I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
9
,
No
.
1
,
Ju
ly
2
0
2
5
,
p
p
.
374
~
3
8
6
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
1
.
pp
374
-
3
8
6
374
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Seeking
bes
t
per
f
o
rma
nce:
a
com
p
a
ra
tive eva
lua
tion o
f
ma
chine
lea
rning
mo
dels i
n t
he
predic
tion o
f
hepa
ti
tis
C
M
icha
el
Ca
ba
nil
la
s
-
Ca
rbo
n
ell
1
,
J
o
s
ely
n Z
a
pa
t
a
-
P
a
uli
ni
2
1
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
d
a
d
P
r
i
v
a
d
a
d
e
l
N
o
r
t
e
,
Li
m
a
,
P
e
r
u
2
G
r
a
d
u
a
t
e
S
c
h
o
o
l
,
U
n
i
v
e
r
si
d
a
d
C
o
n
t
i
n
e
n
t
a
l
,
L
i
ma,
P
e
r
u
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
5
,
2
0
2
4
R
ev
is
ed
J
an
22
,
2
0
2
5
Acc
ep
ted
Mar
25
,
2
0
2
5
He
p
a
ti
ti
s C
is a d
ise
a
se
th
a
t
a
ffe
c
ts mill
io
n
s
o
f
p
e
o
p
le w
o
rld
wi
d
e
.
It
is sp
re
a
d
th
ro
u
g
h
c
o
n
tac
t
wit
h
c
o
n
tam
in
a
te
d
b
lo
o
d
th
ro
u
g
h
i
n
jec
ti
o
n
s,
tra
n
sf
u
sio
n
s
,
o
r
o
th
e
r
m
e
a
n
s.
It
is
e
stim
a
ted
th
a
t
with
e
a
rly
d
e
tec
ti
o
n
p
a
ti
e
n
ts
h
a
v
e
a
h
ig
h
e
r
ra
te
o
f
re
c
o
v
e
ry
.
Th
e
o
b
jec
ti
v
e
o
f
th
is
st
u
d
y
is
t
o
p
e
rfo
rm
a
c
o
m
p
a
ra
ti
v
e
e
v
a
lu
a
ti
o
n
o
f
d
iffere
n
t
m
o
d
e
ls
f
o
c
u
se
d
o
n
th
e
p
re
d
ictio
n
o
f
h
e
p
a
ti
ti
s
C,
to
d
e
term
in
e
wh
ich
o
f
th
e
m
o
d
e
l
s
o
ffe
rs
b
e
tt
e
r
p
e
rfo
rm
a
n
c
e
in
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
a
n
d
se
n
sit
iv
it
y
.
Th
e
m
o
d
e
ls
u
se
d
we
re
lo
g
isti
c
re
g
re
ss
io
n
(LR),
ra
n
d
o
m
fo
re
st
(RF
),
K
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(KN
N),
d
e
c
isio
n
tree
(DT),
a
n
d
g
ra
d
ien
t
b
o
o
sti
n
g
(G
B),
a
ime
d
a
t
h
e
p
a
ti
ti
s
C
p
re
d
ictio
n
.
T
h
e
trai
n
in
g
o
f
t
h
e
m
o
d
e
ls
wa
s
c
a
rried
o
u
t
u
si
n
g
a
d
a
tas
e
t
c
o
m
p
o
se
d
o
f
6
1
5
re
c
o
r
d
s,
wh
ich
in
c
o
rp
o
ra
te
1
4
a
tt
ri
b
u
tes
.
Th
e
stru
c
tu
re
o
f
t
h
e
a
rti
c
le
is
d
iv
id
e
d
i
n
to
six
se
c
ti
o
n
s,
in
c
lu
d
i
n
g
i
n
tro
d
u
c
ti
o
n
,
re
v
iew
o
f
re
late
d
a
rti
c
les
,
m
e
t
h
o
d
o
l
o
g
y
,
re
su
lt
s,
d
isc
u
ss
io
n
,
a
n
d
c
o
n
c
l
u
si
o
n
s.
T
h
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
m
o
d
e
ls
wa
s
e
v
a
lu
a
ted
th
r
o
u
g
h
m
e
tri
c
s
su
c
h
a
s
a
c
c
u
ra
c
y
,
se
n
siti
v
i
ty
,
F
1
c
o
u
n
t,
a
n
d
,
m
a
in
ly
,
p
re
c
isio
n
.
Th
e
re
su
lt
s
o
b
tain
e
d
p
lac
e
th
e
DT
m
o
d
e
l
a
s
th
e
m
o
st
e
fficie
n
t
p
re
d
icto
r
,
re
a
c
h
in
g
a
p
r
e
c
isio
n
,
a
c
c
u
ra
c
y
,
se
n
siti
v
it
y
,
a
n
d
F1
-
sc
o
re
o
f
9
5
%
.
K
ey
w
o
r
d
s
:
E
v
alu
atio
n
Hep
atitis
Ma
ch
in
e
lear
n
in
g
Mo
d
els
Pre
d
ictio
n
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
:
J
o
s
ely
n
Z
ap
ata
-
Pau
lin
i
Gr
ad
u
ate
Sch
o
o
l,
Un
iv
er
s
id
ad
C
o
n
tin
en
tal
Alf
r
ed
o
Me
n
d
io
la
5
2
1
0
,
L
o
s
Oliv
o
s
1
5
3
1
1
,
L
im
a,
Per
ú
E
m
ail: 7
0
9
9
4
3
3
7
@
co
n
tin
en
tal
.
ed
u
.
p
e
1.
I
NT
RO
D
UCT
I
O
N
Hep
atitis
C
(
HC
V)
i
s
a
v
ir
al
d
is
ea
s
e
th
at
wa
s
h
is
to
r
ically
cla
s
s
if
ied
s
im
p
ly
as
v
ir
al
h
ep
atiti
s
wh
en
it
was
n
o
t
id
en
tifie
d
as
ty
p
e
A
o
r
ty
p
e
B
.
T
h
is
v
ir
u
s
is
m
ain
ly
tr
an
s
m
itted
th
r
o
u
g
h
b
lo
o
d
tr
a
n
s
f
u
s
io
n
s
an
d
o
th
er
co
n
tacts
with
co
n
tam
in
ated
b
l
o
o
d
.
O
n
ce
th
e
in
f
ec
tio
n
is
ac
q
u
ir
ed
,
p
atien
ts
f
ac
e
a
h
ig
h
er
r
is
k
o
f
d
ev
elo
p
i
n
g
ch
r
o
n
ic
liv
er
d
is
ea
s
es,
s
u
ch
as
h
ep
ato
ce
llu
lar
ca
r
cin
o
m
a
o
r
cir
r
h
o
s
is
[
1
]
Acc
o
r
d
in
g
to
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
,
ap
p
r
o
x
im
ately
5
8
m
illi
o
n
p
eo
p
le
wo
r
ld
wid
e
ar
e
ch
r
o
n
ically
in
f
ec
t
ed
with
HC
V,
an
d
m
o
r
e
th
a
n
1
.
2
m
illi
o
n
n
ew
in
f
ec
tio
n
s
ar
e
r
ep
o
r
ted
ea
c
h
y
ea
r
.
Of
th
ese,
a
b
o
u
t
3
m
illi
o
n
ch
ild
r
e
n
an
d
ad
o
lescen
ts
ar
e
also
ch
r
o
n
icall
y
af
f
ec
ted
[
2
]
.
HC
V
p
r
im
ar
i
ly
attac
k
s
liv
er
ce
lls
an
d
is
u
n
iq
u
e
to
h
u
m
an
s
.
T
h
is
v
ir
u
s
p
o
s
s
ess
es
a
r
em
ar
k
ab
le
ab
ilit
y
to
ev
ad
e
b
o
th
i
n
n
a
te
an
d
ad
ap
tiv
e
im
m
u
n
it
y
,
r
esu
ltin
g
in
ch
r
o
n
ic
in
f
ec
tio
n
s
in
ap
p
r
o
x
i
m
ately
7
0
%
o
f
ca
s
es
[
3
]
.
