Validation of EEG‐based brain age index as a biomarker for dementia Biomarkers (non‐neuroimaging) / novel biomarkers

• Published in: Alzheimer's & dementia Vol. 16; no. S4
• Main Authors: Ye, Elissa M, Sun, Haoqi M, Lam, Alice D, Westover, M Brandon
• Format: Journal Article
• Language: English
• Published: 01.12.2020
• ISSN: 1552-5260; 1552-5279
• DOI: 10.1002/alz.044025

Abstract Background Dementia is a growing cause of disability and loss of independence in the elderly, yet remains largely under‐diagnosed. A biomarker for dementia that can identify individuals with or at risk for developing dementia may help close this diagnostic gap. Deviations from the normal aging trajectory, known as Brain Age Index (BAI), have shown potential to serve as biomarkers for cognitive impairment. We aimed to investigate the association between BAI and dementia and determine whether an overnight sleep EEG‐based BAI could serve as a useful biomarker for dementia. We hypothesized that patients with dementia‐related diseases have significantly higher brain age indices than patients without dementia. Method Using a dataset of polysomnograms from 11,039 patients, we computed BAI using an EEG‐based brain age algorithm. Patients were categorized into four groups, including dementia, mild cognitive impairment (MCI), symptomatic, and non‐dementia, based on clinical diagnoses, Montreal Cognitive Assessment (MoCA), and/or Mini‐Mental State Exam (MMSE) scores. Result We found an overall significant trend across dementia groups using Cuzick's test (p=0.0007). The BAI of patients with dementia (4.11 ± 10.02 yrs) were significantly higher than those of patients with no dementia (0.516 ±10.40 yrs), with p‐value of 0.002, and those of healthy subjects (‐0.67 ± 9.52 yrs), with p‐value of 0.0002. BAI was negatively correlated with MoCA (R = ‐0.1359, p = 0.006) and MMSE (R = ‐0.1201, p = 0.005). Features related to delta activity in non‐REM sleep stages 2 (N2) and 3 (N3) tend to correlate with non‐dementia, and features related to theta and delta waves in the Wake and N1 stages tend to correlate with dementia. Conclusion Our results suggests a potential for an EEG‐based Brain Age Index to serve as a biomarker of dementia. This opens new possibilities for using BAI as an assessment tool for the presence of underlying neurodegenerative disease and monitoring of disease progression.