Table 4.

Diagnostic performance of deep convolutional neural network model for differentiating luminal A and non-luminal A subtypes based on patient age in the main cohort.

Experiment	Model	AUC (%)	ACC (%)	SEN (%)	SPC (%)	YI (%)
Age ≤ 50	EfficientNet-B0	58.1	46.4	35.7	92.3	28.0
	DenseNet-121	59.6	53.6	48.2	76.9	25.1
	VGGNet-19	57.4	53.6	48.2	76.9	25.1
Age > 50	EfficientNet-B0	75.2	83.3	90.0	62.5	54.6
	DenseNet-121	77.6	83.3	89.0	65.6	54.6
	VGGNet-19	72.7	81.8	88.0	62.5	50.5

AUC, area under the curve; ACC, accuracy; SEN, sensitivity; SPC, specificity; YI, Youden’s index.