Machine learning and EEG can classify passive viewing of discrete categories of visual stimuli but not the observation of pain

Table 3 Mean sample performance metrics for scenes—faces classification

Metric	Cross validation		Cross-subject validation		Within-subject validation
Metric	Mean	SD	Mean	SD	Mean	SD
Accuracy	0.7456	0.0459	0.6415	0.0634	0.6880	0.0792
AUC	0.8189	0.0406	0.7088	0.0753	0.7558	0.0922
Brier Score	0.1707	0.0164	0.2152	0.0253	0.1970	0.0358
F1 Score	0.7854	0.0299	0.6972	0.0460	0.7388	0.0557
Precision	0.6924	0.0495	0.6129	0.0583	0.6597	0.0959
Recall	0.9111	0.0240	0.8207	0.0890	0.8560	0.0802

Optimal hyperparameters: Number of estimators = 766, Maximum depth = 53, Minimum samples to split = 9, Minimum samples at leaf = 2, Maximum features = sqrt, Bootstrap = False

ISSN: 1471-2202