I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
7
,
No
.
2
,
A
p
r
il
201
7
,
p
p
.
10
2
3
~
10
3
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
2
.
p
p
1
0
2
3
-
10
3
1
1023
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
H
y
brid Sys
t
e
m
of
Tiered Mul
tiva
ria
te
Ana
ly
sis
and
Artif
i
cia
l
Neura
l Ne
tw
o
rk
f
o
r Coro
na
ry
H
ea
rt
Disea
se
Dia
g
no
sis
Wiha
rt
o
1
,
H
a
ri
K
us
na
nto
2
,
H
er
ia
nto
H
er
ia
nto
3
1
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
,
S
e
b
e
las
M
a
re
t
Un
iv
e
rsit
y
,
In
d
o
n
e
sia
1,
2
,3
De
p
a
rtm
e
n
t
o
f
Bio
m
e
d
ica
l
En
g
in
e
e
rin
g
,
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
,
In
d
o
n
e
sia
2
De
p
a
rtme
n
t
o
f
M
e
d
icin
e
,
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
,
In
d
o
n
e
sia
3
De
p
a
rtme
n
t
o
f
M
e
c
h
a
n
ica
l
&
In
d
u
strial
E
n
g
in
e
e
rin
g
,
G
a
d
jah
M
a
d
a
Un
iv
e
rsi
t
y
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
28
,
2
0
1
6
R
ev
i
s
ed
J
an
4
,
2
0
1
7
A
cc
ep
ted
J
an
1
9
,
2
0
1
7
Im
p
ro
v
e
d
s
y
ste
m
p
e
r
f
o
rm
a
n
c
e
d
i
a
g
n
o
sis
o
f
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
s
e
b
e
c
o
m
e
s
a
n
im
p
o
rtan
t
to
p
ic
in
re
se
a
rc
h
f
o
r
se
v
e
ra
l
d
e
c
a
d
e
s.
On
e
i
m
p
ro
v
e
m
e
n
t
w
o
u
ld
b
e
d
o
n
e
b
y
f
e
a
tu
re
s
se
lec
ti
o
n
,
so
o
n
ly
th
e
a
tt
rib
u
tes
th
a
t
in
f
lu
e
n
c
e
is
u
se
d
i
n
th
e
d
iag
n
o
sis
sy
ste
m
u
sin
g
d
a
ta
m
in
in
g
a
lg
o
rit
h
m
s.
Un
f
o
rtu
n
a
tely
,
th
e
m
o
st
f
e
a
tu
re
se
lec
ti
o
n
is
d
o
n
e
w
it
h
th
e
a
ss
u
m
p
ti
o
n
h
a
s
p
r
o
v
id
e
d
a
ll
t
h
e
n
e
c
e
ss
a
r
y
a
tt
rib
u
tes
,
re
g
a
rd
les
s
o
f
th
e
sta
g
e
o
f
o
b
tain
i
n
g
th
e
a
tt
ri
b
u
te,
a
n
d
c
o
s
t
re
q
u
ired
.
T
h
is
re
se
a
r
c
h
p
ro
p
o
se
s a h
y
b
rid
m
o
d
e
l
s
y
ste
m
f
o
r
d
iag
n
o
sis o
f
c
o
r
o
n
a
ry
h
e
a
rt
d
ise
a
se
.
S
y
ste
m
d
iag
n
o
sis
p
re
c
e
d
e
d
th
e
f
e
a
tu
re
se
lec
ti
o
n
p
r
o
c
e
ss
,
u
sin
g
ti
e
re
d
m
u
lt
iv
a
riate
a
n
a
l
y
sis.
T
h
e
a
n
a
l
y
ti
c
a
l
m
e
th
o
d
u
se
d
is
lo
g
isti
c
re
g
re
ss
io
n
.
T
h
e
n
e
x
t
sta
g
e
,
th
e
c
la
ss
i
f
ica
ti
o
n
b
y
u
sin
g
m
u
lt
i
-
la
y
e
r
p
e
rc
e
p
tro
n
n
e
u
ra
l
n
e
tw
o
rk
.
Ba
se
d
o
n
tes
t
re
su
lt
s
,
sy
ste
m
p
e
rf
o
r
m
a
n
c
e
p
ro
p
o
se
d
v
a
lu
e
f
o
r
a
c
c
u
ra
c
y
8
6
.
3
%
,
se
n
siti
v
it
y
8
4
.
8
0
%
,
sp
e
c
if
icit
y
8
8
.
2
0
%
,
p
o
si
ti
v
e
p
re
d
ictio
n
v
a
lu
e
(P
P
V
)
9
0
.
0
3
%
,
n
e
g
a
ti
v
e
p
re
d
icti
o
n
v
a
lu
e
(NPV
)
8
1
.
8
0
%
,
a
c
c
u
ra
c
y
8
6
,
3
0
%
a
n
d
a
re
a
u
n
d
e
r
t
h
e
c
u
rv
e
(A
UC)
o
f
9
2
.
1
%
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
a
d
iag
n
o
sis
u
sin
g
a
c
o
m
b
in
a
ti
o
n
a
tt
rib
u
tes
o
f
risk
f
a
c
to
rs,
s
y
m
p
to
m
s
a
n
d
e
x
e
r
c
ise
EC
G
.
T
h
e
c
o
n
c
lu
sio
n
th
a
t
c
a
n
b
e
d
ra
w
n
is
th
a
t
th
e
p
r
o
p
o
se
d
d
iag
n
o
sis
s
y
ste
m
c
a
p
a
b
le
o
f
d
e
li
v
e
rin
g
p
e
rf
o
r
m
a
n
c
e
in
th
e
v
e
ry
g
o
o
d
c
a
teg
o
r
y
,
w
it
h
a
n
u
m
b
e
r
o
f
a
tt
rib
u
tes
t
h
a
t
a
re
n
o
t
a
lo
t
o
f
c
h
e
c
k
s an
d
a
re
lativ
e
l
y
lo
w
c
o
st
.
K
ey
w
o
r
d
:
C
o
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e
Diag
n
o
s
is
L
o
g
i
s
tic
r
eg
r
e
s
s
io
n
Mu
lti
-
la
y
er
n
e
u
r
al
n
et
w
o
r
k
Mu
lti
v
ar
iate
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
ih
ar
to
,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
,
Seb
elas M
ar
et
Un
i
v
er
s
it
y
,
J
l.
I
r
.
Su
ta
m
i N
o
.
3
6
A
,
Ken
ti
n
g
an
,
S
u
r
ak
ar
ta,
C
en
tr
al
o
f
J
av
a,
I
n
d
o
n
esia
.
E
m
ail:
w
i
h
ar
to
@
s
ta
f
f
.
u
n
s
.
ac
.
i
d
1.
I
NT
RO
D
UCT
I
O
N
R
ap
id
ec
o
n
o
m
ic
g
r
o
w
th
b
r
o
u
g
h
t
ab
o
u
t
m
an
y
c
h
an
g
es
in
th
e
p
atter
n
o
f
li
f
e,
esp
ec
iall
y
i
n
d
ev
elo
p
ed
an
d
d
ev
elo
p
in
g
co
u
n
tr
ie
s
.
C
h
an
g
e
s
in
l
if
e
s
t
y
le
ca
n
g
iv
e
a
b
ad
ef
f
ec
t
o
n
h
ea
lth
.
O
n
e
o
f
t
h
e
d
is
ea
s
e
s
th
at
ar
e
in
f
lu
e
n
ce
d
b
y
li
f
est
y
le
i
s
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
[
1
]
.
T
o
o
v
er
co
m
e
t
h
i
s
,
p
r
ev
en
tio
n
a
n
d
ea
r
l
y
d
etec
tio
n
ar
e
v
er
y
i
m
p
o
r
tan
t
to
m
ai
n
tai
n
a
g
o
o
d
lif
es
t
y
le
.
Diag
n
o
s
i
s
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
r
eq
u
ir
es
s
o
m
e
k
i
n
d
o
f
in
s
p
ec
tio
n
.
E
ac
h
i
n
s
p
ec
tio
n
n
ee
d
co
s
ts
.
T
h
e
n
u
m
b
er
o
f
co
s
t
is
d
ep
en
d
in
g
o
n
t
h
e
t
y
p
e
o
f
ex
a
m
in
at
io
n
p
er
f
o
r
m
ed
.
T
h
e
m
o
r
e
t
y
p
es
o
f
test
s
w
ill
b
e
g
r
ea
ter
co
s
ts
t
h
at
m
u
s
t
b
e
is
s
u
ed
in
t
h
e
p
r
o
ce
s
s
o
f
d
i
ag
n
o
s
i
s
.
I
n
m
ak
in
g
a
d
ia
g
n
o
s
is
,
a
cli
n
icia
n
w
ill
m
a
k
e
t
h
e
s
e
lectio
n
o
f
t
h
e
v
ar
io
u
s
t
y
p
es
o
f
i
n
s
p
ec
tio
n
.
Selectio
n
i
s
b
ased
o
n
w
h
et
h
er
th
e
i
n
v
e
s
ti
g
atio
n
h
as
a
r
elativ
e
ad
v
an
ta
g
e
co
m
p
ar
ed
to
o
th
er
test
s
.
T
h
ese
ad
v
an
ta
g
es
ca
n
b
e
a
v
alu
e
h
i
g
h
er
d
iag
n
o
s
is
,
ex
a
m
i
n
atio
n
f
as
ter
,
lo
w
er
r
is
k
,
ch
ec
k
s
t
h
at
ar
e
n
o
t
e
x
p
en
s
i
v
e
a
n
d
s
o
m
e
o
th
er
cli
n
ica
l
co
n
s
id
er
atio
n
s
.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
co
r
o
n
ar
y
h
ea
r
t
d
i
s
ea
s
e
d
ia
g
n
o
s
i
s
s
y
s
te
m
h
a
s
b
ee
n
w
id
el
y
ap
p
li
ed
,
u
s
in
g
tr
en
d
in
g
cla
s
s
i
f
icatio
n
al
g
o
r
ith
m
s
a
n
d
f
ea
tu
r
e
s
elec
tio
n
.
A
d
iag
n
o
s
t
ic
s
y
s
te
m
t
h
at
h
as
b
ee
n
d
o
n
e
ca
n
b
e
g
r
o
u
p
ed
in
to
t
w
o
ca
teg
o
r
ies,
n
a
m
e
l
y
u
s
in
g
a
n
d
n
o
t
u
s
i
n
g
t
h
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
.
Featu
r
e
s
elec
tio
n
is
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
2
,
A
p
r
il 2
0
1
7
:
10
2
3
–
10
3
1
1024
p
r
ep
r
o
ce
s
s
in
g
to
ch
o
o
s
e
th
e
f
ea
tu
r
es
th
a
t
ef
f
ec
t
an
d
o
v
er
r
id
e
f
ea
tu
r
e
d
o
es
n
o
t
af
f
ec
t
in
a
n
y
ac
t
iv
i
t
y
m
o
d
eli
n
g
o
r
d
ata
an
aly
s
is
[
2
]
.
T
h
e
m
et
h
o
d
o
f
f
ea
tu
r
e
s
elec
tio
n
i
s
d
iv
i
d
ed
in
to
t
w
o
g
r
o
u
p
s
,
r
an
k
i
n
g
s
elec
tio
n
a
n
d
s
u
b
s
et
s
elec
tio
n
.
R
a
n
k
in
g
u
n
m
atc
h
ed
s
p
ec
if
icall
y
g
a
v
e
th
e
r
an
k
o
n
ev
er
y
ex
i
s
ti
n
g
f
ea
t
u
r
e
an
d
o
v
er
r
id
e
f
ea
tu
r
e
th
a
t
d
o
es
n
o
t
m
ee
t
ce
r
tain
s
tan
d
ar
d
s
.
Su
b
s
et
s
elec
tio
n
i
s
th
e
m
et
h
o
d
o
f
s
elec
tio
n
w
er
e
lo
o
k
in
g
f
o
r
a
s
et
o
f
f
ea
tu
r
e
s
w
h
ic
h
ar
e
co
n
s
id
er
ed
as th
e
o
p
ti
m
al
f
ea
t
u
r
e.
T
h
e
s
u
b
s
e
t sele
ctio
n
is
d
iv
id
ed
i
n
to
th
r
ee
ap
p
r
o
ac
h
es,
n
a
m
el
y
t
h
e
w
r
ap
p
er
,
f
ilter
,
an
d
e
m
b
ed
d
ed
ap
p
r
o
ac
h
[
2
]
,
[
3
]
.
W
r
ap
p
er
ap
p
r
o
ac
h
es
t
h
e
s
elec
tio
n
p
r
o
ce
s
s
alo
n
g
w
it
h
th
e
i
m
p
le
m
en
ta
tio
n
o
f
cla
s
s
i
f
icat
io
n
.
T
h
is
ap
p
r
o
ac
h
also
u
s
e
s
cr
iter
ia
b
y
u
ti
lizi
n
g
t
h
e
cl
ass
i
f
icatio
n
r
ate
o
f
class
i
f
icatio
n
m
et
h
o
d
s
ar
e
u
s
e
d
.
W
r
a
p
p
er
an
d
f
ilter
is
al
m
o
s
t
s
i
m
ilar
to
o
,
b
u
t
th
e
f
ilter
d
o
es
n
o
t
in
v
o
lv
e
t
h
e
me
t
h
o
d
o
f
class
i
f
icatio
n
.
