End‐to‐End EEG ‐Based Schizophrenia Detection via Hybrid Temporal–Spatial Dependency Learning

ABSTRACT Electroencephalogram (EEG)‐based schizophrenia (SZ) detection is promising because EEG provides a noninvasive characterisation of abnormal brain activity. However, many existing methods still depend on handcrafted features or insufficiently model the coupled temporal–spatial dependencies in EEG signals. Moreover, a considerable number of prior studies are evaluated on only a single dataset, leaving their robustness across heterogeneous acquisition conditions unclear. To address these issues, we propose a novel end‐to‐end framework, termed Hybrid Temporal–Spatial Dependency Learning Network (HTSD), for automatic SZ detection directly from raw EEG signals. HTSD integrates convolution‐based temporal encoding and transformer‐based spatial dependency learning in a unified architecture. Specifically, a multibranch local temporal encoder is designed to capture diverse short‐range temporal dynamics, while a spatial correlation encoder based on multihead self‐attention explicitly models adaptive interchannel dependencies and long‐range interactions among brain regions. A global temporal encoder is further employed to aggregate high‐level temporal representations for classification. We evaluate HTSD on three public EEG datasets under both segment‐level five‐fold cross‐validation and subject‐level leave‐one‐subject‐out (LOSO) cross‐subject validation. HTSD achieves five‐fold accuracies of 98.03%, 99.51% and 97.12% and LOSO accuracies of 93.87%, 96.43% and 91.74% on the three datasets, respectively. These results indicate that HTSD provides accurate SZ detection while retaining promising robustness under subject‐independent evaluation.