Esmaeil Mohammadi - Institute of Medical Science and Technology, Shahid Beheshti University, Tehran, Iran,Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute,Tehran University of Medical Sciences, Tehran, Iran
Bahram Mohajer - Institute of Medical Science and Technology, Shahid Beheshti University, Tehran, Iran,Non-Communicable Diseases Research Center, Endocrinology and Metabolism Population Sciences Institute,Tehran University of Medical Sciences, Tehran, Iran
Nooshin Abbasi - McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, Montreal, QC, Canada
Habibolah Khazaie - Sleep Disorders Research Center, Kermanshah University of Medical Sciences, Kermanshah, Iran
S Osorio Ricardo - Sleep and Brain Plasticity Centre, Department of Neuroimaging, IOPPN, King
Ivana Rosenzweig - Sleep Disorders Centre, Guy’s and St Thomas’ Hospital, GSTT NHS, London, UK
Mojtaba Zarei - Institute of Medical Science and Technology, Shahid Beheshti University, Tehran, Iran
Masoud Tahmasian - Institute of Medical Science and Technology, Shahid Beheshti University, Tehran, Iran

It is suggested that sleep-disordered breathing (SDB) may contribute to cognitive decline and advanced aging as present in Alzheimer’s diseases (AD)[1]. Hereby we used a machine learning approach to assess the ageing properties of participants brain with history of self-reported SDB.Method A total of 330 participants, matched for age and gender, from Alzheimer’s Disease Neuroimaging Initiative (ADNI), were used. Further, cognitive status of them was taken into account to divide them into AD, mild cognitive impairment (MCI), and healthy controls (HC). Each group was further divided to SDB+ or SDB- based on self-reported history of SDB. As a result, participants were assigned to one of the six groups of study. First, we used conventional automated methods to evaluate the regional gray matter volumes. Next, BrainAge was utilized to estimate each case’s brain age [2]. It has been practically designed based on a separate dataset’s brain images and was trained to correlate the combination of 637 cortical parcels volume to the chronological ages of the six groups of study. A BrainAge score was calculated for each case based on the difference between the chronological and brain ages.ResultsCognitive impairment and advanced age were associated with lower gray matter volume in various regions, particularly in the bilateral temporal lobes. Brain’s age was well predicted from the morphological data in HC and as expected elevated in MCI and particularly AD. However, there was neither a significant difference between regional gray matter volume in any diagnostic group related to the SDB status nor SDB-by-cognitive interaction. Also, we found neither a significant difference in BrainAge score related to SDB nor SDB-by-cognitive status interaction for this measure. Conclusions In summary, SDB seems to not accelerate the ageing process of brain. Also, SDB did not compromise the ageing pattern seen in the AD.