Digital Health,
Journal Year:
2025,
Volume and Issue:
11
Published: April 1, 2025
Digital
communication
between
patients
and
healthcare
teams
is
increasing.
Most
find
this
effective,
yet
many
remain
digitally
isolated,
a
social
determinant
of
health.
This
study
investigates
patient
attitudes
toward
healthcare's
newest
digital
assistant,
the
chatbot,
perceptions
regarding
access.
We
conducted
mixed
methods
among
users
large
system's
chatbot
integrated
within
an
electronic
health
record.
purposively
oversampled
by
race
ethnicity
to
survey
617/3089
(response
rate
20%)
online
using
de
novo
validated
items.
In
addition,
we
semi-structured
interviews
with
(n
=
46)
sampled
based
on
diversity,
age,
or
select
responses
November
2022
May
2024.
surveys,
213/609
(35.0%)
felt
they
could
not
understand
completely,
376/614
(61.2%)
did
completely
them.
Of
238
who
understood
178
(74.8%)
believed
was
intended
help
them
access
healthcare;
in
comparison,
376
understood,
155
(41%)
(p
<
0.001).
interviews,
themes
observed,
Black,
Hispanic,
less
educated,
younger,
lower-income
participants
expressed
more
positivity
about
aiding
access,
stating
convenience
perceived
absence
judgment
bias.
Patients'
experience
appears
affect
their
perception
intent
chatbot's
implementation;
those
adept
at
historically
trusting
groups
may
prefer
quick,
non-judgmental
answer
questions
via
rather
than
human
interaction.
Although
our
findings
are
limited
one
existing
users,
as
patient-facing
chatbots
expand,
attention
these
factors
can
support
systems'
efforts
design
that
meet
unique
needs
all
patients,
expressly
risk
isolation.
Applied Ergonomics,
Journal Year:
2025,
Volume and Issue:
128, P. 104515 - 104515
Published: April 17, 2025
The
emergence
of
large
language
models
offers
new
opportunities
to
deliver
effective
healthcare
information
through
web-based
chatbots.
Health
is
often
complex
and
technical,
making
it
crucial
design
human-AI
interactions
that
effectively
meet
user
needs.
Employing
a
2x2
between
subjects
design,
we
controlled
for
two
independent
variables:
communication
style
(conversational
vs.
informative)
(technical
non-technical).
We
used
hierarchical
Bayesian
regression
assess
the
impact
varying
presentation
styles
on
effectiveness,
trustworthiness,
usability.
findings
revealed
perceptions
low
usability
significantly
decreased
effectiveness
chatbot.
Additionally,
participants
exposed
conversational
chatbot
had
increased
likelihoods
perceive
with
higher
but
were
also
more
likely
be
less
trusting
These
results
indicate
can
experience
insights
future
research
chatbots
other
AI
systems.
The Oncologist,
Journal Year:
2025,
Volume and Issue:
30(4)
Published: March 29, 2025
Abstract
Background
Recent
advances
in
large
language
models
(LLM)
have
enabled
human-like
qualities
of
natural
competency.
Applied
to
oncology,
LLMs
been
proposed
serve
as
an
information
resource
and
interpret
vast
amounts
data
a
clinical
decision-support
tool
improve
outcomes.
Objective
This
review
aims
describe
the
current
status
medical
accuracy
oncology-related
LLM
applications
research
trends
for
further
areas
investigation.
Methods
A
scoping
literature
search
was
conducted
on
Ovid
Medline
peer-reviewed
studies
published
since
2000.
We
included
primary
that
evaluated
model
applied
oncology
settings.
Study
characteristics
outcomes
were
extracted
landscape
LLMs.
Results
Sixty
based
inclusion
exclusion
criteria.
The
majority
health
question-answer
style
examinations
(48%),
followed
by
diagnosis
(20%)
management
(17%).
number
utility
fine-tuning
prompt-engineering
increased
over
time
from
2022
2024.
Studies
reported
advantages
accurate
resource,
reduction
clinician
workload,
improved
accessibility
readability
information,
while
noting
disadvantages
such
poor
reliability,
hallucinations,
need
oversight.
Discussion
There
exists
significant
interest
application
with
particular
focus
decision
support
tool.
However,
is
needed
validate
these
tools
external
hold-out
datasets
generalizability
across
diverse
scenarios,
underscoring
supervision
tools.
Digital Health,
Journal Year:
2025,
Volume and Issue:
11
Published: April 1, 2025
Digital
communication
between
patients
and
healthcare
teams
is
increasing.
Most
find
this
effective,
yet
many
remain
digitally
isolated,
a
social
determinant
of
health.
This
study
investigates
patient
attitudes
toward
healthcare's
newest
digital
assistant,
the
chatbot,
perceptions
regarding
access.
We
conducted
mixed
methods
among
users
large
system's
chatbot
integrated
within
an
electronic
health
record.
purposively
oversampled
by
race
ethnicity
to
survey
617/3089
(response
rate
20%)
online
using
de
novo
validated
items.
In
addition,
we
semi-structured
interviews
with
(n
=
46)
sampled
based
on
diversity,
age,
or
select
responses
November
2022
May
2024.
surveys,
213/609
(35.0%)
felt
they
could
not
understand
completely,
376/614
(61.2%)
did
completely
them.
Of
238
who
understood
178
(74.8%)
believed
was
intended
help
them
access
healthcare;
in
comparison,
376
understood,
155
(41%)
(p
<
0.001).
interviews,
themes
observed,
Black,
Hispanic,
less
educated,
younger,
lower-income
participants
expressed
more
positivity
about
aiding
access,
stating
convenience
perceived
absence
judgment
bias.
Patients'
experience
appears
affect
their
perception
intent
chatbot's
implementation;
those
adept
at
historically
trusting
groups
may
prefer
quick,
non-judgmental
answer
questions
via
rather
than
human
interaction.
Although
our
findings
are
limited
one
existing
users,
as
patient-facing
chatbots
expand,
attention
these
factors
can
support
systems'
efforts
design
that
meet
unique
needs
all
patients,
expressly
risk
isolation.
