International Journal of Molecular Sciences,
Journal Year:
2024,
Volume and Issue:
25(24), P. 13741 - 13741
Published: Dec. 23, 2024
Yakutia
is
one
of
the
coldest
permanently
inhabited
regions
in
world,
characterized
by
a
subarctic
climate
with
average
January
temperatures
near
−40
°C
and
minimum
below
−60
°C.
Recently,
we
demonstrated
accelerated
epigenetic
aging
Yakutian
population
comparison
to
their
Central
Russian
counterparts,
residing
considerably
milder
climate.
In
this
paper,
analyzed
these
cohorts
from
inflammaging
perspective
addressed
two
hypotheses:
mismatch
immunological
profiles
inflammatory
Yakuts.
We
found
that
levels
17
cytokines
displayed
statistically
significant
differences
mean
values
between
groups
(with
minimal
p-value
=
2.06
×
10−19),
6
them
are
among
10
SImAge
markers.
five
out
six
markers
(PDGFB,
CD40LG,
VEGFA,
PDGFA,
CXCL10)
had
higher
cohort,
therefore,
due
positive
chronological
age
correlation,
might
indicate
trend
toward
aging.
At
same
time,
biological
acceleration
difference
according
clock
was
not
detected
because
they
similar
CXCL9,
CCL22,
IL6,
top
contributing
biomarkers
SImAge.
introduced
an
explainable
deep
neural
network
separate
individual
groups,
resulting
over
95%
accuracy.
The
obtained
results
allow
for
hypothesizing
specificity
cytokine
chemokine
people
living
extremely
cold
climates,
possibly
reflecting
effects
long-term
human
(dis)adaptation
conditions
related
risk
developing
number
pathologies.
Ageing Research Reviews,
Journal Year:
2024,
Volume and Issue:
96, P. 102253 - 102253
Published: March 4, 2024
Aging
is
a
complex
multidimensional,
progressive
remodeling
process
affecting
multiple
organ
systems.
While
many
studies
have
focused
on
studying
aging
across
organs,
assessment
of
the
contribution
individual
organs
to
overall
processes
cutting-edge
issue.
An
organ's
biological
age
might
influence
other
revealing
multiorgan
network.
Recent
data
demonstrated
similar
yet
asynchronous
inter-organs
and
inter-individuals
progression
aging,
thereby
providing
foundation
track
sources
declining
health
in
old
age.
The
integration
omics
with
common
clinical
parameters
through
artificial
intelligence
has
allowed
building
organ-specific
clocks,
which
can
predict
development
specific
age-related
diseases
at
high
resolution.
peculiar
aging-trajectory,
referred
as
ageotype,
provide
novel
tool
for
personalized
anti-aging,
preventive
medicine.
Here,
we
review
relative
clocks
omics-based
data,
suggesting
different
rates.
Additional
research
longitudinal
including
young
subjects
analyzing
sex-related
differences,
should
be
encouraged
apply
ageotyping
analysis
purposes
practice.
Diagnostics,
Journal Year:
2025,
Volume and Issue:
15(3), P. 252 - 252
Published: Jan. 22, 2025
In
recent
years,
novel
findings
have
progressively
and
promisingly
supported
the
potential
role
of
Artificial
intelligence
(AI)
in
transforming
management
various
neoplasms,
including
hepatocellular
carcinoma
(HCC).
HCC
represents
most
common
primary
liver
cancer.
Alarmingly,
incidence
is
dramatically
increasing
worldwide
due
to
simultaneous
“pandemic”
spreading
metabolic
dysfunction-associated
steatotic
disease
(MASLD).
MASLD
currently
constitutes
leading
cause
chronic
hepatic
damage
(steatosis
steatohepatitis),
fibrosis,
cirrhosis,
configuring
a
scenario
where
an
onset
has
been
reported
even
early
stage.
On
other
hand,
serious
plague,
significantly
burdening
outcomes
hepatitis
B
(HBV)
C
(HCV)
virus-infected
patients.
Despite
progress
this
cancer,
overall
prognosis
for
advanced-stage
patients
continues
be
poor,
suggesting
absolute
need
develop
personalized
healthcare
strategies
further.
