LERD: Latent Event-Relational Dynamics for Neurodegenerative Classification

TL;DR

This paper introduces LERD, a Bayesian model that infers latent neural events and their relationships from EEG data to improve Alzheimer's disease diagnosis and understanding of brain dynamics.

Contribution

LERD is the first end-to-end Bayesian electrophysiological model that explicitly captures neural event-relational dynamics from EEG without annotations.

Findings

LERD outperforms baseline methods on synthetic and real EEG data.

LERD provides physiology-aligned latent representations.

LERD offers theoretical guarantees for training stability.

Abstract

Alzheimer's disease (AD) alters brain electrophysiology and disrupts multichannel EEG dynamics, making accurate and clinically useful EEG-based diagnosis increasingly important for screening and disease monitoring. However, many existing approaches rely on black-box classifiers and do not explicitly model the underlying dynamics that generate observed signals. To address these limitations, we propose LERD, an end-to-end Bayesian electrophysiological neural dynamical system that infers latent neural events and their relational structure directly from multichannel EEG without event or interaction annotations. LERD combines a continuous-time event inference module with a stochastic event-generation process to capture flexible temporal patterns, while incorporating an electrophysiology-inspired dynamical prior to guide learning in a principled way. We further provide theoretical analysis that yields a tractable bound for training and stability guarantees for the inferred relational dynamics. Extensive experiments on synthetic benchmarks and two real-world AD EEG cohorts demonstrate that LERD consistently outperforms strong baselines and yields physiology-aligned latent summaries that help characterize group-level dynamical differences.