Objective:The COVID-19 pandemic poses a significant threat to global health.Given the lack of studies on risk factors for COVID-19 progression at present,this study aimed to build a predictive model to predict the pro...Objective:The COVID-19 pandemic poses a significant threat to global health.Given the lack of studies on risk factors for COVID-19 progression at present,this study aimed to build a predictive model to predict the progression risk among hospitalized COVID-19 patients.Methods:We extracted data from 1074 mild and moderate COVID-19 patients from Electronic Health Records(EHRs)in a designated Wuhan hospital including demographic characteristics and clinical and laboratory information.Disease progression was defined as progressing to severe critical illness after admission.The LASSO regression was used to select the predicted variables and a logistic regression model was applied to build the predictive model.Nomogram was used to show the results.Results:Seven variables were included in the predictive model:age per 10 years(OR,1.15;95%CI,1.03-1.29),lactate dehydrogenase(OR,1.73;95%CI,1.14-2.62),neutrophil-to-lymphocyte ratio(OR,2.07;95%CI,1.42-3.02),eosinophil count(OR,2.10;95%CI,1.20-3.69),albumin(OR,2.37;95%CI,1.65-3.45),hemoglobin(OR,1.50;95%CI,1.10-2.05),D-dimer(OR,1.63;95%CI,1.19-2.23).The mean area under the receiver operating characteristic curve of the predictive model was 0.72(95%CI,0.69-0.76).Conclusions:This study built a predictive model that could effectively predict the progression risk among hospitalized COVID-19 patients.展开更多
基金supported by the National Key Technology R&D Program of China(No.2020YFC0840800).
文摘Objective:The COVID-19 pandemic poses a significant threat to global health.Given the lack of studies on risk factors for COVID-19 progression at present,this study aimed to build a predictive model to predict the progression risk among hospitalized COVID-19 patients.Methods:We extracted data from 1074 mild and moderate COVID-19 patients from Electronic Health Records(EHRs)in a designated Wuhan hospital including demographic characteristics and clinical and laboratory information.Disease progression was defined as progressing to severe critical illness after admission.The LASSO regression was used to select the predicted variables and a logistic regression model was applied to build the predictive model.Nomogram was used to show the results.Results:Seven variables were included in the predictive model:age per 10 years(OR,1.15;95%CI,1.03-1.29),lactate dehydrogenase(OR,1.73;95%CI,1.14-2.62),neutrophil-to-lymphocyte ratio(OR,2.07;95%CI,1.42-3.02),eosinophil count(OR,2.10;95%CI,1.20-3.69),albumin(OR,2.37;95%CI,1.65-3.45),hemoglobin(OR,1.50;95%CI,1.10-2.05),D-dimer(OR,1.63;95%CI,1.19-2.23).The mean area under the receiver operating characteristic curve of the predictive model was 0.72(95%CI,0.69-0.76).Conclusions:This study built a predictive model that could effectively predict the progression risk among hospitalized COVID-19 patients.