基于Nomogram图预测儿童重症肺炎支原体肺炎的模型建立及临床价值  

Model establishment and clinical value of Nomogram-based prediction of severe Mycoplasma pneumoniae pneumonia in children

作　　者：柴焕然 张敬芳[1] 张俊霞[1] 陈冉 歹丽红 徐明慧 CHAI Huan-ran;ZHANG Jing-fang;ZHANG Jun-xia;CHEN Ran;DAI Li-hong;XU Ming-hui(Department of Pediatrics,Puyang People's Hospital,Puyang,Henan 457000,China)

机构地区：[1]濮阳市人民医院儿内科,河南濮阳457000

出　　处：《医药论坛杂志》2024年第8期791-796,共6页Journal of Medical Forum

摘　　要：目的基于Nomogram图建立预测儿童重症肺炎支原体肺炎(severe Mycoplasma pneumoniae pneumonia,SMPP)的模型,并分析模型的临床价值。方法回顾性收集2021年11月至2023年11月濮阳市人民医院收治的350名肺炎支原体肺炎(MPP)患儿为研究对象,按照随机数字表法以7∶3的比例分为训练集和验证集。入院后,根据患儿病情的发展情况分为轻症组和重症组。训练集中,单因素分析采用χ^(2)检验,多因素分析采用二分类logistic回归分析。基于独立危险因素建立Nomogram图预测模型。校准曲线和受试者工作特征(ROC)曲线评估模型的预测准确度,临床决策曲线分析(DCA)评估模型的临床安全性和实用性。结果训练集和验证集的一般临床资料对比,差异无统计学意义(P>0.05)。训练集的单因素分析显示,轻症组和重症组的年龄、体温、热程、支原体抗体滴度、ESR及CRP相比差异有统计学意义(P<0.05)。多因素分析结果显示年龄<7岁、体温≥39.0℃、热程≥5 d、支原体抗体滴度>1∶160、ESR>20 mm/h及CRP>10 mg/L是SMPP发生的独立危险因素。基于上述危险因素建立的Nomogram图预测模型在训练集的曲线下面积(AUC)为0.905,验证集的AUC为0.873。校正曲线在训练集和验证集中都表现出较高的拟合度和一致性。DCA结果显示Nomogram模型在SMPP的预测方面表现出较高的安全性和实用性。结论儿童SMPP的发生与年龄、体温、热程、支原体抗体滴度、ESR及CRP相关。以上述因素构建的Nomogram图预测模型准确度高,有助于及早识别患儿的SMPP风险,进而采取有效的预防和治疗措施。Objective To develop a model for predicting severe Mycoplasma pneumoniae pneumonia(SMPP)in children based on Nomograms and to analyse the clinical value of the model.Methods Totally 350 children with Mycoplasma pneumoniae pneumonia(MPP)admitted to our hospital from June 2021 to June 2023 were collected as study subjects and divided into training set and validation set according to the random number table method in the ratio of 7∶3 retrospectively.After admission,the children were divided into mild and severe groups according to the progression of their disease.In the training set,the χ^(2) test was used for univariate analyses,and binary logistic regression analysis was used for multivariate analyses.Nomogram prediction model was established based on independent risk factors.Calibration and receiver operating characteristic(ROC)curves were used to assess the predictive accuracy of the model,and clinical decision curve analysis(DCA)was used to assess the clinical safety and utility of the model.Results Comparison of general clinical data between the training and validation sets showed no statistically significant differences(P>0.05).Univariate analysis of the training set showed statistically significant differences(P<0.05)when comparing age,temperature,fever duration,mycoplasma antibody titer,ESR and CRP between the mild and severe groups.The results of multivariate analysis showed that age<7 years,temperature≥39.0℃,fever duration≥5 d,mycoplasma antibody titer>1∶160,ESR>20 mm/h and CRP>10 mg/L were independent risk factors for the development of SMPP.The area under the curve(AUC)of the Nomogram prediction model based on the above risk factors was 0.905 in the training set and 0.873 in the validation set.The calibration curves showed high fit and consistency in both the training and validation sets.The results of the DCA showed that the Nomogram model demonstrated a high degree of safety and utility in the prediction of SMPP.Conclusion The occurrence of SMPP in children is associated with age,temperatur

关 键 词：Nomogram图 肺炎支原体肺炎 重症 儿童 预测模型 

分 类 号：R375.2[医药卫生—病原生物学]