Deep Convolutional Neural Networks for Interpretable Analysis of EEG Sleep Stage Scoring

TL;DR

This paper introduces a deep learning approach using multitaper spectral analysis to generate interpretable EEG images for automatic sleep stage classification, achieving competitive results and enhancing interpretability.

Contribution

It presents a novel combination of spectral analysis and deep convolutional networks for interpretable sleep stage scoring, with transfer learning for new patient classification.

Findings

Achieved state-of-the-art accuracy on a public sleep dataset.

Provided a framework for visual interpretation of sleep stage classification.

Demonstrated effective transfer learning for unseen patients.

Abstract

Sleep studies are important for diagnosing sleep disorders such as insomnia, narcolepsy or sleep apnea. They rely on manual scoring of sleep stages from raw polisomnography signals, which is a tedious visual task requiring the workload of highly trained professionals. Consequently, research efforts to purse for an automatic stage scoring based on machine learning techniques have been carried out over the last years. In this work, we resort to multitaper spectral analysis to create visually interpretable images of sleep patterns from EEG signals as inputs to a deep convolutional network trained to solve visual recognition tasks. As a working example of transfer learning, a system able to accurately classify sleep stages in new unseen patients is presented. Evaluations in a widely-used publicly available dataset favourably compare to state-of-the-art results, while providing a framework for visual interpretation of outcomes.