Objective:To construct a model based on immune function and lung CT to predict the risk of severe progression in viral pneumonia.Methods:A retrospective analysis was conducted on the clinical data of 138 patients with viral pneumonia admitted to the People's Hospital of Liangjiang New Area,Chongqing,China from January 2021 to December 2022.The patients were divided into severe and non-severe groups based on clinical features.The demographic characteristics,lung CT scores,CD4(cluster of differentiation 4 receptors)+T cell,and CD8+T cell levels were compared between the two groups.A binary logistic regression analysis was used to construct a predictive model and evaluate its performance.The optimal cutoff value was determined based on the receiver operating characteristic(ROC)curve of the risk score.Results:Among the study population,41 patients(29.2％)developed severe or critical illness.Age,CD4+T cell count,and CT score were independent risk factors for the progression of viral pneumonia.The joint predictive model was established as Y=1.063×age+0.998×CD4+1.239×CT score-5.544.The area under the ROC curve of the model was 0.899,which was higher than that of individual indicators,with a sensitivity of 87.5％,specificity of 84.5％,and Youden index of 0.7254.Conclusions:The joint predictive model constructed in this study has good predictive efficacy for the risk of severe progression in viral pneumonia.
维普
万方数据