Fig. 4

Predicting and verification of 3-year and 5-year overall survival. A The risk factors were represented by points on the axis, with each factor corresponding to a line drawn upward. The total points located on the axis indicated the probability of 3-year and 5-year overall survival, represented by a line drawn downward to the survival axis. B 3-year overall survival in new mode. C 5-year overall survival in new model. D 3-year overall survival in only clinical variables model. E 5-year overall survival in only clinical variables model. AUC represents the area under the ROC curve. AUC value is between 0.5 and 1, the closer to 1, the better the performance of model diagnosis, the higher the accuracy. (1) 0.7 < AUC < 0.9, indicating that the accuracy of the model is good and has certain clinical application value. (2) 0.5 < AUC < 0.7, indicating that the accuracy of this index/model is low and has little clinical application value. AUC: area under curve