Using Explainable AI for EEG-based Reduced Montage Neonatal Seizure Detection

TL;DR

This paper introduces an explainable deep learning model for neonatal seizure detection using reduced EEG channels, aiming to provide accurate, real-time diagnosis with interpretability, especially useful in resource-limited settings.

Contribution

A novel explainable deep learning approach employing convolutional and graph attention layers for neonatal seizure detection with reduced EEG montage.

Findings

Achieved 8.31% improvement in AUC

Achieved 42.86% improvement in recall

Demonstrated real-time interpretability of the model

Abstract

The neonatal period is the most vulnerable time for the development of seizures. Seizures in the immature brain lead to detrimental consequences, therefore require early diagnosis. The gold-standard for neonatal seizure detection currently relies on continuous video-EEG monitoring; which involves recording multi-channel electroencephalogram (EEG) alongside real-time video monitoring within a neonatal intensive care unit (NICU). However, video-EEG monitoring technology requires clinical expertise and is often limited to technologically advanced and resourceful settings. Cost-effective new techniques could help the medical fraternity make an accurate diagnosis and advocate treatment without delay. In this work, a novel explainable deep learning model to automate the neonatal seizure detection process with a reduced EEG montage is proposed, which employs convolutional nets, graph attention layers, and fully connected layers. Beyond its ability to detect seizures in real-time with a reduced montage, this model offers the unique advantage of real-time interpretability. By evaluating the performance on the Zenodo dataset with 10-fold cross-validation, the presented model achieves an absolute improvement of 8.31% and 42.86% in area under curve (AUC) and recall, respectively.