Journal of Epidemiology and Global Health,
Journal Year:
2024,
Volume and Issue:
14(3), P. 645 - 657
Published: Aug. 14, 2024
Abstract
The
last
decade
has
seen
major
advances
and
growth
in
internet-based
surveillance
for
infectious
diseases
through
advanced
computational
capacity,
growing
adoption
of
smart
devices,
increased
availability
Artificial
Intelligence
(AI),
alongside
environmental
pressures
including
climate
land
use
change
contributing
to
threat
spread
pandemics
emerging
diseases.
With
the
increasing
burden
COVID-19
pandemic,
need
developing
novel
technologies
integrating
data
approaches
improving
disease
is
greater
than
ever.
In
this
systematic
review,
we
searched
scientific
literature
research
on
or
digital
influenza,
dengue
fever
from
2013
2023.
We
have
provided
an
overview
recent
(EID),
describing
changes
landscape,
with
recommendations
future
directed
at
public
health
policymakers,
healthcare
providers,
government
departments
enhance
traditional
detecting,
monitoring,
reporting,
responding
dengue,
COVID-19.
Open Forum Infectious Diseases,
Journal Year:
2024,
Volume and Issue:
11(3)
Published: Jan. 31, 2024
Abstract
With
the
rapid
advancement
of
artificial
intelligence
(AI),
field
infectious
diseases
(ID)
faces
both
innovation
and
disruption.
AI
its
subfields
including
machine
learning,
deep
large
language
models
can
support
ID
clinicians’
decision
making
streamline
their
workflow.
may
help
ensure
earlier
detection
disease,
more
personalized
empiric
treatment
recommendations,
allocation
human
resources
to
higher-yield
antimicrobial
stewardship
infection
prevention
strategies.
is
unlikely
replace
role
experts,
but
could
instead
augment
it.
However,
limitations
will
need
be
carefully
addressed
mitigated
safe
effective
implementation.
experts
engaged
in
implementation
by
participating
training
education,
identifying
use
cases
for
improve
patient
care,
designing,
validating
evaluating
algorithms,
continuing
advocate
vital
care.
Buildings,
Journal Year:
2025,
Volume and Issue:
15(4), P. 527 - 527
Published: Feb. 9, 2025
Subway
construction
accident
reports
often
take
a
lot
of
time
and
personnel
to
analyze
contain
large
amount
data
that
require
professional
identification,
which
increases
the
difficulty
analysis.
This
study
aims
use
Generative
Pre-trained
Transformer
(GPT)
models
for
automated
analysis
subway
investigation
reports,
with
goal
improving
efficiency
identification
By
analyzing
dataset
50
this
developed
Accident
Investigation
Report
(AIR)
Agent,
utilizes
GPTs
automatically
identify
types
extract
key
details
from
reports.
The
chatbot
is
composed
three
core
modules:
conversation
module,
an
instruction
knowledge
module.
Ablation
studies
were
performed
validate
AIR
Agent’s
efficiency,
validation
results
show
Agent
achieves
accuracy
80.32%
when
new
brief
conclusion,
demonstrating
ability
format
structure
in
consistent
correct
manner.
These
findings
suggest
can
significantly
reduce
manual
effort
involved
report
enhance
overall
thereby
effectiveness
management.
Imaging Science in Dentistry,
Journal Year:
2024,
Volume and Issue:
54(3), P. 271 - 271
Published: Jan. 1, 2024
Recent
advancements
in
artificial
intelligence
(AI),
particularly
tools
such
as
ChatGPT
developed
by
OpenAI,
a
U.S.-based
AI
research
organization,
have
transformed
the
healthcare
and
education
sectors.
This
study
investigated
effectiveness
of
answering
dentistry
exam
questions,
demonstrating
its
potential
to
enhance
professional
practice
patient
care.
