Leveraging Subjective Parameters and Biomarkers in Machine Learning Models: The Feasibility of lnc-IL7R for Managing Emphysema Progression
Diagnostics,
Год журнала:
2025,
Номер
15(9), С. 1165 - 1165
Опубликована: Май 3, 2025
Background/Objectives:
Chronic
obstructive
pulmonary
disease
(COPD)
remains
a
leading
cause
of
death
worldwide,
with
emphysema
progression
providing
valuable
insights
into
development.
Clinical
assessment
approaches,
including
function
tests
and
high-resolution
computed
tomography,
are
limited
by
accessibility
constraints
radiation
exposure.
This
study,
therefore,
proposed
an
alternative
approach
integrating
the
novel
biomarker
long
non-coding
interleukin-7
receptor
α-subunit
gene
(lnc-Il7R),
along
other
easily
accessible
clinical
biochemical
metrics,
machine
learning
(ML)
models.
Methods:
cohort
study
collected
baseline
characteristics,
COPD
Assessment
Test
(CAT)
scores,
details
from
enrolled
participants.
Associations
severity,
defined
low
attenuation
area
percentage
(LAA%)
threshold
15%,
were
evaluated
using
simple
multivariate-adjusted
The
dataset
was
then
split
training
validation
(80%)
test
(20%)
subsets.
Five
ML
models
employed,
best-performing
model
being
further
analyzed
for
feature
importance.
Results:
majority
participants
elderly
males.
Compared
to
LAA%
<15%
group,
≥15%
group
demonstrated
significantly
higher
body
mass
index
(BMI),
poor
function,
lower
expression
levels
lnc-Il7R
(all
p
<
0.01).
Fold
changes
in
lnc-IL7R
strongly
negatively
associated
(p
random
forest
(RF)
achieved
highest
accuracy
under
receiver
operating
characteristic
curve
(AUROC)
across
datasets.
A
importance
analysis
identified
fold
as
strongest
predictor
classification
(LAA%
≥15%),
followed
CAT
scores
BMI.
Conclusions:
Machine
incorporated
markers,
particularly
lnc-IL7R,
achieving
AUROC
exceeding
75%
assessments.
These
findings
offer
promising
opportunities
improving
management.
Язык: Английский
Decoding LncRNA in COPD: Unveiling Prognostic and Diagnostic Power and Their Driving Role in Lung Cancer Progressions
Опубликована: Июль 3, 2024
Keywords:
Chronic
Obstructive
Pulmonary
Disease
(COPD),
Long
Non-Coding
RNAs
(lncRNAs),
Molecular
Pathogenesis,
Inflammation,
Lung
Cancer,
Diagnostic
Biomarkers
Язык: Английский