2025/04/13 by Tian Feng, Juntong Ni, Feng, Tianning +5 · 2 citations
Computer Science · Neuroscience · #EEG and Brain-Computer Interfaces #FOS: Computer and information sciences #FOS: Electrical engineering #Functional Brain Connectivity Studies #I.2.6 #I.5.1 #Machine Learning (cs.LG) #Machine Learning in Healthcare #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2504.16098
openalex publication_date 2025/04/13 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28
We present SeizureFormer, a Transformer-based model for long-term seizure risk forecasting using interictal epileptiform activity (IEA) surrogate biomarkers and long episode (LE) biomarkers from responsive neurostimulation (RNS) systems. Unlike raw scalp EEG-based models, SeizureFormer leverages structured, clinically relevant features and integrates CNN-based patch embedding, multi-head self-attention, and squeeze-and-excitation blocks to model both short-term dynamics and long-term seizure cycles. Tested across five patients and multiple prediction windows (1 to 14 days), SeizureFormer achieved state-of-the-art performance with mean ROC AUC of 79.44 percent and mean PR AUC of 76.29 percent. Compared to statistical, machine learning, and deep learning baselines, it demonstrates enhanced generalizability and seizure risk forecasting performance under class imbalance. This work supports future clinical integration of interpretable and robust seizure forecasting tools for personalized epilepsy management.