A novel ST-GCN model based on homologous microstate for subject-independent seizure prediction

• Published in: Scientific reports Vol. 15; no. 1; pp. 22852 - 13
• Main Authors: Shi, Wei, Shi, Yi, Chen, Fangni, Zhang, Lei, Wan, Jian
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 02.07.2025; Nature Portfolio
• Subjects: 692/699/375; 692/699/375/178; Electroencephalography - methods; Homologous microstate dynamic attributes; Humanities and Social Sciences; Humans; multidisciplinary; Neural Networks, Computer; Online deployment stage; Science; Science (multidisciplinary); Seizures - diagnosis; Seizures - physiopathology; ST-GCN; Subject-independent seizure prediction; ST-GCN; Subject-independent seizure prediction; Online deployment stage; Homologous microstate dynamic attributes
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-06123-5

Due to the lack of validated universal seizure markers, population-level prediction methods often exhibit limited performance. This study proposes homologous microstate dynamic attributes as a generalized, subject-independent seizure marker. Homologous microstate dynamic attributes were extracted using a novel spatiotemporal graph convolutional network (ST-GCN) model for subject-independent seizure prediction. An online deployment stage was introduced to validate the model’s clinical applicability. The online deployment stage demonstrated that the model achieved sensitivities of 96.79% and 98.84% on the private dataset and Siena dataset, respectively. The ST-GCN model successfully predicts seizures in a subject-independent manner, demonstrating its potential as a generalized tool for seizure prediction in clinical settings. This study indicates that dynamics within homologous microstates can serve as a universal predictive biomarker for seizures, expanding microstate research beyond transition patterns. It also provides a practical template for clinical seizure prediction models.