高龄病毒性肺炎患者院内死亡危险因素分析及预测模型构建

Analysis of risk factors for in-hospital mortality in advanced age patients with viral pneumonia and construction of a prediction model

中文关键词: 高龄  病毒性肺炎  死亡  影响因素  列线图

英文关键词: advanced age  viral pneumonia  mortality  influence factor  nomogram

中文摘要:

      目的 探讨高龄病毒性肺炎患者院内死亡的独立危险因素,构建列线图预测模型.方法 回顾性分析2022年12月2023年2月上海交通大学医学院附属瑞金医院收治的高龄病毒性肺炎患者.按7∶3的比例随机分为训练集和测试集,采用LASSO回归筛选变量,多因素二元Logistic回归确定患者死亡的影响因素,并构建列线图模型.以受试者工作特征曲线下面积(AUC)、校准曲线和决策曲线分析评估模型性能.结果 249例高龄病毒性肺炎患者年龄80～99岁,中位年龄86岁,死亡65例(26.10％).二元Logistic回归分析显示,血肌酐、D-二聚体和CRP水平升高为高龄病毒性肺炎患者死亡的危险因素,预后营养指数(PNI)升高为患者死亡的保护因素.训练集AUC为0.835(95％CI:0.769～0.902),灵敏度为80.00％,特异度为74.42％.测试集AUC为0.832(95％CI:0.723～0.941),灵敏度为70.00％,特异度为87.27％.校准曲线显示预测与实际风险一致性良好.结论 血肌酐、D-二聚体及CRP水平升高可能是高龄病毒性肺炎患者死亡的独立危险因素,高PNI则是患者死亡的保护因素.列线图能一定程度可视化预测高龄病毒性肺炎患者的死亡概率.

英文摘要:

      Objective To identify independent risk factors for in-hospital mortality in advanced age patients with viral pneumonia and construct a nomogram prediction model.Methods A retrospective analysis was conducted on advanced age patients with viral pneumonia admitted to Ruijin Hospital Affiliated to Medical College of Shanghai Jiaotong University from December 2022 to February 2023.Patients were randomly divided into a training set and a test set in a 7∶3 ratio.Least absolute shrinkage and selection operator(LASSO)regression was used for variable selection,and multivariate binary Logistic regression was employed to identify factors influencing patient mortality.Then a nomogram prediction model was constructed.The model's performance was evaluated using the area under the receiver operating characteristic curve(AUC),calibration curves,and decision curve analysis.Results The ages of 249 advanced age patients with viral pneumonia ranged from 80 to 99 years old,with a median age of 86 years old.Among them,65 cases(26.10％)died.Multivariate binary Logistic regression analysis showed that elevated serum levels of creatinine,D-dimer and C-reactive protein(CRP)were risk factors for mortality,while a higher prognostic nutritional index(PNI)was a protective factor.In the training set,the model achieved an AUC of 0.835(95％CI:0.769-0.902),with a sensitivity of 80.00％and a specificity of74.42％.In the test set,the AUC was 0.832(95％CI:0.723-0.941),with a sensitivity of 70.00％and a specificity of 87.27％.The calibration curve indicated good consistency between the predicted and actual mortality risks.Conclusion Elevated serum levels of D-dimer,creatinine,and CRP may serve as independent risk factors for mortality in advanced age patients with viral pneumonia,whereas a higher PNI value is a protective factor.The constructed nomogram prediction model can visually predict the mortality probability of advanced age patients with viral pneumonia to a certain extent.