Seizure onset zone (SOZ) identification using effective brain connectivity of epileptogenic networks.
Sai Sanjay BalajiKeshab K ParhiPublished in: Journal of neural engineering (2024)
The centrality features achieve high accuracies exceeding 90% in distinguishing SOZ electrodes from non-SOZ electrodes. Notably, a sparse graph representation with just ten features and simple machine learning models effectively achieves such performance. The study identifies
FD-CCM centrality measures as particularly significant, with a mean AUC of 0.93, outperforming prior literature. The FD-CCM-based graph modeling also highlights elevated centrality measures among SOZ electrodes, emphasizing heightened activity relative to non-SOZ electrodes during ictogenesis.
Significance: This research not only underscores the efficacy of automated SOZ identification but also illuminates the potential of specific EC measures in enhancing discriminative power within the context of epilepsy research.
Keyphrases
- machine learning
- reduced graphene oxide
- carbon nanotubes
- solid state
- neural network
- resting state
- white matter
- deep learning
- systematic review
- convolutional neural network
- genome wide
- high throughput
- gold nanoparticles
- bioinformatics analysis
- artificial intelligence
- big data
- gene expression
- risk assessment
- climate change
- temporal lobe epilepsy
- human health
- blood brain barrier
- dna methylation
- cerebral ischemia