T
h
e
ap
p
ea
r
a
n
ce
o
f
HC
V
an
tib
o
d
ies
is
a
co
m
m
o
n
in
d
icato
r
o
f
in
f
ec
tio
n
;
ac
co
r
d
in
g
t
o
r
ec
o
r
d
s
,
Af
r
ica
an
d
Asi
a
ar
e
k
n
o
wn
to
b
e
th
e
c
o
n
tin
en
ts
with
th
e
h
ig
h
est
p
r
e
v
alen
ce
r
ates
o
f
th
ese
an
tib
o
d
ies,
wh
ile
Au
s
tr
alia,
No
r
th
Am
er
ica,
an
d
W
ester
n
E
u
r
o
p
e
s
h
o
w
th
e
lo
west
r
ates
[
4
]
.
Alth
o
u
g
h
p
r
ev
e
n
tiv
e
m
eth
o
d
s
,
s
u
ch
as
v
ac
cin
atio
n
an
d
t
h
e
u
s
e
o
f
p
r
o
m
is
in
g
n
ew
d
r
u
g
s
,
ca
n
c
u
r
e
HC
V
in
f
ec
tio
n
in
u
p
to
7
0
%
o
f
tr
ea
t
ed
p
atien
ts
[
5
]
,
m
o
s
t
in
f
ec
ted
i
n
d
iv
id
u
als
a
r
e
u
n
awa
r
e
o
f
t
h
eir
co
n
d
itio
n
,
s
o
it
is
a
p
r
io
r
ity
t
o
im
p
lem
en
t scr
ee
n
in
g
p
r
o
g
r
a
m
s
f
o
r
ea
r
l
y
an
d
tim
ely
d
etec
tio
n
o
f
th
e
d
is
ea
s
e
[
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
S
ee
kin
g
b
est p
erfo
r
ma
n
ce
:
a
c
o
mp
a
r
a
tive
ev
a
lu
a
tio
n
o
f m
a
c
h
in
e
…
(
Mich
a
el
C
a
b
a
n
illa
s
-
C
a
r
b
o
n
ell
)
375
HC
V
i
s
d
iv
id
ed
in
to
a
to
tal
o
f
s
ev
en
g
en
o
ty
p
es,
wh
ich
ar
e
d
iv
id
ed
in
t
o
m
u
ltip
le
s
u
b
ty
p
es,
th
e
class
if
icatio
n
o
f
th
ese
g
e
n
o
ty
p
es
d
ep
en
d
s
o
n
th
e
et
h
n
ic
g
r
o
u
p
an
d
m
o
d
e
o
f
t
r
an
s
m
is
i
o
n
[
7
]
.
Gen
o
ty
p
e
1
is
th
e
m
o
s
t
co
m
m
o
n
with
4
6
%
o
f
all
ca
s
es,
with
p
r
esen
ce
in
r
eg
io
n
s
o
f
Asi
a,
No
r
th
Am
e
r
ic
a,
Au
s
tr
alia,
So
u
th
Am
er
ica,
No
r
th
er
n
a
n
d
W
ester
n
E
u
r
o
p
e
No
r
th
e
r
n
an
d
W
est
er
n
E
u
r
o
p
e
[
8
]
,
[
9
]
.
Gen
o
ty
p
e
s
2
,
4
,
an
d
6
ac
c
o
u
n
t
f
o
r
m
o
s
t
o
f
th
e
r
em
ain
in
g
HC
V
ca
s
es,
b
u
t
o
n
ly
o
n
e
ca
s
e
o
f
ty
p
e
7
h
as
b
ee
n
r
ep
o
r
ted
s
o
f
ar
in
C
an
ad
a
[
1
0
]
.
Du
r
in
g
a
p
r
e
v
alen
ce
r
ev
iew
in
th
e
Un
ited
States
,
an
av
er
ag
e
o
f
3
.
5
m
illi
o
n
p
eo
p
le
in
th
e
co
u
n
tr
y
wer
e
id
en
tifie
d
as
b
ei
n
g
in
f
ec
ted
w
ith
HC
V
[
1
1
]
.
I
t
was
also
id
e
n
tifie
d
th
at
5
7
%
o
f
p
e
o
p
le
h
a
d
b
ee
n
s
cr
ee
n
ed
an
d
wer
e
awa
r
e
o
f
th
eir
co
n
d
itio
n
,
an
d
5
0
%
h
ad
HC
V
an
tib
o
d
ies
in
th
eir
s
y
s
tem
[
1
2
]
.
T
h
e
p
r
ev
alen
ce
o
f
th
e
d
is
ea
s
e
in
co
u
n
tr
ies
s
u
ch
as
E
g
y
p
t
is
1
8
%
to
2
2
%,
in
I
taly
i
t
is
2
.
5
%
to
1
0
%,
in
Pak
is
tan
it
is
4
.
9
%,
in
C
h
in
a
it is
3
.
2
% a
n
d
in
I
n
d
o
n
esia
,
it is
2
.
1
%
[
1
3
]
.
C
u
r
r
en
tly
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
m
eth
o
d
s
,
s
u
ch
as
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
m
o
d
els,
ar
e
p
la
y
in
g
a
cr
u
cial
r
o
le
in
th
e
p
r
o
ce
s
s
o
f
d
ia
g
n
o
s
is
,
p
r
ed
ictio
n
,
a
n
d
tr
ea
tm
en
t o
f
d
is
ea
s
es,
s
u
ch
as
d
iab
etes,
Alzh
eim
er
’
s
d
is
e
ase
,
an
d
h
ea
r
t
d
is
ea
s
e
[
1
4
]
,
[
1
5
]
.
I
n
ML
-
r
elate
d
s
tu
d
ies,
al
g
o
r
ith
m
s
o
r
m
o
d
els
ar
e
em
p
lo
y
e
d
to
id
en
tify
p
at
ter
n
s
o
r
in
d
icato
r
s
with
in
lar
g
e
d
ata
s
ets
[
1
6
]
,
[
1
7
]
;
to
d
etec
t
th
e
p
o
s
s
ib
le
ex
is
ten
ce
o
r
ab
s
en
ce
o
f
th
e
ailm
en
t
u
n
d
er
in
v
esti
g
atio
n
[
1
8
]
.
T
h
er
ef
o
r
e,
th
is
to
o
l
ca
n
b
e
u
s
ef
u
l
f
o
r
th
e
d
ev
elo
p
m
e
n
t o
f
an
HC
V
p
r
ed
i
ctio
n
m
o
d
el.
T
h
is
s
tu
d
y
aim
s
to
ad
d
r
ess
t
h
e
n
e
ed
to
d
ev
elo
p
in
n
o
v
ativ
e
tech
n
iq
u
es
to
p
r
ed
ict
HC
V
in
f
ec
tio
n
.
T
h
r
o
u
g
h
t
h
e
b
e
n
ch
m
a
r
k
in
g
o
f
v
ar
io
u
s
ML
m
o
d
els,
in
o
r
d
e
r
to
d
ete
r
m
in
e
wh
ic
h
o
f
th
e
m
o
d
els
o
f
f
e
r
s
b
etter
p
er
f
o
r
m
an
ce
in
ac
cu
r
ac
y
,
p
r
e
cisi
o
n
,
an
d
s
en
s
itiv
ity
.
T
o
th
i
s
en
d
,
th
e
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
r
an
d
o
m
f
o
r
est
(
R
F),
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
d
ec
is
io
n
tr
ee
(
DT
)
,
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
(
GB
)
m
o
d
els
ar
e
co
n
ce
p
tu
alize
d
an
d
d
ev
elo
p
e
d
.
T
h
is
r
esear
ch
aim
s
n
o
t
o
n
ly
t
o
f
ac
ilit
ate
th
e
ea
r
ly
d
etec
tio
n
o
f
HC
V,
b
u
t
a
ls
o
to
im
p
r
o
v
e
th
e
d
esig
n
o
f
m
o
r
e
ef
f
ec
ti
v
e
tr
ea
t
m
en
ts
ag
ain
s
t
th
e
v
ir
u
s
,
th
u
s
c
o
n
tr
ib
u
tin
g
to
th
e
r
e
d
u
ctio
n
o
f
th
e
o
v
er
all
im
p
ac
t
o
f
th
is
d
is
ea
s
e
.
T
h
is
ar
ticle
i
s
s
tr
u
ctu
r
ed
in
s
ix
p
ar
ts
.
T
h
e
f
ir
s
t
p
ar
t
d
etails
an
d
co
n
tex
tu
alize
s
th
e
p
r
o
b
le
m
s
o
f
th
e
s
tu
d
y
.
T
h
e
s
ec
o
n
d
p
a
r
t
is
a
r
ev
iew
o
f
r
elate
d
s
tu
d
ies.
