Low-dimensional representation of brain networks for seizure risk forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rico-Aparicio, Steven, Guillemaud, Martin, Longhena, Alice, Navarro, Vincent, Cousyn, Louis, Chavez, Mario
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913848549703680
author Rico-Aparicio, Steven
Guillemaud, Martin
Longhena, Alice
Navarro, Vincent
Cousyn, Louis
Chavez, Mario
author_facet Rico-Aparicio, Steven
Guillemaud, Martin
Longhena, Alice
Navarro, Vincent
Cousyn, Louis
Chavez, Mario
contents Identifying preictal states -- periods during which seizures are more likely to occur -- remains a central challenge in clinical computational neuroscience. In this study, we introduce a novel framework that embeds functional brain connectivity networks, derived from intracranial EEG (iEEG) recordings, into a low-dimensional Euclidean space. This compact representation captures essential topological features of brain dynamics and facilitates the detection of subtle connectivity changes preceding seizures. Using standard machine learning techniques, we define a dimensionless biomarker, $\mathcal{B}$, that discriminates between interictal (seizure-free) and preictal (within 24 hours of seizure) network states. Our method focuses on connectivity patterns among a subset of informative iEEG electrodes, enabling robust classification of brain states across time. We validate our approach using a leave-one-out cross-validation scheme and a pseudo-prospective forecasting strategy, assessing performance with metrics such as F1-score and balanced accuracy. Results show that low-dimensional Euclidean embeddings of iEEG connectivity yield interpretable and predictive markers of preictal activity, offering promising implications for real-time seizure forecasting and individualized therapeutic interventions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Low-dimensional representation of brain networks for seizure risk forecasting
Rico-Aparicio, Steven
Guillemaud, Martin
Longhena, Alice
Navarro, Vincent
Cousyn, Louis
Chavez, Mario
Neurons and Cognition
Data Analysis, Statistics and Probability
Identifying preictal states -- periods during which seizures are more likely to occur -- remains a central challenge in clinical computational neuroscience. In this study, we introduce a novel framework that embeds functional brain connectivity networks, derived from intracranial EEG (iEEG) recordings, into a low-dimensional Euclidean space. This compact representation captures essential topological features of brain dynamics and facilitates the detection of subtle connectivity changes preceding seizures. Using standard machine learning techniques, we define a dimensionless biomarker, $\mathcal{B}$, that discriminates between interictal (seizure-free) and preictal (within 24 hours of seizure) network states. Our method focuses on connectivity patterns among a subset of informative iEEG electrodes, enabling robust classification of brain states across time. We validate our approach using a leave-one-out cross-validation scheme and a pseudo-prospective forecasting strategy, assessing performance with metrics such as F1-score and balanced accuracy. Results show that low-dimensional Euclidean embeddings of iEEG connectivity yield interpretable and predictive markers of preictal activity, offering promising implications for real-time seizure forecasting and individualized therapeutic interventions.
title Low-dimensional representation of brain networks for seizure risk forecasting
topic Neurons and Cognition
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2505.00856