Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
7
,
No
.
1
, M
ar
c
h
20
26
,
p
p
.
1
21
~
1
30
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v
7
i
1
.
pp
1
21
-
1
30
121
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
Adv
a
nces in
Park
inso
n’s disea
se di
a
g
no
sis
and treat
ment
using
a
rtif
icia
l in
tellige
nce:
a
r
ev
iew
M
ehr
Ali Q
a
s
im
i
1
,
Z
üley
ha
Yılm
a
z
Aca
r
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
e
l
ç
u
k
U
n
i
v
e
r
s
i
t
y
,
K
o
n
y
a
,
Tü
r
k
i
y
e
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
Te
c
h
n
o
l
o
g
y
,
S
e
l
ç
u
k
U
n
i
v
e
r
si
t
y
,
K
o
n
y
a
,
T
ü
r
k
i
y
e
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
24
,
2
0
2
5
R
ev
is
ed
No
v
27
,
2
0
2
5
Acc
ep
ted
J
an
1
,
2
0
2
6
P
a
rk
in
so
n
’s
d
ise
a
se
(P
D)
d
iag
n
o
sis
a
n
d
m
o
n
it
o
r
in
g
h
a
v
e
si
g
n
ifi
c
a
n
t
ly
imp
ro
v
e
d
b
e
c
a
u
se
to
c
u
rre
n
t
a
d
v
a
n
c
e
m
e
n
ts
in
a
rti
ficia
l
i
n
telli
g
e
n
c
e
(AI),
p
a
rti
c
u
larly
i
n
th
e
a
re
a
s
o
f
d
e
e
p
lea
rn
in
g
(DL)
a
n
d
m
a
c
h
in
e
lea
rn
in
g
(M
L)
.
Early
-
sta
g
e
i
n
se
n
siti
v
it
y
o
f
trad
it
i
o
n
a
l
d
iag
n
o
st
ic
tec
h
n
iq
u
e
s
n
e
c
e
ss
it
a
tes
th
e
u
se
o
f
c
lev
e
r,
d
a
ta
-
d
riv
e
n
a
lt
e
rn
a
ti
v
e
s.
AI
-
p
o
we
re
d
n
o
n
in
v
a
siv
e
d
iag
n
o
stic
m
e
th
o
d
s
li
k
e
sp
e
e
c
h
re
c
o
g
n
i
ti
o
n
,
h
a
n
d
wri
ti
n
g
a
n
a
ly
sis,
a
n
d
n
e
u
r
o
ima
g
in
g
c
a
teg
o
riza
ti
o
n
a
re
t
h
e
m
a
in
to
p
i
c
o
f
th
is
tec
h
n
ica
l
re
v
iew
.
We
p
ro
v
id
e
a
su
m
m
a
ry
o
f
c
o
m
p
a
ra
t
iv
e
p
e
rf
o
rm
a
n
c
e
m
e
a
su
re
s
fro
m
re
c
e
n
t
m
o
d
e
ls,
h
ig
h
li
g
h
ti
n
g
th
e
ir
p
ra
c
ti
c
a
l
u
se
f
u
ln
e
ss
,
d
a
ta
m
o
d
a
li
t
y
,
a
n
d
a
c
c
u
ra
c
y
.
Also
c
o
v
e
re
d
a
re
imp
o
rta
n
t
issu
e
s li
k
e
d
a
ta v
a
riab
il
it
y
,
re
a
l
-
wo
rl
d
imp
lem
e
n
tatio
n
,
a
n
d
m
o
d
e
l
in
ter
p
re
tab
il
it
y
.
U
n
li
k
e
p
ri
o
r
su
r
v
e
y
s
t
h
a
t
p
rima
r
il
y
re
p
o
rt
a
c
c
u
ra
c
y
m
e
tri
c
s,
th
is
re
v
iew
e
x
p
li
c
it
ly
f
o
c
u
se
s
o
n
id
e
n
t
ify
i
n
g
th
e
g
a
p
b
e
twe
e
n
e
x
p
e
rime
n
tal
AI
p
e
rfo
r
m
a
n
c
e
a
n
d
re
a
l
-
wo
rld
c
li
n
ica
l
d
e
p
lo
y
m
e
n
t
,
e
m
p
h
a
siz
in
g
in
terp
re
tab
il
i
ty
,
v
a
li
d
a
ti
o
n
,
a
n
d
sc
a
lab
il
i
ty
c
h
a
ll
e
n
g
e
s
in
PD
d
iag
n
o
sis.
Th
e
p
u
r
p
o
se
o
f
t
h
is
le
tt
e
r
is
t
o
p
ro
v
id
e
g
u
id
a
n
c
e
f
o
r
re
se
a
rc
h
e
rs
c
re
a
ti
n
g
d
e
p
lo
y
a
b
le an
d
c
li
n
ica
ll
y
v
a
li
d
AI sy
ste
m
s fo
r
PD
d
e
tec
ti
o
n
.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Dee
p
lear
n
in
g
Ma
ch
in
e
lear
n
in
g
No
n
-
in
v
asiv
e
d
ia
g
n
o
s
is
Par
k
in
s
o
n
’
s
d
is
ea
s
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Me
h
r
Ali Q
asimi
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
I
n
s
titu
te
o
f
Scien
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
Selçu
k
U
n
iv
er
s
ity
Ko
n
y
a,
T
ü
r
k
iy
e
E
m
ail:
q
1
.
m
eh
r
ali@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
(
P
D
)
is
a
d
eg
e
n
e
r
a
t
iv
e
n
eu
r
o
l
o
g
ic
a
l
d
i
s
o
r
d
e
r
m
a
r
k
e
d
b
y
m
o
v
e
m
en
t
d
i
f
f
ic
u
l
t
i
e
s
,
r
i
g
id
i
t
y
,
an
d
tr
em
o
r
s
,
r
e
s
u
l
t
in
g
f
r
o
m
t
h
e
lo
s
s
o
f
d
o
p
am
i
n
er
g
i
c
n
e
u
r
o
n
s
.
T
h
e
d
i
s
e
a
s
e
m
an
i
f
e
s
t
s
t
h
r
o
u
g
h
a
b
r
o
a
d
s
p
ec
t
r
u
m
o
f
m
o
t
o
r
a
n
d
n
o
n
-
m
o
t
o
r
s
y
m
p
to
m
s
,
i
n
c
l
u
d
i
n
g
t
r
e
m
o
r
,
b
r
a
d
y
k
i
n
e
s
i
a
,
m
u
s
c
u
l
ar
r
i
g
i
d
i
ty
,
p
o
s
t
u
r
a
l
in
s
t
a
b
i
l
i
ty
,
s
p
e
e
ch
i
m
p
a
ir
m
en
t
,
a
n
x
i
e
t
y
,
co
g
n
it
i
v
e
d
ec
l
i
n
e,
an
d
l
o
s
s
o
f
s
m
e
l
l
.
T
h
e
s
e
m
o
to
r
a
n
d
n
o
n
-
m
o
to
r
m
an
i
f
e
s
t
a
t
io
n
s
o
f
PD
a
r
e
i
l
l
u
s
t
r
a
t
e
d
i
n
F
ig
u
r
e
1
,
h
ig
h
l
ig
h
t
in
g
t
h
e
b
r
o
ad
s
y
m
p
to
m
s
p
e
c
t
r
u
m
t
h
a
t
m
o
t
iv
a
t
e
s
th
e
d
e
v
e
l
o
p
m
en
t
o
f
m
u
l
t
im
o
d
a
l
ar
t
i
f
i
c
ia
l
in
te
l
l
i
g
e
n
c
e
(
A
I
)
-
b
a
s
ed
d
i
ag
n
o
s
t
i
c
a
p
p
r
o
a
ch
e
s
.
T
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
A
I
s
y
s
t
em
s
u
t
i
l
i
z
i
n
g
m
u
l
t
im
o
d
a
l
b
io
m
ed
i
ca
l
d
a
t
a
h
a
s
b
e
e
n
p
r
o
m
p
t
e
d
b
y
t
h
e
n
e
e
d
f
o
r
e
ar
l
y
d
i
a
g
n
o
s
i
s
[
1
]
.
A
I
t
e
c
h
n
i
q
u
e
s
c
a
n
id
e
n
t
if
y
s
m
a
l
l
b
i
o
m
a
r
k
e
r
s
i
n
s
p
e
e
c
h
,
g
a
i
t
,
el
e
c
t
r
o
e
n
c
e
p
h
a
l
o
g
r
ap
h
y
(
E
E
G
)
,
a
n
d
i
m
ag
i
n
g
d
a
ta
,
i
n
co
n
t
r
a
s
t
t
o
tr
a
d
i
t
io
n
a
l
d
i
a
g
n
o
s
e
s
t
h
a
t
d
e
p
e
n
d
o
n
cl
i
n
i
c
a
l
ev
a
l
u
a
t
i
o
n
s
.
T
h
e
f
o
c
u
s
o
f
th
i
s
r
e
v
i
e
w
i
s
o
n
d
e
ep
l
e
ar
n
in
g
(
D
L
)
an
d
m
a
ch
i
n
e
l
e
a
r
n
i
n
g
(
M
L
)
m
o
d
e
l
s
th
a
t
h
a
v
e
th
e
p
o
t
e
n
t
ia
l
t
o
b
e
i
m
p
l
e
m
e
n
t
ed
in
t
h
e
r
e
a
l
w
o
r
ld
an
d
h
a
v
e
ex
c
e
l
l
en
t
d
i
ag
n
o
s
t
i
c
a
c
cu
r
a
c
y
[
2
]
.
P
D
h
a
s
a
s
u
b
s
t
a
n
t
i
a
l
n
e
g
a
t
iv
e
i
m
p
a
c
t
o
n
a
p
a
t
i
e
n
t’
s
q
u
a
l
i
t
y
o
f
l
i
f
e,
s
o
c
i
a
l
in
t
e
r
ac
t
i
o
n
s
,
f
am
i
l
y
d
y
n
am
i
c
s
,
an
d
f
in
an
c
e
s
f
o
r
b
o
th
p
eo
p
l
e
an
d
s
o
c
i
e
t
y
.
P
D
s
y
m
p
to
m
s
in
c
l
u
d
e
t
r
em
o
r
,
s
lo
w
n
e
s
s
o
f
m
o
v
em
e
n
t
,
t
i
g
h
t
m
u
s
c
l
e
s
,
i
r
r
e
g
u
l
a
r
g
a
i
t
,
an
d
p
r
o
b
le
m
s
w
i
t
h
b
a
l
a
n
ce
an
d
c
o
o
r
d
in
a
t
io
n
[
3
]
.
C
u
r
in
g
PD
is
n
o
t
y
et
p
o
s
s
ib
le,
an
d
ef
f
ec
tiv
e
m
ed
icatio
n
is
s
till
v
er
y
d
if
f
ic
u
lt
to
c
o
m
e
b
y
.
A
m
ix
o
f
h
er
ed
itar
y
a
n
d
en
v
ir
o
n
m
en
tal
v
ar
iab
les
ar
e
th
o
u
g
h
t
to
c
o
n
tr
ib
u
te
to
PD,
wh
ile
th
e
p
r
ec
is
e
r
ea
s
o
n
s
ar
e
y
et
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
1
,
M
ar
ch
20
26
:
1
21
-
1
30
122
u
n
k
n
o
wn
.
A
p
er
s
o
n
’
s
q
u
ality
o
f
life
m
ay
also
b
e
im
p
ac
te
d
b
y
n
o
n
-
m
o
t
o
r
illn
ess
es
in
clu
d
in
g
d
ep
r
ess
io
n
an
d
d
em
en
tia.
B
ec
au
s
e
th
er
e
is
n
o
o
n
e
b
lo
o
d
test
o
r
la
b
o
r
ato
r
y
t
est
th
at
ca
n
ac
cu
r
ately
d
iag
n
o
s
e
PD
an
d
tr
ac
k
its
p
r
o
g
r
ess
io
n
,
tim
ely
d
iag
n
o
s
is
is
cr
itical
to
p
r
eser
v
in
g
a
h
ig
h
q
u
ality
o
f
life
[
4
]
.
Sin
ce
t
h
ese
n
eu
r
o
tr
an
s
m
itter
s
ar
e
ess
en
tial
f
o
r
r
eg
u
latin
g
m
o
v
em
en
t,
m
o
to
r
f
u
n
ctio
n
is
th
e
PD
p
r
im
ar
y
f
ea
t
u
r
e.
T
h
e
illn
ess
d
ev
elo
p
s
in
f
iv
e
p
h
ases
,
with
th
e
f
ir
s
t
s
tag
e
e
x
h
ib
itin
g
m
in
o
r
tr
em
o
r
s
an
d
m
o
b
ilit
y
p
r
o
b
lem
s
an
d
th
e
la
s
t
s
tag
e
ex
h
ib
itin
g
s
ev
er
e
an
d
in
ca
p
ac
itatin
g
s
y
m
p
to
m
s
,
lo
s
s
o
f
m
o
v
em
en
t,
an
d
an
elev
ate
d
ch
a
n
ce
o
f
d
ev
elo
p
in
g
o
th
er
ch
r
o
n
ic
co
n
d
itio
n
s
[
5
]
.
B
ased
o
n
o
u
r
r
esear
ch
an
d
r
ev
iews,
a
lar
g
e
n
u
m
b
er
o
f
ar
ticles
h
av
e
d
is
cu
s
s
ed
v
ar
io
u
s
m
eth
o
d
s
f
o
r
d
etec
tin
g
o
r
d
iag
n
o
s
in
g
P
D
an
d
its
u
n
iq
u
e
v
ar
iety
.
I
n
th
is
p
ap
er
,
we
p
r
esen
t
a
s
y
s
tem
atic
r
ev
iew
o
f
r
ec
en
t
s
tu
d
ies
o
n
PD
th
at
ap
p
ly
AI
,
ML
,
an
d
DL
tech
n
iq
u
es
f
o
r
d
ia
g
n
o
s
is
an
d
tr
ea
tm
en
t.
Fo
llo
win
g
t
h
e
PR
I
SMA
f
r
am
ewo
r
k
,
3
1
s
tu
d
ies
p
u
b
lis
h
ed
b
etwe
en
2
0
1
6
a
n
d
2
0
2
4
ar
e
a
n
aly
ze
d
an
d
ca
teg
o
r
ize
d
ac
co
r
d
i
n
g
to
d
iag
n
o
s
tic
m
o
d
alities
,
tr
ea
tm
en
t
ap
p
r
o
ac
h
es,
AI
tech
n
iq
u
es,
an
d
PD
s
u
b
ty
p
es.
T
h
is
s
tr
u
ctu
r
ed
s
y
n
th
esis
p
r
o
v
id
es
an
o
r
g
an
ized
o
v
er
v
iew
o
f
r
ec
en
t
a
d
v
an
ce
s
an
d
lay
s
th
e
f
o
u
n
d
atio
n
f
o
r
id
e
n
tify
in
g
c
u
r
r
en
t lim
itatio
n
s
an
d
o
p
en
r
esear
ch
c
h
allen
g
es.
Fig
u
r
e
1
.
Par
k
i
n
s
o
n
'
s
d
is
ea
s
e
c
an
s
h
o
w
u
p
in
s
ig
n
if
ican
t m
o
t
o
r
an
d
n
o
n
-
m
o
to
r
way
s
[
6
]
2.