I
n
th
e
th
ir
d
p
ar
t,
we
d
ev
elo
p
th
e
m
eth
o
d
o
lo
g
y
d
iv
i
d
ed
in
to
two
s
ec
tio
n
s
,
in
th
e
f
ir
s
t
s
ec
tio
n
we
co
n
ce
p
tu
alize
th
e
ML
m
o
d
els,
an
d
in
th
e
s
ec
o
n
d
s
ec
tio
n
,
we
d
ev
elo
p
th
e
ca
s
e
s
tu
d
y
.
I
n
p
a
r
t
f
o
u
r
o
f
th
e
ar
ticle
we
p
r
esen
t
th
e
r
esu
lts
o
f
th
e
m
o
d
els.
I
n
p
ar
t
f
iv
e
we
d
is
cu
s
s
th
e
r
esu
lts
o
b
tain
ed
with
r
elate
d
s
t
u
d
ies.
Fin
ally
,
in
p
a
r
t six
we
p
r
esen
t th
e
co
n
clu
s
io
n
s
.
2.
RE
L
AT
E
D
WO
RK
I
n
th
is
s
ec
tio
n
,
we
d
is
cu
s
s
wo
r
k
r
elate
d
to
t
h
e
ca
s
e
s
tu
d
y
.
Alizar
g
ar
et
a
l.
[
1
9
]
,
aim
ed
to
u
s
e
d
if
f
er
en
t
ML
m
o
d
els
t
o
p
r
ed
ict
h
ep
atit
is
C
with
b
lo
o
d
test
s
,
to
tr
ea
t
p
atien
ts
in
th
e
ea
r
ly
s
tag
es
o
f
in
f
ec
tio
n
;
in
th
eir
m
eth
o
d
o
l
o
g
y
,
th
e
y
u
s
ed
d
ata
m
in
in
g
tech
n
iq
u
es
to
p
r
o
ce
s
s
th
e
d
atasets
,
to
s
u
b
s
eq
u
en
tly
tr
ain
s
ix
ML
m
o
d
els;
th
e
s
tu
d
y
c
o
n
clu
d
ed
t
h
at
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
S
VM
)
an
d
ex
tr
em
e
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
XGBo
o
s
t)
m
o
d
els
r
ea
ch
ed
an
ac
c
u
r
ac
y
o
f
0
.
8
2
,
b
ein
g
th
e
b
est
r
esu
lt
s
ac
h
iev
ed
.
L
ik
ewise,
in
th
e
s
tu
d
y
f
r
o
m
Sy
af
aa
h
et
a
l.
[
2
0
]
th
e
y
ev
al
u
ated
t
h
e
lev
el
o
f
ac
cu
r
ac
y
ac
h
iev
ed
b
y
d
if
f
er
e
n
t
ML
m
o
d
els
to
d
eter
m
in
e
wh
ich
is
th
e
m
o
s
t
ac
cu
r
ate
i
n
th
e
d
etec
tio
n
o
f
h
ep
atitis
C
;
in
th
ei
r
m
eth
o
d
o
lo
g
y
th
e
y
to
o
k
i
n
to
ac
c
o
u
n
t
m
u
ltip
le
in
d
icato
r
s
o
f
b
lo
o
d
test
s
to
d
etec
t
th
e
d
i
s
ea
s
e,
to
s
u
b
s
eq
u
en
tly
tr
ain
th
e
class
if
icatio
n
m
o
d
els;
th
e
r
esu
lts
o
f
th
e
s
tu
d
y
p
o
s
itio
n
ed
n
eu
r
al
n
etwo
r
k
s
(
NN)
as
th
e
b
est
with
0
.
9
5
1
2
i
n
ac
cu
r
ac
y
,
f
o
llo
we
d
b
y
KNN
,
Naiv
e
B
ay
es
(
NB
)
an
d
R
F
with
0
.
8
9
4
3
,
0
.
9
0
2
4
,
an
d
0
.
9
4
3
1
,
r
esp
ec
tiv
ely
.
On
th
e
o
th
er
h
an
d
,
in
th
e
s
tu
d
y
f
r
o
m
Ma
et
a
l.
[
2
1
]
th
ey
ev
alu
ated
s
ev
er
al
ML
cla
s
s
i
f
ier
s
f
o
r
ea
r
ly
p
r
e
d
ictio
n
o
f
h
ep
atitis
C
;
in
th
eir
m
eth
o
d
o
l
o
g
y
,
t
h
ey
u
s
ed
th
e
b
lo
o
d
r
ec
o
r
d
s
o
f
m
u
ltip
le
p
ati
en
ts
d
iag
n
o
s
ed
with
th
is
d
is
ea
s
e
to
tr
ain
th
e
m
o
d
els;
th
e
s
tu
d
y
p
o
s
itio
n
ed
t
h
e
XGBo
o
s
t
m
o
d
el
as
th
e
b
est
in
p
r
e
d
ictin
g
th
e
d
is
ea
s
e
with
an
ac
cu
r
ac
y
o
f
0
.
9
1
5
6
,
p
r
e
cisi
o
n
o
f
0
.
9
8
an
d
s
en
s
itiv
ity
o
f
0
.
9
8
.
I
n
t
u
r
n
,
A
h
am
m
ed
et
a
l.
[
2
2
]
th
ey
s
o
u
g
h
t
to
class
if
y
th
e
liv
er
s
tate
s
o
f
p
eo
p
le
in
f
ec
ted
with
th
e
v
ir
u
s
b
y
m
ak
in
g
u
s
e
o
f
th
r
ee
ML
m
o
d
els;
in
th
eir
m
eth
o
d
o
l
o
g
y
,
th
ey
em
p
lo
y
e
d
th
e
d
ataset
f
r
o
m
t
h
e
I
C
U
r
ep
o
s
ito
r
y
,
wh
ic
h
was
s
u
b
jecte
d
to
th
e
s
y
n
th
etic
m
in
o
r
ity
o
v
er
s
am
p
lin
g
tech
n
iq
u
e
(
SMO
TE)
,
an
d
s
u
b
s
eq
u
en
tly
a
p
p
lied
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
to
f
in
ally
tr
a
in
th
e
m
o
d
els;
th
e
s
tu
d
y
c
o
n
cl
u
d
ed
t
h
at
th
e
KNN
m
o
d
el
ac
h
iev
ed
th
e
b
est
p
er
f
o
r
m
an
ce
with
0
.
9
4
4
0
in
ac
cu
r
a
cy
.
I
n
a
r
ea
l
ca
s
e,
Far
g
h
aly
et
a
l.
[
2
3
]
ev
alu
ate
d
d
if
f
er
en
t
ML
m
o
d
els
f
o
cu
s
ed
o
n
p
r
ed
ictin
g
h
e
p
atitis
C
,
in
h
ea
lth
ca
r
e
wo
r
k
e
r
s
in
E
g
y
p
t;
f
o
r
tr
ain
in
g
th
e
m
o
d
els
th
ey
em
p
lo
y
ed
a
two
-
s
tag
e
d
ataset,
in
th
e
f
ir
s
t
s
tag
e
th
e
d
ataset
was
with
o
u
t
f
ea
tu
r
e
s
elec
tio
n
an
d
in
th
e
s
ec
o
n
d
s
tag
e
th
ey
ap
p
li
ed
f
ea
tu
r
e
s
elec
tio
n
f
o
cu
s
ed
o
n
id
en
tify
in
g
f
o
r
war
d
s
eq
u
en
ce
s
;
th
e
s
tu
d
y
co
n
clu
d
e
d
th
at
th
e
R
F
m
o
d
el
ac
h
iev
ed
th
e
b
est
r
esu
lt
s
in
ce
in
th
e
f
ir
s
t
s
tag
e
it
r
ea
ch
ed
an
ac
cu
r
ac
y
o
f
0
.
9
4
0
6
an
d
in
th
e
s
ec
o
n
d
s
tag
e
a
0
.
9
4
8
8
.
I
n
th
e
s
tu
d
y
f
r
o
m
Ali
et
a
l.
