I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI)
Vo
l.
1
0
,
No
.
2
,
J
u
n
e
2
0
2
1
,
p
p
.
4
76
~
4
81
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
ai.
v
1
0
.
i2
.
p
p
4
76
-
4
81
476
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Pancrea
tic
ca
ncer
clas
sifica
tion usi
ng
log
istic regress
io
n and
ra
ndo
m
forest
Z
u
her
m
a
n Ru
s
t
a
m
,
F
il
dza
h Z
h
a
f
a
rina
,
G
lo
ri
Ste
ph
a
ni
S
a
ra
g
ih,
Sri H
a
rt
ini
De
p
a
rtme
n
t
o
f
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
,
De
p
o
k
,
I
n
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
M
ar
2
9
,
2
0
2
0
R
ev
i
s
ed
M
ar
2
,
2
0
2
1
A
cc
ep
ted
A
p
r
6
,
2
0
2
1
In
th
e
m
e
d
ica
l
f
ield
,
tec
h
n
o
lo
g
y
m
a
c
h
in
e
ry
is
n
e
e
d
e
d
to
so
lv
e
se
v
e
ra
l
c
las
si
f
ica
ti
o
n
p
ro
b
lem
s.
T
h
e
re
fo
re
,
th
is
re
se
a
rc
h
is
u
se
f
u
l
to
so
lv
e
th
e
p
ro
b
lem
o
f
th
e
m
e
d
ica
l
f
ield
b
y
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
.
T
h
is
stu
d
y
d
isc
u
ss
e
s
th
e
c
las
sif
ica
ti
o
n
o
f
p
a
n
c
re
a
ti
c
c
a
n
c
e
r
b
y
u
sin
g
re
g
re
ss
io
n
lo
g
isti
c
s
a
n
d
ra
n
d
o
m
f
o
re
st.
B
y
c
o
m
p
a
rin
g
th
e
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
ll
(se
n
siti
v
it
y
),
a
n
d
F1
-
sc
o
re
o
f
b
o
th
m
e
th
o
d
s,
th
e
n
w
e
w
il
l
k
n
o
w
w
h
ich
m
e
th
o
d
is
b
e
tt
e
r
in
c
las
si
fy
in
g
th
e
p
a
n
c
re
a
ti
c
c
a
n
c
e
r
d
a
tas
e
t
th
a
t
w
e
g
e
t
f
ro
m
A
l
-
Isla
m
Ho
sp
it
a
l,
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
.
T
h
e
re
su
lt
s
sh
o
w
e
d
th
a
t
ra
n
d
o
m
f
o
re
st
h
a
s
b
e
tt
e
r
a
c
c
u
ra
c
y
th
a
n
lo
g
isti
c
re
g
re
ss
io
n
s.
It
c
a
n
b
e
se
e
n
w
it
h
m
a
x
i
m
u
m
a
c
c
u
ra
c
y
o
f
lo
g
isti
c
re
g
re
ss
io
n
s
9
6
.
4
8
w
it
h
3
0
%
d
a
ta
train
in
g
a
n
d
ra
n
d
o
m
f
o
re
st
9
9
.
3
8
%
w
it
h
2
0
%
o
f
d
a
ta t
ra
in
i
n
g
.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
L
o
g
i
s
tic
r
eg
r
e
s
s
io
n
Ma
ch
i
n
e
lear
n
i
n
g
P
an
cr
ea
tic
ca
n
ce
r
R
an
d
o
m
f
o
r
est
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Fil
d
za
h
Z
h
a
f
ar
i
n
a
Dep
ar
t
m
en
t o
f
Ma
th
e
m
at
ics
Un
i
v
er
s
it
y
o
f
I
n
d
o
n
e
s
ia
Un
i
v
er
s
it
y
o
f
I
n
d
o
n
e
s
ia,
Dep
o
k
1
6
4
2
4
,
I
n
d
o
n
esia
E
m
ail:
f
ild
za
h
.
z
h
a
f
ar
in
a
@
s
c
i.u
i.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
On
e
o
f
t
h
e
m
a
in
d
is
ea
s
es
t
h
at
ca
u
s
e
d
ea
th
i
n
t
h
e
w
o
r
ld
is
c
an
ce
r
[
1
]
,
[
2
]
.
T
h
ese
d
is
ea
s
es
ca
n
attac
k
all
p
ar
ts
o
f
t
h
e
b
o
d
y
[
3
]
.
On
e
o
f
th
e
m
ai
n
ca
u
s
es
o
f
ca
n
ce
r
-
r
elate
d
d
ea
th
s
w
o
r
ld
w
id
e
is
p
a
n
cr
ea
tic
ca
n
ce
r
.
I
n
th
e
ea
r
l
y
s
tag
e,
th
e
d
is
ea
s
e
s
h
av
e
n
o
s
h
o
w
in
g
o
r
s
y
m
p
to
m
s
.
T
h
e
m
o
s
t
s
y
m
p
to
m
s
o
cc
u
r
wh
en
t
h
e
d
is
ea
s
es
i
n
th
e
f
i
n
al
s
ta
g
e
[
4
]
.
P
an
cr
ea
ti
c
ca
n
ce
r
i
s
ca
n
ce
r
t
h
at
s
tar
t
s
i
n
t
h
e
p
a
n
cr
ea
s
.
T
h
e
m
o
s
t
co
m
m
o
n
t
y
p
e
o
f
p
an
cr
ea
tic
ca
n
ce
r
is
p
a
n
cr
ea
ti
c
ad
en
o
ca
r
cin
o
m
a
[
5
]
.
L
o
ca
ti
o
n
o
f
th
e
p
an
cr
ea
tic
o
r
g
a
n
s
b
eh
in
d
th
e
s
to
m
ac
h
.
T
h
e
p
an
cr
ea
s
is
ab
o
u
t
6
in
c
h
es
lo
n
g
an
d
le
s
s
th
a
n
2
i
n
ch
e
s
w
i
d
e
in
ad
u
l
ts
[
6
]
.
T
h
er
e
ar
e
v
ar
i
o
u
s
tr
ea
t
m
e
n
ts
f
o
r
p
an
cr
ea
tic
ca
n
ce
r
,
s
u
ch
a
s
s
u
r
g
er
y
,
c
h
e
m
o
t
h
er
ap
y
,
r
ad
iatio
n
th
er
ap
y
,
o
r
a
co
m
b
in
at
io
n
o
f
th
ese.
T
h
e
m
eth
o
d
o
f
tr
ea
t
m
e
n
t
is
c
h
o
s
e
n
b
ased
o
n
th
e
e
x
te
n
t
o
f
ca
n
ce
r
[
7
]
.
I
n
f
o
r
m
at
io
n
tec
h
n
o
lo
g
y
h
as
an
i
m
p
o
r
ta
n
t
r
o
le
in
t
h
e
f
ield
o
f
m
ed
icin
e.
C
a
n
ce
r
is
a
d
is
ea
s
e
t
h
at
ca
n
b
e
d
etec
ted
b
y
m
ac
h
i
n
e
lear
n
i
n
g
.
Data
i
s
v
er
y
u
s
e
f
u
l
i
n
th
e
m
ed
ical
f
ield
.
