Sensors,
Год журнала:
2025,
Номер
25(1), С. 205 - 205
Опубликована: Янв. 2, 2025
Objective:
In
this
paper,
we
explore
the
correlation
between
performance
reporting
and
development
of
inclusive
AI
solutions
for
biomedical
problems.
Our
study
examines
critical
aspects
bias
noise
in
context
medical
decision
support,
aiming
to
provide
actionable
solutions.
Contributions:
A
key
contribution
our
work
is
recognition
that
measurement
processes
introduce
arising
from
human
data
interpretation
selection.
We
concept
“noise-bias
cascade”
explain
their
interconnected
nature.
While
current
models
handle
well,
remains
a
significant
obstacle
achieving
practical
these
models.
analysis
spans
entire
lifecycle,
collection
model
deployment.
Recommendations:
To
effectively
mitigate
bias,
assert
need
implement
additional
measures
such
as
rigorous
design;
appropriate
statistical
analysis;
transparent
reporting;
diverse
research
representation.
Furthermore,
strongly
recommend
integration
uncertainty
during
deployment
ensure
utmost
fairness
inclusivity.
These
comprehensive
recommendations
aim
minimize
both
noise,
thereby
improving
future
support
systems.
Decision Analytics Journal,
Год журнала:
2023,
Номер
7, С. 100230 - 100230
Опубликована: Апрель 17, 2023
Artificial
Intelligence
(AI)
uses
systems
and
machines
to
simulate
human
intelligence
solve
common
real-world
problems.
Machine
learning
deep
are
technologies
that
use
algorithms
predict
outcomes
more
accurately
without
relying
on
intervention.
However,
the
opaque
black
box
model
cumulative
complexity
can
be
used
achieve.
Explainable
(XAI)
is
a
term
refers
provide
explanations
for
their
decision
or
predictions
users.
XAI
aims
increase
transparency,
trustworthiness
accountability
of
AI
system,
especially
when
they
high-stakes
application
such
as
healthcare,
finance
security.
This
paper
offers
systematic
literature
review
approaches
with
different
observes
91
recently
published
articles
describing
development
applications
in
manufacturing,
transportation,
finance.
We
investigated
Scopus,
Web
Science,
IEEE
Xplore
PubMed
databases,
find
pertinent
publications
between
January
2018
October
2022.
It
contains
research
modelling
were
retrieved
from
scholarly
databases
using
keyword
searches.
think
our
extends
by
working
roadmap
further
field.
Information Fusion,
Год журнала:
2023,
Номер
99, С. 101898 - 101898
Опубликована: Июнь 25, 2023
Mental
health
is
a
basic
need
for
sustainable
and
developing
society.
The
prevalence
financial
burden
of
mental
illness
have
increased
globally,
especially
in
response
to
community
worldwide
pandemic
events.
Children
suffering
from
such
disorders
find
it
difficult
cope
with
educational,
occupational,
personal,
societal
developments,
treatments
are
not
accessible
all.
Advancements
technology
resulted
much
research
examining
the
use
artificial
intelligence
detect
or
identify
characteristics
illness.
Therefore,
this
paper
presents
systematic
review
nine
developmental
(Autism
spectrum
disorder,
Attention
deficit
hyperactivity
Schizophrenia,
Anxiety,
Depression,
Dyslexia,
Post-traumatic
stress
Tourette
syndrome,
Obsessive-compulsive
disorder)
prominent
children
adolescents.
Our
focuses
on
automated
detection
these
using
physiological
signals.
This
also
detailed
discussion
signal
analysis,
feature
engineering,
decision-making
their
advantages,
future
directions
challenges
papers
published
children.
We
presented
details
dataset
description,
validation
techniques,
features
extracted
models.
present
open
questions
availability,
uncertainty,
explainability,
hardware
implementation
resources
analysis
machine
deep
learning
Finally,
main
findings
study
conclusion
section.
Human-Centric Intelligent Systems,
Год журнала:
2023,
Номер
3(3), С. 161 - 188
Опубликована: Авг. 10, 2023
Abstract
In
recent
years,
artificial
intelligence
(AI)
technology
has
been
used
in
most
if
not
all
domains
and
greatly
benefited
our
lives.
While
AI
can
accurately
extract
critical
features
valuable
information
from
large
amounts
of
data
to
help
people
complete
tasks
faster,
there
are
growing
concerns
about
the
non-transparency
decision-making
process.
The
emergence
explainable
(XAI)
allowed
humans
better
understand
control
systems,
which
is
motivated
provide
transparent
explanations
for
decisions
made
by
AI.
This
article
aims
present
a
comprehensive
overview
research
on
XAI
approaches
three
well-defined
taxonomies.
We
offer
an
in-depth
analysis
summary
status
prospects
applications
several
key
areas
where
reliable
urgently
needed
avoid
mistakes
decision-making.
conclude
discussing
XAI’s
limitations
future
directions.
Frontiers in Psychology,
Год журнала:
2023,
Номер
14
Опубликована: Июль 24, 2023
The
rapid
advancement
of
artificial
intelligence
(AI)
has
generated
an
increasing
demand
for
tools
that
can
assess
public
attitudes
toward
AI.
