Sensors,
Journal Year:
2025,
Volume and Issue:
25(7), P. 1994 - 1994
Published: March 22, 2025
Stroke
is
the
fifth
leading
cause
of
death
in
Taiwan.
In
process
stroke
treatment,
rehabilitation
for
gait
recovery
one
most
critical
aspects
treatment.
The
Gait
Assessment
and
Intervention
Tool
(G.A.I.T.)
currently
used
clinical
practice
to
assess
level;
however,
G.A.I.T.
heavily
depends
on
physician
training
judgment.
With
advancement
technology,
today's
small,
lightweight
inertial
measurement
unit
(IMU)
wearable
sensors
are
rapidly
revolutionizing
assessment
may
be
incorporated
into
routine
practice.
this
paper,
we
developed
a
data
acquisition
analysis
system
based
IMU
devices,
proposed
simple
yet
accurate
calibration
reduce
drifting
errors,
designed
machine
learning
algorithm
obtain
real-time
coordinates
from
data,
computed
parameters,
derived
formula
scores
with
significant
correlation
physician's
observational
scores.
Frontiers in Medical Technology,
Journal Year:
2022,
Volume and Issue:
4
Published: Dec. 16, 2022
Background
Despite
being
available
for
more
than
three
decades,
quantitative
gait
analysis
remains
largely
associated
with
research
institutions
and
not
well
leveraged
in
clinical
settings.
This
is
mostly
due
to
the
high
cost/cumbersome
equipment
complex
protocols
data
management/analysis
traditional
labs,
as
diverse
training/experience
preference
of
teams.
Observational
qualitative
scales
continue
be
predominantly
used
clinics
despite
evidence
less
efficacy
quantifying
gait.
Research
objective
study
provides
a
scoping
review
status
assessment,
including
shedding
light
on
common
pathologies,
parameters,
indices,
scales.
We
also
highlight
novel
state-of-the-art
characterization
approaches
integration
commercially
wearable
tools
technology
AI-driven
computational
platforms.
Methods
A
comprehensive
literature
search
was
conducted
within
PubMed,
Web
Science,
Medline,
ScienceDirect
all
articles
published
until
December
2021
using
set
keywords,
normal
pathological
gait,
analysis,
systems,
inertial
measurement
units,
accelerometer,
gyroscope,
magnetometer,
insole
sensors,
electromyography
sensors.
Original
that
met
selection
criteria
were
included.
Results
significance
Clinical
highly
observational
hence
subjective
influenced
by
observer's
background
experience.
Quantitative
Instrumented
(IGA)
has
capability
providing
clinicians
accurate
reliable
diagnosis
monitoring
but
limited
applicability
mainly
logistics.
Rapidly
emerging
smart
technology,
multi-modality,
sensor
fusion
approaches,
platforms
are
increasingly
commanding
greater
attention
assessment.
These
promise
paradigm
shift
quantification
clinic
beyond.
On
other
hand,
standardization
ensuring
their
feasibility
map
features
human
represent
them
meaningfully
remain
critical
challenges.
Sensors,
Journal Year:
2022,
Volume and Issue:
22(10), P. 3859 - 3859
Published: May 19, 2022
Many
algorithms
use
3D
accelerometer
and/or
gyroscope
data
from
inertial
measurement
unit
(IMU)
sensors
to
detect
gait
events
(i.e.,
initial
and
final
foot
contact).
However,
these
often
require
knowledge
about
sensor
orientation
empirically
derived
thresholds.
As
alignment
cannot
always
be
controlled
for
in
ambulatory
assessments,
methods
are
needed
that
little
on
location
orientation,
e.g.,
a
convolutional
neural
network-based
deep
learning
model.
Therefore,
157
participants
healthy
neurologically
diseased
cohorts
walked
5
m
distances
at
slow,
preferred,
fast
walking
speed,
while
were
collected
IMUs
the
left
right
ankle
shank.
Gait
detected
stride
parameters
extracted
using
model
an
optoelectronic
motion
capture
(OMC)
system
reference.
The
consisted
of
layers
dilated
convolutions,
followed
by
two
independent
fully
connected
predict
whether
time
step
corresponded
event
contact
(IC)
or
(FC),
respectively.
Results
showed
high
detection
rate
both
contacts
across
locations
(recall
≥92%,
precision
≥97%).
Time
agreement
was
excellent
as
witnessed
median
error
(0.005
s)
corresponding
inter-quartile
range
(0.020
s).
stride-specific
good
with
OMC
(maximum
mean
difference
0.003
s
maximum
limits
(-0.049
s,
0.051
95%
confidence
level).
Thus,
approach
considered
valid
detecting
extracting
exact
IMU
conditions
without
pathologies
due
neurological
diseases.
Sensors,
Journal Year:
2024,
Volume and Issue:
24(20), P. 6585 - 6585
Published: Oct. 12, 2024
Stroke
is
a
leading
cause
of
long-term
disability
worldwide.
