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
.
4
,
A
u
g
u
st
201
7
,
p
p
.
2
1
8
3
~
2
1
9
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
4
.
p
p
2
1
8
3
-
2191
2183
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
The Ana
ly
sis
of P
erfor
m
a
ce Mo
del
Tiered A
rtif
i
cia
l
Neura
l
Netw
o
rk
f
o
r Asse
ss
m
en
t
o
f
Co
ro
na
ry
H
ea
rt
Disea
se
Wiha
rt
o
Wiha
rt
o
1
,
H
er
ia
nto
H
er
ia
nto
2
,
H
a
ri
K
us
na
nto
3
1
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s
,
S
e
b
e
las
M
a
re
t
Un
iv
e
rsit
y
,
In
d
o
n
e
sia
2
De
p
a
rtme
n
t
o
f
M
e
c
h
a
n
ica
l
a
n
d
I
n
d
u
str
ial
En
g
i
n
e
e
rin
g
,
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
d
icin
e
,
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
,
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
Dec
9
,
2
0
1
6
R
ev
i
s
ed
Ma
y
1
0
,
2
0
1
7
A
cc
ep
ted
Ma
y
2
4
,
2
0
1
7
T
h
e
a
ss
e
s
s
m
e
n
t
m
o
d
e
l
o
f
c
o
ro
n
a
r
y
h
e
a
rt
d
ise
a
se
is
so
m
u
c
h
d
e
v
e
lo
p
e
d
i
n
li
n
e
w
it
h
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
in
f
o
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
,
p
a
rti
c
u
larly
th
e
f
ield
o
f
a
rti
f
icia
l
in
telli
g
e
n
c
e
.
Un
f
o
rtu
n
a
tel
y
,
th
e
a
ss
e
ss
m
e
n
t
m
o
d
e
ls
d
e
v
e
lo
p
e
d
m
o
stl
y
d
o
n
o
t
u
se
su
c
h
a
n
a
p
p
ro
a
c
h
m
a
d
e
b
y
th
e
c
li
n
icia
n
,
th
a
t
is
th
e
ti
e
re
d
a
p
p
ro
a
c
h
.
T
h
is
m
a
k
e
s
th
e
a
ss
e
s
s
m
e
n
t
p
ro
c
e
ss
sh
o
u
ld
c
o
n
d
u
c
t
a
th
o
r
o
u
g
h
e
x
a
m
in
a
ti
o
n
.
T
h
is
stu
d
y
a
i
m
s
to
a
n
a
ly
z
e
th
e
p
e
rf
o
rm
a
n
c
e
o
f
a
ti
e
re
d
m
o
d
e
l
a
ss
e
ss
m
e
n
t.
T
h
e
a
ss
e
ss
m
e
n
t
s
y
ste
m
is
d
iv
id
e
d
in
to
se
v
e
ra
l
le
v
e
ls,
w
it
h
re
fe
re
n
c
e
to
th
e
sta
g
e
s
o
f
th
e
in
sp
e
c
ti
o
n
p
ro
c
e
d
u
re
.
T
h
e
m
e
th
o
d
u
se
d
f
o
r
e
a
c
h
lev
e
l
is,
p
re
p
ro
c
e
ss
in
g
,
b
u
i
ld
i
n
g
a
rc
h
it
e
c
tu
re
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
(
A
NN
),
c
o
n
d
u
c
t
train
in
g
u
sin
g
th
e
L
e
v
e
n
b
e
rg
-
M
a
rq
u
a
rd
t
a
lg
o
rit
h
m
a
n
d
o
n
e
ste
p
se
c
a
n
t,
a
s
w
e
ll
a
s
tes
ti
n
g
th
e
sy
ste
m
.
T
h
e
tes
t
re
su
lt
s
sh
o
w
e
d
th
e
in
f
lu
e
n
c
e
o
f
e
a
c
h
lev
e
l,
b
o
th
w
h
e
n
th
e
o
u
tp
u
t
lev
e
l
o
f
th
e
p
re
v
io
u
s
p
o
siti
v
e
o
r
n
e
g
a
ti
v
e
,
w
e
r
e
tes
ted
b
a
c
k
a
t
th
e
n
e
x
t
lev
e
l.
T
h
e
e
ff
e
c
t
in
d
ica
tes
th
a
t
th
e
le
v
e
l
a
b
o
v
e
g
iv
e
s
p
e
r
f
o
rm
a
n
c
e
i
m
p
ro
v
e
m
e
n
t
a
n
d
o
r
stre
n
g
th
e
n
s
th
e
p
e
rf
o
rm
a
n
c
e
a
t
th
e
p
re
v
io
u
s lev
e
l.
K
ey
w
o
r
d
:
A
r
ti
f
icial
i
n
tel
lig
e
n
ce
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
Ass
es
s
m
en
t
C
o
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e
T
ier
e
d
m
o
d
el
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
W
ih
ar
to
,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
s
,
Seb
elas M
ar
et
Un
i
v
er
s
it
y
,
J
l.
I
r
.
Su
ta
m
i,
No
.
3
6
A
,
Ken
ti
n
g
a
n
,
S
u
r
ak
ar
ta,
I
n
d
o
n
e
s
ia
.
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
T
h
e
d
ev
elo
p
m
en
t
o
f
tech
n
o
lo
g
y
,
m
a
k
in
g
a
lo
t
o
f
ch
an
g
es,
es
p
ec
iall
y
a
p
er
s
o
n
's
lif
e
s
t
y
le.
I
n
f
o
r
m
atio
n
tech
n
o
lo
g
y
b
r
in
g
s
p
eo
p
le
in
to
ac
tiv
itie
s
m
o
r
e
ea
s
i
l
y
,
w
h
ic
h
i
s
a
lo
t o
f
ac
tiv
i
ties
t
h
at
ca
n
b
e
d
o
n
e
b
y
j
u
s
t
s
itti
n
g
b
eh
in
d
a
d
e
s
k
.
T
h
e
a
m
o
u
n
t
o
f
ch
a
n
g
e
u
n
h
ea
lt
h
y
li
f
est
y
le
w
i
ll
h
a
v
e
a
n
i
m
p
ac
t
o
n
o
n
e
's
h
e
alth
[
1
]
.
Un
h
ea
lt
h
y
lif
es
t
y
le
i
s
o
n
e
o
f
t
h
e
r
is
k
f
ac
to
r
s
f
o
r
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
A
g
o
o
d
an
ticip
ato
r
y
ac
tio
n
is
tr
y
i
n
g
to
m
a
k
e
a
h
ea
lt
h
y
li
f
e
s
t
y
le
a
n
d
d
ilig
e
n
t
to
co
n
d
u
ct
a
th
o
r
o
u
g
h
m
ed
ical
ex
a
m
in
at
io
n
to
d
eter
m
in
e
th
e
p
r
esen
ce
o
r
ab
s
en
ce
o
f
b
lo
ck
a
g
e
i
n
ar
ter
y
co
r
o
n
ar
y
b
lo
o
d
v
ess
el
s
.
Un
f
o
r
tu
n
atel
y
,
s
u
ch
c
h
ec
k
s
ar
e
ex
p
en
s
iv
e,
a
n
d
n
o
t
ev
er
y
le
v
el
o
f
h
ea
lt
h
s
er
v
ices
p
r
o
v
id
ed
.
R
elate
d
to
co
s
t,
a
n
u
m
b
er
o
f
co
u
n
tr
ie
s
ap
p
l
y
i
n
g
t
h
e
co
n
ce
p
t
o
f
h
ea
lt
h
in
s
u
r
an
ce
,
s
u
c
h
a
s
i
n
I
n
d
o
n
e
s
i
a
w
ith
a
n
a
tio
n
al
h
ea
lt
h
i
n
s
u
r
a
n
ce
p
r
o
g
r
a
m
(
J
KN)
.
T
h
e
co
n
c
ep
t
o
f
ap
p
l
y
i
n
g
th
e
co
n
ce
p
t o
f
t
ier
ed
J
KN
s
er
v
ice
s
,
w
h
ich
ar
e
s
er
v
ices o
f
p
r
i
m
a
r
y
,
s
ec
o
n
d
ar
y
an
d
ter
tiar
y
[
2
]
.
R
ef
er
r
i
n
g
m
a
k
i
n
g
it
th
e
m
ed
ical
e
x
a
m
i
n
atio
n
s
h
o
u
l
d
b
e
co
n
d
u
cted
in
p
h
ases
.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
i
n
f
o
r
m
at
io
n
tech
n
o
lo
g
y
,
esp
ec
iall
y
i
n
th
e
f
ield
o
f
ar
tific
ial
i
n
telli
g
en
ce
,
to
o
k
ef
f
ec
t
i
n
m
o
d
els
o
f
cli
n
ical
d
ec
is
io
n
s
u
p
p
o
r
t
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
e
ase.
Nu
m
er
o
u
s
s
tu
d
ie
s
h
a
v
e
b
ee
n
d
ev
elo
p
ed
u
s
in
g
ar
ti
f
icial
i
n
telli
g
e
n
c
e
alg
o
r
ith
m
s
,
s
u
c
h
as
C
4
.
5
[
3
]
,
[
4
]
,
w
eig
h
ted
ass
o
ciatio
n
clas
s
if
ier
[
5
]
,
k
NN
[
6
]
,
ar
tif
icial
n
e
u
r
al
n
e
t
w
o
r
k
[
7
]
,
[
8
]
,
th
e
f
u
zz
y
s
y
s
te
m
[
9
]
an
d
t
h
e
co
m
b
i
n
atio
n
o
f
clas
s
i
f
icatio
n
an
d
clu
s
ter
i
n
g
[
1
0
]
.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
r
esear
c
h
o
n
t
h
e
s
y
s
te
m
o
f
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
ca
n
b
e
g
r
o
u
p
ed
in
to
f
o
u
r
.
T
h
e
f
ir
s
t a
d
iag
n
o
s
t
ic
s
y
s
te
m
w
it
h
o
u
t r
ed
u
cin
g
t
h
e
n
u
m
b
er
o
f
attr
ib
u
tes.
T
h
e
s
ec
o
n
d
th
e
s
y
s
te
m
o
f
d
ia
g
n
o
s
is
b
y
r
ed
u
cin
g
t
h
e
attr
ib
u
te
d
i
m
e
n
s
io
n
s
[
1
1
]
,
[
1
2
]
.
T
h
e
th
ir
d
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
.
4
,
A
u
g
u
s
t
2
0
1
7
:
2
1
8
3
–
2
1
9
1
2184
d
iag
n
o
s
t
ic
s
y
s
te
m
s
ar
e
b
y
th
e
r
ed
u
ctio
n
o
f
t
h
e
attr
ib
u
te
d
i
m
en
s
io
n
s
t
h
at
c
o
n
s
id
er
th
e
co
s
t
s
[
1
3
]
,
[
1
4
]
,
an
d
th
e
f
o
u
r
t
h
d
iag
n
o
s
tic
s
y
s
te
m
s
ar
e
b
y
a
tier
ed
ap
p
r
o
ac
h
[
1
5
]
,
[
1
6
]
.
T
h
e
w
id
el
y
d
e
v
elo
p
ed
ap
p
r
o
ac
h
to
h
ea
r
t
d
is
ea
s
e
d
iag
n
o
s
i
s
is
f
o
cu
s
ed
o
n
d
im
e
n
s
io
n
al
r
ed
u
ctio
n
co
m
b
i
n
atio
n
s
w
it
h
ar
ti
f
icial
i
n
telli
g
e
n
ce
al
g
o
r
ith
m
s
.
T
h
e
r
esear
ch
w
i
th
t
h
e
t
h
e
m
e
o
f
d
im
en
s
io
n
r
ed
u
ctio
n
co
m
b
i
n
atio
n
w
it
h
co
n
s
id
er
ati
o
n
o
f
co
s
t
an
d
tier
ed
ap
p
r
o
a
ch
i
s
s
t
ill
r
elati
v
el
y
s
m
al
l.
