Unsupervised seizure annotation and detection with neural dynamic divergence
Year: 2026
Type: preprint
Abstract: Annotating seizure onset and spread in intracranial EEG is essential for epilepsy surgical planning, yet manual annotation is unreliable and cannot scale to large datasets. We introduce Neural Dynamic Divergence (NDD), an unsupervised framework that detects seizure activity by measuring deviation from patient-specific baseline neural dynamics using autoregressive models. NDD requires no labeled training data and adapts to individual patients, channels, and brain states. Validating against expert consensus annotations from 46 seizures, NDD achieves human-level agreement ( ϕ = 0.58 vs. inter-rater ϕ = 0.64) and outperforms existing algorithms on 1,019 seizures with soft labels (AUROC = 0.87). We demonstrate clinical utility by automatically annotating 2,017 seizures, revealing that seizure spread patterns distinguish epilepsy subtypes and predict surgical outcomes. NDD also generalizes to continuous ICU scalp EEG monitoring (AUROC = 0.77). We provide NDD as an open-source Python package to enable scalable seizure annotation across research centers.
Source: medRxiv
Authors: William K.S. Ojemann, Zhongchuan Xu, Haoer Shi, Katie Walsh, Akash Pattnaik, Nishant Sinha, Sarah Lavelle, Carlos Aguila, Ryan Gallagher, Andrew Revell, Joshua J. LaRocque, Jacob Korzun, Catherine V. Kulick-Soper, Daniel J. Zhou, Peter D. Galer, Saurabh R. Sinha, Russell T. Shinohara, Kathryn A. Davis, Brian Litt, Erin C. Conrad
Institution: University of Pennsylvania
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7129494215