2022 IEEE 6th Conference on Information and Communication Technology (CICT),
Journal Year:
2023,
Volume and Issue:
unknown, P. 1 - 6
Published: Dec. 15, 2023
The
Secure
Health
Management
and
Prediction
System
for
Chronic
illnesses
has
transformed
healthcare
by
predicting
controlling
chronic
using
user-provided
data.
It
lowers
expenses
combining
machine
learning,
data
analytics,
cloud
computing.
With
strong
safeguards
such
as
encryption
authentication,
the
system
protects
privacy
security.
Its
HIPAA
compliance
focus
on
patient
make
it
helpful
in
rural
Sri
Lanka,
where
experts
are
few.
Using
computing,
research
study
proposes
a
secure
health
management
prediction
diseases.
Based
medical
information,
algorithm
forecasts
diabetes
cardiovascular
disorders.
For
disease
prediction,
employs
techniques
Decision
Tree,
Linear
Regression,
Random
Forest,
Support
V
ector
Machine,
Logistic
Naive
Bayes.
feedback,
also
assesses
insurance
costs
suggests
providers.
SSRN Electronic Journal,
Journal Year:
2025,
Volume and Issue:
unknown
Published: Jan. 1, 2025
A
blood
group
system
used
in
medical
and
forensic
biology
to
classify
types
based
on
the
presence
of
specific
molecules
or
antigens
that
are
attached
red
cells.
The
traditional
detection
methods
for
grouping
an
invasive
method
manual
analysis,
which
results
too
slow
obtain
bringing
incorrect
diagnosis
many
times.
In
recent
times
AI
&
image
processing
techniques
has
proven
be
a
reliable
way
automatic
classification
group.
To
address
this
issue,
high-resolution
images
samples
acquired
using
dedicated
imaging
work.
pre-processing
would
include
denoising,
contrast
stretching
segmentation
improve
quality
concentrate
regions
interest
Then
feature
extraction
discover
distinctive
features
could
shapes,
color
texture
any
other
visual
characteristic
differentiate
groups.
segregation
train
deep
neural
network
(DNN)
Optimization
Using
Firefly
Algorithm:
solve
performance
issue
model,
function
is
optimized
by
technique
inspired
firefly
called
Algorithm.
This
algorithm
return
some
best
model
parameters,
like
architecture,
learning
rate
regularization
increase
prediction
accuracy.
It
can
observed
from
output
while
integrating
AI,
FA
refine
Bgroup
accuracy
as
well
efficiency
at
great
height.
Journal of Machine and Computing,
Journal Year:
2023,
Volume and Issue:
unknown, P. 456 - 464
Published: Oct. 5, 2023
Healthcare
practices
have
a
tremendous
amount
of
potential
to
change
as
result
the
convergence
IoT
technologies
with
cutting-edge
machine
learning.
This
study
offers
an
IoT-connected
sensor-based
Intelligent
Health
Monitoring
System
for
real-time
patient
health
assessment.
Our
system
continuous
monitoring
and
early
anomaly
identification
by
integrating
temperature,
blood
pressure,
ECG
sensors.
The
Support
Vector
Machine
(SVM)
model
proves
be
reliable
predictor
after
thorough
analysis,
obtaining
astounding
accuracy
rates
94%
specificity,
95%
F1
score,
92%
recall,
total
accuracy.
These
outcomes
demonstrate
how
well
our
performs
when
it
comes
providing
precise
timely
predictions.
facilities
can
easily
integrate
part
practical
application
research.
Real-time
sensor
data
used
doctors
proactively
spot
issues
provide
prompt
interventions,
improving
quality
care.
study's
integration
advanced
learning
underlines
strategy's
disruptive
transforming
healthcare
procedures.
provides
foundation
more
effective,
responsive,
patient-centered
ecosystem
employing
connected
devices
predictive
analytics.
Heart
disease
is
among
the
main
causes
of
fatalities
worldwide,
in
our
days.
However,
early
detection
cardiac
problems
and
timely
care
by
health
practitioners
can
reduce
mortality
rate.
Therefore,
a
reliable
system
for
assessing
such
pathologies
utmost
importance
to
be
able
process
an
adequate
treatment.
In
this
paper,
we
investigate
various
classification
techniques
diagnose
persons
registered
receive
medical
treatment
who
are
suffering
from
heart
malfunctions.
Accordingly,
proactively
identify
issues
based
on
collected
clinical
data.
