Role of artificial intelligence in predicting disease-related malnutrition - A narrative review
Nutrición Hospitalaria,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Jan. 1, 2025
disease-related
malnutrition
(DRM)
affects
30-50
%
of
hospitalized
patients
and
is
often
underdiagnosed,
increasing
risks
complications
healthcare
costs.
Traditional
DRM
detection
has
relied
on
manual
methods
that
lack
accuracy
efficiency.
this
narrative
review
explores
how
artificial
intelligence
(AI),
specifically
machine
learning
(ML)
deep
(DL),
can
transform
the
prediction
management
in
clinical
settings.
we
examine
widely
used
ML
DL
models,
assessing
their
applicability,
advantages,
limitations.
The
integration
these
models
into
electronic
health
record
systems
allows
for
automated
risk
optimizes
real-time
patient
management.
show
significant
potential
accurate
assessment
nutritional
status
with
DRM.
These
facilitate
improved
decision-making
more
efficient
resource
management,
although
implementation
faces
challenges
related
to
need
large
volumes
standardized
data
existing
systems.
AI
offers
promising
prospects
proactive
highlighting
interdisciplinary
collaboration
overcome
barriers
maximize
its
positive
impact
care.
Language: Английский
ASSOCIATION BETWEEN MUSCLE MASS ASSESSED BY AN ARTIFICIAL INTELLIGENCE-BASED ULTRASOUND IMAGING SYSTEM AND QUALITY OF LIFE IN PATIENTS WITH MALNUTRITION RELATED WITH CANCER
Nutrition,
Journal Year:
2025,
Volume and Issue:
135, P. 112763 - 112763
Published: March 13, 2025
Language: Английский
Artificial Intelligence-Assisted Muscular Ultrasonography for Assessing Inflammation and Muscle Mass in Patients at Risk of Malnutrition
Nutrients,
Journal Year:
2025,
Volume and Issue:
17(10), P. 1620 - 1620
Published: May 9, 2025
Background:
Malnutrition,
influenced
by
inflammation,
is
associated
with
muscle
depletion
and
body
composition
changes.
This
study
aimed
to
evaluate
mass
quality
using
Artificial
Intelligence
(AI)-enhanced
ultrasonography
in
patients
inflammation.
Methods:
observational,
cross-sectional
included
502
malnourished
patients,
assessed
through
anthropometry,
electrical
bioimpedanciometry,
of
the
quadriceps
rectus
femoris
(QRF).
AI-assisted
was
used
segment
regions
interest
(ROI)
from
transversal
QRF
images
measure
thickness
(RFMT)
area
(RFMA),
while
a
Multi-Otsu
algorithm
extract
biomarkers
for
(MiT)
fat
(FatiT).
Inflammation
defined
as
C-reactive
protein
(CRP)
levels
above
3
mg/L.
Results:
The
results
showed
mean
patient
age
63.72
(15.95)
years,
malnutrition
present
82.3%
inflammation
44.8%.
Oncological
diseases
were
prevalent
(46.8%).
44.8%
(CRP
>
3)
exhibited
reduced
RFMA
(2.91
(1.11)
vs.
3.20
(1.19)
cm2,
p
<
0.01)
RFMT
(0.94
(0.28)
1.01
(0.30)
cm,
0.01).
Muscle
reduced,
lower
MiT
(45.32
(9.98%)
49.10
(1.22%),
higher
FatiT
(40.03
(6.72%)
37.58
(5.63%),
Adjusted
sex,
increased
risks
low
(OR
=
1.59,
CI:
1.10–2.31),
1.49,
1.04–2.15),
high
1.44,
1.00–2.06).
Conclusions:
revealed
that
had
area,
thickness,
(higher
content
percentage).
Elevated
poor
metrics.
Future
research
should
focus
on
exploring
impact
muscles
across
various
groups
developing
AI-driven
enhance
diagnosis,
monitoring,
treatment
sarcopenia.
Language: Английский