耐碳青霉烯肺炎克雷伯菌感染风险因素分析及预测模型的构建

Analysis of risk factors and construction of predictive model for carbapenem-resistant Klebsiella pneumoniae infection

目的:探讨耐碳青霉烯肺炎克雷伯菌(CRKP)感染的风险因素,构建风险预测模型及验证。方法:收集肺炎克雷伯菌感染病人资料2377例,排除2117例,最终纳入符合条件260例,按照3∶1随机拆分为训练集195例和验证集65例。训练集按碳青霉烯是否耐药分为CRKP组72例和碳青霉烯敏感肺炎克雷伯菌(CSKP)组123例,应用R语言构建模型并进行验证。结果:ALB降低、尿管留置、呼吸机应用≥7 d、入住ICU时间≥7 d、联合应用抗生素是CRKP感染的风险因素(P<0.05)。应用这5个变量构建风险预测模型并绘制列线图。训练集ROC曲线下面积(AUC)为0.864(95%CI:0.814~0.915),验证集AUC为0.855(95%CI:0.763~0.947)。训练集和验证集校准曲线检验结果一致性较好,Hosmer-Lemeshow拟合度较好。临床决策曲线显示模型具有一定的临床实用性。结论:研究所构建的风险预测模型可以为临床判断病人CRKP感染风险及尽早调整治疗方案提供参考。

Objective:To explore the risk factors of carbapenem-resistant Klebsiella pneumoniae(CRKP)infection,construct and validate a risk predictive model.Methods:A total of 2377 patients with Klebsiella pneumoniae infection were collected,with 2117 cases excluded.Finally,260 eligible patients were included and randomly divided into the training set of 195 cases and the validation set of 65 cases in a 3∶1 ratio.The training group was divided into a CRKP group with 72 cases and a carbapenem-sensitive Klebsiella pneumoniae(CSKP)group with 123 cases based on whether carbapenem was resistant.The model was constructed using R language and validated.Results:ALB decrease,indwelling urethral catheter,ventilator use for≥7 days,ICU stay for≥7 days,and combined use of antibiotics were risk factors for CRKP infection(P<0.05).A risk prediction model was constructed and a nomogram was drawn using these 5 variables.The area under the ROC curve(AUC)of the training set was 0.864(95%CI:0.814-0.915),and the AUC of the validation set was 0.855(95%CI:0.763-0.947).The consistency of the calibration curve test results between the training set and validation set was good,and the Hosmer-Lemeshow fit was good.The clinical decision curve showed that the model had good prediction accuracy.Conclusions:The risk predictive model constructed in this study can provide reference for the clinical assessment of CRKP infection risk in patients,which has certain guiding significance for early diagnosis and treatment.