ICU获得性肌无力风险预测模型的构建及应用-Linux大棚

admin 管理员组

文章数量: 1184232

2024年5月26日发(作者：网络安全攻防)

护理研究 2023 年 8 月第 37 卷第 15 期（总第 731 期）

·2673·

· 科研论著 ·

ICU获得性肌无力风险预测模型的构建

及应用

杨霞

1，

，于红静

，潘泽林

，梁梓杨

，叶敏怡

，何志丽

，梅楚楠

，覃湘君

，凌冬兰

，陈利芬

1.广州医科大学附属第二医院，广东 510260；2.中山大学护理学院；3.肇庆市第一人民医院；

4.广东省中西医结合医院；5.中山大学附属第一医院

Abstract Objective：To construct risk prediction model of intensive care unit‐acquired weakness，and to verify its application effect.

Methods：A total of 330 ICU patients in the adult general intensive care department of 4 tertiary grade A hospitals in Guangdong

province from August 2020 to December 2021，were selected as the study objects，and patients data were collected by self‐designed

case report ariate Logistic regression method was used to construct the risk prediction model，and the model was verified

internally and mini program and Nomograph based on Logistic regression model were s：Multivariate

Logistic regression model included the length of stay in ICU，mechanical ventilation，age，ventilator use time and APACHEⅡ.

The internal verification results of the model showed that the area under the receiver operating characteristic curve（AUC） was 0.879，

the sensitivity was 0.762，the specificity was 0.838，and the accuracy was al verification results showed that AUC was

0.755，the sensitivity was 0.682，the specificity was 0.740，and the accuracy was results of clinical application of the

model showed that：the probability≥0.648 from the mini‐program suggested that patients were at risk for ICU acquired weakness；

the total Nomogram score ≥14.2 suggested that patients were at high risk for ICU acquired sion：

The constructed risk prediction model of intensive care unit‐acquired weakness had high degree of distinction and WeChat

mini program and Nomograph methods could help patients to screen the risk of ICU acquired weakness quickly and efficiently.

Keywords intensive care unit； intensive care unit‐acquired weakness； risk factors； Nomograph

摘要目的:构建ICU获得性肌无力的风险预测模型并验证应用效果。方法:选取2020年8月—2021年12月广东省4所三级甲等综

合医院成人综合重症医学科330例ICU病人作为研究对象，采用自行设计的病例报告表收集病人资料。采用多因素Logistic回归

方法构建风险预测模型，对模型进行内部验证和外部验证。基于Logistic回归模型开发微信小程序和绘制列线图。结果:最终纳入

ICU住院天数、是否机械通气、年龄、呼吸机使用时间、急性生理与慢性健康状况评分（APACHEⅡ）5个因素构建多因素Logistic回

归模型。模型内部验证：受试者工作特征曲线下面积（AUC）为0.879，灵敏度为0.762，特异度为0.838，准确性为0.805；外部验证：

AUC为0.755，灵敏度为0.682，特异度为0.740，准确性为0.727。模型的两种临床实际应用方法：小程序得出概率≥0.648时，提示

病人有发生ICU获得性肌无力的风险；列线图总得分≥14.2分时，表明病人极有可能发生ICU获得性肌无力。结论:构建的ICU获

得性肌无力风险预测模型具有较高的区分度和校准度，微信小程序和列线图两种方法均能帮助临床快速、高效地筛查出病人发生

ICU获得性肌无力的风险。

关键词重症监护室；ICU获得性肌无力；危险因素；列线图

doi:10.12102/.1009-6493.2023.15.002

YANG　Xia, YU　Hongjing, PAN　Zelin, LIANG　Ziyang, YE　Minyi, HE　Zhili, MEI　Chunan, QIN　Xiangjun,

LING　Donglan, CHEN　Lifen

The Second Affiliated Hospital of Guangzhou Medical University, Guangdong 510260 China

Corresponding Author CHENLifen,E⁃mail:******************

Construction and application of risk prediction model of intensive care unit⁃acquired weakness

重症监护病房（ICU）获得性肌无力（intensive

care unit‐acquired weakness,ICU‐AW）指在ICU住院

期间发生发展的，无法用危重症疾病以外的其他原因

进行解释的，以广泛性肢体乏力为特征的临床综合

征

[1]

。据报道，重症监护病房ICU获得性肌无力的发

生率为50%~100%，尤其是脓毒血症病人，发生率远

高于其他疾病病人

[2]

。然而，目前仍无针对ICU获得

性肌无力的有效治疗药物

[3]

。一旦临床出现ICU获得

性肌无力，将延长机械通气时间和ICU住院时间，导

致病死率和致残率增加，降低预后生活质量并增加医

基金项目广州医科大学附属第二医院护理科研基金项目，编号：

A202001；2021年广州护理学会科研课题立项项目，编号：A2021079

作者简介杨霞，主管护师，硕士

本文标签：病人肌无力获得性模型研究

版权声明：本文标题：ICU获得性肌无力风险预测模型的构建及应用内容由网友自发贡献，该文观点仅代表作者本人，转载请联系作者并注明出处：http://www.roclinux.cn/p/1716719097a696178.html，本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。