Skip to main content
. 2023 Feb 27;13:1096468. doi: 10.3389/fonc.2023.1096468

Figure 3.

Figure 3

Comparison of the prediction models for chronic postsurgical pain (CPSP) - receiver operating characteristic (ROC) curve in the training dataset (A) and the testing dataset (B). AUC, area under the curve; GBDT, gradient boosting decision tree (blue); LR, logistic regression (red); RF, random forest (green); XGBoost, extreme gradient boosting (purple).