Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Июнь 24, 2024
Abstract
Sarcopenic
obesity
(SO)
is
characterized
by
concomitant
sarcopenia
and
presents
a
high
risk
of
disability,
morbidity,
mortality
among
older
adults.
However,
predictions
based
on
sequential
neural
network
SO
studies
the
relationship
between
physical
fitness
factors
are
lacking.
This
study
aimed
to
develop
predictive
model
for
in
adults
focusing
factors.
A
comprehensive
dataset
Korean
participating
national
programs
was
analyzed
using
networks.
Appendicular
skeletal
muscle/body
weight
defined
as
an
anthropometric
equation.
Independent
variables
included
body
fat
(BF,
%),
waist
circumference,
systolic
diastolic
blood
pressure,
various
The
dependent
variable
binary
outcome
(possible
vs
normal).
We
hyperparameter
tuning
stratified
K-fold
validation
optimize
model.
prevalence
significantly
higher
women
(13.81%)
than
men,
highlighting
sex-specific
differences.
optimized
Shapley
Additive
Explanations
analysis
demonstrated
accuracy
93.1%,
with
BF%
absolute
grip
strength
emerging
most
influential
predictors
SO.
highly
accurate
adults,
emphasizing
critical
roles
strength.
identified
BF,
strength,
sit-and-reach
key
predictors.
Our
findings
underscore
nature
importance
its
prediction.
Information Technology And Control,
Год журнала:
2023,
Номер
52(4), С. 819 - 832
Опубликована: Дек. 22, 2023
Melanoma,
a
rapidly
spreading
and
perilous
type
of
skin
cancer,
is
the
focus
this
study,
presenting
reliable
technique
for
its
detection.
It
one
most
prevalent
types
cancer
that
might
be
challenging
medical
professionals
to
diagnose.
Artificial
intelligence
can
improve
diagnostic
accuracy
when
utilized
in
conjunction
with
expertise
specialists.
An
innovative
computer-aided
method
diagnosis
has
been
introduced
current
study.
The
construction
proposed
uses
African
Gorilla
Troops
Optimizer
(AGTO)
Algorithm,
recently
meta-heuristic
optimization
algorithm,
deep
learning
models
such
as
Faster
Region
Convolutional
Neural
Networks.
To
reduce
complexity
analytic
process,
valuable
features
are
chosen
using
AGTO
method,
further
classification
implemented
R-CNN.
model
applied
ISIC-2020
dataset.
When
final
performance
results
from
compared
those
four
existing
works,
findings
show
system
outperforms
an
98.55%.
IEEE Access,
Год журнала:
2024,
Номер
12, С. 57366 - 57380
Опубликована: Янв. 1, 2024
The
classification
of
skin
lesions
is
crucial
because
it
increases
the
likelihood
that
malignant
will
be
discovered
early
on,
allowing
for
more
effective
treatment.
Due
to
abundance
lesion
images
and
possibility
human
error,
detection
can
difficult
dermatologists.
This
work
aims
classify
using
two
pipelines
were
designed
support
vector
machine
(SVM)
AlexNet
convolutional
neural
network
(CNN)
models.
Pipeline-1
uses
CNN,
while
pipeline-2
proposes
a
bisectional
feature
extraction
approach
with
an
SVM
model.
are
initially
preprocessed
regions
segmented.
further
subdivided
into
four
based
on
intensity
mapping
function.
features
then
extracted
from
trained
dataset
used
in
experiment
HAM-10000
PAD-UFES-20
dataset,
which
consists
dermatoscopic
images.
Based
models'
accuracy,
sensitivity,
DCI,
specificity,
F1-score,
experiment's
findings
assessed
five
different
conditions.
By
accurately
effectively
classifying
lesions,
study's
help
diagnosis
treatment
disorders.
pipeline
performs
better
than
CNN
where
result
accuracy
98.66%
97.68%
respectively
dataset.
structure
results
96.87%
98.10%
Scientific Reports,
Год журнала:
2024,
Номер
14(1)
Опубликована: Июнь 24, 2024
Abstract
Sarcopenic
obesity
(SO)
is
characterized
by
concomitant
sarcopenia
and
presents
a
high
risk
of
disability,
morbidity,
mortality
among
older
adults.
However,
predictions
based
on
sequential
neural
network
SO
studies
the
relationship
between
physical
fitness
factors
are
lacking.
This
study
aimed
to
develop
predictive
model
for
in
adults
focusing
factors.
A
comprehensive
dataset
Korean
participating
national
programs
was
analyzed
using
networks.
Appendicular
skeletal
muscle/body
weight
defined
as
an
anthropometric
equation.
Independent
variables
included
body
fat
(BF,
%),
waist
circumference,
systolic
diastolic
blood
pressure,
various
The
dependent
variable
binary
outcome
(possible
vs
normal).
We
hyperparameter
tuning
stratified
K-fold
validation
optimize
model.
prevalence
significantly
higher
women
(13.81%)
than
men,
highlighting
sex-specific
differences.
optimized
Shapley
Additive
Explanations
analysis
demonstrated
accuracy
93.1%,
with
BF%
absolute
grip
strength
emerging
most
influential
predictors
SO.
highly
accurate
adults,
emphasizing
critical
roles
strength.
identified
BF,
strength,
sit-and-reach
key
predictors.
Our
findings
underscore
nature
importance
its
prediction.