Clinical Breast Cancer,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 1, 2025
Older
adult
breast
cancer
(OABC)
patients
(≥
65
years)
frequently
experience
poorer
prognoses
compared
to
younger
adults,
attributed
complex
tumor
biology
and
age-related
factors.
The
present
study
employs
a
multiomics
approach
combined
with
machine
learning
develop
novel
prognostic
model
for
OABC,
focus
on
the
hypoxic
immune
characteristics
of
microenvironment.
Genetic
molecular
data
from
503
OABC
589
(YABC)
were
analyzed
using
Cancer
Genome
Atlas
(TCGA)
database.
An
ensemble
machine-learning
was
developed,
integrating
data-including
mRNA,
miRNA,
lncRNA,
copy
number
variations
(CNVs),
single
nucleotide
variants
(SNVs)-along
clinicopathological
features,
predict
survival
outcomes.
trained
300
samples
validated
203
samples.
achieved
predictive
accuracy
69.5%
outcomes
in
patients.
Distinct
hypoxia-related
gene
expression
patterns
reduced
cell
infiltration
observed
YABC.
Hypoxia
significantly
associated
disease-free
(DFS)
(P
=
.037),
but
not
YABC
.38).
multiomics-based
developed
showed
clinical
potential,
findings
highlight
critical
role
hypoxia
microenvironment
prognosis
OABC.
Further
research
is
warranted
validate
this
larger
cohorts
explore
its
potential
application
guiding
personalized
treatment
strategies
Frontiers in Artificial Intelligence,
Год журнала:
2024,
Номер
7
Опубликована: Июль 3, 2024
Survival
prediction
integrates
patient-specific
molecular
information
and
clinical
signatures
to
forecast
the
anticipated
time
of
an
event,
such
as
recurrence,
death,
or
disease
progression.
proves
valuable
in
guiding
treatment
decisions,
optimizing
resource
allocation,
interventions
precision
medicine.
The
wide
range
diseases,
existence
various
variants
within
same
disease,
reliance
on
available
data
necessitate
disease-specific
computational
survival
predictors.
widespread
adoption
artificial
intelligence
(AI)
methods
crafting
predictors
has
undoubtedly
revolutionized
this
field.
However,
ever-increasing
demand
for
more
sophisticated
effective
models
necessitates
continued
creation
innovative
advancements.
To
catalyze
these
advancements,
it
is
crucial
bring
existing
knowledge
insights
into
a
centralized
platform.
paper
hand
thoroughly
examines
23
review
studies
provides
concise
overview
their
scope
limitations.
Focusing
comprehensive
set
90
most
recent
across
44
diverse
delves
types
that
are
used
development
This
exhaustive
analysis
encompasses
utilized
modalities
along
with
detailed
subsets
features,
feature
engineering
methods,
specific
statistical,
machine
deep
learning
approaches
have
been
employed.
It
also
about
sources,
open-source
predictors,
frameworks.
Medicine in Novel Technology and Devices,
Год журнала:
2024,
Номер
24, С. 100327 - 100327
Опубликована: Авг. 27, 2024
Hepatocellular
carcinoma
(HCC)
continues
to
be
a
diagnostic
and
therapeutic
challenge
for
healthcare
systems
around
the
world
in
addition
being
significant
contributor
oncologic
mortality.
To
improve
standard
of
life
survival
patients,
early
diagnosis
condition
subsequent
appropriate
treatment
are
essential.
observation,
detection,
diagnosis,
follow-up
all
depend
heavily
on
imaging
modalities.
They
provide
valuable
information
about
characteristics
HCC
nodules,
aiding
non-invasive
staging.
Imaging
has
evolved
beyond
simply
confirming
suspected
management
hepatocellular
(HCC).
Several
traditional
modalities,
including
PET/CT,
MRI,
MR
elastography,
ultrasound
(US),
endoscopy,
along
with
next-generation
modalities
such
as
photoacoustic
imaging,
Cerenkov
luminescence
utilization
contrasting
agents
further
enhance
their
capabilities
HCC.
The
selection
most
modality
agent
depends
various
factors,
clinical
scenario,
patient
characteristics,
availability
resources.
In
these
advancements,
artificial
intelligence
(AI)
developed
tool
radiology
this
review,
we
highlighted
important
techniques
managing
patients
high
risk
Clinical Breast Cancer,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 1, 2025
Older
adult
breast
cancer
(OABC)
patients
(≥
65
years)
frequently
experience
poorer
prognoses
compared
to
younger
adults,
attributed
complex
tumor
biology
and
age-related
factors.
The
present
study
employs
a
multiomics
approach
combined
with
machine
learning
develop
novel
prognostic
model
for
OABC,
focus
on
the
hypoxic
immune
characteristics
of
microenvironment.
Genetic
molecular
data
from
503
OABC
589
(YABC)
were
analyzed
using
Cancer
Genome
Atlas
(TCGA)
database.
An
ensemble
machine-learning
was
developed,
integrating
data-including
mRNA,
miRNA,
lncRNA,
copy
number
variations
(CNVs),
single
nucleotide
variants
(SNVs)-along
clinicopathological
features,
predict
survival
outcomes.
trained
300
samples
validated
203
samples.
achieved
predictive
accuracy
69.5%
outcomes
in
patients.
Distinct
hypoxia-related
gene
expression
patterns
reduced
cell
infiltration
observed
YABC.
Hypoxia
significantly
associated
disease-free
(DFS)
(P
=
.037),
but
not
YABC
.38).
multiomics-based
developed
showed
clinical
potential,
findings
highlight
critical
role
hypoxia
microenvironment
prognosis
OABC.
Further
research
is
warranted
validate
this
larger
cohorts
explore
its
potential
application
guiding
personalized
treatment
strategies