I
t
ca
n
b
e
s
ee
n
f
r
o
m
th
e
d
ev
elo
p
m
e
n
t
o
f
d
ata
m
i
n
in
g
in
m
ed
ical
s
cie
n
ce
i
s
in
cr
ea
s
i
n
g
r
ap
id
l
y
.
T
h
is
in
cr
ea
s
e
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
h
i
g
h
p
r
ed
ictio
n
r
es
u
lt
s
,
ca
n
r
ed
u
ce
tr
ea
t
m
e
n
t c
o
s
ts
,
i
n
cr
ea
s
e
th
e
ch
a
n
ce
s
o
f
r
ec
o
v
er
y
o
f
p
atien
ts
,
a
n
d
d
ec
is
io
n
s
to
s
av
e
liv
e
s
[
8
]
,
[
9
]
.
C
lass
i
f
icatio
n
is
a
w
a
y
to
id
en
ti
f
y
g
r
o
u
p
s
o
f
ca
teg
o
r
ies
to
b
e
p
ar
t
o
f
o
b
s
er
v
atio
n
s
[
1
0
]
.
On
e
g
e
n
er
al
cla
s
s
i
f
icatio
n
is
t
h
e
co
n
tin
u
o
u
s
v
alu
e
o
f
th
e
p
r
ed
icti
v
e
attr
ib
u
te.
W
h
er
ea
s
,
en
s
e
m
b
le
class
i
f
icatio
n
is
u
s
e
f
u
l
f
o
r
in
cr
ea
s
i
n
g
cla
s
s
i
f
ica
tio
n
ac
c
u
r
ac
y
i
n
e
n
s
e
m
b
le
ap
p
licatio
n
s
[
1
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
P
a
n
crea
tic
ca
n
ce
r
cla
s
s
ifica
tio
n
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
r
a
n
d
o
m
fo
r
est
(
Zu
h
erma
n
R
u
s
ta
m
)
477
2.
RE
S
E
ARCH
M
E
T
H
O
D
P
an
cr
ea
tic
c
an
ce
r
d
ataset
w
a
s
o
b
tain
ed
f
r
o
m
Al
-
I
s
la
m
Ho
s
p
ital,
B
an
d
u
n
g
,
I
n
d
o
n
e
s
ia.
T
h
is
d
ataset
co
n
s
is
ts
o
f
7
9
n
o
n
-
ca
n
ce
r
an
d
1
2
4
ca
n
ce
r
s
am
p
les
w
i
th
n
u
m
er
ical
ch
ar
ac
ter
is
tics
d
escr
ib
e
d
b
y
6
attr
ib
u
tes,
as
s
h
o
w
n
i
n
T
ab
le
1
.
T
h
is
r
esear
ch
u
s
e
s
lo
g
is
tic
r
eg
r
ess
io
n
s
a
n
d
r
an
d
o
m
f
o
r
est
f
o
r
class
if
icat
io
n
.
T
h
is
m
eth
o
d
is
ev
alu
a
ted
u
s
i
n
g
3
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
,
4
5
-
r
an
d
o
m
s
tate,
an
d
later
co
m
p
ar
ed
.
T
ab
le
s
a
m
p
le
o
f
d
ataset
i
s
s
h
o
w
n
in
T
a
b
le
2
.
T
ab
le
1
.
P
an
cr
ea
tic
ca
n
ce
r
d
ataset
v
ar
iab
le
A
t
t
r
i
b
u
t
e
s
D
e
scri
p
t
i
o
n
A
g
e
T
h
e
n
u
m
b
e
r
o
f
a
g
e
p
a
t
i
e
n
t
s w
h
o
a
r
e
i
n
c
h
e
c
k
C
A
1
9
-
9
T
h
e
n
u
m
b
e
r
o
f
c
a
n
c
e
r
a
n
t
i
g
e
n
u
n
i
t
s
p
e
r
mi
l
l
i
l
i
t
e
r
o
f
b
l
o
o
d
H
e
mo
g
l
o
b
i
n
T
h
e
n
u
m
b
e
r
o
f
h
e
mo
g
l
o
b
i
n
g
r
a
m
p
e
r
d
e
c
i
l
i
t
e
r
o
f
b
l
o
o
d
L
e
u
k
o
c
y
t
e
T
h
e
n
u
m
b
e
r
o
f
l
e
u
k
o
c
y
t
e
c
e
l
l
p
e
r
u
L
o
f
b
l
o
o
d
H
e
mat
o
c
r
i
t
H
e
mat
o
c
r
i
t
o
r
t
h
e
v
o
l
u
me
p
e
r
c
e
n
t
a
g
e
o
f
r
e
d
b
l
o
o
d
c
e
l
l
s
T
h
r
o
mb
o
si
s
T
h
e
n
u
m
b
e
r
o
f
t
h
r
o
m
b
o
si
s
c
e
l
l
p
e
r
u
L
o
f
b
l
o
o
d
T
ab
le
2
.
Sam
p
le
o
f
d
ataset
f
r
o
m
A
l
-
I
s
la
m
Ho
s
p
ital,
B
an
d
u
n
g
,
I
n
d
o
n
esia
A
g
e
C
A
1
9
-
9
<
3
7
(
U
/
mL
)
H
e
mo
g
l
o
b
i
n
1
3
-
1
8
(
g
/
d
L
)
L
e
u
k
o
c
y
t
4
0
0
0
-
1
0
0
0
0
(
se
l
/
u
L
)
H
e
mat
o
k
r
i
t
40
-
5
4
(
%)
T
h
r
o
mb
o
si
s 1
5
0
0
0
0
-
4
5
0
0
0
0
(
se
l
/
u
L
)
38
3
4
.
6
1
1
2
.
1
7
6
0
0
3
6
.
9
2
4
4
0
0
0
82
3
5
.
0
2
1
2
.
1
4
9
0
0
3
6
.
7
2
5
3
0
0
0
35
3
5
.
4
6
.
3
1
0
1
0
0
2
3
.
4
4
9
6
0
0
0
58
3
5
.
8
3
9
.
8
3
3
5
0
0
2
9
.
1
4
6
7
0
0
0
52
36
9
.
8
7
6
0
0
2
9
.
9
6
1
3
0
0
0
41
3
6
.
0
3
1
2
.
6
3
4
0
0
38
2
0
3
0
0
0
40
3
6
.
9
4
1
1
.
9
8
9
0
0
3
9
.
8
4
3
0
0
0
0
51
3
7
.
4
1
6
.
6
9
5
0
0
2
3
.
5
2
5
9
0
0
0
64
3
9
.
2
5
1
1
.
5
1
5
5
0
0
3
5
.
3
2
3
0
0
0
0
2
.
1
.
L
o
g
is
t
ic
re
g
re
s
s
io
ns
I
n
s
o
m
e
ca
s
e
s
,
t
h
e
n
a
tu
r
al
co
m
p
le
m
e
n
t
o
f
o
r
d
in
ar
y
li
n
ea
r
i
s
lo
g
i
s
tic
r
e
g
r
ess
io
n
.
T
h
is
h
ap
p
en
s
w
h
e
n
ea
ch
tar
g
et
v
ar
iab
le
is
ca
te
g
o
r
ized
.
