Brain Age Gap as a Predictive Biomarker: Linking Aging, Lifestyle, and Neuropsychiatric Health
Abstract
Background
The
brain
age
gap
(BAG),
a
neuroimaging-derived
biomarker
of
accelerated
aging,
faces
translational
challenges
due
to
model
inaccuracies
and
unclear
disease-mechanism
linkages.
We
systematically
evaluated
BAG's
clinical
relevance
across
neuropsychiatric
disorders,
cognitive
trajectories,
mortality,
lifestyle
interventions.
Methods
Using
multi-cohort
data
(UK
Biobank
[n
=
38,967],
Alzheimer’s
Disease
Neuroimaging
Initiative
[ADNI;
n
1,402],
Parkinson’s
Progression
Markers
[PPMI;
1,182]),
we
developed
3D
Vision
Transformer
(3D-ViT)
for
whole-brain
estimation.
Survival
analyses,
restricted
cubic
splines,
stratified
regressions
assessed
BAG’s
associations
with
cognition,
16
mortality.
Lifestyle
modulation
effects
were
quantified
through
longitudinal
BAG
progression.
Results
demonstrated
robust
predictive
accuracy,
achieving
mean
absolute
error
(MAE)
2.68
years
in
the
UK
cohort
2.99–3.20
external
validation
cohorts
(ADNI/PPMI).
Per
1-year
increment
was
linearly
associated
elevated
risks
Alzheimer's
disease
(HR
1.165,
95%
CI
1.086–1.249;
+16.5%
risk/year),
mild
impairment
1.040,
1.030–1.050;
+4.0%),
all-cause
mortality
1.12,
1.09–1.15;
+12%;
all
p
<
0.001).
Individuals
highest
quartile
(Q4)
faced
substantially
amplified
risks:
2.8-fold
2.801),
6.4-fold
multiple
sclerosis
6.417),
1.5-fold
major
depressive
disorder
1.466).
Notably,
prodromal
Parkinson's
exhibited
paradoxical
rejuvenation
(mean
Δ=−1.441
years,
0.001),
contrasting
nonsignificant
incident
cases
1.830,
0.154).
Cognitive
decline
followed
nonlinear
critical
thresholds
domain-specific
emerging
at
Q4
(BAG
>
2.48
years).
interventions
synergistically
attenuated
progression
advanced
neurodegeneration
(Q3–Q4;
0.05),
particularly
smoking
cessation,
moderated
alcohol
consumption,
physical
activity.
Interpretation :
robustly
predicts
multimorbidity,
Its
stage-dependent
modifiability
underscore
utility
risk
stratification
personalized
prevention
strategies.
Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown
Published: April 16, 2025
Language: Английский