[
2
4
]
th
ey
a
n
aly
ze
d
an
d
ev
alu
ated
th
e
p
er
f
o
r
m
an
ce
o
f
m
u
ltip
le
ML
alg
o
r
ith
m
s
f
o
r
t
h
e
ea
r
ly
d
ia
g
n
o
s
is
o
f
h
ep
atitis
C
;
in
th
eir
m
eth
o
d
o
l
o
g
y
,
t
h
ey
ap
p
lied
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es o
n
th
e
d
ataset
s
u
c
h
as f
ea
tu
r
e
s
elec
tio
n
,
f
o
r
war
d
f
ea
tu
r
e
s
elec
tio
n
an
d
SMOT
E
;
th
e
r
esu
lts
o
f
th
e
s
tu
d
y
s
p
ec
if
ied
th
at
th
e
ev
alu
ated
m
o
d
els
ac
h
iev
ed
an
av
er
ag
e
ac
cu
r
ac
y
o
f
0
.
8
3
,
s
u
ch
as
KNN,
R
F
,
an
d
L
R
m
o
d
els
with
a
p
er
f
o
r
m
a
n
ce
o
f
0
.
8
3
1
,
0
.
8
2
4
a
n
d
0
.
8
2
9
,
r
esp
ec
tiv
ely
.
On
th
e
o
th
e
r
h
an
d
,
C
h
en
et
a
l.
[
2
5
]
t
h
ey
p
r
o
p
o
s
e
a
u
n
iq
u
e
m
o
d
el
f
o
r
ea
ch
o
f
th
e
p
atien
ts
s
ee
k
in
g
to
b
e
d
iag
n
o
s
ed
with
h
ep
atitis
C
;
t
h
e
r
es
u
l
ts
p
o
s
i
ti
o
n
t
h
e
X
GB
o
o
s
t
m
o
d
e
l
as
t
h
e
b
e
s
t
wi
t
h
0
.
9
5
i
n
a
c
c
u
r
a
c
y
a
n
d
0
.
7
0
i
n
s
e
n
s
i
ti
v
i
t
y
.
S
a
n
t
o
s
[
2
6
]
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
374
-
3
8
6
376
co
n
tr
ast
d
if
f
er
e
n
t
ML
m
o
d
els
f
o
r
t
h
e
p
r
e
d
ictio
n
o
f
th
e
s
ev
er
ity
o
f
h
ep
atitis
C
in
f
ec
tio
n
in
p
atien
ts
;
in
th
ei
r
m
eth
o
d
o
l
o
g
y
,
th
e
y
u
s
ed
d
if
f
er
en
t
d
ata
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es,
d
ata
en
g
in
ee
r
in
g
,
a
n
d
h
y
p
e
r
p
ar
am
eter
o
p
tim
izatio
n
ap
p
lied
t
o
b
o
th
t
h
e
d
ataset
an
d
th
e
f
o
u
r
alg
o
r
ith
m
s
th
at
wer
e
ev
alu
ated
;
th
e
s
t
u
d
y
co
n
cl
u
d
ed
th
a
t
th
e
R
F
an
d
GB
m
o
d
els
ac
h
ie
v
ed
th
e
b
est
ac
cu
r
ac
y
an
d
p
r
ec
i
s
io
n
with
0
.
9
3
5
0
.
Similar
ly
,
Har
ab
o
r
et
a
l.
[
2
7
]
,
th
ey
d
ev
el
o
p
ed
a
s
tu
d
y
t
o
co
m
p
ar
e
an
d
ev
alu
ate
th
e
p
e
r
f
o
r
m
an
ce
o
f
f
o
u
r
ML
m
o
d
els
f
o
r
th
e
p
r
ed
ictio
n
o
f
Hep
atitis
B
an
d
C
s
tatu
s
;
th
e
r
esu
lts
o
f
th
e
s
tu
d
y
s
h
o
wed
th
at
th
e
m
o
d
el
with
th
e
b
est
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
is
KNN,
with
an
ac
cu
r
ac
y
o
f
0
.
9
8
1
,
f
o
llo
wed
b
y
SVM
an
d
R
F
wi
th
eq
u
al
ac
cu
r
ac
y
o
f
0
.
9
7
6
a
n
d
NB
with
0
.
9
5
7
.
T
h
e
s
tu
d
y
f
r
o
m
E
l
-
Salam
et
a
l.
[
2
8
]
aim
ed
to
an
aly
ze
an
d
ev
alu
a
te
d
if
f
er
e
n
t
ML
m
o
d
els
f
o
r
ea
r
ly
p
r
ed
ictio
n
o
f
h
e
p
atitis
C
;
in
th
eir
m
eth
o
d
o
lo
g
y
,
th
ey
ap
p
lied
d
if
f
er
en
t
tech
n
iq
u
es
s
u
c
h
as
f
ea
tu
r
e
s
elec
tio
n
f
o
r
d
ata
p
r
o
ce
s
s
in
g
;
th
e
r
esu
lts
o
f
th
e
s
tu
d
y
p
o
s
itio
n
ed
t
h
e
B
ay
esian
Netwo
r
k
m
o
d
el
with
th
e
b
est
p
er
f
o
r
m
a
n
ce
with
0
.
7
4
8
in
ac
cu
r
ac
y
.
Hash
e
m
et
a
l.
[
2
9
]
c
o
n
tr
asted
d
i
f
f
er
en
t
ML
m
o
d
els
f
o
cu
s
ed
o
n
th
e
p
r
ed
ictio
n
o
f
liv
e
r
f
ib
r
o
s
is
in
p
atien
ts
with
ch
r
o
n
ic
h
ep
atitis
C
;
th
e
r
esu
lts
d
eter
m
in
ed
th
at
th
e
m
o
d
els
o
b
tain
ed
r
esu
lts
r
an
g
in
g
f
r
o
m
0
.
6
6
3
to
0
.
8
4
4
i
n
ac
cu
r
ac
y
.
Kar
ee
m
[
3
0
]
f
o
u
r
ML
m
o
d
els
to
class
if
y
an
d
d
iag
n
o
s
e
h
ep
atitis
C
;
th
e
r
esu
lts
o
f
th
e
s
tu
d
y
p
o
s
itio
n
ed
DT
with
th
e
b
est
p
er
f
o
r
m
a
n
c
e
with
an
ac
c
u
r
ac
y
o
f
0
.
9
3
4
4
.
Me
an
wh
ile,
L
ilh
o
r
e
et
a
l.
[
3
1
]
t
h
ey
p
r
o
p
o
s
e
a
h
y
b
r
id
m
o
d
el
b
etwe
en
R
F a
n
d
SVM
f
o
r
th
e
p
r
ed
ictio
n
an
d
class
if
icatio
n
o
f
h
e
p
atitis
C
;
in
th
eir
m
eth
o
d
o
l
o
g
y
,
t
h
e
y
em
p
lo
y
e
d
v
ar
i
o
u
s
o
p
tim
iza
tio
n
tech
n
iq
u
es
f
o
r
th
e
m
o
d
e
ls
an
d
SMOT
E
to
cr
ea
te
s
y
n
th
etic
d
ata
to
e
n
h
an
ce
th
e
d
ataset;
th
e
s
tu
d
y
c
o
n
cl
u
d
ed
th
at
t
h
e
h
y
b
r
id
m
o
d
el
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
0
.
9
5
8
9
.
Fin
ally
,
Gh
az
al
et
a
l.
[
3
2
]
u
s
ed
th
e
SVM
m
o
d
el
f
o
r
h
ep
atitis
C
p
r
ed
ictio
n
; th
e
s
t
u
d
y
co
n
clu
d
e
d
th
at
th
e
m
o
d
el
m
a
n
ag
ed
to
ac
h
iev
e
an
ac
cu
r
ac
y
o
f
0
.
9
7
9
.
3.
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
o
f
th
e
s
tu
d
y
,
we
p
r
esen
t
th
e
m
eth
o
d
o
l
o
g
y
d
iv
id
ed
in
to
two
p
ar
ts
,
i
n
p
a
r
t
A,
we
co
n
ce
p
tu
alize
th
e
ML
m
o
d
els
(
L
R
,
R
F,
KNN,
DT
,
an
d
GB
)
th
at
we
em
p
lo
y
in
th
is
s
tu
d
y
.
I
n
p
ar
t
B
,
we
d
ev
elo
p
t
h
e
ca
s
e
s
tu
d
y
b
y
an
aly
zin
g
a
n
d
o
p
tim
izin
g
th
e
d
ataset
to
s
u
b
s
eq
u
en
tly
tr
ain
th
e
m
o
d
els.
3
.
1
.
Descript
io
n o
f
t
he
M
L
m
o
dels
3.
1
.
1
.