W
h
i
le
e
m
b
ed
d
ed
,
u
tili
zin
g
a
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
,
s
o
th
at
f
ea
tu
r
e
n
atu
r
all
y
eli
m
i
n
ated
,
if
t
h
e
m
ac
h
i
n
e
lear
n
in
g
as
s
u
m
e
t
h
ese
f
ea
t
u
r
es a
r
e
n
o
t so
in
f
l
u
en
tia
l [
2
],
[
3
]
.
Mo
d
el
f
ea
t
u
r
e
s
elec
t
io
n
th
at
i
s
w
id
el
y
u
s
ed
i
s
t
h
e
s
u
b
s
et
s
elec
tio
n
w
i
th
g
o
o
d
f
ilter
s
,
w
r
ap
p
er
an
d
e
m
b
ed
d
ed
ap
p
r
o
ac
h
.
Su
b
an
y
a
an
d
R
aj
alax
m
i
[
3
]
p
r
o
p
o
s
ed
a
s
y
s
te
m
o
f
d
ia
g
n
o
s
is
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e,
w
h
ic
h
p
r
ec
ed
ed
th
e
p
r
o
ce
s
s
o
f
f
ea
t
u
r
e
s
e
lectio
n
.
T
h
e
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
b
y
u
s
in
g
a
n
al
g
o
r
ith
m
ar
ti
f
icial
b
ee
co
lo
n
y
(
A
B
C
)
.
T
h
e
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
it
h
m
s
p
er
f
o
r
m
ag
ain
s
t
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
1
3
attr
ib
u
tes
o
f
th
e
d
ataset
Un
i
v
er
s
i
t
y
o
f
C
a
lif
o
r
n
i
a
I
r
v
in
e
(
U
C
I
)
.
T
h
e
r
esu
lts
p
r
o
d
u
ce
d
s
ev
en
f
ea
t
u
r
e
s
elec
tio
n
attr
ib
u
te
s
f
r
o
m
1
3
attr
ib
u
tes.
T
h
e
r
e
s
u
l
tin
g
attr
ib
u
te
f
u
r
t
h
er
c
lass
if
ied
alg
o
r
it
h
m
s
u
s
i
n
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
.
Use
o
f
s
tag
e
f
ea
t
u
r
e
s
elec
tio
n
w
i
th
AB
C
alg
o
r
it
h
m
is
ab
le
to
p
r
o
v
id
e
b
etter
s
y
s
te
m
p
er
f
o
r
m
a
n
ce
d
iag
n
o
s
is
.
Si
m
ilar
to
th
e
s
tu
d
y
co
n
d
u
cted
M
u
r
th
y
an
d
Me
e
n
a
k
s
h
i
[
4
]
,
i
n
t
h
e
s
t
u
d
y
b
e
f
o
r
e
it
is
c
lass
if
ied
b
y
t
h
e
m
u
lti
la
y
er
p
er
ce
p
tr
o
n
b
ac
k
p
r
o
p
ag
atio
n
,
p
r
ec
ed
ed
th
e
p
r
o
ce
s
s
o
f
f
ea
t
u
r
e
s
elec
tio
n
.
T
h
e
f
ea
tu
r
e
s
elec
tio
n
al
g
o
r
ith
m
u
s
ed
is
a
co
m
b
i
n
atio
n
o
f
Neu
r
o
-
f
u
zz
y
an
d
g
e
n
etic
al
g
o
r
ith
m
s
(
Neu
r
o
-
g
en
et
ic)
.
Featu
r
e
s
elec
tio
n
attr
ib
u
te
s
g
en
er
ate
s
8
o
f
1
3
attr
i
b
u
tes
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
Si
m
ilar
w
i
th
r
esear
ch
co
n
d
u
cted
b
y
Mo
k
ed
d
e
m
et.
al
[
5
]
,
th
e
f
ea
t
u
r
e
s
elec
tio
n
is
d
o
n
e
b
y
u
s
i
n
g
a
g
en
etic
al
g
o
r
it
h
m
,
b
u
t
th
e
cla
s
s
i
f
icatio
n
is
u
s
i
n
g
n
aiv
e
B
a
y
e
s
ia
n
.
T
h
e
r
esu
lts
o
f
f
ea
tu
r
e
s
elec
tio
n
w
h
ich
u
s
i
n
g
th
e
w
r
ap
p
er
ap
p
r
o
ac
h
,
o
b
tain
ed
7
attr
ib
u
tes
f
r
o
m
1
3
attr
ib
u
tes.
Gen
etic
alg
o
r
ith
m
s
ar
e
also
u
s
ed
f
o
r
f
ea
tu
r
e
s
elec
tio
n
in
r
esear
ch
Sa
n
t
h
an
a
m
a
n
d
E
p
h
zib
ah
[
6
]
,
b
u
t
th
e
g
en
e
tic
alg
o
r
it
h
m
co
m
b
in
ed
w
it
h
a
f
u
zz
y
i
n
f
er
e
n
ce
s
y
s
te
m
f
o
r
class
i
f
icatio
n
.
Featu
r
e
s
elec
tio
n
alg
o
r
ith
m
r
es
u
lts
w
i
th
t
h
o
s
e
o
b
tain
ed
7
attr
ib
u
tes o
f
co
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e.
Fu
r
t
h
er
s
tu
d
ies
ar
e
ass
o
ciate
d
w
it
h
th
e
f
ea
tu
r
e
s
elec
tio
n
w
a
s
p
r
o
p
o
s
ed
b
y
Mu
t
h
u
k
ar
u
p
p
a
n
&
E
r
[
7
]
in
w
h
ic
h
co
m
b
i
n
in
g
p
ar
ticle
s
w
ar
m
o
p
ti
m
izatio
n
(
P
SO)
,
an
d
class
if
ied
b
y
f
u
zz
y
i
n
f
er
e
n
c
e
s
y
s
te
m
(
FIS)
.
T
h
e
r
esu
lt
s
o
f
th
e
f
ea
t
u
r
e
s
el
ec
tio
n
attr
ib
u
te
o
b
tain
ed
9
o
f
1
3
attr
i
b
u
tes.
No
t
f
ar
to
th
e
s
t
u
d
y
Ma
r
ateb
&
Go
u
d
ar
zi
[
8
]
p
r
o
p
o
s
ed
a
s
y
s
te
m
o
f
d
iag
n
o
s
i
s
b
y
a
co
m
b
i
n
atio
n
o
f
m
u
ltip
le
lo
g
is
t
ic
r
eg
r
es
s
io
n
(
ML
R
)
w
i
th
Ne
u
r
o
-
f
u
zz
y
c
las
s
if
ier
.
T
h
e
s
y
s
te
m
i
s
ab
le
to
r
ed
u
ce
to
6
attr
ib
u
tes
f
r
o
m
2
0
attr
ib
u
tes.
I
n
ad
d
itio
n
to
u
s
i
n
g
m
u
ltip
le
lo
g
i
s
tic
r
eg
r
ess
io
n
,
t
h
e
s
t
u
d
y
also
test
ed
th
e
alg
o
r
it
h
m
s
eq
u
e
n
ce
f
ea
t
u
r
e
s
elec
tio
n
(
S
FS
)
.
SF
S
is
ab
le
to
r
ed
u
ce
to
9
.
Per
f
o
r
m
an
ce
attr
ib
u
tes
r
esu
lti
n
g
f
r
o
m
t
h
e
co
m
b
in
a
tio
n
o
f
S
FS
an
d
Neu
r
o
-
f
u
zz
y
class
i
f
ier
i
s
n
o
t
b
etter
t
h
a
n
t
h
e
co
m
b
i
n
atio
n
o
f
m
u
ltip
le
lo
g
is
tic
r
e
g
r
es
s
io
n
w
i
th
Neu
r
o
-
f
u
zz
y
clas
s
i
f
ier
.
A
r
j
en
ak
i
et.
al
[
9
]
,
p
r
o
p
o
s
ed
a
s
y
s
te
m
o
f
d
iag
n
o
s
is
b
y
co
n
s
i
d
er
in
g
th
e
co
s
t
r
eq
u
ir
ed
f
o
r
d
i
ag
n
o
s
is
.
T
h
e
s
tu
d
y
u
s
ed
a
g
en
et
ic
alg
o
r
it
h
m
to
d
o
th
e
f
ea
t
u
r
e
s
elec
t
io
n
w
it
h
co
n
s
id
er
atio
n
o
f
co
s
ts
,
a
n
d
class
i
f
ied
b
y
n
ai
v
e
B
ay
e
s
ian
.
T
h
e
r
esu
l
ts
o
f
f
ea
t
u
r
e
s
elec
tio
n
p
r
o
d
u
ce
8
attr
ib
u
tes
f
r
o
m
1
3
attr
ib
u
tes
ar
e
av
ailab
le.
T
h
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
is
ab
le
to
r
ed
u
ce
co
s
tl
y
a
ttrib
u
te
s
,
n
a
m
el
y
s
cin
ti
g
r
ap
h
y
a
n
d
f
lo
u
r
o
s
co
p
y
ex
a
m
in
at
io
n
.
R
ed
u
ctio
n
o
f
d
i
m
e
n
s
io
n
s
in
ad
d
itio
n
to
u
s
in
g
f
ea
t
u
r
e
s
el
ec
tio
n
,
ca
n
also
b
e
d
o
n
e
w
i
th
f
ea
t
u
r
e
ex
tr
ac
tio
n
.
O
n
e
f
ea
t
u
r
e
ex
tr
ac
t
io
n
alg
o
r
it
h
m
u
s
ed
is
t
h
e
p
r
in
c
ip
le
co
m
p
o
n
en
t a
n
al
y
s
i
s
(
P
C
A)
.
P
r
ev
io
u
s
s
t
u
d
ies
o
n
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
d
i
ag
n
o
s
is
s
y
s
te
m
h
as
b
ee
n
w
i
d
ely
u
s
ed
f
ea
t
u
r
e
e
x
tr
ac
tio
n
alg
o
r
ith
m
p
r
in
c
ip
le
co
m
p
o
n
e
n
t
a
n
al
y
s
i
s
.
Mo
d
el
s
tu
d
ies
co
n
d
u
cted
Z
h
a
n
g
et.
al
[
1
0
]
,
w
h
ic
h
co
m
b
i
n
e
P
C
A
w
it
h
S
VM
f
o
r
th
e
d
iag
n
o
s
i
s
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
P
C
A
f
ea
t
u
r
e
ex
tr
ac
t
io
n
b
y
g
en
er
at
in
g
9
attr
ib
u
tes
f
r
o
m
1
3
attr
ib
u
tes.
A
s
i
m
ilar
s
t
u
d
y
co
n
d
u
cted
B
h
u
v
an
e
s
a
w
ar
i
Am
m
a
N
G
[
1
1
]
,
o
n
l
y
t
h
e
clas
s
if
icatio
n
o
f
r
ese
ar
ch
u
s
i
n
g
ad
ap
tiv
e
n
eu
r
o
f
u
zz
y
in
f
er
e
n
ce
s
y
s
te
m
(
A
NFI
S).
I
n
t
h
e
s
t
u
d
y
w
er
e
ab
le
to
r
ed
u
ce
t
h
e
at
tr
ib
u
tes
to
7
attr
ib
u
te
s
o
f
t
h
e
1
3
attr
ib
u
tes o
f
co
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e.
Diag
n
o
s
is
s
y
s
te
m
m
o
d
el
b
y
c
o
m
b
i
n
i
n
g
a
f
ea
tu
r
e
s
elec
t
io
n
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
i
n
p
r
ev
io
u
s
s
t
u
d
ies,
g
en
er
all
y
d
o
n
o
t
p
a
y
a
tten
tio
n
to
th
e
ex
a
m
i
n
atio
n
s
ta
g
e
as
t
h
at
d
o
n
e
b
y
t
h
e
cli
n
icia
n
.
C
li
n
icia
n
s
p
er
f
o
r
m
t
h
e
ex
a
m
in
at
io
n
w
it
h
a
tier
ed
m
a
n
n
er
,
f
o
r
ea
ch
ad
d
itio
n
al
i
n
s
p
ec
tio
n
s
h
o
u
ld
p
r
o
v
id
e
ad
d
ed
v
alu
e
to
d
iag
n
o
s
e
v
alu
e
s
.
Mo
s
t
o
f
th
e
r
esear
ch
t
h
at
h
as
b
ee
n
d
o
n
e
f
ea
t
u
r
e
s
ele
ctio
n
p
r
o
ce
s
s
ca
r
r
ied
o
u
t
w
it
h
th
e
ass
u
m
p
tio
n
th
at
all
attr
ib
u
tes
h
a
v
e
av
ailab
le,
f
o
r
f
u
r
th
er
s
elec
t
io
n
p
r
o
ce
s
s
.
Un
d
er
th
ese
co
n
d
itio
n
s
,
t
h
i
s
s
tu
d
y
p
r
o
p
o
s
es
a
s
y
s
te
m
o
f
d
iag
n
o
s
is
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
b
y
u
s
in
g
th
e
co
m
b
in
at
io
n
o
f
tier
ed
m
u
lti
v
ar
iate
a
n
al
y
s
i
s
a
n
d
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
n
eu
r
al
n
et
w
o
r
k
(
ML
P
-
N
N)
.
