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

FIGURE 4.

Panel A shows an ROC curve comparing sensitivity versus 1-specificity for eight machine learning models in the training cohort. Panel B displays the same comparison for the test cohort. Panel C and Panel D present calibration curves indicating observed event percentages against predicted probabilities for both cohorts. Panel E and Panel F depict decision curve analysis (DCA) plots illustrating standardized net benefit across various risk thresholds for both datasets. Panel G and Panel H are heatmaps of DeLong test p-values comparing model performances, with color gradients representing significance levels for the training and test cohorts, respectively.

Efficacy of proteomics-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.