An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review
Information,
Journal Year:
2024,
Volume and Issue:
15(4), P. 235 - 235
Published: April 19, 2024
Support
vector
machines
(SVMs)
are
well-known
machine
learning
algorithms
for
classification
and
regression
applications.
In
the
healthcare
domain,
they
have
been
used
a
variety
of
tasks
including
diagnosis,
prognosis,
prediction
disease
outcomes.
This
review
is
an
extensive
survey
on
current
state-of-the-art
SVMs
developed
applied
in
medical
field
over
years.
Many
variants
SVM-based
approaches
to
enhance
their
generalisation
capabilities.
We
illustrate
most
interesting
models
that
improve
performance
metrics
benchmark
datasets,
hybrid
methods
combine,
instance,
optimization
with
SVMs.
even
report
results
found
applications
related
real-world
data.
Several
issues
around
SVMs,
such
as
selection
hyperparameters
from
data
questionable
quality,
discussed
well.
The
several
introduced
years
could
be
useful
designing
new
critical
fields
healthcare,
where
accuracy,
specificity,
other
crucial.
Finally,
research
trends
future
directions
underlined.
Language: Английский
A machine learning based death risk analysis and prediction of ST-segment elevation myocardial infarction (STEMI) patients
Computers in Biology and Medicine,
Journal Year:
2025,
Volume and Issue:
188, P. 109839 - 109839
Published: Feb. 14, 2025
Language: Английский
Predictive value of machine learning for in-hospital mortality risk in acute myocardial infarction: A systematic review and meta-analysis
International Journal of Medical Informatics,
Journal Year:
2025,
Volume and Issue:
198, P. 105875 - 105875
Published: March 8, 2025
Language: Английский
Fair and explainable Myocardial Infarction (MI) prediction: Novel strategies for feature selection and class imbalance correction
Simon Bin Akter,
No information about this author
Sumya Akter,
No information about this author
Moon Das Tuli
No information about this author
et al.
Computers in Biology and Medicine,
Journal Year:
2024,
Volume and Issue:
184, P. 109413 - 109413
Published: Nov. 29, 2024
Language: Английский
Navigating AI in Cardiology: A Scoping Review of Integration through Clinical Decision Support Systems for Acute Coronary Syndrome
Shuhui Chen,
No information about this author
Chin‐Chieh Wu,
No information about this author
Kuan‐Fu Chen
No information about this author
et al.
Biomedical Journal,
Journal Year:
2025,
Volume and Issue:
unknown, P. 100853 - 100853
Published: April 1, 2025
The
integration
of
AI
in
diagnosing
and
managing
ACS
shows
increasing
promise,
yet
challenges
remain
translating
AI-CDSS
into
clinical
practice.
This
study
evaluates
the
advancements
limitations
for
over
past
three
years,
purpose
understanding
scope,
limitations,
potential
ACS.
We
conducted
a
systematic
review
recent
literature,
adhering
to
guidelines
reviews.
applied
QUADAS-2
PROBAST
tools
quality
assessment,
focusing
on
biases
designs.
Ten
studies
about
management
underwent
critical
analysis,
emphasizing
strength
their
research
methods
thoroughness
prospective
validation
ensure
theoretical
integrity
practical
reliability.
Our
reveals
that
while
discourse
around
intensifies,
obstacles
hinder
efficacy
settings.
These
include
tests
unrepresentative
patient
selection,
pointing
need
rigorous
inclusive
samples.
lack
sufficient
external
also
raises
concerns
utility
AI-CDSS.
result
is
gap
between
benefits
actual
impact
improving
diagnostic
accuracy
outcomes
identified.
While
promise
accuracy,
treatment
efficacy,
workflows
ACS,
this
highlights
imperative
enhance
model
validation,
including
address
lingering
gaps.
