Cureus,
Journal Year:
2023,
Volume and Issue:
unknown
Published: Oct. 13, 2023
Cognitive
impairment
is
an
age-associated
disorder
of
increasing
prevalence
as
the
aging
population
continues
to
grow.
Classified
based
on
level
cognitive
decline,
memory,
function,
and
capacity
conduct
activities
daily
living,
ranges
from
mild
dementia.
When
considering
insidious
nature
etiologies
responsible
for
varying
degrees
impairment,
early
diagnosis
may
provide
a
clinical
benefit
through
facilitation
treatment.
Typical
relies
heavily
evaluation
in
primary
care
setting.
However,
there
evidence
that
other
diagnostic
tools
aid
earlier
different
underlying
pathologies
impairment.
Artificial
intelligence
represents
new
intersecting
field
with
healthcare
detection
neurodegenerative
disorders.
assessing
role
AI
detecting
it
important
consider
both
efficacy
algorithms
relevance
impact
interventions
result
detection.
Thus,
this
review
highlights
promising
investigations
developments
space
artificial
their
potential
patient
outcomes.
Biosensors,
Journal Year:
2025,
Volume and Issue:
15(2), P. 102 - 102
Published: Feb. 11, 2025
Monitoring
and
assessing
the
progression
of
symptoms
in
neurodegenerative
diseases,
including
Alzheimer's
Parkinson's
disease,
are
critical
for
improving
patient
outcomes.
Traditional
biomarkers,
such
as
cerebrospinal
fluid
analysis
brain
imaging,
widely
used
to
investigate
underlying
mechanisms
disease
enable
early
diagnosis.
In
contrast,
digital
biomarkers
derived
from
phenotypic
changes-such
EEG,
eye
movement,
gait,
speech
analysis-offer
a
noninvasive
accessible
alternative.
Leveraging
portable
available
devices,
smartphones
wearable
sensors,
emerging
promising
tool
ND
diagnosis
monitoring.
This
review
highlights
comprehensive
developments
emphasizing
their
unique
advantages
integration
potential
alongside
traditional
biomarkers.
medRxiv (Cold Spring Harbor Laboratory),
Journal Year:
2024,
Volume and Issue:
unknown
Published: April 5, 2024
Abstract
Background
Large
language
models
(LLMs)
have
shown
promising
performance
in
various
healthcare
domains,
but
their
effectiveness
identifying
specific
clinical
conditions
real
medical
records
is
less
explored.
This
study
evaluates
LLMs
for
detecting
signs
of
cognitive
decline
electronic
health
record
(EHR)
notes,
comparing
error
profiles
with
traditional
models.
The
insights
gained
will
inform
strategies
enhancement.
Methods
study,
conducted
at
Mass
General
Brigham
Boston,
MA,
analyzed
notes
from
the
four
years
prior
to
a
2019
diagnosis
mild
impairment
patients
aged
50
and
older.
We
used
randomly
annotated
sample
4,949
note
sections,
filtered
keywords
related
functions,
model
development.
For
testing,
random
1,996
sections
without
keyword
filtering
was
utilized.
developed
prompts
two
LLMs,
Llama
2
GPT-4,
on
HIPAA-compliant
cloud-computing
platforms
using
multiple
approaches
(e.g.,
both
hard
soft
prompting
analysis-based
instructions)
select
optimal
LLM-based
method.
Baseline
included
hierarchical
attention-based
neural
network
XGBoost.
Subsequently,
we
constructed
an
ensemble
three
majority
vote
approach.
Results
GPT-4
demonstrated
superior
accuracy
efficiency
compared
2,
did
not
outperform
outperformed
individual
models,
achieving
precision
90.3%,
recall
94.2%,
F1-score
92.2%.
Notably,
showed
significant
improvement
precision,
increasing
range
70%-79%
above
90%,
best-performing
single
model.
Error
analysis
revealed
that
63
samples
were
incorrectly
predicted
by
least
one
model;
however,
only
cases
(3.2%)
mutual
errors
across
all
indicating
diverse
among
them.
Conclusions
machine
learning
trained
local
EHR
data
exhibited
profiles.
these
found
be
complementary,
enhancing
diagnostic
performance.
Future
research
should
investigate
integrating
smaller,
localized
incorporating
domain
knowledge
enhance
tasks.