S
ev
er
al
s
t
u
d
ies
h
a
v
e
p
r
o
p
o
s
ed
s
u
c
h
a
co
m
b
i
n
atio
n
m
o
d
el,
s
u
c
h
a
s
r
esear
c
h
c
o
n
d
u
cted
b
y
A
r
j
en
a
k
i
e
t.a
l
[
1
3
]
.
T
h
e
s
t
u
d
y
u
s
ed
a
g
en
et
ic
al
g
o
r
ith
m
w
it
h
a
n
ele
m
en
t
o
f
t
h
e
f
it
n
es
s
f
u
n
ctio
n
a
ttrib
u
te
i
n
s
p
ec
tio
n
co
s
t
co
n
s
id
er
atio
n
s
.
A
r
ti
f
ici
al
in
telli
g
e
n
ce
alg
o
r
it
h
m
s
u
s
ed
to
class
if
y
is
n
ai
v
e
B
ay
e
s
ia
n
.
A
s
i
m
i
l
ar
s
tu
d
y
co
n
d
u
cted
b
y
Fes
h
k
i
&
Sh
ij
an
i
[
1
4
]
.
On
l
y
i
n
t
h
e
s
t
u
d
y
u
s
i
n
g
t
h
e
p
ar
ticle
s
w
ar
m
o
p
ti
m
izat
io
n
f
o
r
d
i
m
e
n
s
io
n
r
ed
u
ctio
n
b
y
th
e
f
it
n
es
s
f
u
n
ctio
n
co
n
s
id
er
in
g
th
e
c
o
s
t
o
f
in
s
p
ec
tio
n
attr
ib
u
tes.
C
lass
if
ica
tio
n
is
d
o
n
e
b
y
u
s
i
n
g
a
f
ee
d
f
o
r
war
d
n
eu
r
al
n
et
w
o
r
k
alg
o
r
ith
m
.
T
h
e
s
t
u
d
y
also
s
u
g
g
est
s
g
r
o
u
p
i
n
g
attr
ib
u
te
s
in
v
e
s
tig
a
tio
n
b
ased
o
n
t
h
e
co
s
ts
.
T
h
e
m
et
h
o
d
u
s
ed
in
b
o
th
s
tu
d
ie
s
,
ca
p
ab
le
o
f
r
ed
u
cin
g
co
s
t
l
y
attr
ib
u
tes i
n
t
h
e
d
iag
n
o
s
is
s
y
s
te
m
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
T
h
e
d
ev
elo
p
m
e
n
t
o
f
a
f
u
r
th
er
d
iag
n
o
s
t
ic
m
o
d
el
is
to
u
s
e
a
ti
er
ed
ap
p
r
o
ac
h
.
T
h
e
m
o
d
el
h
a
s
n
o
t
b
ee
n
w
id
el
y
d
ev
elo
p
ed
.
T
h
e
co
n
ce
p
t
o
f
th
i
s
ap
p
r
o
ac
h
is
a
co
m
m
o
n
p
r
o
ce
d
u
r
e
u
s
ed
i
n
t
h
e
d
iag
n
o
s
i
s
p
r
o
ce
s
s
co
n
d
u
cted
cl
i
n
icia
n
.
T
h
is
co
n
ce
p
t
ca
n
b
e
u
s
ed
f
o
r
d
i
m
e
n
s
io
n
r
ed
u
ctio
n
p
r
o
ce
s
s
,
s
u
ch
as
i
n
s
tu
d
ie
s
co
n
d
u
cted
W
ih
ar
to
et.
al
[
1
6
]
.
T
h
e
g
r
o
u
p
in
g
attr
ib
u
te
r
esear
c
h
in
ac
co
r
d
an
ce
w
it
h
th
e
p
r
o
ce
d
u
r
e
clin
icia
n
,
f
o
r
later
an
al
y
s
is
u
s
i
n
g
a
h
ier
ar
ch
ical
o
f
lo
g
is
tic
r
e
g
r
ess
io
n
alg
o
r
it
h
m
s
.
A
ttrib
u
te
d
i
m
e
n
s
io
n
r
ed
u
ctio
n
r
esu
lt
s
,
f
u
r
th
er
class
i
f
ied
b
y
u
s
i
n
g
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
al
g
o
r
ith
m
.
R
ef
er
r
in
g
to
t
h
e
g
r
o
u
p
i
n
g
p
er
f
o
r
m
ed
i
n
r
e
s
ea
r
ch
Fes
h
k
i
&
Sh
ij
an
i
[
1
4
]
,
th
ese
s
tu
d
ies
also
ab
le
to
r
ed
u
ce
co
s
tl
y
attr
ib
u
te,
w
it
h
th
e
s
y
s
t
e
m
s
till
p
r
o
v
id
es
a
r
elativ
el
y
g
o
o
d
p
er
f
o
r
m
an
ce
.
L
o
g
i
s
tic
r
eg
r
es
s
io
n
alg
o
r
it
h
m
is
al
s
o
u
s
ed
i
n
r
esear
c
h
A
b
d
a
r
et.
al
[
1
2
]
,
b
u
t
t
h
e
r
esu
lt
s
g
e
n
er
ated
d
i
m
e
n
s
io
n
r
e
d
u
ctio
n
t
h
er
e
ar
e
t
w
o
attr
ib
u
te
s
co
s
tl
y
,
e
v
en
if
u
s
i
n
g
th
e
C
5
.
0
alg
o
r
ith
m
is
ab
le
to
p
r
o
v
id
e
b
etter
p
er
f
o
r
m
a
n
ce
.
T
ier
e
d
ap
p
r
o
ac
h
es
ca
n
b
e
u
s
e
d
to
th
e
m
o
d
el
o
f
d
iag
n
o
s
i
s
s
y
s
te
m
s
an
d
d
i
m
e
n
s
io
n
al
r
ed
u
cti
o
n
,
as
in
a
s
tu
d
y
co
n
d
u
cted
b
y
W
ih
ar
t
o
et.
al
[
1
5
]
.
T
h
e
r
esear
ch
u
s
e
s
f
u
zz
y
i
n
f
er
en
ce
s
y
s
te
m
alg
o
r
ith
m
,
f
o
r
its
class
i
f
icatio
n
.
T
h
e
d
iag
n
o
s
tic
s
y
s
te
m
i
n
t
h
e
r
esear
c
h
i
s
p
r
ec
ed
ed
b
y
th
e
r
u
le
ex
tr
ac
tio
n
p
r
o
ce
s
s
u
s
i
n
g
a
C
4
.
5
alg
o
r
ith
m
.
Un
f
o
r
tu
n
atel
y
in
t
h
e
s
t
u
d
y
h
a
s
n
o
t
co
n
d
u
cted
a
p
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
th
at
ex
p
lain
s
h
o
w
m
u
c
h
i
m
p
r
o
v
e
m
en
t
a
n
d
lo
s
s
o
f
s
y
s
te
m
p
er
f
o
r
m
a
n
ce
,
f
o
r
ea
ch
ad
d
it
io
n
o
f
ex
a
m
i
n
atio
n
lev
el.
I
n
a
d
d
itio
n
,
at
th
e
lev
e
l
o
f
r
is
k
f
ac
to
r
e
x
a
m
in
atio
n
,
t
h
e
s
t
u
d
y
u
s
ed
f
r
a
m
i
n
g
h
a
m
r
i
s
k
s
co
r
e
m
o
d
elin
g
to
m
o
d
el
f
u
zz
y
r
u
le
-
b
ased
.
I
f
r
ef
er
r
ed
to
in
Ki
m
et.
al
'
s
s
tu
d
y
[
1
7
]
,
u
n
d
er
th
e
u
s
e
o
f
f
r
a
m
in
g
h
a
m
r
is
k
s
co
r
e
i
s
s
o
m
e
ti
m
es
u
n
s
u
itab
le
f
o
r
a
p
ar
ticu
lar
co
u
n
tr
y
,
th
i
s
is
d
u
e
t
o
th
e
d
ev
elo
p
m
en
t o
f
t
h
e
m
o
d
el
r
ef
er
s
to
a
p
o
p
u
latio
n
in
a
p
ar
ticu
lar
co
u
n
tr
y
.
R
ef
er
r
i
n
g
to
a
n
u
m
b
er
o
f
s
t
u
d
i
es
th
at
h
a
v
e
b
ee
n
d
o
n
e,
s
o
in
t
h
is
s
t
u
d
y
co
n
d
u
ct
p
er
f
o
r
m
a
n
c
e
an
al
y
s
i
s
o
f
ea
ch
le
v
el,
t
h
e
m
o
d
el
as
s
es
s
m
e
n
t
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
w
it
h
a
tier
ed
ap
p
r
o
ac
h
.
T
ier
ed
ap
p
r
o
ac
h
r
ef
e
r
s
to
a
co
m
m
o
n
l
y
u
s
ed
p
r
o
ce
d
u
r
e
o
f
clin
ician
s
i
n
t
h
e
d
iag
n
o
s
is
an
d
th
e
co
n
ce
p
t
o
f
a
tier
ed
s
y
s
te
m
J
KN
s
er
v
ice
s
.
A
r
ti
f
icial
in
te
lli
g
en
ce
al
g
o
r
ith
m
s
t
h
at
ar
e
u
s
ed
f
o
r
ea
ch
h
i
er
ar
ch
icall
y
u
s
in
g
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
.
T
h
e
s
y
s
te
m
i
s
d
i
v
id
ed
in
to
th
r
ee
l
ev
els
A
NN
s
y
s
te
m
.
A
t
th
e
f
i
r
s
t
an
d
th
e
t
h
ir
d
le
v
el
ar
c
h
ite
ctu
r
e
A
N
N
tr
ai
n
ed
u
s
i
n
g
th
e
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
alg
o
r
ith
m
,
w
h
i
le
th
e
s
ec
o
n
d
lev
el
u
s
in
g
t
h
e
o
n
e
s
tep
s
e
ca
n
t.
P
er
f
o
r
m
an
ce
p
ar
am
eter
s
an
al
y
ze
d
w
er
e
s
e
n
s
it
iv
i
t
y
,
s
p
ec
i
f
icit
y
,
p
o
s
itiv
e
p
r
ed
ictio
n
v
alu
e,
n
eg
at
iv
e
p
r
ed
ictio
n
v
alu
e,
t
h
e
ar
ea
u
n
d
er
th
e
cu
r
v
e
an
d
ac
c
u
r
ac
y
at
ev
er
y
lev
el.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
T
h
is
s
tu
d
y
u
s
ed
t
h
e
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
d
ata
s
et
o
f
t
h
e
UC
I
r
ep
o
s
ito
r
y
,
w
h
ic
h
ca
n
b
e
ac
ce
s
s
ed
o
n
lin
e
[
1
8
]
.
Data
s
et
co
n
s
i
s
ts
o
f
1
3
ex
a
m
in
at
io
n
attr
ib
u
tes
an
d
1
attr
ib
u
te
co
n
c
lu
s
io
n
e
x
a
m
i
n
atio
n
,
w
i
th
th
e
a
m
o
u
n
t
o
f
d
ata
as
m
u
ch
a
s
3
0
3
.
Data
s
et
ca
n
b
e
g
r
o
u
p
ed
b
ased
o
n
i
n
s
p
ec
tio
n
p
r
o
ce
d
u
r
es
co
n
s
is
tin
g
o
f
t
h
r
ee
g
r
o
u
p
s
.
T
h
e
f
ir
s
t
g
r
o
u
p
is
r
is
k
f
ac
to
r
s
,
b
o
th
m
o
d
if
ied
an
d
ca
n
n
o
t b
e
m
o
d
i
f
ied
,
as s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
el
1
.
R
is
k
f
ac
to
r
P
a
r
a
me
t
e
r
s
C
a
t
e
g
o
r
y
N
o
.
