Despite the clinical importance and significant social burden of neuropsychiatric symptoms (NPS) in dementia, the underlying neurobiological mechanism remains poorly understood. Recently, neuroimaging-derived brain-age estimation by machine-learning analysis has shown promise as an individual-level biomarker. We investigated the relationship between NPS and brain-age in amnestic mild cognitive impairment (MCI) and early dementia. In this cross-sectional study, clinical data, including neuropsychiatric inventory (NPI), and structural brain MRI of 499 individuals with clinical diagnoses of amnestic MCI (n = 185), early Alzheimer's disease (AD) (n = 258) or dementia with Lewy bodies (DLB) (n = 56) were analyzed. We established a brain-age prediction model using 694 healthy brain MRIs and a support vector regression model and applied it to the participants' data. Finally, the brain-predicted age difference (brain-PAD: predicted age minus chronological age) was calculated. All groups showed significantly increased brain-PAD, and the median (IQR) brain-PAD was 4.3 (5.4) years in MCI, 6.3 (6.2) years in AD, and 5.0 (6.5) years in DLB. The NPI scores were subdivided into the following four categories: (i) Agitation and Irritability, (ii) Depression and Apathy, (iii) Delusions and Hallucinations, and (iv) Euphoria and Disinhibition. We found a significantly positive correlation between brain-PAD and the depression/apathy factor (Spearman's rs = 0.156, FDR-corrected P = 0.002), whereas no significance was shown for the other NPS factors. Higher brain-age may be associated with depression and apathy symptoms presented in MCI to early dementia stages, and brain-age analysis may be useful as a novel biomarker for the assessment or monitoring of NPS.
Read full abstract