The Spine Journal,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 1, 2025
A
machine
learning
(ML)
model
was
recently
developed
to
predict
massive
intraoperative
blood
loss
(>2500mL)
during
posterior
decompressive
surgery
for
spinal
metastasis
that
performed
well
on
external
validation
within
the
same
region
in
China.
We
sought
externally
validate
this
across
new
geographic
regions
(North
America
and
Europe)
patient
cohorts.
Multi-institutional
retrospective
cohort
study
PATIENT
SAMPLE:
retrospectively
included
patients
18
years
or
older
who
underwent
three
institutions
United
States,
Kingdom
Netherlands
between
2016
2022.
Inclusion
exclusion
criteria
were
consistent
with
development
additional
inclusion
of
(1)
undergoing
palliative
decompression
without
stabilization,
(2)
multiple
myeloma
lymphoma,
(3)
continued
anticoagulants
perioperatively.
Model
performance
assessed
by
comparing
incidence
(>2,500mL)
our
predicted
risk
generated
ML
model.
Blood
quantified
7
ways
(including
formula
from
study)
as
no
gold
standard
exists,
method
paper
not
clearly
defined.
estimated
using
anesthesia
report,
calculated
it
transfusion
data,
preoperative
postoperative
hematocrit
levels.
The
following
five
input
variables
necessary
calculation
manually
collected:
tumor
type,
smoking
status,
ECOG
score,
surgical
process,
platelet
count.
overall
fit
(Brier
score),
discriminatory
ability
(area
under
curve
(AUC)),
calibration
(intercept
&
slope),
clinical
utility
(decision
analysis
(DCA))
total
cohort,
North
American
European
cohorts
separately.
sub-analysis,
excluding
groups,
predictive
model's
cohort.
880
a
range
5.3%
18%
depending
which
quantification
used.
Using
most
favorable
method,
overestimated
scored
poorly
score:
0.278),
discrimination
(AUC:
0.631
[95%CI:
0.583,
0.680]),
calibration,
(intercept:
-2.082,
-2.285,
-1.879]),
slope:
0.283
0.173,
0.393]),
utility,
net
harm
observed
decision
20%.
Similar
poor
results
sub-analysis
(n=676)
when
analyzing
(n=539)
(n=341)
To
knowledge,
is
first
published
orthopedic
demonstrate
performance.
This
might
be
attributed
overfitting
sampling
bias
had
an
insufficient
sample
size,
distributional
shift
key
differences
used
These
findings
emphasize
importance
extensive
different
geographical
areas
addressing
biases
known
pitfalls
before
implementation,
untested
models
may
do
more
than
good.
Healthcare,
Год журнала:
2024,
Номер
12(3), С. 300 - 300
Опубликована: Янв. 24, 2024
The
remarkable
progress
in
data
aggregation
and
deep
learning
algorithms
has
positioned
artificial
intelligence
(AI)
machine
(ML)
to
revolutionize
the
field
of
medicine.
AI
is
becoming
more
prevalent
healthcare
sector,
its
impact
on
orthopedic
surgery
already
evident
several
fields.
This
review
aims
examine
literature
that
explores
comprehensive
clinical
relevance
AI-based
tools
utilized
before,
during,
after
anterior
cruciate
ligament
(ACL)
reconstruction.
focuses
current
applications
future
prospects
preoperative
management,
encompassing
risk
prediction
diagnostics;
intraoperative
tools,
specifically
navigation,
identifying
complex
anatomic
landmarks
during
surgery;
postoperative
terms
care
rehabilitation.
Additionally,
educational
training
settings
are
presented.
Orthopedic
surgeons
showing
a
growing
interest
AI,
as
evidenced
by
discussed
this
review,
particularly
those
related
ACL
injury.
exponential
increase
studies
applicable
management
tears
promises
significant
application,
with
attention
from
surgeons.
Annals of Medicine and Surgery,
Год журнала:
2024,
Номер
86(9), С. 5401 - 5409
Опубликована: Авг. 1, 2024
Robotic
surgery,
known
for
its
minimally
invasive
techniques
and
computer-controlled
robotic
arms,
has
revolutionized
modern
medicine
by
providing
improved
dexterity,
visualization,
tremor
reduction
compared
to
traditional
methods.
The
integration
of
artificial
intelligence
(AI)
into
surgery
further
advanced
surgical
precision,
efficiency,
accessibility.
This
paper
examines
the
current
landscape
AI-driven
systems,
detailing
their
benefits,
limitations,
future
prospects.
Initially,
AI
applications
in
focused
on
automating
tasks
like
suturing
tissue
dissection
enhance
consistency
reduce
surgeon
workload.
