Manual
sleep
stage
classification
relies
on
visual
inspection
of
30-second
windows
comprising
multi-sensor
measurements
The
ability
neural
networks
to
model
complex
relations
has
made
them
a
popular,
faster,
alternative.
However,
it
often
remains
unclear
which
parts
the
data
predominantly
contributed
model's
decision.
This
is
especially
ambiguous
in
staging,
where
coarse
labeling
per
may
assign
mixtures
class-specific
features
single
class.
To
boost
transparency
deep
classifiers,
we
propose
dynamic
discrete
attention
module
that
actively
selects
subset
input
space
aligned
with
class
label.
can
be
combined
typical
network,
and
additionally
serve
as
data-driven
tool
discover
specific
polysomnography
data.
We
validate
method
synthetic
patient
observe
only
small
from
window
required
retain
accurate
classification,
mechanism
boosts
performance.
Analysis
masks,
moreover,
shows
clear
adaptive
channel
selection.
Scientific Reports,
Год журнала:
2023,
Номер
13(1)
Опубликована: Ноя. 30, 2023
Due
to
the
association
between
dysfunctional
maternal
autonomic
regulation
and
pregnancy
complications,
tracking
non-invasive
features
of
derived
from
wrist-worn
photoplethysmography
(PPG)
measurements
may
allow
for
early
detection
deteriorations
in
health.
However,
even
though
a
plethora
these
features-specifically,
describing
heart
rate
variability
(HRV)
morphology
PPG
waveform
(morphological
features)-exist
literature,
it
is
unclear
which
be
valuable
As
an
initial
step
towards
clarity,
we
compute
comprehensive
sets
HRV
morphological
nighttime
measurements.
From
these,
using
logistic
regression
stepwise
forward
feature
elimination,
identify
that
best
differentiate
healthy
pregnant
women
non-pregnant
women,
since
likely
capture
physiological
adaptations
necessary
sustaining
pregnancy.
Overall,
were
more
discriminating
than
(area
under
receiver
operating
characteristics
curve
0.825
0.74,
respectively),
with
systolic
pulse
wave
deterioration
being
most
single
feature,
followed
by
mean
(HR).
Additionally,
stratified
analysis
sleep
stages
found
calculated
only
periods
deep
enhanced
differences
two
groups.
In
conclusion,
postulate
addition
features,
also
useful
health
suggest
specific
included
future
research
concerning
Journal of Applied Physiology,
Год журнала:
2023,
Номер
135(5), С. 1199 - 1212
Опубликована: Сен. 28, 2023
We
compare
CRC,
i.e.,
the
reciprocal
interaction
between
cardiac
and
respiratory
systems,
healthy
pregnant
nonpregnant
women
for
first
time.
Although
CRC
is
present
in
both
groups,
reduced
during
pregnancy;
there
less
synchronization
maternal
activity
a
smaller
response
heart
rate
to
inhalations
exhalations.
Stratifying
this
analysis
by
sleep
stages
reveals
that
differences
are
most
prominent
deep
sleep.
Hypnograms
contain
a
wealth
of
information
and
play
an
important
role
in
sleep
medicine.
However,
interpretation
the
hypnogram
is
difficult
task
requires
domain
knowledge
"clinical
intuition."
This
study
aimed
to
uncover
which
features
drive
by
physicians.
In
other
words,
make
explicit
physicians
implicitly
look
for
hypnograms.
Three
experts
evaluated
up
612
hypnograms,
indicating
normal
or
abnormal
structure
suspicion
disorders.
ElasticNet
convolutional
neural
network
classification
models
were
trained
predict
collected
expert
evaluations
using
stages
as
input.
The
several
measures,
including
accuracy,
Cohen's
kappa,
Matthew's
correlation
coefficient,
confusion
matrices.
Finally,
model
coefficients
visual
analytics
techniques
used
interpret
associate
with
evaluation.
