The Journal of Engineering,
Journal Year:
2023,
Volume and Issue:
2023(2)
Published: Jan. 23, 2023
The
2019
coronavirus
disease
began
in
Wuhan,
China,
and
spread
worldwide.
This
pandemic
was
concerning,
given
its
significant
worrying
impact
on
human
health.
Strategies
to
manage
the
begin
with
diagnosing
infection,
often
using
real-time
reverse
transcription
polymerase
chain
reaction
(RT-PCR)
assay.
However,
this
process
is
time
intensive.
Therefore,
alternative
rapid
methods
diagnose
high
accuracy
are
needed.
X-ray
computerized
tomography
(CT)
scans
reasonable
solutions
for
diagnosis.
dataset
of
500
patients
tested,
including
286
uninfected
214
infected
COVID-19.
Clinical
parameters,
heart
rate
(HR),
temperature
(T),
blood
oxygen
level,
D-dimer,
CT
scan,
red-green-blue
(RGB)
pixel
values
left
right
lungs,
were
collected
from
used
train
an
artificial
neural
network
(ANN)
coronavirus.
ANN
hybridized
a
particle
swarm
optimization
(PSO)
algorithm
improve
diagnosis
accuracy.
results
show
that
proposed
PSO-ANN
method
significantly
improved
(98.93%),
sensitivity
(100%),
specificity
(98.13%).
effectiveness
confirmed
by
comparing
findings
those
previous
studies.
Mathematics,
Journal Year:
2023,
Volume and Issue:
11(6), P. 1279 - 1279
Published: March 7, 2023
Deep
learning
is
a
sub-discipline
of
artificial
intelligence
that
uses
neural
networks,
machine
technique,
to
extract
patterns
and
make
predictions
from
large
datasets.
In
recent
years,
it
has
achieved
rapid
development
widely
used
in
numerous
disciplines
with
fruitful
results.
Learning
valuable
information
complex,
high-dimensional,
heterogeneous
biomedical
data
key
challenge
transforming
healthcare.
this
review,
we
provide
an
overview
emerging
deep-learning
techniques,
COVID-19
research
involving
deep
learning,
concrete
examples
methods
diagnosis,
prognosis,
treatment
management.
can
process
medical
imaging
data,
laboratory
test
results,
other
relevant
diagnose
diseases
judge
disease
progression
even
recommend
plans
drug-use
strategies
accelerate
drug
improve
quality.
Furthermore,
help
governments
develop
proper
prevention
control
measures.
We
also
assess
the
current
limitations
challenges
therapy
precision
for
COVID-19,
including
lack
phenotypically
abundant
need
more
interpretable
models.
Finally,
discuss
how
barriers
be
overcome
enable
future
clinical
applications
learning.
BMC Medical Informatics and Decision Making,
Journal Year:
2024,
Volume and Issue:
24(1)
Published: June 24, 2024
Abstract
With
the
outbreak
of
COVID-19
in
2020,
countries
worldwide
faced
significant
concerns
and
challenges.
Various
studies
have
emerged
utilizing
Artificial
Intelligence
(AI)
Data
Science
techniques
for
disease
detection.
Although
cases
declined,
there
are
still
deaths
around
world.
Therefore,
early
detection
before
onset
symptoms
has
become
crucial
reducing
its
extensive
impact.
Fortunately,
wearable
devices
such
as
smartwatches
proven
to
be
valuable
sources
physiological
data,
including
Heart
Rate
(HR)
sleep
quality,
enabling
inflammatory
diseases.
In
this
study,
we
utilize
an
already-existing
dataset
that
includes
individual
step
counts
heart
rate
data
predict
probability
infection
symptoms.
We
train
three
main
model
architectures:
Gradient
Boosting
classifier
(GB),
CatBoost
trees,
TabNet
analyze
compare
their
respective
performances.
also
add
interpretability
layer
our
best-performing
model,
which
clarifies
prediction
results
allows
a
detailed
assessment
effectiveness.
Moreover,
created
private
by
gathering
from
Fitbit
guarantee
reliability
avoid
bias.
The
identical
set
models
was
then
applied
using
same
pre-trained
models,
were
documented.
Using
tree-based
method,
outperformed
previous
with
accuracy
85%
on
publicly
available
dataset.
Furthermore,
produced
81%
when
You
will
find
source
code
link:
https://github.com/OpenUAE-LAB/Covid-19-detection-using-Wearable-data.git
.
Journal of Imaging,
Journal Year:
2022,
Volume and Issue:
8(10), P. 267 - 267
Published: Sept. 30, 2022
The
last
two
years
are
considered
the
most
crucial
and
critical
period
of
COVID-19
pandemic
affecting
life
aspects
worldwide.
This
virus
spreads
quickly
within
a
short
period,
increasing
fatality
rate
associated
with
virus.
From
clinical
perspective,
several
diagnosis
methods
carried
out
for
early
detection
to
avoid
propagation.
However,
capabilities
these
limited
have
various
challenges.
Consequently,
many
studies
been
performed
automated
without
involving
manual
intervention
allowing
an
accurate
fast
decision.