(
%)
M
e
a
n
±
S
D
A
g
e
5
4
,
4
3
9
±
9
,
0
G
e
n
d
e
r
1
:
M
e
n
2
0
6
(
6
7
,
9
9
)
0
:
W
o
me
n
9
7
(
3
2
,
0
1
)
D
i
a
st
o
l
i
c
b
l
o
o
d
p
r
e
ssu
r
e
(
mm
H
g
)
1
3
1
,
6
9
±
1
7
,
6
C
h
o
l
e
st
e
r
o
l
i
n
mg
/
d
l
2
4
6
,
6
9
±
5
1
,
7
8
F
a
st
i
n
g
b
l
o
o
d
su
g
e
r
1
:
>
1
2
0
mg
/
d
l
4
5
(
1
4
,
8
5
)
0
:
≤
1
2
0
mg
/
d
l
2
5
8
(
8
5
,
1
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
Th
e
A
n
a
lysi
s
o
f P
erfo
r
ma
ce
Mo
d
el
Tier
ed
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
fo
r
A
s
s
e
s
s
men
t o
f …
.
(
W
ih
a
r
to
W
ih
a
r
to
)
2185
T
h
e
s
ec
o
n
d
g
r
o
u
p
is
c
h
e
s
t
p
a
in
t
y
p
e
a
n
d
E
C
G,
w
h
ich
is
th
e
ex
a
m
i
n
atio
n
to
d
eter
m
i
n
e
t
h
e
t
y
p
e
o
f
ch
est
p
ain
an
d
ca
r
d
iac
elec
tr
ic
al
ac
tiv
it
y
,
b
o
th
d
u
r
in
g
r
es
t
a
n
d
ex
er
cise,
a
s
w
el
l
as
m
ax
i
m
u
m
h
ea
r
t
r
ate
d
u
r
in
g
ex
er
cise.
A
n
u
m
b
er
o
f
at
tr
ib
u
t
es a
n
d
ca
teg
o
r
ies o
f
i
n
s
p
ec
tio
n
r
esu
lts
a
s
s
h
o
w
n
i
n
T
ab
le
2
.
T
ab
el
2
.
C
h
est p
ain
t
y
p
e
a
n
d
elec
tr
o
ca
r
d
io
g
r
ap
h
y
(
E
C
G)
P
a
r
a
me
t
e
r
s
C
a
t
e
g
o
r
y
N
o
.
(
%)
M
e
a
n
±
S
D
C
h
e
st
p
a
i
n
t
y
p
e
1
:
T
y
p
i
c
a
l
A
n
g
i
n
a
2
3
(
7
,
5
9
)
2
:
a
t
y
p
i
c
a
l
a
n
g
i
n
a
5
0
(
1
6
,
5
)
3
:
n
o
n
-
a
n
g
i
n
a
l
p
a
i
n
,
8
6
(
2
8
,
3
8
)
4
:
a
sy
mt
o
mat
i
c
1
4
4
(
4
7
,
5
2
)
R
e
st
i
n
g
EC
G
0
:
N
o
r
mal
1
5
1
(
4
9
,
8
3
)
1
:
S
T
-
T
w
a
v
e
a
b
n
o
r
mal
4
(
1
,
3
2
)
2
:
V
e
n
t
r
i
c
u
l
a
r
h
y
p
e
r
t
r
o
p
h
y
1
4
8
(
4
8
,
8
4
)
M
a
x
i
m
u
m
h
e
a
r
t
r
a
t
e
a
c
h
i
e
v
e
d
1
4
9
,
6
1
±
2
2
,
8
8
Ex
e
r
c
i
se
i
n
d
u
c
e
d
a
n
g
i
n
a
1
:
Y
e
s
9
9
(
3
2
,
6
7
)
0
:
N
o
2
0
4
(
6
7
,
3
3
)
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
1
,
0
4
±
1
,
1
6
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
1
:
u
p
sl
o
p
i
n
g
1
4
2
(
4
6
,
8
6
)
2
:
f
l
a
t
1
4
0
(
4
6
,
2
0
)
3
:
d
o
w
n
sl
o
p
i
n
g
2
1
(
6
,
9
3
)
T
h
e
th
ir
d
g
r
o
u
p
is
f
l
u
o
r
o
s
c
o
p
y
a
n
d
s
ci
n
ti
g
r
ap
h
y
.
T
h
is
g
r
o
u
p
co
n
s
is
t
s
o
f
t
w
o
t
y
p
es
n
a
m
el
y
f
l
u
o
r
o
s
co
p
y
e
x
a
m
in
a
tio
n
to
d
eter
m
i
n
e
th
e
n
u
m
b
er
o
f
b
lo
o
d
v
es
s
els
co
n
s
tr
ict,
a
n
d
s
cin
tig
r
ap
h
y
to
d
eter
m
i
n
e
th
e
t
y
p
e
o
f
d
ef
ec
t t
h
at
o
cc
u
r
s
.
A
ttrib
u
te
a
n
d
ca
teg
o
r
y
e
x
a
m
in
atio
n
r
es
u
lts
ar
e
s
h
o
w
n
in
T
ab
le
3
.
I
n
ad
d
itio
n
,
in
T
ab
le
3
also
co
n
tain
ed
th
e
o
u
t
p
u
t a
ttrib
u
te
tes
ts
r
es
u
lts
s
h
o
wed
n
o
r
m
a
l o
r
co
r
o
n
ar
y
ar
te
r
y
a
b
n
o
r
m
alitie
s
.
T
ab
el
3
.
Flu
o
r
o
s
co
p
y
an
d
Sci
n
tig
r
ap
h
y
P
a
r
a
me
t
e
r
s
C
a
t
e
g
o
r
y
N
o
.
(
%)
M
e
a
n
±
S
D
N
u
mb
e
r
o
f
ma
j
o
r
v
e
sse
l
s
c
o
l
o
r
e
d
b
y
f
l
u
o
r
o
sco
p
y
(
0
-
3)
0
:
N
o
r
mal
1
:
S
i
n
g
l
e
V
e
ssel
2
:
D
o
u
b
l
e
V
e
sse
l
3
:
T
r
i
p
p
l
e
V
e
sse
l
D
e
f
e
c
t
t
y
p
e
(
S
c
i
n
t
i
g
r
a
p
h
y
)
3
:
N
o
r
mal
1
6
6
(
5
4
,
7
9
)
6
:
f
i
x
e
d
d
e
f
e
c
t
1
8
(
5
,
9
4
)
7
:
r
e
v
e
r
si
b
l
e
d
e
f
e
c
t
1
1
7
(
3
8
,
6
)
L
e
v
e
l
H
e
a
r
t
d
i
se
a
se
(
0
/
1
)
0
:
N
o
r
mal
1
6
4
(
5
4
,
1
2
)
1
:
A
b
n
o
r
mal
1
3
9
(
4
5
,
8
8
)
2
.
3
.
Art
if
icia
l N
eura
l N
et
w
o
rk
T
h
is
s
t
u
d
y
u
s
e
s
a
m
u
lti
-
la
y
e
r
A
N
N
ar
ch
i
tectu
r
e,
u
s
in
g
t
w
o
t
y
p
es
o
f
tr
ai
n
i
n
g
alg
o
r
it
h
m
w
h
ic
h
L
e
v
en
b
er
g
-
Ma
r
q
u
ar
d
t
(
L
M)
a
n
d
o
n
e
s
tep
s
ec
an
t
(
OS
S).
On
e
s
tep
s
ec
an
t
alg
o
r
it
h
m
is
a
b
r
id
g
e
b
et
w
ee
n
q
u
as
i
-
n
e
w
to
n
al
g
o
r
ith
m
w
it
h
t
h
e
co
n
j
u
g
ate
g
r
ad
ien
t.
T
h
is
alg
o
r
it
h
m
d
o
es
n
o
t
s
to
r
e
th
e
co
m
p
lete
h
ess
ia
n
m
atr
ix
.
I
n
th
e
alg
o
r
it
h
m
a
s
s
u
m
es
t
h
at
t
h
e
p
r
ev
io
u
s
H
es
s
ian
m
atr
i
x
is
th
e
id
en
ti
t
y
m
atr
i
x
s
o
th
at
t
h
e
m
o
d
el
ch
an
g
e
in
w
ei
g
h
t th
a
t o
cc
u
r
s
i
n
ea
ch
i
ter
atio
n
ca
n
b
e
s
h
o
w
n
i
n
E
q
u
atio
n
(
1
)
.
(
1
)
w
h
er
e
W
k
i
s
t
h
e
w
e
ig
h
t
v
al
u
es
to
k
,
H
k
i
s
t
h
e
h
es
s
ia
n
m
atr
i
x
o
f
t
h
e
p
er
f
o
r
m
a
n
ce
in
d
e
x
w
ei
g
h
t
s
t
h
e
v
al
u
e
o
f
al
l
k
[
1
9
]
.
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
w
i
t
h
L
e
v
e
n
b
er
g
-
Ma
r
q
u
ar
d
t
tr
ain
i
n
g
al
g
o
r
ith
m
d
esi
g
n
ed
u
s
i
n
g
th
e
s
ec
o
n
d
d
er
iv
ativ
e
ap
p
r
o
ac
h
w
it
h
o
u
t
h
av
in
g
to
ca
lc
u
late
t
h
e
h
e
s
s
ia
n
m
atr
ix
[
2
0
]
.
T
h
e
Hess
i
an
m
atr
ix
ca
n
b
e
ap
p
r
o
x
im
a
ted
u
s
i
n
g
E
q
u
atio
n
(
2
)
.
(
2
)
W
h
er
e
J
is
th
e
J
ac
o
b
ian
m
a
tr
ix
,
w
h
ich
co
n
tai
n
s
t
h
e
f
ir
s
t
d
er
iv
ativ
e
o
f
a
n
et
w
o
r
k
er
r
o
r
to
th
e
w
e
ig
h
t
s
,
s
y
m
b
o
lized
,
e,
w
h
ile
th
e
s
lo
p
e
ca
n
b
e
ca
lcu
lated
u
s
in
g
E
q
u
at
io
n
(
3
)
(3
)
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
.
4
,
A
u
g
u
s
t
2
0
1
7
:
2
1
8
3
–
2
1
9
1
2186
W
eig
h
t i
m
p
r
o
v
e
m
en
t in
L
M
al
g
o
r
ith
m
ca
n
b
e
ex
p
r
es
s
ed
in
a
n
E
q
u
atio
n
(
4
)
[
2
1
]
.
[
]
(
4
)
I
f
th
e
v
al
u
e
o
f
μ
=
0
,
t
h
en
th
i
s
m
et
h
o
d
is
t
h
e
s
a
m
e
a
s
t
h
e
m
et
h
o
d
o
f
Ne
w
to
n
,
a
n
d
i
f
to
o
lar
g
e
w
o
u
ld
b
e
t
h
e
s
a
m
e
as t
h
e
g
r
ad
ien
t d
esce
n
t
w
it
h
a
v
er
y
s
m
all
lear
n
i
n
g
r
ate
.
2
.
4
.
T
iere
d
M
o
del o
f
A
ss
ess
m
ent
C
o
ro
na
ry
H
ea
r
t
D
is
ea
s
e
Mo
d
el
ass
ess
m
e
n
t
s
y
s
te
m
o
f
c
o
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
is
d
i
v
id
e
d
in
to
th
r
ee
le
v
el
s
.
T
h
e
f
ir
s
t
le
v
el
is
th
e
ass
es
s
m
en
t
o
f
th
e
r
i
s
k
f
ac
to
r
s
,
w
h
ic
h
co
n
s
i
s
t
o
f
f
i
v
e
attr
ib
u
t
es.
T
h
e
s
ec
o
n
d
lev
el,
an
as
s
es
s
m
e
n
t
o
f
c
h
est
p
ai
n
t
y
p
e
an
d
i
n
s
p
ec
tio
n
e
lectr
o
ca
r
d
io
g
r
ap
h
y
(
E
C
G)
,
eit
h
er
at
r
e
s
t
o
r
ex
er
cise.
F
u
r
th
er
m
o
r
e,
th
e
th
ir
d
lev
el
i
s
an
ass
es
s
m
en
t b
y
s
ci
n
ti
g
r
ap
h
y
e
x
a
m
i
n
atio
n
a
n
d
f
lu
o
r
o
s
co
p
y
.