Var
iab
le
Y
is
a
v
ar
iab
le
tar
g
et
an
d
d
ep
en
d
en
t
w
i
th
t
w
o
class
an
d
v
ar
iab
le
X
is
a
v
ar
iab
le
p
r
ed
icto
r
an
d
in
d
ep
en
d
en
t,
let
(
)
=
Pr
(
=
)
=
1
−
Pr
(
=
)
th
e
lo
g
is
ti
c
r
eg
r
ess
io
n
m
o
d
el
h
as a
li
n
ea
r
f
o
r
m
f
o
r
Lo
g
it
w
it
h
p
r
o
b
ab
ilit
y
as f
o
llo
w
s
[
1
2
]
-
[
1
4
]
:
[
(
)
]
=
l
og
(
(
)
1
−
(
)
)
=
+
,
ℎ
ℎ
(
)
1
−
(
)
(
1
)
T
h
e
f
o
r
m
o
f
li
n
ea
r
ap
p
r
o
x
i
m
atio
n
an
d
p
r
o
b
ab
ilit
y
lo
g
ar
it
h
m
i
s
d
er
iv
ed
f
r
o
m
Lo
g
it
.
T
h
e
r
ate
o
f
in
cr
ea
s
e
o
r
d
ec
r
ea
s
e
o
f
th
e
S
h
ap
e
g
(
x)
cu
r
v
e
is
d
en
o
ted
b
y
t
h
e
p
ar
a
m
eter
β [
1
5
]
.
2
.
2
.
Ra
nd
o
m
f
o
re
s
t
R
an
d
o
m
f
o
r
est
is
a
m
et
h
o
d
d
e
v
elo
p
ed
b
y
B
r
ei
m
a
n
in
2
0
0
1
[
1
6
]
,
[
17
]
.
R
an
d
o
m
f
o
r
est
w
o
r
k
s
w
h
en
i
t
r
ea
ch
es
m
a
x
i
m
u
m
ac
cu
r
ac
y
,
a
d
ec
is
io
n
tr
ee
ca
n
b
e
u
s
ed
to
a
v
o
id
o
v
er
f
itti
n
g
d
ata
[
1
8
]
.
T
h
e
esti
m
atio
n
p
r
o
ce
s
s
p
r
ev
io
u
s
l
y
ca
r
r
ied
o
u
t
b
y
d
ec
is
io
n
tr
ee
an
d
C
AR
T
w
a
s
en
h
a
n
ce
d
b
y
B
r
ei
m
an
,
w
h
ic
h
w
as
s
tar
ted
b
y
r
a
n
d
o
m
l
y
s
elec
ti
n
g
m
v
ar
iab
les
f
r
o
m
s
e
v
er
al
in
d
ep
en
d
en
t
v
ar
iab
les.
A
d
ec
is
io
n
tr
ee
o
r
C
A
R
T
m
et
h
o
d
is
a
tr
ee
th
at
is
g
r
o
w
n
w
it
h
o
u
t
p
r
u
n
i
n
g
.
T
h
es
e
tr
ee
s
w
i
ll
b
e
s
elec
ted
w
i
th
th
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
.
T
h
e
p
r
o
ce
d
u
r
e
o
f
r
an
d
o
m
f
o
r
est
d
ep
en
d
s
o
n
t
h
e
n
u
m
b
er
o
f
cla
s
s
i
f
icatio
n
s
[
1
9
].
T
h
er
e
ar
e
s
o
m
e
ad
v
an
tag
e
s
o
f
r
an
d
o
m
f
o
r
est
[
2
0
]
,
s
u
c
h
as
o
v
er
co
m
i
n
g
t
h
e
p
r
o
b
le
m
o
f
ex
ce
s
s
i
v
e
co
m
p
atib
ilit
y
,
le
s
s
s
en
s
iti
v
e
to
o
u
t
lier
d
ata,
p
ar
am
eter
s
ca
n
b
e
ea
s
il
y
ad
j
u
s
ted
an
d
t
h
er
ef
o
r
e
eli
m
i
n
ate
th
e
n
ee
d
f
o
r
tr
ee
p
r
u
n
i
n
g
,
an
d
t
h
e
i
m
p
o
r
tan
ce
o
f
v
ar
iab
le
s
an
d
ac
cu
r
ac
y
ar
e
g
en
er
ated
au
to
m
atica
ll
y
.
R
a
n
d
o
m
f
o
r
est
s
e
lecte
d
f
ea
tu
r
e
s
ar
e
in
ag
r
ee
m
en
t
w
i
th
ex
is
ti
n
g
d
o
m
ai
n
k
n
o
w
led
g
e
(
e.
g
.
p
h
y
s
io
lo
g
ical
k
n
o
w
led
g
e
Gu
an
et
a
l
.
,
2
0
1
2
)
[
2
1
]
.
Flo
w
ch
ar
t o
f
r
an
d
o
m
f
o
r
est s
h
o
w
n
in
Fi
g
u
r
e
1
.
2
.
3
.
Co
nfusi
o
n
m
a
t
rix
On
e
o
f
t
h
e
m
et
h
o
d
s
u
s
ed
to
ca
lcu
late
ac
cu
r
ac
y
i
n
th
e
co
n
ce
p
t
o
f
d
ata
m
i
n
i
n
g
o
r
d
ec
is
i
o
n
s
u
p
p
o
r
t
s
y
s
te
m
s
is
co
n
f
u
s
io
n
m
atr
i
x
[
22
]
.
I
t
is
b
alan
ce
d
in
th
e
p
r
ec
is
io
n
an
d
s
en
s
itiv
it
y
t
h
at
d
is
ti
n
g
u
is
h
es
co
r
r
ec
t
lab
el
class
i
f
icatio
n
s
i
n
d
if
f
er
en
t
cla
s
s
es
[
23
]
,
[
24
]
.
A
cc
u
r
ac
y
is
t
h
e
r
atio
o
f
th
e
tr
u
e
p
r
ed
ictio
n
s
in
t
h
e
w
h
o
le
d
ata.
P
r
ec
is
io
n
is
a
tr
u
e
p
o
s
itiv
e
p
r
ed
ictio
n
r
atio
co
m
p
ar
ed
to
o
v
er
all
p
o
s
itiv
e
p
r
ed
icted
r
esu
lts
.
I
n
ad
d
itio
n
,
th
e
th
ir
d
is
s
e
n
s
iti
v
it
y
is
a
tr
u
e
p
o
s
itiv
e
p
r
ed
ictio
n
r
atio
co
m
p
ar
ed
to
o
v
er
all
tr
u
e
p
o
s
itiv
e
d
ata.
T
h
e
last
w
as
d
en
o
ted
as F1
-
s
co
r
e
,
u
s
ed
to
d
eter
m
i
n
e
th
e
b
alan
ce
b
et
w
ee
n
s
en
s
iti
v
it
y
a
n
d
p
r
ec
is
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell,
Vo
l.
1
0
,
No
.
