IGI Global eBooks,
Год журнала:
2025,
Номер
unknown, С. 1 - 20
Опубликована: Апрель 24, 2025
Artificial
intelligence
(AI)
is
a
field
of
computing
that
has
been
increasingly
applied
in
healthcare
services,
demonstrating
significant
potential
to
enhance
both
the
delivery
care
populations
and
management
human
resources.
This
study
based
on
literature
review
aims
evaluate
whether
use
AI
emergency
services
might
challenge
bioethical
principles
healthcare,
as
well
assess
its
improve
streamline
patient
triage.
Online
databases
grey
providing
open-access
documents
from
last
five
years
were
consulted
December
2024
January
2025.
process
resulted
total
20
documents,
which
analyzed
form
basis
this
article.
Articles
deemed
relevant
for
inclusion
if
their
abstracts
or
conclusions
demonstrated
correlation
between
identified
keywords
objectives
outlined
study.
npj Digital Medicine,
Год журнала:
2025,
Номер
8(1)
Опубликована: Янв. 31, 2025
The
confluence
of
new
technologies
with
artificial
intelligence
(AI)
and
machine
learning
(ML)
analytical
techniques
is
rapidly
advancing
the
field
precision
oncology,
promising
to
improve
diagnostic
approaches
therapeutic
strategies
for
patients
cancer.
By
analyzing
multi-dimensional,
multiomic,
spatial
pathology,
radiomic
data,
these
enable
a
deeper
understanding
intricate
molecular
pathways,
aiding
in
identification
critical
nodes
within
tumor's
biology
optimize
treatment
selection.
applications
AI/ML
oncology
are
extensive
include
generation
synthetic
e.g.,
digital
twins,
order
provide
necessary
information
design
or
expedite
conduct
clinical
trials.
Currently,
many
operational
technical
challenges
exist
related
data
technology,
engineering,
storage;
algorithm
development
structures;
quality
quantity
pipeline;
sharing
generalizability;
incorporation
into
current
workflow
reimbursement
models.
Frontiers in Medicine,
Год журнала:
2025,
Номер
12
Опубликована: Фев. 11, 2025
Artificial
intelligence
is
increasingly
influencing
healthcare,
providing
transformative
opportunities
and
challenges
for
nursing
practice.
This
review
critically
evaluates
the
integration
of
AI
in
nursing,
focusing
on
its
current
applications,
limitations,
areas
that
require
further
investigation.
A
comprehensive
analysis
recent
studies
highlights
use
clinical
decision
support
systems,
patient
monitoring,
education.
However,
several
barriers
to
successful
implementation
are
identified,
including
technical
constraints,
ethical
dilemmas,
need
workforce
adaptation.
Significant
gaps
literature
also
evident,
such
as
limited
development
nursing-specific
tools,
insufficient
long-term
impact
assessments,
absence
frameworks
tailored
contexts.
The
potential
reshape
personalized
care,
advance
robotics
address
global
health
explored
depth.
integrates
existing
knowledge
identifies
critical
future
research,
emphasizing
necessity
aligning
advancements
with
specific
needs
nursing.
Addressing
these
essential
fully
harness
AI's
while
reducing
associated
risks,
ultimately
enhancing
practice
improving
outcomes.
Journal of Clinical Medicine,
Год журнала:
2025,
Номер
14(2), С. 571 - 571
Опубликована: Янв. 17, 2025
Background/Objectives:
Acute
ischemic
stroke
(AIS)
is
a
leading
cause
of
mortality
and
disability
worldwide,
with
early
accurate
diagnosis
being
critical
for
timely
intervention
improved
patient
outcomes.
This
retrospective
study
aimed
to
assess
the
diagnostic
performance
two
advanced
artificial
intelligence
(AI)
models,
Chat
Generative
Pre-trained
Transformer
(ChatGPT-4o)
Claude
3.5
Sonnet,
in
identifying
AIS
from
diffusion-weighted
imaging
(DWI).
Methods:
The
DWI
images
total
110
cases
(AIS
group:
n
=
55,
healthy
controls:
55)
were
provided
AI
models
via
standardized
prompts.
models'
responses
compared
radiologists'
gold-standard
evaluations,
metrics
such
as
sensitivity,
specificity,
accuracy
calculated.
Results:
Both
exhibited
high
sensitivity
detection
(ChatGPT-4o:
100%,
Sonnet:
94.5%).
However,
ChatGPT-4o
demonstrated
significantly
lower
specificity
(3.6%)
Sonnet
(74.5%).
agreement
radiologists
was
poor
(κ
0.036;
%95
CI:
-0.013,
0.085)
but
good
0.691;
0.558,
0.824).
In
terms
hemispheric
localization
accuracy,
(67.2%)
outperformed
(32.7%).
Similarly,
specific
localization,
(30.9%)
showed
greater
than
(7.3%),
these
differences
statistically
significant
(p
<
0.05).
Conclusions:
highlights
superior
DWI.
Despite
its
advantages,
both
notable
limitations
emphasizing
need
further
development
before
achieving
full
clinical
applicability.
These
findings
underline
potential
tools
radiological
diagnostics
while
acknowledging
their
current
limitations.
Journal of Lipid and Atherosclerosis,
Год журнала:
2025,
Номер
14(1), С. 77 - 77
Опубликована: Янв. 1, 2025
Dyslipidemia
dramatically
increases
the
risk
of
cardiovascular
diseases,
necessitating
appropriate
treatment
techniques.