M
o
d
el
ass
ess
m
e
n
t s
y
s
te
m
o
f
co
r
o
n
ar
y
h
ea
r
t d
i
s
ea
s
e
b
y
u
s
i
n
g
t
h
e
ar
tif
icia
l
n
e
u
r
al
n
et
w
o
r
k
i
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
T
h
e
tier
ed
m
o
d
el
ad
o
p
ts
th
e
p
r
o
ce
d
u
r
es
u
s
ed
b
y
clin
icia
n
s
,
a
n
d
also
t
h
e
co
n
c
ep
t
o
f
tier
ed
in
J
KN
s
er
v
ice
s
y
s
te
m
.
W
h
e
n
r
ef
er
r
i
n
g
to
t
h
e
J
KN
s
y
s
te
m
,
i
n
m
ak
in
g
a
d
iag
n
o
s
is
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e,
ca
n
n
o
t
b
e
s
er
v
ed
d
ir
ec
tl
y
in
t
h
e
p
ath
o
f
s
er
v
ice
J
KN.
T
h
e
lev
el
o
f
s
er
v
ice
th
a
t
m
u
s
t
b
e
p
ass
e
d
f
ir
s
t
i
s
t
h
e
p
r
i
m
ar
y
s
er
v
ice,
th
e
s
er
v
ice
ca
n
co
n
d
u
c
t
an
i
n
itial
s
cr
ee
n
i
n
g
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
I
f
t
h
e
p
o
s
itiv
e
s
cr
ee
n
i
n
g
r
esu
lt
s
,
th
e
n
co
n
ti
n
u
e
o
n
th
e
le
v
el
o
f
s
ec
o
n
d
ar
y
s
er
v
ices
f
o
r
f
u
r
t
h
er
d
iag
n
o
s
i
s
f
o
r
E
C
G
e
x
a
m
in
at
io
n
,
eit
h
er
at
r
est
o
r
ex
er
cise.
I
f
n
ec
e
s
s
ar
y
,
it
ca
n
b
e
ex
a
m
i
n
ed
a
s
f
l
u
o
r
o
s
co
p
y
a
n
d
s
cin
tig
r
ap
h
y
.
T
h
e
s
ec
o
n
d
t
y
p
e
o
f
ex
a
m
i
n
at
io
n
t
h
e
p
atie
n
t
m
a
y
o
n
l
y
b
e
s
er
v
ed
at
t
h
e
ter
tiar
y
ca
r
e
lev
el
.
T
h
e
tier
ed
m
o
d
el
o
f
ANN
s
h
o
w
n
i
n
Fi
g
u
r
e
1
,
is
d
i
v
id
ed
i
n
to
t
h
r
ee
lev
e
ls
,
t
h
e
f
ir
s
t
le
v
e
l
o
f
a
r
i
s
k
f
ac
to
r
,
th
e
s
ec
o
n
d
le
v
el
o
f
c
h
e
s
t p
ain
&
E
C
G,
a
n
d
th
e
t
h
ir
d
l
ev
el
o
f
s
ci
n
ti
g
r
ap
h
y
&
f
l
u
o
r
o
s
co
p
y
.
I
n
ad
d
itio
n
to
th
e
s
y
s
te
m
i
s
d
iv
id
ed
in
to
t
h
r
ee
lev
els,
t
h
e
s
y
s
te
m
is
al
s
o
d
iv
id
ed
in
to
t
w
o
s
ta
g
es
o
f
t
h
e
p
r
o
ce
s
s
,
n
a
m
el
y
t
h
e
p
r
o
ce
s
s
o
f
tr
ain
i
n
g
a
n
d
test
in
g
.
T
h
e
tr
ai
n
i
n
g
p
r
o
ce
s
s
i
s
d
o
n
e
at
ea
ch
lev
e
l
to
g
et
o
p
ti
m
al
ar
ch
itectu
r
e
o
f
th
e
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
.
T
r
ai
n
in
g
f
o
r
th
e
f
ir
s
t
an
d
th
ir
d
lev
els
u
s
i
n
g
a
L
ev
e
n
b
er
g
-
Ma
r
q
u
a
r
d
t
alg
o
r
ith
m
,
w
h
ile
at
th
e
s
ec
o
n
d
le
v
el
u
s
in
g
o
n
e
s
tep
s
ec
a
n
t
al
g
o
r
ith
m
.
T
h
e
r
es
u
lti
n
g
ar
ch
ite
c
tu
r
e
i
n
t
h
e
tr
ai
n
in
g
p
r
o
ce
s
s
is
t
h
en
u
s
ed
as
a
s
y
s
te
m
m
o
d
el
f
o
r
as
s
ess
m
e
n
t
o
f
co
r
o
n
ar
y
h
ea
r
t
d
i
s
ea
s
e.
A
r
ti
f
icial
n
e
u
r
al
n
et
w
o
r
k
ar
ch
i
tectu
r
e
u
s
e
s
t
w
o
h
id
d
en
la
y
er
s
,
w
it
h
t
h
e
o
p
ti
m
al
ar
ch
itec
tu
r
e
o
n
t
h
e
f
ir
s
t
lev
el
is
5
-
20
-
15
-
1
.
T
h
e
ar
ch
it
ec
tu
r
e
co
n
s
i
s
ts
o
f
5
n
eu
r
o
n
s
in
th
e
i
n
p
u
t
la
y
er
,
2
0
n
e
u
r
o
n
s
i
n
t
h
e
f
ir
s
t
la
y
er
h
id
d
en
,
1
5
n
e
u
r
o
n
s
i
n
t
h
e
s
ec
o
n
d
h
id
d
en
la
y
er
a
n
d
1
n
eu
r
o
n
i
n
t
h
e
o
u
tp
u
t
la
y
er
.
I
n
th
e
s
ec
o
n
d
le
v
el,
t
h
e
ar
c
h
ite
ctu
r
e
u
s
ed
i
s
6
-
30
-
25
-
1
,
w
h
il
e
o
n
t
h
e
th
ir
d
lev
e
l
2
-
20
-
15
-
1.
T
h
e
p
r
o
p
o
s
ed
n
eu
r
al
n
et
w
o
r
k
ar
ch
itec
tu
r
e
m
o
d
el
u
s
es
a
n
u
m
b
er
o
f
ac
ti
v
atio
n
f
u
n
cti
o
n
s
,
f
ir
s
tl
y
s
ig
m
o
id
b
ip
o
lar
(
tan
s
ig
)
f
o
r
t
h
e
f
ir
s
t
h
id
d
en
la
y
er
.
T
h
e
s
e
co
n
d
is
b
in
ar
y
s
i
g
m
o
id
(
lo
g
s
i
g
)
f
o
r
t
h
e
s
ec
o
n
d
h
id
d
en
la
y
er
.
T
h
e
th
ir
d
is
a
lin
ea
r
f
u
n
c
tio
n
(
p
u
r
elin
)
f
o
r
th
e
o
u
tp
u
t
la
y
er
.
T
h
e
ac
tiv
atio
n
f
u
n
ctio
n
is
t
h
e
s
a
m
e,
b
o
th
f
o
r
tr
ain
i
n
g
u
s
i
n
g
a
L
e
v
e
n
b
er
g
-
Ma
r
q
u
ar
d
t a
lg
o
r
ith
m
a
n
d
o
n
e
s
tep
s
ec
an
alg
o
r
it
h
m
.
D
a
t
a
E
x
p
e
r
i
m
e
n
t
G
r
o
u
p
i
n
g
T
r
a
i
n
i
n
g
A
N
N
w
i
t
h
L
e
v
e
n
b
e
r
g
-
M
a
r
q
u
a
r
d
t
P
r
e
p
r
o
c
e
s
s
i
n
g
R
e
m
o
v
e
M
i
s
s
i
n
g
V
a
l
u
e
D
a
t
a
T
r
a
i
n
i
n
g
R
i
s
k
F
a
c
t
o
r
D
a
t
a
T
r
a
i
n
i
n
g
C
h
e
s
t
p
a
i
n
&
E
C
G
D
a
t
a
T
r
a
i
n
i
n
g
S
c
i
n
i
t
g
r
a
p
h
y
&
F
l
o
u
r
o
s
c
o
p
y
T
r
a
i
n
i
n
g
A
N
N
w
i
t
h
O
n
e
S
t
e
p
S
e
c
a
n
t
T
r
a
i
n
i
n
g
A
N
N
w
i
t
h
L
e
v
e
n
b
e
r
g
-
M
a
r
q
u
a
r
d
t
A
r
c
h
i
t
e
c
t
u
r
e
A
N
N
[
5
-
2
0
-
1
5
-
1
]
A
r
c
h
i
t
e
c
t
u
r
e
A
N
N
[
6
-
3
0
-
2
5
-
1
]
A
r
c
h
i
t
e
c
t
u
r
e
A
N
N
[
2
-
2
0
-
1
5
-
1
]
D
a
t
a
T
e
s
t
i
n
g
T
h
e
f
i
r
s
t
t
i
e
r
A
r
c
i
t
e
c
t
u
r
e
A
N
N
[
5
-
2
0
-
1
5
-
1
]
T
h
e
s
e
c
o
n
d
t
i
e
r
A
r
c
i
t
e
c
t
u
r
e
A
N
N
[
6
-
3
0
-
2
5
-
1
]
T
h
e
t
h
i
r
d
t
i
e
r
A
r
c
i
t
e
c
t
u
r
e
A
N
N
[
2
-
2
0
-
1
5
-
1
]
S
p
l
i
t
D
a
t
a
D
a
t
a
T
r
a
i
n
i
n
g
P
o
s
i
t
i
v
e
?
Y
e
s
P
o
s
i
t
i
v
e
?
Y
e
s
c
o
n
c
l
u
s
i
o
n
c
o
n
c
l
u
s
i
o
n
c
o
n
c
l
u
s
i
o
n
N
o
N
o
Fig
u
r
e
1
.
T
h
e
p
r
o
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
J
E
C
E
I
SS
N:
2088
-
8708
Th
e
A
n
a
lysi
s
o
f P
erfo
r
ma
ce
Mo
d
el
Tier
ed
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
fo
r
A
s
s
e
s
s
men
t o
f …
.
(
W
ih
a
r
to
W
ih
a
r
to
)
2187
2.
5.
P
er
f
o
r
m
a
nce
Ana
ly
s
i
s
P
er
f
o
r
m
a
n
ce
an
al
y
s
is
o
f
tier
e
d
ass
ess
m
e
n
t
s
y
s
te
m
m
o
d
el
u
s
in
g
ar
tific
ial
n
e
u
r
al
n
et
w
o
r
k
co
n
s
is
ts
o
f
s
ev
er
al
p
er
f
o
r
m
an
ce
p
ar
a
m
et
er
s
,
n
a
m
el
y
s
e
n
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
,
ac
c
u
r
ac
y
,
p
o
s
itiv
e
p
r
ed
ictio
n
v
alu
e
(
P
P
V)
,
n
eg
at
iv
e
p
r
ed
ictio
n
v
alu
e
(
NP
V)
,
an
d
u
n
d
er
t
h
e
c
u
r
v
e
(
AUC
)
ar
ea
.
T
h
ese
p
ar
a
m
eter
s
ca
n
b
e
d
er
iv
ed
f
r
o
m
t
h
e
m
atr
i
x
co
n
f
u
s
io
n
tab
le
s
h
o
wn
in
T
ab
le
4
.
T
h
e
ca
lcu
latio
n
E
q
u
atio
n
s
f
o
r
ea
ch
p
er
f
o
r
m
an
ce
p
ar
a
m
eter
as
s
h
o
w
n
in
(
5
-
1
1
)
.
T
ab
le
4
.