Present
systems
incorporate
functionalities
such
as
image
recognition,
motion
control,
haptic
feedback,
allowing
real-time
analysis
field
images
optimizing
instrument
movements
surgeons.
advantages
include
enhanced
reduced
fatigue,
safety.
However,
challenges
high
development
costs,
reliance
data
quality,
ethical
concerns
about
autonomy
liability
hinder
widespread
adoption.
Regulatory
hurdles
workflow
also
present
obstacles.
Future
directions
enhancing
autonomy,
personalizing
approaches,
refining
training
through
AI-powered
simulations
virtual
reality.
Overall,
holds
promise
advancing
care,
with
potential
benefits
including
patient
outcomes
increased
access
specialized
expertise.
Addressing
promoting
responsible
adoption
are
essential
realizing
full
surgery.
Journal of Experimental Orthopaedics,
Год журнала:
2023,
Номер
10(1)
Опубликована: Янв. 1, 2023
Abstract
ChatGPT
has
quickly
popularized
since
its
release
in
November
2022.
Currently,
large
language
models
(LLMs)
and
have
been
applied
various
domains
of
medical
science,
including
cardiology,
nephrology,
orthopedics,
ophthalmology,
gastroenterology,
radiology.
Researchers
are
exploring
the
potential
LLMs
for
clinicians
surgeons
every
domain.
This
study
discusses
how
can
help
orthopedic
perform
tasks.
patient
community
by
providing
suggestions
diagnostic
guidelines.
In
this
study,
use
to
enhance
expand
field
education,
surgery,
research,
is
explored.
Present
several
shortcomings,
which
discussed
herein.
However,
next‐generation
future
domain‐specific
expected
be
more
potent
transform
patients’
quality
life.
Foot & Ankle Orthopaedics,
Год журнала:
2024,
Номер
9(2)
Опубликована: Апрель 1, 2024
Background:
The
incidence
of
primary
total
ankle
arthroplasty
(TAA)
is
rising,
with
a
corresponding
increase
in
revision
surgeries.
Despite
this,
research
on
risk
factors
for
TAA
following
remains
limited.
Radiographic
soft
tissue
thickness
has
been
explored
as
potential
predictor
outcomes
hip,
knee,
and
shoulder
arthroplasty,
but
its
role
not
assessed.
This
study
aimed
to
assess
the
predictive
value
radiographic
identifying
patients
at
requiring
surgery
TAA.
Methods:
A
retrospective
was
conducted
323
who
underwent
between
2003
2019.
measurements
were
obtained
from
preoperative
radiographs.
Two
novel
measures
developed
assessed
(tibial
talus
thickness).
Clinical
variables
including
age,
gender,
body
mass
index
(BMI),
American
Society
Anesthesiologists
(ASA)
classification,
diabetes,
smoking
status,
diagnosis,
implant
type
recorded.
Logistic
regression
analysis
used
BMI
Results:
rate
4.3%
(14
patients).
Patients
had
significantly
greater
tibial
(3.54
vs
2.48
cm;
P
=
.02)
(2.79
2.42
compared
those
revision.
Both
(odds
ratio
1.16
[1.12-1.20];
<
.01)
ratio:
1.10
[1.05-1.15];
significant
predictors
multivariable
logistic
models.
However,
two
metrics
demonstrated
excellent
interrater
reliability.
Conclusion:
Greater
better
BMI.
These
findings
suggest
that
may
be
valuable
tool
assessing
need
Further
needed
validate
explore
impact
clinical
practice.
Level
Evidence:
III,
comparative
study.
Diagnostics,
Год журнала:
2024,
Номер
14(13), С. 1321 - 1321
Опубликована: Июнь 21, 2024
In
recent
years,
preoperative
planning
has
undergone
significant
advancements,
with
a
dual
focus:
improving
the
accuracy
of
implant
placement
and
enhancing
prediction
functional
outcomes.
These
breakthroughs
have
been
made
possible
through
development
advanced
processing
methods
for
3D
images.
not
only
offer
novel
visualization
techniques
but
can
also
be
seamlessly
integrated
into
computer-aided
design
models.
Additionally,
refinement
motion
capture
systems
played
pivotal
role
in
this
progress.
"markerless"
are
more
straightforward
to
implement
facilitate
easier
data
analysis.
Simultaneously,
emergence
machine
learning
algorithms,
utilizing
artificial
intelligence,
enabled
amalgamation
anatomical
data,
leading
highly
personalized
plans
patients.
The
shift
from
2D
towards
3D,
static
dynamic,
is
closely
linked
technological
advances,
which
will
described
instructional
review.
Finally,
concept
4D
planning,
encompassing
periarticular
soft
tissues,
introduced
as
forward-looking
field
orthopedic
surgery.