T
ier
e
d
an
al
y
s
is
d
o
n
e
b
y
f
o
llo
w
i
n
g
th
e
s
tep
s
in
t
h
e
ex
a
m
in
at
io
n
co
n
d
u
cted
clin
ic
ian
,
n
a
m
el
y
t
h
at
th
e
ad
d
itio
n
o
f
th
e
e
x
a
m
in
at
io
n
s
h
o
u
ld
p
r
o
v
id
e
s
ig
n
if
ica
n
t
ad
d
itio
n
al
d
iag
n
o
s
tic
v
a
lu
e
a
n
d
co
s
t
is
r
elativ
e
l
y
ch
ea
p
er
.
I
n
th
i
s
s
t
u
d
y
,
u
s
i
n
g
t
h
e
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
co
m
m
o
n
l
y
u
s
ed
b
y
clin
ici
an
s
,
th
e
s
e
n
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
,
p
o
s
itiv
e
p
r
ed
ictio
n
v
al
u
e,
n
eg
a
tiv
e
p
r
ed
ictio
n
v
alu
e,
ac
cu
r
ac
y
a
n
d
ar
ea
u
n
d
er
th
e
c
u
r
v
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
S
ystem
o
f Tiered
Mu
lti
va
r
ia
te
A
n
a
lysi
s
a
n
d
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
fo
r
.
.
.
.
(
W
ih
a
r
to
)
1025
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
r
esear
ch
i
s
co
n
d
u
cted
u
s
i
n
g
th
e
d
ataset
C
le
v
ela
n
d
s
o
f
t
h
e
U
n
i
v
er
s
it
y
o
f
C
al
if
o
r
n
ia
I
r
v
in
e
(
UC
I
)
an
d
is
av
ailab
le
o
n
l
in
e
[
1
2
]
.
T
h
e
d
ataset
co
n
s
is
ts
o
f
1
3
attr
ib
u
tes
th
a
t
in
f
l
u
en
ce
t
h
e
in
c
i
d
en
ce
o
f
co
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e,
an
d
o
n
e
at
tr
ib
u
t
e
is
th
e
o
u
tp
u
t r
es
u
lt o
f
t
h
e
d
ia
g
n
o
s
is
.
T
h
e
d
atase
t a
ttrib
u
tes
ca
n
b
e
g
r
o
u
p
ed
in
to
s
ix
,
n
a
m
el
y
t
h
e
r
is
k
f
ac
to
r
s
,
s
y
m
p
to
m
s
,
r
est
E
C
G,
e
x
er
cise
E
C
G,
s
ci
n
ti
g
r
ap
h
y
an
d
Flo
u
r
o
s
co
p
h
y
.
T
h
e
r
is
k
f
ac
to
r
s
co
n
s
is
t
o
f
ag
e,
g
en
d
e
r
,
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
(
r
estb
p
s
)
,
f
asti
n
g
b
lo
o
d
s
u
g
er
(
f
b
s
)
an
d
ch
o
lest
er
o
l
(
ch
o
l)
.
Fu
r
th
er
E
C
G
b
o
th
r
est
an
d
ex
er
cise
co
n
s
is
ted
o
f
R
es
tin
g
E
C
G
(
r
estec
g
)
,
m
ax
i
m
u
m
h
ea
r
t
r
ate
A
c
h
ie
v
ed
(
th
alac
)
,
e
x
er
cise
i
n
d
u
ce
d
a
n
g
i
n
a
(
e
x
a
n
g
)
,
ST
d
ep
r
ess
io
n
i
n
d
u
ce
d
b
y
ex
er
c
is
e
r
elati
v
e
to
r
es
t
(
o
ld
p
ea
k
)
,
an
d
th
e
s
lo
p
e
o
f
th
e
ST
s
eg
m
e
n
t
f
o
r
p
ea
k
e
x
er
ci
s
e
(
s
lo
p
e)
.
W
h
ile
s
ci
n
ti
g
r
ap
h
y
to
d
eter
m
i
n
e
t
h
e
d
ef
ec
t
t
y
p
e
an
d
f
lo
u
r
o
s
co
p
y
t
o
d
etec
t
w
h
et
h
er
th
er
e
is
a
b
lo
ck
ag
e
o
f
b
lo
o
d
v
ess
els
t
h
at
ar
e
class
if
ied
i
n
to
s
in
g
le,
d
o
u
b
le,
tr
ip
p
le
v
ess
el
d
is
ea
s
e.
Diag
n
o
s
is
g
en
er
ate
d
ca
teg
o
r
ized
in
to
t
w
o
,
n
a
m
el
y
th
e
b
lo
ck
a
g
e
o
f
co
r
o
n
ar
y
ar
ter
ies
<5
0
%
(
h
ea
lt
h
y
)
an
d
b
lo
ck
a
g
e
o
f
b
lo
o
d
v
e
s
s
els>
5
0
%
(
s
ic
k
)
.
T
h
e
g
r
o
u
p
in
g
i
s
r
ein
f
o
r
ce
d
in
p
r
ev
io
u
s
r
esear
c
h
th
a
t
s
u
g
g
es
t
s
th
at,
b
lo
ck
a
g
e
o
f
co
r
o
n
ar
y
ar
ter
ies
<5
0
%
is
n
o
t
s
i
g
n
i
f
ica
n
t,
b
u
t
if
it
h
ad
>
5
0
%
o
r
7
0
%
it
h
ad
a
s
ig
n
i
f
ica
n
t
[
1
3
]
.
Data
s
et
to
taled
3
0
3
,
w
it
h
1
6
4
co
m
p
o
s
itio
n
s
o
b
s
tr
u
ct
i
o
n
<5
0
%
an
d
1
3
9
b
lo
ck
ag
es
o
f
>
5
0
%.
T
h
e
m
et
h
o
d
u
s
ed
i
n
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
d
iv
id
ed
i
n
to
s
e
v
er
al
p
h
ases
,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
T
h
e
f
ir
s
t
s
tep
is
to
p
er
f
o
r
m
t
h
e
ca
t
eg
o
r
izatio
n
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
attr
ib
u
te
s
t
h
at
h
a
v
e
co
n
ti
n
u
o
u
s
d
ata
i
n
to
d
is
cr
ete.
T
h
e
s
ec
o
n
d
s
ta
g
e
d
o
i
n
g
f
ea
t
u
r
e
s
elec
tio
n
,
is
d
i
v
id
e
d
in
to
f
o
u
r
s
ta
g
e
s
o
f
th
e
p
r
o
ce
s
s
.
T
h
e
f
ir
s
t
p
r
o
ce
s
s
b
iv
ar
iate
an
al
y
s
i
s
,
th
e
a
n
al
y
s
i
s
is
d
o
n
e
b
y
u
s
in
g
a
s
i
g
n
i
f
ica
n
ce
v
al
u
e
o
f
9
5
%.
A
t
tr
ib
u
te
w
it
h
a
p
-
v
al
u
e
<0
.
2
5
w
il
l
d
o
m
u
lt
iv
ar
iate
tier
ed
an
a
l
y
s
i
s
p
r
o
ce
s
s
.
T
h
e
s
ec
o
n
d
p
r
o
c
ess
is
a
ti
er
ed
m
u
lti
v
ar
iate
an
a
l
y
s
i
s
u
s
i
n
g
lo
g
is
ti
c
r
eg
r
ess
io
n
.
A
ttrib
u
te
th
e
r
esu
lt
s
o
f
t
h
e
lo
g
is
tic
r
eg
r
es
s
io
n
th
a
t
h
as a
p
-
v
al
u
e
<0
.
0
5
ca
n
b
e
u
s
ed
as a
cr
iter
io
n
i
n
th
e
d
ia
g
n
o
s
i
s
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
T
h
e
th
ir
d
p
r
o
ce
s
s
o
f
ca
lcu
lati
n
g
th
e
AUC
v
al
u
e
s
o
f
th
e
r
e
s
u
lt
s
o
f
lo
g
is
tic
r
e
g
r
ess
io
n
.
T
h
e
n
ex
t
s
tep
,
d
o
an
y
r
ec
u
r
r
e
n
ce
o
f
t
h
e
f
ir
s
t
p
r
o
ce
s
s
.
A
ll
t
h
ese
p
r
o
ce
s
s
es
ar
e
ca
r
r
ied
o
u
t
w
it
h
a
co
m
b
in
a
tio
n
o
f
r
is
k
f
ac
to
r
s
,
s
y
m
p
to
m
s
,
r
e
s
t
E
C
G
,
ex
er
cise
E
C
G,
s
ci
n
ti
g
r
ap
h
y
an
d
f
lo
u
r
o
s
co
p
y
.
Hav
i
n
g
d
o
n
e
all
th
e
co
m
b
i
n
at
io
n
s
,
t
h
e
f
o
u
r
t
h
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
i
n
ter
p
r
etatio
n
AUC
v
a
lu
es.
I
n
ter
p
r
etatio
n
is
d
o
n
e
u
s
in
g
a
s
tati
s
tical
ap
p
r
o
ac
h
an
d
cli
n
ical
co
n
s
id
er
a
tio
n
s
.
I
n
ter
p
r
etatio
n
AUC
v
al
u
es
w
i
t
h
s
tatis
t
ical
ap
p
r
o
ac
h
is
to
class
i
f
y
th
e
AU
C
v
al
u
e
s
.
T
h
e
class
i
f
icatio
n
is
b
ein
g
v
er
y
w
ea
k
at
5
0
%
-
6
0
%,
w
ea
k
er
at
6
0
%
-
7
0
%,
m
ed
iu
m
at
7
0
%
-
8
0
%,
g
o
o
d
at
8
0
%
-
9
0
% a
n
d
v
er
y
g
o
o
d
at
9
0
%
-
1
0
0
% [
1
4
]
.
Use c
lin
ical
j
u
d
g
m
e
n
t
is
th
e
co
s
t o
f
ea
c
h
in
s
p
ec
tio
n
attr
ib
u
te
g
r
o
u
p
.
B
i
v
a
r
i
a
t
e
A
n
a
l
y
s
i
s
M
L
P
-
N
N
L
o
g
i
s
t
i
c
R
e
g
r
e
s
s
i
o
n
E
n
d
E
v
a
l
u
a
t
i
o
n
C
l
a
s
s
i
f
i
e
r
S
p
l
i
t
e
t
h
e
D
a
t
a
T
e
s
t
i
n
g
D
a
t
a
T
r
a
i
n
i
n
g
D
a
t
a
D
a
t
a
s
e
t
U
C
I
S
t
a
r
t
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
I
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
A
U
C
b
a
s
e
d
o
n
s
t
a
t
i
s
t
i
c
s
a
n
d
c
l
i
n
i
c
a
l
C
a
t
e
g
o
r
i
z
i
n
g
D
a
t
a
C
a
l
c
u
l
a
t
i
o
n
o
f
A
U
C
L
i
s
t
o
f
A
U
C
A
d
d
A
t
t
r
i
b
u
t
e
A
l
l
t
i
e
r
e
d
?
N
o
Y
e
s
Fig
u
r
e
1
.
T
h
e
Pro
p
o
s
ed
s
y
s
te
m
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
2
,
A
p
r
il 2
0
1
7
:
10
2
3
–
10
3
1
1026
T
h
e
th
ir
d
s
tag
e
is
th
e
p
r
o
ce
s
s
o
f
clas
s
if
icatio
n
b
y
u
s
i
n
g
m
u
lt
i
-
la
y
er
p
er
ce
p
tr
o
n
n
eu
r
al
n
et
w
o
r
k
(
ML
P
-
NN)
.
A
t
tr
ib
u
te
t
h
at
i
s
i
n
t
h
e
p
r
o
ce
s
s
s
tag
e
s
ar
e
attr
ib
u
tes
r
e
s
u
l
t
p
r
ev
io
u
s
f
ea
t
u
r
e
s
el
ec
tio
n
s
ta
g
e.
M
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
n
e
u
r
al
n
et
w
o
k
tr
ai
n
ed
u
s
i
n
g
b
a
ck
p
r
o
p
ag
ati
o
n
g
r
ad
ie
n
t
d
esce
n
t
al
g
o
r
ith
m
w
ith
m
o
m
e
n
t
u
m
.
T
h
e
alg
o
r
ith
m
i
s
a
d
e
v
elo
p
m
en
t
o
f
b
ac
k
p
r
o
p
ag
atio
n
g
r
ad
i
en
t
d
esce
n
t
al
g
o
r
ith
m
,
is
to
p
er
f
o
r
m
u
p
d
ates
o
n
ch
an
g
es
in
w
e
ig
h
t.
T
h
e
ad
d
itio
n
o
f
v
ar
iab
le
w
ei
g
h
ts
m
o
m
e
n
tu
m
o
f
ch
a
n
g
e
ca
n
ac
ce
ler
ate
th
e
co
n
v
er
g
e
n
ce
i
n
tr
ain
i
n
g
,
co
m
p
ar
ed
g
r
ad
ien
t
d
escen
t
[
1
5
]
,
[
1
6
]
.
T
h
e
f
o
llo
w
in
g
eq
u
atio
n
(
1
)
an
d
(
2
)
,
a
r
e
w
e
ig
h
t
ch
a
n
g
es
d
u
r
i
n
g
tr
ain
i
n
g
:
(
)
(
)
[
(
)
(
)
]
(
1
)
an
d
(
)
(
)
[
(
)
(
)
]
(
2
)
w
h
er
e
μ
is
t
h
e
m
o
m
en
t
u
m
p
ar
a
m
eter
,
w
h
ich
h
a
s
a
v
alu
e
b
etw
ee
n
0
-
1
,
w
is
t
h
e
w
ei
g
h
t
o
f
t
h
e
i
n
p
u
t
la
y
er
a
n
d
v
is
th
e
w
ei
g
h
t o
f
t
h
e
h
id
d
en
la
y
er
.