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
N
(
F
a
l
s
e
N
e
g
a
t
i
v
e
)
N
e
g
a
t
i
v
e
F
P
(
F
a
l
s
e
P
o
si
t
i
f
)
T
N
(
Tr
u
e
N
e
g
a
t
i
v
e
)
(
5
)
(
6
)
(
7
)
(
8
)
(
9
)
(
1
0
)
[
2
2
]
(
1
1
)
]
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
ier
e
d
ass
ess
m
en
t
s
y
s
te
m
m
o
d
el
test
in
g
ca
r
r
ied
o
u
t
b
y
u
s
i
n
g
d
atasets
f
r
o
m
t
h
e
U
n
i
v
er
s
i
t
y
C
alif
o
r
n
i
a
I
r
v
in
e
(
UC
I
)
r
ep
o
s
ito
r
y
[
1
8
]
.
T
h
e
d
ataset
is
d
ataset
C
lev
ela
n
d
's,
w
ith
a
d
is
tr
ib
u
tio
n
o
f
d
ata
1
7
8
f
o
r
tr
ain
in
g
an
d
1
0
0
f
o
r
test
in
g
.
T
h
e
test
r
esu
lt
s
ass
e
s
s
m
e
n
t
s
y
s
te
m
w
it
h
tier
ed
ap
p
r
o
ac
h
ca
n
b
e
g
r
o
u
p
ed
in
to
t
w
o
p
ar
ts
.
T
h
e
f
ir
s
t
is
a
p
er
f
o
r
m
a
n
ce
o
n
ea
ch
le
v
el,
b
o
th
th
e
p
er
f
o
r
m
a
n
ce
w
h
e
n
t
h
e
o
u
tp
u
t a
t p
r
ev
io
u
s
lev
el
s
te
s
ted
ag
ai
n
at
th
e
n
ex
t
le
v
el,
w
h
et
h
er
p
o
s
itiv
e
o
r
n
eg
ati
v
e
o
u
tp
u
t.
T
h
e
test
r
esu
l
ts
a
s
s
e
s
s
m
e
n
t
s
y
s
te
m
w
it
h
a
tier
ed
ap
p
r
o
ac
h
ca
n
b
e
s
h
o
w
n
i
n
T
ab
le
5
.
P
er
f
o
r
m
a
n
ce
test
r
e
s
u
l
ts
f
o
r
p
o
s
itiv
e
a
n
d
n
e
g
ati
v
e
o
u
tp
u
t
o
n
th
e
f
ir
s
t
tier
,
w
h
ich
w
as
te
s
te
d
ag
ain
o
n
th
e
s
ec
o
n
d
ti
er
i
s
s
h
o
w
n
i
n
T
ab
le
6
.
T
h
e
s
ec
o
n
d
is
p
er
f
o
r
m
an
ce
,
t
h
e
test
r
es
u
lt
s
w
h
en
th
e
o
u
tp
u
t,
eith
er
p
o
s
itiv
e
o
r
n
eg
a
tiv
e
o
n
th
e
s
e
co
n
d
tier
,
test
ed
a
g
ai
n
o
n
t
h
e
th
ir
d
tier
ar
e
s
h
o
w
n
in
T
ab
le
7
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
n
th
e
te
s
t
p
r
ess
i
n
g
o
n
p
ar
a
m
eter
p
er
f
o
r
m
a
n
ce
o
f
s
e
n
s
iti
v
it
y
,
s
p
ec
i
f
icit
y
,
a
n
d
ac
cu
r
ac
y
,
d
eter
m
i
n
es
t
h
e
le
v
e
l
o
f
r
ep
air
s
an
d
lo
s
s
o
f
t
h
e
s
ec
o
n
d
an
d
th
ir
d
tier
.
T
ab
le
5
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
ti
er
ed
ar
tif
icial
n
e
u
r
al
n
et
w
o
r
k
se
n
si
t
i
v
i
t
y
sp
e
c
i
f
i
c
i
t
y
PPV
N
P
V
A
U
C
A
c
c
u
r
a
c
y
T
h
e
f
i
r
st
t
i
e
r
0
,
7
8
7
2
0
,
4
5
2
8
0
,
5
6
0
6
0
,
7
0
5
9
0
,
6
2
0
0
0
,
6
1
0
0
T
h
e
s
e
c
o
n
d
t
i
e
r
0
,
6
5
9
6
0
,
9
4
3
4
0
,
9
1
1
8
0
,
7
5
7
6
0
,
8
0
1
5
0
,
8
1
0
0
T
h
e
t
h
i
r
d
t
i
e
r
0
,
6
5
9
6
0
,
9
4
3
4
0
,
9
1
1
8
0
,
7
5
7
6
0
,
8
0
1
5
0
,
8
1
0
0
T
ab
le
6
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
s
ec
o
n
d
tier
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
a
c
c
u
r
a
c
y
P
o
si
t
i
v
e
0
,
8
3
7
8
0
,
8
9
6
6
0
,
8
6
3
6
N
e
g
a
t
i
v
e
0
,
9
0
0
0
0
,
8
7
5
0
0
,
8
8
2
4
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
.
4
,
A
u
g
u
s
t
2
0
1
7
:
2
1
8
3
–
2
1
9
1
2188
T
ab
le
7
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
th
ir
d
tier
S
e
n
si
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
a
c
c
u
r
a
c
y
P
o
si
t
i
v
e
0
,
8
0
6
5
0
,
6
6
6
7
0
,
7
9
4
1
N
e
g
a
t
i
v
e
0
,
6
8
7
5
0
,
8
6
0
0
0
,
8
1
8
2
3
.
1
.
T
he
O
utput
A
na
ly
s
is
o
f
t
he
F
irst
T
ier
t
hen
E
x
a
m
i
ned a
t
t
he
S
ec
o
nd
T
ier
T
h
e
p
er
f
o
r
m
an
ce
o
f
tier
ed
d
iag
n
o
s
tic
s
y
s
te
m
,
ca
n
b
e
an
al
y
z
ed
its
p
er
f
o
r
m
a
n
ce
f
o
r
ea
ch
lev
el,
s
o
it
ca
n
k
n
o
w
t
h
e
i
n
f
lu
e
n
ce
o
f
ea
c
h
lev
el.
T
h
e
p
er
f
o
r
m
an
ce
a
n
al
y
s
i
s
is
d
iv
id
ed
in
to
t
w
o
b
ased
o
n
th
e
test
m
o
d
el.
T
h
e
f
ir
s
t,
w
h
e
n
t
h
e
f
ir
s
t
-
le
v
el
d
iag
n
o
s
t
ic
s
y
s
te
m
g
iv
e
s
n
eg
at
i
v
e
o
u
tp
u
t,
it
is
c
h
ec
k
ed
ag
ai
n
at
th
e
s
ec
o
n
d
lev
el.
T
h
e
s
ec
o
n
d
,
w
h
e
n
t
h
e
d
iag
n
o
s
tic
s
y
s
te
m
g
iv
e
s
a
p
o
s
itiv
e
r
esu
lt
at
t
h
e
f
ir
s
t
le
v
el,
it
is
r
et
ested
at
th
e
s
ec
o
n
d
lev
el.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
d
iag
n
o
s
t
ic
s
y
s
te
m
g
en
er
ate
d
b
ased
o
n
th
e
t
w
o
test
m
o
d
els
ca
n
b
e
s
h
o
w
n
i
n
T
ab
le
6
.
T
ab
le
8
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
o
f
o
u
tp
u
t
n
eg
at
iv
e
o
f
t
h
e
f
ir
s
t
tier
w
as te
s
ted
o
n
t
h
e
s
ec
o
n
d
ti
er
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
a
g
a
t
i
v
e
P
o
si
t
i
v
e
37
10
N
e
g
a
t
i
v
e
29
24
(
a)
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
9
1
N
e
g
a
t
i
v
e
3
21
(
b
)
T
o
ex
p
lain
th
e
p
er
f
o
r
m
an
ce
b
et
w
ee
n
t
h
e
f
ir
s
t
a
n
d
s
ec
o
n
d
tier
ca
n
b
e
e
x
p
lai
n
ed
w
it
h
r
ef
er
en
ce
to
T
ab
le
8
.
T
ab
le
8
(
a
)
s
h
o
w
s
th
e
co
n
f
u
s
io
n
m
atr
i
x
o
u
tp
u
t
o
n
t
h
e
f
ir
s
t
tier
.
A
t
t
h
e
tier
o
f
t
h
e
f
ir
s
t
n
e
g
ati
v
e
o
u
tp
u
t
n
u
m
b
er
o
f
3
4
p
atien
t
s
,
w
it
h
d
etails o
f
1
0
p
atien
ts
w
h
o
s
h
o
u
l
d
h
av
e
b
ee
n
p
o
s
itiv
e,
b
u
t
d
iag
n
o
s
ed
n
eg
ati
v
e,
a
n
d
2
4
p
atien
ts
n
e
g
ati
v
e
d
ia
g
n
o
s
e
d
n
eg
a
tiv
e.
T
ests
co
m
e
b
ac
k
o
n
t
h
e
s
ec
o
n
d
tier
g
e
n
er
ate
c
o
n
f
u
s
io
n
m
atr
i
x
a
s
s
h
o
w
n
i
n
T
ab
le
8
(
b
)
.
R
ef
e
r
r
i
n
g
to
t
h
e
tab
le
ca
n
b
e
a
ca
lc
u
lated
i
m
p
r
o
v
e
m
en
t
o
f
t
h
e
s
y
s
te
m
,
w
h
ic
h
is
1
0
p
atien
t
t
h
at
s
h
o
u
ld
b
e
p
o
s
itiv
e,
ab
le
to
b
e
d
iag
n
o
s
ed
p
o
s
iti
v
e
n
u
m
b
er
9
,
s
o
th
at
t
h
e
s
e
n
s
itiv
it
y
o
f
9
0
.
0
0
%
as
s
h
o
w
n
i
n
T
ab
le
6
.
T
h
e
s
en
s
it
i
v
it
y
v
alu
e
also
s
h
o
w
ed
a
p
er
f
o
r
m
a
n
ce
i
m
p
r
o
v
e
m
en
t
o
f
9
0
%
o
n
t
h
e
s
ec
o
n
d
tier
,
As
f
o
r
th
e
n
e
g
ati
v
e
p
atien
t
s
,
t
h
e
s
ec
o
n
d
tier
d
iag
n
o
s
ed
n
e
g
a
tiv
e
r
etu
r
n
o
f
8
7
.
5
%
o
r
a
lo
s
s
o
f
ab
o
u
t
2
.
5
%
at
th
e
s
ec
o
n
d
tier
.
T
ab
le
9
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
o
f
o
u
tp
u
t p
o
s
iti
v
e
o
f
t
h
e
f
ir
s
t t
ier
w
as te
s
ted
at
th
e
s
ec
o
n
d
tier
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
a
g
a
t
i
v
e
P
o
si
t
i
v
e
37
10
N
e
g
a
t
i
v
e
29
24
(
a)
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
31
6
N
e
g
a
t
i
v
e
3
26
(
b
)
Fu
r
t
h
er
an
al
y
s
is
to
th
e
o
u
tp
u
t
o
f
th
e
f
ir
s
t
tier
p
o
s
itiv
e,
w
er
e
r
etested
o
n
th
e
s
ec
o
n
d
tier
.
T
o
an
al
y
ze
th
e
p
er
f
o
r
m
a
n
ce
o
n
th
e
s
e
te
s
t
s
,
ca
r
r
ied
o
u
t
b
y
u
s
i
n
g
th
e
tab
le
j
u
s
t
as
th
e
co
n
f
u
s
io
n
m
atr
i
x
s
h
o
w
n
in
T
ab
le
9
.
Ou
tp
u
t
p
o
s
itiv
e
o
n
th
e
f
ir
s
t
tie
r
am
o
u
n
ted
to
6
6
p
atien
ts
,
co
n
s
i
s
ti
n
g
o
f
3
7
p
atien
ts
d
ia
g
n
o
s
ed
p
o
s
itiv
e
a
n
d
2
9
n
eg
a
t
iv
e
p
atie
n
ts
d
iag
n
o
s
ed
p
o
s
itiv
e,
j
u
s
t
as
s
h
o
w
n
i
n
T
ab
l
e
9
(
a)
.