L
o
g
is
t
ic
r
eg
re
s
s
io
n
L
R
is
u
s
ed
in
ML
f
o
r
b
in
ar
y
class
if
icatio
n
,
f
o
r
ex
am
p
le,
t
o
p
r
ed
ict
t
h
e
p
r
esen
ce
o
r
a
b
s
en
ce
o
f
a
d
i
s
e
a
s
e
i
n
a
p
a
t
i
e
n
t
,
t
h
i
s
i
s
d
o
n
e
b
y
a
n
a
l
y
z
i
n
g
a
d
a
t
a
s
e
t
t
h
a
t
i
n
c
l
u
d
e
s
s
e
v
e
r
a
l
f
e
a
t
u
r
e
s
a
n
d
a
t
a
r
g
e
t
v
a
r
i
a
b
l
e
[
3
3
]
.
T
h
e
m
o
d
el
is
a
s
u
p
er
v
is
ed
lea
r
n
in
g
al
g
o
r
ith
m
,
wh
ich
aim
s
to
m
o
d
el
th
e
r
elatio
n
s
h
ip
b
etw
ee
n
in
p
u
t
f
ea
tu
r
es
an
d
o
u
tp
u
t
lab
els,
co
n
s
eq
u
en
tl
y
,
th
e
r
esu
lt
is
ex
p
r
ess
ed
as
th
e
p
r
o
b
ab
ilit
y
th
at
th
e
i
n
p
u
t b
el
o
n
g
s
to
a
p
a
r
ticu
lar
class
[3
4
]
.
U
n
lik
e
o
th
er
m
o
d
el
s
,
L
R
h
as
s
o
m
e
lim
itatio
n
s
s
u
ch
as
ass
u
m
in
g
th
at
t
h
e
in
p
u
t
f
ea
tu
r
es
an
d
o
u
tp
u
t
lab
els
ar
e
lin
ea
r
an
d
th
e
f
ea
tu
r
es
in
d
ep
e
n
d
en
t,
to
o
v
er
c
o
m
e
th
ese
d
r
awb
ac
k
s
o
th
er
m
o
d
els
wer
e
cr
ea
te
d
[
3
5
]
.
I
n
(
1
)
th
e
m
o
d
el
is
m
ath
em
atica
lly
r
ep
r
esen
ted
.
Y
is
th
e
v
ar
iab
le
r
ep
r
esen
tin
g
th
e
p
r
o
b
ab
ilit
y
o
f
an
ev
en
t
o
cc
u
r
r
in
g
,
d
e
n
o
ted
b
y
P
(
Y)
.
(
)
=
1
1
+
−
(
0
+
1
1
+
2
2
+
⋯
+
)
(
1
)
3.
1
.
2
.
Ra
nd
o
m
f
o
re
s
t
R
F
r
ep
r
esen
ts
a
g
en
er
al
ML
alg
o
r
ith
m
th
at
is
u
s
ed
in
b
o
t
h
class
if
icatio
n
an
d
r
eg
r
ess
io
n
task
s
[
3
6
]
.
T
h
is
en
s
em
b
le
lea
r
n
in
g
m
eth
o
d
cr
ea
tes m
u
ltip
le
d
ec
is
io
n
tr
e
es
d
u
r
in
g
tr
ai
n
in
g
an
d
g
e
n
er
at
es
a
m
o
d
al
class
(
in
class
if
icatio
n
)
o
r
an
av
er
a
g
e
p
r
ed
ictio
n
(
i
n
r
e
g
r
ess
io
n
)
f
r
o
m
th
e
in
d
iv
id
u
al
tr
es
[
3
7
]
.
E
ac
h
tr
ee
in
th
e
f
o
r
est
is
cr
ea
ted
f
r
o
m
a
r
an
d
o
m
s
elec
tio
n
o
f
tr
ain
in
g
d
ata
an
d
f
ea
tu
r
e
s
,
th
is
in
tr
o
d
u
ctio
n
o
f
r
an
d
o
m
n
ess
h
elp
s
to
r
ed
u
ce
o
v
er
f
itti
n
g
a
n
d
im
p
r
o
v
e
th
e
a
cc
u
r
ac
y
o
f
th
e
m
o
d
el
[
3
8
]
.
I
n
(
2
)
s
h
o
ws
t
h
e
f
o
r
m
u
la
th
at
th
e
m
o
d
el
u
s
es
to
esti
m
ate
th
e
p
r
ed
ictio
n
s
f
o
r
ea
ch
tr
ee
.
̅
(
,
)
=
[
(
,
,
)
]
(
2
)
3.
1
.
3
.
K
-
nea
re
s
t
neig
hb
o
rs
KNN
in
ML
is
u
s
ed
in
b
o
th
class
if
icatio
n
an
d
r
eg
r
ess
io
n
,
it
is
b
ased
o
n
clu
s
ter
in
g
d
ata
p
o
in
ts
in
to
g
r
o
u
p
s
an
d
ass
ig
n
in
g
th
em
t
o
th
e
g
r
o
u
p
co
n
tain
in
g
th
e
clo
s
est
d
ata
p
o
i
n
t,
ca
lled
k
-
n
ea
r
est
n
eig
h
b
o
r
[
3
9
]
.
Mo
r
eo
v
er
,
it
m
ak
es
n
o
ass
u
m
p
tio
n
s
ab
o
u
t
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
d
ata,
as
it
i
s
a
n
o
n
p
ar
am
etr
ic
m
o
d
el
[
4
0
]
.
T
h
e
m
o
d
el
u
s
es
th
e
E
u
clid
ea
n
eq
u
atio
n
,
r
ep
r
esen
ted
in
(
3
)
,
to
ca
lcu
late
th
e
d
is
tan
ce
b
etwe
en
co
n
tin
u
o
u
s
v
ar
iab
les,
wh
ile
it
r
eso
r
ts
to
t
h
e
o
v
er
lap
m
etr
ic
f
o
r
d
is
cr
ete
v
ar
iab
les
wh
en
m
ea
s
u
r
in
g
th
e
p
r
o
x
im
ity
b
etwe
en
n
eig
h
b
o
r
s
[
4
1
]
.
(
,
)
=
√
∑
(
−
)
2
=
1
(
3)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
S
ee
kin
g
b
est p
erfo
r
ma
n
ce
:
a
c
o
mp
a
r
a
tive
ev
a
lu
a
tio
n
o
f m
a
c
h
in
e
…
(
Mich
a
el
C
a
b
a
n
illa
s
-
C
a
r
b
o
n
ell
)
377
3.
1
.
4
.
Dec
is
io
n
t
ree
T
h
e
D
T
m
o
d
e
l
i
s
p
r
e
s
e
n
t
e
d
a
s
a
s
u
p
e
r
v
i
s
e
d
M
L
a
l
g
o
r
i
t
h
m
u
s
e
d
i
n
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
r
e
g
r
e
s
s
i
o
n
t
a
s
k
s
[
4
2
]
.
I
t
wo
r
k
s
b
y
r
ec
u
r
s
iv
ely
d
iv
id
i
n
g
th
e
d
ata
in
to
s
u
b
s
ets
ac
co
r
d
in
g
to
th
e
m
o
s
t
r
elev
an
t
attr
i
b
u
te,
cr
ea
tin
g
a
tr
ee
s
tr
u
ctu
r
e,
th
is
p
r
o
ce
s
s
co
n
tin
u
es
u
n
t
il
th
e
d
ata
in
ea
ch
s
u
b
s
et
b
ec
o
m
es
c
o
n
s
is
ten
t
co
n
ce
r
n
in
g
th
e
ta
r
g
et
v
ar
iab
le
o
r
u
n
til a
p
r
ed
eter
m
in
ed
s
to
p
p
in
g
cr
iter
io
n
is
m
et
[
4
3
]
.
I
n
(
4
)
th
e
m
ath
em
atica
l e
q
u
atio
n
o
f
th
e
m
o
d
el
is
ex
p
r
ess
ed
.
W
ith
in
t
h
e
eq
u
atio
n
,
Pn
is
u
s
ed
to
ex
p
r
ess
th
e
p
r
o
b
ab
ilit
y
o
f
n
o
n
-
o
cc
u
r
r
en
ce
,
s
is
u
s
ed
to
r
ep
r
esen
t th
e
s
am
p
le,
E
is
in
ter
p
r
eted
as th
e
e
n
tr
o
p
y
an
d
Py
i
s
u
s
ed
to
ex
p
r
ess
th
e
p
r
o
b
a
b
ilit
y
o
f
o
cc
u
r
r
e
n
ce
.
