Graph-based learning for sleep microarchitecture: a hybrid graph autoencoder and graph attention network approach

Amala Ann Kurisinkal Augustine; Vaidhehi

doi:10.18203/2320-6012.ijrms20253587

Authors

Amala Ann Kurisinkal Augustine Department of Data Science, CHRIST (Deemed to be) University, Bengaluru, Karnataka, India
Vaidhehi Department of Data Science, CHRIST (Deemed to be) University, Bengaluru, Karnataka, India

DOI:

https://doi.org/10.18203/2320-6012.ijrms20253587

Keywords:

Polysomnography, Paediatrics, Graph attention networks, Genetic disorders, Sleep microarchitecture

Abstract

Background: Sleep plays a vital role in cognitive function, memory consolidation, and overall neurological health. Analysis of sleep microarchitecture including features such as sleep spindles, K-complexes, slow waves, and EEG bandpower components provides critical insights into sleep disorders and genetic diseases. However, the complex interactions between sleep architecture and underlying genetic abnormalities remain underexplored. This study aims to investigate these interactions by leveraging advanced graph-based deep learning methods to uncover hidden relationships within EEG signals.

Methods: We developed a graph autoencoder (GAE) combined with a Graph attention network (GAT) to analyze polysomnography (PSG) data from the National Children's Hospital (NCH) dataset. EEG epochs were modelled as graph nodes, while edges were constructed based on bandpower similarity between epochs, enabling dynamic representation of sleep activity. The GAE learned latent embeddings that capture subtle patterns in sleep microarchitecture, and the GAT applied attention mechanisms to classify and interpret relationships between EEG events, sleep disorders, and genetic abnormalities. Three core analyses were conducted: (1) identifying differences in sleep microarchitecture across sleep disorders, (2) detecting EEG event changes associated with genetic disorders, and (3) exploring shared patterns linking sleep and genetic abnormalities.

Results: The model achieved classification accuracies of 92.4%, 91.2%, and 88.6% across the three tasks, respectively. The approach successfully identified distinct EEG event patterns in subjects with co-occurring sleep disorders.

Conclusions: This work presents a scalable, automated, and interpretable framework for analyzing the interplay between sleep microarchitecture, sleep disorders, and genetic disorders.

Metrics

Metrics Loading ...

References

Wara TU, Hossain Fahad A, Shankar Das A, Mehedi Hasan Shawon M. A systematic review and meta-analysis on sleep stage classification and sleep disorder detection using artificial intelligence. arXiv e-prints, arXiv-2405; 2024. DOI: https://doi.org/10.1016/j.heliyon.2025.e43576

Ahadian P, Xu W, Wang S, Guan Q. Adopting Trustworthy AI for Sleep Disorder Prediction: Deep Time Series Analysis with Temporal Attention Mechanism and Counterfactual Explanations. In 2024 IEEE International Conference on Big Data (BigData) (pp. 4621-4626). IEEE.; 2024. DOI: https://doi.org/10.1109/BigData62323.2024.10825687

Yang H, Lu S, Yang L. Clinical prediction models for the early diagnosis of obstructive sleep apnea in stroke patients: a systematic review. Systematic Reviews. 2024;13(1):38. DOI: https://doi.org/10.1186/s13643-024-02449-9

El-Kenawy ESM, Ibrahim A, Abdelhamid AA, Khodadadi N, Abualigah L, et al. Predicting sleep disorders: leveraging sleep health and lifestyle data with dipper throated optimization algorithm for feature selection and logistic regression for classification. Computational Journal of Mathematical and Statistical Sciences. 2024;3(2):341-58. DOI: https://doi.org/10.21608/cjmss.2024.290167.1053

Olivera-López C, Ortega-Robles D, Salvador-Cruz J, Jimenez-Genchi A. 0660 Association between sleep architecture and attention and memory abnormalities in patients with insomnia disorder comorbid with major depression. Sleep. 2022;45(Supplement_1):A290-A290. DOI: https://doi.org/10.1093/sleep/zsac079.656

Parker J, Vakulin A, Melaku Y, Wittert G, Martin S, D'Rozario A, et al. O003 Longitudinal associations of obstructive sleep apnea and sleep macroarchitecture with future cognitive function in middle-aged and older men from a community-based cohort study. Sleep Advances. 2022;3(Supplement_1):A1-A2. DOI: https://doi.org/10.1093/sleepadvances/zpac029.002

