Table 2. .

Results of the classification analyses for the validation cohort

Variable	True negatives: SF		True positives: NSF		Acc.	Prec.	Sensitivity	F1	AUC
S(Rop)	19	0.73	6	0.75	0.74	0.46	0.75	0.57	0.71
Ov(RA, Rop)	18	0.69	6	0.75	0.71	0.43	0.75	0.55	0.69
δIR(RA)	21	0.81	6	0.75	0.79	0.55	0.75	0.63	0.78

Note. Results correspond to the optimal points of the ROC curves according to the Youden criterion to account for class imbalance. For each group (SF, NSF), we show the number of correctly identified cases by absolute number and relative frequency. The remaining columns correspond respectively to the accuracy (Acc.), precision (Prec.), sensitivity, F1 statistic, and area under the curve (AUC).