ProductGraphSleepNet: Sleep staging using product spatio-temporal graph learning with attentive temporal aggregation

• Published in: Neural networks Vol. 164; pp. 667 - 680
• Main Authors: Einizade, Aref, Nasiri, Samaneh, Sardouie, Sepideh Hajipour, Clifford, Gari D.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.07.2023
• Subjects: Brain connectivity; Databases, Factual; Electroencephalography; Graph convolutional neural (GCN) network; Graph signal processing (GSP); Healthy Volunteers; Humans; Neural Networks, Computer; Product graph learning (PGL); Sleep; Sleep Stages; Sleep staging; Graph convolutional neural (GCN) network; Product graph learning (PGL); Brain connectivity; Graph signal processing (GSP); Sleep staging
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2023.05.016

The classification of sleep stages plays a crucial role in understanding and diagnosing sleep pathophysiology. Sleep stage scoring relies heavily on visual inspection by an expert, which is a time-consuming and subjective procedure. Recently, deep learning neural network approaches have been leveraged to develop a generalized automated sleep staging and account for shifts in distributions that may be caused by inherent inter/intra-subject variability, heterogeneity across datasets, and different recording environments. However, these networks (mostly) ignore the connections among brain regions and disregard modeling the connections between temporally adjacent sleep epochs. To address these issues, this work proposes an adaptive product graph learning-based graph convolutional network, named ProductGraphSleepNet, for learning joint spatio-temporal graphs along with a bidirectional gated recurrent unit and a modified graph attention network to capture the attentive dynamics of sleep stage transitions. Evaluation on two public databases: the Montreal Archive of Sleep Studies (MASS) SS3; and the SleepEDF, which contain full night polysomnography recordings of 62 and 20 healthy subjects, respectively, demonstrates performance comparable to the state-of-the-art (Accuracy: 0.867;0.838, F1-score: 0.818;0.774 and Kappa: 0.802;0.775, on each database respectively). More importantly, the proposed network makes it possible for clinicians to comprehend and interpret the learned spatial and temporal connectivity graphs for sleep stages.