Table 2.

Accuracy indices of binary classification (HS vs FTD) in Test cohort.

Classifiers	Variables	N° of features	ACC %	SENS	SPEC	PPV	NPV
KNN	All features	6	88	0.85	0.90	0.89	0.86
	AngleR	1	85	0.95	0.67	0.83	0.89
	PerpPD	1	79	0.90	0.60	0.79	0.79
	PerpPD	1	77	0.80	0.75	0.76	0.79
	MD	1	72	0.70	0.75	0.74	0.71
	GM_fr	1	79	0.90	0.60	0.79	0.79
	MMSE	1	69	0.57	0.88	0.89	0.55

Accuracies for binary classification using whole brain measures (AngleR, PerpPD and Gm_fr) and MMSE. Abbreviations: ACC accuracy, SENS sensitivity, SPEC specificity, PPV  Positive predictive values, NPV negative predictive value.