Skip to main content
. 2019 Jan 24;10(2):879–891. doi: 10.1364/BOE.10.000879

Table 1. Quantitative analysis of the constructed modelsa.

Model ROC-AUC Accuracy(%) Sensitivity(%) Specificity(%)
ED 0.75 70 70 70
SAM 0.66 72.5 70 75
Logi 0.72 72.5 65 80
SVM 0.76 72.5 75 70
MLP 0.73 72.5 75 70
a

using 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 psoriasis on the scalp (total number of patients = 40); ROC-AUC, area under the receiver-operating characteristic curve