Agreement
between
(Kappa
0.47
0.52)
similar
agreement
0.38
0.50).
Sleep
fragmentation,
measured
transitions
per
hour,
stage
distribution
identified
predictors
interpretation.
By
comparing
hypnograms
not
solely
on
epoch-by-epoch
basis,
but
also
these
more
specific
that
are
relevant
evaluation
experts,
performance
assessment
(automatic)
sleep-staging
surrogate
trackers
may
be
improved.
particular,
fragmentation
feature
deserves
attention
it
often
included
PSG
report,
existing
(wearable)
have
shown
relatively
poor
this
aspect.
Journal of Sleep Research,
Год журнала:
2023,
Номер
33(3)
Опубликована: Дек. 9, 2023
Summary
Non‐rapid
eye
movement
parasomnia
disorders,
also
called
disorders
of
arousal,
are
characterized
by
abnormal
nocturnal
behaviours,
such
as
confusional
arousals
or
sleep
walking.
Their
pathophysiology
is
not
yet
fully
understood,
and
objective
diagnostic
criteria
lacking.
It
known,
however,
that
behavioural
episodes
occur
mostly
in
the
beginning
night,
after
an
increase
slow‐wave
activity
during
sleep.
A
better
understanding
prospect
may
lead
to
new
insights
underlying
mechanisms
eventually
facilitate
diagnosis.
We
investigated
temporal
dynamics
transitions
from
52
patients
79
controls.
Within
patient
group,
non‐behavioural
N3
awakenings
were
distinguished.
Patients
showed
a
higher
probability
wake
up
bout
ended
than
controls,
this
increased
with
duration.
Bouts
longer
15
min
resulted
awakening
73%
34%
time
respectively.
Behavioural
reduced
over
cycles
due
reduction
reducing
ratio
between
awakenings.
In
first
two
cycles,
bouts
prior
significantly
shorter
advancing
patients,
Our
findings
provide
timing
both
N3,
which
result
prediction
potentially
prevention
episodes.
This
work,
moreover,
leads
more
complete
characterization
prototypical
hypnogram
parasomnias,
could
Sensors,
Год журнала:
2024,
Номер
24(19), С. 6374 - 6374
Опубликована: Окт. 1, 2024
:
Contactless
monitoring
of
instantaneous
heart
rate
and
respiration
has
a
significant
clinical
relevance.
This
work
aims
to
use
Speckle
Vibrometry
(i.e.,
based
on
the
secondary
laser
speckle
effect)
contactlessly
measure
these
two
vital
signs
in
an
intensive
care
unit.
In
this
work,
we
investigated
the
feasibility
of
extracting
continuous
respiratory
parameters
from
a
single
RGB
camera
stationed
in
short-stay
ward.
Based
on
extracted
respiration
parameters,
further
using
features
to
aid
detection
atrial
fibrillation
(AF).
To
extract
respiration,
implemented
two
algorithms:
chest
optical
flow
(COF)
and
energy
variance
maximization
(EVM).
We
used
COF
patient's
thoracic
area
EVM
facial
area.
Using
capnography
as
reference,
for
average
breath-to-breath
rate
estimation
(i.e.,
15-second
sliding
windows
with
50%
overlap),
achieved
errors
within
3
breaths
per
minute
3.5
EVM.
detect
presence
AF
signal,
three
derived
measurements.
fed
these
logistic
regression
model
an
AUC
value
0.64.
This
result
showcases
potential
camera-based
predictors
AF,
or
surrogate
when
there
is
no
sufficient
camera's
field
view
extraction
cardiac
Sensors,
Год журнала:
2023,
Номер
23(14), С. 6312 - 6312
Опубликована: Июль 11, 2023
Instantaneous
heart
rate
(IHR)
has
been
investigated
for
sleep
applications,
such
as
apnea
detection
and
staging.
To
ensure
the
comfort
of
patient
during
sleep,
it
is
desirable
IHR
to
be
measured
in
a
contact-free
fashion.
