Proceedings of the National Academy of Sciences,
Год журнала:
2025,
Номер
122(7)
Опубликована: Фев. 11, 2025
In
wearable
smart
systems,
continuous
monitoring
and
accurate
classification
of
different
sleep-related
conditions
are
critical
for
enhancing
sleep
quality
preventing
chronic
conditions.
However,
the
requirements
device–skin
coupling
in
electrophysiological
systems
hinder
comfort
reliability
night
wearing.
Here,
we
report
a
washable,
skin-compatible
garment
system
that
captures
local
skin
strain
signals
under
weak
without
positioning
or
preparation
requirements.
A
printed
textile-based
sensor
array
responds
to
from
0.1
10%
with
gauge
factor
as
high
100
shows
independence
extrinsic
motion
artifacts
via
strain-isolating
pattern
design.
Through
reversible
starching
treatment,
ink
penetration
depth
during
direct
printing
on
garments
is
controlled
achieve
batch-to-batch
performance
variation
<10%.
Coupled
deep
learning,
explainable
AI,
transfer
learning
data
processing,
capable
classifying
six
states
an
accuracy
98.6%,
maintaining
excellent
explainability
(classification
low
bias)
generalization
(95%
new
users
few-shot
less
than
15
samples
per
class)
practical
applications,
paving
way
next-generation
daily
healthcare
management.
BMC Medical Informatics and Decision Making,
Год журнала:
2023,
Номер
23(1)
Опубликована: Ноя. 3, 2023
Abstract
Smartwatches
have
become
increasingly
popular
in
recent
times
because
of
their
capacity
to
track
different
health
indicators,
including
heart
rate,
patterns
sleep,
and
physical
movements.
This
scoping
review
aims
explore
the
utilisation
smartwatches
within
healthcare
sector.
According
Arksey
O'Malley's
methodology,
an
organised
search
was
performed
PubMed/Medline,
Scopus,
Embase,
Web
Science,
ERIC
Google
Scholar.
In
our
strategy,
761
articles
were
returned.
The
exclusion/inclusion
criteria
applied.
Finally,
35
selected
for
extracting
data.
These
included
six
studies
on
stress
monitoring,
movement
disorders,
three
sleep
tracking,
blood
pressure,
two
disease,
covid
pandemic,
safety
validation.
use
has
been
found
be
effective
diagnosing
symptoms
various
diseases.
particular,
shown
promise
detecting
diseases,
even
early
signs
COVID-19.
Nevertheless,
it
should
emphasised
that
there
is
ongoing
discussion
concerning
reliability
smartwatch
diagnoses
systems.
Despite
potential
advantages
offered
by
utilising
disease
detection,
imperative
approach
data
interpretation
with
prudence.
discrepancies
detection
between
algorithms
important
implications
use.
accuracy
used
are
crucial,
as
well
high
changes
status
themselves.
calls
development
medical
watches
creation
AI-hospital
assistants.
assistants
will
designed
help
patient
appointment
scheduling,
medication
management
tasks.
They
can
educate
patients
answer
common
questions,
freeing
providers
focus
more
complex
Journal of Medical Internet Research,
Год журнала:
2021,
Номер
24(1), С. e27487 - e27487
Опубликована: Ноя. 9, 2021
Background
Photoplethysmography
is
a
noninvasive
and
low-cost
method
to
remotely
continuously
track
vital
signs.
The
Oura
Ring
compact
photoplethysmography-based
smart
ring,
which
has
recently
drawn
attention
remote
health
monitoring
wellness
applications.
ring
used
acquire
nocturnal
heart
rate
(HR)
HR
variability
(HRV)
parameters
ubiquitously.
However,
these
are
highly
susceptible
motion
artifacts
environmental
noise.
Therefore,
validity
assessment
of
the
required
in
everyday
settings.
Objective
This
study
aims
evaluate
accuracy
time
domain
frequency
HRV
collected
by
against
medical
grade
chest
electrocardiogram
monitor.
Methods
We
conducted
overnight
home-based
using
an
Shimmer3
device.
35
healthy
individuals
were
assessed.
evaluated
within
2
tests,
that
is,
values
from
5-minute
recordings
(ie,
short-term
analysis)
average
per
night
sleep.
A
linear
regression
method,
Pearson
correlation
coefficient,
Bland–Altman
plot
compare
measurements
devices.
Results
Our
findings
showed
low
mean
biases
both
average-per-night
tests.