Generative
AI
(GenAI),
an
advanced
technology
that
can
generate
diverse
content
by
learning
from
vast
datasets,
provides
promising
new
opportunities
to
address
this
challenge.
GenAI-powered
frequently
asked
questions
systems
and
chatbots
offer
continuous,
personalized
support
addressing
lifestyle
modifications
medication
adherence,
which
is
crucial
for
patients
with
dyslipidemia.
These
tools
also
help
promote
health
literacy
making
information
more
accessible
reliable.
GenAI
helps
healthcare
providers
construct
clinical
case
scenarios,
training
materials,
evaluation
tools,
supports
professional
development
evidence-based
practice.
Multimodal
analyzes
food
images
nutritional
deliver
dietary
recommendations
tailored
each
patient's
condition,
improving
long-term
management
those
Moreover,
using
image
generation
enhances
visual
quality
educational
materials
both
professionals,
allowing
create
real-time,
customized
aids.
To
apply
successfully,
must
develop
GenAI-related
abilities,
such
as
prompt
engineering
critical
GenAI-generated
data.
Abstract
Generative
artificial
intelligence
has
brought
disruptive
innovations
in
health
care
but
faces
certain
challenges.
Retrieval-augmented
generation
(RAG)
enables
models
to
generate
more
reliable
content
by
leveraging
the
retrieval
of
external
knowledge.
In
this
perspective,
we
analyze
possible
contributions
that
RAG
could
bring
equity,
reliability,
and
personalization.
Additionally,
discuss
current
limitations
challenges
implementing
medical
scenarios.
Social
anxiety
(SA)
has
become
increasingly
prevalent.
Traditional
coping
strategies
often
face
accessibility
challenges.
Generative
AI
(GenAI),
known
for
their
knowledgeable
and
conversational
capabilities,
are
emerging
as
alternative
tools
mental
well-being.
With
the
increased
integration
of
GenAI,
it
is
important
to
examine
individuals'
attitudes
trust
in
GenAI
chatbots'
support
SA.
Through
a
mixed-method
approach
that
involved
surveys
(n
=
159)
interviews
17),
we
found
individuals
with
severe
symptoms
tended
embrace
chatbots
more
readily,
valuing
non-judgmental
perceived
emotional
comprehension.
However,
those
milder
prioritized
technical
reliability.
We
identified
factors
influencing
trust,
such
ability
generate
empathetic
responses
its
context-sensitive
limitations,
which
were
particularly
among
also
discuss
design
implications
use
fostering
cognitive
practical
considerations.
International Journal of Infectious Diseases,
Год журнала:
2025,
Номер
unknown, С. 107838 - 107838
Опубликована: Фев. 1, 2025
Highlights•Identified
three
novel
combinations
of
transcriptional
biomarkers
for
TB
screening•Novel
met
WHO's
minimum
benchmarks
triage
test•Transcriptional
are
better
suited
screening
than
confirmatory
tests•Bacterial
load
in
patients
affects
the
effectiveness
biomarkersAbstractObjectivesNon-sputum-based
methods
active
case
finding
a
priority
ending
tuberculosis.
We
sought
to
identify
and
evaluate
blood
suitable
tuberculosis
screening.MethodsWe
integrated
five
RNA-seq
datasets
from
global
identified
genes
that
differentially
expressed
between
healthy
controls,
using
resampling
exhaustive
testing.
Three
candidate
biomarker
were
seven
microarray
small-scale
clinical
samples.
The
performance
these
was
evaluated
cohort
close
contacts
pulmonary
(PTB)
patients,
results
compared
with
Xpert
HR.ResultsWe
3-gene
combinations,
each
containing
two
upregulated
(FCGR1A,
BATF2,
or
GBP5)
one
downregulated
gene
(KLF2),
used
screen
352
PTB.
distinguished
confirmed
PTB
other
participants
AUCs
ranging
0.848
0.870.
With
specificity
fixed
at
70%,
all
showed
sensitivities
87.5%.
In
205
presumptive
distinguishing
diseases
ranged
0.784
0.806.
At
70%
specificity,
75.9%
81.5%,
significantly
higher
larger
sputum
bacterial
loads.
performances
diagnosis
comparable
HR.ConclusionThe
transcriptomic
this
study
performed
well
screening,
nearly
meeting
WHO
test
potential
utility
development
new
tools.
Abstract
Conversational
agents
are
increasingly
used
in
healthcare,
with
Large
Language
Models
(LLMs)
significantly
enhancing
their
capabilities.
When
integrated
into
social
robots,
LLMs
offer
the
potential
for
more
natural
interactions.
However,
while
promise
numerous
benefits,
they
also
raise
critical
ethical
concerns,
particularly
regarding
hallucinations
and
deceptive
patterns.
In
this
case
study,
we
observed
a
pattern
of
behavior
commercially
available
LLM-based
care
software
robots.
The
LLM-equipped
robot
falsely
claimed
to
have
medication
reminder
functionalities,
not
only
assuring
users
its
ability
manage
schedules
but
proactively
suggesting
capability
despite
lacking
it.
This
poses
significant
risks
healthcare
environments,
where
reliability
is
paramount.
Our
findings
highlights
safety
concerns
surrounding
deployment
LLM-integrated
robots
emphasizing
need
oversight
prevent
potentially
harmful
consequences
vulnerable
populations.