M
E
T
H
O
D
W
e
u
s
ed
k
ey
wo
r
d
s
lik
e
“P
ar
k
in
s
o
n
’
s
Dis
ea
s
e”
,
“M
ac
h
in
e
L
ea
r
n
in
g
”,
“De
ep
L
ea
r
n
in
g
”
an
d
“Dia
g
n
o
s
is
”
to
s
ea
r
ch
an
d
s
elec
t
p
ap
er
s
f
r
o
m
Pu
b
Me
d
,
Go
o
g
le
Sch
o
lar
,
Scien
ce
Dir
ec
t,
a
n
d
Natu
r
e
t
h
at
wer
e
p
u
b
lis
h
ed
b
etwe
en
2
0
1
6
an
d
2
0
2
4
.
W
e
o
n
ly
c
o
n
s
id
er
ed
r
e
s
ea
r
ch
th
at
r
ep
o
r
ted
AI
-
b
ased
d
iag
n
o
s
tic
m
o
d
els
with
p
er
f
o
r
m
an
ce
m
ea
s
u
r
es.
E
x
clu
d
ed
wer
e
s
tu
d
ies
th
at
o
n
ly
ex
am
in
e
d
clin
ical
o
u
tc
o
m
es
with
o
u
t
in
clu
d
in
g
AI
in
n
o
v
atio
n
.
Af
ter
th
o
r
o
u
g
h
ly
r
e
v
iewin
g
t
h
e
f
u
ll
tex
ts
o
f
r
ele
v
an
t
s
tu
d
ies
a
n
d
r
em
o
v
in
g
d
u
p
licates,
w
e
f
o
llo
wed
th
e
PR
I
SMA
s
tatem
en
t f
r
am
ewo
r
k
f
o
r
p
r
ep
ar
atio
n
an
d
r
e
p
o
r
tin
g
,
as sh
o
wn
in
Fi
g
u
r
e
2.
T
h
e
s
tep
s
in
th
e
f
r
am
ew
o
r
k
a
r
e
lis
ted
b
elo
w:
i)
Step
1
:
t
h
er
e
wer
e
1
1
4
ar
ticle
s
p
r
o
d
u
ce
d
a
f
ter
th
e
s
ea
r
ch
s
tr
ateg
y
was
ap
p
lie
d
u
s
in
g
k
ey
w
o
r
d
s
f
r
o
m
t
h
e
f
o
u
r
d
atab
ases
(
Scien
ce
Dir
ec
t,
Natu
r
e,
Pu
b
Me
d
,
a
n
d
Go
o
g
l
e
Sch
o
lar
)
.
Of
th
ese,
8
2
wer
e
r
etr
iev
ed
f
r
o
m
Go
o
g
le
Sch
o
lar
,
1
5
f
r
o
m
Scie
n
ce
Dir
ec
t,
1
2
f
r
o
m
Pu
b
Me
d
,
an
d
5
f
r
o
m
th
e
Natu
r
e
d
atab
as
e.
I
n
th
is
s
tep
2
4
d
u
p
licated
p
a
p
er
s
wer
e
f
o
u
n
d
an
d
r
em
o
v
ed
.
ii)
Step
2
:
f
o
llo
win
g
a
n
an
al
y
s
is
o
f
th
e
ab
s
tr
ac
ts
an
d
titl
es,
th
e
au
th
o
r
s
elim
in
ated
3
0
p
u
b
lica
tio
n
s
th
at
d
id
n
o
t u
s
e
AI
,
ML
,
o
r
DL
tech
n
iq
u
es,
wer
e
ir
r
elev
an
t,
o
r
wer
e
p
aid
f
o
r
.
iii)
Step
3
:
2
9
ar
ticles
f
ailed
to
m
atch
th
e
in
clu
s
io
n
r
eq
u
ir
e
m
en
ts
at
th
e
f
in
al
s
tag
e,
f
o
llo
win
g
f
u
ll
-
te
x
t
ev
alu
atio
n
,
f
o
r
e
x
am
p
le,
n
o
t b
ein
g
r
elev
an
t a
r
ticles o
r
u
s
in
g
AI
,
ML
,
o
r
DL
ap
p
r
o
ac
h
es.
iv
)
Step
4
:
f
in
ally
,
we
ac
h
ie
v
ed
3
1
m
ain
o
r
r
elev
a
n
t o
n
es a
n
d
in
clu
d
ed
th
em
in
o
u
r
s
tu
d
y
.
Am
o
n
g
th
e
3
1
s
tu
d
ies
r
ev
iew
ed
,
9
co
n
ce
n
tr
ate
o
n
PD
,
8
ar
t
icles
ad
d
r
ess
its
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t,
an
d
1
1
p
a
p
er
s
ex
p
lo
r
e
th
e
u
s
e
o
f
AI
an
d
v
ar
io
u
s
ML
o
r
DL
m
eth
o
d
s
f
o
r
PD
p
r
ed
ictio
n
.
A
d
d
itio
n
ally
,
3
p
a
p
er
s
f
o
cu
s
o
n
d
if
f
er
e
n
t ty
p
es o
f
PD
.
T
h
e
p
e
r
ce
n
tag
e
a
n
aly
s
is
o
f
th
ese
v
alu
es is
illu
s
tr
ated
in
Fig
u
r
e
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
d
va
n
ce
s
in
P
a
r
kin
s
o
n
’
s
d
is
ea
s
e
d
ia
g
n
o
s
is
a
n
d
tr
ea
tmen
t u
s
in
g
a
r
tifi
cia
l in
tellig
en
ce
:
…
(
Meh
r
A
li Qa
s
imi)
123
Fig
u
r
e
2
.
PR
I
SMA
di
ag
r
am
o
f
Par
k
is
o
n
’
s
d
is
ea
s
e
f
r
o
m
d
i
f
f
er
en
t p
ap
er
s
an
d
d
atab
ases
Fig
u
r
e
3
.
Dis
tr
ib
u
tio
n
o
f
r
ev
ie
wed
s
tu
d
ies
o
n
Par
k
in
s
o
n
’
s
di
s
ea
s
e
3.
O
VE
RVI
E
W
O
F
P
ARK
I
N
S
O
N’
S DIS
E
AS
E
Acc
o
r
d
in
g
to
o
u
r
s
y
s
tem
atic
r
ev
iew,
wh
ich
c
o
v
er
s
all
3
1
o
f
th
e
ch
o
s
en
p
u
b
licatio
n
s
,
we
id
en
tifie
d
th
r
ee
d
is
tin
ct
s
u
b
s
ec
tio
n
s
.
T
h
ese
in
clu
d
e
ty
p
es
o
f
PD,
AI
,
ML
,
an
d
DL
m
o
d
els
f
o
r
q
u
i
ck
an
d
p
r
ec
is
e
PD
d
iag
n
o
s
is
.
T
h
e
f
i
n
al
s
u
b
s
ec
tio
n
f
o
cu
s
es o
n
PD tr
ea
tm
en
t.
3
.
1
.
T
y
pes
o
f
P
a
rk
ins
o
n’s
dis
ea
s
e
PD
is
clas
s
if
ied
in
to
two
b
asic c
ateg
o
r
ies:
‒
Ak
in
etic
-
r
ig
id
ty
p
e
is
p
r
im
ar
il
y
d
ef
in
e
d
b
y
s
tiff
n
ess
an
d
s
lo
wn
ess
o
f
m
o
v
em
e
n
t.
‒
T
r
em
o
r
-
d
o
m
in
a
n
t f
o
r
m
is
d
is
tin
g
u
is
h
ed
b
y
s
ig
n
if
ican
t t
r
em
o
r
s
,
esp
ec
ially
at
r
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
1
,
M
ar
ch
20
26
:
1
21
-
1
30
124
T
h
ese
k
in
d
s
m
ig
h
t
b
e
u
s
ef
u
l
i
n
co
m
p
r
eh
e
n
d
in
g
a
n
d
tr
ea
tin
g
th
e
m
an
y
s
y
m
p
t
o
m
s
th
at
p
eo
p
le
with
PD
m
ig
h
t
en
co
u
n
ter
[
7
]
.
3
.
2
.
P
a
rk
ins
o
n’s
dis
ea
s
e
dia
g
no
s
is
A
s
u
b
s
et
o
f
AI
ca
lled
ML
u
s
e
s
d
ata
an
aly
s
is
an
d
r
ap
id
,
n
o
n
-
p
r
o
g
r
am
m
in
g
d
ec
is
io
n
s
.
I
t
u
s
es
tr
ain
in
g
d
ata
to
au
to
m
atica
lly
g
en
er
at
e
an
aly
tical
m
o
d
els
[
8
]
.
PD
h
as
b
ee
n
id
en
tifie
d
u
s
in
g
a
n
u
m
b
er
o
f
tech
n
iq
u
es
b
ased
o
n
d
ata
f
r
o
m
s
p
ee
c
h
,
g
ait
p
atter
n
s
,
f
o
r
ce
m
o
n
ito
r
in
g
,
s
m
ell
id
e
n
tific
atio
n
,
an
d
s
p
o
n
tan
e
o
u
s
ca
r
d
io
v
ascu
lar
o
s
cillatio
n
s
.
Ma
n
y
s
tr
ateg
ies
h
av
e
s
h
o
wed
p
o
ten
tial,
in
clu
d
in
g
estab
lis
h
in
g
an
ea
r
ly
d
etec
tio
n
s
y
s
tem
b
ased
o
n
r
ed
u
ce
d
v
o
ca
l
f
ea
tu
r
es
an
d
ev
alu
atin
g
s
p
ee
ch
d
is
o
r
d
er
s
u
s
in
g
SW
I
PE
s
ch
em
e
[
9
]
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
th
ese
ap
p
r
o
ac
h
es
v
ar
ies
ac
r
o
s
s
s
tu
d
ies
d
u
e
to
d
if
f
er
en
ce
s
in
d
ata
m
o
d
ality
,
f
ea
tu
r
e
s
tr
u
ctu
r
e,
an
d
d
ataset
s
ize,
in
d
icatin
g
t
h
at
p
er
f
o
r
m
a
n
ce
is
h
ig
h
ly
co
n
tex
t
-
d
ep
e
n
d
en
t
r
ath
er
th
a
n
u
n
iv
er
s
ally
o
p
tim
al.
Fu
r
th
er
m
o
r
e
,
a
g
ait
s
ig
n
al
-
b
ased
1
D
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
e
two
r
k
PD
d
etec
tio
n
s
y
s
tem
h
as
b
ee
n
s
h
o
wn
.
Gait
tr
ac
k
in
g
an
d
in
s
p
ec
tio
n
s
till
f
a
ce
a
n
u
m
b
e
r
o
f
d
if
f
icu
lties
,
in
clu
d
in
g
th
e
r
eq
u
ir
e
m
en
t
f
o
r
s
p
ec
ialis
t
eq
u
ip
m
en
t,
p
len
ty
o
f
r
o
o
m
,
an
d
s
en
s
itiv
ity
to
b
ac
k
g
r
o
u
n
d
n
o
is
e
in
s
p
ee
ch
r
ec
o
r
d
in
g
s
.
Alth
o
u
g
h
DL
m
o
d
els
ca
n
ca
p
tu
r
e
co
m
p
lex
tem
p
o
r
al
p
atter
n
s
in
g
ait
s
ig
n
als,
th
eir
p
er
f
o
r
m
an
ce
m
ay
b
e
co
n
s
tr
ain
ed
in
s
m
all
d
atasets
wh
er
e
s
im
p
ler
m
o
d
els
g
en
e
r
alize
m
o
r
e
ef
f
ec
tiv
ely
.
T
h
e
a
b
ilit
y
to
s
lo
w
d
o
wn
t
h
e
p
r
o
g
r
ess
io
n
o
f
P
D
m
ak
es
ea
r
ly
an
d
p
r
ec
is
e
PD
id
en
tific
atio
n
cr
u
cial
[
1
0
]
.
T
o
en
h
a
n
ce
th
e
id
en
tific
atio
n
o
f
PD,
n
u
m
er
o
u
s
d
ata
-
d
r
iv
en
tech
n
iq
u
es
h
av
e
b
ee
n
cr
ea
ted
o
v
er
tim
e.
A
h
is
to
r
ical
d
ata
s
et
is
all
th
at
is
n
ee
d
ed
f
o
r
d
ata
-
d
r
iv
e
n
d
ete
ctio
n
ap
p
r
o
ac
h
es,
as
o
p
p
o
s
ed
to
m
o
d
el
-
b
ased
d
et
ec
tio
n
tech
n
iq
u
es,
wh
ich
r
e
q
u
ir
e
th
e
p
r
e
v
io
u
s
av
ailab
ili
ty
o
f
an
a
n
aly
tical
m
o
d
el
[
1
1
]
.
Ho
we
v
er
,
r
elia
n
c
e
o
n
lim
ited
h
is
to
r
ical
d
ataset
s
m
ay
lead
to
o
p
tim
is
tic
ac
cu
r
ac
y
esti
m
ates
an
d
r
ed
u
ce
d
r
o
b
u
s
tn
ess
wh
en
m
o
d
els
ar
e
ap
p
lied
to
u
n
s
ee
n
p
o
p
u
latio
n
s
.
T
h
r
o
u
g
h
m
ag
n
etic
r
eso
n
an
ce
im
ag
in
g
(
MRI)
,
th
e
s
tr
u
ctu
r
al
c
h
an
g
es
in
th
e
b
r
ain
ca
u
s
ed
b
y
d
o
p
am
i
n
e
d
ep
letio
n
in
PD p
atien
ts
ca
n
b
e
s
h
o
wn
.
I
n
t
h
e
w
o
r
k
,
a
DL
n
eu
r
a
l
n
e
t
w
o
r
k
h
a
s
b
e
e
n
u
t
i
l
i
z
ed
t
o
t
r
y
an
d
c
a
te
g
o
r
i
z
e
M
R
i
m
ag
e
s
o
f
P
D
p
a
t
i
e
n
t
s
a
n
d
h
e
a
l
th
y
c
o
n
t
r
o
l
s
.
F
o
r
t
h
e
e
ar
l
y
d
i
ag
n
o
s
i
s
o
f
PD
,
n
eu
r
o
i
m
ag
i
n
g
m
e
t
h
o
d
s
i
n
c
l
u
d
in
g
M
R
I
,
P
E
T
,
a
n
d
S
P
E
C
T
ar
e
o
f
t
e
n
u
t
i
l
iz
e
d
.
B
e
c
au
s
e
o
f
t
h
e
s
e
t
e
ch
n
iq
u
e
s
,
p
a
t
h
o
p
h
y
s
i
o
lo
g
ic
a
l
a
l
t
e
r
a
t
io
n
s
i
n
th
e
b
r
a
i
n
c
an
b
e
s
e
en
,
f
a
c
i
l
i
t
a
t
i
n
g
e
a
r
ly
i
n
te
r
v
en
t
i
o
n
a
n
d
im
p
r
o
v
e
d
t
h
e
r
a
p
e
u
t
ic
ap
p
r
o
ac
h
e
s
.
T
h
e
e
a
r
ly
ch
a
r
a
c
t
e
r
i
s
a
t
io
n
a
n
d
m
o
n
i
to
r
in
g
o
f
P
D
u
t
i
l
i
z
in
g
M
R
I
t
e
ch
n
iq
u
e
s
h
a
s
s
h
o
wn
e
n
co
u
r
a
g
in
g
o
u
t
co
m
e
s
in
r
e
c
e
n
t
r
e
s
e
a
r
ch
[
1
2
]
.
