Advances in healthcare information systems and administration book series,
Год журнала:
2024,
Номер
unknown, С. 15 - 48
Опубликована: Дек. 13, 2024
This
study
aims
to
enhance
cancer
diagnosis
through
the
integration
of
artificial
intelligence
(AI)
and
advanced
data
analytics.
Utilizing
a
quantitative
research
design,
we
collected
analyzed
diverse
datasets,
including
demographic,
clinical,
genetic
information,
develop
predictive
models
for
early
detection.
The
findings
reveal
that
machine
learning
algorithms
significantly
improve
diagnostic
accuracy,
enabling
identification
risk
factors
facilitating
timely
interventions.
results
underscore
potential
AI
transform
care
by
personalizing
treatment
strategies
improving
patient
outcomes.
highlights
importance
ethical
considerations
quality
in
developing
AI-driven
healthcare
solutions,
suggesting
collaborative
approach
is
essential
future
advancements
management.
Journal of the American Medical Informatics Association,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 27, 2025
Abstract
Objective
Building
upon
our
previous
work
on
predicting
chronic
opioid
use
using
electronic
health
records
(EHR)
and
wearable
data,
this
study
leveraged
the
Health
Equity
Across
AI
Lifecycle
(HEAAL)
framework
to
(a)
fine
tune
previously
built
model
with
genomic
data
evaluate
performance
in
(b)
apply
IBM’s
AIF360
pre-processing
toolkit
mitigate
bias
related
gender
race
various
fairness
metrics.
Materials
Methods
Participants
included
approximately
271
All
of
Us
Research
Program
subjects
EHR,
wearable,
data.
We
fine-tuned
4
machine
learning
models
new
dataset.
The
SHapley
Additive
exPlanations
(SHAP)
technique
identified
best-performing
predictors.
A
preprocessing
boosted
by
race.
Results
genetic
enhanced
from
prior
model,
area
under
curve
improving
0.90
(95%
CI,
0.88-0.92)
0.95
0.89-0.95).
Key
predictors
Dopamine
D1
Receptor
(DRD1)
rs4532,
general
type
surgery,
time
spent
physical
activity.
reweighing
applied
stacking
algorithm
effectively
improved
model’s
across
racial
groups
without
compromising
performance.
Conclusion
2
dimensions
HEAAL
build
a
fair
artificial
intelligence
(AI)
solution.
Multi-modal
datasets
(including
data)
applying
mitigation
strategies
can
help
more
fairly
accurately
assess
risk
diverse
populations,
promoting
healthcare.
Journal of the American Medical Informatics Association,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 5, 2025
Abstract
Importance
The
US
healthcare
system
faces
significant
challenges,
including
clinician
burnout,
operational
inefficiencies,
and
concerns
about
patient
safety.
Artificial
intelligence
(AI),
particularly
generative
AI,
has
the
potential
to
address
these
but
its
adoption,
effectiveness,
barriers
implementation
are
not
well
understood.
Objective
To
evaluate
current
state
of
AI
adoption
in
systems,
assess
successes
during
early
era.
Design,
setting,
participants
This
cross-sectional
survey
was
conducted
Fall
2024,
included
67
health
systems
members
Scottsdale
Institute,
a
collaborative
non-profit
organizations.
Forty-three
completed
(64%
response
rate).
Respondents
provided
data
on
deployment
status
perceived
success
37
use
cases
across
10
categories.
Main
outcomes
measures
primary
were
extent
case
development,
piloting,
or
deployment,
degree
reported
for
cases,
most
adoption.
Results
Across
43
responding
perceptions
varied
significantly.
Ambient
Notes,
tool
clinical
documentation,
only
with
100%
respondents
reporting
activities,
53%
high
using
Clinical
Documentation.
Imaging
radiology
emerged
as
widely
deployed
case,
90%
organizations
at
least
partial
although
diagnostic
limited.
Similarly,
many
have
risk
stratification
such
sepsis
detection,
38%
report
this
area.
Immature
tools
identified
barrier
cited
by
77%
respondents,
followed
financial
(47%)
regulatory
uncertainty
(40%).
Conclusions
relevance
Notes
is
rapidly
advancing
demonstrating
success.
Other
show
varying
degrees
success,
constrained
immature
tools,
concerns,
uncertainty.
Addressing
challenges
through
robust
evaluations,
shared
strategies,
governance
models
will
be
essential
ensure
effective
integration
into
practice.
PLOS Digital Health,
Год журнала:
2024,
Номер
3(6), С. e0000513 - e0000513
Опубликована: Июнь 6, 2024
Healthcare
delivery
organizations
(HDOs)
in
the
US
must
contend
with
potential
for
AI
to
worsen
health
inequities.
But
there
is
no
standard
set
of
procedures
HDOs
adopt
navigate
these
challenges.
There
an
urgent
need
present
a
unified
approach
proactively
address
Amidst
this
background,
Health
Partnership
(HAIP)
launched
community
practice
convene
stakeholders
from
across
tackle
challenges
related
use
AI.
On
February
15,
2023,
HAIP
hosted
inaugural
workshop
focused
on
question,
“Our
care
setting
considering
adopting
new
solution
that
uses
How
do
we
assess
future
impact
inequities?”
This
topic
emerged
as
common
challenge
faced
by
all
participating
HAIP.
The
had
2
main
goals.
First,
wanted
ensure
participants
could
talk
openly
without
reservations
about
challenging
topics
such
equity.
second
goal
was
develop
actionable,
generalizable
framework
be
immediately
put
into
practice.
engaged
77
100%
representation
10
and
invited
ecosystem
partners.
In
accompanying
Research
Article,
share
Equity
Across
Lifecycle
(HEAAL)
framework.
We
invite
encourage
test
HEAAL
internally
feedback
so
can
continue
refine
maintain
procedures.
reveals
associated
rigorously
assessing
Significant
investment
personnel,
capabilities,
data
infrastructure
required,
level
needed
beyond
reach
most
HDOs.
look
forward
expanding
our
assist
around
world.
International Journal for Equity in Health,
Год журнала:
2024,
Номер
23(1)
Опубликована: Ноя. 11, 2024
There
are
avoidable
differences
(i.e.,
inequities)
in
the
prevalence
and
distribution
of
chronic
pain
across
diverse
populations,
as
well
access
to
outcomes
management
services.
Digital
self-reporting
tools
have
potential
reduce
or
exacerbate
these
inequities.
This
study
aimed
better
understand
how
optimise
health
equity
impact
digital
on
people
who
experiencing
(or
at
risk
of)
