Clinical and Translational Science,
Год журнала:
2025,
Номер
18(3)
Опубликована: Март 1, 2025
ABSTRACT
Approaches
to
artificial
intelligence
and
machine
learning
(AI/ML)
continue
advance
in
the
field
of
drug
development.
A
sound
understanding
underlying
concepts
guiding
principles
AI/ML
implementation
is
a
prerequisite
identifying
which
approach
most
appropriate
based
on
context.
This
tutorial
focuses
popular
eXtreme
gradient
boosting
(XGBoost)
algorithm
for
classification
regression
simple
clinical
trial‐like
datasets.
Emphasis
placed
relating
code
implementation.
In
doing
so,
aim
reader
gain
knowledge
about
become
better
versed
with
how
implement
functions
relevant
development
questions.
turn,
this
will
provide
practical
ML
experience
can
be
applied
algorithms
problems
beyond
scope
tutorial.
Journal of Perinatal Medicine,
Год журнала:
2024,
Номер
52(9), С. 899 - 913
Опубликована: Окт. 9, 2024
Abstract
Artificial
intelligence
(AI)
has
emerged
as
a
transformative
technology
in
the
field
of
healthcare,
offering
significant
advancements
various
medical
disciplines,
including
obstetrics.
The
integration
artificial
into
3D/4D
ultrasound
analysis
fetal
facial
profiles
presents
numerous
benefits.
By
leveraging
machine
learning
and
deep
algorithms,
AI
can
assist
accurate
efficient
interpretation
complex
data,
enabling
healthcare
providers
to
make
more
informed
decisions
deliver
better
prenatal
care.
One
such
innovation
that
significantly
improved
is
imaging.
In
conclusion,
data
for
offers
benefits,
accuracy,
consistency,
efficiency
diagnosis
Diagnostic and Interventional Radiology,
Год журнала:
2024,
Номер
unknown
Опубликована: Сен. 2, 2024
Stroke
is
a
neurological
emergency
requiring
rapid,
accurate
diagnosis
to
prevent
severe
consequences.
Early
crucial
for
reducing
morbidity
and
mortality.
Artificial
intelligence
(AI)
support
tools,
such
as
Chat
Generative
Pre-trained
Transformer
(ChatGPT),
offer
rapid
diagnostic
advantages.
This
study
assesses
ChatGPT's
accuracy
in
interpreting
diffusion-weighted
imaging
(DWI)
acute
stroke
diagnosis.
Neurospine,
Год журнала:
2024,
Номер
21(3), С. 833 - 841
Опубликована: Сен. 27, 2024
To
develop
and
evaluate
a
technique
using
convolutional
neural
networks
(CNNs)
for
the
computer-assisted
diagnosis
of
cervical
spine
fractures
from
radiographic
x-ray
images.
By
leveraging
deep
learning
techniques,
study
might
potentially
lead
to
improved
patient
outcomes
clinical
decision-making.
Introduction
Diabetic
retinopathy
(DR)
is
a
leading
cause
of
blindness
globally,
emphasizing
the
urgent
need
for
efficient
diagnostic
tools.
Machine
learning,
particularly
convolutional
neural
networks
(CNNs),
has
shown
promise
in
automating
diagnosis
retinal
conditions
with
high
accuracy.
This
study
evaluates
two
CNN
models,
VGG16
and
InceptionV3,
classifying
optical
coherence
tomography
(OCT)
images
into
four
categories:
normal,
choroidal
neovascularization,
diabetic
macular
edema
(DME),
drusen.
Methods
Using
83,000
OCT
across
categories,
CNNs
were
trained
tested
via
Python-based
libraries,
including
TensorFlow
Keras.
Metrics
such
as
accuracy,
sensitivity,
specificity
analyzed
confusion
matrices
performance
graphs.
Comparisons
dataset
sizes
evaluated
impact
on
model
accuracy
tools
deployed
JupyterLab.
Results
InceptionV3
achieved
between
85%
95%,
peaking
at
94%
outperforming
(92%).
Larger
datasets
improved
sensitivity
by
7%
all
highest
normal
drusen
classifications.
like
positively
correlated
size.
Conclusions
The
confirms
CNNs'
potential
diagnostics,
achieving
classification
Limitations
included
reliance
grayscale
computational
intensity,
which
hindered
finer
distinctions.
Future
work
should
integrate
data
augmentation,
patient-specific
variables,
lightweight
architectures
to
optimize
clinical
use,
reducing
costs
improving
outcomes.
Translational Medicine,
Год журнала:
2025,
Номер
11(6), С. 562 - 576
Опубликована: Янв. 26, 2025
Cardiovascular
diseases
(CVD)
remain
the
leading
cause
of
death
worldwide,
including
in
Russian
Federation.
Early
detection
and
continuous
monitoring
are
crucial
to
reduce
mortality
improve
patient
outcomes.
This
article
examines
use
artificial
intelligence
technologies
treatment
cardiovascular
diseases,
emphasizing
their
potential
for
development
field
cardiology.
A
comprehensive
literature
search
was
conducted
using,
focusing
on
studies
which
used
diagnose,
treat,
monitor
diseases.
The
review
includes
an
analysis
various
methods,
machine
learning
neural
networks,
effectiveness
detecting
heart
rhythm
disorders
using
wireless
sensors
wearable
devices.
highlights
promising
solutions
developed
both
internationally
Federation,
provides
practical
recommendations
implementation.
By
addressing
existing
research
gaps
offering
directions
future,
aims
understanding
application
cardiology,
ultimately
contributes
improved
care
Journal of Clinical Ultrasound,
Год журнала:
2025,
Номер
unknown
Опубликована: Янв. 29, 2025
ABSTRACT
This
narrative
review
examines
the
integration
of
Artificial
Intelligence
(AI)
in
prenatal
care,
particularly
managing
pregnancies
complicated
by
Fetal
Growth
Restriction
(FGR).
AI
provides
a
transformative
approach
to
diagnosing
and
monitoring
FGR
leveraging
advanced
machine‐learning
algorithms
extensive
data
analysis.
Automated
fetal
biometry
using
has
demonstrated
significant
precision
identifying
structures,
while
predictive
models
analyzing
Doppler
indices
maternal
characteristics
improve
reliability
adverse
outcome
predictions.
enabled
early
detection
stratification
risk,
facilitating
targeted
strategies
individualized
delivery
plans,
potentially
improving
neonatal
outcomes.
For
instance,
studies
have
shown
enhancements
detecting
placental
insufficiency‐related
abnormalities
when
tools
are
integrated
with
traditional
ultrasound
techniques.
also
explores
challenges
such
as
algorithm
bias,
ethical
considerations,
standardization,
underscoring
importance
global
accessibility
regulatory
frameworks
ensure
equitable
implementation.
The
potential
revolutionize
care
highlights
urgent
need
for
further
clinical
validation
interdisciplinary
collaboration.
