95%CI）=0.801（0.767～0.834）；验证集：AUC（95%CI）=0.799（0.746～0.851），P<0.001］。校正曲线分析结果显示，列线图模型具有良好的拟合度，诊断准确度高。DCA结果显示，列线图模型在诊断SMPP方面净获益率高，具有较好的临床应用价值。结论 基于年龄、呼吸音减弱、肺内并发症、LDH、ESR指标构建的诊断儿童SMPP的列线图模型具有较高的准确度，有助于临床早期识别SMPP高风险患儿并采取相应的预防和治疗措施，改善预后。 |
| 关键词: 儿童 重症肺炎支原体肺炎 列线图模型 |
| DOI：10.3969/j.issn.1674-3806.2026.07.08 |
| 分类号:R 725.6 |
| 基金项目:“天山英才”医药卫生高层次人才培养计划（编号：TSYC202301B003） |
|
| Construction of a nomogram model for diagnosing severe Mycoplasma pneumoniae pneumonia in children and analysis on its diagnostic efficacy |
|
Wang Yingru1, Ru Liang2
|
|
1.Department of Pediatrics, the Friendship Hospital of Ili Kazakh Autonomous Prefecture, Yining 835000, China; 2.Second Department of Pediatric Internal Medicine, the First Teaching Hospital of Xinjiang Medical University, Urumqi 830054,China
|
| Abstract: |
| ［Abstract］ Objective To construct a nomogram model for diagnosing severe Mycoplasma pneumoniae pneumonia(SMPP) in children and to analyze the diagnostic efficacy of the model. Methods A retrospective analysis was conducted on the clinical data of 966 pediatric patients with Mycoplasma pneumoniae pneumonia(MPP) who were admitted to the First Teaching Hospital of Xinjiang Medical University from May 2023 to May 2024. The pediatric patients were randomly divided into a training set(680 patients) and a validation set(286 patients) at a ratio of 7∶3. According to the severity of MPP, the pediatric patients were divided into SMPP group and non-SMPP group. Univariate analysis, Lasso regression analysis and multivariate logistic regression analysis were performed on the training set data to screen variables with diagnostic significance for SMPP and a nomogram model was constructed based on these variables. The diagnostic accuracy and clinical application value of the nomogram model were evaluated through receiver operating characteristic(ROC) curve analysis, calibration curve analysis and decision curve analysis(DCA) using the training set and validation set data. Results A total of 12 significant indicators were obtained through Lasso regression analysis: age, fever, decreased breath sounds, pulmonary complications(overall), pleural effusion, neutrophil-to-lymphocyte ratio(NLR), platelet-to-lymphocyte ratio(PLR), C-reactive protein(CRP), erythrocyte sedimentation rate(ESR), lactate dehydrogenase(LDH), bronchial inflation sign, and lesion site in the lower left lobe. The results of multivariate logistic regression analysis showed that age(OR=1.102), decreased breath sounds(OR=4.714), pulmonary complications(OR=4.740), LDH(OR=1.012) and ESR(OR=1.053) were independent influencing factors for the occurrence of SMPP(P<0.05). The results of ROC curve analysis showed that the constructed nomogram model could effectively differentiate between SMPP and MPP［training set: AUC(95%CI)=0.801(0.767-0.834); validation set: AUC(95%CI)=0.799(0.746-0.851), P<0.05］. The results of calibration curve analysis indicated that the nomogram model had satisfactory goodness of fit and high diagnostic accuracy. The results of DCA showed that the nomogram model had a high net benefit rate in diagnosing SMPP and has good clinical practical value. Conclusion The nomogram model constructed based on the indicators of age, decreased breath sounds, pulmonary complications, LDH and ESR has high accuracy in diagnosing SMPP in children, which is helpful for early clinical identification of the children at high risk of SMPP and for taking corresponding preventive and therapeutic measures to improve their prognosis. |
| Key words: children severe Mycoplasma pneumoniae pneumonia(SMPP) nomogram model |