2
,
J
u
n
e
2
0
2
1
:
4
76
–
481
478
T
r
u
e
Po
s
itiv
e
(
TP
)
: N
u
m
b
er
o
f
s
a
m
p
les
h
av
i
n
g
p
an
cr
ea
tic
ca
n
ce
r
d
iag
n
o
s
ed
co
r
r
ec
tl
y
Fals
e
P
o
s
itiv
e
(
FP
)
: Su
m
o
f
h
e
alth
y
p
eo
p
le
th
at
w
er
e
i
n
co
r
r
ec
tl
y
id
en
t
if
ied
to
h
av
e
p
an
cr
ea
tic
ca
n
ce
r
T
r
u
e
Neg
ativ
e
(
TN
)
: N
u
m
b
er
o
f
h
ea
lt
h
y
p
eo
p
le
co
r
r
ec
tly
s
p
o
tted
Fals
e
Ne
g
ati
v
e
(
FN
)
:
N
u
m
b
e
r
o
f
s
a
m
p
les
w
it
h
p
an
cr
ea
tic
ca
n
ce
r
t
h
at
w
er
e
in
co
r
r
ec
tl
y
class
i
f
ied
a
s
h
ea
lt
h
y
Fro
m
T
ab
le
3
it
ca
n
b
u
ild
th
e
f
o
r
m
u
la
f
o
r
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
(
s
en
s
it
iv
i
t
y
)
,
an
d
F
1
-
s
co
r
e
th
at
ar
e
s
ee
n
in
(
2
)
-
(
5
)
.
=
+
+
+
+
100%
(
2
)
=
+
100%
(
3
)
=
+
100%
(
4
)
1
=
2
(
)
(
+
)
100%
(
5
)
Fig
u
r
e
1
.
Flo
w
c
h
ar
t o
f
r
an
d
o
m
f
o
r
est
[
25
]
T
ab
l
e
3
.
C
o
n
f
u
s
io
n
m
atr
i
x
A
c
t
u
a
l
V
a
l
u
e
R
e
c
o
g
n
i
z
e
V
a
l
u
e
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
TP
FN
N
e
g
a
t
i
v
e
FP
TN
3
.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
T
h
is
r
esear
ch
u
s
i
n
g
J
u
p
y
ter
n
o
teb
o
o
k
as so
f
t
w
ar
e
f
o
r
r
u
n
n
i
n
g
th
e
p
r
o
g
r
a
m
o
f
lo
g
is
tic
r
eg
r
es
s
io
n
s
a
n
d
r
an
d
o
m
f
o
r
est
i
n
p
r
o
ce
s
s
in
g
p
an
cr
ea
tic
ca
n
ce
r
clas
s
i
f
icatio
n
p
r
o
b
lem
.
T
esti
n
g
t
h
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F
1
-
s
co
r
e
in
t
h
is
t
y
p
e
o
f
cl
ass
i
f
icatio
n
ar
e
b
y
ch
a
n
g
in
g
t
h
e
a
m
o
u
n
t o
f
d
ata
tr
ai
n
i
n
g
.
I
n
t
h
is
te
s
t,
t
h
e
n
u
m
b
er
o
f
d
ata
tr
ain
i
n
g
i
s
eq
u
al
to
1
0
,
2
0
,
3
0
,
4
0
,
5
0
,
6
0
,
7
0
,
8
0
,
an
d
9
0
w
h
ic
h
w
il
l
b
e
u
s
ed
o
n
th
e
r
es
u
lt
s
o
f
t
h
e
d
ataset.
T
h
e
r
esu
lts
o
f
ac
c
u
r
a
c
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F
1
-
s
co
r
e
w
h
ic
h
ar
e
g
i
v
en
b
y
lo
g
i
s
tic
r
eg
r
ess
io
n
s
a
n
d
r
an
d
o
m
f
o
r
est cla
s
s
i
f
ier
m
e
th
o
d
ar
e
s
h
o
w
n
in
T
ab
le
4
an
d
T
a
b
le
5
.
B
ased
o
n
T
ab
le
4
,
it
is
s
h
o
w
n
th
at
t
h
e
n
u
m
b
er
o
f
d
ata
tr
ain
in
g
is
a
f
f
ec
t
i
n
g
b
y
t
h
e
v
al
u
e
s
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
a
ll
,
a
n
d
F
1
-
s
co
r
e
.
I
n
t
h
i
s
r
esear
c
h
,
t
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
v
al
u
e
w
as
r
ec
o
r
d
ed
w
h
e
n
t
h
e
d
ata
tr
ain
i
n
g
is
3
0
%
w
it
h
9
6
.
4
8
%
w
h
ile
th
e
lo
w
est
ac
cu
r
ac
y
v
al
u
e
w
a
s
r
ec
o
r
d
ed
w
h
en
th
e
d
ata
tr
ain
i
n
g
i
s
7
0
%
w
it
h
9
1
.
4
9
%.
I
n
p
r
ec
is
io
n
,
7
0%
an
d
9
0%
o
f
d
ata
tr
ain
in
g
r
ea
ch
ed
a
m
ax
i
m
u
m
v
a
lu
e
t
h
a
t
is
1
0
0
%.
Fo
r
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
P
a
n
crea
tic
ca
n
ce
r
cla
s
s
ifica
tio
n
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
r
a
n
d
o
m
fo
r
est
(
Zu
h
erma
n
R
u
s
ta
m
)
479
r
ec
all
,
th
e
r
ec
all
o
f
th
e
h
ig
h
es
t
v
alu
e
is
9
7
.
7
0
%
f
o
r
3
0
%
o
f
d
ata
tr
ain
in
g
.
T
h
e
last
f
o
r
F
1
-
s
co
r
e,
3
0
%
o
f
d
ata
tr
ain
i
n
g
r
ea
ch
ed
t
h
e
h
i
g
h
est
v
a
lu
e
th
a
t is
9
6
.
2
9
%.
B
ased
o
n
T
ab
le
5
,
it
i
s
s
h
o
w
n
th
at
th
e
n
u
m
b
er
o
f
d
ata
tr
ai
n
i
n
g
is
a
f
f
ec
ted
b
y
th
e
v
a
lu
e
s
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
a
n
d
F
1
-
s
co
r
e
.
I
n
t
h
i
s
r
esear
c
h
,
t
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
v
al
u
e
w
as
r
ec
o
r
d
ed
w
h
e
n
t
h
e
d
ata
tr
ain
i
n
g
is
2
0
%
w
it
h
9
9
.
3
8
%
w
h
ile
th
e
lo
w
est
ac
cu
r
ac
y
v
al
u
e
w
a
s
r
ec
o
r
d
ed
w
h
en
th
e
d
ata
tr
ain
i
n
g
i
s
9
0
%
w
it
h
8
9
.
6
8
%.
I
n
p
r
ec
is
io
n
,
1
0%
,
2
0
%,
an
d
3
0%
o
f
d
ata
tr
ai
n
in
g
r
ea
ch
ed
a
m
a
x
i
m
u
m
v
alu
e
th
at
is
1
0
0
%.
Fo
r
th
e
r
ec
all
,
th
e
r
ec
all
o
f
t
h
e
h
i
g
h
e
s
t
v
al
u
e
i
s
9
9
.
1
0
%
f
o
r
1
0
%
o
f
d
ata
tr
ain
in
g
.
T
h
e
la
s
t
f
o
r
F
1
-
s
co
r
e,
2
0
%
o
f
d
ata
tr
ain
in
g
r
ea
ch
ed
th
e
m
a
x
i
m
u
m
v
al
u
e
th
at
i
s
100
%.
T
ab
le
4
.
T
h
e
r
esu
lts
o
f
p
an
cr
e
atic
ca
n
ce
r
class
i
f
ica
tio
n
u
s
i
n
g
lo
g
is
tic
r
eg
r
e
s
s
io
n
N
o
.
