Fig. 8
From: Prediction model of poorly differentiated colorectal cancer (CRC) based on gut bacteria
Validation of risk prediction model for poorly differentiated CRC. We used the relevant functions in the rminer Package (version 1.4.5) of R language for modeling analysis and used the fit function for modeling the variable importance calculation. All data were divided into 70% training set to build the model and 30% test set to verify the model. A-F are the LR model (A), RF model (B), NN model (C), SVM model (D), GBDT model (E) and CatBoost model (F). The left panel (a1, b1, c1, d1, e1, f1) show the AUC curve of the model, and the right panel (a2, b2, c2, d2, e2, f2) show the accuracy of the model