Explainable Interictal Epileptiform Discharge Detection Method Based on Scalp EEG and Retrieval-Augmented Generation

TL;DR

This paper introduces IED-RAG, an explainable multimodal framework combining EEG analysis and retrieval-augmented generation to improve interictal epileptiform discharge detection and report interpretability.

Contribution

It presents a novel dual-encoder approach with contrastive learning and retrieval-augmented report generation, enhancing interpretability and diagnostic accuracy over traditional methods.

Findings

Achieved 89.17% accuracy on private dataset

Attained 64.14 BLEU score on public dataset

Enhanced interpretability through explicit evidence retrieval

Abstract

The detection of interictal epileptiform discharge (IED) is crucial for the diagnosis of epilepsy, but automated methods often lack interpretability. This study proposes IED-RAG, an explainable multimodal framework for joint IED detection and report generation. Our approach employs a dual-encoder to extract electrophysiological and semantic features, aligned via contrastive learning in a shared EEG-text embedding space. During inference, clinically relevant EEG-text pairs are retrieved from a vector database as explicit evidence to condition a large language model (LLM) for the generation of evidence-based reports. Evaluated on a private dataset from Wuhan Children's Hospital and the public TUH EEG Events Corpus (TUEV), the framework achieved balanced accuracies of 89.17\% and 71.38\%, with BLEU scores of 89.61\% and 64.14\%, respectively. The results demonstrate that retrieval of explicit evidence enhances both diagnostic performance and clinical interpretability compared to standard black-box methods.