As
is
case
other
diseases
medical
issues,
Artificial
Intelligence
(AI)
provides
community
potential
technical
solutions
that
help
doctors
radiologists
diagnose
based
on
chest
images.
In
this
paper,
comprehensive
review
mentioned
AI-based
solution
proposals
conducted.
More
than
200
papers
reviewed
analyzed,
145
articles
extensively
examined
specify
proposed
AI
mechanisms
A
examination
advantages
shortcomings
illustrated
summarized.
Several
findings
concluded
as
result
deep
analysis
all
previous
works
using
machine
learning
detection,
segmentation,
classification.
ECONOMIC COMPUTATION AND ECONOMIC CYBERNETICS STUDIES AND RESEARCH,
Journal Year:
2024,
Volume and Issue:
58(2/2024), P. 165 - 181
Published: June 12, 2024
The
"Viral
Immunogenic
Syndrome"
(VIS)
incorporates
the
concepts
of
"viral"
and
"immunogenic"
to
emphasise
pathogenic
character
illness
immunological
response
it
generates,
as
well
word
"syndrome"
describe
broad
set
symptoms
consequences.Our
research
focused
on
analyzing
COVID-19
genome
sequence
using
a
proposed
framework
improve
computation
time
model
efficiency.We
also
aimed
identify
frequent
patterns,
missing
indices,
variations
in
while
comparing
performance
with
varying
minimum
support
existing
models.We
used
FCSM
classify
genomic
sequences
detect
calculating
time.Additionally,
we
novel
utilizing
FIMAR
nucleotide
compute
consecutive
sets,
resulting
more
efficient
accurate
approach
than
methods.Our
study
shows
that
algorithms
is
94.34%
system
for
computing
sequence.We
identified
0.2%
1.61%
variation
USA
China
datasets,
respectively,
which
failed
detect.Additionally,
conducted
comparative
an
Apriori
methods
patterns.In
this
work,
present
analysis
substitution
rate
at
each
isolation
step.
PeerJ Computer Science,
Journal Year:
2024,
Volume and Issue:
10, P. e2062 - e2062
Published: July 30, 2024
The
SARS-CoV-2
virus,
which
induces
an
acute
respiratory
illness
commonly
referred
to
as
COVID-19,
had
been
designated
a
pandemic
by
the
World
Health
Organization
due
its
highly
infectious
nature
and
associated
public
health
risks
it
poses
globally.
Identifying
critical
factors
for
predicting
mortality
is
essential
improving
patient
therapy.
Unlike
other
data
types,
such
computed
tomography
scans,
x-radiation,
ultrasounds,
basic
blood
test
results
are
widely
accessible
can
aid
in
mortality.
present
research
advocates
utilization
of
machine
learning
(ML)
methodologies
likelihood
disease
like
COVID-19
leveraging
data.
Age,
LDH
(lactate
dehydrogenase),
lymphocytes,
neutrophils,
hs-CRP
(high-sensitivity
C-reactive
protein)
five
extremely
potent
characteristics
that,
when
combined,
accurately
predict
96%
cases.
By
combining
XGBoost
feature
importance
with
neural
network
classification,
optimal
approach
exceptional
accuracy
from
disease,
along
achieving
precision
rate
90%
up
16
days
before
event.
studies
suggested
model’s
excellent
predictive
performance
practicality
were
confirmed
through
testing
three
instances
that
depended
on
outcome.
carefully
analyzing
identifying
patterns
these
significant
biomarkers
insightful
information
has
obtained
simple
application.
This
study
offers
potential
remedies
could
accelerate
decision-making
targeted
medical
treatments
within
healthcare
systems,
utilizing
timely,
accurate,
reliable
method.
Bioengineering,
Journal Year:
2023,
Volume and Issue:
10(5), P. 529 - 529
Published: April 26, 2023
Even
with
over
80%
of
the
population
being
vaccinated
against
COVID-19,
disease
continues
to
claim
victims.
Therefore,
it
is
crucial
have
a
secure
Computer-Aided
Diagnostic
system
that
can
assist
in
identifying
COVID-19
and
determining
necessary
level
care.
This
especially
important
Intensive
Care
Unit
monitor
progression
or
regression
fight
this
epidemic.
To
accomplish
this,
we
merged
public
datasets
from
literature
train
lung
lesion
segmentation
models
five
different
distributions.
We
then
trained
eight
CNN
for
Common-Acquired
Pneumonia
classification.
If
examination
was
classified
as
quantified
lesions
assessed
severity
full
CT
scan.
validate
system,
used
Resnetxt101
Unet++
Mobilenet
Unet
segmentation,
respectively,
achieving
accuracy
98.05%,
F1-score
98.70%,
precision
98.7%,
recall
specificity
96.05%.
accomplished
just
19.70
s
per
scan,
external
validation
on
SPGC
dataset.
Finally,
when
classifying
these
detected
lesions,
Densenet201
achieved
90.47%,
93.85%,
88.42%,
100.0%,
65.07%.
The
results
demonstrate
our
pipeline
correctly
detect
segment
due
scans.
It
differentiate
two
classes
normal
exams,
indicating
efficient
effective
assessing
condition.