Independent replication of advanced brain age in mild cognitive impairment and dementia: detection of future cognitive dysfunction

Abstract

We previously developed a novel machine-learning-based brain age model that was sensitive to amyloid. We aimed to independently validate it and to demonstrate its utility using independent clinical data. We recruited 650 participants from South Korean memory clinics to undergo magnetic resonance imaging and clinical assessments. We employed a pretrained brain age model that used data from an independent set of largely Caucasian individuals (n = 757) who had no or relatively low levels of amyloid as confirmed by positron emission tomography (PET). We investigated the association between brain age residual and cognitive decline. We found that our pretrained brain age model was able to reliably estimate brain age (mean absolute error = 5.68 years, r(650) = 0.47, age range = 49–89 year) in the sample with 71 participants with subjective cognitive decline (SCD), 375 with mild cognitive impairment (MCI), and 204 with dementia. Greater brain age was associated with greater amyloid and worse cognitive function [Odds Ratio, (95% Confidence Interval {CI}): 1.28 (1.06–1.55), p = 0.030 for amyloid PET positivity; 2.52 (1.76–3.61), p < 0.001 for dementia]. Baseline brain age residual was predictive of future cognitive worsening even after adjusting for apolipoprotein E e4 and amyloid status [Hazard Ratio, (95% CI): 1.94 (1.33–2.81), p = 0.001 for total 336 follow-up sample; 2.31 (1.44–3.71), p = 0.001 for 284 subsample with baseline Clinical Dementia Rating ≤ 0.5; 2.40 (1.43–4.03), p = 0.001 for 240 subsample with baseline SCD or MCI]. In independent data set, these results replicate our previous findings using this model, which was able to delineate significant differences in brain age according to the diagnostic stages of dementia as well as amyloid deposition status. Brain age models may offer benefits in discriminating and tracking cognitive impairment in older adults.

Probing multiple algorithms to calculate brain age: Examining reliability, relations with demographics, and predictive power

“…The presence of cognitive impairment was mapped to a CDR of > = 1, including subjects with mild to severe cognitive impairment, and excluding subjects with no or "questionable" dementia (CDR <1). This was motivated by, and in keeping with, recent projects focused on replicating associations between brain age and mild cognitive impairment or dementia (e.g., Karim et al, 2022).…”

A deep neural network estimation of brain age is sensitive to cognitive impairment and decline

“…Additionally, studies have shown that AD brains undergo deterioration more rapidly than healthy brains 8 . Given these differences, there arose recent efforts of using neuroimaging-derived measures of gray matter volume from T1-weighted magnetic resonance imaging (MRI) and white matter microstructure from diffusion MRI (dMRI) to predict an individual's "brain age" via machine learning approaches [9][10][11][12] , which can differ from their chronological age and predict cognitive decline [13][14][15] . These models were trained on cognitive unimpaired individuals to learn common patterns in healthy aging, which then allowed them to detect aging-related abnormalities such as those associated with AD.…”