Table 5. Prediction accuracues using diffusion based fuctional profiles and annotation based functional profiles quantified by AUC-ROC.

The following table displays the AUC estimates of the 7 independent classifiers trained with two different feature sets (diffusion-based functional activity and annotation-based functional activity) for each clinical indicator.

Clinical Indicator	AUC—Diffusion	AUC–Annotation (Control)	P-value (AUC-Diffusion > AUC-Control)
Basal	0.87 (95% CI = 0.867–0.882)	0.81 (95% CI = 0.803–0.823)	<2.2e-16
Her2	0.73 (95% CI = 0.72–0.746)	0.65 (95% CI = 0.644–0.67)	<2.2e-16
Luminal A	0.74 (95% CI = 0.741–0.756)	0.73 (95% CI = 0.722–0.739)	<2.2e-16
Luminal B	0.73 (95% CI = 0.727–0.742)	0.75 (95% CI = 0.731–0.748)	1
Normal	0. 87(95% CI = 0.866–0.882)	0.81 (95% CI = 0.803–0.823)	<2.2e-16
ER+	0.88 (95% CI = 0.882–0.895)	0.81 (95% CI = 0.811–0.828)	<2.2e-16
PR+	0.74 (95% CI = 0.736–0.75)	0.72 (95% CI = 0.719–0.735)	<2.2e-16