个体化预测ICU机械通气患者发生呼吸机肺炎的风险列线图模型的建立

Establishment of a nomogram model for individualized prediction of risk of ventilator pneumonia in ICU mechanically ventilated patients

目的构建预测重症监护病房(ICU)机械通气患者发生呼吸机肺炎的风险列线图模型并进行验证。方法回顾性分析2016年3月至2021年7月于马鞍山十七冶医院ICU进行机械通气治疗的198例患者临床资料,采用LASSO分析和logistic回归分析筛选患者发生呼吸机肺炎的危险因素,采用R(R3.5.3)建立预测ICU机械通气患者发生呼吸机肺炎的风险列线图模型并进行验证。结果年龄≥60岁、联用抗菌药物、血清白蛋白<40 g/L、机械通气时间≥7 d、住院时间≥14 d、使用抑酸剂、气管切开及糖尿病是ICU机械通气患者发生呼吸机肺炎的危险因素(P<0.05)。基于上述危险因素建立列线图模型,模型一致性指数为0.836,模型预测概率与实际概率基本一致,受试者工作特征(ROC)曲线的曲线下面积为0.815,决策曲线显示阈值概率在5%~84%范围内时,具有较高的净获益值。结论ICU机械通气患者发生呼吸机肺炎的危险因素较多,建立列线图风险预测模型可为临床甄别呼吸机肺炎高危患者并改善其预后提供参考依据。

Objective To construct a nomogram model for predicting the risk of ventilator pneumonia in mechanically ventilated patients in the Intensive Care Unit(ICU).Methods Atotal of 198 patients who underwent mechanical ventilation treatment in the ICU of Ma’anshan Seventeenth Metallurgical Hospital from March 2016 to July 2021 wereselectedas the research objects.LASSO analysis and Logistic regression analysis were used to screen the independent risk factors for ventilator pneumonia in mechanically ventilated patients in ICU.R(R3.5.3)was used to establish a nomogram model for predicting the risk of ventilator pneumonia in ICU mechanically ventilated patients.Results Age≥60 years,combined use of antibacterial drugs,serum albumin<40 g/L,mechanical ventilation time≥7 d,hospitalization time≥14 d,use of acid inhibitors,tracheotomy,and diabetes were independent risk factorsfor ventilator pneumonia in patients withmechanical ventilation in ICU(P<0.05).Based on this,the nomogram model wasestablished.The model consistency index was 0.836,the predicted probability of the model was basically the same as the actual probability,the area under the ROC curve was 0.815,and the decision curve showed that the threshold probability was within the range of 5% to 84%,which brought net benefit value.Conclusions There are many risk factors for ventilator pneumonia in ICU mechanically ventilated patients.The predictive ability of the nomogram established in this study is relatively accurate,which can provide reference for clinical identification of high-risk patients with ventilator pneumonia and improve the prognosis of ICU mechanically ventilated patients.