Table 4. Classification performance of L1 logistic regression (L1-LR) and support vector machine (SVM) approaches for 96 subjects using IBIF features.

Mean (standard deviation) is reported for the performance metrics. Previous results using 51 pairs [3] and 20 pairs [16] are also shown. It is worth noting that the distribution of metrics such as AUC, across all models, may be non-normal and may benefit from other summary statistics such as median (IQR).

Method	AUC	Accuracy	F-score	Sensitivity	Specificity	PPV	NPV	Threshold
L1-LR (IBIF)	0.82 (0.25)	0.83 (0.14)	0.77 (0.27)	0.78 (0.29)	0.85 (0.22)	0.81 (0.21)	0.82 (0.18)	0.54 (0.25)
SVM (IBIF)	0.82 (0.26)	0.84 (0.14)	0.78 (0.27)	0.79 (0.28)	0.84 (0.24)	0.83 (0.22)	0.82 (0.21)	0.02 (0.67)
Mehta et al. [3]	0.74 (0.27)	-	0.77 (0.20)	0.74 (0.30)	0.77 (0.29)	-	-	-
Ghassemi et al. [16]	0.71 (-)	0.66 (-)	0.63 (-)	0.50 (-)	0.81 (-)	0.72 (-)	0.62 (-)	-