Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms

TL;DR

This paper introduces a deep residual neural network approach for automatic sleep stage classification using raw polysomnographic signals, achieving high accuracy and outperforming previous methods.

Contribution

The study presents a novel deep residual network architecture trained on raw polysomnogram data for sleep staging, demonstrating improved accuracy over prior models.

Findings

Achieved 84.1% accuracy in sleep stage classification.

Improved Cohen's kappa to 0.746 compared to previous methods.

Most classification errors occurred in non-REM stages 1 and 3.

Abstract

We have developed an automatic sleep stage classification algorithm based on deep residual neural networks and raw polysomnogram signals. Briefly, the raw data is passed through 50 convolutional layers before subsequent classification into one of five sleep stages. Three model configurations were trained on 1850 polysomnogram recordings and subsequently tested on 230 independent recordings. Our best performing model yielded an accuracy of 84.1% and a Cohen's kappa of 0.746, improving on previous reported results by other groups also using only raw polysomnogram data. Most errors were made on non-REM stage 1 and 3 decisions, errors likely resulting from the definition of these stages. Further testing on independent cohorts is needed to verify performance for clinical use.