D
a
t
a
T
r
a
i
n
i
n
g
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
si
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
1.
10
9
5
.
6
2
9
6
.
5
6
9
6
.
4
9
5
.
4
2.
20
9
5
.
6
8
9
6
.
0
2
9
6
.
9
7
9
5
.
4
5
3.
30
9
6
.
4
8
9
6
.
7
4
9
7
.
7
9
6
.
2
9
4.
40
9
5
.
9
4
9
7
.
4
4
96
9
5
.
7
3
5.
50
9
6
.
0
5
9
8
.
3
3
9
5
.
1
6
9
5
.
8
8
6.
60
9
5
.
0
1
9
6
.
0
6
9
5
.
8
3
9
4
.
7
6
7.
70
9
1
.
4
9
1
0
0
8
6
.
1
1
9
1
.
3
9
8.
80
9
5
.
0
5
9
6
.
3
9
5
.
8
3
9
4
.
7
7
9.
90
9
4
.
4
4
1
0
0
9
1
.
6
7
9
4
.
2
9
T
ab
le
5
.
T
h
e
r
esu
lt o
f
p
an
cr
ea
t
ic
ca
n
ce
r
class
i
f
icat
io
n
u
s
i
n
g
r
an
d
o
m
f
o
r
est
N
o
.
D
a
t
a
T
r
a
i
n
i
n
g
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
si
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
1.
10
9
8
.
9
1
1
0
0
9
9
.
1
9
8
.
8
5
2.
20
9
9
.
3
8
1
0
0
9
8
.
9
9
1
0
0
3.
30
9
9
.
2
9
1
0
0
9
8
.
8
5
9
9
.
2
6
4.
40
9
5
.
1
2
9
6
.
4
3
9
8
.
6
7
9
5
.
5
4
5.
50
97
9
6
.
9
9
8
.
4
1
9
6
.
8
5
6.
60
9
7
.
4
8
9
8
.
0
4
9
1
.
9
1
9
8
.
6
7
7.
70
9
1
.
7
3
9
7
.
4
4
9
4
.
4
4
9
6
.
5
7
8.
80
9
7
.
6
2
9
2
.
5
9
9
1
.
6
7
9
7
.
1
7
9.
90
8
9
.
6
8
9
3
.
3
3
9
1
.
6
7
7
0
.
8
3
4
.
CO
NCLU
SI
O
N
A
f
ter
cla
s
s
i
f
y
i
n
g
p
an
cr
ea
tic
ca
n
ce
r
w
it
h
lo
g
is
tic
r
eg
r
e
s
s
i
o
n
s
a
n
d
r
an
d
o
m
f
o
r
est
m
et
h
o
d
s
,
it
g
et
s
s
ev
er
al
r
es
u
lt
s
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F
1
-
s
co
r
e.
B
y
co
m
p
ar
in
g
t
h
e
v
al
u
es t
h
at
ar
e
g
iv
e
n
f
r
o
m
th
o
s
e
m
et
h
o
d
s
(
lo
g
i
s
tic
r
e
g
r
ess
io
n
s
an
d
r
an
d
o
m
f
o
r
est
)
,
it
i
s
p
o
s
s
ib
le
to
co
n
cl
u
d
e
t
h
at
r
a
n
d
o
m
f
o
r
est
g
e
n
er
ates
a
b
etter
r
esu
lt
th
a
n
lo
g
is
tic
r
e
g
r
ess
i
o
n
.
T
h
e
r
esu
lts
o
f
t
h
e
t
w
o
m
et
h
o
d
s
r
an
d
o
m
f
o
r
est
g
i
v
es
t
h
e
h
i
g
h
est
ac
c
u
r
ac
y
r
ate
w
h
e
n
th
e
d
ata
tr
ain
i
n
g
is
2
0
%
w
it
h
9
9
.
3
8
%,
w
h
ile
lo
g
is
tic
r
eg
r
es
s
io
n
r
ea
ch
e
s
9
6
.
4
8
%
w
h
e
n
th
e
d
ata
tr
ain
i
n
g
is
3
0
%.
B
ec
au
s
e
o
f
th
e
g
o
o
d
r
esu
lt
s
,
r
an
d
o
m
f
o
r
est
i
s
s
u
g
g
e
s
ted
to
h
elp
t
h
e
m
ed
ica
l sta
f
f
to
p
r
ed
ict
o
r
class
i
f
y
a
d
is
ea
s
e
r
ath
er
t
h
an
l
o
g
is
tic
r
eg
r
e
s
s
io
n
,
esp
ec
iall
y
f
o
r
a
d
ataset
th
at
is
s
i
m
ilar
to
t
h
is
r
esear
c
h
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
f
u
ll
s
u
p
p
o
r
ted
f
i
n
an
cia
ll
y
b
y
Un
i
v
er
s
i
t
y
o
f
I
n
d
o
n
esia
w
it
h
a
P
UT
I
2
0
2
0
r
esear
ch
s
ch
e
m
e
g
r
a
n
t.
RE
F
E
R
E
NC
E
S
[1
]
U.
S
.
L
.
W
a
n
g
e
t
a
l.
,
“
S
ig
n
a
li
n
g
a
d
a
p
to
r
p
r
o
tein
Crk
is
in
v
o
l
v
e
d
in
m
a
li
g
n
a
n
t
f
e
a
tu
re
o
f
p
a
n
c
re
a
ti
c
c
a
n
c
e
r
a
ss
o
c
iate
d
w
it
h
p
h
o
sp
h
o
ry
latio
n
o
f
c
-
M
e
t,
”
Bi
o
c
h
e
mic
a
l
a
n
d
b
io
p
h
y
sic
a
l
re
se
a
rc
h
c
o
mm
u
n
ica
ti
o
n
s,
v
o
l.
5
2
4
,
n
o
.
2
,
p
p
.
3
7
8
-
3
8
4
,
2
0
2
0
.
h
tt
p
s://
d
o
i.
o
rg
/1
0
.
1
0
1
6
/j
.
b
b
rc
.
2
0
2
0
.
0
1
.
1
0
5
.
[2
]
W
o
rld
He
a
lt
h
Org
a
n
iza
ti
o
n
,
“
1
0
F
a
c
ts
A
b
o
u
t
Ca
n
c
e
r,
”
2
0
1
8
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
w
h
o
.
in
t/
f
e
a
tu
re
s/f
a
c
t
f
il
e
s/c
a
n
c
e
r/en
/.
[
A
c
c
e
ss
e
d
2
6
M
a
rc
h
2
0
2
1
].
[3
]
M
.
S
a
m
a
n
d
a
ri,
M
.
G
.
Ju
li
a
,
A
.
Ri
c
e
,
A
.
Ch
ro
n
o
p
o
u
lo
s
,
A
.
E.
D.
R.
He
rn
a
n
d
e
s,
“
L
iq
u
id
b
i
o
p
sie
s
f
o
r
m
a
n
a
g
e
m
e
n
t
o
f
p
a
n
c
re
a
ti
c
c
a
n
c
e
r,
”
T
ra
n
sla
t
io
n
a
l
Res
e
a
rc
h
,
v
o
l.
2
0
1
,
p
p
.
