• Citer

Brain Connectivity for the diagnosis of Epileptic Encephalopathy with Spike Wave Activation in Sleep (EE-SWAS) syndrome*

par Cottin, Lise ;Van Gyseghem, Pauline;Sclavont, Zoé Alice J ;Aeby, Alec ;Gaspard, Nicolas ;Nonclercq, Antoine
Référence (14-17 July, 2025: Copenhagen, Denmark), Proceedings of the 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Publication Publié, 2025-07

Publication dans des actes

• Accès en ligne
• Détails
• Contenu
• Statistiques

Résumé :

This diagnostic accuracy study demonstrates the potential of traditional feature-based and brain connectivity indicators, in sleep and awake electroencephalographic (EEG) recordings, to differentiate patients with epileptic encephalopathy with spike-wave activation in sleep (EE-SWAS) from those without neurocognitive impairment along the spectrum of Self-Limited Focal Epilepsy with Centro-Temporal Spikes (SeLECTS). Both types of indicators were highly effective, with the spike-wave index in sleep EEG achieving the best univariate performance (AUC-ROC: 94.51%). Connectivity features showed significant discriminatory power, with clustering coefficient, strength, and characteristic path length achieving AUC-ROC values exceeding 90%, in awake EEG recordings. Combining feature-based and connectivity indicators in multivariate analysis further improved classification accuracy, reaching a top AUC-ROC of 96.60%. These findings show that brain connectivity is a promising biomarker for EE-SWAS, complementing traditional EEG approaches. It enhances diagnostic capabilities and offers valuable insights into understanding the connectivity mechanisms underlying neurocognitive regression in SeLECTS.