Table 2.

Classification performance metrics of independent validation sets. Classification performance metrics of the machine learning classifiers. Classifier metrics are shown at cut-off points according to the maximum Matthews correlation coefficient. AUC, area under the curve; ER, estrogen receptor; PR, progesterone receptor; HER2, human epidermal growth factor receptor 2; PPV, positive predictive value; NPV, negative predictive value; MCC, Matthews correlation coefficient; CI, confidence interval.

		Matthews Correlation Coefficient (MCC) Maximum Operating Point
Receptor Status	AUC [95% CI]	Sensitivity [95% CI]	Specificity [95% CI]	PPV [95% CI]	NPV [95% CI]	Accuracy [95% CI]	MCC [95% CI]
	5-fold cross-validation (n = 412 samples)
ER+	0.82 [0.78; 0.85]	84% [81%; 88%]	68% [65%; 71%]	69% [67%; 72%]	84% [82%; 88%]	76% [73%; 78%]	0.53 [0.49; 0.58]
PR+	0.73 [0.69; 0.77]	59% [56%; 64%]	82% [77%; 85%]	69% [67%; 76%]	74% [70%; 76%]	72% [69%; 75%]	0.42 [0.37; 0.48]
HER2+	0.74 [0.70; 0.78]	61% [57%; 65%]	84% [81%; 88%]	73% [72%; 80%]	76% [74%; 78%]	75% [73%; 76%]	0.47 [0.45; 0.52]