In
test,
error
variances
different.
provided
dashboard
root
square
successive
differences
[RMSSD])
relatively
variance
compared
with
extracted
normal
interbeat
interval
signals.
coefficient
tests
(P<.001)
indicated
HR,
RMSSD,
beat
intervals
(AVNN),
percentage
beat-to-beat
differ
more
than
50
ms
(pNN50)
had
high
positive
correlations
baseline
values;
SD
(SDNN)
(HF)
moderate
correlations,
(LF)
LF:HF
ratio
correlations.
AVNN,
pNN50
narrow
95%
CIs;
however,
SDNN,
LF,
HF,
wider
CIs.
contrast,
test
pNN50,
HF
relationships
(P<.001),
relationship
(P<.001).
also
considerably
lower
for
parameters.
Conclusions
could
accurately
measure
RMSSD
It
acceptable
SDNN
but
not
test.
LF
rates
Sensors,
Год журнала:
2021,
Номер
21(7), С. 2281 - 2281
Опубликована: Март 24, 2021
Pregnancy
is
a
unique
time
when
many
mothers
gain
awareness
of
their
lifestyle
and
its
impacts
on
the
fetus.
High-quality
care
during
pregnancy
needed
to
identify
possible
complications
early
ensure
mother’s
her
unborn
baby’s
health
well-being.
Different
studies
have
thus
far
proposed
maternal
monitoring
systems.
However,
they
are
designed
for
specific
problem
or
limited
questionnaires
short-term
data
collection
methods.
Moreover,
requirements
challenges
not
been
evaluated
in
long-term
studies.
Maternal
necessitates
comprehensive
framework
enabling
continuous
pregnant
women.
In
this
paper,
we
present
an
Internet-of-Things
(IoT)-based
system
provide
ubiquitous
postpartum.
The
consists
various
collectors
track
condition,
including
stress,
sleep,
physical
activity.
We
carried
out
full
implementation
conducted
real
human
subject
study
women
Southwestern
Finland.
then
system’s
feasibility,
energy
efficiency,
reliability.
Our
results
show
that
implemented
feasible
terms
usage
nine
months.
also
indicate
smartwatch,
used
our
study,
has
acceptable
efficiency
able
collect
reliable
photoplethysmography
data.
Finally,
discuss
integration
presented
with
current
healthcare
system.
Journal of Neuroscience,
Год журнала:
2022,
Номер
42(12), С. 2503 - 2515
Опубликована: Фев. 8, 2022
The
physiological
underpinnings
of
the
necessity
sleep
remain
uncertain.
Recent
evidence
suggests
that
increases
convection
cerebrospinal
fluid
(CSF)
and
promotes
export
interstitial
solutes,
thus
providing
a
framework
to
explain
why
all
vertebrate
species
require
sleep.
Cardiovascular,
respiratory
vasomotor
brain
pulsations
have
each
been
shown
drive
CSF
flow
along
perivascular
spaces,
yet
it
is
unknown
how
such
may
change
during
in
humans.
To
investigate
these
pulsation
phenomena
relation
sleep,
we
simultaneously
recorded
fast
fMRI,
magnetic
resonance
encephalography
(MREG),
electroencephalography
(EEG)
signals
group
healthy
volunteers.
We
quantified
sleep-related
changes
signal
frequency
distributions
by
spectral
entropy
analysis
calculated
strength
(vasomotor,
respiratory,
cardiac)
power
sum
15
subjects
(age
26.5
±
4.2
years,
6
females).
Finally,
identified
spatial
similarities
between
EEG
slow
oscillation
(0.2–2
Hz)
MREG
pulsations.
Compared
with
wakefulness,
nonrapid
eye
movement
(NREM)
was
characterized
reduced
increased
intensity.
These
effects
were
most
pronounced
posterior
areas
for
very
low-frequency
(≤0.1
but
also
evident
brain-wide
pulsations,
lesser
extent
cardiac
There
regions
spatially
overlapping
those
showing
changes.
suggest
enhanced
intensity
are
characteristic
NREM
With
our
findings
oscillation,
present
results
support
proposition
transport
human
brain.
SIGNIFICANCE
STATEMENT
report
mechanisms
driven
vasomotor,
respiration,
rhythms
increase
extending
previous
observations
their
association
glymphatic
clearance
rodents.
magnitudes
follow
rank
order
greater
than
correspondingly
declining
extents.
Spectral
entropy,
previously
known
as
vigilance
an
anesthesia
metric,
decreased
compared
awake
state
low
frequencies,
indicating
complexity.
An
occurring
early
phase
(NREM
1–2)
overlapped
changes,
reciprocal
measures.
