TABLE 5.

Logistic regression model performances on testing data showing the median (90% CI) for each image and tissue type (ROI) (median values above 0.7 for all the performance metrics for the same model are highlighted with bold font).

ROI	Image	Accuracy	AUC	Sensitivity	Specificity
WM	T1w	0.74 (0.66, 0.82)	0.90 (0.84, 0.95)	0.76 (0.67, 0.86)	0.72 (0.59, 0.82)
	PD	0.64 (0.58, 0.71)	0.98 (0.95, 1.00)	1.00 (1.00, 1.00)	0.28 (0.17, 0.42)
	MT	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)
	R1	0.82 (0.76, 0.88)	1.00 (1.00, 1.00)	0.64 (0.52, 0.75)	1.00 (1.00, 1.00)
	R2*	0.73 (0.63, 0.83)	0.86 (0.78, 0.93)	0.76 (0.62, 0.86)	0.72 (0.58, 0.84)
	qMRIcomb	0.93 (0.88, 0.97)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	0.86 (0.77, 0.94)
NAWM	T1w	0.73 (0.66, 0.82)	0.86 (0.77, 0.93)	0.76 (0.64, 0.87)	0.70 (0.59, 0.81)
	PD	0.37 (0.30, 0.44)	0.67 (0.55, 0.81)	0.74 (0.60, 0.87)	0.00 (0.00, 0.00)
	MT	0.81 (0.74, 0.89)	0.79 (0.69, 0.90)	0.76 (0.64, 0.87)	0.86 (0.77, 0.94)
	R1	0.87 (0.80, 0.93)	0.97 (0.93, 0.99)	0.88 (0.77, 0.98)	0.86 (0.77, 0.94)
	R2*	0.66 (0.56, 0.76)	0.83 (0.73, 0.94)	0.76 (0.64, 0.87)	0.56 (0.40, 0.72)
	qMRIcomb	0.74 (0.67, 0.81)	0.82 (0.73, 0.90)	0.62 (0.48, 0.77)	0.86 (0.77, 0.94)
GM	T1w	0.41 (0.32, 0.52)	0.60 (0.47, 0.73)	0.26 (0.16, 0.40)	0.56 (0.43, 0.71)
	PD	0.69 (0.61, 0.79)	0.83 (0.74, 0.91)	0.51 (0.38, 0.66)	0.86 (0.77, 0.94)
	MT	0.88 (0.82, 0.94)	0.81 (0.71, 0.90)	0.76 (0.64, 0.87)	1.00 (1.00, 1.00)
	R1	0.82 (0.75, 0.87)	0.81 (0.72, 0.88)	0.64 (0.50, 0.74)	1.00 (1.00, 1.00)
	R2*	0.73 (0.65, 0.83)	0.86 (0.78, 0.95)	0.76 (0.64, 0.87)	0.71 (0.58, 0.84)
	qMRIcomb	0.81 (0.73, 0.88)	0.86 (0.78, 0.93)	0.76 (0.64, 0.87)	0.84 (0.77, 0.95)