首页|期刊导航|全科护理|住院病人鼻肠管非计划拔管风险预测模型的构建与验证

住院病人鼻肠管非计划拔管风险预测模型的构建与验证OA

Construction and validation of a risk prediction model for unplanned extubation of nasojejunal tube in hospitalized patients

中文摘要英文摘要

目的:构建并验证鼻肠管病人非计划拔管风险预测模型,为医护人员早期识别高风险人群提供参考.方法:采用目的抽样法,选取2022年1月—2024年9月在西宁市某三级甲等医院住院的280例鼻肠管病人为研究对象,使用R软件随机数方法按7∶3比例将研究对象随机分为训练集(n=196)和验证集(n=84),根据是否非计划拔出鼻肠管分为拔出组和未拔出组.采用LASSO回归、单因素及多因素Logistic回归分析筛选危险因素,构建预测模型,绘制可视化列线图,采用受试者工作特征(ROC)曲线、Hosmer-Lemeshow检验、校准曲线、决策曲线(DCA)、临床影响曲线(CIC)评价模型的性能.结果:Logistic回归分析显示,病人年龄、责任护士职称、导管材质及留置时间为鼻肠管病人发生非计划拔管的独立危险因素(P<0.05).训练集ROC曲线下面积为0.81,敏感度为64%,特异度为88%,Hosmer-Lemeshow检验(x2=4.824,P=0.776 2)及校准曲线表明模型校准度较好,临床决策曲线表明临床能获净收益,临床影响曲线表明临床预测效能高.结论:病人年龄、责任护士职称、导管材质及留置时间是住院病人鼻肠管非计划拔管的影响因素,基于此构建的模型具有较好的区分度和校准度,可为临床医护人员筛查鼻肠管非计划拔管的高危人群提供参考.

Objective:To construct and validate a risk prediction model for unplanned extubation in patients with nasojejunal tube,so as to provide reference for early identification of highrisk individuals by medical staff.Methods:A total of 280 patients with nasojejunal tubes who were hospitalized in a tertiary grade A hospital in Xining City from January 2022 to September 2024 were selected as the research subjects by using the purity-based sampling method.The research subjects were randomly divided into the training set(n=196)and the validation set(n=84)in a 7∶3 ratio using the random number method of R software.They were divided into the extraction group and the non-extraction group according to whether the nasojejunal tube was extracted.LASSO regression,univariate and multivariate Logistic regression analysis were used to screen risk factors,construct predictive models,and draw visual Nomograms.The performance of the model was evaluated by using the receiver operating characteristic(ROC)curve,Hosmer-Lemeshow test,correction curve,decision curve analysis(DCA),and clinical impact curve(CIC).Results:Logistic regression analysis showed that the patient's age,the professional title of the responsible nurse,the material of the catheter and the indwelling time were independent risk factors for unplanned extubation in patients with nasoenteric tubes(P<0.05).The area under the ROC curve of the training set was 0.81,the sensitivity was 64%,and the specificity was 88%.The Hosmer-Lemehow test(x2=4.824,P=0.776 2)and the correction curve indicated that the model had good calibration.The clinical decision curve analysis indicated that net clinical benefits could be obtained,and the clinical impact curve indicated high clinical predictive efficacy.Conclusions:The patient's age,the professional title of the responsible nurse,the material of the catheter and the indwelling time are the influencing factors of unplanned extubation of nasoenteric tubes in inpatients.The model constructed based on this has good discrimination and calibration,which can provide reference for clinical medical staff to screen high-risk groups of unplanned extubation of nasoenteric tubes.

范明嫄;马洁;马亚如;王展;刘柳;王键;罗彩霞

810000,青海大学临床医学院青海大学附属医院青海大学附属医院青海大学附属医院青海大学附属医院810000,青海大学临床医学院810000,青海大学临床医学院

鼻肠管非计划拔管列线图预测模型

nasojejunal tubeunplanned extubationNomogramprediction model

《全科护理》 2026 (10)

1813-1818,6

国家临床重点专科建设项目青海大学附属医院肝胆外科(包虫病),编号:青卫健办-125号青海大学附属医院中青年科研基金一般项目,编号:ASRF-2024-YB-17.

10.12104/j.issn.1674-4748.2026.10.002

评论