D
e
s
p
i
t
e
h
i
g
h
r
ep
o
r
t
ed
a
c
c
u
r
a
c
y
,
n
e
u
r
o
i
m
a
g
in
g
-
b
a
s
ed
m
et
h
o
d
s
f
a
c
e
p
r
a
c
t
i
ca
l
l
i
m
i
t
a
t
io
n
s
r
e
l
a
t
ed
t
o
co
s
t
,
a
c
c
e
s
s
i
b
i
l
i
t
y
,
a
n
d
s
c
a
l
ab
i
l
i
ty
in
r
o
u
t
in
e
c
l
in
i
c
a
l
s
e
t
t
in
g
s
.
A
k
e
y
n
o
n
-
in
v
a
s
iv
e
t
ec
h
n
i
q
u
e
f
o
r
d
i
a
g
n
o
s
in
g
P
D
i
s
s
p
e
e
c
h
s
i
g
n
a
l
a
n
a
l
y
s
i
s
.
C
l
i
n
i
c
a
l
p
r
o
f
e
s
s
i
o
n
a
l
s
a
n
d
n
eu
r
o
s
c
i
en
t
i
s
t
s
a
r
e
a
t
tr
a
c
t
ed
t
o
n
o
n
-
i
n
v
a
s
i
v
e
P
D
p
r
ed
i
c
t
i
o
n
an
d
d
e
t
e
c
t
io
n
te
ch
n
o
lo
g
i
e
s
.
T
h
e
d
i
a
g
n
o
s
i
s
o
f
s
p
e
e
c
h
p
r
o
b
le
m
s
i
n
P
D
p
at
i
e
n
t
s
m
ay
e
n
a
b
l
e
i
d
e
n
t
if
i
c
a
t
i
o
n
an
d
t
r
e
a
t
m
en
t
p
r
i
o
r
to
t
h
e
o
n
s
e
t
o
f
p
h
y
s
i
c
a
l
ly
i
n
c
a
p
ac
i
t
a
t
i
n
g
c
o
m
p
l
a
in
t
s
.
B
o
t
h
t
h
e
h
e
a
l
th
c
ar
e
s
y
s
t
e
m
an
d
th
e
p
a
t
i
en
t
s
'
q
u
al
i
t
y
o
f
l
if
e
m
a
y
b
e
s
e
r
i
o
u
s
l
y
a
f
f
e
c
t
e
d
b
y
th
i
s
.
R
e
s
e
a
r
c
h
s
p
a
n
n
in
g
m
u
l
t
i
p
l
e
d
i
s
c
i
p
l
i
n
e
s
,
p
a
r
t
ic
u
l
ar
l
y
A
I
an
d
m
u
l
t
im
o
d
a
l
s
ig
n
a
l
p
r
o
c
e
s
s
i
n
g
,
i
s
e
s
s
e
n
t
i
a
l
t
o
th
e
ad
v
an
c
e
m
en
t
o
f
m
o
d
er
n
s
p
e
e
c
h
p
r
o
c
e
s
s
i
n
g
t
ec
h
n
o
lo
g
y
[
1
3
]
.
S
ev
e
r
a
l
o
b
s
er
v
a
t
io
n
s
f
r
o
m
t
h
e
an
a
l
y
s
i
s
o
f
P
D
s
p
e
e
ch
s
u
g
g
e
s
t
t
h
a
t
i
n
d
iv
i
d
u
a
l
s
w
i
th
P
D
ex
h
ib
i
t
i
n
cr
e
a
s
ed
m
a
x
im
u
m
p
h
o
n
a
ti
o
n
t
i
m
e,
ji
t
t
e
r
an
d
s
h
i
m
m
e
r
,
p
i
t
c
h
r
a
n
g
e
,
an
d
p
h
o
n
a
t
io
n
th
r
e
s
h
o
ld
p
r
e
s
s
u
r
e
[
1
4
]
.
I
n
s
u
ch
s
t
r
u
c
t
u
r
e
d
f
e
a
t
u
r
e
s
p
a
c
e
s
,
t
r
ad
i
t
i
o
n
a
l
ML
c
l
a
s
s
i
f
i
e
r
s
m
a
y
o
u
t
p
e
r
f
o
r
m
DL
m
o
d
e
l
s
b
e
c
a
u
s
e
h
a
n
d
c
r
a
f
t
ed
f
ea
t
u
r
e
s
a
l
r
ea
d
y
ca
p
tu
r
e
d
i
s
e
a
s
e
-
r
e
l
ev
a
n
t
p
a
t
t
e
r
n
s
ef
f
ec
t
i
v
e
ly
.
D
e
t
e
c
t
i
n
g
P
D
f
r
o
m
s
p
e
e
ch
in
v
o
l
v
e
s
a
t
w
o
-
s
t
e
p
p
r
o
c
e
s
s
.
I
n
it
i
a
l
l
y
,
t
h
e
i
n
p
u
t
s
p
e
ec
h
s
i
g
n
a
l
m
u
s
t
b
e
co
n
v
e
r
t
ed
i
n
t
o
s
p
e
e
ch
f
e
a
t
u
r
e
v
e
c
t
o
r
s
o
r
t
e
n
s
o
r
s
s
u
i
t
ab
l
e
f
o
r
a
n
a
l
y
s
i
s
b
y
DL
m
o
d
e
l
s
.
T
h
e
s
p
ee
ch
ch
ar
ac
ter
is
tics
o
f
PD
p
atien
ts
en
co
m
p
ass
m
u
ltip
le
d
im
en
s
io
n
s
.
,
s
u
ch
as
ar
ticu
latio
n
,
p
h
o
n
atio
n
,
an
d
p
r
o
s
o
d
y
.
Ph
o
n
atio
n
f
ea
tu
r
es
ar
e
ch
ar
ac
ter
i
ze
d
b
y
b
o
win
g
a
n
d
in
ad
eq
u
a
te
clo
s
u
r
e
o
f
v
o
ca
l
f
o
ld
s
an
d
ar
e
r
elate
d
t
o
p
er
tu
r
b
atio
n
m
ea
s
u
r
es su
ch
as jitter
,
s
h
im
m
er
,
am
p
litu
d
e
p
e
r
tu
r
b
at
io
n
q
u
o
tien
t
(
APQ)
,
an
d
p
itch
p
er
tu
r
b
atio
n
q
u
o
tien
t
(
PP
Q)
[
1
5
]
.
T
h
e
E
E
G
m
a
k
es
it
s
im
p
le
to
d
eter
m
in
e
th
e
r
o
les
o
f
th
e
co
r
tical
an
d
s
u
b
c
o
r
tical
r
e
g
io
n
s
o
f
t
h
e
b
r
ai
n
.
Usi
n
g
th
e
E
E
G
s
ig
n
als,
n
eu
r
o
lo
g
ical
co
n
d
itio
n
s
s
u
ch
as
ep
ilep
s
y
,
s
ch
izo
p
h
r
en
ia,
a
n
d
Alzh
eim
er
’
s
ca
n
also
b
e
id
en
tifie
d
.
W
e
u
s
e
E
E
G
f
o
r
PD
d
iag
n
o
s
is
.
Sin
ce
E
E
G
s
ig
n
als
ar
e
in
h
er
en
tly
co
m
p
le
x
an
d
n
o
n
l
in
ea
r
,
n
u
m
er
o
u
s
lin
ea
r
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
ca
n
'
t
a
d
eq
u
ately
d
escr
ib
e
th
em
.
PD
is
s
ee
n
to
wo
r
s
en
wh
en
th
er
e
is
co
m
p
lex
ity
in
th
e
E
E
G
s
ig
n
al.
T
h
is
is
ca
u
s
ed
b
y
th
e
n
o
n
lin
ea
r
elem
en
ts
in
th
e
E
E
G
s
ig
n
als.
T
h
u
s
,
it
ca
n
b
e
co
n
clu
d
ed
th
a
t
th
e
s
ep
ar
atio
n
o
f
n
o
r
m
al
an
d
PD
E
E
G
s
ig
n
als
m
ig
h
t
b
en
ef
it
f
r
o
m
ap
p
licatio
n
o
f
n
o
n
lin
ea
r
f
ea
tu
r
es
ex
tr
a
ctio
n
tech
n
iq
u
es
[
1
6
]
.
Nev
er
t
h
eless
,
E
E
G
-
b
ased
ap
p
r
o
ac
h
es
ar
e
s
en
s
itiv
e
to
n
o
is
e
an
d
in
ter
-
s
u
b
ject
v
ar
ia
b
ilit
y
,
wh
ich
ca
n
af
f
ec
t
co
n
s
is
te
n
cy
ac
r
o
s
s
s
tu
d
ies.
Mo
lecu
lar
im
ag
in
g
m
eth
o
d
s
li
k
e
PET
an
d
SP
E
C
T
ar
e
em
p
lo
y
ed
to
i
n
v
esti
g
ate
a
r
a
n
g
e
o
f
m
ed
ical
co
n
d
itio
n
s
.
A
cy
clo
tr
o
n
is
n
ee
d
e
d
f
o
r
PE
T
,
wh
ich
h
as
p
ar
ticu
lar
tr
ac
e
r
s
an
d
g
r
ea
t
r
eso
lu
tio
n
,
alth
o
u
g
h
SP
E
C
T
is
m
o
r
e
wid
ely
av
ailab
le.
D
o
p
a
m
i
n
e
p
r
o
d
u
c
ti
o
n
a
n
d
n
eu
r
o
n
d
en
s
it
y
ar
e
m
ea
s
u
r
e
d
i
n
o
r
d
e
r
t
o
a
i
d
i
n
t
h
e
d
i
ag
n
o
s
is
o
f
n
e
u
r
o
d
eg
en
e
r
ati
v
e
d
is
ea
s
es,
in
clu
d
i
n
g
PD
.
R
a
d
i
o
t
r
a
ce
r
s
s
p
ec
i
f
ic
to
d
o
p
a
m
i
n
e
t
r
a
n
s
p
o
r
te
r
s
a
n
d
D1
/D
2
r
ec
ep
to
r
s
ar
e
a
m
o
n
g
t
h
e
s
ev
e
r
al
t
h
at
a
r
e
a
v
a
ila
b
l
e
f
o
r
PE
T
/SP
E
C
T
i
m
a
g
i
n
g
.
Ho
we
v
e
r
,
l
ess
e
r
r
es
o
lu
t
io
n
s
till
m
a
k
es
it
d
i
f
f
ic
u
lt
t
o
d
is
ti
n
g
u
is
h
PD
f
r
o
m
o
t
h
e
r
Pa
r
k
i
n
s
o
n
i
a
n
d
is
o
r
d
e
r
s
o
r
h
ea
lt
h
y
p
e
o
p
le
.
I
t
is
b
eli
ev
ed
t
h
a
t
th
e
m
o
s
t
s
en
s
i
ti
v
e
m
et
h
o
d
o
f
d
ia
g
n
o
s
is
co
m
b
i
n
es
p
r
e
-
a
n
d
p
o
s
t
-
s
y
n
a
p
t
ic
im
ag
in
g
wit
h
cl
in
ic
al
o
b
s
e
r
v
ati
o
n
s
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
d
va
n
ce
s
in
P
a
r
kin
s
o
n
’
s
d
is
ea
s
e
d
ia
g
n
o
s
is
a
n
d
tr
ea
tmen
t u
s
in
g
a
r
tifi
cia
l in
tellig
en
ce
:
…
(
Meh
r
A
li Qa
s
imi)
125
3
.
3
.
P
a
rk
ins
o
n’s
dis
ea
s
e
t
re
a
t
m
ent
Dete
ctin
g
PD
at
an
ea
r
ly
s
tag
e
is
cr
u
cial
to
s
lo
win
g
its
p
r
o
g
r
ess
io
n
an
d
en
s
u
r
i
n
g
p
atien
ts
ca
n
ac
ce
s
s
tr
ea
tm
en
ts
th
at
m
o
d
if
y
th
e
d
is
ea
s
e.
T
h
e
p
r
em
o
to
r
s
tag
e
o
f
P
D
s
h
o
u
ld
b
e
clo
s
ely
watc
h
ed
in
o
r
d
er
to
ac
h
iev
e
th
is
.
T
o
d
eter
m
in
e
ea
r
ly
o
n
wh
eth
er
a
p
e
r
s
o
n
h
as
PD
o
r
n
o
t,
a
n
o
v
el
d
ee
p
-
lear
n
in
g
t
ec
h
n
iq
u
e
b
ased
o
n
p
r
em
o
to
r
tr
aits
is
in
tr
o
d
u
ce
d
[
1
8
]
.
PD
f
r
e
q
u
en
tly
lead
s
to
d
ea
th
in
its
later
s
tag
es.
I
t
is
cr
itical
to
cr
ea
te
a
lo
w
-
co
s
t,
ef
f
ec
tiv
e,
an
d
p
r
ec
is
e
ap
p
r
o
ac
h
f
o
r
ea
r
ly
-
s
tag
e
PD
d
iag
n
o
s
is
b
ec
au
s
e
th
e
cu
r
r
en
t d
iag
n
o
s
tic
test
s
ar
e
co
s
tly
an
d
n
o
t
v
er
y
ac
cu
r
ate.
R
esear
ch
er
s
ar
e
lo
o
k
in
g
at
b
i
o
m
ar
k
er
s
t
o
id
e
n
tify
PD
ea
r
ly
,
b
u
t
th
er
e
is
s
till
n
o
clea
r
-
cu
t
m
eth
o
d
f
o
r
d
iag
n
o
s
in
g
th
e
co
n
d
itio
n
.
C
u
r
r
e
n
t
tr
e
atm
en
ts
h
elp
allev
iate
s
y
m
p
to
m
s
,
b
u
t
th
ey
d
o
n
’
t
h
alt
o
r
d
elay
th
e
d
is
ea
s
e’
s
co
u
r
s
e.
T
o
p
o
s
s
ib
ly
s
to
p
t
h
e
ad
v
an
ce
m
en
t
o
f
th
e
d
is
ea
s
e,
it’s
cr
itical
to
r
ec
o
g
n
ize
non
-
m
o
to
r
s
y
m
p
to
m
s
as
s
o
o
n
as
th
ey
ap
p
ea
r
.
Yet,
it
m
ig
h
t
b
e
d
if
f
icu
lt
to
d
iag
n
o
s
e
PD
o
n
ly
o
n
th
e
b
asis
o
f
s
y
m
p
to
m
s
,
as o
th
er
c
o
n
d
itio
n
s
ca
n
h
av
e
s
im
ilar
s
y
m
p
to
m
s
[
1
9
]
.
3
.
4
.
P
re
dict
ing
P
a
rk
ins
o
n’s
dis
ea
s
e
u
s
ing
AI a
nd
M
L
/DL
t
ec
hn
iqu
e
s
ML
an
d
DL
tech
n
iq
u
es
h
av
e
em
er
g
ed
as
p
o
wer
f
u
l
to
o
ls
in
th
e
r
ea
lm
o
f
m
e
d
ical
d
iag
n
o
s
tics
,
p
ar
ticu
lar
ly
f
o
r
p
r
ed
ictin
g
an
d
d
iag
n
o
s
in
g
PD.
T
h
ese
d
ata
-
d
r
iv
en
alg
o
r
ith
m
s
an
aly
ze
ex
t
en
s
iv
e
p
atien
t
d
ata,
in
clu
d
in
g
m
o
t
o
r
s
y
m
p
to
m
s
a
n
d
m
ed
ical
h
is
to
r
y
,
en
a
b
lin
g
ac
cu
r
ate
p
r
ed
ictio
n
s
an
d
cla
s
s
if
icatio
n
s
o
f
th
e
d
is
ea
s
e.