Zheng K, Little D, Laberinto K, Jaiyeola AJ, Sadeghi K, Tjiptarto N, et al. 0907 Macro and microarchitectural sleep features in Alzheimer’s dementia and mild cognitive impairment in a large clinical cohort. Sleep. 2023;46(Supplement_1):A399-A400. DOI: https://doi.org/10.1093/sleep/zsad077.0907

Ämmälä AJ, Urrila AS, Lahtinen A, Santangeli O, Hakkarainen A, Kantojärvi K, et al. Epigenetic dysregulation of genes related to synaptic long-term depression among adolescents with depressive disorder and sleep symptoms. Sleep Medicine. 2019;61:95-103. DOI: https://doi.org/10.1016/j.sleep.2019.01.050

Huebra L, Coelho FM, Filho FMR, Barsottini OG, Pedroso JL. Sleep disorders in hereditary ataxias. Current neurology and Neuroscience Reports. 2019;19:1-10. DOI: https://doi.org/10.1007/s11910-019-0968-1

Abo-Zahhad M, Ahmed SM, Abbas SN. A new EEG acquisition protocol for biometric identification using eye blinking signals. International Journal of Intelligent Systems and Applications. 2015;7(6):48. DOI: https://doi.org/10.5815/ijisa.2015.06.05

Zietsch BP, Hansen JL, Hansell NK, Geffen GM, Martin NG, Wright MJ. Common and specific genetic influences on EEG power bands delta, theta, alpha, and beta. Biological Psychology. 2007;75(2):154-64. DOI: https://doi.org/10.1016/j.biopsycho.2007.01.004

Naxon Labs. Understanding the strategic placement of sensors on EEG devices, 2025. Available at: https://naxonlabs.com/blog/understandingstrategicplacement-sensors-eeg-devices. Accessed on 10 October 2025.

Gu W, Hou J, Gu W. Improving link prediction accuracy of network embedding algorithms via rich node attribute information. Journal of Social Computing. 2023;4(4):326-36. DOI: https://doi.org/10.23919/JSC.2023.0018

Fayyaz H, Strang A, D'Souza NS, Beheshti R. Multimodal Sleep Apnea Detection with Missing or Noisy Modalities. 2024;arXiv preprint arXiv:2402.17788.

Martinez C, Chen ZS. Identification of atypical sleep microarchitecture biomarkers in children with autism spectrum disorder. Frontiers in Psychiatry. 2023;14:1115374. DOI: https://doi.org/10.3389/fpsyt.2023.1115374

Deng G, Niu M, Luo Y, Rao S, Sun J, Jiang X, et al. LPSGM: A Unified Flexible Large PSG Model for Sleep Staging and Mental Disorder Diagnosis. medRxiv, 2024;2024-12. DOI: https://doi.org/10.1101/2024.12.11.24318815

Zhang GQ, Cui L, Mueller R, Tao S, Kim M, Rueschman M, et al. The National Sleep Research Resource: towards a sleep data commons. J Am Med Inform Assoc. 2018;25(10):1351-8. DOI: https://doi.org/10.1093/jamia/ocy064

Genome. Genome-Wide Association Studies (GWAS), 2025. Available at: https://www.genome.gov/genetics-glossary/Genome-Wide-Association-Studies-GWAS. Accessed on 10 October 2025.

Sehgal A, Mignot E. Genetics of sleep and sleep disorders. Cell. 2011;146(2):194-207. DOI: https://doi.org/10.1016/j.cell.2011.07.004

Rodenbeck A, Binder R, Geisler P, Danker‐Hopfe H, Lund R, Raschke & Schulz H. A review of sleep EEG patterns. Part I: a compilation of amended rules for their visual recognition according to Rechtschaffen and Kales. Somnologie. 2006;10(4):159-75. DOI: https://doi.org/10.1111/j.1439-054X.2006.00101.x

Hussain I, Hossain MA, Jany R, Bari MA., Uddin M, Kamal ARM, et al. Quantitative evaluation of EEG-biomarkers for prediction of sleep stages. Sensors, 2022;22(8):3079. DOI: https://doi.org/10.3390/s22083079

Klepl D, Wu M, He F. Graph neural network-based eeg classification: A survey. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2024;32:493-503. DOI: https://doi.org/10.1109/TNSRE.2024.3355750