(
)
=
∑
(
)
−
=
0
∗
l
og
2
(
4
)
3.
1
.
5
.
G
ra
dient
b
o
o
s
t
ing
I
s
an
en
s
em
b
le
lear
n
in
g
tech
n
iq
u
e
th
at
in
teg
r
ates
th
e
p
r
ed
ic
tio
n
s
o
f
v
ar
io
u
s
b
ase
esti
m
ato
r
s
,
u
s
u
ally
DT
-
b
ased
,
to
i
n
cr
ea
s
e
m
o
d
el
ac
cu
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
[
4
4
]
.
I
n
m
o
d
elin
g
,
th
e
wo
r
d
‘
g
r
a
d
ien
t
’
r
ef
er
s
to
th
e
im
p
lem
en
tatio
n
o
f
a
g
r
ad
ien
t
d
escen
t
alg
o
r
ith
m
to
m
in
im
i
ze
lo
s
s
es
wh
en
in
teg
r
atin
g
n
ew
m
o
d
els
in
to
an
en
s
em
b
le
[
4
5
]
.
L
ik
ewise,
th
e
ter
m
‘
b
o
o
s
tin
g
’
is
u
s
ed
to
d
e
s
cr
ib
e
th
e
p
r
o
g
r
ess
iv
e
in
clu
s
io
n
o
f
m
o
d
els
in
an
en
s
em
b
le,
with
th
e
p
ar
ticu
la
r
ity
th
at
ea
ch
n
ew
m
o
d
el
h
as
th
e
f
u
n
ctio
n
o
f
co
r
r
ec
tin
g
th
e
er
r
o
r
s
o
f
its
p
r
ed
ec
ess
o
r
s
[
4
6
]
.
As
a
r
esu
lt,
a
p
o
wer
f
u
l
p
r
ed
ictiv
e
m
o
d
el
is
o
b
tain
ed
th
at
ca
n
id
en
tify
c
o
m
p
lex
p
atter
n
s
in
th
e
d
ata
an
d
h
as
a
lo
wer
te
n
d
en
cy
to
o
v
er
f
it
[
4
7
]
.
T
h
e
m
o
d
el
eq
u
atio
n
ca
n
b
e
ex
p
r
ess
ed
in
(
5
)
.
W
h
er
e
f(
x
)
r
ep
r
esen
ts
th
e
p
r
e
d
ictio
n
f
u
n
ct
io
n
,
h
(
x
)
co
r
r
esp
o
n
d
s
to
th
e
p
r
ed
ictio
n
o
f
th
e
i
-
th
least
r
o
b
u
s
t
m
o
d
el,
̂
d
en
o
tes
th
e
f
in
al
m
o
d
el
ac
cu
r
ac
y
,
an
d
γ
is
th
e
lear
n
in
g
c
o
ef
f
icien
t.
̂
=
(
)
=
∑
∗
ℎ
(
)
(
5
)
3.
2
.
Ca
s
e
s
t
ud
y
3.
2
.
1
.
Understa
nd
ing
t
he
da
t
a
s
et
A
d
ataset
ex
tr
ac
ted
f
r
o
m
th
e
UC
I
ML
r
ep
o
s
ito
r
y
was
u
s
ed
f
o
r
th
e
ML
m
o
d
el
tr
ain
i
n
g
p
r
o
ce
s
s
.
T
h
is
d
ataset
co
n
tain
s
lab
o
r
ato
r
y
v
a
lu
es
o
f
b
lo
o
d
d
o
n
o
r
s
,
p
atien
ts
with
h
ep
atitis
C
,
an
d
d
em
o
g
r
ap
h
ic
v
alu
es.
I
t
h
as
6
1
5
r
ec
o
r
d
s
an
d
1
4
attr
i
b
u
te
s
,
wh
er
e
all
ar
e
n
u
m
e
r
ical,
ex
ce
p
t
ca
teg
o
r
y
an
d
s
ex
.
T
h
e
attr
ib
u
tes
ar
e
th
e
f
o
llo
win
g
:
“
X
”
(
p
atien
t
id
)
,
“
C
ateg
o
r
y
”
wh
ich
r
e
f
er
s
to
th
e
d
iag
n
o
s
is
(
v
alu
es:
‘
0
=Blo
o
d
d
o
n
o
r
’
,
‘
0
s
=su
s
p
ec
ted
b
lo
o
d
d
o
n
o
r
’
,
‘
1
=H
ep
atitis
’
,
‘
2
=Fib
r
o
s
is
’
,
‘
3
=Cirr
h
o
s
is
’
)
,
“
Ag
e
”
(
in
y
ea
r
s
)
,
“
Sex
”
(
h
,
m
)
an
d
th
e
lab
o
r
ato
r
y
attr
ib
u
tes:
“
A
L
B
”
(
alb
u
m
in
b
lo
o
d
test
)
,
“
AL
P
”
(
Alk
alin
e
Ph
o
s
p
h
atase
)
,
“
AL
T
”
(
Alan
in
e
T
r
an
s
am
in
ase)
,
“
AST
”
(
As
p
ar
tate
T
r
an
s
am
in
ase)
,
“
B
I
L
”
(
B
iliru
b
in
)
,
“
C
HE
”
(
A
ce
ty
lch
o
lin
ester
ase)
,
“
C
HOL
”
(
C
h
o
lest
er
o
l)
,
“
C
R
E
A
”
(
C
r
ea
tin
in
e)
,
“
GGT
”
(
G
am
m
a
-
Glu
tam
y
l
T
r
an
s
f
er
ase)
,
“
PR
OT
”
(
Pro
tein
)
.
T
h
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
o
f
t
h
e
s
tu
d
y
is
d
etailed
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
C
ase
s
tu
d
y
d
e
v
elo
p
m
en
t p
r
o
ce
s
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
374
-
3
8
6
378
3.
2
.
2
.
Da
t
a
prepa
ra
t
io
n
B
ef
o
r
e
th
e
ex
p
l
o
r
ato
r
y
an
aly
s
i
s
o
f
th
e
d
ata,
we
p
er
f
o
r
m
ed
a
g
en
er
al
an
aly
s
is
o
f
t
h
e
ch
ar
ac
t
er
is
tics
o
f
th
e
attr
ib
u
tes
co
n
tain
ed
in
ea
ch
v
ar
iab
le.
Af
ter
lo
ad
i
n
g
th
e
d
ata
s
et,
we
n
o
ticed
th
e
ex
is
ten
ce
o
f
a
co
lu
m
n
ca
lled
“
Un
n
am
ed
: 0
”
,
wh
ich
we
p
r
o
ce
ed
e
d
to
el
im
in
ate.
Af
ter
th
is
,
we
v
er
if
ied
t
h
e
ty
p
e
o
f
d
ata
s
to
r
ed
i
n
ea
ch
co
lu
m
n
o
f
th
e
d
ataset,
we
n
o
ti
ce
d
th
at
th
e
co
lu
m
n
s
“
ca
teg
o
r
y
”
an
d
“
ag
e
”
ar
e
o
f
t
y
p
e
o
b
jec
t,
s
o
we
p
r
o
ce
ed
ed
to
tr
an
s
f
o
r
m
th
e
m
to
ty
p
e
i
n
t to
en
s
u
r
e
a
b
etter
p
r
o
ce
s
s
in
g
o
f
th
e
d
ata
b
y
th
e
m
o
d
e
ls
,
th
e
r
e
s
u
lts
ca
n
b
e
s
ee
n
in
T
ab
le
1
.
L
ik
ewise,
we
v
er
if
ied
th
e
u
n
iq
u
e
v
alu
es a
n
d
th
e
ex
i
s
ten
ce
o
f
m
is
s
in
g
v
alu
es,
id
en
t
if
y
in
g
th
e
co
lu
m
n
s
“
AL
P
”
,
“
AL
T
”
,
an
d
“
PR
OT
”
with
m
is
s
in
g
elem
e
n
ts
an
d
p
r
o
ce
ed
ed
to
f
ill
th
ese
v
alu
es.
T
a
b
le
2
s
h
o
ws
th
e
f
in
al
r
esu
lt o
f
th
e
d
ata
s
et.
T
ab
le
1
.