ML
tech
n
iq
u
es
f
a
ll
in
to
f
o
u
r
ca
teg
o
r
ies:
s
u
p
er
v
is
ed
,
s
em
i
-
s
u
p
er
v
is
ed
,
u
n
s
u
p
er
v
is
ed
,
an
d
r
ein
f
o
r
ce
m
e
n
t
lear
n
i
n
g
.
E
ac
h
h
as
s
p
ec
ial
b
en
ef
its
f
o
r
h
a
n
d
l
in
g
an
d
an
aly
zi
n
g
in
t
r
icate
clin
ical
d
ata.
R
ec
en
t
ad
v
an
ce
m
e
n
ts
h
ig
h
lig
h
t
v
ar
io
u
s
ML
tech
n
iq
u
es
th
at
ass
e
s
s
PD
s
ev
er
ity
th
r
o
u
g
h
p
h
y
s
io
l
o
g
ical
s
ig
n
als.
Fo
r
in
s
tan
ce
,
ce
r
tain
s
tu
d
ies
h
av
e
r
ep
o
r
ted
a
ch
iev
in
g
u
p
t
o
9
7
.
5
%
ac
cu
r
ac
y
b
y
im
p
lem
en
tin
g
n
eu
r
al
n
etwo
r
k
s
o
n
s
p
ee
ch
d
ata,
wh
ic
h
is
a
p
r
o
m
i
s
in
g
in
d
icato
r
o
f
t
h
e
p
o
ten
tial
f
o
r
ac
c
u
r
ate
ea
r
ly
d
iag
n
o
s
is
.
Su
ch
h
i
g
h
ac
c
u
r
ac
y
v
alu
es
m
ay
b
e
in
f
lu
e
n
ce
d
b
y
o
p
tim
ized
f
ea
tu
r
e
s
elec
tio
n
o
r
lim
ited
d
atasets
an
d
s
h
o
u
ld
t
h
er
ef
o
r
e
b
e
in
ter
p
r
eted
with
ca
u
tio
n
r
e
g
a
r
d
in
g
g
e
n
er
aliza
b
ilit
y
.
Ad
d
iti
o
n
ally
,
tech
n
iq
u
es
s
u
ch
as
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
h
av
e
r
ef
in
ed
f
ea
tu
r
e
s
ets
f
o
r
b
etter
ef
f
icie
n
c
y
,
wh
ile
SVM
h
av
e
s
u
cc
ess
f
u
lly
d
if
f
e
r
en
tiated
PD
p
atien
ts
f
r
o
m
h
ea
lth
y
i
n
d
iv
id
u
als.
E
n
s
em
b
le
lear
n
in
g
m
eth
o
d
s
,
in
clu
d
in
g
s
tack
in
g
class
if
i
er
s
,
f
u
r
th
er
e
n
h
an
ce
p
r
ed
ictiv
e
ac
cu
r
ac
y
,
u
n
d
e
r
s
co
r
in
g
th
e
ef
f
ec
tiv
en
ess
o
f
AI
-
d
r
i
v
en
ap
p
r
o
ac
h
es in
d
iag
n
o
s
in
g
PD
[
2
0
]
.
AI
m
eth
o
d
o
lo
g
ies
ar
e
n
o
t
lim
ited
to
ju
s
t
o
n
e
ty
p
e
o
f
d
a
ta;
th
ey
s
p
an
d
iv
er
s
e
s
o
u
r
ce
s
in
clu
d
in
g
s
p
ee
ch
r
ec
o
r
d
in
g
s
,
h
an
d
wr
itin
g
s
am
p
les,
g
ait
p
atter
n
s
,
an
d
MRI
s
ca
n
s
.
No
n
-
in
v
asiv
e
s
p
e
ec
h
p
r
o
ce
s
s
in
g
h
as
g
ain
ed
tr
ac
tio
n
d
u
e
to
its
ab
ilit
y
to
d
etec
t
ea
r
ly
v
o
ca
l
b
io
m
a
r
k
er
s
o
f
PD.
Acc
u
r
ac
y
r
ates
in
th
ese
ap
p
licatio
n
s
ar
e
r
em
ar
k
ab
le,
with
ce
r
tain
m
o
d
els
ac
h
iev
in
g
as
h
ig
h
as
9
9
.
4
9
%
u
s
in
g
a
s
et
o
f
k
ey
s
p
ee
ch
attr
ib
u
tes,
wh
ile
o
th
er
s
h
av
e
r
ea
ch
ed
9
8
%
ac
cu
r
ac
y
b
y
lev
er
a
g
in
g
m
u
ltiv
a
r
iate
v
o
ca
l
d
ata.
Nea
r
-
p
er
f
ec
t
p
er
f
o
r
m
an
ce
m
ay
r
ef
lect
s
u
b
ject
-
d
e
p
en
d
e
n
t
ev
al
u
atio
n
s
o
r
ex
ten
s
iv
e
tu
n
in
g
r
at
h
er
th
a
n
tr
u
e
clin
ical
r
o
b
u
s
tn
ess
,
em
p
h
asizin
g
th
e
n
ee
d
f
o
r
cr
itical
co
m
p
a
r
is
o
n
a
cr
o
s
s
s
tu
d
ies.
Han
d
wr
itin
g
an
aly
s
is
,
em
p
lo
y
in
g
DL
ar
ch
itectu
r
es
lik
e
C
NN
an
d
C
NN
-
B
L
STM
,
h
as
also
s
h
o
w
n
s
ig
n
if
ican
t
p
r
o
m
is
e.
I
n
ad
d
itio
n
,
s
E
MG
s
ig
n
als
p
r
o
ce
s
s
ed
th
r
o
u
g
h
lig
h
tweig
h
t
co
n
v
o
l
u
tio
n
al
n
etwo
r
k
s
,
s
u
ch
as
S
-
Net,
h
av
e
b
ee
n
u
tili
ze
d
t
o
ev
alu
ate
tr
e
m
o
r
s
ev
er
ity
ef
f
ec
tiv
ely
[
2
1
]
.
Gait
d
y
n
am
ics
s
er
v
e
as
an
o
th
er
cr
it
ical
m
o
d
ality
,
with
m
o
d
els
th
at
an
aly
ze
s
p
atial
-
tem
p
o
r
al
f
e
atu
r
es
ca
teg
o
r
izin
g
PD
p
atien
ts
an
d
as
s
es
s
in
g
th
eir
co
n
d
itio
n
s
ev
er
ity
.
T
ec
h
n
iq
u
es
lik
e
R
e
s
Net,
V
GG1
9
,
an
d
I
n
ce
p
tio
n
V3
,
wh
e
n
u
tili
ze
d
th
r
o
u
g
h
tr
an
s
f
er
lea
r
n
in
g
,
h
av
e
r
ed
u
ce
d
tr
ain
i
n
g
tim
es
wh
ile
m
ain
tain
in
g
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
[
2
2
]
.
Fu
r
th
er
m
o
r
e,
ML
m
eth
o
d
s
lik
e
SVM
an
d
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P)
h
av
e
p
r
o
v
e
n
p
ar
ticu
lar
ly
ef
f
ec
tiv
e
in
class
if
y
in
g
PD
b
ased
o
n
n
o
n
-
m
o
t
o
r
s
y
m
p
to
m
s
,
s
h
o
wca
s
in
g
th
e
v
ast
p
o
ten
tial
o
f
ad
v
an
ce
d
AI
an
d
ML
tech
n
iq
u
es in
tr
an
s
f
o
r
m
in
g
th
e
d
ia
g
n
o
s
tic
lan
d
s
ca
p
e
f
o
r
PD
[
2
3
]
.
Desp
ite
th
e
p
r
o
m
is
in
g
ac
cu
r
ac
y
r
ep
o
r
te
d
ac
r
o
s
s
n
u
m
er
o
u
s
s
tu
d
ies,
m
o
s
t
ex
is
tin
g
AI
-
b
ased
ap
p
r
o
ac
h
es
f
o
r
PD
d
iag
n
o
s
is
ar
e
ev
alu
ated
i
n
co
n
t
r
o
lled
ex
p
er
im
en
tal
en
v
ir
o
n
m
en
ts
.
C
lin
ical
v
alid
atio
n
in
v
o
lv
in
g
n
eu
r
o
lo
g
is
ts
,
m
u
lti
-
ce
n
ter
co
h
o
r
ts
,
an
d
r
ea
l
-
wo
r
ld
d
ep
lo
y
m
en
t
s
ce
n
ar
io
s
r
em
ain
s
lim
ited
.
Fu
r
th
er
m
o
r
e
,
m
an
y
h
ig
h
-
p
e
r
f
o
r
m
in
g
DL
m
o
d
els
o
p
er
ate
as
b
lack
-
b
o
x
s
y
s
tem
s
,
o
f
f
er
in
g
lim
ited
in
ter
p
r
etab
ilit
y
,
wh
ich
p
o
s
es
ch
allen
g
es
f
o
r
clin
ical
tr
u
s
t
an
d
ad
o
p
tio
n
.
T
h
ese
f
ac
to
r
s
h
ig
h
l
ig
h
t
a
g
ap
b
etwe
en
ex
p
er
im
en
tal
p
er
f
o
r
m
an
ce
an
d
p
r
ac
tical
clin
ical
ap
p
licab
ilit
y
.
Ov
er
all,
th
e
s
y
n
th
esis
o
f
th
e
r
ev
iewe
d
liter
atu
r
e
d
em
o
n
s
tr
ates
th
at
s
p
ee
ch
a
n
a
ly
s
is
,
g
ait
ass
es
s
m
en
t,
an
d
n
eu
r
o
im
ag
in
g
—
p
ar
ticu
lar
ly
M
R
I
—
em
er
g
e
as
th
e
m
o
s
t
p
r
o
m
is
in
g
m
o
d
alities
f
o
r
PD
d
ia
g
n
o
s
is
.
T
h
is
s
y
s
te
m
atic
co
n
s
o
lid
atio
n
o
f
r
esu
lt
s
en
ab
les
a
clea
r
e
r
co
m
p
ar
is
o
n
o
f
AI
tech
n
iq
u
es
an
d
p
e
r
f
o
r
m
an
ce
tr
en
d
s
,
p
r
o
v
i
d
in
g
a
s
tr
u
ctu
r
ed
r
ef
e
r
en
ce
f
o
r
r
esear
ch
er
s
w
h
ile
em
p
h
asizin
g
th
e
in
cr
em
en
tal
y
et
v
alu
ab
le
co
n
tr
ib
u
tio
n
o
f
co
m
p
r
eh
e
n
s
iv
e
s
y
n
th
esis
o
v
er
is
o
lated
s
tu
d
y
r
ep
o
r
tin
g
.
3
.
5
.
Cha
lleng
es a
nd
o
pen r
esea
rc
h is
s
ues
Alth
o
u
g
h
s
ig
n
if
ican
t
p
r
o
g
r
ess
h
as
b
ee
n
ac
h
iev
ed
,
s
ev
er
al
c
h
allen
g
es
r
em
ain
u
n
r
eso
lv
ed
in
cu
r
r
en
t
PD
r
esear
ch
.
Ma
n
y
s
tu
d
ies
r
e
ly
o
n
s
m
all
a
n
d
im
b
alan
ce
d
d
atasets
,
wh
ich
ca
n
b
ias
m
o
d
e
l
p
er
f
o
r
m
an
ce
a
n
d
lim
it
g
en
er
aliza
b
ilit
y
.
I
n
ad
d
it
io
n
,
r
e
p
r
o
d
u
cib
ilit
y
is
o
f
ten
h
in
d
er
ed
b
y
in
co
n
s
is
ten
t
ev
alu
atio
n
p
r
o
to
co
ls
a
n
d
th
e
ab
s
en
ce
o
f
s
tan
d
ar
d
ized
b
en
ch
m
ar
k
s
.
L
o
n
g
itu
d
in
al
s
tu
d
ies
th
at
tr
ac
k
d
is
ea
s
e
p
r
o
g
r
es
s
io
n
o
v
er
tim
e
a
r
e
also
s
ca
r
ce
,
r
estrictin
g
th
e
a
b
ilit
y
o
f
e
x
is
tin
g
m
o
d
els
to
s
u
p
p
o
r
t
lo
n
g
-
ter
m
m
o
n
ito
r
in
g
an
d
p
r
o
g
n
o
s
is
.
Ad
d
r
ess
in
g
th
ese
ch
allen
g
es is
ess
en
tial f
o
r
ad
v
an
ci
n
g
clin
ic
ally
r
eliab
le
an
d
d
ep
lo
y
ab
le
A
I
-
b
ased
s
o
lu
tio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
1
,
M
ar
ch
20
26
:
1
21
-
1
30
126
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
r
esear
ch
o
b
tain
ed
f
r
o
m
t
h
e
ar
ticle
s
ea
r
ch
r
esu
lts
is
a
s
f
o
llo
ws:
t
h
e
s
tu
d
y
s
u
g
g
ests
a
h
y
b
r
id
DL
s
tr
ateg
y
th
at
co
m
b
in
es
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
ANN)
with
r
eg
r
ess
io
n
an
al
y
s
is
(
R
A)
.
W
h
ile
ANN
is
u
s
ed
to
id
en
tify
PD
p
atien
ts
b
y
co
m
p
ar
in
g
o
u
tco
m
es
with
a
th
r
esh
o
ld
v
al
u
e,
R
A
is
u
tili
ze
d
f
o
r
d
ata
p
r
e
p
ar
atio
n
an
d
p
r
o
b
a
b
ilit
y
ca
lcu
latio
n
.
T
h
e
m
o
d
el
p
er
f
o
r
m
e
d
b
etter
th
a
n
co
n
v
en
tio
n
al
class
if
ier
s
lik
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
an
d
k
-
n
ea
r
est
n
eig
h
b
o
r
(k
-
NN)
,
with
9
3
.
4
6
%
ac
cu
r
a
cy
wh
en
ev
alu
ated
o
n
a
d
ataset
in
clu
d
in
g
s
p
ee
c
h
r
ec
o
g
n
itio
n
,
ir
o
n
co
n
te
n
t,
an
d
p
u
ls
e
r
ate.
T
h
e
s
tu
d
y
f
o
u
n
d
th
at
ch
ar
ac
ter
is
tics
s
u
ch
as ir
o
n
ac
cu
m
u
latio
n
in
th
e
s
p
in
al
co
r
d
an
d
r
ed
u
ce
d
p
itch
p
er
io
d
en
tr
o
p
y
(
PP
E
)
illu
s
tr
a
te
th
e
h
y
b
r
id
m
eth
o
d
'
s
ef
f
ec
tiv
en
ess
f
o
r
ea
r
ly
PD
d
etec
tio
n
[
2
4
]
.
T
h
e
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
o
f
th
is
ap
p
r
o
ac
h
ap
p
ea
r
s
to
ar
is
e
f
r
o
m
t
h
e
co
m
p
lem
en
ta
r
y
s
tr
en
g
th
s
o
f
ANN
in
ca
p
tu
r
in
g
n
o
n
lin
ea
r
p
atter
n
s
an
d
R
A
in
s
tr
u
ctu
r
in
g
p
r
o
b
ab
ilis
tic
r
elatio
n
s
h
ip
s
,
alth
o
u
g
h
s
u
ch
h
y
b
r
id
f
r
a
m
ewo
r
k
s
m
a
y
r
em
ain
s
en
s
itiv
e
to
f
ea
tu
r
e
s
ele
ctio
n
an
d
d
ataset
co
n
s
is
ten
cy
.
T
h
e
s
tu
d
y
u
s
es
v
o
ice
f
ea
tu
r
es
to
e
v
alu
ate
DL
an
d
ML
m
o
d
els
f
o
r
th
e
ea
r
ly
id
e
n
tific
atio
n
o
f
PD
.