T
h
e
test
r
esu
lts
b
ac
k
o
n
th
e
s
ec
o
n
d
tier
,
as
s
h
o
w
n
in
T
ab
le
9
(
b
)
.
T
h
ese
r
e
s
u
lt
s
s
h
o
w
ed
an
i
m
p
r
o
v
ed
p
er
f
o
r
m
a
n
ce
,
ie
p
atien
t
s
b
y
t
h
e
f
i
r
s
t
tier
s
h
o
u
ld
h
a
v
e
b
ee
n
a
n
eg
ati
v
e
b
u
t
p
o
s
iti
v
e
d
iag
n
o
s
is
,
th
e
2
9
p
atien
ts
,
t
h
e
s
ec
o
n
d
tier
is
ab
le
to
b
e
d
iag
n
o
s
ed
to
b
e
n
eg
ativ
e
as
m
an
y
a
s
2
6
p
atie
n
ts
.
T
h
e
i
m
p
r
o
v
e
m
e
n
t
in
t
h
e
a
m
o
u
n
t
o
f
s
p
ec
if
icit
y
as
s
h
o
w
n
in
T
ab
le
6
,
w
h
ic
h
i
s
8
9
.
6
6
%.
I
n
th
i
s
test
also
t
h
er
e
is
a
lo
s
s
,
ie
3
7
p
o
s
itiv
e
p
atien
ts
wh
o
w
er
e
d
iag
n
o
s
e
d
p
o
s
itiv
e
b
y
t
h
e
f
ir
s
t
tier
,
r
e
-
d
iag
n
o
s
ed
p
o
s
it
iv
e
b
y
t
h
e
s
ec
o
n
d
tier
o
f
3
1
p
atien
t
s
.
I
t
s
h
o
w
s
t
h
e
o
cc
u
r
r
e
n
ce
o
f
a
lo
s
s
o
f
1
-
s
e
n
s
i
tiv
it
y
,
o
r
b
y
1
6
.
2
2
%.
T
h
e
lo
s
s
v
alu
e
is
g
r
ea
ter
th
an
t
h
e
lo
s
s
t
h
at
o
cc
u
r
s
wh
en
te
s
ti
n
g
n
e
g
ati
v
e
(
h
ea
lt
h
y
)
.
3
.
2
.
T
he
O
utput
A
na
ly
s
is
o
f
t
he
S
ec
o
nd
T
ier
t
he
n
E
x
a
m
ine
d a
t
t
he
T
hird
T
ier
T
h
e
test
r
es
u
lt
w
h
e
n
t
h
e
o
u
t
p
u
t
at
t
h
e
s
ec
o
n
d
tier
,
te
s
ted
ag
ai
n
o
n
t
h
e
t
h
ir
d
tier
,
t
h
e
r
esu
lt
in
g
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
v
al
u
es
,
n
a
m
el
y
s
e
n
s
it
iv
it
y
,
s
p
ec
i
f
icit
y
,
an
d
ac
cu
r
ac
y
,
ca
n
b
e
s
h
o
w
n
in
T
ab
le
7
.
T
est
o
n
th
e
th
ir
d
tier
,
p
er
f
o
r
m
ed
well
w
h
e
n
t
h
e
o
u
tp
u
t
t
h
e
s
ec
o
n
d
tier
n
eg
a
tiv
e
an
d
p
o
s
iti
v
e.
T
o
b
e
ab
le
to
an
al
y
ze
in
m
o
r
e
d
etail,
w
e
ca
n
s
ee
th
e
p
er
f
o
r
m
a
n
ce
f
o
r
ea
ch
o
u
tp
u
t.
First
f
o
r
o
u
tp
u
t
t
h
e
s
ec
o
n
d
ti
er
n
eg
ati
v
e,
w
h
ic
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
Th
e
A
n
a
lysi
s
o
f P
erfo
r
ma
ce
Mo
d
el
Tier
ed
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
fo
r
A
s
s
e
s
s
men
t o
f …
.
(
W
ih
a
r
to
W
ih
a
r
to
)
2189
w
il
l
b
e
te
s
ted
a
g
ain
o
n
th
e
t
h
i
r
d
tier
,
th
e
r
e
s
u
l
tin
g
co
n
f
u
s
io
n
m
atr
i
x
a
s
s
h
o
w
n
i
n
T
ab
l
e
1
0
.
T
ab
le
1
0
(
a
)
s
h
o
w
s
th
at
t
h
e
o
u
tp
u
t
at
le
v
el
2
,
co
m
p
r
is
in
g
1
6
p
atien
t
s
p
o
s
iti
v
e
b
u
t
n
e
g
ati
v
e
d
etec
ted
a
n
d
5
0
p
atien
ts
w
it
h
n
e
g
ativ
e
an
d
n
e
g
ati
v
e
d
etec
ted
.
T
h
e
test
r
es
u
lts
co
m
e
b
ac
k
n
e
g
ati
v
e
o
u
tp
u
t
at
lev
el
2
,
w
er
e
te
s
te
d
b
ac
k
o
n
t
h
e
th
ir
d
tier
,
ar
e
s
h
o
w
n
in
T
ab
le
1
0
(
b
)
.
Ou
tp
u
t
a
t
th
e
th
ir
d
tier
in
d
i
ca
tes
a
p
er
f
o
r
m
a
n
ce
i
m
p
r
o
v
e
m
en
t
o
f
s
en
s
iti
v
it
y
v
alu
e,
ie
6
8
.
7
5
%
.
T
h
e
r
esu
lti
n
g
i
m
p
r
o
v
e
m
e
n
t
is
lo
w
er
t
h
a
n
w
h
e
n
t
h
e
o
u
tp
u
t
tes
ted
n
e
g
ativ
e
o
n
t
h
e
s
ec
o
n
d
tier
.
B
esid
es
an
i
m
p
r
o
v
e
m
e
n
t,
o
n
th
e
t
h
ir
d
tier
also
o
cc
u
r
r
elativ
el
y
lar
g
e
lo
s
s
,
w
h
i
ch
a
m
o
u
n
ted
to
1
-
s
p
ec
if
icit
y
,
ie
1
4
.
0
0
%.
T
ab
le
1
0
.
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
o
f
o
u
tp
u
t n
e
g
ati
v
e
o
f
t
h
e
s
ec
o
n
d
tier
w
as te
s
ted
at
th
e
t
h
ir
d
tier
.
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
a
g
a
t
i
v
e
P
o
si
t
i
v
e
31
16
N
e
g
a
t
i
v
e
3
50
(
a)
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
11
5
N
e
g
a
t
i
v
e
7
43
(
b
)
T
h
e
s
ec
o
n
d
test
is
w
h
en
t
h
e
o
u
tp
u
t
o
f
th
e
s
ec
o
n
d
tier
is
p
o
s
itiv
e
a
n
d
w
a
s
f
u
r
t
h
er
test
ed
at
th
e
th
ir
d
tier
.
T
o
ex
p
lain
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
te
m
ca
n
b
e
d
o
n
e
b
y
u
s
i
n
g
T
ab
le
1
1
.
T
h
e
o
u
tp
u
t
o
f
th
e
s
ec
o
n
d
tier
co
n
s
is
ted
o
f
3
1
p
atie
n
ts
p
o
s
iti
v
e
u
n
d
ia
g
n
o
s
ed
p
o
s
iti
v
e
an
d
3
p
atie
n
ts
n
e
g
ati
v
e
u
n
d
iag
n
o
s
ed
p
o
s
iti
v
e.
I
m
p
r
o
v
e
m
e
n
t o
f
s
y
s
te
m
p
er
f
o
r
m
an
ce
a
t th
e
th
ir
d
tier
i
n
d
icate
d
b
y
it
s
s
p
ec
i
f
icit
y
,
ie
6
6
.
6
7
%,
an
d
th
er
e
is
a
lo
s
s
o
f
1
-
s
en
s
iti
v
it
y
,
ie
1
9
.
5
3
%.
At
th
e
t
h
ir
d
tier
,
b
o
th
f
o
r
p
o
s
it
iv
e
a
n
d
n
eg
at
iv
e
o
u
tp
u
t
s
u
f
f
e
r
ed
o
n
l
y
r
elat
iv
el
y
litt
le
i
m
p
r
o
v
e
m
e
n
t,
b
u
t t
h
er
e
i
s
a
lo
s
s
o
f
r
elati
v
el
y
lar
g
e,
co
m
p
ar
ed
to
th
e
p
er
f
o
r
m
a
n
ce
at
th
e
s
ec
o
n
d
tier
.
T
ab
le
1
1
.
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
o
f
o
u
tp
u
t p
o
s
itiv
e
o
f
th
e
s
ec
o
n
d
tier
w
as te
s
ted
at
th
e
t
h
ir
d
tier
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
a
g
a
t
i
v
e
P
o
si
t
i
v
e
31
16
N
e
g
a
t
i
v
e
3
50
(
a)
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
25
6
N
e
g
a
t
i
v
e
1
2
(
b
)
T
h
e
test
r
esu
lts
at
th
e
th
ir
d
ti
er
,
s
h
o
w
s
a
r
elativ
e
l
y
lar
g
e
lo
s
s
o
cc
u
r
s
,
b
u
t
b
alan
ce
d
w
it
h
a
r
elativ
el
y
h
ig
h
i
m
p
r
o
v
e
m
e
n
t.
T
h
ese
co
n
d
itio
n
s
m
a
k
e
t
h
e
p
er
f
o
r
m
an
ce
at
th
e
th
ir
d
tier
n
o
t
r
elativ
e
g
i
v
e
i
m
p
r
o
v
e
m
e
n
t
o
f
o
u
tp
u
t
a
t
t
h
e
s
ec
o
n
d
tier
.
T
h
i
s
ca
n
b
e
s
h
o
w
n
i
n
T
ab
le
5
,
w
h
er
e
th
e
v
al
u
e
o
f
p
er
f
o
r
m
an
ce
p
ar
am
eter
s
d
o
es
n
o
t
ch
an
g
e.
B
y
v
al
u
e,
it r
ei
n
f
o
r
ce
s
th
e
te
s
t a
t t
h
e
s
ec
o
n
d
tier
,
b
u
t
n
o
t so
w
h
en
a
n
al
y
ze
d
f
o
r
ea
c
h
d
ata,
as d
escr
ib
ed
in
th
e
a
n
al
y
s
i
s
in
T
ab
le
1
0
-
1
1
,
it
m
ea
n
s
t
h
at
th
er
e
ar
e
s
o
m
e
i
m
p
r
o
v
e
m
e
n
t a
n
d
s
o
m
e
lo
s
s
.
3.
3
.
Ana
ly
s
is
t
iere
d
m
o
de
l per
f
o
rm
a
nce
A
NN
P
er
f
o
r
m
a
n
ce
ass
e
s
s
m
e
n
t
tier
e
d
s
y
s
te
m
w
it
h
A
NN,
t
h
e
f
ir
s
t
t
ier
is
ab
le
to
p
r
o
v
id
e
s
en
s
it
iv
i
t
y
v
al
u
e
o
f
7
8
.
7
2
%,
as
s
h
o
w
n
i
n
T
ab
le
5
.
T
h
is
v
alu
e
i
n
d
icate
s
t
h
at
w
h
e
n
p
atien
ts
d
ec
lar
ed
p
o
s
itiv
e,
th
e
s
y
s
te
m
i
s
ex
p
r
ess
ed
s
tr
o
n
g
l
y
p
o
s
iti
v
e
w
i
th
a
p
er
ce
n
tag
e
o
f
7
8
.
7
2
%,
w
h
er
ea
s
w
h
e
n
th
e
p
atie
n
t
is
d
ec
lar
ed
n
eg
ativ
e,
t
h
e
s
y
s
t
e
m
ac
tu
al
l
y
d
ec
lar
ed
n
e
g
ativ
e
b
y
t
h
e
p
er
ce
n
ta
g
e
o
f
t
h
e
v
alu
e
o
f
s
p
ec
i
f
icit
y
,
ie
4
5
.
