Table 3. Quantitative analysis of the constructed model for seborrheic dermatitis versus normal skin^c.

Model	ROC-AUC	Accuracy(%)	Sensitivity(%)	Specificity(%)
ED	0.96	90	95	85
SAM	1.00	100	100	100
Logi	0.99	97.5	95	100
SVM	0.99	97.5	95	100
MLP	0.99	95	90	100

^cusing the Euclidean distance (ED), spectral angle mapper (SAM), logistic regression (Logi), support vector machine (SVM), and multilayer perceptron (MLP) with reference spectral signatures in the discrimination between seborrheic dermatitis and normal skin on the scalp (total number of patients = 40, number of patients with seborrheic dermatitis = 20, and number of normal subjects = 20). ROC-AUC, area under the receiver-operating characteristic curve