Algebraic topology-based machine learning using MRI predicts outcomes in primary sclerosing cholangitis

European Radiology Experimental

Table 2 Median (± median absolute deviation) values for metrics obtained during a 5-fold stratified cross-validation evaluation of the decision tree classifier in the derivation cohort

Metric	Fold 1	Fold 2	Fold 3	Fold 4	Fold 5	Median (± median absolute deviation)
Balanced accuracy	0.8	0.91	0.67	0.67	0.8	0.80 (± 0.12)
F1 score	0.8	0.90	0.69	0.69	0.77	0.70 (± 0.08)
Average precision	0.74	0.93	0.69	0.69	0.81	0.74 (± 0.04)
AUROC	0.8	0.91	0.67	0.67	0.80	0.80 (± 0.12)