Canonical Tail Dependence for Soft Extremal Clustering of Multichannel Brain Signals

2025-12-06

AI Summary

Modeling tail dependence in multichannel EEG signals during extreme neonatal brain events—such as neonatal seizures—remains challenging. To address this, we propose Tail-dependent Canonical Correlation Analysis (TCCA) and the Tail-dependent Pairwise Dependence Matrix (TPDM), the first framework to identify the critical EEG channels driving maximal tail dependence between two cortical regions. Our method builds a frequency-domain tail-dependence model grounded in extreme value theory and integrates it within the canonical correlation analysis framework. We further design an efficient TPDM estimator enabling soft clustering of multichannel EEG. Unlike conventional connectivity approaches—which fail to pinpoint discriminative channels—TCCA/TPDM significantly improves detection accuracy of extreme events in neonatal EEG, effectively distinguishing ictal from non-ictal states. This advances precision epilepsy diagnosis and dynamic brain-state characterization.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Security and Privacy: Large-scale security measurements

Abstract

We develop a novel characterization of extremal dependence between two cortical regions of the brain when its signals display extremely large amplitudes. We show that connectivity in the tails of the distribution reveals unique features of extreme events (e.g., seizures) that can help to identify their occurrence. Numerous studies have established that connectivity-based features are effective for discriminating brain states. Here, we demonstrate the advantage of the proposed approach: that tail connectivity provides additional discriminatory power, enabling more accurate identification of extreme-related events and improved seizure risk management. Common approaches in tail dependence modeling use pairwise summary measures or parametric models. However, these approaches do not identify channels that drive the maximal tail dependence between two groups of signals -- an information that is useful when analyzing electroencephalography of epileptic patients where specific channels are responsible for seizure occurrences. A familiar approach in traditional signal processing is canonical correlation, which we extend to the tails to develop a visualization of extremal channel-contributions. Through the tail pairwise dependence matrix (TPDM), we develop a computationally-efficient estimator for our canonical tail dependence measure. Our method is then used for accurate frequency-based soft clustering of neonates, distinguishing those with seizures from those without.

Problem

• Characterizes extremal dependence in brain signals during extreme events like seizures.
• Identifies channels driving maximal tail dependence for improved seizure risk management.
• Enables accurate frequency-based soft clustering to distinguish neonates with seizures.

Innovation

• Canonical tail dependence extends correlation to extreme events
• Tail pairwise dependence matrix enables efficient estimation
• Soft clustering uses tail connectivity for seizure identification