摘要
目的:构建老年稳定性冠心病病人住院时间延长预测模型并验证其灵敏度和特异度。方法:选取镇江市某三级甲等医院2018年1月—2020年12月1 551例老年稳定性冠心病病人,按照住院时间分为住院时间未延长组和住院时间延长组,应用二元Logistic回归分析构建预测模型,采用受试者工作特征曲线(ROC)验证预测模型的灵敏度和特异度。结果:最终纳入自理能力评分、抑郁自评量表(SDS)评分、血糖、C反应蛋白、清蛋白5个独立危险因素。预测模型公式为P=1/[1+exp(-Z)],最终得到预测模型:Z=10.380-0.015×自理能力评分+1.403×SDS评分+0.784×血糖+0.214×C反应蛋白-0.133×清蛋白,ROC曲线下面积为(AUC)=0.835,95%CI(0.781,0.889),约登指数最大值为0.542,灵敏度为0.812,特异度为0.789。独立数据模型验证结果:灵敏度为0.883,特异度为0.801,准确率为88.5%。结论:该模型能较好地预测老年稳定性冠心病病人住院时间延长的发生风险,为临床医护人员的治疗与干预提供参考。
Objective:To construct a predictive model for a prolonged length of stay(LOS)in elderly patients with stable coronary artery disease(SCAD)and verify its sensitivity and specificity.Methods:A total of 1,551 elderly patients with SCAD from January 2018 to December 2020 in a tertiary grade⁃A hospital in the urban area of Zhenjiang city were enrolled in this study and were divided into non-extended LOS group and extended LOS group according to their LOS.Duality Logistic regression analysis was used to construct a prediction model,and the ROC curve was used to verify the sensitivity and specificity of the prediction model.Results:Finally,a total of five independent risk factors:self-care ability score,depression scale score,blood sugar,C⁃reactive protein,and albumin were included in this study.The prediction model was P=1/[1+exp(-Z)],and the final prediction model was Z=10.380-0.015×self⁃care ability score+1.403×SDS+0.784×blood sugar+0.214×C⁃reactive protein-0.133×albumin;the area under the ROC curve was(AUC)=0.835,95%CI(0.781,0.889);the maximum Youden index was 0.542,the sensitivity was 0.812,and the specificity was 0.789.Independent data model verification results showed that the sensitivity was 0.883,the specificity was 0.801,and the accuracy was 88.5%.Conclusions:This model could better predict the risk of prolonged LOS in elderly patients with SCAD,which could provide a reference for the treatment and intervention of clinical medical staff.
作者
杨吉羚
唐靓
邹圣强
蔡伟
茆敏
苗振英
YANG Jiling;TANG Liang;ZOU Shengqiang;CAI Wei;MAO Min;MIAO Zhenying(Zhenjiang Third Hospital Affiliated to Jiangsu University,Jiangsu 212000 China)
出处
《护理研究》
北大核心
2021年第23期4163-4168,共6页
Chinese Nursing Research
基金
2018年镇江市重点研发计划(社会发展)项目,编号:SH2018028
中国肝炎防治基金会王宝恩肝纤维化研究基金资助项目,编号:WBEXJS2018001。
关键词
老年人
冠心病
风险预测模型
住院时间延长
构建
护理
elderly
coronary heart disease
risk prediction model
prolonged length of stay
construction
nursing