Using ChatGPT for writing hospital inpatient discharge summaries – perspectives from an inpatient infectious diseases service
BMC Health Services Research,
Год журнала:
2025,
Номер
25(1)
Опубликована: Фев. 10, 2025
Hospital
discharge
summaries
are
important
tools
for
communication
between
healthcare
professionals.
They
convey
events
that
occurred
during
hospitalisation,
as
well
the
subsequent
follow-up
plans.
Artificial
intelligence
models
can
be
used
to
summarise
information
succinctly
from
large
amounts
of
raw
data
input.
We
explored
ChatGPT's
ability
generate
effective
assist
junior
doctors
in
writing
these
documents.
constructed
three
hypothetical
scenarios
inpatient
encounters,
with
different
outcomes:
i)
home
a
general
practitioner,
ii)
stepdown
facility
further
physical
rehabilitation,
iii)
transfer
tertiary
centre
more
advanced
care.
ChatGPT
was
scenarios.
The
quality
responses
provided
were
evaluated.
able
provide
an
framework
summaries.
It
processed
volumes
text,
summarising
pertinent
issues
and
communicating
plans
clearly.
is
potentially
useful
tool
documentation
clinicians.
However,
pitfalls
remain,
where
close
reading
still
required
ensure
veracity
output
provided.
synthesize
patient
long
prosaic
format
structured
summary.
Future
prospective
study
could
evaluate
if
this
by
helpful
aid
learning
about
efficiently.
Язык: Английский
How to write a good discharge summary: a primer for junior physicians
Postgraduate Medical Journal,
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 17, 2025
A
discharge
summary
is
an
important
clinical
document
that
summarizes
a
patient's
information
and
relevant
events
occurred
during
hospitalization.
It
serves
as
detailed
handover
of
the
most
recent
updated
medical
case
records
to
general
practitioners,
who
continue
longitudinal
follow-up
with
patients
in
community
future
care
providers.
copy
redacted/abbreviated
form
also
usually
given
their
caregivers
so
information,
such
diagnoses,
medication
changes,
return
advice,
plans,
clearly
documented.
However,
reality,
summaries
are
often
written
by
junior
physicians
may
be
inexperienced
or
have
lacked
training
this
area,
audits
reveal
poorly
unclear,
inaccurate,
lack
details.
Therefore,
article,
we
sought
develop
simple
"DISCHARGED"
framework
outlines
components
derived
from
systematic
search
literature
further
discuss
several
pedagogical
strategies
for
assessing
writing.
Язык: Английский
Using Large Language Models to Extract Core Injury Information From Emergency Department Notes
Journal of Korean Medical Science,
Год журнала:
2024,
Номер
39(46)
Опубликована: Янв. 1, 2024
Injuries
pose
a
significant
global
health
challenge
due
to
their
high
incidence
and
mortality
rates.
Although
injury
surveillance
is
essential
for
prevention,
it
resource-intensive.
This
study
aimed
develop
validate
locally
deployable
large
language
models
(LLMs)
extract
core
injury-related
information
from
Emergency
Department
(ED)
clinical
notes.
Язык: Английский
Evaluating the Impact of Artificial Intelligence (AI) on Clinical Documentation Efficiency and Accuracy Across Clinical Settings: A Scoping Review
Cureus,
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 19, 2024
Artificial
intelligence
(AI)
technologies
(natural
language
processing
(NLP),
speech
recognition
(SR),
and
machine
learning
(ML))
can
transform
clinical
documentation
in
healthcare.
This
scoping
review
evaluates
the
impact
of
AI
on
accuracy
efficiency
across
various
settings
(hospital
wards,
emergency
departments,
outpatient
clinics).
We
found
176
articles
by
applying
a
specific
search
string
Ovid.
To
ensure
more
comprehensive
process,
we
also
performed
manual
searches
PubMed
BMJ,
examining
any
relevant
references
encountered.
In
this
way,
were
able
to
add
46
articles,
resulting
222
total.
After
removing
duplicates,
208
screened.
led
inclusion
36
studies.
mostly
interested
discussing
technologies,
such
as
NLP,
ML,
SR,
their
documentation.
that
our
research
reflected
recent
work,
focused
efforts
studies
published
2019
beyond.
criterion
was
pilot-tested
beforehand
necessary
adjustments
made.
comparing
screened
independently,
ensured
inter-rater
reliability
(Cohen's
kappa=1.0),
data
extraction
completed
these
articles.
conducted
study
according
Preferred
Reporting
Items
for
Systematic
Reviews
Meta-Analyses
(PRISMA)
guidelines.
shows
improvements
using
with
an
emphasis
efficiency.
There
reduction
clinician
workload,
streamlining
processes.
Subsequently,
doctors
had
time
patient
care.
However,
raised
challenges
surrounding
use
settings.
These
included
management
errors,
legal
liability,
integration
electronic
health
records
(EHRs).
some
ethical
concerns
regarding
data.
massive
potential
improving
day-to-day
work
life
is
needed
address
many
associated
its
use.
Studies
demonstrate
improved
AI.
With
better
regulatory
frameworks,
implementation,
research,
significantly
reduce
burden
placed
Язык: Английский