Alzheimer s & Dementia,
Journal Year:
2024,
Volume and Issue:
20(5), P. 3228 - 3250
Published: March 19, 2024
Alzheimer's
disease
(AD)
and
behavioral
variant
frontotemporal
dementia
(bvFTD)
lack
mechanistic
biophysical
modeling
in
diverse,
underrepresented
populations.
Electroencephalography
(EEG)
is
a
high
temporal
resolution,
cost-effective
technique
for
studying
globally,
but
lacks
models
produces
non-replicable
results.
PLOS Digital Health,
Journal Year:
2024,
Volume and Issue:
3(5), P. e0000519 - e0000519
Published: May 16, 2024
In
the
evolving
landscape
of
digital
medicine,
biomarkers
have
emerged
as
a
transformative
source
health
data,
positioning
them
an
indispensable
element
for
future
discipline.
This
necessitates
comprehensive
exploration
ethical
complexities
and
challenges
intrinsic
to
this
cutting-edge
technology.
To
address
imperative,
we
conducted
scoping
review,
seeking
distill
scientific
literature
exploring
dimensions
use
biomarkers.
By
closely
scrutinizing
literature,
review
aims
bring
light
underlying
issues
associated
with
development
integration
into
medical
practice.
Alzheimer s & Dementia,
Journal Year:
2024,
Volume and Issue:
20(11), P. 7437 - 7452
Published: Oct. 9, 2024
Abstract
INTRODUCTION
Early
detection
of
both
objective
and
subjective
cognitive
impairment
is
important.
Subjective
complaints
in
healthy
individuals
can
precede
deficits.
However,
the
differential
associations
cognition
with
modifiable
dementia
risk
factors
are
unclear.
METHODS
We
gathered
a
large
cross‐sectional
sample
(
N
=
3327,
age
18
to
84)
via
smartphone
app
quantified
13
memory
problems
three
measures
executive
function
(visual
working
memory,
flexibility,
model‐based
planning).
RESULTS
Depression,
socioeconomic
status,
hearing
handicap,
loneliness,
education,
smoking,
tinnitus,
little
exercise,
small
social
network,
stroke,
diabetes,
hypertension
were
all
associated
impairments
at
least
one
measure.
had
strongest
link
most
factors;
these
persisted
after
controlling
for
depression.
Age
mostly
did
not
moderate
associations.
DISCUSSION
was
more
sensitive
self‐report
than
cognition.
Smartphones
could
facilitate
detecting
earliest
impairments.
Highlights
Smartphone
assessments
factors.
stronger
links
These
fully
explained
by
largely
consistent
across
lifespan.
Current Neurology and Neuroscience Reports,
Journal Year:
2024,
Volume and Issue:
24(6), P. 151 - 161
Published: May 11, 2024
The
aging
global
population
poses
increasing
challenges
related
to
falls
and
dementia.
Early
identification
of
cognitive
decline,
particularly
before
noticeable
symptoms
manifest,
is
crucial
for
effective
intervention.
This
review
aims
determine
the
dynamic
balance
test
most
closely
associated
with
executive
function,
potentially
serving
as
a
biomarker
decline.
Based
on
recent
reviews,
inhibitory
control,
component
holds
significance
in
influencing
performance.
Studies
suggest
that
strength
correlation
between
cognition
tends
be
domain-specific
task-specific.
Despite
these
findings,
inconclusive
evidence
remains
regarding
connection
function
various
assessments.
Our
identifies
significant
association
all
tests
albeit
varying
strengths.
Notably,
medium
effect
size
observed
Timed
Up
Go
Functional
Reach
Test,
small
scales,
strong
postural
sway.
underscores
clear
relationship
task
performance
function.
Dynamic
posturography
potential
clinical
early
detection
note
caution
due
heterogeneity
limited
studies.
Chemical Science,
Journal Year:
2025,
Volume and Issue:
16(10), P. 4366 - 4373
Published: Jan. 1, 2025
Zn(
ii
)
coordination
to
monomeric
transthyretin
(M-TTR)
forms
a
ternary
complex
with
amyloid-β
(Aβ)
peptides
and
promotes
their
hydrolysis,
which
directs
M-TTR's
anti-amyloidogenic
activity
through
inhibiting
primary
nucleation.
