Skip to main content
. 2026 Sep 11;14:1927235. doi: 10.3389/fcell.2026.1927235

FIGURE 5.

Panel A shows a ROC curve for various machine learning models in the training cohort, illustrating model performance with labeled AUC values. Panel B displays a ROC curve for the test cohort, similarly comparing model performance. Panel C illustrates a calibration curve for the training cohort, mapping predicted against observed event percentages by model. Panel D presents the calibration curve for the test cohort. Panel E features a decision curve analysis (DCA) for the training cohort, showing standardized net benefit at different risk thresholds. Panel F visualizes the DCA for the test cohort. Panel G is a heatmap detailing DeLong test p-values between models in the training cohort, color-coded by significance. Panel H is a comparable DeLong test heatmap for the test cohort.

Efficacy of multiomics-based models. (A,B) The ROC curves of different machine learning models in the training and test cohort. (C,D) The calibration curves of different machine learning models in the training and test cohort. (E,F) The DCA curves of different machine learning models in the training and test cohort. (G,H) The heap map of AUCs comparison of different models by DeLong test in the training and test cohort.