Loading
ROC-AUC is the chance a classifier scores a random positive above a random negative; PR-AUC focuses on the positives and is the better summary when they are rare; time-dependent AUC applies the idea to survival at a chosen horizon.
A receiver operating characteristic curve plots a binary classifier's performance across thresholds and is standard in assessing diagnostic tests (Wikipedia); the area under it summarises ranking quality. Precision and recall measure the retrieved positives (Wikipedia), and the area under the precision-recall curve is sensitive to class imbalance where ROC-AUC is not, which matters when responders or rare subtypes are one in ten. Time-dependent AUC asks the same ranking question about who has had the event by a given time, complementing the C-index.
Shares C-index (concordance index), Harrell's and Uno's, Calibration: reliability diagrams and the Brier score, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Accuracy, macro-F1 and confusion matrices, C-index (concordance index), Harrell's and Uno's, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Calibration: reliability diagrams and the Brier score, Biomarker, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Accuracy, macro-F1 and confusion matrices, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Calibration: reliability diagrams and the Brier score, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares C-index (concordance index), Harrell's and Uno's, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares C-index (concordance index), Harrell's and Uno's, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Calibration: reliability diagrams and the Brier score, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.