Abstract
The
Emognition
dataset
is
dedicated
to
testing
methods
for
emotion
recognition
(ER)
from
physiological
responses
and
facial
expressions.
We
collected
data
43
participants
who
watched
short
film
clips
eliciting
nine
discrete
emotions:
amusement,
awe,
enthusiasm,
liking,
surprise,
anger,
disgust,
fear,
sadness.
Three
wearables
were
used
record
data:
EEG,
BVP
(2x),
HR,
EDA,
SKT,
ACC
(3x),
GYRO
(2x);
in
parallel
with
the
upper-body
videos.
After
each
clip,
completed
two
types
of
self-reports:
(1)
related
emotions
(2)
three
affective
dimensions:
valence,
arousal,
motivation.
obtained
facilitates
various
ER
approaches,
e.g.,
multimodal
ER,
EEG-
vs.
cardiovascular-based
dimensional
representation
transitions.
technical
validation
indicated
that
watching
elicited
targeted
emotions.
It
also
supported
signals’
high
quality.
Diagnostics,
Год журнала:
2022,
Номер
12(9), С. 2110 - 2110
Опубликована: Авг. 31, 2022
The
increasing
usage
of
smart
wearable
devices
has
made
an
impact
not
only
on
the
lifestyle
users,
but
also
biological
research
and
personalized
healthcare
services.
These
devices,
which
carry
different
types
sensors,
have
emerged
as
digital
diagnostic
tools.
Data
from
such
enabled
prediction
detection
various
physiological
well
psychological
conditions
diseases.
In
this
review,
we
focused
applications
wrist-worn
wearables
to
detect
multiple
diseases
cardiovascular
diseases,
neurological
disorders,
fatty
liver
metabolic
including
diabetes,
sleep
quality,
illnesses.
fruitful
requires
fast
insightful
data
analysis,
is
feasible
through
machine
learning.
discussed
machine-learning
outcomes
for
analyses.
Finally,
current
challenges
with
data,
future
perspectives
tools
domains.
Nutrients,
Год журнала:
2023,
Номер
16(1), С. 27 - 27
Опубликована: Дек. 21, 2023
Menopause
is
associated
with
an
increased
prevalence
of
obesity,
metabolic
syndrome,
cardiovascular
diseases,
and
osteoporosis.
These
diseases
unfavorable
laboratory
values,
which
are
characteristic
this
period
in
women,
can
be
significantly
improved
by
eliminating
reducing
dietary
risk
factors.
Changing
habits
during
perimenopause
most
effectively
achieved
through
nutrition
counseling
intervention.
To
reduce
the
factors
all
these
case
already
existing
disease,
therapy
led
a
dietitian
should
integral
part
treatment.
The
following
review
summarizes
recommendations
for
balanced
diet
fluid
intake,
prevention
role
sleep,
key
preventive
nutrients
menopause,
such
as
vitamin
D,
calcium,
C,
B
vitamins,
protein
intake.
In
summary,
many
lifestyle
developing
(cardiovascular
insulin
resistance,
type
2
diabetes
mellitus,
osteoporosis,
tumors)
symptoms
period.
The Journal of Headache and Pain,
Год журнала:
2025,
Номер
26(1)
Опубликована: Янв. 2, 2025
Part
2
explores
the
transformative
potential
of
artificial
intelligence
(AI)
in
addressing
complexities
headache
disorders
through
innovative
approaches,
including
digital
twin
models,
wearable
healthcare
technologies
and
biosensors,
AI-driven
drug
discovery.
Digital
twins,
as
dynamic
representations
patients,
offer
opportunities
for
personalized
management
by
integrating
diverse
datasets
such
neuroimaging,
multiomics,
sensor
data
to
advance
research,
optimize
treatment,
enable
virtual
trials.
In
addition,
devices
equipped
with
next-generation
biosensors
combined
multi-agent
chatbots
could
real-time
physiological
biochemical
monitoring,
diagnosing,
facilitating
early
attack
forecasting
prevention,
disease
tracking,
interventions.
Furthermore,
advances
discovery
leverage
machine
learning
generative
AI
accelerate
identification
novel
therapeutic
targets
treatment
strategies
migraine
other
disorders.
Despite
these
advances,
challenges
standardization,
model
explainability,
ethical
considerations
remain
pivotal.
Collaborative
efforts
between
clinicians,
biomedical
biotechnological
engineers,
scientists,
legal
representatives
bioethics
experts
are
essential
overcoming
barriers
unlocking
AI's
full
transforming
research
healthcare.
This
is
a
call
action
proposing
frameworks
AI-based
into
care.