T
h
e
f
o
u
r
th
s
ta
g
e,
to
ev
al
u
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
t
e
m
.
S
y
s
te
m
p
er
f
o
r
m
a
n
ce
m
e
asu
r
ed
b
y
r
ef
er
en
ce
d
iag
n
o
s
i
s
m
a
tr
ic
co
n
f
u
s
io
n
,
as
s
h
o
w
n
i
n
T
ab
le
1
,
th
e
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
u
s
e
d
ar
e
1.
W
h
en
a
cli
n
ician
w
ill
d
o
an
e
x
a
m
in
at
io
n
,
r
aised
t
w
o
q
u
es
ti
o
n
s
,
w
h
ic
h
i
f
p
o
s
iti
v
e
p
atie
n
ts
s
u
f
f
er
in
g
f
r
o
m
a
d
is
ea
s
e,
h
o
w
th
e
ab
il
it
y
d
ia
g
n
o
s
is
s
y
s
te
m
p
r
o
d
u
ce
s
p
o
s
iti
v
e
r
es
u
lts
?.
T
h
e
q
u
esti
o
n
r
elat
es
to
th
e
v
al
u
e
o
f
s
e
n
s
i
tiv
i
t
y
.
Seco
n
d
l
y
,
i
f
t
h
e
p
atien
t
i
s
n
o
t
s
u
f
f
er
i
n
g
f
r
o
m
a
d
i
s
ea
s
e,
w
h
at
i
s
t
h
e
d
ia
g
n
o
s
is
s
y
s
te
m
's
ab
ilit
y
to
g
en
er
ate
n
eg
at
iv
e
r
e
s
u
lt
s
?
T
h
e
q
u
esti
o
n
r
elate
s
to
th
e
v
al
u
e
o
f
s
p
ec
if
ic
it
y
.
B
o
th
,
th
e
eq
u
atio
n
(
3
)
an
d
(
4
)
,
ar
e
th
e
v
alu
e
o
f
s
e
n
s
it
iv
i
t
y
a
n
d
s
p
ec
if
ic
it
y
ca
n
b
e
f
o
r
m
u
lated
as f
o
llo
w
s
:
(
3
)
(
4
)
2.
W
h
en
a
cli
n
icia
n
s
h
a
v
e
o
b
tain
ed
th
e
d
iag
n
o
s
i
s
is
p
o
s
iti
v
e,
th
en
t
h
e
q
u
e
s
tio
n
ar
is
es,
h
o
w
m
u
c
h
p
o
s
i
tiv
e
r
esu
lt
s
r
ea
ll
y
p
o
s
iti
v
e.
T
h
is
is
r
elate
d
to
P
o
s
itiv
e
P
r
ed
ictio
n
Valu
e
(
P
P
V)
.
W
h
er
ea
s
if
y
o
u
g
et
a
d
iag
n
o
s
is
r
esu
lt
i
s
n
eg
ati
v
e,
t
h
en
h
o
w
m
u
ch
n
e
g
ati
v
e
r
esu
lt
r
ea
ll
y
n
eg
a
tiv
e.
I
t
i
s
as
s
o
ciate
d
with
a
Ne
g
ati
v
e
P
r
ed
ictio
n
Valu
e
(
NP
V)
.
B
o
t
h
o
f
t
h
ese
p
ar
a
m
eter
s
ca
n
b
e
f
o
r
m
u
lated
at
t
h
e
eq
u
atio
n
(
5
)
an
d
(
6
)
w
h
ic
h
s
h
o
w
n
a
s
f
o
llo
w
s
:
(
)
(
5
)
(
)
(
6
)
3.
T
h
e
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
o
f
ar
ea
u
n
d
er
t
h
e
c
u
r
v
e
(
A
U
C
)
,
th
e
v
al
u
e
o
f
th
i
s
p
ar
a
m
eter
in
d
icate
s
i
f
t
h
er
e
ar
e
a
n
u
m
b
er
o
f
p
atien
t
s
w
h
o
ca
r
r
ied
th
e
d
iag
n
o
s
i
s
u
s
i
n
g
th
e
s
y
s
te
m
,
t
h
e
n
h
o
w
m
a
n
y
p
atien
ts
ca
n
b
e
d
iag
n
o
s
ed
co
r
r
ec
tl
y
b
y
t
h
e
s
y
s
te
m
,
s
o
th
e
AUC i
s
th
e
p
er
ce
n
tag
e
o
f
p
atie
n
ts
w
h
o
ar
e
d
iag
n
o
s
ed
co
r
r
ec
tly
.
4.
Th
e
p
er
f
o
r
m
an
ce
p
ar
a
m
eter
s
o
f
ac
cu
r
ac
y
w
h
ic
h
ca
n
b
e
f
o
r
m
u
lated
at
th
e
eq
u
a
tio
n
(
7
)
as f
o
llo
w
s
:
(
7
)
T
ab
le
1
.
C
o
n
f
u
s
io
n
Ma
tr
ic
s
A
c
t
u
a
l
C
l
a
ss
P
r
e
d
i
c
t
i
o
n
C
l
a
ss
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
T
P
(
Tr
u
e
P
o
si
t
i
f
)
F
P
(
F
a
l
s
e
P
o
si
t
i
v
e
)
N
e
g
a
t
i
v
e
F
N
(
F
a
l
s
e
N
e
g
a
t
i
v
e
)
T
N
(
Tr
u
e
N
e
g
a
t
i
v
e
)
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
th
i
s
s
t
u
d
y
p
r
o
p
o
s
es
a
m
o
d
el
o
f
h
y
b
r
id
s
y
s
te
m
s
f
o
r
th
e
d
iag
n
o
s
i
s
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
T
h
e
s
y
s
te
m
co
m
b
i
n
es
t
h
e
t
w
o
p
r
o
ce
s
s
es,
n
a
m
el
y
,
tier
ed
m
u
lti
v
ar
iate
an
al
y
s
i
s
a
n
d
m
u
lti
-
la
y
e
r
p
er
ce
p
tr
o
n
n
eu
r
al
n
et
w
o
r
k
(
M
L
P
-
NN)
.
T
ier
ed
m
u
lti
v
ar
iate
an
a
l
y
s
is
p
r
o
ce
s
s
u
s
i
n
g
lo
g
is
t
ic
r
eg
r
es
s
io
n
al
g
o
r
ith
m
,
a
p
r
o
ce
s
s
ai
m
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
S
ystem
o
f Tiered
Mu
lti
va
r
ia
te
A
n
a
lysi
s
a
n
d
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
fo
r
.
.
.
.
(
W
ih
a
r
to
)
1027
at
o
b
tain
in
g
s
tr
etc
h
er
attr
ib
u
t
e
th
at
s
i
g
n
i
f
ican
tl
y
a
f
f
ec
t
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
T
h
e
p
r
o
ce
s
s
is
ca
lled
t
h
e
p
r
o
ce
s
s
o
f
f
ea
t
u
r
e
s
elec
tio
n
.
T
ier
e
d
m
eth
o
d
i
s
a
r
e
f
lectio
n
o
f
t
h
e
s
ta
g
e
s
i
n
ac
q
u
ir
i
n
g
attr
ib
u
te,
as
is
d
o
n
e
b
y
th
e
cli
n
icia
n
.
T
h
e
A
UC
v
al
u
e
ca
lcu
latio
n
is
d
o
n
e
f
o
r
ea
ch
le
v
el
i
n
o
r
d
er
to
d
eter
m
i
n
e
t
h
e
ef
f
ec
t
o
f
ea
c
h
le
v
el
o
f
ex
a
m
in
at
io
n
.
T
h
e
ca
lcu
lat
io
n
o
f
A
U
C
v
al
u
e
s
f
o
r
ea
ch
lev
el
b
y
u
s
i
n
g
m
u
lti
v
ar
iate
lo
g
is
tic
r
eg
r
e
s
s
io
n
an
al
y
s
is
.
An
al
y
s
i
s
d
o
n
e
u
s
in
g
a
9
5
% c
o
n
f
id
en
ce
le
v
el.
T
h
e
ca
lcu
latio
n
r
es
u
lt
tier
ed
a
n
al
y
s
i
s
w
it
h
lo
g
i
s
tic
r
e
g
r
ess
io
n
m
u
tlti
v
ar
iate
a
s
s
h
o
w
n
i
n
T
ab
le
2
.
T
h
e
tab
le
s
h
o
w
s
AUC
v
al
u
es
b
ased
o
n
a
co
m
b
i
n
atio
n
o
f
attr
ib
u
t
e
g
r
o
u
p
s
.
I
n
ter
p
r
etatio
n
o
f
t
h
e
A
U
C
v
a
lu
e
s
d
o
es
w
it
h
th
e
t
w
o
ap
p
r
o
ac
h
es,
n
a
m
el
y
s
tatis
ticall
y
a
n
d
cli
n
icall
y
ap
p
r
o
ac
h
.
T
h
e
u
s
e
o
f
th
e
t
w
o
ap
p
r
o
ac
h
es
in
o
r
d
er
to
o
b
tain
a
lar
g
e
s
e
lectio
n
o
f
attr
ib
u
te
co
m
b
in
at
io
n
s
t
h
at
p
r
o
d
u
ce
o
p
tim
al
A
U
C
.
T
h
e
ad
d
itio
n
o
f
t
h
e
r
i
s
k
f
ac
to
r
s
to
attr
ib
u
te
s
y
m
p
to
m
s
to
th
e
lev
el
-
2
p
r
o
d
u
c
ed
th
e
AUC
v
al
u
e
s
ch
a
n
g
e
v
er
y
s
i
g
n
i
f
ican
tl
y
f
r
o
m
7
2
.
2
%
to
8
5
.
0
%.
T
h
e
r
esu
lts
w
it
h
s
ta
tis
tical
co
n
s
id
er
atio
n
s
,
s
u
g
g
es
ts
th
e
ad
d
itio
n
o
f
th
e
s
e
attr
ib
u
tes
ar
e
v
er
y
g
o
o
d
,
an
d
w
h
e
n
s
ee
n
f
r
o
m
co
s
t
co
n
s
id
er
atio
n
s
,
e
x
a
m
in
at
io
n
o
f
s
y
m
p
to
m
s
is
r
elat
iv
el
y
s
i
m
p
le
a
n
d
n
o
t
co
s
tl
y
.
T
h
e
n
ex
t
le
v
el
i
s
th
e
ad
d
itio
n
o
f
r
est
E
C
G
e
x
a
m
in
at
io
n
,
A
UC
v
alu
es
g
en
er
ated
r
elati
v
el
y
l
ittl
e
in
cr
ea
s
e,
n
a
m
el
y
0
.
4
%.
A
s
f
o
r
th
e
ad
d
itio
n
o
f
e
x
er
cise
E
C
G
i
s
ab
le
to
g
iv
e
r
is
e
A
U
C
v
a
lu
e
o
f
4
.
1
%
(
8
9
.
1
%).
T
h
is
m
ea
n
s
t
h
at
ch
ec
k
s
t
h
e
E
C
G
p
r
o
v
id
e
s
ad
d
itio
n
al
A
U
C
v
al
u
es
ar
e
r
elativ
el
y
h
ig
h
,
w
h
en
th
e
e
x
a
m
i
n
ati
o
n
o
f
a
n
E
C
G
d
o
n
e
d
u
r
in
g
ex
er
ci
s
e.
R
e
f
er
s
to
a
co
m
b
i
n
atio
n
o
f
r
is
k
f
ac
to
r
s
,
s
y
m
p
to
m
s
an
d
e
x
er
cise
E
C
G,
s
ci
n
ti
g
r
ap
h
y
ex
a
m
in
at
io
n
ad
d
itio
n
,
th
e
AUC
w
i
ll
p
r
o
v
id
e
ad
d
itio
n
al
v
alu
e
b
y
1
.
1
%.
Un
f
o
r
t
u
n
atel
y
,
th
e
v
al
u
e
ad
d
itio
n
s
h
o
u
ld
r
eq
u
ir
e
r
elativ
el
y
ex
p
e
n
s
i
v
e
co
s
t
o
f
in
s
p
ec
tio
n
[
1
7
]
.
So
tak
in
g
in
to
ac
co
u
n
t
th
e
s
ta
tis
tical
an
d
clin
ical
ap
p
r
o
ac
h
es,
th
e
ad
d
itio
n
o
f
s
u
ch
c
h
ec
k
s
d
o
n
o
t
p
r
o
v
id
e
o
p
ti
m
al
d
iag
n
o
s
tic
v
al
u
e,
w
h
e
n
it
is
o
n
l
y
f
o
r
th
e
d
iag
n
o
s
i
s
s
ta
g
e.
T
h
in
g
s
to
d
o
s
i
m
ilar
if
i
n
ad
d
itio
n
f
lo
u
r
o
s
c
o
p
y
e
x
a
m
in
at
io
n
,
o
r
a
co
m
b
i
n
atio
n
o
f
b
o
th
d
o
es
n
o
t
p
r
o
v
id
e
a
s
ig
n
if
ican
t
i
n
cr
e
ase.
