WBC = White Blood Cells; RBC = Red Blood Cells; HGB = Hemoglobin; PLT = Platelets; %Neu = Neutrophils (percentage); %Lymph = Lymphocytes (percentage); %Mon = Monocytes (percentage); #Neu = Neutrophils (number); #Lymph = Lymphocytes (number); #Mon = Monocytes (number); HCT = Hematocrit; MCV = Mean Corpuscular Volume; MCHC = Mean Corpuscular Hemoglobin Concentration; MCH = Mean Corpuscular Hemoglobin; RDW-SD = Red Cell Distribution Width-Standard Deviation; RDW-CV = Red Cell Distribution Width-Coefficient of Variation; PDW = Platelet Distribution Width; MPV = Mean Platelet Volume; PCT = Plateletcrit; P-LCR = Platelet Large Cell Ratio; InCRP = natural log-transformed value of CRP; %Eos = Eosinophils (percentage); #Eos = Eosinophils (number); %Bas = Basophils (percentage); #Bas = Basophils (number).
Construction and evaluation of the nomogram prediction model.
Multivariable logistic regression analysis established a nomogram model based on the final selected predictor variables(FIGURE 3. A). The AUC of the pneumonia risk model was 0.7820 (95% CI: 0.7254-0.8439) in the training cohort and 0.8432 (95% CI: 0.7588-0.9151) in the validation cohort(FIGURE 3. B, C); at the cut-off value of 0.5, the sensitivity and specificity of the pneumonia risk model were 70.75%, 66. 33% (training cohort), 76.09%, and 73.91% (validation cohort), respectively; the calibration curve showed good agreement between the predicted probability of pneumonia from the pneumonia risk model and the actually observed probability. Decision curve analysis (DCA) showed good clinical validity of the pneumonia risk model in the training and validation cohort (FIGURE 3. F, G). Other diagnostic parameters of the model are shown in TABLE 3. Comparison of the AUC and DCA for the pneumonia risk model with predictors incorporated in the model alone in the whole study cohort were shown in FIGURE 4, showing that the pneumonia risk model combining multiple predictors has better diagnostic performance than a single predictor.
TABLE 3. Diagnostic parameters ofthe pneumonia risk model.