Ssleepnet: a structured sleep network for sleep staging based on sleep apnea severity

Abstract

Sleep stage classification is essential in evaluating sleep quality. Sleep disorders disrupt the periodicity of sleep stages, especially the common obstructive sleep apnea (OSA). Many methods only consider how to effectively extract features from physiological signals to classify sleep stages, ignoring the impact of OSA on sleep staging. We propose a structured sleep staging network (SSleepNet) based on OSA to solve the above problem. This research focused on the effect of sleep apnea patients with different severity on sleep staging performance and how to reduce this effect. Considering that the transfer relationship between sleep stages of OSA subjects is different, SSleepNet learns comprehensive features and transfer relationships to improve the sleep staging performance. First, the network uses the multi-scale feature extraction (MSFE) module to learn rich features. Second, the network uses a structured learning module (SLM) to understand the transfer relationship between sleep stages, reducing the impact of OSA on sleep stages and making the network more universal. We validate the model on two datasets. The experimental results show that the detection accuracy can reach 84.6% on the Sleep-EDF-2013 dataset. The detection accuracy decreased slightly with the increase of OSA severity on the Sleep Heart Health Study (SHHS) dataset. The accuracy of healthy subjects to severe OSA subjects ranged from 79.8 to 78.4%, with a difference of only 1.4%. It shows that the SSleepNet can perform better sleep staging for healthy and OSA subjects.