R
ef
er
r
i
n
g
to
t
h
e
an
al
y
s
is
b
y
co
n
s
id
er
in
g
n
e
w
in
ter
p
r
etatio
n
s
A
U
C
v
a
lu
e
s
,
th
e
s
tat
is
tical
ap
p
r
o
ac
h
an
d
cl
in
icia
n
s
,
t
h
e
attr
ib
u
te
s
f
o
r
d
iag
n
o
s
is
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
e
ase
ca
n
b
e
r
ed
u
ce
d
,
w
h
ic
h
is
as
s
h
o
w
n
in
T
ab
le
3
.
T
ab
le
2
.
T
ier
e
d
Mu
ltiv
ar
iate
An
al
y
s
i
s
w
it
h
L
o
g
is
tic
R
e
g
r
es
s
io
n
T
i
e
r
e
d
T
e
st
R
e
su
l
t
V
a
r
i
a
b
l
e
s
A
U
C
p
-
v
a
l
u
e
p
-
v
a
l
u
e
9
5
%
C
o
n
f
i
d
e
n
c
e
I
n
t
e
r
v
a
l
L
o
w
e
r
B
o
u
n
d
U
p
p
e
r
B
o
u
n
d
1
R
i
s
k
,
7
2
2
,
0
0
0
,
6
6
5
,
7
7
9
2
R
i
s
k
+
S
y
mt
o
ms
,
8
5
0
,
0
0
0
,
8
0
7
,
8
9
3
3
R
i
s
k
+
S
y
mt
o
ms+R
e
st
EC
G
,
8
5
4
,
0
0
0
,
8
1
2
,
8
9
6
4
R
i
s
k
+
S
y
mt
o
ms+
Ex
e
r
c
i
se
E
C
G
,
8
9
1
,
0
0
0
,
8
5
6
,
9
2
7
5
R
i
s
k
+
S
y
mt
o
ms+R
e
st
EC
G
+
Ex
e
r
c
i
se
EC
G
,
8
9
3
,
0
0
0
,
8
5
8
,
9
2
8
6
R
i
s
k
+
S
y
mt
o
ms+
Ex
e
r
c
i
se
E
C
G
+
S
c
i
n
t
i
g
r
a
p
h
y
,
9
0
2
,
0
0
0
,
8
6
8
,
9
3
6
7
R
i
s
k
+
S
y
mt
o
ms+
Ex
e
r
c
i
se
E
C
G
+
F
l
o
u
r
o
sco
p
h
y
,
9
0
7
,
0
0
0
,
8
7
5
,
9
4
0
8
R
i
s
k
+
S
y
mt
o
ms+
Ex
e
r
c
i
se
E
C
G
+
S
c
i
n
t
i
g
r
a
p
h
y
+
F
l
o
u
r
o
sco
p
h
y
,
9
1
5
,
0
0
0
,
8
8
3
,
9
4
6
T
ab
le
3
.
L
is
t o
f
A
ttrib
u
te
C
o
r
o
n
ar
y
Hea
r
t D
i
s
ea
s
e
No
A
t
t
r
i
b
u
t
e
G
r
o
u
p
S
e
l
e
c
t
e
d
1
A
g
e
R
i
s
k
F
a
c
t
o
r
2
G
e
n
d
e
r
R
i
s
k
F
a
c
t
o
r
3
C
h
e
st
P
a
i
n
T
y
p
e
S
y
mp
t
o
ms
4
S
y
st
o
l
i
c
B
l
o
o
d
P
r
e
ssu
r
e
(
mm
H
g
)
R
i
s
k
F
a
c
t
o
r
5
C
h
o
l
e
st
e
r
o
l
(
mg
/
d
l
)
R
i
s
k
F
a
c
t
o
r
6
F
a
st
i
n
g
B
l
o
o
d
S
u
g
a
r
R
i
s
k
F
a
c
t
o
r
7
R
e
st
i
n
g
EC
G
R
e
st
E
C
G
8
M
a
x
i
m
u
m
h
e
a
r
t
r
a
t
e
a
c
h
i
e
v
e
d
Ex
e
r
c
i
se
EC
G
9
Ex
e
r
c
i
se
i
n
d
u
c
e
d
a
n
g
i
n
a
Ex
e
r
c
i
se
EC
G
10
S
T
D
e
p
r
e
ssi
o
n
i
n
d
u
c
e
d
b
y
e
x
e
r
c
i
se
r
e
l
a
t
i
v
e
t
o
r
e
st
Ex
e
r
c
i
se
EC
G
11
T
h
e
sl
o
p
e
o
f
t
h
e
S
T
se
g
m
e
n
t
f
o
r
p
e
a
k
e
x
e
r
c
i
se
Ex
e
r
c
i
se
EC
G
12
N
u
mb
e
r
o
f
M
a
j
o
r
v
e
sse
l
c
o
l
o
r
e
d
b
y
F
l
o
u
r
o
sco
p
h
y
F
l
o
r
o
sco
p
y
13
D
e
f
e
c
t
T
y
p
e
b
y
S
c
i
n
t
i
g
r
a
p
h
y
S
c
i
n
t
i
g
r
a
p
h
y
A
ttrib
u
tes
r
esu
lted
in
t
h
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
,
w
ill
n
o
w
b
e
en
ter
ed
in
th
e
clas
s
if
icatio
n
p
r
o
ce
s
s
.
T
h
e
class
i
f
icatio
n
p
r
o
ce
s
s
is
d
o
n
e
u
s
in
g
ML
P
-
NN
al
g
o
r
it
h
m
.
T
h
e
co
m
p
o
s
i
tio
n
o
f
th
e
d
ata
u
s
ed
is
7
0
%
to
3
0
%
f
o
r
tr
ain
in
g
an
d
test
in
g
,
t
h
e
d
iv
is
io
n
o
f
th
e
co
m
p
o
s
itio
n
d
o
n
e
r
an
d
o
m
l
y
.
T
h
e
ML
P
-
N
N
ar
ch
itectu
r
e
u
s
ed
co
n
s
is
ted
o
f
s
e
v
er
al
p
ar
ts
,
th
e
f
ir
s
t
p
ar
t
co
m
p
r
is
e
s
7
in
p
u
ts
la
y
er
an
d
2
1
n
e
u
r
o
n
s
.
T
h
e
s
ec
o
n
d
p
ar
t,
a
m
o
u
n
ti
n
g
2
h
id
d
en
la
y
er
s
,
ea
ch
h
id
d
en
l
a
y
er
n
e
u
r
o
n
h
a
v
i
n
g
8
an
d
6
n
e
u
r
o
n
s
w
i
th
s
ig
m
o
id
ac
tiv
a
tio
n
f
u
n
ctio
n
.
T
h
e
th
ir
d
p
ar
t
co
n
s
is
ts
o
f
a
s
ec
o
n
d
la
y
e
r
o
u
tp
u
t
n
e
u
r
o
n
w
i
th
s
ig
m
o
id
ac
tiv
atio
n
f
u
n
ctio
n
.
B
ased
o
n
test
r
e
s
u
lt
s
s
h
o
w
th
at,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
r
o
v
id
es
t
h
e
p
er
f
o
r
m
a
n
ce
to
v
alu
e
s
en
s
iti
v
it
y
8
4
.
8
0
%,
s
p
ec
if
ici
t
y
8
8
.
2
0
%,
p
o
s
itiv
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
2
,
A
p
r
il 2
0
1
7
:
10
2
3
–
10
3
1
1028
p
r
ed
ictio
n
v
alu
e
(
P
P
V)
9
0
.
0
3
%,
n
e
g
ati
v
e
p
r
ed
ictio
n
v
al
u
e
(
NP
V)
8
1
.
8
0
%,
ac
cu
r
ac
y
8
6
,
3
% a
n
d
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
A
U
C
)
o
f
9
2
.
1
%.
S
y
s
te
m
p
er
f
o
r
m
an
ce
f
o
r
A
UC
p
ar
am
eter
s
ca
n
b
e
r
ep
r
esen
te
d
in
a
g
r
ap
h
ic
w
h
ic
h
y
-
a
x
is
i
s
s
en
s
iti
v
it
y
an
d
x
-
a
x
is
as
s
p
ec
i
f
icit
y
,
as
s
h
o
w
n
in
Fi
g
u
r
e
2
.
R
e
f
er
r
in
g
t
o
th
e
s
tati
s
tical
i
n
ter
p
r
etatio
n
,
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
it
h
A
U
C
v
al
u
es
o
f
9
2
.
1
%,
in
clu
d
in
g
i
n
th
e
v
er
y
g
o
o
d
ca
teg
o
r
y
(
9
0
%
-
1
0
0
%).
Fig
u
r
e
2
.
Gr
ap
h
ic
o
f
AUC
I
n
th
i
s
s
t
u
d
y
ca
n
b
e
s
h
o
w
n
t
h
e
p
er
ce
n
tag
e
o
f
t
h
e
d
eg
r
ee
o
f
u
r
g
e
n
c
y
o
f
ea
c
h
attr
ib
u
te
w
h
ic
h
h
as
b
ee
n
r
ed
u
ce
d
as s
h
o
w
n
i
n
T
ab
le
4
.
T
h
e
o
r
d
er
o
f
th
e
i
m
p
o
r
tan
ce
le
v
el
o
f
t
h
e
h
i
g
h
e
s
t a
ttrib
u
te
is
a
t
y
p
e
o
f
c
h
est
p
ain
,
ST
d
e
p
r
ess
io
n
in
d
u
ce
d
b
y
ex
e
r
cise r
elativ
e
to
r
est,
t
h
e
s
lo
p
e
o
f
th
e
ST
s
eg
m
e
n
t
f
o
r
p
ea
k
ex
er
cise,
g
en
d
er
,
ag
e,
m
ax
i
m
u
m
h
ea
r
t
r
ate
a
n
d
ex
e
r
cise
-
i
n
d
u
ce
d
a
n
g
in
a
ac
h
ie
v
e
d
.
C
h
es
t
p
ain
is
a
s
y
m
p
to
m
o
f
th
a
t
t
y
p
e
is
v
er
y
i
m
p
o
r
tan
t
a
n
d
t
y
p
ical
a
s
a
s
i
g
n
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
C
h
est
p
ai
n
t
y
p
e
co
n
s
i
s
ts
o
f
t
y
p
i
ca
l
an
g
in
a,
at
y
p
ical
an
g
i
n
a,
n
o
n
-
a
n
g
in
a
p
ai
n
an
d
as
y
m
p
to
m
at
ic.
T
h
is
t
y
p
e
ca
n
b
e
id
en
tif
ied
f
r
o
m
t
h
r
ee
th
i
n
g
s
:
th
e
d
is
co
m
f
o
r
t
o
r
p
ain
is
f
elt
b
eh
i
n
d
th
e
b
r
ea
s
t
b
o
n
e
w
ith
th
e
q
u
alit
y
a
n
d
le
n
g
t
h
o
f
a
t
y
p
ical,
p
ain
tr
ig
g
e
r
ed
b
y
ac
ti
v
it
y
o
r
e
m
o
tio
n
al
s
tr
es
s
a
n
d
p
ain
s
u
b
s
id
e
w
h
e
n
a
b
r
ea
k
o
r
ar
e
g
i
v
e
n
n
itro
g
l
y
ce
r
i
n
[
1
8
]
.
T
h
e
n
ex
t
attr
ib
u
te
th
at
h
a
s
a
p
er
ce
n
tag
e
o
f
8
0
%
ab
o
v
e
th
e
lev
el
o
f
u
r
g
en
c
y
is
w
h
et
h
er
o
r
n
o
t
th
er
e
eith
er
w
h
e
n
r
esti
n
g
ST
d
ep
r
ess
io
n
,
ex
er
cise
a
n
d
g
en
d
er
r
i
s
k
f
ac
to
r
s
.
ST
d
ep
r
ess
io
n
w
it
h
ce
r
tain
co
n
d
itio
n
s
i
s
t
h
e
d
escr
ip
tio
n
t
h
at
t
h
e
ce
lls
o
f
th
e
m
y
o
ca
r
d
iu
m
b
eg
a
n
to
lack
o
f
o
x
y
g
en
.
F
u
r
th
er
attr
ib
u
tes
g
e
n
d
er
,
f
o
r
m
en
h
av
e
a
g
r
ea
ter
r
is
k
o
f
h
ea
r
t
attac
k
an
d
h
ap
p
en
ed
ea
r
lier
th
an
i
n
w
o
m
en
[
1
9
]
,
w
h
ile
m
o
r
b
id
it
y
in
m
e
n
,
t
w
o
ti
m
es
g
r
ea
ter
th
an
w
o
m
e
n
,
an
d
t
h
is
i
s
th
e
ca
s
e
a
l
m
o
s
t
1
0
y
ea
r
s
ea
r
li
er
in
m
en
th
a
n
w
o
m
e
n
[
2
0
]
.
T
h
e
r
is
k
f
ac
to
r
s
h
a
v
e
p
er
ce
n
ta
g
e
lev
els
o
f
u
r
g
e
n
c
y
ag
e
ab
o
v
e
6
0
%,
lo
w
er
t
h
an
g
en
d
er
.