2
8
%.
P
er
f
o
r
m
an
ce
d
iag
n
o
s
i
s
s
y
s
te
m
o
n
t
h
e
f
ir
s
t
tier
is
a
p
r
ed
ictio
n
b
ased
o
n
r
is
k
f
ac
to
r
s
.
T
h
is
i
s
co
m
p
a
r
ed
to
t
h
e
r
esear
ch
co
n
d
u
cted
b
y
Ki
m
et.
al
[
1
7
]
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
h
a
s
b
etter
p
er
f
o
r
m
an
ce
.
T
h
e
p
er
f
o
r
m
an
ce
in
r
e
s
ea
r
ch
K
i
m
et.
al
[
1
7
]
,
w
h
e
n
u
s
in
g
al
g
o
r
ith
m
s
A
NN,
p
ar
a
m
eter
s
e
n
s
itiv
it
y
p
er
f
o
r
m
a
n
ce
o
f
7
3
.
1
0
%,
w
h
ile
4
3
.
5
9
%
s
p
ec
if
icit
y
.
Sti
ll,
in
t
h
e
s
a
m
e
s
tu
d
y
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
b
etter
co
m
p
ar
ed
u
s
i
n
g
lo
g
is
tic
r
eg
r
e
s
s
io
n
alg
o
r
ith
m
an
d
C
5
.
0
.
I
t
is
d
if
f
er
en
t
w
h
e
n
co
m
p
ar
ed
to
th
e
u
s
e
o
f
A
NN
i
n
r
esear
ch
Ya
n
g
.
et.
al
[
2
3
]
,
th
e
p
er
f
o
r
m
a
n
ce
o
n
th
e
f
ir
s
t
tier
is
r
el
ati
v
el
y
lo
w
er
.
I
n
r
esea
r
ch
Yan
g
et.
al
[
2
3
]
,
th
e
r
es
u
lti
n
g
p
er
f
o
r
m
a
n
ce
p
ar
am
eter
s
s
en
s
iti
v
it
y
o
f
8
5
.
7
%.
T
h
e
h
ig
h
s
e
n
s
it
iv
i
t
y
an
d
s
p
ec
if
icit
y
p
er
f
o
r
m
a
n
ce
in
r
esea
r
ch
Yan
g
et.
al
[
2
3
]
,
o
n
e
o
f
t
h
e
f
ac
to
r
s
d
u
e
to
th
e
n
u
m
b
er
o
f
attr
ib
u
te
s
t
h
at
ar
e
u
s
ed
in
t
h
e
d
iag
n
o
s
i
s
m
o
r
e,
co
m
p
ar
ed
to
th
e
s
y
s
te
m
p
r
o
p
o
s
ed
.
Ass
es
s
m
en
t
s
y
s
te
m
at
t
h
e
s
ec
o
n
d
an
d
th
e
th
ir
d
tier
h
av
e
a
s
i
m
ilar
p
er
f
o
r
m
a
n
ce
,
w
h
ich
m
ea
n
s
th
at
ch
ec
k
s
o
n
t
h
e
th
ir
d
tier
r
ein
f
o
r
ce
ch
ec
k
s
o
n
th
e
s
ec
o
n
d
tier
,
th
at
i
f
o
n
l
y
li
m
ited
atte
n
tio
n
to
th
e
p
er
f
o
r
m
a
n
ce
p
ar
am
eter
v
al
u
e.
T
h
e
m
o
v
e
m
en
t
o
f
t
h
e
p
atien
t
ch
a
n
g
e
s
w
h
en
test
ed
at
t
h
e
s
ec
o
n
d
tier
a
n
d
test
ed
at
th
e
th
ir
d
tier
,
f
o
r
th
e
o
u
tp
u
t
p
o
s
itiv
e
o
f
th
e
p
r
ev
io
u
s
tier
ca
n
b
e
v
ie
w
e
d
in
d
etail
in
T
ab
le
1
0
-
11.
A
c
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
p
ar
am
eter
s
f
o
r
t
h
e
s
ec
o
n
d
tier
r
ea
ch
ed
a
v
al
u
e
o
f
8
1
.
0
0
%,
t
h
e
p
er
f
o
r
m
an
ce
is
b
etter
t
h
an
a
tier
ed
ap
p
r
o
ac
h
in
r
esear
ch
W
i
h
ar
to
et.
al
[
1
5
]
,
w
h
ich
o
n
l
y
r
ea
c
h
ed
7
5
.
4
2
%.
R
esear
ch
W
i
h
ar
to
et.
al
[
1
5
]
u
s
i
n
g
a
t
ier
ed
co
n
ce
p
t
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
.
4
,
A
u
g
u
s
t
2
0
1
7
:
2
1
8
3
–
2
1
9
1
2190
th
at
is
i
m
p
le
m
e
n
ted
w
i
th
f
u
z
z
y
i
n
f
er
en
ce
s
y
s
te
m
(
FIS)
,
wh
ich
p
r
ec
ed
ed
h
is
r
u
le
-
m
a
k
i
n
g
al
g
o
r
ith
m
C
4
.
5
.
W
h
en
co
m
p
ar
ed
to
o
th
er
s
tu
d
ies,
w
h
ic
h
b
o
th
u
s
e
A
NN,
s
u
ch
a
s
in
r
esear
c
h
W
ih
ar
to
e
t.a
l
[
1
6
]
,
p
ar
am
eter
ac
cu
r
ac
y
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
is
r
elati
v
el
y
lo
w
er
.
I
t'
s
j
u
s
t
t
h
at
t
h
er
e
ar
e
d
if
f
er
en
ce
s
in
t
h
e
ap
p
licatio
n
o
f
its
ti
er
ed
co
n
ce
p
t,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
u
s
ed
in
m
ak
in
g
th
e
d
ia
g
n
o
s
is
,
w
h
er
ea
s
i
n
th
e
s
t
u
d
y
W
ih
ar
to
et.
al
[
1
6
]
u
s
in
g
a
tier
e
d
co
n
ce
p
t to
p
er
f
o
r
m
r
ed
u
ctio
n
o
f
attr
ib
u
te
s
d
i
m
e
n
s
io
n
s
.
4.
CO
NCLU
SI
O
N
An
as
s
es
s
m
e
n
t
s
y
s
te
m
m
o
d
el
w
it
h
a
t
ier
ed
ap
p
r
o
ac
h
u
s
in
g
A
N
N,
ab
le
to
p
r
o
v
id
e
i
m
p
r
o
v
e
m
en
t
an
d
s
tr
en
g
t
h
e
n
i
n
g
p
er
f
o
r
m
a
n
ce
f
o
r
ea
ch
i
n
cr
ea
s
i
n
g
o
f
le
v
el.
T
h
e
r
esu
lti
n
g
p
er
f
o
r
m
a
n
ce
at
t
h
e
s
ec
o
n
d
tier
w
ith
th
e
attr
ib
u
te
co
n
s
is
ti
n
g
o
f
t
h
e
r
is
k
f
ac
to
r
,
ch
est
p
ain
t
y
p
e
a
n
d
E
C
G
ab
le
to
g
i
v
e
8
1
.
0
0
%
ac
cu
r
ac
y
p
er
f
o
r
m
a
n
ce
.
T
h
e
p
er
f
o
r
m
a
n
ce
i
s
b
etter
t
h
a
n
a
n
u
m
b
er
o
f
p
r
ev
io
u
s
s
t
u
d
ie
s
.
E
s
p
ec
iall
y
at
t
h
e
t
h
ir
d
le
v
el
s
h
o
w
s
t
h
e
b
alan
ce
o
f
r
ep
air
s
an
d
lo
s
s
,
s
o
t
h
e
p
er
f
o
r
m
an
ce
at
t
h
e
t
h
ir
d
tier
is
r
elativ
el
y
t
h
e
s
a
m
e
w
i
th
th
e
p
er
f
o
r
m
a
n
ce
at
th
e
s
ec
o
n
d
tier
,
o
r
ca
n
b
e
s
ee
n
b
y
th
e
v
alu
e
o
f
p
er
f
o
r
m
an
ce
p
ar
a
m
eter
s
o
cc
u
r
r
ed
th
e
s
tr
en
g
th
e
n
in
g
o
f
t
h
e
p
r
ev
io
u
s
lad
d
er
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
w
o
u
ld
li
k
e
to
th
an
k
t
h
e
Se
b
elas
Ma
r
et
Un
iv
er
s
it
y
I
n
d
o
n
e
s
ia,
w
h
ic
h
h
a
s
p
r
o
v
id
ed
r
esear
ch
g
r
a
n
ts
w
it
h
f
u
n
d
in
g
P
NB
P
UNS,
b
y
co
n
tr
ac
t
n
u
m
b
er
:
6
3
2
/UN2
7
.
2
1
/L
T
/2
0
1
6
.
T
h
e
au
th
o
r
s
th
a
n
k
t
h
e
an
o
n
y
m
o
u
s
r
ef
er
ee
s
f
o
r
th
e
ir
co
n
s
tr
u
cti
v
e
s
u
g
g
esti
o
n
s
a
n
d
co
m
m
e
n
ts
w
h
ich
h
e
lp
ed
in
th
e
i
m
p
r
o
v
e
m
e
n
t
o
f
th
e
p
r
esen
tatio
n
o
f
th
e
m
a
n
u
s
cr
ip
t
.
RE
F
E
R
E
NC
E
S
[1
]
H.
K.
L
e
e
,
H.
K.
Ki
m
,
“
L
i
f
e
st
y
l
e
a
n
d
He
a
lt
h
-
Re
late
d
Qu
a
li
ty
o
f
L
i
f
e
b
y
Ty
p
e
-
D
P
e
rso
n
a
li
ty
in
th
e
P
a
ti
e
n
ts
w
it
h
Isc
h
e
m
ic He
a
rt
Dise
a
se
,
”
In
d
ia
n
J
.
S
c
i.
T
e
c
h
n
o
l
.
2
0
1
6
;
9
(
13
):
1
–
1
0
.
[2
]
F
.
Id
ris,
“
Op
ti
m
a
li
sa
si
sist
e
m
p
e
la
y
a
n
a
n
k
e
se
h
a
tan
b
e
rjen
jan
g
p
a
d
a
p
ro
g
ra
m
Ka
rtu
Ja
k
a
rta
S
e
h
a
t,
”
Ke
sm
a
s
Na
tl
.
Pu
b
li
c
He
a
lt
h
J
.
2
0
1
4
;
9
(
1
):
94
–
1
0
0
.
[3
]
W
.
W
ih
a
rto
,
H.
Ku
sn
a
n
t
o
,
a
n
d
H.
He
rian
to
,
“
In
ter
p
re
tatio
n
o
f
Cli
n
ica
l
Da
ta
Ba
se
d
o
n
C4
.
5
A
lg
o
rit
h
m
f
o
r
th
e
Dia
g
n
o
sis o
f
Co
ro
n
a
ry
He
a
rt
Dis
e
a
se
,
”
He
a
lt
h
c
.
In
fo
rm
.
Res
.
2
0
1
6
;
22
(
3
):
1
8
6
,
2
0
1
6
.
[4
]
X
.
L
iu
e
t
a
l.
,
“
A
H
y
b
rid
Clas
si
f
ic
a
ti
o
n
S
y
ste
m
f
o
r
H
e
a
rt
Dise
a
se
D
iag
n
o
sis
Ba
se
d
o
n
th
e
RF
RS
M
e
t
h
o
d
,
”
Co
mp
u
t.
M
a
th
.
M
e
th
o
d
s M
e
d
.
2
0
1
7
;
2
0
1
7
(
2
0
1
7
):
1
–
1
1
.
[5
]
K.
Ra
jala
k
sh
m
i
a
n
d
K.
