Fig. 4.

Establishment and evaluation of the logistic regression model. A The logistic regression model. The red dashed line indicates the COOK distance. In general, points with the COOK distance larger than 0.5 (influential points) may influence the model accuracy. B The ROC curve. The horizontal axis represents false positive rate (FPR), and the vertical axis represents true positive rate (TPR). AUC value could assess the performance of the model, and the high AUC value ranging from 0 to 1 indicates good performance of the model