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

Table 5 Mean sample performance metrics for neutral—pain faces classification

Metric	Cross validation		Cross-subject validation		Within-subject validation
Metric	Mean	SD	Mean	SD	Mean	SD
Accuracy	0.6132	0.0300	0.5473	0.0501	0.5076	0.0383
AUC	0.6717	0.0396	0.5629	0.0667	0.5241	0.0557
Brier Score	0.2268	0.0073	0.2523	0.0155	0.2594	0.0108
F1 Score	0.5944	0.0505	0.5046	0.1053	0.3942	0.1003
Precision	0.6216	0.0353	0.5585	0.0720	0.5182	0.0834
Recall	0.5788	0.0930	0.4932	0.1804	0.3355	0.1200

Optimal hyperparameters: Number of estimators = 161, Maximum depth = 27, Minimum samples to split = 2, Minimum samples at leaf = 4, Maximum features = log2, Bootstrap = False

ISSN: 1471-2202