Nirm
a
l
a
,
“
He
a
rt
Dise
a
se
P
re
d
ictio
n
w
it
h
M
a
p
Re
d
u
c
e
b
y
u
sin
g
W
e
i
g
h
ted
A
s
so
c
iatio
n
Clas
sif
ier
a
n
d
K
-
M
e
a
n
s,”
In
d
i
a
n
J
.
S
c
i.
T
e
c
h
n
o
l
.
2
0
1
6
;
9
(
19
):
1
-
7
.
[6
]
M
.
A
.
jab
b
a
r,
B.
L
.
De
e
k
sh
a
tu
lu
,
a
n
d
P
.
Ch
a
n
d
ra
,
“
Clas
si
f
ica
ti
o
n
o
f
He
a
rt
Dise
a
s
e
Us
in
g
K
-
N
e
a
re
st
Ne
ig
h
b
o
r
a
n
d
G
e
n
e
ti
c
A
lg
o
rit
h
m
,
”
in
Pro
c
e
d
i
a
T
e
c
h
n
o
l
o
g
y
.
2
0
1
3
;
10
:
85
–
9
4
.
[7
]
K.
S
rin
iv
a
s,
B.
R.
Re
d
d
y
,
B.
K.
Ra
n
i,
a
n
d
R.
M
o
g
il
i,
“
Hy
b
rid
A
p
p
ro
a
c
h
f
o
r
P
re
d
icti
o
n
o
f
Ca
rd
io
v
a
sc
u
lar
Dise
a
s
e
Us
in
g
Clas
s As
so
c
iatio
n
Ru
les
a
n
d
M
L
P
,
”
In
t
.
J
.
El
e
c
tr.
C
o
mp
u
t.
E
n
g
.
IJ
ECE
.
2
0
1
6
;
6
(
4
)
:
1
8
0
0
–
1
8
1
0
.
[8
]
R.
Ra
u
t
a
n
d
S
.
V
.
D
u
d
u
l,
“
In
tell
i
g
e
n
t
d
iag
n
o
si
s
o
f
h
e
a
rt
d
ise
a
se
s
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
a
p
p
ro
a
c
h
,
”
In
t.
J
.
Co
mp
u
t.
Ap
p
l
.
2
0
1
0
;
1
(
2
):
97
–
1
0
2
.
[9
]
N.
A
.
S
e
ti
a
w
a
n
,
“
F
u
z
z
y
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
m
f
o
r
Co
ro
n
a
ry
A
rter
y
Dise
a
se
Dia
g
n
o
sis
Ba
se
d
o
n
R
o
u
g
h
S
e
t
T
h
e
o
r
y
,
”
In
t.
J
.
R
o
u
g
h
S
e
ts
Da
t
a
An
a
l
.
2
0
1
4
;
1
(1
):
65
–
80.
[1
0
]
L
.
V
e
r
m
a
,
S
.
S
riv
a
sta
v
a
,
a
n
d
P
.
C.
Ne
g
i,
“
A
H
y
b
rid
D
a
ta
M
in
in
g
M
o
d
e
l
to
P
re
d
ict
Co
ro
n
a
ry
Arte
r
y
Dise
a
se
Ca
s
e
s
Us
in
g
No
n
-
In
v
a
siv
e
Cli
n
ica
l
Da
ta,”
J
.
M
e
d
.
S
y
st.
2
0
1
6
;
40
(7
):
1
–
7.
[1
1
]
J.
Na
h
a
r,
T
.
Im
a
m
,
K.
S
.
T
ick
le
,
a
n
d
Y.
-
P
.
P
.
Ch
e
n
,
“
Co
m
p
u
tati
o
n
a
l
i
n
telli
g
e
n
c
e
f
o
r
h
e
a
rt
d
ise
a
se
d
iag
n
o
sis:
A
m
e
d
ica
l
k
n
o
w
led
g
e
d
riv
e
n
a
p
p
ro
a
c
h
,
”
Exp
e
rt S
y
st.
Ap
p
l.
2
0
1
3
;
40
(
1
):
96
–
1
0
4
.
[1
2
]
M
.
A
b
d
a
r,
S
.
R.
N.
Ka
lh
o
ri,
T
.
S
u
ti
k
n
o
,
I.
M
.
I.
S
u
b
ro
t
o
,
a
n
d
G
.
A
rji
,
“
Co
m
p
a
rin
g
P
e
rf
o
r
m
a
n
c
e
o
f
Da
ta
M
in
in
g
A
l
g
o
rit
h
m
s in
P
re
d
icti
o
n
He
a
rt
D
ise
a
se
s
,
”
In
t.
J
.
El
e
c
tr.
Co
mp
u
t.
E
n
g
.
IJ
ECE
.
2
0
1
5
;
5
(6
)
:
1
5
6
9
–
1
5
7
6
.
[1
3
]
H.
G
.
A
rjen
a
k
i,
M
.
H.
N.
S
h
a
h
ra
k
i,
a
n
d
N.
No
u
ra
f
z
a
,
“
A
L
o
w
Co
st
M
o
d
e
l
f
o
r
Dia
g
n
o
si
n
g
Co
ro
n
a
ry
A
rter
y
Dise
a
se
Ba
se
d
On
Ef
fe
c
ti
v
e
F
e
a
tu
re
s,”
In
t.
J
.
El
e
c
tro
n
.
Co
mm
u
n
.
Co
mp
u
t.
En
g
.
2
0
1
5
;
6
(1
):
93
–
97.
[1
4
]
M
.
G
.
F
e
sh
k
i
a
n
d
O.
S
.
S
h
ij
a
n
i,
“
I
m
p
ro
v
in
g
th
e
He
a
rt
Dise
a
se
Di
a
g
n
o
sis
b
y
Ev
o
lu
ti
o
n
a
ry
A
lg
o
rit
h
m
o
f
P
S
O
a
n
d
F
e
e
d
F
o
rw
a
rd
Ne
u
ra
l
Ne
tw
o
rk
,
”
p
re
se
n
ted
a
t
t
h
e
A
rti
f
icia
l
In
telli
g
e
n
c
e
a
n
d
Ro
b
o
ti
c
s
(IR
A
NO
P
EN),
2
0
1
6
;
p
p
.
48
–
53.
[1
5
]
W
.
W
ih
a
rto
,
H.
Ku
sn
a
n
to
,
a
n
d
H
.
He
rian
to
,
“
T
iere
d
M
o
d
e
l
Ba
se
d
On
F
u
z
z
y
In
f
e
re
n
c
e
S
y
ste
m
F
o
r
T
h
e
Dia
g
n
o
sis
o
f
Co
ro
n
a
ry
He
a
rt
Dise
a
se
,
”
Fa
r E
a
st J.
El
e
c
tro
n
.
C
o
mm
u
n
.
2
0
1
6
;
16
(
4
):
9
8
5
–
1
0
0
0
.
[1
6
]
W
.
W
ih
a
rto
,
H.
Ku
sn
a
n
to
,
a
n
d
H
.
He
rian
to
,
“
Hy
b
rid
S
y
ste
m
o
f
T
iere
d
M
u
lt
iv
a
riate
A
n
a
l
y
sis
a
n
d
Ne
u
r
a
l
Ne
tw
o
rk
f
o
r
Co
ro
n
a
ry
He
a
rt
Dise
a
se
Dia
g
n
o
sis,”
I
n
t.
J
.
El
e
c
tr.
Co
mp
u
t.
En
g
.
2
0
1
7
;
7
(2
)
:
1
0
2
3
-
1
0
3
1
.
[1
7
]
J.
Kim
,
J.
Lee
,
a
n
d
Y.
L
e
e
,
“
Da
ta
-
M
in
i
n
g
-
Ba
se
d
Co
ro
n
a
ry
He
a
rt
Di
se
a
se
Ris
k
P
re
d
icti
o
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
.
In
f
o
rm
.
Res
.
20
1
5
;
21
(3
):
1
6
7
–
1
7
4
.
[1
8
]
R.
De
tran
o
,
A
.
Jo
n
a
si,
W
.
S
tei
n
b
ru
n
n
,
a
n
d
M
.
P
f
istere
r,
He
a
rt
Di
se
a
se
Da
ta
se
t
.
Ca
li
f
o
rn
ia:
Un
iv
e
rsity
C
a
li
f
o
rn
ia
Irv
in
e
,
1
9
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
Th
e
A
n
a
lysi
s
o
f P
erfo
r
ma
ce
Mo
d
el
Tier
ed
A
r
tifi
cia
l Neu
r
a
l
N
etw
o
r
k
fo
r
A
s
s
e
s
s
men
t o
f …
.
(
W
ih
a
r
to
W
ih
a
r
to
)
2191
[1
9
]
R.
Co
n
sta
n
ti
n
e
sc
u
,
V
.
L
a
z
a
re
sc
u
,
a
n
d
R.
T
a
h
b
o
u
b
,
“
G
e
o
m
e
tri
c
a
l
F
o
rm
Re
c
o
g
n
it
io
n
Us
i
n
g
„On
e
-
S
tep
se
c
a
n
t‟
A
l
g
o
rit
h
m
In
Ca
se
Of
Ne
u
ra
l
Ne
t
w
o
rk
,
”
UPB
S
c
i
Bu
ll
S
e
r.
C
.
2
0
0
8
;
70
(
2
):
1
5
-
28
.
[2
0
]
L
.
W
a
n
g
,
Y.
L
iu
,
Y.
L
iu
,
W
.
Wan
g
,
Y.
Zh
a
o
,
a
n
d
Z.
Ya
n
g
,
“
O
p
ti
m
iza
ti
o
n
o
f
Hy
d
ro
g
e
n
-
f
u
e
led
En
g
in
e
Ig
n
it
i
o
n
T
i
m
in
g
Ba
se
d
o
n
L
-
M
Ne
u
ra
l
Ne
tw
o
rk
A
l
g
o
rit
h
m
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
.
Co
mp
u
t.
E
l
e
c
tro
n
.
Co
n
tro
l
.
2
0
1
6
;
14
(
3
):
9
2
3
–
9
3
2
.
[2
1
]
S
.
M
.
A
.
Bu
rn
e
y
,
T
.
A
.
Jilan
i,
a
n
d
C
.
A
rd
il
,
“
A
Co
m
p
a
riso
n
o
f
F
irst
a
n
d
S
e
c
o
n
d
Or
d
e
r
T
ra
in
in
g
A
lg
o
rit
h
m
s
f
o
r
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
s
,
”
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ta
ti
o
n
a
l
I
n
telli
g
e
n
c
e
.
2
0
0
4
;
p
p
.
1
2
–
1
8
.
[2
2
]
E
.
Ra
m
e
n
to
l,
Y.
Ca
b
ll
e
r
o
,
R.
B
e
ll
o
,
a
n
d
F
.
He
rre
ra
,
“
S
M
OT
E
-
RS
B:
a
h
y
b
rid
p
re
p
ro
c
e
ss
in
g
a
p
p
ro
a
c
h
b
a
se
d
o
n
o
v
e
rsa
m
p
li
n
g
a
n
d
u
n
d
e
rsa
m
p
li
n
g
f
o
r
h
ig
h
i
m
b
a
lan
c
e
d
d
a
ta
-
se
ts
u
sin
g
S
M
OT
E
a
n
d
ro
u
g
h
se
ts
th
e
o
ry
,
”
Kn
o
wl.
In
fro
ma
t
io
n
S
y
st.
2
0
1
2
;
33
(2
)
:
245
–
2
6
5
.
[2
3
]
J.
Ya
n
g
,
Y.
L
e
e
,
a
n
d
U.
-
G
.
K
a
n
g
,
“
Co
m
p
a
riso
n
o
f
P
re
d
icti
o
n
M
o
d
e
ls
f
o
r
Co
ro
n
a
ry
He
a
rt
Dise
a
s
e
s
in
De
p
re
ss
io
n
P
a
ti
e
n
ts,
”
In
t
.
J
.
M
u
lt
ime
d
.
Ub
iq
u
it
o
u
s
En
g
.
2
0
1
5
;
10
(
3
):
2
5
7
–
2
6
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.