Ag
e
p
er
s
o
n
m
o
r
e
s
u
s
ce
p
tib
le
to
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e,
b
u
t
r
ar
el
y
ca
u
s
e
s
er
io
u
s
d
is
ea
s
e
b
e
f
o
r
e
4
0
y
ea
r
s
an
d
in
cr
ea
s
ed
5
-
f
o
ld
at
th
e
ag
e
o
f
4
0
-
6
0
y
ea
r
s
[
2
1
]
.
A
ttri
b
u
tes
th
a
t
h
a
v
e
th
e
lo
w
es
t
p
er
ce
n
tag
e
o
f
7
attr
i
b
u
te
is
ex
er
cise
-
i
n
d
u
ce
d
an
g
in
a,
w
h
ic
h
is
4
1
.
9
%
o
r
b
el
o
w
5
0
%.
T
h
e
lo
w
p
er
ce
n
tag
e
o
f
th
e
d
e
g
r
ee
o
f
u
r
g
en
c
y
o
f
th
e
s
y
s
te
m
d
iag
n
o
s
i
s
is
p
o
s
s
ib
le
o
n
l
y
attr
ib
u
ted
d
es
cr
ib
es
th
e
p
r
esen
ce
o
r
ab
s
en
ce
o
f
in
d
u
ce
d
an
g
i
n
a
i
n
th
e
e
x
a
m
in
a
tio
n
.
T
ab
le
4
.
I
n
d
ep
en
d
en
t a
ttrib
u
te
i
m
p
o
r
tan
ce
N
o
A
t
t
r
i
b
u
t
e
I
mp
o
r
t
a
n
c
e
N
o
r
mal
i
z
e
d
I
mp
o
r
t
a
n
c
e
1
0
,
1
1
9
6
1
,
1
%
2
0
,
1
6
3
8
3
,
9
%
3
0
,
1
9
4
1
0
0
,
0
%
8
0
,
1
0
2
5
2
,
7
%
9
0
,
0
8
1
4
1
,
9
%
10
0
,
1
7
6
9
0
,
4
%
11
0
,
1
6
4
8
4
,
7
%
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
w
e
co
m
p
ar
e
w
it
h
p
r
ev
io
u
s
s
tu
d
ie
s
u
s
i
n
g
s
e
v
er
al
p
ar
a
m
e
ter
s
s
u
ch
as,
th
e
ac
cu
r
ac
y
a
n
d
th
e
n
u
m
b
er
o
f
a
ttrib
u
tes.
C
o
m
p
ar
is
o
n
s
ar
e
g
r
o
u
p
ed
in
to
t
w
o
,
n
a
m
el
y
,
t
h
e
c
o
m
p
ar
is
o
n
w
it
h
t
h
e
r
esear
ch
g
r
o
u
p
th
at
h
a
s
lo
w
er
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
,
an
d
h
ig
h
er
t
h
an
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
h
e
s
tu
d
ies
w
il
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
S
ystem
o
f Tiered
Mu
lti
va
r
ia
te
A
n
a
lysi
s
a
n
d
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
fo
r
.
.
.
.
(
W
ih
a
r
to
)
1029
b
e
co
m
p
ar
ed
as
s
h
o
w
n
in
T
ab
le
5
.
T
h
e
s
tu
d
y
w
a
s
co
n
d
u
cted
An
o
o
j
[
2
2
]
,
Detr
an
o
[
2
3
]
,
M
o
k
ed
d
em
et.
al
[
2
4
]
,
B
ash
ir
et.
al
[
2
5
]
,
Ma
r
ateb
&
Go
u
d
d
ar
zi
[
8
]
,
San
th
a
n
a
m
&
A
p
h
izib
ah
[
6
]
,
Kh
e
m
p
h
ila
&
B
o
o
n
j
in
g
[
2
6
]
an
d
A
b
d
a
r
et.
al
[
2
7
]
,
p
r
o
v
id
in
g
p
er
f
o
r
m
an
ce
ac
c
u
r
ac
y
w
as
co
n
s
i
d
er
ab
ly
lo
w
er
,
co
m
p
ar
ed
to
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
B
esid
es
h
av
i
n
g
lo
w
er
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
,
t
h
ese
s
tu
d
ie
s
also
u
s
e
o
n
e
o
r
t
w
o
attr
ib
u
te
s
c
o
s
tl
y
i
n
co
n
d
u
cti
n
g
th
e
i
n
v
e
s
ti
g
atio
n
,
n
a
m
e
l
y
f
lo
u
r
o
s
co
p
y
an
d
s
ci
n
ti
g
r
ap
h
y
[
1
7
]
.
Fu
r
th
er
m
o
r
e,
if
it
r
e
f
er
s
to
th
e
n
u
m
b
er
o
f
attr
ib
u
tes
in
r
esear
ch
co
n
d
u
c
ted
b
y
An
o
o
j
[
2
2
]
w
h
ic
h
u
s
in
g
F
u
zz
y
I
n
f
er
e
n
ce
S
y
s
te
m
is
ab
le
to
r
ed
u
ce
attr
ib
u
tes
i
n
to
s
i
x
attr
ib
u
te
s
.
T
h
ese
s
ix
attr
ib
u
tes
ar
e
th
e
attr
ib
u
tes
w
it
h
co
s
tl
y
e
x
a
m
i
n
atio
n
,
n
a
m
e
l
y
f
lo
u
r
o
s
co
p
h
y
.
Fu
r
t
h
er
m
o
r
e
M
o
k
ed
d
em
et.
al
[
2
4
]
b
y
u
s
i
n
g
a
w
r
ap
p
er
f
ea
tu
r
e
s
elec
tio
n
,
w
h
ich
is
i
m
p
le
m
e
n
ted
b
y
g
e
n
etic
al
g
o
r
ith
m
a
n
d
C
4
.
5
,
p
r
o
d
u
ce
a
n
u
m
b
er
o
f
attr
ib
u
tes
th
at
ar
e
le
s
s
th
a
n
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
b
u
t
w
ea
k
n
ess
e
s
attr
ib
u
te
s
g
e
n
er
ate
d
,
h
as t
w
o
attr
ib
u
tes co
s
tl
y
i
n
ex
a
m
in
at
io
n
.
T
h
e
n
ex
t
co
m
p
ar
is
o
n
w
it
h
r
e
s
ea
r
ch
co
n
d
u
cted
M
u
th
u
k
r
u
p
p
an
&
E
r
[
7
]
,
A
b
d
ar
et.
al
[
2
7
]
,
W
ih
ar
to
et.
al
[
2
8
]
an
d
Su
b
an
y
a
&
R
aj
alax
m
i
[
3
]
.
T
h
ese
s
tu
d
ies
ar
e
ab
le
to
p
r
o
v
id
e
h
ig
h
er
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
a
s
co
m
p
ar
ed
to
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
U
n
f
o
r
t
u
n
a
tel
y
,
t
h
e
h
i
g
h
ac
c
u
r
ac
y
s
h
o
u
ld
s
til
l
r
eq
u
ir
e
co
s
tl
y
attr
ib
u
te,
n
a
m
e
l
y
s
ci
n
ti
g
r
ap
h
y
e
x
a
m
in
at
io
n
an
d
f
lo
u
r
o
s
co
p
y
.
I
n
ad
d
iti
o
n
th
e
n
u
m
b
er
o
f
a
ttrib
u
tes
r
e
q
u
ir
ed
in
r
e
s
ea
r
ch
Mu
t
h
u
k
r
u
p
p
an
&
E
r
[
7
]
an
d
W
ih
ar
to
et.
al
[
2
8
]
to
p
r
o
d
u
ce
an
ac
cu
r
a
c
y
ab
o
v
e
9
0
%
r
eq
u
i
r
e
a
r
elativ
el
y
lar
g
e
n
u
m
b
er
o
f
attr
ib
u
tes
co
m
p
ar
e
d
to
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
W
h
ile
th
e
r
esear
c
h
co
n
d
u
cted
A
b
d
ar
et.
al
[
2
7
]
,
u
s
in
g
lo
g
is
tic
r
e
g
r
ess
io
n
attr
ib
u
te
i
s
ab
le
to
r
e
d
u
ce
f
r
o
m
1
3
to
6
attr
ib
u
tes,
an
d
w
it
h
C
5
.
0
alg
o
r
ith
m
s
ca
p
ab
le
o
f
g
en
er
ati
n
g
an
ac
c
u
r
ac
y
ab
o
v
e
9
0
%.
Un
f
o
r
tu
n
atel
y
,
t
h
e
y
s
till
n
ee
d
ab
o
u
t
s
ix
attr
ib
u
tes
w
h
ic
h
co
s
tl
y
,
ev
e
n
n
eg
ate
t
h
e
E
C
G
ex
a
m
i
n
atio
n
.
E
C
G
e
x
a
m
in
a
tio
n
co
s
ts
ar
e
r
elativ
el
y
c
h
ea
p
er
co
m
p
ar
ed
to
t
w
o
f
lo
u
r
o
s
co
p
y
ex
a
m
in
at
io
n
a
n
d
s
ci
n
ti
g
r
ap
h
y
.
I
n
th
e
p
r
o
p
o
s
ed
s
y
s
t
e
m
h
as
a
n
u
m
b
er
o
f
attr
ib
u
tes
t
h
at
ev
en
m
o
r
e
th
a
n
i
n
r
esear
ch
A
b
d
ar
et.
al
[
2
7
]
,
b
u
t
th
ese
attr
ib
u
te
s
ca
n
b
e
f
o
u
n
d
i
n
t
h
e
e
x
a
m
i
n
atio
n
o
f
r
is
k
f
ac
t
o
r
s
,
s
y
m
p
to
m
s
a
n
d
E
C
G.
W
h
ile
t
h
e
r
esear
ch
A
b
d
ar
et.
al
[
2
7
]
r
eq
u
ir
es
th
e
ex
a
m
i
n
atio
n
o
f
r
is
k
f
ac
to
r
s
,
s
y
m
p
to
m
s
,
f
lo
u
r
o
s
co
p
h
y
an
d
s
cin
tig
r
ap
h
y
,
r
es
u
lti
n
g
f
r
o
m
th
e
e
x
a
m
i
n
atio
n
g
r
o
u
p
m
o
r
e.
T
h
e
u
s
e
o
f
a
tier
ed
m
et
h
o
d
in
t
h
e
p
r
o
ce
s
s
o
f
f
ea
t
u
r
e
s
elec
tio
n
w
it
h
lo
g
is
tic
r
e
g
r
ess
io
n
,
is
ab
le
to
p
r
o
v
id
e
A
U
C
v
al
u
es
w
er
e
b
e
tter
th
a
n
w
it
h
o
u
t
u
s
in
g
a
tier
e
d
ap
p
r
o
ac
h
.
T
h
is
is
s
h
o
w
n
A
UC
v
al
u
e
o
f
0
.
8
9
1
tier
ed
,
w
h
ile
n
o
t
u
s
i
n
g
a
tier
ed
ap
p
r
o
ac
h
as
in
r
esear
ch
A
b
d
ar
et.
al
[
2
7
]
is
0
.
8
3
5
.
Fu
r
t
h
er
m
o
r
e,
w
h
en
co
m
b
i
n
ed
w
ith
cla
s
s
i
f
icatio
n
alg
o
r
ith
m
s
,
f
o
r
lo
g
is
tic
r
eg
r
es
s
io
n
w
it
h
tier
ed
ap
p
r
o
a
ch
ca
p
ab
le
o
f
p
r
o
v
id
in
g
A
U
C
v
al
u
e
o
f
0
.
9
2
1
,
w
h
ile
r
esear
ch
b
y
A
b
d
ar
et.
al
[
2
7
]
w
h
ic
h
co
m
b
i
n
ed
w
it
h
C
5
.
0
o
n
l
y
ab
le
to
p
r
o
v
id
e
A
U
C
v
a
lu
e
o
f
0
.
8
6
9
.
Fu
r
th
er
m
o
r
e,
i
f
th
e
tier
ed
lo
g
i
s
tic
r
eg
r
ess
io
n
m
et
h
o
d
w
it
h
a
co
m
b
in
atio
n
o
f
7
attr
ib
u
tes
p
r
o
v
id
es
A
U
C
0
.
8
9
1
,
w
h
er
ea
s
w
h
e
n
co
m
b
i
n
ed
w
ith
M
L
P
-
NN,
ca
p
ab
le
o
f
p
r
o
v
id
in
g
a
h
i
g
h
er
A
U
C
is
0
.
9
2
1
.
T
ier
e
d
lo
g
is
tic
r
eg
r
es
s
io
n
m
et
h
o
d
u
s
i
n
g
all
t
h
e
attr
ib
u
te
s
is
a
ls
o
ca
p
ab
le
o
f
p
r
o
v
id
in
g
AUC
v
alu
e
o
f
0
.
9
1
5
,
th
e
v
alu
e
i
s
s
ti
ll lo
w
er
th
a
n
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
ab
le
5
.
C
o
m
p
ar
atio
n
r
esear
c
h
A
u
t
h
o
r
M
e
t
h
o
d
N
o
mo
r
A
t
t
r
i
b
u
t
e
A
c
c
u
r
acy
A
n
o
o
j
[
2
2
F
u
z
z
y
I
n
f
e
r
e
n
c
e
S
y
st
e
m (
F
I
S
)
1
,
4
,
5
,
8
,
1
0
,
1
2
6
8
.
