Table VI.

The estimated AUC and its 95% CIs on MammaPrint datasets by different methods.

Train set	Test set	PW	SW	MM	MVN	LR	Ridge	LASSO
Glas78	Buyse307	0.72 (0.65, 0.78)	0.65 (0.57, 0.73)	0.48 (0.39, 0.57)	0.56(0.47, 0.65)	0.55 (0.45, 0.64)	0.70 (0.62, 0.77)	0.69 (0.61, 0.76)
	Glas84	0.70 (0.55, 0.83)	0.62 (0.43, 0.78)	0.65 (0.48, 0.81)	0.61(0.45, 0.75)	0.59 (0.42, 0.75)	0.65 (0.46, 0.83)	0.62 (0.44, 0.80)
	Glas78	0.91 (0.84, 0.97)	0.99 (0.98, 1.00)	0.51 (0.39, 0.64)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	0.98 (0.95, 1.00)
Glas84	Buyes307	0.69 (0.61, 0.76)	0.64 (0.56, 0.72)	0.55 (0.46, 0.64)	0.57 (0.48, 0.65)	0.57 (0.49, 0.66)	0.69 (0.62, 0.76)	0.64 (0.56, 0.73)
	Glas78	0.77 (0.66, 0.86)	0.67 (0.55, 0.79)	0.50 (0.37, 0.63)	0.60 (0.48, 0.73)	0.56 (0.43, 0.70)	0.81 (0.71, 0.90)	0.79 (0.68, 0.89)
	Glas84	0.94 (0.87, 0.98)	0.99 (0.96, 1.00)	0.65 (0.51, 0.78)	1.00 (1.00, 1.00)	1.00 (1.00, 1.00)	0.95 (0.89, 0.99)	0.86 (0.71, 0.96)
Buyse307	Glas78	0.80 (0.69, 0.89)	0.74 (0.62, 0.85)	0.49 (0.36, 0.63)	0.71 (0.59, 0.82)	0.76 (0.64, 0.87)	0.82 (0.72, 0.91)	0.82 (0.72, 0.90)
	Glas84	0.71 (0.56, 0.83)	0.57 (0.38, 0.75)	0.64 (0.48, 0.78)	0.61 (0.46, 0.76)	0.57 (0.39, 0.73)	0.68 (0.52, 0.83)	0.56 (0.41, 0.71)
	Buyse307	0.76 (0.69, 0.82)	0.88 (0.83, 0.91)	0.55 (0.46, 0.63)	0.91 (0.88, 0.94)	0.92 (0.87, 0.96)	0.82 (0.76, 0.87)	0.82 (0.75, 0.87)

AUC, area under the receiver operating characteristic curve; PW, pairwise; SW, stepwise; MM, min–max; MVN, multivariate normal; LR, logistic regression; LASSO, Least Absolute Shrinkage and Selection Operator.

The cases using re-substitution are italicized.