“cold
war”,
machine
learning
techniques
neural
networks
are
emerging
as
weapons,
able
identify
patterns
biomarkers
that
would
normally
escaped
human
observation.
Using
advanced
algorithms,
AI
can
analyze
large
volumes
clinical
data
medical
images
(including
routinely
obtained
ultrasound
data)
with
elevated
accuracy,
facilitating
diagnosis,
improving
performance
predictive
models,
supporting
multidisciplinary
(oncologist,
gastroenterologist,
surgeon,
radiologist)
team
opting
best
“tailored”
individual
treatment.
Additionally,
contribute
enhancing
effectiveness
metabolomics–radiomics-based
promoting
identification
specific
HCC-pathogenetic
molecules
new
targets
realizing
therapeutic
regimens.
era
precision
medicine,
integrating
into
routine
practice
appears
promising
frontier,
opening
avenues
cancer
research
Pflügers Archiv - European Journal of Physiology,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Feb. 25, 2025
Abstract
Explainable
artificial
intelligence
(XAI)
is
gaining
importance
in
physiological
research,
where
now
used
as
an
analytical
and
predictive
tool
for
many
medical
research
questions.
The
primary
goal
of
XAI
to
make
AI
models
understandable
human
decision-makers.
This
can
be
achieved
particular
through
providing
inherently
interpretable
methods
or
by
making
opaque
their
outputs
transparent
using
post
hoc
explanations.
review
introduces
core
topics
provides
a
selective
overview
current
physiology.
It
further
illustrates
solved
discusses
open
challenges
existing
practical
examples
from
the
field.
article
gives
outlook
on
two
possible
future
prospects:
(1)
provide
trustworthy
integrative
(2)
integrating
expertise
about
explanation
into
method
development
useful
beneficial
human-AI
partnerships.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: Feb. 11, 2025
Deep
learning
(DL)
and
explainable
artificial
intelligence
(XAI)
have
emerged
as
powerful
machine-learning
tools
to
identify
complex
predictive
data
patterns
in
a
spatial
or
temporal
domain.
Here,
we
consider
the
application
of
DL
XAI
large
omic
datasets,
order
study
biological
aging
at
molecular
level.
We
develop
an
advanced
multi-view
graph-level
representation
(MGRL)
framework
that
integrates
prior
network
information,
build
clocks
cell-type
resolution,
which
subsequently
interpret
using
XAI.
apply
this
one
largest
single-cell
transcriptomic
datasets
encompassing
over
million
immune
cells
from
981
donors,
revealing
ribosomal
gene
subnetwork,
whose
expression
correlates
with
age
independently
cell-type.
Application
same
DL-XAI
DNA
methylation
sorted
monocytes
reveals
epigenetically
deregulated
inflammatory
response
pathway
activity
increases
age.
show
module
pathways
would
not
been
discovered
had
used
more
standard
methods.
In
summary,
computational
deep
presented
here
illustrates
how
when
combined
AI
tools,
can
reveal
novel
insights
into
process
aging.
bioRxiv (Cold Spring Harbor Laboratory),
Journal Year:
2024,
Volume and Issue:
unknown
Published: March 17, 2024
Abstract
This
study
is
the
first
systematic
meta-analysis
of
epigenetic
age
acceleration
largest
publicly
available
DNA
methylation
data
for
healthy
samples
(93
datasets,
23K
samples),
focusing
on
geographic
and
ethnic
aspects
different
countries
(25
countries)
populations
(31
ethnicities)
around
world.
The
most
popular
tools
assessing
were
examined
in
detail,
their
quality
metrics
analyzed,
ability
to
extrapolate
from
tissue
types
ranges
training
these
models
was
explored.
In
cases,
are
not
consistent
with
each
other
show
signs
acceleration,
PhenoAge
model
tending
systematically
underestimate
versions
GrimAge
overestimate
prediction
subjects.
Although
GEO
open-access
database,
represented,
datasets
use
criteria
determining
controls.
Because
this,
it
difficult
fully
isolate
contribution
“geography/environment”,
“ethnicity”
“healthiness”
acceleration.
However,
DunedinPACE
metric,
which
measures
aging
rate,
adequately
reflects
standard
living
socioeconomic
indicators
countries,
although
can
be
applied
only
blood
data.
When
comparing
males
faster
than
females
considered.
