Development and clinical validation of a novel nomogram model for screening respiratory infectious diseases in the emergency department

Ma Li; Zhang Hua; Zhou Xiaoshu; Li Baohua; Hu Xianjing; Feng Chunyan; Jiang Yuting; Ma Qingbian

doi:10.3969/j.issn.1002-1949.2025.08.002

Abstract：Objective To develop and validate a nomogram model for early prediction of respiratory infectious disease severity in emergency triage,and to compare its clinical value with traditional scoring tools[modified early warning score(MEWS)and sequential organ failure assessment(SOFA)].Methods The data of a total of 7 615 patients were retrieved from December 2022 to March 2023,November 2023 to March 2024,and November 2024 to December 2024,and 4 727 eligible participants were included in the final analysis.In the training set of random sampling(70％),routinely available triage data were used as predictors(such as demographic data,vital signs,current disease,and past medical history).The severity was defined as the patient admitted to the intensive care unit after the emergency visit.Binary Logistic regression analysis was used to develop a nomogram to perform accurate calibration,identification and clinical application evaluation of the performance of the model.Results Predictors in the individualized prediction nomogram included age,pulse,respiratory rate,fever,shortness of breath,and the level of consciousness.The nomogram model showed good discrimination and good calibration,with the area under ROC curve(AUC)of the nomogram model was 0.830(95％CI 0.791～0.870)in the training set and 0.750(95％CI 0.638～0.864)in the validation set.Compared with MEWS and SOFA,the nomogram model demonstrated higher accuracy and specificity in predicting the severity of patients with respiratory infectious diseases.Conclusions The nomogram model of respiratory infectious diseases developed in this study for emergency triage has high accuracy in predicting the severity of respiratory infectious disease,which facilitates the rational allocation of healthcare resources and timely intervention for high-risk patients by emergency clinicians.