Data
t
y
p
es
A
t
t
r
i
b
u
t
e
Ty
p
e
C
a
t
e
g
o
r
y
i
n
t
6
4
A
g
e
i
n
t
6
4
S
e
x
i
n
t
6
4
A
LB
f
l
o
a
t
6
4
A
LP
f
l
o
a
t
6
4
A
LT
f
l
o
a
t
6
4
A
S
T
f
l
o
a
t
6
4
B
I
L
f
l
o
a
t
6
4
C
H
E
f
l
o
a
t
6
4
C
H
O
L
f
l
o
a
t
6
4
C
R
EA
f
l
o
a
t
6
4
GGT
f
l
o
a
t
6
4
P
R
O
T
f
l
o
a
t
6
4
d
t
y
p
e
:
o
b
j
e
c
t
T
ab
le
2
.
C
o
n
ten
t t
h
e
d
ata
s
et
C
a
t
e
g
o
r
y
A
g
e
S
e
x
A
LB
A
LP
A
LT
A
S
T
B
I
L
C
H
E
C
H
O
L
C
R
EA
GGT
P
R
O
T
0
0
32
0
3
8
.
5
5
2
.
5
7
.
7
2
2
.
1
7
.
5
6
.
9
3
3
.
2
3
1
0
6
1
2
.
1
69
1
0
32
0
3
8
.
5
7
0
.
3
18
2
4
.
7
3
.
9
1
1
.
1
7
4
.
8
74
1
5
.
6
7
6
.
5
2
0
32
0
4
6
.
9
7
4
.
7
3
6
.
2
5
2
.
6
6
.
1
8
.
8
4
5
.
2
86
3
3
.
2
7
9
.
3
3
0
32
0
4
3
.
2
52
3
0
.
6
2
2
.
6
1
8
.
9
7
.
3
3
4
.
7
4
80
3
3
.
8
7
5
.
7
...
...
...
...
...
...
...
...
...
...
...
...
...
...
6
1
1
1
64
1
24
1
0
2
.
8
2
.
9
4
4
.
4
20
1
.
5
4
3
.
0
2
63
3
5
.
9
7
1
.
3
6
1
2
1
64
1
29
8
7
.
3
3
.
5
99
48
1
.
6
6
3
.
6
3
6
6
.
7
6
4
.
2
82
6
1
3
1
46
1
33
6
8
.
2
8
3
9
2
39
62
20
3
.
5
6
4
.
2
52
50
71
6
1
4
1
59
1
36
6
8
.
2
8
3
9
2
1
0
0
80
12
9
.
0
7
5
.
3
67
34
68
3.
2
.
3
.
E
x
plo
ra
t
o
ry
a
na
ly
s
is
o
f
t
he
da
t
a
I
n
Fig
u
r
e
2
,
an
ex
h
au
s
tiv
e
an
aly
s
is
o
f
th
e
tar
g
et
v
ar
iab
le
“
C
ateg
o
r
y
”
was
ca
r
r
ied
o
u
t.
T
h
e
r
esu
lts
r
ev
ea
l
th
at
a
p
p
r
o
x
im
ately
7
0
%
o
f
th
e
p
atien
ts
s
h
o
w
s
ig
n
s
o
f
h
ep
atitis
C
,
wh
ile
th
e
r
em
ain
in
g
3
0
%
s
h
o
w
a
h
ea
lth
s
tatu
s
co
n
s
id
er
ed
n
o
r
m
al.
T
h
is
f
in
d
in
g
s
u
g
g
ests
a
s
ig
n
if
ican
t
p
r
ev
alen
ce
o
f
h
ep
ati
tis
C
in
th
e
s
tu
d
ied
p
o
p
u
latio
n
a
n
d
a
s
ig
n
if
ican
t i
m
b
alan
ce
th
at
will h
av
e
t
o
b
e
t
ak
en
in
to
ac
c
o
u
n
t w
h
en
tr
ain
i
n
g
ML
m
o
d
els.
Fig
u
r
e
2
.
T
a
r
g
et
v
a
r
iab
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
S
ee
kin
g
b
est p
erfo
r
ma
n
ce
:
a
c
o
mp
a
r
a
tive
ev
a
lu
a
tio
n
o
f m
a
c
h
in
e
…
(
Mich
a
el
C
a
b
a
n
illa
s
-
C
a
r
b
o
n
ell
)
379
On
th
e
o
th
er
h
an
d
,
wh
en
p
er
f
o
r
m
in
g
a
u
n
iv
ar
iate
an
aly
s
is
o
f
th
e
p
atien
t
d
ata,
a
s
ig
n
if
ican
t
d
is
p
ar
ity
in
ter
m
s
o
f
g
en
d
er
was
o
b
s
er
v
ed
.
I
n
Fig
u
r
e
3
,
t
h
e
r
esu
lts
r
ev
ea
l th
at
6
1
.
3
0
% o
f
th
e
in
d
iv
i
d
u
als ar
e
m
ale,
wh
ile
3
8
.
7
0
%
co
r
r
esp
o
n
d
to
th
e
f
em
ale
s
ex
in
th
e
d
ata
s
et.
T
h
is
f
in
d
in
g
h
ig
h
lig
h
ts
a
m
ar
k
ed
p
r
ed
o
m
in
an
ce
o
f
m
ales
in
th
e
s
am
p
le,
wh
ich
c
o
u
ld
h
a
v
e
im
p
o
r
ta
n
t im
p
licatio
n
s
wh
e
n
tr
ain
in
g
t
h
e
m
o
d
els.
Fig
u
r
e
3
.
Sex
o
f
p
atie
n
ts
s
tu
d
ied
Fig
u
r
e
4
s
h
o
ws
th
e
ag
e
d
is
tr
ib
u
tio
n
o
f
th
e
p
atien
ts
in
clu
d
ed
in
th
e
d
ata
s
et.
T
h
e
r
e
is
a
n
o
tab
le
co
n
ce
n
tr
atio
n
o
f
in
d
iv
id
u
als
i
n
th
e
a
g
e
r
an
g
e
b
etwe
en
4
0
an
d
6
0
y
ea
r
s
,
with
a
s
ig
n
if
ican
t
p
r
esen
ce
o
f
p
atien
ts
ag
ed
5
0
y
ea
r
s
.
On
th
e
o
th
er
h
an
d
,
t
h
er
e
is
a
s
m
aller
p
r
esen
ce
o
f
p
atien
ts
in
th
e
1
0
t
o
3
0
a
g
e
r
an
g
e,
as
well
as
in
th
o
s
e
o
v
er
6
0
y
ea
r
s
o
f
ag
e
.
T
h
is
d
is
p
ar
ity
in
ag
e
d
is
tr
ib
u
t
io
n
u
n
d
er
s
co
r
es
th
e
im
p
o
r
ta
n
c
e
o
f
an
aly
zin
g
a
n
d
u
n
d
er
s
tan
d
i
n
g
th
e
d
em
o
g
r
ap
h
i
c
ch
ar
ac
ter
is
tics
o
f
th
e
p
o
p
u
lat
io
n
u
n
d
er
in
v
esti
g
atio
n
.
Fig
u
r
e
4
.
Gen
e
r
al
d
is
tr
ib
u
tio
n
b
y
a
ge
L
ik
ewise,
in
Fig
u
r
e
5
,
a
c
o
m
p
ar
is
o
n
was
m
a
d
e
b
etwe
en
t
h
e
ag
e
o
f
th
e
p
atien
ts
an
d
th
eir
h
ep
atic
s
tatu
s
.
I
t
is
o
b
s
er
v
e
d
t
h
at
th
o
s
e
in
th
e
ag
e
r
an
g
e
o
f
2
0
to
4
0
y
ea
r
s
p
r
esen
t
a
h
ig
h
e
r
p
r
o
p
en
s
ity
to
d
ev
elo
p
h
ep
atitis
s
in
ce
th
er
e
is
a
s
ig
n
i
f
ican
tly
h
i
g
h
er
co
n
ce
n
tr
atio
n
o
f
ca
s
es
i
n
th
is
in
ter
v
al
in
th
e
d
ata
s
et
a
n
aly
ze
d
.
I
n
ad
d
itio
n
,
it
is
h
ig
h
lig
h
ted
t
h
at
p
atien
ts
wh
o
r
ea
ch
5
0
y
ea
r
s
o
f
ag
e
s
h
o
w
a
h
ig
h
e
r
p
r
o
b
a
b
ilit
y
o
f
d
ev
elo
p
in
g
f
ib
r
o
s
is
in
th
e
f
u
tu
r
e.
