Research Paper Volume 16, Issue 20 pp 13076—13103
A lactate metabolism-related gene signature to diagnose osteoarthritis based on machine learning combined with experimental validation
Figure 7. The predictive performance of the RF, SVM, and XGB diagnosis models. (A, B) ROC (A) and DCA (B) analysis indicates the predictive performance of RF model in the training (left), validation-cartilage (middle), and validation-synovial (right) cohorts. (C, D) ROC (C) and DCA (D) analysis indicates the predictive performance of SVM model in the training (left), validation-cartilage (middle), and validation-synovial (right) cohorts. (E, F) ROC (E) and DCA (F) analysis indicates the predictive performance of XGB model in the training (left), validation-cartilage (middle), and validation-synovial (right) cohorts. Abbreviations: RF, random forest; SVM, supporter vector machine; XGB, XGBoost; AUC, area under curve; CI, confidence interval.