Figure 3

The performances of the EasiAI, RF, SVM, LR, and NB. The x-axis is the sensitivity. The y-axis is the specificity. Different color denotes different machine learning model. The curves of different colors consist of sensitivity and specificity points of different models. The closer the sensitivity and specificity points are to the upper right corner, the large the sensitivity and specificity are, the better the model performs. All the sensitivity and specificity points of the NB are the farthest from the upper right corner and fall below the curves of other models. The two curves of the LR and the SVM are intertwined whose most of sensitivity and specificity points fall below the curve of the RF. The two curves of RF and EasiAI are intertwined and most of the RF’s sensitivity and specificity points fall below the ones of the EasiAI, especially between point a and b. The sensitivity and specificity points of the EasiAI are closest to the upper right corner, and have the highest AUC value 0.95.