Adaptive Multi-band Dynamic Functional-Connectivity Graph Attention Network for Parkinson’s Disease Classification from Resting-State EEG
Parkinson’s disease is a progressive neurodegenerative disorder whose reliable diagnosis from non-invasive electrophysiological signals remains challenging because the discriminative information is distributed across spectral bands and across spatially interacting cortical regions. This study proposes an Adaptive Multi-band Dynamic Functional-Connectivity Graph Attention Network (AMD-FCGAT) that represents resting-state electroencephalography as a set of band-resolved brain graphs and learns disease-specific connectivity signatures through attention. For each rhythmic band the framework estimates functional connectivity using the weighted phase-lag index, the phase-locking value and spectral coherence, constructs a sparse electrode graph, and encodes it with a residual multi-head graph attention encoder. An adaptive cross-band gate fuses the band-specific embeddings, and a dynamic temporal self-attention module models the evolution of connectivity across sliding windows before an attention readout produces the classification decision. Experiments on the publicly available University of California San Diego resting-state dataset show that the proposed model attains 97.31 percent accuracy, 97.22 percent F1-score and an area under the curve of 0.998 under a stratified protocol, while a stricter subject-independent evaluation retains 90.97 percent accuracy. Ablation confirms that the cross-band fusion and temporal attention modules contribute the largest gains, and interpretability analysis localises the strongest alterations to central and parietal beta-band synchrony, in agreement with established Parkinsonian neurophysiology. The framework offers an accurate and transparent tool for electroencephalography-based screening.