npj Digital Medicine,
Год журнала:
2025,
Номер
8(1)
Опубликована: Март 19, 2025
Abstract
Understanding
the
factors
associated
with
persistent
symptoms
after
SARS-CoV-2
infection
is
critical
to
improving
long-term
health
outcomes.
Using
a
wearable-derived
behavioral
and
physiological
dataset
(
n
=
20,815),
we
identified
individuals
characterized
by
self-reported
fatigue
shortness
of
breath
infection.
Compared
symptom-free
COVID-19
positive
(n
150)
negative
controls
150),
these
50)
had
higher
resting
heart
rates
(mean
difference
2.37/1.49
bpm)
lower
daily
step
counts
3030/2909
steps
fewer),
even
at
least
three
weeks
prior
In
addition,
were
significant
reduction
in
mean
quality
life
(WHO-5,
EQ-5D),
before
Here
show
that
may
be
pre-existing
fitness
levels
or
conditions.
These
findings
additionally
highlight
potential
wearable
devices
track
dynamics
provide
valuable
insights
into
outcomes
infectious
diseases.
Journal of Healthcare Informatics Research,
Год журнала:
2023,
Номер
7(2), С. 203 - 224
Опубликована: Июнь 1, 2023
Personal
health
data
is
subject
to
privacy
regulations,
making
it
challenging
apply
centralized
data-driven
methods
in
healthcare,
where
personalized
training
frequently
used.
Federated
Learning
(FL)
promises
provide
a
decentralized
solution
this
problem.
In
FL,
siloed
used
for
the
model
ensure
privacy.
paper,
we
investigate
viability
of
federated
approach
using
detection
COVID-19
pneumonia
as
use
case.
1411
individual
chest
radiographs,
sourced
from
public
repository
COVIDx8
are
The
dataset
contains
radiographs
753
normal
lung
findings
and
658
related
pneumonias.
We
partition
unevenly
across
five
separate
silos
order
reflect
typical
FL
scenario.
For
binary
image
classification
analysis
these
propose
ResNetFed,
pre-trained
ResNet50
modified
federation
so
that
supports
Differential
Privacy.
addition,
customized
strategy
with
radiographs.
experimental
results
show
ResNetFed
clearly
outperforms
locally
trained
models.
Due
uneven
distribution
silos,
observe
models
perform
significantly
worse
than
(mean
accuracies
63%
82.82%,
respectively).
particular,
shows
excellent
performance
underpopulated
achieving
up
+34.9
percentage
points
higher
accuracy
compared
local
Thus,
can
assist
initial
screening
medical
centers
privacy-preserving
manner.
Heliyon,
Год журнала:
2024,
Номер
10(2), С. e24053 - e24053
Опубликована: Янв. 1, 2024
After
severe
acute
respiratory
syndrome
coronavirus
2
(SARS-CoV-2)
infection,
a
series
of
symptoms
may
persist
for
long
time,
which
is
now
called
COVID.
It
was
found
that
COVID
can
affect
all
patients
with
COVID-19.
Therefore,
has
become
hot
topic.
In
this
study,
we
used
the
WOS
database
as
sample
data
source
to
conduct
bibliometric
and
visual
analysis
1765
articles
over
past
three
years
through
VOSviewer
R
package.
The
results
show
countries/authors
in
Europe
United
States
America
contribute
most
articles,
their
cooperation
also
active.
Keyword
co-occurrence
identified
four
clusters,
important
topics
including
mechanism,
clinical
symptoms,
epidemiological
characteristics,
management/treatment
Themes
such
"cognitive
impairment",
"endothelial
dysfunction",
"diagnosis",
"biomarkers"
are
likely
be
focus
new
attention
coming
period.
addition,
put
forward
possible
research
opportunities
on
researchers
practitioners
facilitate
future
research.
BMC Infectious Diseases,
Год журнала:
2025,
Номер
25(1)
Опубликована: Янв. 30, 2025
Abstract
Background
The
long-term
effects
of
COVID-19,
which
can
vary
significantly
in
type
and
timing,
are
considered
relevant
impacting
on
the
well-being
individuals.
present
study
aims
to
assess
incidence
outpatient
care
post-acute
phase
SARS-CoV-2
infection
two
Italian
regions.
Methods
has
a
multicentre,
population-based,
pre-post,
repeated
measures
design
compare
rate
access
visits
diagnostics
before
after
infection,
considering
follow-up
24
months.
made
use
previously
recorded
large-scale
healthcare
data
available
administrative
databases
Emilia-Romagna
(E-R)
Veneto
Analyses
were
carried
out
separately
regions
results
pooled
using
random
meta-analysis.
Results
There
27,140
subjects
E-R
22,876
who
included
analysis.
outputs
showed
an
increase
rates
starting
from
month
2
(IRR
=
1.68,
95%
CI
1.56–1.81)
with
peak
at
4
2.05,
1.95–2.15);
continued
reduced
intensity
up
15.
Stratified
analysis
revealed
that
severe
acute
COVID-19
had
higher
(up
IRR
3.96,
2.89–5.44),
as
well
patients
no
comorbidities
2.71,
2.60–2.83).
Conclusion
Long-term
include
burden
especially
first
months
infection.
increased
demand
for
resources
last
years
particular
subgroups
such
admitted
hospital
during
due
presentation
disease.
npj Digital Medicine,
Год журнала:
2025,
Номер
8(1)
Опубликована: Март 19, 2025
Abstract
Understanding
the
factors
associated
with
persistent
symptoms
after
SARS-CoV-2
infection
is
critical
to
improving
long-term
health
outcomes.
Using
a
wearable-derived
behavioral
and
physiological
dataset
(
n
=
20,815),
we
identified
individuals
characterized
by
self-reported
fatigue
shortness
of
breath
infection.
Compared
symptom-free
COVID-19
positive
(n
150)
negative
controls
150),
these
50)
had
higher
resting
heart
rates
(mean
difference
2.37/1.49
bpm)
lower
daily
step
counts
3030/2909
steps
fewer),
even
at
least
three
weeks
prior
In
addition,
were
significant
reduction
in
mean
quality
life
(WHO-5,
EQ-5D),
before
Here
show
that
may
be
pre-existing
fitness
levels
or
conditions.
These
findings
additionally
highlight
potential
wearable
devices
track
dynamics
provide
valuable
insights
into
outcomes
infectious
diseases.