Improving
design
mitigating
crucial
acceptance
effectiveness
acute
cardiac
care
Language: Английский
Prediction of Hospital Mortality in Patients with ST Segment Elevation Myocardial Infarction: Evolution of Risk Measurement Techniques and Assessment of Their Effectiveness (Review)
Sovremennye tehnologii v medicine,
Journal Year:
2024,
Volume and Issue:
16(4), P. 61 - 61
Published: Aug. 30, 2024
Risk
stratification
of
hospital
mortality
in
patients
with
ST
segment
elevation
myocardial
infarction
on
the
electrocardiogram
is
an
important
part
specialized
medical
care
provision.The
systematic
review
presents
scientific
literature
data
characterizing
predictive
value
both
classical
prognostic
scales
(GRACE,
CADDILLAC,
TIMI
risk
score
for
STEMI,
RECORD,
etc.)
and
new
measurement
tools
developed
basis
modern
machine
learning
techniques.Most
studies
this
issue
are
often
focused
search
predictors
adverse
events,
which
allow
to
detail
relations
between
indicators
clinical
functional
status
end
point
study.Here,
task
develop
algorithms
characterized
by
explainable
artificial
intelligence
trusted
doctors.
Language: Английский
Vascular medicine in the 21st century: Embracing comprehensive vasculature evaluation and multidisciplinary treatment
Yoram Chaiter,
No information about this author
Daniel Fink,
No information about this author
Yossy Machluf
No information about this author
et al.
World Journal of Clinical Cases,
Journal Year:
2024,
Volume and Issue:
12(27), P. 6032 - 6044
Published: July 29, 2024
The
field
of
vascular
medicine
has
undergone
a
profound
transformation
in
the
21
Language: Английский
GAMe-BiLSTM: a novel modified metaheuristic deep learning technique for non-ST-segment elevation myocardial infarction classification
International Journal of Information Technology,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Oct. 3, 2024
Language: Английский
Miyokard Enfarktüsü Hastalarının Tespitinde Doğrusal Olmayan Özniteliklerin Performans Analizi
Afyon Kocatepe University Journal of Sciences and Engineering,
Journal Year:
2024,
Volume and Issue:
24(6), P. 1499 - 1505
Published: Dec. 2, 2024
Kalp
rahatsızlıklarından
biri
olan
Miyokard
enfarktüsü
(ME),
kalbin
bölgelerine
kısmen
veya
tamamen
kan
akışının
kesilmesi
sonucunda
kalp
kaslarına
zarar
vermesi
durumudur.
Bu
durum
kalbe
kalıcı
hasar
vermekte
ve
hayati
risk
oluşturmaktadır.
ME
tespiti
için
kolay
ucuz
elde
edilebilen
elektrokardiyogram
(EKG)
sinyalleri
uzmanlar
tarafından
kullanılmaktadır.
Fakat,
bazı
EKG
üzerinde
ile
ilişkili
anormallikler
gözden
kaçırılabilmekte
hatta
farklı
yorumlanabilmektedir.
Karşılaşılan
problemlere
çözüm
olması
amacıyla
yapay
zekâ
tabanlı
karar
destek
sistemleri
otomatik
çalışmalar
devam
etmektedir.
çalışmada
52
sağlıklı
148
bireye
ait
12
derivasyonlu
sinyallerinden
lead-II
derivasyonu
analiz
edilmiştir.
Shannon
entropi,
Renyi
Dalgacık
Kolmogorov-Sinai
entropi
Bulanık
olmak
üzere
beş
yöntem
edilen
öznitelikler
kullanılarak
tespitindeki
başarımlar
araştırılmıştır.
Her
bir
ölçümünün
gürültülü
gürültüsüz
performansları
karşılaştırılmıştır.
K-en
yakın
komşu
(kNN),
Naive
Bayes
Topluluk
sınıflandırıcı
algoritmaları
Beş
yöntemden
özniteliklerin
sınıflandırılması
sonucu
en
yüksek
doğruluk
değeri
%87,72
değer,
sinyallerin
kNN
sınıflandırıcısının
kullanılması
Tüm
birlikte
%90,99
genel
doğruluk,
%95,58
hassasiyet,
%71,55
özgünlük
değerleri
En
bu
sinyal
kullanımı