9
8
-
1
2
7
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
6
3
/1
.
4
9
9
1
2
3
7
.
[4
]
V
.
P
a
n
c
a
a
n
d
Z.
Ru
sta
m
,
“
A
p
p
li
c
a
ti
o
n
o
f
m
a
c
h
in
e
l
e
a
rn
in
g
o
n
b
ra
in
c
a
n
c
e
r
m
u
lt
icla
ss
c
las
sif
ica
ti
o
n
,
”
AIP
Pu
b
li
s
h
in
g
L
L
C,
v
o
l
.
1
8
6
2
,
p
.
0
3
0
1
3
3
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
trsl.
2
0
1
8
.
0
7
.
0
0
8
.
[5
]
J.
Ko
k
k
in
o
s
e
t
a
l.
,
“
T
a
rg
e
ti
n
g
th
e
Un
d
r
u
g
g
a
b
le
in
p
a
n
c
re
a
ti
c
C
a
n
c
e
r
u
sin
g
Na
n
o
-
b
a
se
d
g
e
n
e
si
len
c
in
g
d
r
u
g
s,”
Bi
o
ma
ter
i
a
ls,
v
o
l.
2
4
0
,
p
.
1
1
9
7
4
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
b
i
o
m
a
teria
l
s.2
0
1
9
.
1
1
9
7
4
2
.
[6
]
Am
e
rica
n
Ca
n
c
e
r
S
o
c
iety
,
“
P
a
n
c
re
a
ti
c
Ca
n
c
e
r,
”
[
On
li
n
e
]
.
A
v
a
il
a
b
le:
h
t
tp
s://
w
ww
.
c
a
n
c
e
r.
o
rg
/ca
n
c
e
r/p
a
n
c
re
a
ti
c
-
c
a
n
c
e
r.
h
tm
l.
[
A
c
c
e
ss
e
d
2
6
M
a
rc
h
2
0
2
1
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
I
n
t J
A
r
ti
f
I
n
tell,
Vo
l.
1
0
,
No
.
2
,
J
u
n
e
2
0
2
1
:
4
76
–
481
480
[7
]
M
a
y
o
c
li
n
ic,
“
P
a
n
c
re
a
ti
c
Ca
n
c
e
r,
”
2
0
1
9
.
[
O
n
l
in
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
w
ww
.
m
a
y
o
c
li
n
ic.o
rg
/d
ise
a
se
s
-
c
o
n
d
i
ti
o
n
s/p
a
n
c
re
a
ti
c
-
c
a
n
c
e
r/s
y
m
p
to
m
s
-
c
a
u
se
s/s
y
c
-
2
0
3
5
5
4
2
1
.
[
A
c
c
e
ss
e
d
2
6
M
a
rc
h
2
0
2
1
]
.
[8
]
H.
A
sri,
H.
M
o
u
sa
n
n
if
,
H.
A
l
M
o
a
tas
sim
e
a
n
d
T
.
No
e
l,
“
Us
in
g
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
f
o
r
b
re
a
st
c
a
n
c
e
r
ris
k
p
re
d
ict
io
n
a
n
d
d
iag
n
o
sis,”
Pro
c
e
d
ia
Co
m
p
u
t
.
S
c
i
,
v
o
l.
8
3
,
p
p
.
1
0
6
4
-
1
0
6
9
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.
2
0
1
6
.
0
4
.
2
2
4
.
[9
]
D.
L
.
S
.
Ag
ra
wa
l,
R.
P
a
n
d
a
a
n
d
A
.
A
b
ra
h
a
m
,
“
Op
ti
m
a
l
b
re
a
st
c
a
n
c
e
r
c
las
sif
i
c
a
ti
o
n
u
sin
g
G
a
u
ss
–
Ne
w
to
n
re
p
re
se
n
tatio
n
b
a
se
d
a
lg
o
rit
h
m
,
”
Exp
e
rt
S
y
ste
ms
wi
th
Ap
p
li
c
a
ti
o
n
s,
v
o
l.
8
5
,
p
p
.
1
3
4
-
1
4
5
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
7
.
0
5
.
0
3
5
.
[1
0
]
J.
T
a
n
g
,
S
.
A
lel
y
a
n
i
a
n
d
H.
L
iu
,
“
F
e
a
tu
re
se
lec
ti
o
n
f
o
r
c
las
si
f
ic
a
ti
o
n
:
A
re
v
ie
w
,
”
CRC
Pre
ss
,
2
0
1
4
.
[
On
li
n
e
]
.
Av
a
il
a
b
le:
h
tt
p
:/
/www
.
m
a
th
.
c
h
a
lme
rs.se
/S
tat/
G
ru
n
d
u
tb
/G
U/M
S
A
2
2
0
/S
1
8
/f
e
a
tse
le
c
t.
p
d
f
.
[1
1
]
K.
F
a
wa
g
re
h
,
M
.
M
.
G
a
b
e
r
a
n
d
E.
El
y
a
n
,
“
Ra
n
d
o
m
f
o
re
sts:
f
ro
m
e
a
rl
y
d
e
v
e
lo
p
m
e
n
ts
to
re
c
e
n
t
a
d
v
a
n
c
e
m
e
n
ts,”
S
y
ste
ms
S
c
ien
c
e
&
Co
n
tro
l
En
g
i
n
e
e
rin
g
:
An
Op
e
n
Acc
e
ss
J
o
u
rn
a
l
2
,
v
o
l.
1
,
p
p
.
6
0
2
-
6
0
9
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
8
0
/
2
1
6
4
2
5
8
3
.
2
0
1
4
.
9
5
6
2
6
5
.
[1
2
]
C.
P
e
n
g
,
K
.
L
e
e
a
n
d
G
.
In
g
e
rso
l
l,
“
A
n
in
tro
d
u
c
ti
o
n
t
o
lo
g
isti
c
re
g
re
ss
io
n
a
n
a
l
y
sis
a
n
d
re
p
o
rti
n
g
,
”
T
h
e
jo
u
rn
a
l
o
f
e
d
u
c
a
ti
o
n
a
l
re
se
a
rc
h
,
v
o
l
.
9
6
,
n
o
.
1
,
p
p
.
3
-
1
4
,
2
0
0
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
2
0
6
7
0
2
0
9
5
9
8
7
8
6
.
[1
3
]
K.
G
h
a
z
v
in
i,
M
.
Yo
u
se
f
i,
F
.
F
i
ro
o
z
e
h
a
n
d
S
.
M
a
n
so
u
r
i,
“
P
re
d
i
c
to
rs
o
f
tu
b
e
rc
u
lo
sis:
A
p
p
l
ica
ti
o
n
o
f
a
lo
g
isti
c
re
g
re
ss
io
n
m
o
d
e
l,
”
Ge
n
e
Rep
o
rts,
v
o
l.
1
7
,
p
.
1
0
0
5
2
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
1
6
/j
.
g
e
n
re
p
.
2
0
1
9
.
1
0
0
5
2
7
.
[1
4
]
Y.
Ca
o
,
X
.
Z
h
a
n
g
,
Y.
F
u
,
Z.
L
u
a
n
d
X
.
