Fig. 4
From: Using random forest and biomarkers for differentiating COVID-19 and Mycoplasma pneumoniae infections
Receiver operating characteristic (ROC) curves for the multi-class classification performance of the random forest model. 95% CI, 95% confidence interval; class 1 (COVID-19 positive), AUC = 0.86 (95% CI: 0.70–0.97); class 2 (Mycoplasma pneumoniae positive), AUC = 0.79 (95% CI: 0.64–0.92); class 3 (co-infected), AUC = 0.69 (95% CI: 0.50–0.87); micro-average ROC curve: AUC = 0.90 (95% CI: 0.83–0.95).
