The Open Public Health Journal,
Год журнала:
2024,
Номер
17(1)
Опубликована: Июнь 6, 2024
Introduction/Background
This
research
introduces
the
EO-optimized
Lightweight
Automatic
Modulation
Classification
Network
(EO-LWAMCNet)
model,
employing
AI
and
sensor
data
for
forecasting
chronic
illnesses
within
Internet
of
Things
framework.
A
transformative
tool
in
remote
healthcare
monitoring,
it
exemplifies
AI's
potential
to
revolutionize
patient
experiences
outcomes.
study
unveils
a
novel
Healthcare
System
integrating
Convolutional
Neural
(CNN)
swift
disease
prediction
through
Artificial
Intelligence.
Leveraging
efficiency
lightweight
CNN,
model
holds
promise
revolutionizing
early
diagnosis
enhancing
overall
care.
By
merging
advanced
techniques,
this
improving
Materials
Methods
The
is
implemented
analyze
real-time
an
(IoT)
methodology
also
involves
integration
EO-LWAMCNet
into
cloud-based
IoT
ecosystem,
demonstrating
its
reshaping
monitoring
expanding
access
high-quality
care
beyond
conventional
medical
settings.
Results
Utilizing
Chronic
Liver
Disease
(CLD)
Brain
(BD)
datasets,
algorithm
achieved
remarkable
accuracy
rates
94.8%
95%,
respectively,
showcasing
robustness
as
reliable
clinical
tool.
Discussion
These
outcomes
affirm
model's
reliability
robust
tool,
particularly
crucial
diseases
benefiting
from
detection.
impact
on
emphasized
suggesting
paradigm
shift
traditional
confines.
Conclusion
Our
proposed
presents
cutting-edge
solution
with
illnesses.
revolutionization
ecosystem
underscores
innovative
Healthcare,
Год журнала:
2023,
Номер
11(16), С. 2240 - 2240
Опубликована: Авг. 9, 2023
According
to
the
Pan
American
Health
Organization,
cardiovascular
disease
is
leading
cause
of
death
worldwide,
claiming
an
estimated
17.9
million
lives
each
year.
This
paper
presents
a
systematic
review
highlight
use
IoT,
IoMT,
and
machine
learning
detect,
predict,
or
monitor
disease.
We
had
final
sample
164
high-impact
journal
papers,
focusing
on
two
categories:
detection
using
IoT/IoMT
technologies
techniques.
For
first
category,
we
found
82
proposals,
while
for
second,
85
proposals.
The
research
highlights
list
technologies,
techniques,
datasets,
most
discussed
diseases.
Neural
networks
have
been
popularly
used,
achieving
accuracy
over
90%,
followed
by
random
forest,
XGBoost,
k-NN,
SVM.
Based
results,
conclude
that
can
predict
diseases
in
real
time,
ensemble
techniques
obtained
one
best
performances
metric,
hypertension
arrhythmia
were
Finally,
identified
lack
public
data
as
main
obstacles
approaches
prediction.
International Journal of Emerging Technology and Advanced Engineering,
Год журнала:
2022,
Номер
12(7), С. 186 - 195
Опубликована: Июль 2, 2022
This
study
provides
a
thorough
analysis
of
earlier
DL
techniques
used
to
classify
the
ECG
data.
The
large
variability
among
individual
patients
and
high
expense
labeling
clinical
records
are
main
hurdles
in
automatically
detecting
arrhythmia
by
electrocardiogram
(ECG).
classification
(ECG)
arrhythmias
using
novel
more
effective
technique
is
presented
this
research.
A
high-performance
(ECG)-based
arrhythmic
beats
system
described
research
develop
plan
with
an
autonomous
feature
learning
strategy
optimization
mechanism,
based
on
heartbeat
approach.
We
propose
method
efficient
12-layer,
MIT-BIH
Arrhythmia
dataset's
five
micro-classes
types
wavelet
denoising
technique.
Compared
state-of-the-art
approaches,
newly
enables
considerable
accuracy
increase
quicker
online
retraining
less
professional
involvement.
Diagnostics,
Год журнала:
2024,
Номер
14(13), С. 1344 - 1344
Опубликована: Июнь 25, 2024
The
healthcare
industry
has
evolved
with
the
advent
of
artificial
intelligence
(AI),
which
uses
advanced
computational
methods
and
algorithms,
leading
to
quicker
inspection,
forecasting,
evaluation
treatment.
In
context
healthcare,
(AI)
sophisticated
evaluate,
decipher
draw
conclusions
from
patient
data.
AI
potential
revolutionize
in
several
ways,
including
better
managerial
effectiveness,
individualized
treatment
regimens
diagnostic
improvements.
this
research,
ECG
signals
are
preprocessed
for
noise
elimination
heartbeat
segmentation.
Multi-feature
extraction
is
employed
extract
features
data,
an
optimization
technique
used
choose
most
feasible
features.
i-AlexNet
classifier,
improved
version
AlexNet
model,
classify
between
normal
anomalous
signals.
For
experimental
evaluation,
proposed
approach
applied
PTB
MIT_BIH
databases,
it
observed
that
suggested
method
achieves
a
higher
accuracy
98.8%
compared
other
works
literature.