S
h
e
n
,
“
Urb
a
n
sp
a
ti
a
l
g
ro
w
th
m
o
d
e
li
n
g
u
sin
g
lo
g
isti
c
re
g
re
ss
i
o
n
a
n
d
c
e
ll
u
lar
a
u
to
m
a
ta:
A
c
a
se
stu
d
y
o
f
Ha
n
g
z
h
o
u
,
”
Eco
l
o
g
ica
l
In
d
i
c
a
to
rs
,
v
o
l.
1
1
3
,
p
.
1
0
6
2
0
0
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/
j.
e
c
o
li
n
d
.
2
0
2
0
.
1
0
6
2
0
0
.
[1
5
]
C.
A
ro
e
f
,
R.
Yu
d
a
,
Z.
Ru
sta
m
a
n
d
J.
P
a
n
d
e
lak
i,
“
M
u
lt
in
o
m
ial
L
o
g
isti
c
Re
g
r
e
ss
io
n
a
n
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
i
n
e
f
o
r
Os
teo
a
rth
rit
is
Clas
sf
isica
ti
o
n
,
”
In
J
o
u
r
n
a
l
o
f
Ph
y
sic
s:
Co
n
fer
e
n
c
e
S
e
rie
s,
v
o
l.
0
1
2
0
1
2
,
p
.
1
4
1
7
(
1
),
2
0
1
9
,
d
o
i:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/1
4
1
7
/1
/
0
1
2
0
1
2
.
[1
6
]
T
.
Oc
ta
v
ian
i
a
n
d
Z.
Ru
sta
m
,
“
a
n
d
o
m
f
o
re
st
f
o
r
b
re
a
st
c
a
n
c
e
r
p
re
d
ictio
n
,
”
In
AIP
C
o
n
fer
e
n
c
e
Pro
c
e
e
d
in
g
s,
v
o
l.
2
1
6
8
,
n
o
.
1
,
p
.
0
2
0
0
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
6
3
/
1
.
5
1
3
2
4
7
7
.
[1
7
]
L
.
Bre
i
m
a
n
,
“
Ra
n
d
o
m
F
o
re
st,”
M
a
c
h
in
e
L
e
a
rn
i
n
g
,
v
o
l.
4
5
,
n
o
.
1
,
p
p
.
5
-
3
2
,
2
0
0
1
,
d
o
i:
1
0
.
1
0
2
3
/A
:1
0
1
0
9
3
3
4
0
4
3
2
4
.
[1
8
]
M
.
Hu
l
jan
a
h
,
Z.
Ru
sta
m
,
S
.
Ut
a
m
a
a
n
d
T
.
S
isw
a
n
ti
n
in
g
,
“
F
e
a
t
u
re
se
lec
ti
o
n
u
sin
g
ra
n
d
o
m
f
o
re
st
c
las
sif
ier
f
o
r
p
re
d
ictin
g
p
r
o
sta
te
c
a
n
c
e
r,
”
In
IOP
Co
n
fer
e
n
c
e
S
e
rie
s:
M
a
ter
ia
ls
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
5
4
6
,
n
o
.
5
,
p
.
0
5
2
0
3
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
8
8
/1
7
5
7
-
8
9
9
X/5
4
6
/
5
/0
5
2
0
3
1
.
[1
9
]
T
.
Ho
,
“
Ra
n
d
o
m
d
e
c
isio
n
f
o
re
sts,”
In
Pro
c
e
e
d
in
g
s
o
f
3
rd
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
d
o
c
u
me
n
t
a
n
a
lys
is
a
n
d
re
c
o
g
n
it
i
o
n
,
v
o
l.
1
,
p
p
.
2
7
8
-
2
8
2
,
1
9
9
5
,
d
o
i:
1
0
.
1
1
0
9
/ICDA
R.
1
9
9
5
.
5
9
8
9
9
4
.
[2
0
]
J.
S
in
g
h
a
n
d
A
.
S
.
A
ro
ra
,
“
A
f
r
a
m
e
w
o
rk
f
o
r
e
n
h
a
n
c
i
n
g
th
e
th
e
r
m
o
g
r
a
p
h
ic
e
v
a
lu
a
ti
o
n
o
n
c
h
a
ra
c
t
e
risti
c
a
re
a
s
f
o
r
p
a
ra
n
a
sa
l
sin
u
siti
s
d
e
tec
ti
o
n
,
”
In
fra
re
d
Ph
y
sic
s
&
T
e
c
h
n
o
lo
g
y
,
v
o
l.
8
5
,
p
p
.
4
5
7
-
4
6
4
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
1
6
/
j.
in
f
ra
re
d
.
2
0
1
7
.
0
8
.
0
1
1
.
[2
1
]
A
.
A
r
f
ian
i
a
n
d
Z.
R
u
sta
m
,
“
Ov
a
ri
a
n
c
a
n
c
e
r
d
a
ta
c
las
sif
ica
ti
o
n
u
si
n
g
b
a
g
g
in
g
a
n
d
ra
n
d
o
m
f
o
re
st,”
In
AIP
Co
n
fer
e
n
c
e
Pro
c
e
e
d
in
g
s
,
v
o
l.
2
1
6
8
,
p
.
0
2
0
0
4
6
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
6
3
/
1
.
5
1
3
2
4
7
3
.
[2
2
]
V
.
Ro
d
rig
u
e
z
-
G
a
li
a
n
o
,
M
.
S
a
n
c
h
e
z
-
Ca
stil
lo
,
J.
Da
sh
,
P
.
A
tk
in
so
n
a
n
d
J.
Oje
d
a
-
Zu
jar,
“
M
o
d
e
ll
in
g
in
tera
n
n
u
a
l
v
a
riatio
n
in
th
e
sp
ri
n
g
a
n
d
a
u
tu
m
n
lan
d
su
rf
a
c
e
p
h
e
n
o
l
o
g
y
o
f
th
e
E
u
ro
p
e
a
n
f
o
re
st,”
Bi
o
g
e
o
sc
ien
c
e
s
,
v
o
l.
1
3
,
n
o
.
1
1
,
p
p
.
3
3
0
5
-
1
7
,
2
0
1
6
,
d
o
i:
1
0
.
5
1
9
4
/
b
g
-
13
-
3
3
0
5
-
2
0
1
6
.
[2
3
]
Z.
Ru
sta
m
,
S
.
Ha
rti
n
i,
N.
P
u
tri
a
n
d
J.
P
a
n
d
e
lak
i,
“
Hie
ra
rc
h
ica
l
Clu
ste
rin
g
A
lg
o
rit
h
m
B
a
se
d
o
n
De
n
s
it
y
P
e
a
k
s
u
sin
g
Ke
rn
e
l
F
u
n
c
ti
o
n
f
o
r
T
h
a
las
se
m
i
a
Clas
sif
ic
a
ti
o
n
,
”
in
2
n
d
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
In
te
ll
ig
e
n
t
S
y
ste
ms
fo
r S
u
sta
i
n
a
b
le De
v
e
lo
p
me
n
t
,
AI2
S
D 2
0
1
9
,
M
a
rra
k
e
c
h
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/9
7
8
-
3
-
0
3
0
-
3
6
6
7
4
-
2
_
2
1
.
[2
4
]
M
.
S
o
k
o
lo
v
a
,
N.
Ja
p
k
o
w
icz
a
n
d
S
.
