Novel neuroelectrophysiological age index associated with imaging features of brain aging and sleep disorders

• Published in: NeuroImage (Orlando, Fla.) Vol. 264; p. 119753
• Main Authors: Yook, Soonhyun, Park, Hea Ree, Park, Claire, Park, Gilsoon, Lim, Diane C., Kim, Jinyoung, Joo, Eun Yeon, Kim, Hosung
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2022; Elsevier Limited; Elsevier
• Subjects: Age; Aging; Aging - physiology; Airway management; Apnea; Biomarker; Biomarkers; Brain - physiology; Brain age; Datasets; Deep learning; Disease; EEG; Electroencephalography - methods; Humans; Insomnia; Neural networks; Neuroelectrophysiology; Neuroimaging; Prediction models; Sleep - physiology; Sleep apnea; Sleep disorder; Sleep disorders; Sleep EEG; Sleep Wake Disorders - diagnostic imaging; Wavelet transforms; Deep learning; Sleep disorder; Sleep EEG; Neuroelectrophysiology; Biomarker; Brain age
• ISSN: 1053-8119; 1095-9572
• DOI: 10.1016/j.neuroimage.2022.119753

•We proposed a sleep EEG-based brain age prediction model using convolutional neural networks.•A higher BAI is associated with cortical thinning in various functional areas.•A higher BAI for sleep disorder groups compared to healthy sleepers, as well as significant differences in the spectral pattern of EEG among different sleep disorders (lower power in slow and θ waves for sleep apnea vs. higher power in β and σ for insomnia).•This result suggested that sleep EEG-BAI may reflect not only neural electroactivity responding to the same night sleep quality/depth but also neuroelectrophysiological changes in relation to chronic neural loss and altered brain connectivity.•Suggested EEG-based BAI can be used to phenotype sleep disorders as well as screen for sleep abnormalities that potentially harm brain health. Sleep architecture and microstructures alter with aging and sleep disorder-led accelerated aging. We proposed a sleep EEG based brain age prediction model using convolutional neural networks. We then associated the estimated brain age index with brain structural aging features, sleep disorders and various sleep parameters. Our model also showed a higher BAI (predicted brain age minus chronological age) is associated with cortical thinning in various functional areas. We found a higher BAI for sleep disorder groups compared to healthy sleepers, as well as significant differences in the spectral pattern of EEG among different sleep disorders (lower power in slow and ϑ waves for sleep apnea vs. higher power in β and σ for insomnia), suggesting sleep disorder-dependent pathomechanisms of aging. Our results demonstrate that the new EEG-BAI can be a biomarker reflecting brain health in normal and various sleep disorder subjects, and may be used to assess treatment efficacy.