老年心力衰竭住院患者营养不良风险预测模型的构建及验证  

Construction and validation of a malnutrition risk prediction model for elderly hospitalized patients with heart failure

作　　者：陈永梅 吴迪 卢梅 李晓娜 王信坤 陶明 Chen Yongmei;Wu Di;Lu Mei;Li Xiaona;Wang Xinkun;Tao Ming(Department of Nursing,Affiliated Hospital of Zunyi Medical University,Zunyi Guizhou 563000,China;School of Nursing,Zunyi Medical University,Zunyi Guizhou 563006,China)

机构地区：[1]遵义医科大学附属医院护理部,贵州遵义563000 [2]遵义医科大学护理学院,贵州遵义563006

出　　处：《遵义医科大学学报》2025年第3期286-294,共9页Journal of Zunyi Medical University

基　　金：遵义市科技计划项目(NO:遵市科合HZ字(2022)329)。

摘　　要：目的 构建老年心力衰竭住院患者营养不良风险预测模型,并验证其效果。方法 选取2019年1月至2022年12月在遵义医科大学附属医院心血管内科住院的老年心力衰竭患者375例作为建模集,采用NRS2002评估量表将其分为营养不良风险组(184例)和营养正常组(191例)。采用LASSO联合Logistic回归分析确定营养不良风险的独立危险因素并构建列线图模型。选取2024年1-7月同一所医院心血管内科住院的老年心力衰竭患者162例作为验证集。采用受试者操作特征曲线(ROC)下面积、校准曲线(caliboration curve)、Hosmer-Lemeshow拟合优度检验及决策曲线(DCA)进行模型评价。结果 建模集与验证集营养不良风险患病率分别为49%、50.6%;合并冠心病、年龄、前白蛋白、尿素、中性粒细胞与淋巴细胞比值是老年心力衰竭住院患者营养不良风险的独立预测因子。建模集ROC曲线下面积为0.791(95%CI:0.746~0.837),Hosmer-Lemeshow拟合优度检验显示χ^(2)=7.122,P=0.524;验证集ROC曲线下面积为0.753(95%CI:0.676~0.829),Hosmer-Lemeshow拟合优度检验显示χ^(2)=9.202,P=0.326,建模集预测曲线与校准曲线接近于理想曲线,验证集预测曲线与校准曲线总体趋势与理想曲线大致相同,DCA曲线显示建模集在16.5%~96.5%,验证集在12.5%~71%的风险阈值下模型均有较高的临床净获益。结论 本研究构建的风险预测模型预测效果良好,可为老年心力衰竭住院患者营养管理提供参考。Objective To construct a malnutrition risk prediction model for elderly hospitalized patients with heart failure and to verify its effect.Methods A total of 375 elderly patients with heart failure who were hospitalized in the Department of Cardiovascular Medicine of Affiliated Hospital of Zunyi Medical University from January 2019 to December 2022 were conveniently selected as the modeling set,and they were divided into malnutrition risk group(184 cases)and normal nutrition group(191 cases)by NRS2002 assessment scale.LASSO combined with Logistic regression analysis was used to identify the independent risk factors of malnutrition risk and construct a nomogram model.A total of 162 elderly patients with heart failure who were hospitalized in the Department of Cardiovascular Medicine of the same hospital from January-July 2024 were selected as the validation set.The receiver operator characteristic curve(ROC),calibration curve,Hosmer-Lemeshow goodness-of-fit test and decision curve analysis(DCA)were used for model evaluation.Results The prevalence of malnutrition in the modeling set and the validation set was 49%and 50.6%,respectively.Coronary heart disease,age,prealbumin,urea,and neutrophil-to-lymphocyte ratio were independent predictors of malnutrition risk in elderly hospitalized patients with heart failure.The area under the ROC curve of the modeling set was 0.791(95%CI:0.746-0.837),the Hosmer-Lemeshow goodness-of-fit test showedχ^(2)=7.122,P=0.524,and the area under the ROC curve of the validation set was 0.753(95%CI:0.676-0.829),and the Hosmer-Lemeshow goodness-of-fit test showedχ^(2)=9.202,P=0.326,the prediction curve and calibration curve of the modeling set were close to the ideal curve,the overall trend of the prediction curve and the calibration curve of the validation set was about the same as that of the ideal curve,the DCA curve showed that the modeling set was 16.5%-96.5%,and the model had a higher clinical net benefit under the risk threshold of 12.5%-71%of the validation set.Conclusion The risk pr

关 键 词：老年 心力衰竭 营养不良 预测模型 列线图 

分 类 号：R541.4[医药卫生—心血管疾病]