3
5
%
K
h
e
mp
h
i
l
a
&
B
o
o
n
j
i
n
g
[
2
6
]
D
e
c
i
si
o
n
T
r
e
e
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
,
1
1
,
1
2
,
1
3
7
3
,
3
0
%
D
e
t
r
a
n
o
e
t
.
a
l
[
2
3
]
P
r
o
b
a
b
i
l
i
t
y
T
h
e
o
r
y
(
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
)
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
,
1
1
,
1
2
,
1
3
7
7
,
0
0
%
K
h
e
mp
h
i
l
a
&
B
o
o
n
j
i
n
g
[
2
6
]
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
,
1
1
,
1
2
,
1
3
7
7
,
7
0
%
M
o
k
a
d
d
e
m e
t
.
a
l
[
5
]
G
A
W
r
a
p
p
e
r
+
C
4
.
5
3
,
6
,
1
2
,
1
3
7
8
,
5
4
%
M
o
k
a
d
d
e
m e
t
.
a
l
[
5
]
G
A
W
r
a
p
p
e
r
+
M
L
P
-
NN
1
,
2
,
3
,
4
,
1
1
,
1
2
,
1
3
7
9
,
8
6
%
K
h
e
mp
h
i
l
a
&
B
o
o
n
j
i
n
g
[
2
6
]
N
e
u
r
a
l
N
e
t
w
o
r
k
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
,
1
1
,
1
2
,
1
3
8
0
,
2
0
%
A
b
d
a
r
e
t
.
a
l
[
2
7
]
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
+
N
e
u
r
a
l
N
e
t
w
o
r
k
2
,
3
,
4
,
9
,
1
2
,
1
3
8
0
,
2
3
%
B
a
s
h
i
r
e
t
.
a
l
[
2
5
]
M
a
j
o
r
i
t
y
V
o
t
i
n
g
(
N
a
i
v
e
B
a
y
e
si
a
n
,
D
e
c
i
s
i
o
n
T
r
e
e
,
S
V
M
)
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
,
1
1
,
1
2
,
1
3
8
1
,
8
2
%
M
o
k
a
d
d
e
m e
t
.
a
l
[
5
]
G
A
W
a
r
p
p
e
r
+
S
V
M
1
,
3
,
9
,
1
0
,
1
1
,
1
2
,
1
3
8
3
,
8
2
%
M
a
r
a
t
e
b
&
G
o
u
d
a
r
z
i
[
8
]
M
u
l
t
i
p
l
e
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
+
N
e
u
r
o
-
F
u
z
z
y
C
l
a
ssi
f
i
e
r
1
,
8
,
9
,
1
0
,
1
2
,
1
3
8
4
,
0
0
%
M
o
k
a
d
d
e
m e
t
.
a
l
[
5
]
G
A
W
r
a
p
p
e
r
+
N
a
i
v
e
B
a
y
e
si
a
n
2
,
3
,
7
,
1
0
,
1
1
,
1
2
,
1
3
8
5
,
5
0
%
S
a
n
t
h
a
n
a
m &
A
p
h
z
i
b
a
h
[
6
]
G
A
+
F
u
z
z
y
I
n
f
e
r
e
n
c
e
S
y
st
e
m
(
F
I
S
)
2
,
5
,
8
,
1
0
,
1
2
,
1
3
8
6
.
0
0
%
A
b
d
a
r
e
t
.
a
l
[
2
7
]
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
+
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
2
,
3
,
4
,
9
,
1
2
,
1
3
8
6
,
0
5
%
S
u
b
a
n
y
a
&
R
a
j
a
l
a
x
mi
[
3
]
A
r
t
i
f
i
c
i
a
l
B
e
e
C
o
l
o
n
y
+
S
V
M
1
,
5
,
6
,
7
,
8
,
1
1
,
1
2
8
6
,
7
6
%
A
b
d
a
r
e
t
.
a
l
[
2
7
]
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
+
k
N
N
2
,
3
,
4
,
9
,
1
2
,
1
3
8
8
,
3
7
%
W
i
h
a
r
t
o
e
t
.
a
l
[
2
8
]
k
-
st
a
r
t
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
,
1
1
,
1
2
,
1
3
9
2
,
0
2
%
A
b
d
a
r
e
t
.
a
l
[
2
7
]
L
o
g
i
st
i
c
R
e
g
r
e
ssi
o
n
+
C
5
.
0
2
,
3
,
4
,
9
,
1
2
,
1
3
9
3
,
0
2
%
M
u
t
h
u
k
a
r
u
p
p
a
n
&
Er
[
7
]
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
mi
z
a
t
i
o
n
+
F
u
z
z
y
I
n
f
e
r
e
n
c
e
3
,
4
,
5
,
7
,
8
,
1
0
,
1
1
,
1
2
,
1
3
9
3
,
2
7
%
A
r
j
e
n
a
k
i
e
t
.
a
l
[
9
]
G
A
+
N
a
i
v
e
B
a
y
e
si
a
n
1
,
3
,
4
,
6
,
7
,
8
,
9
,
1
0
8
5
,
1
8
%
P
o
r
p
o
se
d
T
i
e
r
e
d
M
u
l
t
i
v
a
r
i
a
t
e
A
n
a
l
y
si
s
+
M
L
P
-
NN
1
,
2
,
3
,
8
,
9
,
1
0
,
1
1
8
6
,
3
0
%
Su
b
s
eq
u
e
n
t
r
esear
ch
co
n
d
u
cte
d
b
y
A
r
j
en
a
k
i
et.
al
[
9
]
,
w
h
ich
co
m
b
i
n
es
g
e
n
etic
al
g
o
r
ith
m
w
it
h
n
a
iv
e
B
ay
e
s
ian
.
F
itn
e
s
s
f
u
n
ct
io
n
u
s
ed
in
t
h
e
g
e
n
etic
al
g
o
r
ith
m
is
a
f
u
n
ctio
n
o
f
th
e
e
x
a
m
i
n
atio
n
f
ee
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
2
,
A
p
r
il 2
0
1
7
:
10
2
3
–
10
3
1
1030
co
m
b
i
n
atio
n
o
f
t
h
ese
t
w
o
attr
i
b
u
tes ca
n
r
ed
u
ce
co
s
tl
y
f
o
r
th
e
ex
a
m
in
atio
n
is
s
cin
tig
r
ap
h
y
a
n
d
f
lo
u
r
o
s
co
p
y
.
O
n
r
esear
ch
b
y
A
r
j
en
ak
i
et.
al
[
9
]
,
s
till
n
ee
d
lab
o
r
ato
r
y
te
s
ts
f
o
r
f
asti
n
g
b
lo
o
d
s
u
g
ar
attr
ib
u
te
d
eter
m
in
e
s
.
I
n
th
i
s
p
r
o
p
o
s
ed
s
y
s
te
m
d
o
es
n
o
t
r
eq
u
ir
e
lab
o
r
ato
r
y
e
x
a
m
i
n
atio
n
.
I
n
t
h
e
s
t
u
d
y
o
f
A
r
j
en
a
k
i
et.
al
[
9
]
also
s
till
h
as
a
n
u
m
b
er
o
f
attr
ib
u
tes
m
o
r
e
th
a
n
th
e
p
r
o
p
o
s
ed
r
esear
ch
.
I
n
th
e
co
u
r
s
e
o
f
a
s
tu
d
y
A
r
j
en
ak
i
e
t.a
l
[
9
]
am
o
u
n
ted
to
8
attr
ib
u
tes,
w
h
er
ea
s
t
h
e
p
r
o
p
o
s
ed
am
o
u
n
t
to
7
attr
ib
u
tes.
F
u
r
th
er
m
o
r
e,
t
h
e
r
esu
lt
in
g
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
w
it
h
7
attr
ib
u
tes b
etter
th
a
n
u
s
in
g
8
attr
i
b
u
tes i
n
r
esear
ch
A
r
j
en
ak
i e
t.a
l [
9
]
.
4.
CO
NCLU
SI
O
N
D
iag
n
o
s
is
u
s
in
g
h
y
b
r
id
s
y
s
te
m
tier
ed
m
u
lti
v
ar
iate
a
n
al
y
s
i
s
m
o
d
el
an
d
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
n
e
u
r
al
n
et
w
o
r
k
,
ca
p
ab
le
o
f
d
eli
v
er
in
g
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
ac
c
u
r
ac
y
8
6
.
3
%,
s
en
s
iti
v
it
y
8
4
.
8
0
%,
s
p
ec
if
icit
y
8
8
.
2
0
%,
P
P
V
9
0
.
0
3
%,
NP
V
8
1
.
8
0
%
a
n
d
AUC
9
2
,
1
%.
T
h
e
p
er
f
o
r
m
an
ce
,
w
h
e
n
v
ie
w
ed
f
r
o
m
t
h
e
r
elativ
e
ac
c
u
r
ac
y
o
f
b
etter
th
an
s
o
m
e
p
r
e
v
io
u
s
s
t
u
d
ies,
w
ith
th
e
e
x
a
m
i
n
atio
n
co
s
t
is
r
elat
iv
el
y
c
h
ea
p
,
f
a
s
t
a
n
d
ex
a
m
in
a
tio
n
r
es
u
lt
s
a
r
e
o
b
tain
ed
at
lo
w
r
is
k
.
I
n
ad
d
itio
n
th
e
n
u
m
b
er
o
f
at
tr
ib
u
tes
th
e
r
es
u
lts
o
f
f
ea
tu
r
e
s
elec
tio
n
ar
e
r
elativ
el
y
litt
l
e
th
at
is
7
attr
ib
u
te
s
,
w
it
h
th
e
p
er
ce
n
tag
e
o
f
t
h
e
h
ig
h
e
s
t
u
r
g
en
c
y
lev
el
at
tr
ib
u
te
t
y
p
e
o
f
ch
e
s
t
p
ain
an
d
ex
er
cise
-
in
d
u
ce
d
an
g
i
n
a
lo
w
s
.
R
ef
er
r
i
n
g
to
th
e
v
a
lu
e
o
f
t
h
e
p
ar
a
m
eter
A
UC
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
t
e
m
in
cl
u
d
ed
in
th
e
ca
teg
o
r
y
o
f
v
er
y
g
o
o
d
.
RE
F
E
R
E
NC
E
S
[1
]
J.
Kim
,
e
t
a
l.
,
“
Da
ta
-
M
in
in
g
-
Ba
se
d
Co
ro
n
a
ry
He
a
rt
Dise
a
se
R
isk
P
re
d
ictio
n
M
o
d
e
l
Us
in
g
F
u
z
z
y
L
o
g
ic
a
n
d
De
c
isio
n
T
re
e
,
”
He
a
lt
h
c
a
re
In
fo
r
ma
ti
c
Res
e
a
rc
h
(
HIR)
,
v
o
l/
issu
e
:
2
1
(
3
),
p
p
.
1
6
7
-
1
7
4
,
2
0
1
5
.
[2
]
A
.
Yo
u
n
g
,
“
Ha
n
d
b
o
o
k
o
f
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
a
n
d
Im
a
g
e
P
ro
c
e
ss
in
g
1
st E
d
it
io
n
,
”
Aca
d
e
mic
Pre
ss
,
1
9
8
6
.
[3
]
B.
S
u
b
a
n
y
a
a
n
d
D.
R.
R.
Ra
jala
x
m
i,
“
F
e
a
tu
re
S
e
le
c
ti
o
n
u
sin
g
Artif
icia
l
Be
e
Co
lo
n
y
f
o
r
Ca
rd
io
v
a
sc
u
lar
Di
se
a
se
Clas
sif
ic
a
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
El
e
c
tro
n
ics
a
n
d
C
o
mm
u
n
ica
ti
o
n
S
y
ste
m.
C
o
imb
a
to
re
,
p
p
.
1
-
6
,
2
0
1
4
.
[4
]
H.
S
.
N.
M
u
rth
y
a
n
d
M
.
M
e
e
n
a
k
sh
i,
“
Di
m
e
n
sio
n
a
li
ty
Re
d
u
c
ti
o
n
Us
in
g
Ne
u
ro
-
G
e
n
e
ti
c
A
p
p
ro
a
c
h
f
o
r
Earl
y
P
re
d
ictio
n
o
f
Co
ro
n
a
ry
He
a
rt
Dise
a
se
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Circ
u
it
s,
Co
mm
u
n
ica
ti
o
n
,
C
o
n
tr
o
l
a
n
d
Co
mp
u
t
in
g
(
I4
C)
,
p
p
.
3
2
9
-
3
3
2
,
2
0
1
4
.
[5
]
R.
O.
Du
d
a
,
e
t
a
l.
,
“
P
a
tt
e
r
n
Clas
sif
ica
ti
o
n
,
”
Ne
w
Yo
rk
:
Jo
h
n
W
il
e
y
&
S
o
n
s
,
2
0
1
2
.
[6
]
T
.
S
a
n
th
a
n
a
m
a
n
d
E.
P
.
Ep
h
z
ib
a
h
,
“
He
a
rt
Dise
a
se
P
re
d
ictio
n
Us
i
n
g
H
y
b
rid
G
e
n
e
ti
c
F
u
z
z
y
M
o
d
e
l,
”
In
d
i
a
n
J
o
u
r
n
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l/
is
su
e
:
8
(9
)
,
p
p
.
7
9
7
–
8
0
3
,
2
0
1
5
.
[7
]
S.
M
u
t
h
u
k
a
ru
p
p
a
n
a
a
n
d
M
.
J.
