1. Deep Learning–Based Assessment of Brain Connectivity Related to Obstructive Sleep Apnea and Daytime Sleepiness
- Author
-
Lee MH, Lee SK, Thomas RJ, Yoon JE, Yun CH, and Shin C
- Subjects
convolutional neural network ,obstructive sleep apnea ,daytime sleepiness ,diffusion tensor imaging ,structural brain network ,Psychiatry ,RC435-571 ,Neurophysiology and neuropsychology ,QP351-495 - Abstract
Min-Hee Lee,1 Seung Ku Lee,1 Robert J Thomas,2 Jee-Eun Yoon,3 Chang-Ho Yun,4,* Chol Shin1,5,* 1Institute of Human Genomic Study, College of Medicine, Korea University Ansan Hospital, Ansan, Republic of Korea; 2Department of Medicine, Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA; 3Department of Neurology, Uijeongbu Eulji Medical Center, Uijeongbu, Republic of Korea; 4Department of Neurology, Seoul National University Bundang Hospital, Seongnam, Republic of Korea; 5Department of Pulmonary Sleep and Critical Care Medicine Disorder Center, College of Medicine, Korea University, Ansan, Republic of Korea*These authors contributed equally to this workCorrespondence: Chang-Ho YunDepartment of Neurology, Bundang Clinical Neuroscience Institute, Seoul National University Bundang Hospital, 82 Gumi-ro 173beon-gil, Bundang-gu, Seongnam, 13620, Republic of KoreaTel +82 31 787 7469Fax +82 31 787 4059Email ych333@gmail.comChol ShinDivision of Pulmonary, Sleep, and Critical Care Medicine, Department of Internal Medicine, Korea University Ansan Hospital and Institute of Human Genomic Study, Korea University Ansan Hospital, 516, Gojan-1-dong, Danwon-gu, Ansan, Gyeonggi-do, 15355, Republic of KoreaTel +82 31 412 5541Fax +82 31 412 5604Email chol-shin@korea.ac.krPurpose: Obstructive sleep apnea (OSA) is associated with altered pairwise connections between brain regions, which might explain cognitive impairment and daytime sleepiness. By adopting a deep learning method, we investigated brain connectivity related to the severity of OSA and daytime sleepiness.Patients and Methods: A cross-sectional design applied a deep learning model on structural brain networks obtained from 553 subjects (age, 59.2 ± 7.4 years; men, 35.6%). The model performance was evaluated with the Pearson’s correlation coefficient (R) and probability of absolute error less than standard deviation (PAE
- Published
- 2021