8 June 2023 in IEEE Journal of Biomedical and Health Informatics
Automatic sleep stage classification plays an essential role in sleep quality measurement and sleep disorder diagnosis. Although many approaches have been developed, most use only single-channel electroencephalogram signals for classification. Polysomnography (PSG) provides multiple channels of signal recording, enabling the use of the appropriate method to extract and integrate the information from different channels to achieve higher sleep staging performance. We present a transformer encoder-based model, MultiChannelSleepNet, for automatic sleep stage classification with multichannel PSG data, whose architecture is implemented based on the transformer encoder for single-channel feature extraction and multichannel feature fusion. In a single-channel feature extraction block, transformer encoders extract features from time-frequency images of each channel independently. Based on our integration strategy, the feature maps extracted from each channel are fused in the multichannel feature fusion block. Another set of transformer encoders further capture joint features, and a residual connection preserves the original information from each channel in this block. Experimental results on three publicly available datasets demonstrate that our method achieves higher classification performance than state-of-the-art techniques. MultiChannelSleepNet is an efficient method to extract and integrate the information from multichannel PSG data, which facilitates precision sleep staging in clinical applications. Source code is available at https://github.com/yangdai97/MultiChannelSleepNet .
24 December 2025 in Science Translational Medicine
Brain stimulation therapies have been increasingly applied to treat patients with drug-resistant epilepsy or other neuropsychiatric disorders, but identifying effective stimulation targets appropriate for individual patients remains challenging. Using intracranial electrophysiological recordings, we found that fast ripple (FR) activity was tightly correlated with the severity of consciousness impairment during seizures in patients with drug-resistant, consciousness-staged epilepsy. Epileptic network analysis based on FR coincidence across brain regions revealed hubs of ictal FR activity, defined as highly connected nodes, specific to individual patients. A small, exploratory study on eight patients with drug-resistant epilepsy showed that stimulating these hubs reduced FRs, ameliorated consciousness impairments, and reduced seizures during a poststimulation time window of up to 11 days. Moreover, FR hub stimulation showed a lower risk of evoking seizures than stimulating seizure onset zones, a now approved treatment option. These results suggest a potentially safe and effective strategy to alleviate epileptic seizures by stimulating patient-specific FR network hubs.