EEGAgent: A Unified Framework for Automated EEG Analysis Using Large Language Models

TL;DR

EEGAgent is a versatile framework that uses large language models to automate and interpret EEG analysis across multiple tasks, enhancing clinical and research applications.

Contribution

The paper introduces EEGAgent, a novel LLM-based framework that integrates multiple EEG analysis tools for automated, multi-task EEG processing and reporting.

Findings

Supports flexible EEG analysis tasks

Demonstrates effectiveness on public datasets

Enables interpretable EEG analysis

Abstract

Scalable and generalizable analysis of brain activity is essential for advancing both clinical diagnostics and cognitive research. Electroencephalography (EEG), a non-invasive modality with high temporal resolution, has been widely used for brain states analysis. However, most existing EEG models are usually tailored for individual specific tasks, limiting their utility in realistic scenarios where EEG analysis often involves multi-task and continuous reasoning. In this work, we introduce EEGAgent, a general-purpose framework that leverages large language models (LLMs) to schedule and plan multiple tools to automatically complete EEG-related tasks. EEGAgent is capable of performing the key functions: EEG basic information perception, spatiotemporal EEG exploration, EEG event detection, interaction with users, and EEG report generation. To realize these capabilities, we design a toolbox composed of different tools for EEG preprocessing, feature extraction, event detection, etc. These capabilities were evaluated on public datasets, and our EEGAgent can support flexible and interpretable EEG analysis, highlighting its potential for real-world clinical applications.