Ambulatory seizure detection
Current Opinion in Neurology,
Год журнала:
2024,
Номер
37(2), С. 99 - 104
Опубликована: Фев. 7, 2024
Purpose
of
review
To
recent
advances
in
the
field
seizure
detection
ambulatory
patients
with
epilepsy.
Recent
findings
studies
have
shown
that
wrist
or
arm
wearable
sensors,
using
3D-accelerometry,
electrodermal
activity
photoplethysmography,
isolation
combination,
can
reliably
detect
focal-to-bilateral
and
generalized
tonic-clonic
seizures
(GTCS),
a
sensitivity
over
90%,
false
alarm
rates
varying
from
0.1
to
1.2
per
day.
A
headband
EEG
has
also
demonstrated
high
for
detecting
help
monitoring
absence
seizures.
In
contrast,
no
appropriate
solution
is
yet
available
focal
seizures,
though
some
promising
were
reported
ECG-based
heart
rate
variability
biomarkers
subcutaneous
EEG.
Summary
Several
FDA
and/or
EU-certified
solutions
are
GTCS
trigger
an
acceptable
alarms.
However,
data
still
missing
regarding
impact
such
intervention
on
patients’
safety.
Noninvasive
patients,
based
either
non-EEG
biosignals,
remain
be
developed.
this
end,
number
challenges
need
addressed,
including
performance,
but
transparency
interpretability
machine
learning
algorithms.
Язык: Английский
Wearable sensors in paediatric neurology
Developmental Medicine & Child Neurology,
Год журнала:
2025,
Номер
unknown
Опубликована: Янв. 31, 2025
Wearable
sensors
have
the
potential
to
transform
diagnosis,
monitoring,
and
management
of
children
who
neurological
conditions.
Traditional
methods
for
assessing
disorders
rely
on
clinical
scales
subjective
measures.
The
snapshot
disease
progression
at
a
particular
time
point,
lack
cooperation
by
during
assessments,
susceptibility
bias
limit
utility
these
sensors,
which
capture
data
continuously
in
natural
settings,
offer
non-invasive
objective
alternative
traditional
methods.
This
review
examines
role
wearable
various
paediatric
conditions,
including
cerebral
palsy,
epilepsy,
autism
spectrum
disorder,
attention-deficit/hyperactivity
as
well
Rett
syndrome,
Down
Angelman
Prader-Willi
neuromuscular
such
Duchenne
muscular
dystrophy
spinal
atrophy,
ataxia,
Gaucher
disease,
headaches,
sleep
disorders.
highlights
their
application
tracking
motor
function,
seizure
activity,
daily
movement
patterns
gain
insights
into
therapeutic
response.
Although
challenges
related
population
size,
compliance,
ethics,
regulatory
approval
remain,
technology
promises
improve
trials
outcomes
patients
neurology.
Язык: Английский
Automated Sleep Staging in Epilepsy Using Deep Learning on Standard Electroencephalogram and Wearable Data
Journal of Sleep Research,
Год журнала:
2025,
Номер
unknown
Опубликована: Апрель 3, 2025
Automated
sleep
staging
on
wearable
data
could
improve
our
understanding
and
management
of
epilepsy.
This
study
evaluated
scoring
by
a
deep
learning
model
223
night-sleep
recordings
from
50
patients
measured
in
the
hospital
with
an
electroencephalogram
(EEG)
device.
The
scored
stage
every
30-s
epoch
EEG
data,
we
compared
output
clinical
expert
20
nights,
each
for
different
patient.
Bland-Altman
analysis
examined
differences
automated
both
modalities,
using
mixed-effect
models,
explored
between
without
seizures.
Overall,
found
moderate
accuracy
Cohen's
kappa
standard
(0.73
0.59)
(0.61
0.43)
versus
expert.
F1
scores
also
varied
modalities.
sensitivity
was
very
low
N1.
Moreover,
underestimated
duration
most
macrostructure
parameters
except
N2.
On
other
hand,
seizures
during
admission
slept
more
night
(6.37,
95%
confidence
interval
[CI]
5.86-7.87)
(5.68,
CI
5.24-6.13),
p
=
0.001,
but
spent
time
In
conclusion,
accelerometry
monitor
epilepsy,
approach
can
help
automate
analysis.
However,
further
steps
are
essential
to
performance
before
implementation.
Trial
Registration:
SeizeIT2
trial
registered
clinicaltrials.gov,
NCT04284072.
Язык: Английский
Automated detection of tonic seizures using wearable movement sensor and artificial neural network
Epilepsia,
Год журнала:
2024,
Номер
65(9)
Опубликована: Июль 30, 2024
Abstract
Although
several
validated
wearable
devices
are
available
for
detection
of
generalized
tonic–clonic
seizures,
automated
tonic
seizures
is
still
a
challenge.
In
this
phase
1
study,
we
report
development
and
validation
an
artificial
neural
network
(ANN)
model
with
visible
clinical
manifestation
using
wristband
movement
sensor
(accelerometer
gyroscope).
The
dataset
prospectively
recorded
study
included
70
from
15
patients
(seven
males,
age
3–46
years,
median
=
19
years).
We
trained
ANN
to
detect
seizures.
independent
test
comprised
nocturnal
recordings,
including
10
three
additional
(distractor)
data
subjects
without
detected
sensitivity
100%
(95%
confidence
interval
69%–100%)
average
false
alarm
rate
.16/night.
mean
latency
was
14.1
s
(median
s),
maximum
47
s.
These
suggest
that
can
be
reliably
sensors
ANN.
Large‐scale,
multicenter
prospective
(phase
3)
trials
needed
provide
compelling
evidence
the
utility
device
algorithm.
Язык: Английский
Wearable biosensors for pediatric hospitals: a scoping review
Pediatric Research,
Год журнала:
2024,
Номер
unknown
Опубликована: Ноя. 7, 2024
Язык: Английский
Technologies for Wearable Seizure Detection: A Systematic Review
Опубликована: Июнь 14, 2024
Knowing
when
a
seizure
occurred
is
helpful
because
this
information
can
be
used
to
evaluate
the
effectiveness
of
interventions
and
possibly
alert
caregivers
emergency
situations.
The
current
practice
for
recording
seizures
outside
hospital
without
sensors
through
keeping
self-reported
diary.
This
may
unreliable
if
diary
not
updated
or
person
having
does
realize
it
happening.
Wearable
detectors
aim
solve
problem
by
reliably
happened
either
sending
out
an
storing
data
later
analysis.
In
systematic
review
literature,
1,018
articles
were
evaluated
assess
status
wearable
detection
technology.
A
look
into
challenges
developing
such
device
how
others
have
overcome
some
these
also
discussed.
Язык: Английский