International Dental Journal,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Aug. 1, 2024
Given
the
increasing
interest
in
using
large
language
models
(LLMs)
for
self-diagnosis,
this
study
aimed
to
evaluate
comprehensiveness
of
two
prominent
LLMs,
ChatGPT-3.5
and
ChatGPT-4,
addressing
common
queries
related
gingival
endodontic
health
across
different
contexts
query
types.
BACKGROUND
Large
language
models
(LLMs)
are
advanced
artificial
neural
networks
trained
on
extensive
datasets
to
accurately
understand
and
generate
natural
language.
While
they
have
received
much
attention
demonstrated
potential
in
digital
health,
their
application
mental
particularly
clinical
settings,
has
generated
considerable
debate.
OBJECTIVE
This
systematic
review
aims
critically
assess
the
use
of
LLMs
specifically
focusing
applicability
efficacy
early
screening,
interventions,
settings.
By
systematically
collating
assessing
evidence
from
current
studies,
our
work
analyzes
models,
methodologies,
data
sources,
outcomes,
thereby
highlighting
challenges
present,
prospects
for
use.
METHODS
Adhering
PRISMA
(Preferred
Reporting
Items
Systematic
Reviews
Meta-Analyses)
guidelines,
this
searched
5
open-access
databases:
MEDLINE
(accessed
by
PubMed),
IEEE
Xplore,
Scopus,
JMIR,
ACM
Digital
Library.
Keywords
used
were
(<i>mental
health</i>
OR
<i>mental
illness</i>
disorder</i>
<i>psychiatry</i>)
AND
(<i>large
models</i>).
study
included
articles
published
between
January
1,
2017,
April
30,
2024,
excluded
languages
other
than
English.
RESULTS
In
total,
40
evaluated,
including
15
(38%)
health
conditions
suicidal
ideation
detection
through
text
analysis,
7
(18%)
as
conversational
agents,
18
(45%)
applications
evaluations
health.
show
good
effectiveness
detecting
issues
providing
accessible,
destigmatized
eHealth
services.
However,
assessments
also
indicate
that
risks
associated
with
might
surpass
benefits.
These
include
inconsistencies
text;
production
hallucinations;
absence
a
comprehensive,
benchmarked
ethical
framework.
CONCLUSIONS
examines
inherent
risks.
The
identifies
several
issues:
lack
multilingual
annotated
experts,
concerns
regarding
accuracy
reliability
content,
interpretability
due
“black
box”
nature
LLMs,
ongoing
dilemmas.
clear,
framework;
privacy
issues;
overreliance
both
physicians
patients,
which
could
compromise
traditional
medical
practices.
As
result,
should
not
be
considered
substitutes
professional
rapid
development
underscores
valuable
aids,
emphasizing
need
continued
research
area.
CLINICALTRIAL
PROSPERO
CRD42024508617;
https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=508617
Journal of Radiological Protection,
Journal Year:
2024,
Volume and Issue:
44(1), P. 013502 - 013502
Published: Jan. 17, 2024
Abstract
This
study
assesses
the
efficacy
of
Generative
Pre-Trained
Transformers
(GPT)
published
by
OpenAI
in
specialised
domains
radiological
protection
and
health
physics.
Utilising
a
set
1064
surrogate
questions
designed
to
mimic
physics
certification
exam,
we
evaluated
models’
ability
accurately
respond
across
five
knowledge
domains.
Our
results
indicated
that
neither
model
met
67%
passing
threshold,
with
GPT-3.5
achieving
45.3%
weighted
average
GPT-4
attaining
61.7%.
Despite
GPT-4’s
significant
parameter
increase
multimodal
capabilities,
it
demonstrated
superior
performance
all
categories
yet
still
fell
short
score.
The
study’s
methodology
involved
simple,
standardised
prompting
strategy
without
employing
prompt
engineering
or
in-context
learning,
which
are
known
potentially
enhance
performance.
analysis
revealed
formatted
answers
more
correctly,
despite
higher
overall
accuracy.
findings
suggest
while
show
promise
handling
domain-specific
content,
their
application
field
should
be
approached
caution,
emphasising
need
for
human
oversight
verification.