This
study
proposes
the
development
and
validation
AI
Attitude
Scale
(AIAS),
a
concise
self-report
instrument
designed
to
evaluate
perceptions
technology.
first
version
AIAS
present
manuscript
comprises
five
items,
including
one
reverse-scored
item,
which
aims
gauge
individuals'
beliefs
about
AI's
influence
on
their
lives,
careers,
humanity
overall.
scale
is
capture
AI,
focusing
perceived
utility
potential
impact
technology
society
humanity.
psychometric
properties
were
investigated
using
diverse
samples
in
two
separate
studies.
An
exploratory
factor
analysis
was
initially
conducted
preliminary
5-item
scale.
Such
revealed
need
divide
into
factors.
While
results
demonstrated
satisfactory
internal
consistency
overall
its
correlation
with
related
measures,
analyses
each
showed
robust
Factor
1
but
insufficient
2.
As
result,
second
developed
validated,
omitting
item
displayed
weak
remaining
items
questionnaire.
refined
final
1-factor,
4-item
superior
compared
initial
proposed
Further
confirmatory
analyses,
performed
different
sample
participants,
confirmed
1-factor
model
(4-items)
exhibited
adequate
fit
data,
providing
additional
evidence
scale's
structural
validity
generalizability
across
populations.
In
conclusion,
reported
this
article
suggest
validated
4-items
be
valuable
researchers
professionals
working
who
seek
understand
users'
general
Computers in Biology and Medicine,
Год журнала:
2023,
Номер
155, С. 106676 - 106676
Опубликована: Фев. 18, 2023
Attention
deficit
hyperactivity
disorder
(ADHD)
is
a
neurodevelopmental
that
affects
person's
sleep,
mood,
anxiety,
and
learning.
Early
diagnosis
timely
medication
can
help
individuals
with
ADHD
perform
daily
tasks
without
difficulty.
Electroencephalogram
(EEG)
signals
neurologists
to
detect
by
examining
the
changes
occurring
in
it.
The
EEG
are
complex,
non-linear,
non-stationary.
It
difficult
find
subtle
differences
between
healthy
control
visually.
Also,
making
decisions
from
existing
machine
learning
(ML)
models
do
not
guarantee
similar
performance
(unreliable).The
paper
explores
combination
of
variational
mode
decomposition
(VMD),
Hilbert
transform
(HT)
called
VMD-HT
extract
hidden
information
signals.
Forty-one
statistical
parameters
extracted
absolute
value
analytical
functions
(AMF)
have
been
classified
using
explainable
boosted
(EBM)
model.
interpretability
model
tested
analysis
measurement.
importance
features,
channels
brain
regions
has
identified
glass-box
black-box
approach.
model's
local
global
explainability
visualized
Local
Interpretable
Model-agnostic
Explanations
(LIME),
SHapley
Additive
exPlanations
(SHAP),
Partial
Dependence
Plot
(PDP),
Morris
sensitivity.
To
best
our
knowledge,
this
first
work
prediction
detection,
particularly
for
children.Our
results
show
provided
an
accuracy
99.81%,
sensitivity
99.78%,
99.84%
specificity,
F-1
measure
99.83%,
precision
99.87%,
false
detection
rate
0.13%,
Mathew's
correlation
coefficient,
negative
predicted
value,
critical
success
index
99.61%,
99.73%,
99.66%,
respectively
detecting
automatically
ten-fold
cross-validation.
area
under
curve
100%
while
99.87%
99.73%
obtained
HC,
respectively.The
frontal
region
highest
compared
pre-frontal,
central,
parietal,
occipital,
temporal
regions.
Our
findings
important
insight
into
developed
which
highly
reliable,
robust,
interpretable,
clinicians
children.
rapid
robust
technologies
may
reduce
cost
treatment
lessen
number
patients
undergoing
lengthy
procedures.
Healthcare,
Год журнала:
2024,
Номер
12(5), С. 562 - 562
Опубликована: Фев. 28, 2024
The
healthcare
sector
is
faced
with
challenges
due
to
a
shrinking
workforce
and
rise
in
chronic
diseases
that
are
worsening
demographic
epidemiological
shifts.
Digital
health
interventions
include
artificial
intelligence
(AI)
being
identified
as
some
of
the
potential
solutions
these
challenges.
ultimate
aim
AI
systems
improve
patient’s
outcomes
satisfaction,
overall
population’s
health,
well-being
professionals.
applications
services
vast
expected
assist,
automate,
augment
several
services.
Like
any
other
emerging
innovation,
also
comes
its
own
risks
requires
regulatory
controls.
A
review
literature
was
undertaken
study
existing
landscape
for
developed
nations.
In
global
landscape,
most
regulations
revolve
around
Software
Medical
Device
(SaMD)
regulated
under
digital
products.
However,
it
necessary
note
current
may
not
suffice
AI-based
technologies
capable
working
autonomously,
adapting
their
algorithms,
improving
performance
over
time
based
on
new
real-world
data
they
have
encountered.
Hence,
convergence
healthcare,
similar
voluntary
code
conduct
by
US-EU
Trade
Technology
Council,
would
be
beneficial
all
nations,
developing
or
developed.
