Prostate Cancer and Prostatic Diseases,
Journal Year:
2024,
Volume and Issue:
unknown
Published: May 14, 2024
Abstract
Background
Generative
Pretrained
Model
(GPT)
chatbots
have
gained
popularity
since
the
public
release
of
ChatGPT.
Studies
evaluated
ability
different
GPT
models
to
provide
information
about
medical
conditions.
To
date,
no
study
has
assessed
quality
ChatGPT
outputs
prostate
cancer
related
questions
from
both
physician
and
perspective
while
optimizing
for
patient
consumption.
Methods
Nine
cancer-related
questions,
identified
through
Google
Trends
(Global),
were
categorized
into
diagnosis,
treatment,
postoperative
follow-up.
These
processed
using
3.5,
responses
recorded.
Subsequently,
these
re-inputted
create
simplified
summaries
understandable
at
a
sixth-grade
level.
Readability
original
layperson
was
validated
readability
tools.
A
survey
conducted
among
urology
providers
(urologists
urologists
in
training)
rate
accuracy,
completeness,
clarity
5-point
Likert
scale.
Furthermore,
two
independent
reviewers
on
correctness
trifecta:
decision-making
sufficiency.
Public
assessment
summaries’
understandability
carried
out
Amazon
Mechanical
Turk
(MTurk).
Participants
rated
demonstrated
their
understanding
multiple-choice
question.
Results
GPT-generated
output
deemed
correct
by
71.7%
94.3%
raters
(36
urologists,
17
residents)
across
9
scenarios.
this
as
accurate
8
(88.9%)
scenarios
sufficient
make
decision
Mean
higher
than
([original
v.
ChatGPT,
mean
(SD),
p
-value]
Flesch
Reading
Ease:
36.5(9.1)
70.2(11.2),
<0.0001;
Gunning
Fog:
15.8(1.7)
9.5(2.0),
<
0.0001;
Grade
Level:
12.8(1.2)
7.4(1.7),
Coleman
Liau:
13.7(2.1)
8.6(2.4),
0.0002;
Smog
index:
11.8(1.2)
6.7(1.8),
Automated
Index:
13.1(1.4)
7.5(2.1),
0.0001).
MTurk
workers
(
n
=
514)
(89.5–95.7%)
correctly
understood
content
(63.0–87.4%).
Conclusion
shows
promise
education
contents,
but
technology
is
not
designed
delivering
patients
information.
Prompting
model
respond
with
may
enhance
its
utility
when
used
GPT-powered
chatbots.
Digital Health,
Journal Year:
2024,
Volume and Issue:
10
Published: Jan. 1, 2024
Objectives
To
assess
the
quality
and
alignment
of
ChatGPT's
cancer
treatment
recommendations
(RECs)
with
National
Comprehensive
Cancer
Network
(NCCN)
guidelines
expert
opinions.
Methods
Three
urologists
performed
quantitative
qualitative
assessments
in
October
2023
analyzing
responses
from
ChatGPT-4
ChatGPT-3.5
to
108
prostate,
kidney,
bladder
prompts
using
two
zero-shot
prompt
templates.
Performance
evaluation
involved
calculating
five
ratios:
expert-approved/expert-disagreed
NCCN-aligned
RECs
against
total
ChatGPT
plus
coverage
adherence
rates
NCCN.
Experts
rated
response's
on
a
1-5
scale
considering
correctness,
comprehensiveness,
specificity,
appropriateness.
Results
outperformed
prostate
inquiries,
an
average
word
count
317.3
versus
124.4
(
p
<
0.001)
6.1
3.9
0.001).
Its
rater-approved
REC
ratio
(96.1%
vs.
89.4%)
NCCN
(76.8%
49.1%,
=
were
superior
scored
significantly
better
all
dimensions.
Across
covering
three
cancers,
produced
6.0
per
case,
88.5%
approval
rate
raters,
86.7%
concordance,
only
9.5%
disagreement
rate.
It
achieved
high
marks
correctness
(4.5),
comprehensiveness
(4.4),
specificity
(4.0),
appropriateness
(4.4).
Subgroup
analyses
across
types,
disease
statuses,
different
templates
reported.
Conclusions
demonstrated
significant
improvement
providing
accurate
detailed
for
urological
cancers
line
clinical
opinion.
However,
it
is
vital
recognize
that
AI
tools
are
not
without
flaws
should
be
utilized
caution.
could
supplement,
but
replace,
personalized
advice
healthcare
professionals.
