Sleep Arousal Detection from Polysomnography using the Scattering Transform and Recurrent Neural Networks

TL;DR

This paper introduces a novel method combining the scattering transform and recurrent neural networks to detect sleep arousals from polysomnography data, achieving high accuracy on a challenging dataset.

Contribution

It presents a new deep learning architecture integrating scattering transforms with LSTM networks for improved sleep arousal detection.

Findings

Achieved AUROC of 88.0% on test data

Attained AUPRC of 42.1% on test data

Reduced data dimensionality by eighteen-fold

Abstract

Sleep disorders are implicated in a growing number of health problems. In this paper, we present a signal-processing/machine learning approach to detecting arousals in the multi-channel polysomnographic recordings of the Physionet/CinC Challenge2018 dataset. Methods: Our network architecture consists of two components. Inputs were presented to a Scattering Transform (ST) representation layer which fed a recurrent neural network for sequence learning using three layers of Long Short-Term Memory (LSTM). The STs were calculated for each signal with downsampling parameters chosen to give approximately 1 s time resolution, resulting in an eighteen-fold data reduction. The LSTM layers then operated at this downsampled rate. Results: The proposed approach detected arousal regions on the 10% random sample of the hidden test set with an AUROC of 88.0% and an AUPRC of 42.1%.