Computational Analysis of EEG Responses to Anxiogenic Stimuli Using Machine Learning Algorithms

Anxiety disorders are commonly assessed using instruments such as HAM-A and GAD-7. These tools rely on patient self-report and clinician interpretation, which may introduce variability. This study proposes an EEG-based computational framework for estimating anxiety levels using portable EEG recordings from the Unicorn Hybrid Black device. These data were harmonized with the DASPS public dataset to ensure methodological consistency. After standardized preprocessing and multi-domain feature extraction, three classifiers—logistic regression, multilayer perceptron (MLP), and k-nearest neighbors (KNN)—were trained and evaluated. Logistic regression achieved 81.25% accuracy (F1 = 0.8247), while the MLP reached 87.5% accuracy (F1 = 0.859). ROC analysis (AUC = 0.98 for logistic regression and 0.92 for MLP) confirmed that both classifiers reliably separated non-anxious from moderate participants. Severe anxiety could not be classified, reflecting the extremely limited number of participants in this category. Predicted anxiety probabilities showed significant correlations with HAM-A scores (r up to 0.71, p < 0.01), supporting the external validity of the proposed approach.