Steady-State Visual-Evoked EEG Dataset for Visual Function Assessment via Biomarker Extraction

Abstract

Amblyopia and intermittent exotropia (IXT) are prevalent pediatric visual impairments characterized by deficits in cortical visual processing. Understanding the underlying neurophysiological mechanisms and tracking neural recovery requires high–quality, objective data, yet open–access EEG datasets specifically designed for these pediatric populations—particularly those with a longitudinal dimension—remain scarce. Here, we present the steady–state visual–evoked EEG (S2VEEG) dataset, a 64–channel electroencephalography (EEG) dataset collected from pediatric participants, including amblyopia, IXT, and healthy controls. The S2VEEG dataset uses a multimodal experimental paradigm comprising resting–state recordings, transient Visual Evoked Potentials (VEP), and Steady–State Visual Evoked Potentials (SSVEP). The dataset employs a longitudinal design, capturing neural activity both at baseline and following therapeutic interventions (perceptual learning for amblyopia and strabismus surgery for IXT). For technical validation, differential entropy (DE) and small–worldness properties are extracted as features and analyzed using Support Vector Machine (SVM), Residual Graph Convolutional Broad Network (RGCB), and Emotion Transformer (EmT) classifiers. The classification performance suggests that the recorded EEG signals contain discriminative electrophysiological information across visual function states, thereby supporting the usability of the S2VEEG dataset as candidate discriminative measures for methodological development and exploratory analyses. These results are intended as a technical validation of data quality and feature separability, while this resource provides a valuable platform for future studies investigating brain–eye interactions, treatment–induced neuroplasticity, and the development of objective biomarkers for monitoring visual function recovery.