Fig. 7

Evaluation of the effect of RF and XGB prediction models. A Confusion matrix of RF model in the training set. B Confusion matrix of the RF model for the validation set. C ROC curves of RF model in both training set and validation set. D Confusion matrix of the XGB model in the training set. E Confusion matrix of the XGB model in the validation set. F ROC curves of XGB model in both training set and validation set. The x-axis represents the predicted situation of the model. The y-axis represents the true situation. 1 represents correct prediction. 0 represents incorrect prediction. And the value in the box is the sample size. The horizontal coordinate is the false positive rate predicted by the model, the vertical coordinate indicates the true positive rate predicted by the model, and the area under the curve represents the AUC value; the higher the AUC value, the higher the diagnostic efficacy of the model