基于随机森林模型的耐碳青霉烯类鲍曼不动杆菌性呼吸机相关性肺炎风险预测模型的构建OA北大核心CSTPCD

Objective:To analyze the risk factors for ventilator-associated pneumonia caused by carbapenem-resistant Acinetobacter baumannii(CRAB).Random forest model and Logistic regression two methods were used to construct prediction models,to provide theoretical basis for ICU to reduce the risk of CRAB ventilators associated pneumonia.Methods:A total of 291 patients with ventilators associated pneumonia admitted to ICU from January 2018 to December 2022 were selected as the study subjects.The influencing factors of CRAB ventilators associated pneumonia were analyzed.The predictive model was constructed based on random forest model and Logistic regression,and the operating characteristic curve(ROC)and area under the curve(AUC)were calculated to compare the differences between the two models.Results:Multivariate analysis results showed that oxygenation index,tracheotomy and coma were independent influencing factors of CRAB ventilator-associated pneumonia.The AUC of the random forest model was 0.78,and the AUC of the Logistic regression model was 0.61.The accuracy(77.97% ),sensitivity(85.37% ),and specificity(61.11% )of the random forest model were higher than those of the Logistic regression model(66.10%,73.17%,50.00% ).Conclusion:Oxygenation index,duration of antibiotic use,tracheotomy and coma are risk factors for CRAB ventilator-associated pneumonia.The random forest prediction model outperforms the Logistic regression model in predicting CRAB ventilator-associated pneumonia.