机械通气病人脱机试验结局影响因素及预测模型构建  

Influencing factors and prediction model construction of spontaneous breathing trial outcome of mechanical ventilation patients

作　　者：徐会美 郑燕琦 XU Huimei;ZHENG Yanqi(The Second People′s Hospital of Lianyungang,Affiliated Kangda College of Nanjing Medical University,Jiangsu 222000 China)

机构地区：[1]南京医科大学康达学院附属连云港市第二人民医院,222000

出　　处：《全科护理》2023年第34期4759-4762,共4页Chinese General Practice Nursing

基　　金：南京医科大学康达学院科研发展基金课题,编号:KD2021KYJJD095。

摘　　要：目的:探讨重症监护室(intensive care unit,ICU)机械通气病人脱机试验结局的影响因素,并据此构建预测模型以为临床病人脱机时机的选择提供参考。方法:本研究为回顾性研究,收集2022年1月1日—12月31日在连云港市第二人民医院重症医学科330例病人的一般资料,并依据脱机试验结局分为成功组(n=264)和失败组(n=66),比较分析两组的一般资料,筛选出差异有统计学意义的变量进行二元Logistic回归分析,根据分析结果建立病人脱机试验结局的预测模型,绘制受试者工作特征(ROC)曲线验证模型的应用效能,采用Hosmer-Lemeshow拟合优度检验评价模型预测效果。结果:单因素分析结果显示,两组病人急性生理学与慢性健康状况评分系统Ⅱ(APACHEⅡ)评分、置管天数、咳痰强度、脱机试验前血气pH值、清蛋白、意识状态、血管活性药物、营养评分(NRS-2002)比较,差异有统计学意义(P<0.05);二元Logistic回归分析显示,置管天数、咳痰强度、营养评分、意识状态、血管活性药物是脱机试验结局的影响因素。据此绘制受试者工作特征(ROC)曲线,曲线下面积为0.926[95%CI(0.896,0.956)],约登指数为0.697,截断值为0.866,灵敏度为0.879[95%CI(0.779,0.937)],特异度为0.818[95%CI(0.767,0.860)],经Hosmer-Lemeshow检验,差异无统计学意义(χ^(2)=6.253,P=0.619)。结论:置管天数、咳痰强度、意识状态、营养评分、血管活性药物是病人脱机试验结局的影响因素,可以较好地预测病人的脱机试验结局。Objective:To investigate the factors influencing of spontaneous breathing trial(SBT)outcome of mechanical ventilation patients in intensive care unit(ICU),and construct a prediction model to provide reference for the selection of spontaneous breathing trial(SBT)for clinical patients.Methods:This study was a retrospective study.General data of 330 patients in the Department of Intensive Care Medicine of the Second People′s Hospital of Lianyungang City from January 1 to December 31,2022 were collected,and they were divided into successful group(n=264)and failure group(n=66)according to the outcome of spontaneous breathing trial.General data of the two groups were compared and analyzed.Variables with statistically significant differences were selected for binary Logistic regression analysis,and a prediction model for the spontaneous breathing trial outcome was established according to the analysis results.Receiver operating characteristic(ROC)curve was drawn to verify the application efficiency of the model,and Hosmer-Lemeshow goodness of fit test was used to evaluate the prediction effect of the model.Results:Unifactor analysis showed that there were statistically significant differences in APACHE II score,the number of days of tube insertion,sputum intensity,blood gas pH value before spontaneous breathing trial,albumin,state of consciousness,vasoactive drugs and Nutrition Score(NRS-2002)between the two groups(P<0.05).Binary Logistic regression analysis showed that the number of days of tube insertion,sputum intensity,Nutritional Score,state of consciousness and vasoactive drugs were the influencing factors of spontaneous breathing trial outcome.According the receiver operating characteristic(ROC)curve was drawn.The area under the curve was 0.926[95%CI(0.896,0.956)],the Jorden index was 0.697,the cutoff value was 0.866,and the sensitivity was 0.879[95%CI(0.779,0.937)].The specificity was 0.818[95%CI(0.767,0.860)],and Hosmer-Lemeshow test showed no statistical significance(χ^(2)=6.253,P=0.619).Conclusions:The num

关 键 词：气管插管 机械通气 脱机试验 危险因素 预测模型 

分 类 号：R473[医药卫生—护理学]