Er,
“
A
h
y
b
rid
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
iza
ti
o
n
b
a
se
d
f
u
z
z
y
e
x
p
e
rt
s
y
ste
m
f
o
r
th
e
d
iag
n
o
s
is
o
f
c
o
ro
n
a
ry
a
rter
y
d
ise
a
se
,
”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
li
c
a
t
io
n
s
,
v
o
l/
issu
e
:
3
9
(
1
4
),
p
p
.
1
1
6
5
7
–
1
1
6
6
5
,
2
0
1
2
.
[8
]
H
.
R.
M
a
ra
teb
a
n
d
S
.
G
o
u
d
a
rz
i,
“
A
n
o
n
in
v
a
siv
e
m
e
th
o
d
f
o
r
c
o
ro
n
a
ry
a
rter
y
d
ise
a
se
s
d
iag
n
o
sis
u
si
n
g
a
c
li
n
ica
ll
y
-
in
terp
re
t
a
b
le
f
u
z
z
y
ru
le
-
b
a
se
d
s
y
ste
m
,
”
J
o
u
rn
a
l
o
f
Res
e
a
rc
h
in
M
e
d
ica
l
S
c
ien
c
e
s
,
v
o
l
/i
ss
u
e
:
2
0
(3
),
p
p
.
2
1
4
-
2
2
3
,
2
0
1
5
.
[9
]
H.
G
.
A
rjen
a
k
i,
e
t
a
l.
,
“
A
L
o
w
C
o
st
M
o
d
e
l
f
o
r
Dia
g
n
o
sin
g
Co
ro
n
a
ry
A
rter
y
Dis
e
a
s
e
Ba
s
e
d
On
Eff
e
c
ti
v
e
F
e
a
tu
re
s,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
tro
n
i
c
s Co
mm
u
n
ica
t
io
n
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l/
iss
u
e
:
6
(
1
),
p
p
.
93
-
97
,
2
0
1
5
.
[1
0
]
Y.
Zh
a
n
g
,
e
t
a
l.
,
“
S
tu
d
ies
o
n
a
p
p
li
c
a
ti
o
n
o
f
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
in
d
iag
n
o
se
o
f
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
se
,”
S
ixt
h
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
tro
ma
g
n
e
ti
c
Fi
e
l
d
Pr
o
b
lem
s
a
n
d
Ap
p
li
c
a
ti
o
n
s
(
ICEF
),
D
a
li
a
n
,
L
i
a
o
n
i
n
g
,
p
p
.
1
-
4
,
2
0
1
2
.
[1
1
]
B.
Am
m
a
N
.
G
.
,
“
A
n
In
tell
ig
e
n
t
A
p
p
ro
a
c
h
Ba
se
d
o
n
P
rin
c
i
p
a
l
Co
m
p
o
n
e
n
t
A
n
a
ly
sis
a
n
d
A
d
a
p
ti
v
e
Ne
u
ro
F
u
z
z
y
In
f
e
re
n
c
e
S
y
ste
m
f
o
r
P
re
d
ictin
g
th
e
Risk
o
f
C
a
rd
io
v
a
sc
u
lar
Dise
a
s
e
s
,
”
Fi
ft
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
Co
mp
u
t
in
g
(
ICo
AC)
,
p
p
.
2
4
1
-
2
4
5
,
2
0
1
3
.
[1
2
]
UCI
A
r
c
h
iv
e
,
“
M
a
c
h
in
e
L
e
a
rn
in
g
Re
p
o
sito
ry
,
”
h
tt
p
s://
a
rc
h
iv
e
.
i
c
s.u
c
i.
e
d
u
/m
l/
m
a
c
h
in
e
-
lea
rn
in
g
-
d
a
tab
a
se
s/h
e
a
rt
-
d
ise
a
se
/
(a
c
c
e
ss
e
d
2
4
A
u
g
u
st 2
0
1
6
).
[1
3
]
D.
M
a
n
n
e
rin
g
,
e
t
a
l.
,
“
A
c
c
u
ra
te
d
e
tec
ti
o
n
o
f
tri
p
le
v
e
ss
e
l
d
ise
a
s
e
in
p
a
ti
e
n
ts
w
it
h
e
x
e
rc
i
se
in
d
u
c
e
d
S
T
se
g
m
e
n
t
d
e
p
re
ss
io
n
a
f
ter i
n
f
a
rc
ti
o
n
,
”
Br
H
e
a
rt J
.
,
v
o
l/
issu
e
:
57
(2
),
p
p
.
1
3
3
-
1
3
8
,
1
9
8
7
.
[1
4
]
F
.
G
o
ru
n
e
sc
u
,
“
Da
ta M
i
n
in
g
C
o
n
c
e
p
ts,
M
o
d
e
ls
a
n
d
T
e
c
h
n
iq
u
e
s,”
Ver
la
g
Ber
li
n
He
id
e
lb
e
rg
:
S
p
rin
g
e
r
,
2
0
1
1
.
[1
5
]
L
.
F
a
u
se
tt
,
“
F
u
n
d
a
m
e
n
tals
o
f
Ne
u
ra
l
Ne
tw
o
rk
s
A
rc
h
it
e
c
tu
r
e
,
A
lg
o
rit
h
m
s,
a
n
d
A
p
p
li
c
a
ti
o
n
s,”
Ne
w
J
e
rse
y
:
P
e
n
ti
c
e
-
Ha
ll
In
c
,
1
9
9
4
.
[1
6
]
S.
H.
J
u
n
g
,
e
t
a
l.
,
“
P
re
d
ictio
n
Da
ta
P
r
o
c
e
ss
in
g
S
c
h
e
m
e
u
sin
g
a
n
Artif
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
a
n
d
Da
ta
Clu
ste
rin
g
f
o
r
Big
Da
ta,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
),
v
o
l/
issu
e
:
6
(1
)
,
p
p
.
3
3
0
-
3
3
6
,
2
0
1
6
.
[1
7
]
D.
T
.
M
a
n
g
a
n
o
,
e
t
a
l
.
,
“
Dip
y
rid
a
m
o
le
T
h
a
ll
iu
m
-
2
0
1
S
c
in
ti
g
ra
p
h
y
a
s
a
P
re
o
p
e
ra
ti
v
e
S
c
re
e
n
in
g
T
e
st
A
Re
e
x
a
m
in
a
ti
o
n
o
f
Its
P
re
d
ictiv
e
P
o
ten
ti
a
l,
”
Circ
u
la
ti
o
n
,
v
o
l/
issu
e
:
8
(2
),
p
p
.
4
9
3
-
5
0
2
,
1
9
9
1
.
[1
8
]
L
.
K.
He
r
m
a
n
n
,
e
t
a
l.
,
“
Co
m
p
a
r
iso
n
o
f
F
re
q
u
e
n
c
y
o
f
In
d
u
c
ib
le
M
y
o
c
a
rd
ial
Is
c
h
e
m
ia
in
P
a
ti
e
n
ts
P
re
se
n
ti
n
g
t
o
Em
e
r
g
e
n
c
y
De
p
a
rt
m
e
n
t
W
it
h
Ty
p
ica
l
V
e
rsu
s
A
t
y
p
ic
a
l
o
r
No
n
a
n
g
in
a
l
Ch
e
st
P
a
i
n
,
”
T
h
e
Ame
ric
a
n
J
o
u
rn
a
l
o
f
Ca
rd
io
lo
g
y
,
v
o
l/
issu
e
:
1
0
5
(
1
1
),
p
p
.
1
5
6
1
-
1
5
6
4
,
2
0
0
9
.
[1
9
]
T
.
F
.
M
.
v
.
Be
rk
e
l,
e
t
a
l.
,
“
Im
p
a
c
t
o
f
s
m
o
k
in
g
c
e
ss
a
ti
o
n
a
n
d
sm
o
k
i
n
g
in
terv
e
n
ti
o
n
s
in
p
a
ti
e
n
t
s
w
it
h
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
se
,”
Eu
ro
p
e
a
n
He
a
rt J
o
u
rn
a
l
,
v
o
l/
issu
e
:
20
(
2
4
)
,
p
p
.
1
7
7
3
–
1
7
8
2
,
1
9
9
9
.
[2
0
]
H.
H.
G
ra
y
,
“
L
e
c
tu
re
n
o
tes
,”
Ja
k
a
rta:
Erl
a
n
g
g
a
M
e
d
ica
l
S
e
ries
,
2
0
0
2
.
[2
1
]
S.
A
.
P
r
ice
a
n
d
L
.
M
.
W
il
so
n
,
“
P
a
th
o
p
h
y
sio
lo
g
y
:
Cli
n
ica
l
C
o
n
c
e
p
ts
o
f
Dise
a
se
P
ro
c
e
ss
e
s 6
e
,
”
M
o
sb
y
,
2
0
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
S
ystem
o
f Tiered
Mu
lti
va
r
ia
te
A
n
a
lysi
s
a
n
d
A
r
tifi
cia
l Neu
r
a
l Netw
o
r
k
fo
r
.
.
.
.
(
W
ih
a
r
to
)
1031
[2
2
]
P.
K.
A
n
o
o
j
,
“
Im
p
le
m
e
n
ti
n
g
De
c
i
sio
n
T
re
e
F
u
z
z
y
Ru
les
in
Cli
n
ica
l
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
m
a
f
ter
C
o
m
p
a
rin
g
w
it
h
F
u
z
z
y
b
a
se
d
a
n
d
Ne
u
ra
l
Ne
t
w
o
rk
b
a
se
d
s
y
ste
m
s
,”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
IT
Co
n
v
e
rg
e
n
c
e
a
n
d
S
e
c
u
rit
y
(
ICIT
CS
).
M
a
c
a
o
,
p
p
.
1
-
6
,
2
0
1
3
.
[2
3
]
R.
De
tran
o
,
e
t
a
l
.
,
“
In
tern
a
ti
o
n
a
l
A
p
p
li
c
a
ti
o
n
o
f
a
Ne
w
P
r
o
b
a
b
i
li
ty
A
lg
o
rit
h
m
f
o
r
th
e
Dia
g
n
o
s
is
o
f
Co
ro
n
a
ry
A
rter
y
Dise
a
se
,”
T
h
e
Ame
ric
a
n
J
o
u
rn
a
l
o
f
Ca
r
d
io
lo
g
y
,
v
o
l/
issu
e
:
6
4
(
5
)
,
p
p
.
3
0
4
-
3
1
0
,
1
9
8
9
.
[2
4
]
S
.
M
o
k
e
d
d
e
m
,
e
t
a
l.
,
“
S
u
p
e
rv
ise
d
F
e
a
tu
re
S
e
lec
ti
o
n
F
o
r
Dia
g
n
o
si
s
o
f
Co
ro
n
a
ry
A
rter
y
Dis
e
a
se
Ba
se
d
o
n
G
e
n
e
ti
c
A
l
g
o
r
it
h
m
,
”
Co
mp
u
ter
S
c
ien
c
e
&
In
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
CS
&
I
T
)
,
v
o
l/
issu
e
:
3
(
3
)
,
p
p
.
41
-
51
,
2
0
1
3
.
[2
5
]
S
.
B
a
sh
ir,
e
t
a
l.
,
“
A
n
En
se
m
b
le
b
a
se
d
De
c
isio
n
S
u
p
p
o
rt
F
ra
m
e
w
o
rk
f
o
r
In
telli
g
e
n
t
He
a
rt
Dise
a
se
Dia
g
n
o
sis
,”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
r
ma
ti
o
n
S
o
c
iety
(
i
-
S
o
c
iety
)
,
p
p
.
2
5
9
-
2
6
4
,
2
0
1
4
.
[2
6
]
A
.
Kh
e
m
p
h
il
a
a
n
d
V.
Bo
o
n
ji
n
g
,
“
Co
m
p
a
rin
g
p
e
rf
o
r
m
a
n
c
e
s
o
f
lo
g
isti
c
re
g
re
ss
io
n
,
d
e
c
isio
n
tree
s
,
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
c
las
sify
in
g
h
e
a
rt
d
i
se
a
se
p
a
ti
e
n
ts
,”
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
In
f
o
rm
a
ti
o
n
S
y
ste
ms
a
n
d
In
d
u
stria
l
M
a
n
a
g
e
me
n
t
A
p
p
l
ica
ti
o
n
s (
CIS
IM
)
,
p
p
.
1
9
3
-
1
9
8
,
2
0
1
0
.
[2
7
]
M
.
A
b
d
a
r,
e
t
a
l.
,
“
Co
m
p
a
rin
g
P
e
r
f
o
r
m
a
n
c
e
o
f
Da
ta
M
in
in
g
A
lg
o
rit
h
m
s
in
P
re
d
ict
io
n
He
a
rt
Dise
a
s
e
s,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
t
e
r E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l/
issu
e
:
5
(6
),
p
p
.
1
5
6
9
-
1
5
7
6
,
2
0
1
5
.
[2
8
]
W
.
W
ih
a
rto
,
e
t
a
l
.
,
“
In
telli
g
e
n
c
e
S
y
st
e
m
f
o
r
Dia
g
n
o
sis
L
e
v
e
l
o
f
C
o
ro
n
a
ry
He
a
rt
Dise
a
se
w
it
h
K
-
S
tar
A
lg
o
rit
h
m
,”
He
a
lt
h
c
a
re
In
fo
rm
a
ti
c
Res
e
a
rc
h
(
HIR)
,
v
o
l/
issu
e
:
2
2
(
1
)
,
p
p
.
30
-
38
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.