S
z
p
a
k
o
w
icz
,
“
Be
y
o
n
d
a
c
c
u
ra
c
y
,
F
-
sc
o
re
a
n
d
ROC:
a
f
a
m
il
y
o
f
d
isc
rim
in
a
n
t
m
e
a
su
re
s
f
o
r
p
e
rf
o
r
m
a
n
c
e
e
v
a
l
u
a
ti
o
n
,
”
in
A
u
stra
l
a
sia
n
jo
i
n
t
c
o
n
fer
e
n
c
e
o
n
a
rti
fi
c
ia
l
i
n
telli
g
e
n
c
e
,
v
o
l.
4
,
p
p
.
1
0
1
5
-
1
0
2
1
,
2
0
0
6
,
d
o
i:
1
0
.
1
0
0
7
/1
1
9
4
1
4
3
9
_
1
1
4
.
[2
5
]
E
.
Iz
q
u
ierd
o
-
V
e
rd
ig
u
ier
a
n
d
R
.
Zu
rit
a
-
M
il
la,
“
A
n
e
v
a
lu
a
ti
o
n
o
f
G
u
id
e
d
Re
g
u
lariz
e
d
Ra
n
d
o
m
F
o
re
st
f
o
r
c
las
si
f
ica
ti
o
n
a
n
d
re
g
re
ss
io
n
tas
k
s
in
re
m
o
te
se
n
sin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
p
p
li
e
d
Ea
rt
h
Ob
se
rv
a
ti
o
n
a
n
d
Ge
o
in
fo
rm
a
ti
o
n
,
v
o
l
.
8
8
,
p
.
1
0
2
0
5
1
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
jag
.
2
0
2
0
.
1
0
2
0
5
1
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Z
u
her
m
a
n
Ru
s
t
a
m
is
an
Ass
o
ciate
P
r
o
f
es
s
o
r
an
d
a
l
ec
tu
r
er
o
f
t
h
e
i
n
telli
g
e
n
ce
co
m
p
u
tatio
n
at
th
e
Dep
ar
t
m
e
n
t
o
f
Ma
t
h
e
m
atics,
U
n
i
v
er
s
it
y
o
f
I
n
d
o
n
esia.
He
o
b
tain
ed
h
is
Ma
s
ter
o
f
Scien
ce
i
n
1
9
8
9
in
i
n
f
o
r
m
atic
s
,
P
ar
is
Did
er
o
t
Un
i
v
er
s
it
y
,
Fre
n
c
h
,
a
n
d
co
m
p
leted
h
i
s
P
h
.
D.
i
n
2
0
0
6
f
r
o
m
co
m
p
u
ter
s
cien
ce
,
Un
iv
er
s
it
y
o
f
I
n
d
o
n
esia.
Ass
o
c.
P
r
o
f
.
Dr
.
R
u
s
ta
m
is
a
m
e
m
b
e
r
o
f
I
E
E
E
w
h
o
i
s
ac
ti
v
el
y
r
es
ea
r
ch
in
g
m
ac
h
in
e
lear
n
i
n
g
,
p
atter
n
r
ec
o
g
n
itio
n
,
n
e
u
r
al
n
et
w
o
r
k
,
ar
ti
f
icial
i
n
telli
g
e
n
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
A
r
ti
f
I
n
tell
I
SS
N:
2252
-
8938
P
a
n
crea
tic
ca
n
ce
r
cla
s
s
ifica
tio
n
u
s
in
g
l
o
g
is
tic
r
eg
r
ess
io
n
a
n
d
r
a
n
d
o
m
fo
r
est
(
Zu
h
erma
n
R
u
s
ta
m
)
481
F
ild
za
h
Z
ha
f
a
rina
is
a
f
i
n
al
y
ea
r
s
t
u
d
en
t
in
t
h
e
De
p
ar
tm
e
n
t
o
f
Ma
th
e
m
atic
s
,
Un
i
v
er
s
it
y
o
f
I
n
d
o
n
e
s
ia.
Sh
e
i
s
cu
r
r
e
n
tl
y
w
o
r
k
i
n
g
o
n
h
er
th
esis
,
w
h
ic
h
i
s
f
ir
m
l
y
ab
o
u
t
ap
p
lied
m
at
h
e
m
atic
s
u
s
i
n
g
m
ac
h
in
e
lear
n
i
n
g
.
A
ls
o
,
M
s
.
Fil
d
za
h
’
s
s
p
ec
ialtie
s
i
n
r
esear
ch
ar
e
m
o
s
tl
y
ab
o
u
t
m
ac
h
in
e
lear
n
i
n
g
i
n
v
ar
io
u
s
f
ield
s
,
e
s
p
ec
iall
y
m
ed
ical.
G
lo
ri
Ste
p
ha
ni
Sa
ra
g
ih
w
as
b
o
r
n
in
Me
d
an
,
1
7
J
an
u
ar
y
1
9
9
7
.
Sh
e
is
a
B
ac
h
elo
r
o
f
Scien
ce
f
r
o
m
Dep
ar
t
m
en
t
o
f
Ma
th
e
m
atics,
U
n
i
v
er
s
ita
s
I
n
d
o
n
esia,
w
h
o
i
s
co
m
p
leti
n
g
th
e
Ma
s
ter
o
f
Sc
ien
ce
at
Un
i
v
er
s
ita
s
I
n
d
o
n
esia
an
d
is
c
u
r
r
en
tl
y
p
u
r
s
u
i
n
g
a
P
h
.
D.
i
n
in
telli
g
e
n
ce
co
m
p
u
tatio
n
.
Ms.
Glo
r
i
is
cu
r
r
en
tl
y
a
P
r
o
ce
s
s
I
m
p
r
o
v
e
m
en
t
Ma
n
a
g
er
i
n
PT
.
A
p
lik
a
s
i
Kar
y
a
An
a
k
B
a
n
g
s
a
(
Go
j
ek
)
.
Her
cu
r
r
en
t
r
esea
r
ch
is
m
ac
h
i
n
e
o
n
m
ac
h
i
n
e
lear
n
in
g
a
n
d
n
eu
r
al
n
et
w
o
r
k
i
n
v
ar
io
u
s
f
ield
s
,
esp
ec
iall
y
m
ed
ical
an
d
f
i
n
a
n
ce
.
Sri
H
a
rt
ini
is
a
B
ac
h
elo
r
o
f
Scien
ce
f
r
o
m
t
h
e
Dep
ar
t
m
e
n
t
o
f
Ma
th
e
m
atic
s
,
Un
iv
er
s
it
y
o
f
I
n
d
o
n
esia,
w
h
o
is
also
co
m
p
let
in
g
th
e
Ma
s
ter
o
f
Scien
ce
at
th
e
Un
i
v
er
s
it
y
o
f
I
n
d
o
n
esia
a
n
d
i
s
c
u
r
r
en
tl
y
p
u
r
s
u
i
n
g
a
P
h
.
D.
in
in
telli
g
en
ce
c
o
m
p
u
tatio
n
.
Ms.
Har
tin
i
is
p
ass
io
n
atel
y
r
esear
c
h
i
n
g
m
ac
h
in
e
lear
n
i
n
g
,
co
m
p
u
ter
v
is
io
n
,
n
e
u
r
al
n
et
w
o
r
k
s
a
n
d
d
ee
p
lear
n
in
g
i
n
v
ar
io
u
s
f
ield
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.