Table 5 Mean and standard deviation of classification performance metrics across 5-fold cross-validation.

From: Non-invasive detection of choroidal melanoma via tear-derived protein corona on gold nanoparticles: a machine learning approach

Model

Accuracy

ROC AUC

F1 Score

Recall

Precision

DNN

0.943 ± 0.004

0.988 ± 0.001

0.945 ± 0.003

0.969 ± 0.005

0.922 ± 0.003

SVM

0.943 ± 0.002

0.986 ± 0.001

0.945 ± 0.002

0.968 ± 0.003

0.922 ± 0.004

DT

0.933 ± 0.004

0.933 ± 0.004

0.933 ± 0.004

0.931 ± 0.005

0.934 ± 0.007

RF

0.959 ± 0.003

0.993 ± 0.000

0.959 ± 0.003

0.975 ± 0.002

0.944 ± 0.005

Back to article page