Cureus,
Journal Year:
2025,
Volume and Issue:
unknown
Published: March 21, 2025
Chatbots
have
emerged
as
one
of
the
revolutionary
tools
in
healthcare
that
combine
artificial
intelligence
to
improve
patient
engagement
diagnosis,
treatment,
monitoring,
and
support.
In
this
review,
application
chatbots
medicine
over
past
two
decades
is
discussed,
focusing
on
their
several
aspects
medicine,
including
oncology,
psychiatry,
chronic
disease
management.
A
total
38
clinically
relevant
studies
were
identified
from
a
comprehensive
literature
search.
These
demonstrate
efficacy
early
symptom
detection,
personalized
treatment
planning,
emotional
support
has
particular
emphasis
addressing
mental
health
needs.
The
review
focuses
role
improving
communication
gap
between
patients
providers
achieve
improved
access
medical
information
adherence.
findings
underscore
substantial
promise
enhancing
delivery
reveal
areas
need
further
exploration,
particularly
radiology
advanced
diagnostics.
With
continuous
rise
technological
development,
use
expected
become
more
central
streamlining
processes
toward
better
outcomes
enhanced
literacy.
This
therefore,
calls
for
continued
investment
incorporation
these
chatbot
innovations
systems
full
potential
be
realized
care.
JMIR Cancer,
Journal Year:
2025,
Volume and Issue:
11, P. e63677 - e63677
Published: April 16, 2025
Abstract
Background
Patients
frequently
resort
to
the
internet
access
information
about
cancer.
However,
these
websites
often
lack
content
accuracy
and
readability.
Recently,
ChatGPT,
an
artificial
intelligence–powered
chatbot,
has
signified
a
potential
paradigm
shift
in
how
patients
with
cancer
can
vast
amounts
of
medical
information,
including
insights
into
radiotherapy.
quality
provided
by
ChatGPT
remains
unclear.
This
is
particularly
significant
given
general
public’s
limited
knowledge
this
treatment
concerns
its
possible
side
effects.
Furthermore,
evaluating
responses
crucial,
as
misinformation
foster
false
sense
security,
lead
noncompliance,
result
delays
receiving
appropriate
treatment.
Objective
study
aims
evaluate
reliability
ChatGPT’s
common
patient
queries
radiotherapy,
comparing
performance
two
versions:
GPT-3.5
GPT-4.
Methods
We
selected
40
commonly
asked
radiotherapy
questions
entered
both
versions
ChatGPT.
Response
were
evaluated
16
experts
using
General
Quality
Score
(GQS),
5-point
Likert
scale,
median
GQS
determined
based
on
experts’
ratings.
Consistency
similarity
assessed
cosine
score,
which
ranges
from
0
(complete
dissimilarity)
1
similarity).
Readability
was
analyzed
Flesch
Reading
Ease
Score,
ranging
100,
Flesch-Kincaid
Grade
Level,
reflecting
average
number
years
education
required
for
comprehension.
Statistical
analyses
performed
Mann-Whitney
test
effect
size,
results
deemed
at
5%
level
(
P
=.05).
To
assess
agreement
between
experts,
Krippendorff
α
Fleiss
κ
used.
Results
GPT-4
demonstrated
superior
performance,
higher
lower
scores
2,
compared
GPT-3.5.
The
revealed
statistically
differences
some
questions,
generally
(IQR)
score
indicated
substantial
(0.81,
IQR
0.05)
consistency
(GPT-3.5:
0.85,
0.04;
GPT-4:
0.83,
0.04).
considered
college
level,
scoring
slightly
better
(34.61)
Level
(12.32)
(32.98
13.32,
respectively).
Responses
challenging
public.
Conclusions
Both
having
capability
address
concepts,
showing
performance.
models
present
readability
challenges
population.
Although
demonstrates
valuable
resource
addressing
related
it
imperative
acknowledge
limitations,
risks
issues.
In
addition,
implementation
should
be
supported
strategies
enhance
accessibility
Journal of Endourology,
Journal Year:
2024,
Volume and Issue:
38(8), P. 763 - 777
Published: June 14, 2024
Among
emerging
AI
technologies,
Chat-Generative
Pre-Trained
Transformer
(ChatGPT)
emerges
as
a
notable
language
model,
uniquely
developed
through
artificial
intelligence
research.
Its
proven
versatility
across
various
domains,
from
translation
to
healthcare
data
processing,
underscores
its
promise
within
medical
documentation,
diagnostics,
research,
and
education.
The
current
comprehensive
review
aimed
investigate
the
utility
of
ChatGPT
in
urology
education
practice
highlight
potential
limitations.