With
the
advancements
in
sensor
technologies
and
data
availability,
artificial
intelligence
(AI)
holds
promise
improving
amount,
quality
efficiency
care
enhancing
precision
stroke
rehabilitation.
We
aimed
to
identify
characterize
existing
research
on
AI
applications
recovery
rehabilitation
adults,
including
categories
application
progression
over
time.
Data
were
collected
from
peer-reviewed
articles
across
various
electronic
databases
up
January
2024.
Insights
extracted
using
AI-enhanced
multi-method,
data-driven
techniques,
clustering
themes
topics.
This
scoping
review
summarizes
outcomes
704
studies.
Four
common
(impairment,
assisted
intervention,
prediction
imaging,
neuroscience)
identified,
which
time-linked
patterns
emerged.
The
impairment
theme
revealed
focus
motor
function,
gait
mobility,
while
intervention
included
robotic
brain-computer
interface
(BCI)
techniques.
progressed
time,
starting
conceptualization
then
expanding
broader
range
techniques
supervised
learning,
neural
networks
(ANN),
natural
language
processing
(NLP)
more.
Applications
focused
upper
limb
reviewed
more
detail,
with
machine
learning
(ML),
deep
sensors
such
as
inertial
measurement
units
(IMU)
used
for
functional
movement
analysis.
have
potential
facilitate
tailored
therapeutic
delivery,
thereby
contributing
optimization
promoting
sustained
real-world
settings.
Sensors,
Journal Year:
2022,
Volume and Issue:
22(3), P. 908 - 908
Published: Jan. 25, 2022
Background:
Gait
is
often
impaired
in
people
after
stroke,
restricting
personal
independence
and
affecting
quality
of
life.
During
stroke
rehabilitation,
walking
capacity
conventionally
assessed
by
measuring
distance
speed.
features,
such
as
asymmetry
variability,
are
not
routinely
determined,
but
may
provide
more
specific
insights
into
the
patient’s
capacity.
Inertial
measurement
units
offer
a
feasible
promising
tool
to
determine
these
gait
features.
Objective:
We
examined
test–retest
reliability
inertial
units-based
features
measured
two-minute
assessment
while
clinical
rehabilitation.
Method:
Thirty-one
performed
two
assessments
with
interval
24
h.
Each
consisted
test
on
14-m
path.
Participants
were
equipped
three
units,
placed
at
both
feet
low
back.
In
total,
166
calculated
for
each
assessment,
consisting
spatio-temporal
(56),
frequency
(26),
complexity
(63),
(14)
The
was
determined
using
intraclass
correlation
coefficient.
Additionally,
minimal
detectable
change
relative
computed.
Results:
Overall,
107
had
good–excellent
reliability,
50
spatio-temporal,
8
frequency,
36
complexity,
13
symmetry
ranged
between
0.5
1.5
standard
deviations.
Conclusion:
can
reliably
be
rehabilitation
units.
Bioengineering,
Journal Year:
2023,
Volume and Issue:
10(7), P. 785 - 785
Published: June 30, 2023
When
brain
damage
occurs,
gait
and
balance
are
often
impaired.
Evaluation
of
the
cycle,
therefore,
has
a
pivotal
role
during
rehabilitation
path
subjects
who
suffer
from
neurological
disorders.
Gait
analysis
can
be
performed
through
laboratory
systems,
non-wearable
sensors
(NWS),
and/or
wearable
(WS).
Using
these
tools,
physiotherapists
neurologists
have
more
objective
measures
motion
function
plan
tailored
specific
training
early
to
achieve
better
outcomes
improve
patients’
quality
life.
However,
most
innovative
tools
used
for
research
purposes
(especially
systems
NWS),
although
they
deserve
attention
in
field,
considering
their
potential
improving
clinical
practice.
In
this
narrative
review,
we
aimed
summarize
patients,
shedding
some
light
on
value
implications
neurorehabilitation
Frontiers in Neurorobotics,
Journal Year:
2023,
Volume and Issue:
17
Published: July 3, 2023
Stroke
is
a
significant
cause
of
disability
worldwide,
and
stroke
survivors
often
experience
severe
motor
impairments.
Lower
limb
rehabilitation
exoskeleton
robots
provide
support
balance
for
assist
them
in
performing
training
tasks,
which
can
effectively
improve
their
quality
life
during
the
later
stages
recovery.
have
become
hot
topic
therapy
research.
This
review
introduces
traditional
assessment
methods,
explores
possibility
lower
combining
sensors
electrophysiological
signals
to
assess
survivors'
objectively,
summarizes
standard
human-robot
coupling
models
recent
years,
critically
adaptive
control
based
on
motion
intent
recognition
robots.
provides
new
design
ideas
future
combination
with
assessment,
assistance,
treatment,
control,
making
process
more
objective
addressing
shortage
therapists
some
extent.
Finally,
article
discusses
current
limitations
proposes
research
directions.