I
t
em
p
lo
y
s
a
d
ataset
f
r
o
m
th
e
U
C
I
r
ep
o
s
ito
r
y
c
o
n
tain
in
g
5
8
7
6
×2
2
en
tr
ies,
c
o
m
p
r
is
in
g
r
ec
o
r
d
in
g
s
f
r
o
m
Hea
lth
y
p
eo
p
le
an
d
th
o
s
e
with
PD.
T
h
e
wo
r
k
co
m
p
ar
es
s
ix
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
s
,
two
DL
ar
ch
itectu
r
es
(
C
NN,
R
NN)
,
an
d
an
en
s
em
b
le
m
eth
o
d
(
XGBo
o
s
t)
.
Am
o
n
g
all
th
e
m
eth
o
d
s
test
ed
,
th
e
KNN
alg
o
r
ith
m
with
k
=5
ac
h
ie
v
ed
th
e
h
ig
h
est
ac
c
u
r
ac
y
o
f
9
7
.
4
3
%,
o
u
tp
e
r
f
o
r
m
in
g
b
o
th
en
s
em
b
le
(
XGBo
o
s
t
at
9
4
.
8
7
%)
an
d
DL
ap
p
r
o
ac
h
es
(
R
NN
at
9
6
.
6
5
%,
C
NN
at
8
4
.
6
1
%).
E
v
er
y
m
o
d
el
was
as
s
es
s
ed
u
tili
zin
g
m
e
tr
ics
s
u
ch
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
s
p
ec
if
icity
,
an
d
s
en
s
itiv
ity
th
r
o
u
g
h
th
r
ee
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
.
T
h
e
f
i
n
d
in
g
s
s
h
o
w
th
at
s
im
p
le
y
et
ef
f
ec
tiv
e
ML
m
o
d
els
lik
e
KNN,
wh
en
p
r
o
p
e
r
ly
tu
n
ed
,
ca
n
o
u
tp
e
r
f
o
r
m
co
m
p
lex
DL
m
o
d
els
f
o
r
s
tr
u
ctu
r
ed
tab
u
lar
d
atasets
in
t
h
e
co
n
tex
t o
f
PD d
iag
n
o
s
is
[
2
5
]
.
T
h
is
r
esu
lt in
d
icate
s
th
at
DL
ar
ch
itectu
r
es m
ay
b
e
d
is
ad
v
a
n
tag
ed
w
h
en
d
ataset
s
ize
an
d
f
ea
t
u
r
e
s
tr
u
ct
u
r
e
ar
e
in
s
u
f
f
icien
t
to
f
u
ll
y
ex
p
lo
it
th
eir
r
ep
r
esen
tatio
n
al
ca
p
ac
ity
,
wh
er
ea
s
s
im
p
ler
m
o
d
els b
en
ef
it f
r
o
m
well
-
d
ef
in
e
d
f
ea
tu
r
e
s
p
ac
es.
T
h
e
wo
r
k
o
f
f
er
s
a
th
o
r
o
u
g
h
a
n
aly
s
is
o
f
AI
m
et
h
o
d
s
t
h
at
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
b
etwe
en
2
0
1
6
an
d
2
0
2
2
f
o
r
th
e
s
cr
ee
n
in
g
,
s
tag
in
g
,
an
d
b
io
m
a
r
k
er
id
en
tific
atio
n
o
f
PD
u
s
in
g
d
ata
f
r
o
m
s
p
ee
ch
test
s
,
h
an
d
wr
itin
g
ex
am
in
atio
n
s
,
E
E
G,
MRI,
an
d
s
en
s
o
r
y
d
ata
[
2
6
]
.
Desp
ite
p
r
o
m
is
in
g
r
esu
lts
ac
r
o
s
s
m
o
d
alities
,
d
if
f
er
en
ce
s
in
d
ata
ac
q
u
is
itio
n
p
r
o
to
c
o
ls
,
co
h
o
r
t
s
ize,
an
d
p
o
p
u
latio
n
ch
a
r
ac
ter
is
tics
co
n
tr
ib
u
te
to
v
ar
iab
ilit
y
in
r
ep
o
r
te
d
p
er
f
o
r
m
an
ce
an
d
lim
it
cr
o
s
s
-
s
tu
d
y
co
m
p
a
r
ab
ilit
y
.
T
h
e
r
esea
r
ch
aim
s
to
en
h
an
ce
th
e
ea
r
ly
d
etec
tio
n
o
f
PD
by
em
p
lo
y
in
g
DL
m
o
d
els
r
ef
in
e
d
th
r
o
u
g
h
Gr
e
y
W
o
lf
Op
tim
i
za
tio
n
(
GW
O)
.
I
t
p
r
esen
ts
f
o
u
r
DL
f
r
am
ew
o
r
k
s
o
p
tim
ized
with
GW
O
—
G
W
O
-
VGG1
6
,
GW
O
-
Den
s
eNe
t,
GW
O
-
Den
s
eNe
t
+
L
STM
,
G
W
O
-
I
n
ce
p
tio
n
V3
—
an
d
a
co
m
b
in
e
d
m
o
d
el,
GW
O
-
VGG1
6
+
I
n
ce
p
tio
n
V
3
.
T
h
es
e
m
o
d
els
ar
e
u
tili
ze
d
o
n
T
1
,
T
2
-
weig
h
ted
MRI,
an
d
SP
E
C
T
DaT
s
ca
n
d
atasets
.
C
o
m
p
r
eh
en
s
iv
e
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
,
s
u
ch
as
s
k
u
ll
s
tr
ip
p
in
g
,
n
o
r
m
aliza
tio
n
,
an
d
th
e
elim
in
atio
n
o
f
em
p
ty
tu
p
les,
ar
e
im
p
lem
e
n
ted
to
en
s
u
r
e
s
u
p
er
i
o
r
d
at
a
q
u
ality
.
T
h
e
h
y
b
r
id
m
o
d
el
GW
O
-
VGG1
6
+
I
n
ce
p
tio
n
V3
d
em
o
n
s
tr
ated
th
e
h
ig
h
est
p
er
f
o
r
m
a
n
ce
,
ac
h
ie
v
in
g
9
9
.
9
4
%
ac
c
u
r
ac
y
a
n
d
9
9
.
9
9
%
AUC
o
n
th
e
T
1
,
T2
-
weig
h
ted
d
ataset,
an
d
1
0
0
%
ac
cu
r
ac
y
with
9
9
.
9
2
%
AUC
o
n
th
e
SP
E
C
T
DaT
s
ca
n
d
ataset.
All
m
o
d
els
s
ig
n
if
ican
tly
s
u
r
p
ass
p
r
ev
io
u
s
m
eth
o
d
s
,
in
clu
d
in
g
tr
ad
itio
n
al
C
NN
s
an
d
en
s
em
b
le
m
o
d
els,
co
n
f
ir
m
in
g
th
e
p
r
o
m
is
e
o
f
m
etah
e
u
r
is
tically
tu
n
ed
h
y
b
r
id
DL
ar
c
h
itectu
r
es
f
o
r
r
eliab
le
PD
d
iag
n
o
s
is
[
2
7
]
.
W
h
ile
th
ese
r
esu
lts
h
ig
h
lig
h
t
s
tr
o
n
g
p
o
te
n
tial,
th
e
ex
ce
p
tio
n
ally
h
ig
h
ac
cu
r
ac
y
is
lik
ely
i
n
f
lu
en
c
ed
b
y
c
o
n
tr
o
lled
ex
p
er
im
en
tal
c
o
n
d
itio
n
s
an
d
c
u
r
ated
d
atasets
,
wh
ich
m
ay
n
o
t
f
u
lly
r
e
f
lect
r
ea
l
-
wo
r
l
d
clin
i
ca
l
v
ar
iab
ilit
y
.
T
h
e
wo
r
k
e
x
p
lo
r
es
s
y
s
tem
-
b
ased
v
o
ice
f
ea
tu
r
es
f
o
r
d
etec
tin
g
PD
u
s
in
g
ML
alg
o
r
ith
m
s
.
I
t
an
al
y
ze
s
v
o
ice
r
ec
o
r
d
in
g
s
co
n
tain
in
g
2
3
ac
o
u
s
tic
f
ea
tu
r
es
f
r
o
m
in
d
iv
id
u
al
s
with
PD
an
d
h
ea
lth
y
co
n
tr
o
ls
.
Fiv
e
s
u
p
er
v
is
ed
ML
m
o
d
els
—
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
k
-
NN,
SVM,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
A
d
aBo
o
s
t
—
ar
e
ev
alu
ated
f
o
r
th
eir
d
iag
n
o
s
tic
p
er
f
o
r
m
a
n
ce
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
SVM
an
d
R
F
ac
h
iev
ed
th
e
h
ig
h
est
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
5
%,
f
o
llo
we
d
b
y
Ad
aBo
o
s
t
(
9
3
%),
k
-
NN
(
9
2
%),
an
d
L
R
(
8
6
%).
T
h
e
s
tu
d
y
em
p
h
asizes
th
ese
m
o
d
els'
ef
f
icac
y
,
p
ar
ticu
lar
ly
SVM
an
d
R
F,
in
d
is
t
in
g
u
is
h
in
g
PD
f
r
o
m
h
ea
lth
y
co
n
t
r
o
ls
b
ased
o
n
v
o
ca
l
b
io
m
ar
k
e
r
s
,
em
p
h
asizin
g
th
ei
r
p
o
ten
tial
f
o
r
ea
r
ly
an
d
n
o
n
-
in
v
asiv
e
d
iag
n
o
s
is
o
f
PD.
T
h
e
ass
es
s
m
en
t
was
ca
r
r
ied
o
u
t
u
s
in
g
s
tan
d
ar
d
p
er
f
o
r
m
an
ce
m
etr
ics
(
ac
cu
r
a
cy
,
p
r
ec
is
io
n
,
r
e
ca
ll,
F1
-
s
co
r
e)
an
d
c
o
n
f
u
s
io
n
m
atr
ices
[
2
8
]
.
T
h
e
s
tr
o
n
g
p
er
f
o
r
m
an
ce
o
f
SVM
an
d
R
F
ca
n
b
e
attr
ib
u
ted
to
th
ei
r
r
o
b
u
s
tn
ess
ag
ain
s
t
n
o
is
e
an
d
f
ea
tu
r
e
r
ed
u
n
d
a
n
cy
c
o
m
m
o
n
ly
p
r
esen
t in
s
p
ee
ch
-
d
er
iv
e
d
d
at
asets
.
T
h
e
wo
r
k
f
o
cu
s
es o
n
im
p
r
o
v
i
n
g
PD
d
iag
n
o
s
is
u
s
in
g
m
u
ltip
o
o
l c
h
em
ical
ex
ch
an
g
e
s
atu
r
at
io
n
tr
an
s
f
er
(
C
E
ST)
MRI
co
m
b
in
ed
with
DL
tech
n
iq
u
es.
A
m
o
d
if
ied
1
D
U
-
Net
m
o
d
el,
ca
lled
Z
-
s
p
ec
tr
al
co
m
p
r
ess
ed
s
en
s
in
g
(
C
S),
was
p
r
o
p
o
s
ed
to
r
ec
o
n
s
tr
u
ct
d
e
n
s
e
Z
-
s
p
ec
tr
a
f
r
o
m
s
p
ar
s
ely
s
am
p
led
d
ata,
s
ig
n
if
ican
tly
r
e
d
u
cin
g
MRI
s
ca
n
tim
e.
T
h
e
DL
m
o
d
el
d
em
o
n
s
tr
ated
s
u
p
er
io
r
r
ec
o
n
s
tr
u
ctio
n
f
id
elity
co
m
p
ar
ed
to
tr
ad
itio
n
al
in
ter
p
o
latio
n
m
eth
o
d
s
.
I
n
class
if
icatio
n
task
s
,
th
e
co
m
b
in
ed
C
E
ST
co
n
tr
ast
ac
h
iev
e
d
t
h
e
b
est
d
iag
n
o
s
tic
p
er
f
o
r
m
an
ce
(
AUC
=0
.
8
4
)
,
o
u
tp
er
f
o
r
m
in
g
in
d
iv
id
u
al
co
n
tr
asts
s
u
ch
as
APT
(
AUC
=0
.
7
3
)
.
T
h
e
s
tu
d
y
co
n
clu
d
es
th
at
DL
–
b
ased
Z
-
s
p
ec
tr
al
C
S
ca
n
ac
ce
ler
ate
C
E
ST
MRI
b
y
u
p
to
6
7
%
with
o
u
t
s
ig
n
if
ican
tl
y
co
m
p
r
o
m
is
in
g
ac
cu
r
ac
y
,
s
h
o
win
g
s
tr
o
n
g
p
o
te
n
tial
f
o
r
ef
f
i
cien
t,
n
o
n
-
in
v
asiv
e
PD
d
iag
n
o
s
is
[
2
9
]
.
H
o
wev
er
,
th
e
co
s
t
o
f
ad
v
an
ce
d
im
ag
in
g
eq
u
ip
m
e
n
t
an
d
th
e
c
o
m
p
u
tatio
n
al
r
eq
u
ir
em
e
n
ts
o
f
DL
-
b
ased
r
ec
o
n
s
tr
u
ctio
n
m
ay
lim
it wid
esp
r
ea
d
clin
ical
ad
o
p
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
d
va
n
ce
s
in
P
a
r
kin
s
o
n
’
s
d
is
ea
s
e
d
ia
g
n
o
s
is
a
n
d
tr
ea
tmen
t u
s
in
g
a
r
tifi
cia
l in
tellig
en
ce
:
…
(
Meh
r
A
li Qa
s
imi)
127
T
h
e
p
a
p
er
o
f
f
er
s
p
r
ed
ictin
g
PD
th
r
o
u
g
h
s
p
ee
c
h
d
is
o
r
d
er
s
u
s
in
g
ML
an
d
en
s
em
b
le
tec
h
n
iq
u
es.
I
t
ev
alu
ates
2
0
class
if
ier
s
,
in
clu
d
in
g
KNN,
XGBo
o
s
t
(
XGB
C
)
,
an
d
ML
P,
ac
r
o
s
s
two
d
if
f
er
e
n
t
ac
o
u
s
tic
d
atasets
.
T
h
e
s
tu
d
y
em
p
h
asizes
th
e
im
p
ac
t
o
f
h
y
p
er
p
ar
am
eter
tu
n
i
n
g
an
d
r
o
b
u
s
t
ev
alu
atio
n
s
tr
ateg
ies
s
u
ch
as
s
tr
atif
ied
k
-
f
o
ld
an
d
leav
e
-
one
-
o
u
t
cr
o
s
s
-
v
alid
atio
n
(
L
OOCV),
esp
ec
i
ally
g
iv
en
th
e
s
m
all
an
d
u
n
b
al
an
ce
d
n
atu
r
e
o
f
th
e
d
atasets
.
T
o
en
h
an
ce
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
e
n
s
em
b
le
v
o
tin
g
class
if
ier
s
wer
e
p
r
o
p
o
s
ed
.
T
h
e
f
ir
s
t
en
s
em
b
le
co
m
b
in
es
KNN
an
d
ML
P
o
n
d
ataset
I
(
1
9
5
s
am
p
les)
an
d
ac
h
iev
e
d
an
ac
cu
r
ac
y
o
f
9
6
.
4
1
%.
