Applying Large Language Models to Interpret Qualitative Interviews in Healthcare
Studies in health technology and informatics,
Journal Year:
2024,
Volume and Issue:
unknown
Published: Aug. 22, 2024
To
address
the
persistent
challenges
in
healthcare,
it
is
crucial
to
incorporate
firsthand
experiences
and
perspectives
from
stakeholders
such
as
patients
healthcare
professionals.
However,
current
process
of
collecting,
analyzing
interpreting
qualitative
data,
interviews,
slow
labor-intensive.
expedite
this
enhance
efficiency,
automated
approaches
aim
extract
meaningful
themes
accelerate
interpretation,
but
topic
modeling
reduce
richness
raw
data.
Here,
we
evaluate
whether
Large
Language
Models
can
be
used
support
semi-automated
interpretation
interview
We
compare
a
novel
approach
based
on
LLMs
manually
identified
across
two
different
datasets.
This
exploratory
study
finds
that
have
potential
incorporating
human
more
widely
advancement
sustainable
systems.
Language: Английский
Navigating Digital Tools in Hospitals: Practical Recommendations for New Users from a Qualitative Interview Study (Preprint)
Published: May 1, 2024
BACKGROUND
The
digitalization
of
health
care
organizations
is
an
integral
part
a
clinician’s
daily
life,
making
it
vital
for
professionals
(HCPs)
to
understand
and
effectively
use
digital
tools
in
hospital
settings.
However,
clinicians
often
express
lack
preparedness
their
work
environments.
Particularly,
new
clinical
end
users,
encompassing
medical
nursing
students,
seasoned
transitioning
environments,
experienced
practitioners
encountering
technologies,
face
critically
intense
learning
periods,
with
adequate
time
tools,
resulting
difficulties
integrating
adopting
these
into
practice<i>.</i>
OBJECTIVE
This
study
aims
comprehensively
collect
advice
from
HCPs
Switzerland
guide
users
on
how
initiate
engagement
ITs
within
METHODS
We
conducted
qualitative
interviews
52
across
Switzerland,
representing
24
specialties
14
hospitals.
were
transcribed
verbatim
analyzed
through
inductive
thematic
analysis.
Codes
developed
iteratively,
themes
aggregated
dimensions
refined
collaborative
discussions.
RESULTS
Ten
emerged
the
interview
data,
namely
(1)
tool
understanding,
(2)
peer-based
strategies,
(3)
experimental
approaches,
(4)
knowledge
exchange
support,
(5)
training
(6)
proactive
innovation,
(7)
adaptive
technology
mindset,
(8)
critical
thinking
(9)
dealing
emotions,
(10)
empathy
human
factors.
Consequently,
we
devised
10
recommendations
specific
approach
following:
take
get
know
you
are
working
with;
proactively
ask
colleagues;
simply
try
out
practice;
where
help
information;
sufficient
training;
embrace
curiosity
pursue
innovation;
maintain
open
adaptable
mindset;
keep
your
base;
overcome
fears,
never
lose
patient
focus.
CONCLUSIONS
Our
emphasized
importance
comprehensive
approaches
technologies
based
Swiss
Moreover,
have
implications
educators
instructors,
providing
effective
methods
instruct
support
enabling
them
novel
proficiently.
Therefore,
advocate
institutions
academic
educators,
regulatory
bodies
prioritize
cultivating
technological
readiness
optimize
IT
care.
Language: Английский