We
analyze
different
machine
learning
approaches
order
recommend
optimal
model
discussing
achieved
performance
terms
multiple
metrics.
Finally,
provide
recommendations
share
lessons-learned.
EAI Endorsed Transactions on Pervasive Health and Technology,
Journal Year:
2024,
Volume and Issue:
10
Published: March 14, 2024
INTRODUCTION:
The
cardiopulmonary
arrest
is
a
major
issue
in
any
country.
Gone
are
the
days
when
it
used
to
happen
those
who
aged
but
now
concern
emerging
among
adolescents
as
well.
According
World
Health
Organization
(WHO),
cardiac
and
stroke
still
remains
public
health
crisis.
In
past
years
India
has
witnessed
many
cases
of
heart
related
issues
which
occur
predominantly
people
having
high
cholesterol.
But
scenario
changed,
have
been
observed
normal
cholesterol
levels.
There
several
factors
involved
such
age,
sex,
blood
pressure,
etc.
by
doctors
monitor
diagnose
same.
OBJECTIVES:
This
paper
focuses
on
different
predictive
models
ways
improve
accuracy
prediction
analyzing
datasets
how
they
affect
certain
algorithms.
METHODS:
contributing
can
be
beacon
predict
help
an
individual
further
consult
doctor
beforehand.
idea
target
algorithms
deep
learning
including
advanced
ones
improvise
attain
better
result.
RESULTS:
brings
out
comparative
analysis
neural
network
techniques
like
ANN,
Transfer
Learning,
MAML
LRP
ANN
showed
best
result
giving
highest
94%.
CONCLUSION:
Furthermore,
discusses
new
attribute
called
“gamma
prime
fibrinogen”
could
future
boost
performance.
This
work
contains
the
classification
of
patients
in
an
Emergency
Department
a
hospital
according
to
their
critical
conditions.
Machine
learning
can
be
applied
based
on
patient's
condition
quickly
determine
if
patient
requires
urgent
medical
intervention
from
clinicians
or
not.
Basic
vital
signs
like
Systolic
Blood
Pressure
(SBP),
Diastolic
(DBP),
Respiratory
Rate
(RR),
Oxygen
saturation
(SPO2),
Random
Sugar
(RBS),
Temperature,
Pulse
(PR)
are
used
as
input
for
patients'
risk
level
identification.
High-risk
non-risk
categories
considered
output
classification.
machine
techniques
such
LR,
Gaussian
NB,
SVM,
KNN
and
DT
Precision,
recall,
F1-score
evaluation.
The
decision
tree
gives
best
77.67
imbalanced
dataset.
2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP),
Journal Year:
2023,
Volume and Issue:
unknown, P. 1418 - 1423
Published: April 21, 2023
As
the
incidence
of
heart
disease
continues
to
rise
globally,
there
is
an
urgent
need
for
accurate
and
efficient
methods
detect
prevent
this
debilitating
condition.
To
address
need,
paper
proposes
a
machine
learning-based
medical
system
predicting
likelihood
occurrence
in
patients.
The
study
utilizes
UCI
dataset
analyze
multiple
indicators
using
eight
different
algorithms
identify
most
comprehensive
attributes
disease.
results
reveal
algorithm
with
highest
accuracy
reliable
attributes,
which
are
then
integrated
into
practical
treatment
system.
This
specifically
designed
effective
application
real-life
settings
improve
diagnosis
reduce
burden
on
hospitals.
proposed
has
significant
implications
enhancing
early
detection
management
disease,
thus
enabling
timely
intervention
treatment.
integration
learning
practice
potential
significantly
patient
outcomes,
healthcare
costs
advise
patients
receive
care
from
professionals
timely.
The
classification
and
prediction
of
blood
group
is
most
important
aspect
for
the
transfusion
blood.
In
present
situations,
they
are
done
in
laboratory
using
manual
process.
This
a
time-consuming
process
hence
need
energy.
To
overcome
constraints
conventional
methods
group,
artificial
intelligence
implemented.
includes
image
processing
techniques
with
segmentation
to
detect
group.
They
through
MATLAB
simulations
components.
Through
collecting
samples
classified
images
feature
extraction
leads
govern
variety
based
on
ABO
Rh
systems.
drawbacks
process,
developed
methodology
reduces
various
errors.
Thus,
technique
helps
determine
rapidly
without
any