T
h
e
s
ec
o
n
d
co
m
b
in
es
KNN
an
d
X
GB
C
o
n
d
ataset
I
I
(
7
5
6
s
am
p
l
es),
ac
h
iev
in
g
an
ac
cu
r
ac
y
o
f
9
7
.
3
5
%.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
en
s
em
b
le
m
o
d
els
s
ig
n
if
ican
tly
o
u
tp
e
r
f
o
r
m
in
d
iv
id
u
al
class
if
ier
s
,
h
ig
h
l
ig
h
tin
g
th
e
p
o
ten
tial
o
f
AI
-
b
ased
v
o
tin
g
s
tr
ateg
ies
f
o
r
ac
c
u
r
ate
a
n
d
ea
r
ly
d
etec
tio
n
o
f
PD
u
s
in
g
v
o
c
al
b
io
m
ar
k
er
s
[
3
0
]
.
Nev
er
th
eless
,
en
s
em
b
le
ap
p
r
o
ac
h
es
o
f
te
n
r
ed
u
ce
m
o
d
el
in
ter
p
r
etab
ilit
y
,
wh
ic
h
r
em
ain
s
a
cr
itical
co
n
s
id
er
atio
n
f
o
r
clin
ical
d
ec
i
s
io
n
-
m
ak
in
g
.
T
h
e
wo
r
k
p
r
esen
ts
a
co
m
p
r
e
h
en
s
iv
e
s
tu
d
y
em
p
lo
y
in
g
ML
an
d
DL
tech
n
iq
u
es
to
d
etec
t
PD
u
s
in
g
v
o
ice
s
ig
n
al
f
e
atu
r
es.
I
t
u
tili
ze
s
d
ata
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
in
clu
d
in
g
SMOT
E
to
ad
d
r
e
s
s
class
im
b
alan
ce
,
SelectKBe
s
t
f
o
r
f
ea
tu
r
e
s
elec
tio
n
,
an
d
R
an
d
o
m
ized
Sear
ch
C
V
f
o
r
h
y
p
er
p
a
r
am
eter
tu
n
i
n
g
.
Var
io
u
s
class
if
ier
s
s
u
ch
as
Ker
n
el
SVM
(
KSVM)
,
RF
,
d
ec
is
io
n
tr
ee
(
DT
)
,
k
-
NN
,
an
d
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
e
two
r
k
(
FNN)
wer
e
ev
alu
ated
.
Am
o
n
g
th
em
,
th
e
F
NN
m
o
d
el
ac
h
iev
ed
th
e
h
ig
h
e
s
t
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
9
.
1
1
%,
f
o
llo
wed
b
y
KSVM
with
9
5
.
8
9
%.
T
h
e
s
tu
d
y
em
p
h
asizes
th
e
e
f
f
ec
tiv
en
e
s
s
o
f
DL
m
o
d
els,
p
a
r
ticu
lar
ly
FNN,
in
ca
p
tu
r
i
n
g
s
u
b
tle
v
o
ca
l
im
p
air
m
en
ts
ass
o
ciate
d
with
PD.
I
t
f
u
r
th
er
h
ig
h
lig
h
ts
th
e
v
iab
ilit
y
o
f
v
o
ice
-
b
ased
,
n
o
n
-
in
v
asiv
e
d
iag
n
o
s
tic
s
y
s
tem
s
as
a
p
r
o
m
is
in
g
alter
n
ativ
e
to
co
n
v
en
t
io
n
al
clin
ical
m
eth
o
d
s
,
o
f
f
er
i
n
g
f
aster
an
d
m
o
r
e
ac
ce
s
s
ib
le
ea
r
ly
d
etec
tio
n
o
f
P
D
[
3
1
]
.
Desp
ite
th
eir
h
ig
h
ac
c
u
r
ac
y
,
DL
m
o
d
els o
f
ten
lac
k
tr
an
s
p
ar
en
cy
,
p
o
s
in
g
ch
allen
g
es f
o
r
r
eg
u
lato
r
y
ap
p
r
o
v
al
an
d
clin
ical
tr
u
s
t.
T
h
is
th
o
r
o
u
g
h
s
y
s
tem
atic
r
ev
i
ew’
s
o
b
jectiv
e
is
to
c
o
m
p
ile
th
e
b
o
d
y
o
f
r
esear
c
h
o
n
th
e
u
s
e
o
f
AI
,
ML
,
an
d
DL
in
th
e
d
ia
g
n
o
s
is
an
d
tr
ea
tm
e
n
t
o
f
PD.
W
e
d
escr
ib
e
th
e
is
s
u
es,
id
e
n
tify
p
o
s
s
ib
le
r
esear
ch
d
ir
ec
tio
n
s
f
o
r
th
ese
tech
n
o
lo
g
i
es,
th
e
r
esu
lts
o
f
AI
m
o
d
els,
an
d
th
e
ch
allen
g
es
f
ac
e
d
d
u
r
i
n
g
th
eir
d
ep
lo
y
m
en
t.
Ov
er
all,
wh
ile
m
an
y
m
o
d
els
ac
h
iev
e
h
ig
h
d
iag
n
o
s
tic
p
er
f
o
r
m
an
ce
u
n
d
er
ex
p
er
im
en
tal
co
n
d
itio
n
s
,
is
s
u
es
r
elate
d
to
d
ataset
h
eter
o
g
en
eit
y
,
in
ter
p
r
etab
ilit
y
,
co
s
t,
an
d
r
eg
u
lato
r
y
v
alid
atio
n
r
em
ain
k
ey
b
ar
r
ie
r
s
to
r
ea
l
-
wo
r
ld
clin
ical
im
p
lem
en
tatio
n
.
A
co
m
p
ar
ativ
e
s
u
m
m
ar
y
o
f
AI
an
d
ML
/DL
-
b
ased
PD
p
r
ed
ictio
n
s
tu
d
ies
is
p
r
o
v
id
ed
i
n
T
ab
le
1
.
Stu
d
ies
f
o
cu
s
in
g
o
n
d
if
f
e
r
en
t
ty
p
es
an
d
s
u
b
t
y
p
es
o
f
PD
a
r
e
s
u
m
m
ar
ized
in
T
ab
le
2
.
R
esear
ch
ad
d
r
ess
in
g
d
iag
n
o
s
is
-
an
d
tr
ea
tm
en
t
-
o
r
ie
n
ted
AI
ap
p
r
o
ac
h
es
f
o
r
PD
is
p
r
esen
ted
in
T
ab
le
3
.
Gen
er
al
PD
r
esear
ch
em
p
lo
y
in
g
AI
tech
n
i
q
u
es is
s
u
m
m
ar
ized
in
T
a
b
le
4
.
T
ab
le
1
.
AI
a
n
d
ML
/DL
tech
n
iq
u
es f
o
r
Par
k
i
n
s
o
n
’
s
di
s
ea
s
e
p
r
ed
ictio
n
p
ap
er
s
A
u
t
h
o
r
C
a
t
e
g
o
r
i
e
s
M
e
t
h
o
d
s
D
a
t
a
s
e
t
A
c
c
(
%)
R
e
f
e
r
e
n
c
e
Y
e
a
r
B
a
b
i
t
a
M
a
j
h
i
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
V
G
G
1
6
,
D
e
n
seN
e
t
,
I
n
c
e
p
t
i
o
n
V
3
M
R
I
_
S
P
EC
T,
P
D
_
M
R
I
_
S
P
EC
T
9
9
t
o
1
0
0
[
2
7
]
2
0
2
4
S
o
u
r
a
b
a
r
n
a
R
o
y
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
M
LP,
C
N
N
,
LST
M
,
R
e
sN
e
t
,
V
G
G
1
9
,
I
n
c
e
p
t
i
o
n
V
3
,
ANN
P
P
M
I
,
H
a
n
d
P
D
,
G
Y
EN
N
O
,
U
C
I
,
A
I
B
L
9
3
.
4
6
[
2
1
]
2
0
2
4
K
e
s
e
r
w
a
n
i
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
P
D
_
R
e
v
i
e
w
,
P
D
_
C
o
mb
i
n
e
d
7
5
.
5
6
t
o
9
9
.
4
9
[
2
0
]
2
0
2
4
M
o
h
a
me
d
S
h
a
b
a
n
e
t
a
l
.
U
n
su
p
e
r
v
i
s
e
d
a
n
d
s
u
p
e
r
v
i
se
d
A
N
N
,
K
N
N
,
LSTM
EEG
,
M
R
I
(
D
TI
,
S
W
I
)
,
S
p
e
e
c
h
(
O
x
f
o
r
d
,
I
st
a
n
b
u
l
)
9
9
.
9
9
[
2
6
]
2
0
2
3
A
d
i
t
i
G
o
v
i
n
d
u
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
K
N
N
,
LR
M
D
V
P
a
u
d
i
o
d
a
t
a
se
t
(
f
r
o
m PP
M
I
a
n
d
U
C
I
)
9
1
.
8
3
[
2
]
2
0
2
3
Li
p
s
i
t
a
S
a
h
u
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
A
N
N
,
S
V
M
,
K
N
N
,
C
N
N
C
u
s
t
o
m_
S
p
e
e
c
h
,
S
p
e
e
c
h
7
4
1
_
C
u
s
t
o
m
9
7
.
4
3
[
2
4
]
2
0
2
2
C
h
a
n
g
q
i
n
Q
u
a
n
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
LSTM
,
C
N
N
,
S
V
M
,
K
N
N
,
M
LP
G
Y
EN
N
O
_
P
D
_
S
p
e
e
c
h
8
4
.
2
9
[
1
5
]
2
0
2
1
M
o
u
n
i
k
a
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
,
K
N
N
,
R
N
N
U
C
I
_
P
D
-
[
2
5
]
2
0
2
1
S
i
v
a
r
a
n
j
i
n
i
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
P
P
M
I
_
T2
8
9
.
3
[
1
2
]
2
0
2
0
S
h
u
Li
h
O
h
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
K
N
N
,
C
N
N
,
A
N
N
,
R
N
N
,
P
S
O
U
K
M
_
P
D
v
sH
C
_
EEG
7
5
.
4
t
o
1
0
0
[
1
6
]
2
0
2
0
G
u
p
t
a
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
P
a
H
a
W
_
P
D
7
9
.
5
5
[
1
1
]
2
0
2
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
1
,
M
ar
ch
20
26
:
1
21
-
1
30
128
T
ab
le
2
.
Stu
d
ies
ad
d
r
ess
in
g
ty
p
es a
n
d
s
u
b
ty
p
es
o
f
Par
k
i
n
s
o
n
’
s
di
s
ea
s
e
A
u
t
h
o
r
C
a
t
e
g
o
r
i
e
s
M
e
t
h
o
d
s
D
a
t
a
s
e
t
A
c
c
(
%)
R
e
f
e
r
e
n
c
e
Y
e
a
r
R
e
d
d
y
e
t
a
l
.
S
u
p
e
r
v
i
se
d
a
n
d
u
n
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
A
N
N
,
C
N
N
,
R
N
N
,
S
V
M
K
N
N
M
u
l
t
i
-
mo
d
a
l
d
a
t
a
(
P
ET,
EEG
,
M
R
I
,
b
i
o
mar
k
e
r
s)
9
1
.
8
3
[
2
3
]
2
0
2
4
K
h
a
c
h
n
a
o
u
i
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
,
A
N
N
,
K
N
N
,
S
V
M
,
R
e
sN
e
t
,
V
G
G
.
M
u
l
t
i
p
l
e
d
a
t
a
se
t
s (e
.
g
.
,
P
P
M
I
,
PC
-
G
I
TA
,
H
a
n
d
P
D
,
S
N
U
H
)
7
5
t
o
9
9
.
4
2
[
1
7
]
2
0
2
1
El
M
a
a
c
h
i
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
,
M
LP
P
h
y
s
i
o
N
e
t
g
a
i
t
i
n
PD
d
a
t
a
s
e
t
9
8
.
7
[
1
0
]
2
0
2
0
T
ab
le
3
.
Stu
d
ies o
n
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t
o
f
Par
k
in
s
o
n
’
s
d
is
ea
s
e
A
u
t
h
o
r
C
a
t
e
g
o
r
i
e
s
M
e
t
h
o
d
s
D
a
t
a
s
e
t
A
c
c
(
%)
R
e
f
e
r
e
n
c
e
Y
e
a
r
N
u
sr
a
t
I
sl
a
m
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
K
N
N
,
C
N
N
,
M
LP
P
P
M
I
d
a
t
a
se
t
.
9
8
.
4
4
[
2
2
]
2
0
2
4
S
o
r
a
t
h
i
y
a
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
K
N
N
,
R
e
sN
e
t
,
D
e
n
seN
e
t
U
C
I
PD
,
s
p
i
r
a
l
/
w
a
v
e
h
a
n
d
w
r
i
t
i
n
g
d
a
t
a
s
e
t
s.
9
6
.
6
7
[
1
]
2
0
2
4
Al
-
N
e
f
a
i
e
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
K
N
N
,
S
V
M
,
A
d
a
B
o
o
st
,
R
F
U
C
I
P
a
r
k
i
n
s
o
n
’
s
d
a
t
a
se
t
.
95
[
2
8
]
2
0
2
4
R
a
h
ma
n
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
X
G
B
o
o
st
,
D
N
N
,
S
V
M
,
K
N
N
U
C
I
P
a
r
k
i
n
s
o
n
’
s
d
a
t
a
se
t
.
95
[
1
9
]
2
0
2
3
M
r
i
d
h
a
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
,
R
N
N
,
G
A
N
,
S
V
M
LI
D
C
-
I
D
R
I
,
LU
N
A
1
6
,
N
S
LT,
T
C
I
A
,
JS
R
T.
9
6
t
o
1
0
0
[
3
]
2
0
2
2
W
u
W
a
n
g
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
F
N
N
,
S
V
M
,
K
N
N
,
B
O
O
S
T_
T
R
EE
P
P
M
I
d
a
t
a
se
t
.
9
6
.
6
8
[
7
]
2
0
2
0
S
a
l
i
m
La
h
m
i
r
i
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
.
U
C
I
P
a
r
k
i
n
s
o
n
’
s
Te
l
e
mo
n
i
t
o
r
i
n
g
d
a
t
a
se
t
.
9
7
.
0
3
[
1
4
]
2
0
1
7
P
r
a
sh
a
n
t
h
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
n
a
ï
v
e
B
a
y
e
s
,
LR
P
P
M
I
d
a
t
a
se
t
.
9
6
.
4
0
[
1
8
]
2
0
1
6
T
ab
le
4
.
Gen
e
r
al
Par
k
in
s
o
n
’
s
d
is
ea
s
e
r
esear
ch
A
u
t
h
o
r
C
a
t
e
g
o
r
i
e
s
M
e
t
h
o
d
s
D
a
t
a
s
e
t
A
c
c
(
%)
R
e
f
e
r
e
n
c
e
Y
e
a
r
M
d
.
A
r
i
f
u
l
I
sl
a
m
e
t
a
l
.
S
u
p
e
r
v
i
se
d
a
n
d
u
n
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
S
V
M
,
K
N
N
,
R
N
N
,
C
N
N
,
LST
M
U
C
I
,
P
P
M
I
,
H
a
n
d
P
D
,
P
D
M
u
l
t
i
M
C
.
1
0
0
[
6
]
2
0
2
4
S
r
i
n
i
v
a
s
a
n
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
F
N
N
,
S
V
M
,
K
N
N
,
DT
U
C
I
P
a
r
k
i
n
s
o
n
’
s
d
a
t
a
se
t
.
9
9
.
