Skip to main content

Table 4 Two-class classification using XGB-linear with texture + morphological features for COVID-19 (N = 130) vs bacterial pneumonia (N = 145), COVID-19 vs non-COVID-19 viral (N = 145) and COVID-19 vs normal (N = 138)

From: Machine-learning classification of texture features of portable chest X-ray accurately classifies COVID-19 lung infection

Classification Sensitivity (%) Specificity (%) PPV (%) NPV (%) Accuracy (%) AUC
COVID-19 vs bacterial pneumonia 95.35 97.44 97.62 95.00 96.34 0.98
COVID-19 vs non-COVID-19 viral pneumonia 97.44 97.67 97.44 97.67 97.56 0.98
COVID-19 vs normal 100 100 100 100 100 1.00