Fig. 3
From: Random forest-based modelling to detect biomarkers for prostate cancer progression
Performance analysis of the model in the test and validation datasets. a, c, e ROC curve analysis of the model’s performance in the test set (a), ICGC PCa cohort (c) and TCGA PRAD cohort (e). The x-axis shows the model’s specificity while the y-axis shows the sensitivity. Red dot represents the performance of the model when a cut-off of 0.5 is used during classification. b, d, f Kaplan-Meier curves using PSA recurrence-free survival as an outcome in the test set (b), in the ICGC PCa cohort (d) and in the TCGA-PRAD cohort (f), based on the predicted prognostic categories (blue: good prognosis, red: poor prognosis). p values were calculated using log-rank test