1
1
[
3
1
]
2
0
2
4
S
h
a
w
k
i
S
a
l
e
h
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
K
N
N
,
M
LP,
S
V
M
,
X
G
B
O
O
S
T,
A
d
a
B
o
o
st
C
EST
M
R
I
d
a
t
a
se
t
(
si
mu
l
a
t
e
d
+
r
a
t
b
r
a
i
n
).
9
7
.
3
5
[
3
0
]
2
0
2
4
Li
n
C
h
e
n
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
U
-
N
ET
P
P
M
I
,
h
a
n
d
P
D
,
G
Y
EN
N
O
,
U
C
I
,
A
I
B
L.
84
[
2
9
]
2
0
2
4
M
o
h
t
a
s
h
i
m
M
i
a
n
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
C
N
N
,
R
N
N
,
A
N
N
,
LSTM
N
/
A
N
/
A
[
8
]
2
0
2
4
G
u
n
j
a
n
P
a
h
u
j
a
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
V
M
,
A
N
N
,
K
N
N
P
a
r
k
i
n
s
o
n
’
s
v
o
i
c
e
d
a
t
a
se
t
.
9
5
.
8
9
[
4
]
2
0
2
1
V
o
j
t
e
c
h
I
l
l
n
e
r
e
t
a
l
.
S
u
p
e
r
v
i
se
d
l
e
a
r
n
i
n
g
S
i
g
n
a
l
p
r
o
c
e
ss
i
n
g
/
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
C
z
e
c
h
s
mar
t
p
h
o
n
e
P
D
s
p
e
e
c
h
d
a
t
a
se
t
.
95
[
9
]
2
0
2
0
S
o
l
a
n
a
-
La
v
a
l
l
e
e
t
a
l
.
S
u
p
e
r
v
i
se
d
a
n
d
u
n
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
K
N
N
,
M
LP,
S
V
M
,
RF
I
st
a
n
b
u
l
P
D
s
p
e
e
c
h
d
a
t
a
se
t
.
9
4
.
7
[
5
]
2
0
2
0
D
e
l
i
c
e
t
a
l
.
N
/
A
R
N
N
,
C
N
N
,
D
N
N
,
LSTM
,
G
A
N
s
N
/
A
N
/
A
[
1
3
]
2
0
1
9
5.
L
I
M
I
T
AT
I
O
NS A
N
D
F
UT
U
RE
DIR
E
C
T
I
O
N
S
D
e
s
p
i
t
e
e
n
c
o
u
r
ag
i
n
g
o
u
t
c
o
m
e
s
,
t
h
e
r
e
a
r
e
a
n
u
m
b
e
r
o
f
o
b
s
t
a
c
l
e
s
t
o
cl
i
n
i
c
a
l
a
d
o
p
t
io
n
.
P
h
y
s
i
c
i
an
t
r
u
s
t
i
s
h
a
m
p
e
r
e
d
b
y
t
h
e
r
e
s
t
r
i
c
t
e
d
in
t
e
r
p
r
e
ta
b
i
l
i
ty
o
f
th
e
m
o
d
e
l.
R
e
p
ea
t
a
b
i
l
i
ty
i
s
h
a
m
p
e
r
e
d
b
y
d
a
t
a
s
e
t
b
i
a
s
a
n
d
a
l
a
ck
o
f
u
n
i
f
o
r
m
i
ty
.
F
u
r
th
e
r
m
o
r
e
,
r
e
a
l
-
t
i
m
e
co
n
n
e
c
t
i
o
n
w
i
th
m
o
b
i
l
e
o
r
w
e
ar
a
b
le
p
la
t
f
o
r
m
s
i
s
e
s
s
e
n
t
i
a
l
f
o
r
o
n
g
o
in
g
m
o
n
i
to
r
in
g
b
u
t
h
a
s
n
o
t
r
e
c
e
i
v
e
d
en
o
u
g
h
at
t
e
n
t
i
o
n
.
F
u
tu
r
e
r
e
s
e
a
r
ch
s
h
o
u
l
d
p
r
io
r
i
t
i
ze
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
d
ep
l
o
y
ab
l
e
a
n
d
c
l
i
n
i
c
a
ll
y
v
a
l
i
d
a
t
e
d
A
I
s
y
s
t
e
m
s
t
h
r
o
u
g
h
t
h
e
u
s
e
o
f
s
t
a
n
d
ar
d
i
ze
d
a
n
d
p
u
b
li
c
l
y
a
v
a
i
la
b
l
e
d
a
ta
s
e
t
s
t
o
im
p
r
o
v
e
r
e
p
r
o
d
u
c
ib
i
l
i
ty
an
d
c
r
o
s
s
-
s
t
u
d
y
co
m
p
a
r
ab
i
l
i
t
y
.
I
n
ad
d
i
t
io
n
,
i
n
c
o
r
p
o
r
a
t
in
g
ex
p
l
a
in
ab
i
l
i
t
y
f
r
a
m
e
wo
r
k
s
s
u
c
h
a
s
S
H
A
P
a
n
d
L
I
M
E
co
u
ld
en
h
an
c
e
m
o
d
el
t
r
a
n
s
p
ar
e
n
c
y
an
d
p
h
y
s
i
c
ia
n
tr
u
s
t
.
T
h
e
in
t
e
g
r
a
t
io
n
o
f
m
u
lt
i
m
o
d
a
l
d
a
t
a
f
u
s
i
o
n
t
e
c
h
n
i
q
u
e
s
,
c
o
m
b
i
n
in
g
s
p
e
e
ch
,
im
a
g
in
g
,
s
e
n
s
o
r
,
a
n
d
c
l
i
n
ic
a
l
d
a
t
a
,
m
ay
f
u
r
t
h
er
i
m
p
r
o
v
e
d
i
ag
n
o
s
t
i
c
r
o
b
u
s
t
n
es
s
.
L
o
n
g
i
tu
d
in
a
l
m
o
n
i
t
o
r
i
n
g
u
s
i
n
g
w
e
a
r
a
b
l
e
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
d
va
n
ce
s
in
P
a
r
kin
s
o
n
’
s
d
is
ea
s
e
d
ia
g
n
o
s
is
a
n
d
tr
ea
tmen
t u
s
in
g
a
r
tifi
cia
l in
tellig
en
ce
:
…
(
Meh
r
A
li Qa
s
imi)
129
m
o
b
i
le
h
ea
l
t
h
t
ec
h
n
o
lo
g
i
e
s
s
h
o
u
ld
a
l
s
o
b
e
e
x
p
l
o
r
e
d
to
ca
p
t
u
r
e
d
i
s
ea
s
e
p
r
o
g
r
e
s
s
i
o
n
o
v
e
r
t
im
e
.
F
in
a
l
l
y
,
s
e
a
m
l
e
s
s
i
n
t
eg
r
a
t
io
n
o
f
A
I
s
y
s
t
e
m
s
i
n
to
e
x
i
s
t
i
n
g
h
e
a
l
th
c
ar
e
w
o
r
k
f
l
o
w
s
i
s
e
s
s
e
n
t
i
a
l
t
o
s
u
p
p
o
r
t
r
e
a
l
-
w
o
r
l
d
c
l
i
n
i
c
a
l
d
e
c
i
s
i
o
n
-
m
a
k
in
g
a
n
d
a
d
o
p
t
i
o
n
.
6.
CO
NCLU
SI
O
N
AI
,
i
n
c
l
u
d
i
n
g
M
L
a
n
d
D
L
,
i
s
r
a
p
i
d
l
y
t
r
a
n
s
f
o
r
m
i
n
g
t
h
e
d
i
a
g
n
o
s
i
s
,
m
o
n
i
t
o
r
i
n
g
,
a
n
d
m
a
n
a
g
e
m
e
n
t
o
f
PD
.
A
I
-
d
r
i
v
e
n
d
i
a
g
n
o
s
t
i
c
t
o
o
l
s
h
a
v
e
d
e
m
o
n
s
t
r
a
t
e
d
i
m
p
r
e
s
s
i
v
e
a
c
c
u
r
a
c
y
a
c
r
o
s
s
d
i
v
e
r
s
e
m
o
d
a
l
i
t
i
e
s
s
u
c
h
a
s
s
p
e
e
c
h
,
h
a
n
d
w
r
i
t
i
n
g
,
g
a
i
t
a
n
a
l
y
s
i
s
,
n
e
u
r
o
i
m
a
g
i
n
g
,
a
n
d
E
E
G
,
w
i
t
h
s
o
m
e
m
o
d
e
l
s
e
x
c
e
e
d
i
n
g
9
5
%
a
c
c
u
r
a
c
y
.
T
h
e
s
e
a
d
v
a
n
c
e
m
e
n
t
s
e
n
a
b
l
e
e
a
r
l
i
e
r
d
e
t
e
c
t
i
o
n
a
n
d
m
o
r
e
p
e
r
s
o
n
a
l
i
z
e
d
t
r
e
a
t
m
e
n
t
s
t
r
a
t
e
g
i
e
s
,
p
a
v
i
n
g
t
h
e
w
a
y
f
o
r
i
m
p
r
o
v
e
d
p
a
t
i
e
n
t
o
u
t
c
o
m
e
s
.
A
l
t
h
o
u
g
h
t
h
i
s
r
e
v
i
e
w
d
o
e
s
n
o
t
i
n
t
r
o
d
u
c
e
n
e
w
e
x
p
e
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
o
r
a
q
u
a
n
t
i
t
a
t
i
v
e
m
e
t
a
-
a
n
a
l
y
s
i
s
,
i
t
p
r
o
v
i
d
e
s
a
s
t
r
u
c
t
u
r
e
d
a
n
d
c
r
i
t
i
c
a
l
s
y
n
t
h
e
s
i
s
o
f
AI
-
b
a
s
e
d
PD
r
e
s
e
a
r
c
h
.
F
u
t
u
r
e
r
e
s
e
a
r
c
h
s
h
o
u
l
d
p
r
i
o
r
i
t
i
z
e
c
l
i
n
i
c
a
l
l
y
v
a
l
i
d
a
t
e
d
,
i
n
t
e
r
p
r
e
t
a
b
l
e
,
a
n
d
r
e
p
r
o
d
u
c
i
b
l
e
A
I
m
o
d
e
l
s
,
s
u
p
p
o
r
t
e
d
b
y
l
o
n
g
i
t
u
d
i
n
a
l
a
n
d
m
u
l
t
i
-
c
e
n
t
e
r
d
a
t
a
s
e
t
s
,
t
o
b
r
i
d
g
e
t
h
e
g
a
p
b
e
t
w
e
e
n
e
x
p
e
r
i
m
e
n
t
a
l
s
u
c
c
e
s
s
a
n
d
r
e
a
l
-
w
o
r
l
d
d
e
p
l
o
y
m
e
n
t
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
S
o
r
a
t
h
i
y
a
,
J.
M
e
h
t
a
,
H
.
R
a
t
h
o
d
,
a
n
d
N
.
M
a
r
a
t
h
e
,
“
E
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
s
i
n
g
ma
c
h
i
n
e
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
,
”
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ro
n
i
c
s
,
C
o
m
p
u
t
e
rs
a
n
d
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
EC
AI
)
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
EC
A
I
6
1
5
0
3
.
2
0
2
4
.
1
0
6
0
7
4
8
2
.
[
2
]
A
.
G
o
v
i
n
d
u
a
n
d
S
.
P
a
l
w
e
,
“
E
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
v
o
l
.
2
1
8
,
p
p
.
2
4
9
–
2
6
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
2
3
.
0
1
.
0
0
7
.
[
3
]
M
.
F
.
M
r
i
d
h
a
e
t
a
l
.
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
o
n
t
h
e
p
r
o
g
r
e
ss,
p
r
o
c
e
ss,
a
n
d
c
h
a
l
l
e
n
g
e
s
o
f
l
u
n
g
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
c
a
r
e
En
g
i
n
e
e
ri
n
g
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
5
9
0
5
2
3
0
.
[
4
]
G
.
P
a
h
u
j
a
a
n
d
T
.
N
.
N
a
g
a
b
h
u
sh
a
n
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
e
x
i
s
t
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
,
”
I
ETE
J
o
u
r
n
a
l
o
f
Re
s
e
a
rc
h
,
v
o
l
.
6
7
,
n
o
.
1
,
p
p
.
4
–
1
4
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
7
7
2
0
6
3
.
2
0
1
8
.
1
5
3
1
7
3
0
.
[
5
]
G
.
S
.
-
L
a
v
a
l
l
e
,
J.
-
C
.
G
.
-
H
e
r
n
á
n
d
e
z
,
a
n
d
R
.
R
.
-
R
o
mero
,
“
A
u
t
o
m
a
t
i
c
P
a
r
k
i
n
so
n
d
i
se
a
se
d
e
t
e
c
t
i
o
n
a
t
e
a
r
l
y
s
t
a
g
e
s
a
s
a
p
r
e
-
d
i
a
g
n
o
si
s
t
o
o
l
b
y
u
si
n
g
c
l
a
ss
i
f
i
e
r
s
a
n
d
a
s
m
a
l
l
se
t
o
f
v
o
c
a
l
f
e
a
t
u
r
e
s,
”
Bi
o
c
y
b
e
r
n
e
t
i
c
s
a
n
d
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
5
0
5
–
5
1
6
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
b
e
.
2
0
2
0
.
0
1
.
0
0
3
.
[
6
]
M
.
A
.
I
sl
a
m,
M
.
Z
.
H
.
M
a
j
u
m
d
e
r
,
M
.
A
.
H
u
sse
i
n
,
K
.
M
.
H
o
ssa
i
n
,
a
n
d
M
.
S
.
M
i
a
h
,
“
A
r
e
v
i
e
w
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
P
a
r
k
i
n
so
n
’
s
d
i
sea
s
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
h
a
n
d
w
r
i
t
i
n
g
a
n
d
v
o
i
c
e
d
a
t
a
s
e
t
s
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
3
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
5
4
6
9
.
[
7
]
W
.
W
a
n
g
,
J.
Le
e
,
F
.
H
a
r
r
o
u
,
a
n
d
Y
.
S
u
n
,
“
Ea
r
l
y
d
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
4
7
6
3
5
–
1
4
7
6
4
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
1
6
0
6
2
.
[
8
]
S
.
M
.
M
i
a
n
,
M
.
S
.
K
h
a
n
,
M
.
S
h
a
w
e
z
,
a
n
d
A
.
K
a
u
r
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
(
A
I
)
,
mac
h
i
n
e
l
e
a
r
n
i
n
g
(
M
L)
&
d
e
e
p
l
e
a
r
n
i
n
g
(
D
L)
:
a
c
o
m
p
r
e
h
e
n
si
v
e
o
v
e
r
v
i
e
w
o
n
t
e
c
h
n
i
q
u
e
s,
a
p
p
l
i
c
a
t
i
o
n
s
a
n
d
r
e
se
a
r
c
h
d
i
r
e
c
t
i
o
n
s
,
”
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
a
n
d
S
m
a
rt
S
y
s
t
e
m
s
(
I
C
S
C
S
S
)
Pro
c
e
e
d
i
n
g
s
,
p
p
.
1
4
0
4
–
1
4
0
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
S
S
6
0
6
6
0
.
2
0
2
4
.
1
0
6
2
5
1
9
8
.
[
9
]
V
.
I
l
l
n
e
r
,
P
.
S
o
v
k
a
,
a
n
d
J
.