In
this
work,
we
use
speckle
vibrometry
(SV)
perform
on-skin
on-textile
monitoring
setting.
Minute
motions
on
laser-illuminated
surface
can
captured
by
defocused
camera,
enabling
cardiac
even
textiles.
We
investigate
supine,
lateral,
prone
sleeping
positions.
Based
Bland–Altman
analysis
between
SV
measurements
electrocardiogram
(ECG),
with
respect
each
position,
achieve
best
limits
agreement
ECG
values
[−8.65,
7.79]
bpm,
[−9.79,
9.25]
[−10.81,
10.23]
respectively.
The
results
indicate
potential
using
method
instantaneous
setting
where
participant
allowed
rest
spontaneous
position
while
covered
textile
layers.
Sensors and Actuators A Physical,
Год журнала:
2024,
Номер
376, С. 115659 - 115659
Опубликована: Июнь 27, 2024
A
non-invasive,
wireless,
smartphone-based
electronic
measurement
system
for
sleep
stage
identification
is
presented
in
this
work.
Ballistocardiograph
signals
are
collected
by
two
piezo-capacitive
thin
film
strips
located
on
the
mattress
base.
Suitable
analog
conditioning
circuits
and
digital
pre-processing
techniques
applied
to
obtain
heart
breathing
rates
(HR,
BR),
an
activity
index
(ACT)
related
body
movements
during
sleep.
An
initial
calibration
proposed
where
signal
amplification
fitted
each
subject,
from
which
derived.
Features
considered
machine
learning
classifications
were
mentioned
data
time
variabilities
of
HR
BR
represented
features
R(k)
B(k),
respectively.
Support
Vector
Machine
(SVM)
K-Nearest-Neighbour
(KNN)
classifiers
employed
both
flat
hierarchical
classification
scenarios
Wake
–
Non
Rapid
Eye
Movement
(WAKE/NREM/REM)
identification.
Twelve
healthy
subjects
recorded
with
developed
using
a
polysomnograph
(PSG)
as
reference
data.
When
compared
PSG,
achieved
average
accuracy
69
%
only
three
features:
R(k),
ACT,
highlighting
88.2
recall
NREM
These
findings
suggest
that
accounting
variability
activity,
satisfactory
results
can
be
provided
complementary
alternative
identification,
designed
affordable,
versatile,
simple
tool
household
applications.
IEEE Transactions on Biomedical Engineering,
Год журнала:
2024,
Номер
72(3), С. 965 - 977
Опубликована: Окт. 15, 2024
Polysomnography
(PSG)
is
the
gold
standard
for
sleep
staging
in
clinics,
but
its
skin-contact
nature
makes
it
uncomfortable
and
inconvenient
to
use
long-term
monitoring.
As
a
complementary
part
of
PSG,
video
cameras
are
not
utilized
their
full
potential,
only
manual
check
simple
events,
thereby
ignoring
potential
physiological
semantic
measurement.
This
leads
pivotal
research
question:
Can
camera
be
used
staging,
what
extent?
We
developed
camera-based
contactless
system
Institute
Respiratory
Diseases
created
clinical
dataset
20
adults.
The
feature
set,
derived
from
both
signals
(pulse
breath)
motions
all
measured
video,
was
evaluated
4-class
(Wake-REM-Light-Deep).
Three
optimization
strategies
were
proposed
enhance
accuracy:
using
motion
metrics
prune
measurement
outliers,
creating
more
personalized
model
based
on
baseline
calibration
waking-stage
signals,
deriving
specialized
REM
detection.
It
achieved
best
accuracy
73.1%
(kappa
=
0.62,
F1-score
0.74)
benchmark
five
sleep-staging
classifiers.
Notably,
exhibited
high
predicting
overall
structure
subtle
changes
between
different
stages.
study
demonstrates
that
new
value
stream
medicine,
which
also
provides
technical
insights
future
implementation.