Diffusion Model-Based Multi-Channel EEG Representation and Forecasting for Early Epileptic Seizure Warning.

Multi-channel electroencephalogram (EEG) signals are essentially spatio-temporal data collected from different regions of the brain. The representation and modeling of their spatio-temporal information are critical for EEG analysis, particularly in the diagnosis and assessment of neurological diseases such as epilepsy. Existing methods often rely on the representation of single-channel signals, overlooking the inherent spatio-temporal correlations within EEG data. Moreover, most deep learning-based EEG algorithms focus only on classifying and predicting the current signal states, with limited attention paid to forecasting the future development of EEG signals for early warning of disease events such as epileptic seizures. To address these limitations, we introduce EEG-DIF, a spatio-temporal representation and forecasting framework based on generative diffusion models. EEG-DIF reformulates the multi-channel signal forecasting task as a signal image completion problem and learns the temporal development relationships among arbitrary numbers of EEG channels through the processes of noise addition and recovery, enabling future trend generation and early warning based on multi-channel EEG data. Experimental results on the publicly available Siena Scalp EEG Database demonstrate that EEG-DIF can simultaneously predict the future dynamics of multi-channel EEG signals with a single model. The generated signals can be directly used for early seizure warning, achieving an average accuracy of 0.89. In summary, EEG-DIF provides a novel framework to represent spatio-temporal multi-channel biomedical signals, introduces an effective method for the early warning of epileptic seizures, and highlights the potential of generative models to optimize the clinical diagnostic workflows. The codes are available online at https://github.com/JZK00/EEG-DIF .