R
u
sz
,
“
V
a
l
i
d
a
t
i
o
n
o
f
f
r
e
e
l
y
-
a
v
a
i
l
a
b
l
e
p
i
t
c
h
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
s
a
c
r
o
ss
v
a
r
i
o
u
s n
o
i
s
e
l
e
v
e
l
s
i
n
a
sse
ssi
n
g
sp
e
e
c
h
c
a
p
t
u
r
e
d
b
y
s
mart
p
h
o
n
e
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
a
n
d
C
o
n
t
ro
l
,
v
o
l
.
5
8
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
1
9
.
1
0
1
8
3
1
.
[
1
0
]
I
.
El
M
a
a
c
h
i
,
G
.
-
A
.
B
i
l
o
d
e
a
u
,
a
n
d
W
.
B
o
u
a
c
h
i
r
,
“
D
e
e
p
1
D
-
c
o
n
v
n
e
t
f
o
r
a
c
c
u
r
a
t
e
P
a
r
k
i
n
so
n
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
a
n
d
s
e
v
e
r
i
t
y
p
r
e
d
i
c
t
i
o
n
f
r
o
m
g
a
i
t
,
”
E
x
p
e
rt
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
3
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
9
.
1
1
3
0
7
5
.
[
1
1
]
U
.
G
u
p
t
a
,
H
.
B
a
n
sa
l
,
a
n
d
D
.
J
o
sh
i
,
“
A
n
i
mp
r
o
v
e
d
se
x
-
sp
e
c
i
f
i
c
a
n
d
a
g
e
-
d
e
p
e
n
d
e
n
t
c
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
f
o
r
P
a
r
k
i
n
s
o
n
’
s
d
i
a
g
n
o
s
i
s
u
si
n
g
h
a
n
d
w
r
i
t
i
n
g
me
a
su
r
e
me
n
t
,
”
C
o
m
p
u
t
e
r
M
e
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
8
9
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
mp
b
.
2
0
1
9
.
1
0
5
3
0
5
.
[
1
2
]
S
.
S
i
v
a
r
a
n
j
i
n
i
a
n
d
C
.
M
.
S
u
j
a
t
h
a
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
d
i
a
g
n
o
si
s
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
9
,
n
o
.
2
1
–
2
2
,
p
p
.
1
5
4
6
7
–
1
5
4
7
9
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
1
9
-
7
4
6
9
-
8.
[
1
3
]
V
.
D
e
l
i
ć
e
t
a
l
.
,
“
S
p
e
e
c
h
t
e
c
h
n
o
l
o
g
y
p
r
o
g
r
e
ss
b
a
se
d
o
n
n
e
w
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
p
a
r
a
d
i
g
m,”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
ro
s
c
i
e
n
c
e
,
p
p
.
1
–
1
9
,
J
u
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
9
/
4
3
6
8
0
3
6
.
[
1
4
]
S
.
La
h
mi
r
i
,
“
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
d
y
sp
h
o
n
i
a
m
e
a
s
u
r
e
men
t
s,
”
P
h
y
si
c
a
A:
S
t
a
t
i
s
t
i
c
a
l
M
e
c
h
a
n
i
c
s
a
n
d
i
t
s
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
7
1
,
p
p
.
9
8
–
1
0
5
,
A
p
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
sa.
2
0
1
6
.
1
2
.
0
0
9
.
[
1
5
]
C
.
Q
u
a
n
,
K
.
R
e
n
,
a
n
d
Z.
L
u
o
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
me
t
h
o
d
f
o
r
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
d
e
t
e
c
t
i
o
n
u
si
n
g
d
y
n
a
mi
c
f
e
a
t
u
r
e
s
o
f
sp
e
e
c
h
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
0
2
3
9
–
1
0
2
5
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
1
.
3
0
5
1
4
3
2
.
[
1
6
]
S
.
L.
O
h
e
t
a
l
.
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
d
i
a
g
n
o
s
i
s
f
r
o
m
EEG
si
g
n
a
l
s
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
1
5
,
p
p
.
1
0
9
2
7
–
1
0
9
3
3
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
1
8
-
3
6
8
9
-
5.
[
1
7
]
H
.
K
h
a
c
h
n
a
o
u
i
,
R
.
M
a
b
r
o
u
k
,
a
n
d
N
.
K
h
l
i
f
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
f
o
r
c
l
i
n
i
c
a
l
d
a
t
a
a
n
d
P
ET
/
S
P
EC
T
i
m
a
g
i
n
g
i
n
p
a
r
k
i
n
so
n
’
s
d
i
s
e
a
s
e
:
a
r
e
v
i
e
w
,
”
I
ET I
m
a
g
e
Pr
o
c
e
ssi
n
g
,
v
o
l
.
1
4
,
n
o
.
1
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
i
p
r
.
2
0
2
0
.
1
0
4
8
.
[
1
8
]
R
.
P
r
a
s
h
a
n
t
h
,
S
.
D
.
R
o
y
,
P
.
K
.
M
a
n
d
a
l
,
a
n
d
S
.
G
h
o
s
h
,
“
H
i
g
h
-
a
c
c
u
r
a
c
y
d
e
t
e
c
t
i
o
n
o
f
e
a
r
l
y
P
a
r
k
i
n
s
o
n
’
s
d
i
sea
se
t
h
r
o
u
g
h
m
u
l
t
i
m
o
d
a
l
f
e
a
t
u
r
e
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
9
0
,
p
p
.
1
3
–
2
1
,
Ju
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
m
e
d
i
n
f
.
2
0
1
6
.
0
3
.
0
0
1
.
[
1
9
]
S
.
R
a
h
ma
n
,
M
.
H
a
s
a
n
,
A
.
K
.
S
a
r
k
a
r
,
a
n
d
F
.
K
h
a
n
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
u
s
i
n
g
s
p
e
e
c
h
si
g
n
a
l
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,
”
E
u
r
o
p
e
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
2
0
–
2
7
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
2
4
0
1
8
/
e
j
e
c
e
.
2
0
2
3
.
7
.
2
.
4
8
8
.
[
2
0
]
P
.
K
.
K
e
s
e
r
w
a
n
i
,
S
.
D
a
s,
a
n
d
N
.
S
a
r
k
a
r
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
:
p
r
e
d
i
c
t
i
o
n
o
f
p
a
r
k
i
n
so
n
’
s
d
i
s
e
a
s
e
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
n
a
t
u
r
e
i
n
s
p
i
r
e
d
a
l
g
o
r
i
t
h
m,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
2
7
,
p
p
.
6
9
3
9
3
–
6
9
4
4
1
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
024
-
1
8
1
8
6
-
z.
[
2
1
]
S
.
R
o
y
,
T
.
P
a
l
,
a
n
d
S
.
D
e
b
b
a
r
ma
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
a
d
v
a
n
c
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
t
o
d
i
a
g
n
o
se
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
se
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
5
,
p
p
.
1
2
2
–
1
3
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
4
.
0
4
.
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
7
,
No
.
1
,
M
ar
ch
20
26
:
1
21
-
1
30
130
[
2
2
]
N
.
I
sl
a
m,
M
.
S
.
A
.
T
u
r
z
a
,
S
.
I
.
F
a
h
i
m,
a
n
d
R
.
M
.
R
a
h
m
a
n
,
“
A
d
v
a
n
c
e
d
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
d
e
t
e
c
t
i
o
n
:
a
c
o
mp
r
e
h
e
n
s
i
v
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
p
p
r
o
a
c
h
u
t
i
l
i
z
i
n
g
c
l
i
n
i
c
a
l
a
ss
e
ssm
e
n
t
a
n
d
n
e
u
r
o
i
ma
g
i
n
g
s
a
mp
l
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
i
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
,
p
p
.
1
9
9
–
2
2
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
c
c
e
.
2
0
2
4
.
0
5
.
0
0
1
.
[
2
3
]
A
.
R
e
d
d
y
e
t
a
l
.
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
:
e
a
r
l
y
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
st
i
c
a
d
v
a
n
c
e
me
n
t
s,”
Ag
e
i
n
g
Re
s
e
a
r
c
h
Re
v
i
e
w
s
,
v
o
l
.
9
9
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
.
2
0
2
4
.
1
0
2
4
1
0
.
[
2
4
]
L.
S
a
h
u
,
R
.
S
h
a
r
m
a
,
I
.
S
a
h
u
,
M
.
D
a
s,
B
.
S
a
h
u
,
a
n
d
R
.
K
u
m
a
r
,
“
Ef
f
i
c
i
e
n
t
d
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
s
e
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
o
v
e
r
m
e
d
i
c
a
l
d
a
t
a
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
,
v
o
l
.
3
9
,
n
o
.
3
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
1
1
/
e
x
s
y
.
1
2
7
8
7
.
[
2
5
]
P
.
M
o
u
n
i
k
a
a
n
d
S
.
G
.
R
a
o
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
d
i
a
g
n
o
si
s
o
f
P
a
r
k
i
n
so
n
’
s
d
i
sea
se
:
a
p
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
si
s
,
”
Pr
o
c
e
e
d
i
n
g
s o
f
t
h
e
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
-
S
MA
C
(
I
o
T
i
n
S
o
c
i
a
l
,
M
o
b
i
l
e
,
An
a
l
y
t
i
c
s
a
n
d
C
l
o
u
d
)
,
p
p
.
3
8
1
–
3
8
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
-
S
M
A
C
5
2
3
3
0
.
2
0
2
1
.
9
6
4
0
6
3
2
.
[
2
6
]
M
.
S
h
a
b
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
P
a
r
k
i
n
so
n
’
s
d
i
s
e
a
s
e
d
i
a
g
n
o
s
i
s:
a
s
h
o
r
t
su
r
v
e
y
,
”
C
o
m
p
u
t
e
rs
,
v
o
l
.
1
2
,
n
o
.
3
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
mp
u
t
e
r
s1
2
0
3
0
0
5
8
.
[
2
7
]
B
.
M
a
j
h
i
e
t
a
l
.
,
“
A
n
i
m
p
r
o
v
e
d
me
t
h
o
d
f
o
r
d
i
a
g
n
o
s
i
s
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
s
e
a
se
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
e
n
h
a
n
c
e
d
w
i
t
h
met
a
h
e
u
r
i
s
t
i
c
a
l
g
o
r
i
t
h
m,
”
B
MC
Me
d
i
c
a
l
I
m
a
g
i
n
g
,
v
o
l
.
2
4
,
n
o
.
1
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
8
0
-
024
-
0
1
3
3
5
-
z.
[
2
8
]
A
.
H
.
A
l
-
N
e
f
a
i
e
,
T.
H
.
H
.
A
l
d
h
y
a
n
i
,
a
n
d
D
.
K
o
u
n
d
a
l
,
“
D
e
v
e
l
o
p
i
n
g
s
y
st
e
m
-
b
a
se
d
v
o
i
c
e
f
e
a
t
u
r
e
s
f
o
r
d
e
t
e
c
t
i
n
g
P
a
r
k
i
n
so
n
’
s
d
i
se
a
s
e
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
J
o
u
r
n
a
l
o
f
D
i
s
a
b
i
l
i
t
y
Re
se
a
r
c
h
,
v
o
l
.
3
,
n
o
.
1
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
5
7
1
9
7
/
JD
R
-
2
0
2
4
-
0
0
0
1
.
[
2
9
]
L.
C
h
e
n
e
t
a
l
.
,
“
A
c
c
e
l
e
r
a
t
i
n
g
m
u
l
t
i
p
o
o
l
C
EST
M
R
I
o
f
P
a
r
k
i
n
s
o
n
’
s
d
i
se
a
se
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
–
b
a
se
d
Z‐
sp
e
c
t
r
a
l
c
o
m
p
r
e
sse
d
sen
s
i
n
g
,
”
Ma
g
n
e
t
i
c
Re
s
o
n
a
n
c
e
i
n
Me
d
i
c
i
n
e
,
Ju
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
2
/
mr
m
.
3
0
2
3
3
.
[
3
0
]
S
.
S
a
l
e
h
,
B
.
C
h
e
r
r
a
d
i
,
O
.
E
l
G
a
n
n
o
u
r
,
S
.
H
a
mi
d
a
,
a
n
d
O
.
B
o
u
a
t
t
a
n
e
,
“
P
r
e
d
i
c
t
i
n
g
p
a
t
i
e
n
t
s
w
i
t
h
P
a
r
k
i
n
s
o
n
’
s
d
i
sea
s
e
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
e
n
s
e
m
b
l
e
v
o
t
i
n
g
t
e
c
h
n
i
q
u
e
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
1
1
,
p
p
.
3
3
2
0
7
–
3
3
2
3
4
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
023
-
1
6
8
8
1
-
x.
[
3
1
]
S
.
S
r
i
n
i
v
a
sa
n
,
P
.
R
a
ma
d
a
ss,
S
.
K
.
M
a
t
h
i
v
a
n
a
n
,
K
.
P
.
S
e
l
v
a
m,
B
.
D
.
S
h
i
v
a
h
a
r
e
,
a
n
d
M
.
A
.
S
h
a
h
,
“
D
e
t
e
c
t
i
o
n
o
f
P
a
r
k
i
n
s
o
n
d
i
s
e
a
s
e
u
si
n
g
m
u
l
t
i
c
l
a
ss
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
4
,
n
o
.
1
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
024
-
6
4
0
0
4
-
9.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mehr
Ali
Q
a
sim
i
is
a
M
a
st
e
r
d
e
g
re
e
stu
d
e
n
t
i
n
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
a
t
S
e
lcu
k
u
n
i
v
e
rsity
,
w
h
e
re
h
e
c
u
rre
n
tl
y
se
rv
e
s
a
s
a
n
a
ss
i
sta
n
t
p
ro
fe
s
so
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
S
y
ste
m
a
t
Ba
d
a
k
h
s
h
a
n
Un
i
v
e
rsity
Af
g
h
a
n
istan
.
His
m
a
ste
r
d
e
g
re
e
fo
c
u
se
d
o
n
d
e
v
e
lo
p
in
g
a
rti
ficia
l
in
tel
li
g
e
n
c
e
t
e
c
h
n
iq
u
e
s
fo
r
id
e
n
ti
fy
i
n
g
d
ise
a
se
.
He
h
a
s
p
u
b
li
sh
e
d
d
i
ffe
re
n
t
p
a
p
e
rs
in
AI
a
n
d
d
ise
a
se
d
e
tec
ti
o
n
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
q
1
.
m
e
h
ra
li
@g
m
a
il
.
c
o
m
o
r
q
.
m
e
h
ra
li
@y
a
h
o
o
.
c
o
m
.
Zü
ley
h
a
Yıl
m
a
z
Ac
a
r
is
a
P
h
.
D.
h
o
ld
e
r
in
Co
m
p
u
ter
En
g
in
e
e
rin
g
fro
m
S
e
lçu
k
Un
iv
e
rsity
,
wh
e
re
sh
e
c
u
rre
n
tl
y
se
rv
e
s
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
wit
h
in
t
h
e
F
a
c
u
lt
y
o
f
Tec
h
n
o
l
o
g
y
.
S
h
e
h
a
s
a
u
th
o
re
d
stu
d
ies
,
in
t
h
e
field
s
o
f
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
b
io
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
,
a
n
d
m
a
c
h
i
n
e
lea
rn
i
n
g
/
d
e
e
p
lea
rn
in
g
a
lg
o
rit
h
m
s.
S
h
e
c
o
n
ti
n
u
e
s
to
w
o
rk
o
n
AI
-
b
a
se
d
m
e
d
ica
l
d
iag
n
o
stic
a
p
p
r
o
a
c
h
e
s.
Sh
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
z
u
ley
h
a
y
il
m
a
z
@s
e
lcu
k
.
e
d
u
.
tr
.
Evaluation Warning : The document was created with Spire.PDF for Python.