I
n
a
s
im
ilar
co
n
tex
t,
p
atien
ts
r
ea
ch
i
n
g
6
0
y
ea
r
s
o
f
a
g
e
s
h
o
w
a
h
ig
h
er
p
r
o
b
a
b
il
ity
o
f
d
ev
elo
p
in
g
cir
r
h
o
s
is
,
wh
ile
th
o
s
e
b
etwe
en
4
0
an
d
5
0
y
e
ar
s
o
f
ag
e
also
ex
h
ib
it
a
ce
r
tain
p
r
ed
is
p
o
s
itio
n
,
alth
o
u
g
h
with
a
s
o
m
ewh
at
lo
wer
p
r
o
b
ab
ilit
y
.
Ho
wev
er
,
it
i
s
im
p
o
r
tan
t
to
n
o
te
th
at
th
e
r
e
i
s
a
g
r
o
u
p
o
f
p
atien
ts
in
g
o
o
d
h
ea
lth
i
n
th
e
3
0
-
4
5
ag
e
r
a
n
g
e.
Acc
o
r
d
in
g
to
Fig
u
r
e
6
,
th
er
e
is
ev
id
en
ce
o
f
a
g
r
ea
ter
p
r
o
p
en
s
ity
o
f
m
en
to
d
ev
el
o
p
li
v
er
d
is
ea
s
e
co
m
p
ar
ed
t
o
wo
m
en
.
W
h
en
e
x
am
in
in
g
Fig
u
r
e
6
(
a)
,
it
s
tan
d
s
o
u
t
th
at
5
.
3
%
o
f
m
ale
p
atien
ts
p
r
esen
t
h
ep
atitis
,
a
f
ig
u
r
e
th
at
is
eq
u
ally
s
ig
n
if
i
ca
n
t
in
t
h
e
ca
s
e
o
f
ci
r
r
h
o
s
is
,
with
a
p
e
r
ce
n
tag
e
o
f
5
.
3
%,
a
n
d
3
.
4
%
in
f
ib
r
o
s
is
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
374
-
3
8
6
380
I
n
co
n
tr
ast,
in
t
h
e
f
em
ale
g
r
o
u
p
,
a
lo
wer
in
cid
e
n
ce
is
o
b
s
er
v
ed
,
with
o
n
ly
1
.
7
%
af
f
ec
te
d
b
y
h
ep
atitis
,
4
.
2
%
b
y
cir
r
h
o
s
is
,
an
d
3
.
4
%
b
y
f
ib
r
o
s
is
as
s
h
o
wn
in
Fig
ur
e
6
(
b
)
.
T
h
ese
f
in
d
in
g
s
u
n
d
e
r
s
c
o
r
e
t
h
e
d
is
p
ar
ity
in
t
h
e
p
r
ev
alen
ce
o
f
liv
e
r
d
is
ea
s
e
b
etwe
en
m
en
an
d
wo
m
en
,
s
u
g
g
esti
n
g
a
g
r
ea
ter
v
u
ln
er
ab
ilit
y
o
f
m
en
to
d
ev
elo
p
th
ese
ty
p
es o
f
co
n
d
itio
n
s
.
Fig
u
r
e
5
.
Dis
tr
ib
u
tio
n
b
y
a
g
e
a
n
d
liv
er
s
tatu
s
(
a)
(
b
)
Fig
u
r
e
6
.
Dis
tr
ib
u
tio
n
b
y
s
ex
a
n
d
liv
er
s
tatu
s
:
(
a)
m
ales a
n
d
l
iv
er
s
tatu
s
an
d
(
b
)
wo
m
en
an
d
liv
er
s
tatu
s
L
ik
ewise,
ac
co
r
d
in
g
to
Fig
u
r
e
7,
Fig
u
r
e
7
(
a)
a
g
r
o
u
p
o
f
5
3
3
in
d
iv
id
u
als
with
a
h
ea
lth
y
liv
er
was
id
en
tifie
d
.
Ho
wev
er
,
it
is
im
p
o
r
tan
t
to
h
ig
h
lig
h
t
th
e
p
r
esen
c
e
o
f
2
4
p
atien
ts
d
iag
n
o
s
ed
wit
h
h
ep
atitis
,
2
1
with
h
ep
atic
f
ib
r
o
s
is
an
d
3
0
with
cir
r
h
o
s
is
.
T
h
ese
liv
er
h
ea
l
th
co
n
d
itio
n
s
d
em
a
n
d
s
p
ec
if
ic
atten
tio
n
a
n
d
a
co
m
p
r
eh
e
n
s
iv
e
ap
p
r
o
ac
h
to
e
n
s
u
r
e
th
e
well
-
b
ein
g
o
f
th
o
s
e
af
f
ec
ted
.
I
n
th
e
ca
s
e
o
f
h
e
p
atitis
,
Fig
u
r
e
7
(
b
)
,
it
is
r
ec
o
m
m
en
d
ed
th
at
p
atien
ts
r
ec
eiv
e
co
n
s
tan
t
m
ed
ical
f
o
llo
w
-
u
p
,
in
clu
d
in
g
lab
o
r
ato
r
y
test
s
to
ass
e
s
s
liv
er
f
u
n
ctio
n
an
d
d
eter
m
in
e
th
e
e
f
f
ec
tiv
en
ess
o
f
tr
ea
tm
e
n
t.
He
p
atic
f
ib
r
o
s
is
,
Fig
u
r
e
7
(
c)
,
ch
ar
ac
ter
ized
b
y
s
ca
r
tis
s
u
e
f
o
r
m
atio
n
in
th
e
liv
e
r
,
r
eq
u
ir
es
r
eg
u
lar
m
o
n
ito
r
in
g
to
ass
es
s
d
is
ea
s
e
p
r
o
g
r
ess
io
n
.
Pa
tien
ts
ar
e
ad
v
is
ed
to
tak
e
m
ea
s
u
r
es
to
m
itig
ate
r
i
s
k
f
ac
to
r
s
,
s
u
ch
as
m
an
ag
e
m
en
t
o
f
c
o
n
cu
r
r
en
t
d
is
ea
s
es
an
d
av
o
id
an
ce
o
f
h
ep
ato
to
x
ic
s
u
b
s
tan
ce
s
.
I
n
th
e
ca
s
e
o
f
cir
r
h
o
s
is
,
Fig
u
r
e
7
(
d
)
,
a
m
o
r
e
ad
v
a
n
ce
d
an
d
s
ev
er
e
co
n
d
itio
n
,
it
is
cr
itical
to
im
p
lem
e
n
t
s
tr
at
eg
ies
to
m
a
n
ag
e
ass
o
ciate
d
co
m
p
licatio
n
s
,
s
u
ch
as
ascites
o
r
h
ep
atic
en
ce
p
h
alo
p
ath
y
.
Patien
ts
with
cir
r
h
o
s
is
s
h
o
u
ld
s
tr
ictly
f
o
llo
w
m
ed
ical
in
d
icatio
n
s
,
in
clu
d
in
g
d
ietar
y
s
o
d
iu
m
r
estrictio
n
an
d
co
n
s
tan
t m
o
n
it
o
r
in
g
o
f
liv
er
f
u
n
ctio
n
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
7
.
L
i
v
er
s
tatu
s
;
(
a)
h
ea
l
th
y
liv
er
,
(
b
)
l
iv
e
r
with
h
ep
atit
is
,
(
c)
l
iv
er
with
f
ib
r
o
s
is
,
an
d
(
d
)
l
iv
er
with
ci
r
r
h
o
s
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
S
ee
kin
g
b
est p
erfo
r
ma
n
ce
:
a
c
o
mp
a
r
a
tive
ev
a
lu
a
tio
n
o
f m
a
c
h
in
e
…
(
Mich
a
el
C
a
b
a
n
illa
s
-
C
a
r
b
o
n
ell
)
381
Fig
u
r
e
8
is
t
ar
g
et
v
ar
iab
le
an
d
b
lo
o
d
test
s
.
Fig
u
r
e
8
(
a)
clea
r
l
y
s
h
o
ws
th
at
th
er
e
is
a
d
ir
ec
t
c
o
r
r
elatio
n
b
etwe
en
th
e
d
ec
r
ea
s
e
i
n
th
e
a
m
o
u
n
t
o
f
ch
o
lin
ester
ase
in
th
e
b
lo
o
d
o
f
p
atien
ts
an
d
a
s
ig
n
if
i
ca
n
t
in
cr
ea
s
e
i
n
th
e
p
r
o
b
a
b
ilit
y
o
f
co
n
tr
ac
tin
g
h
e
p
atitis
.
T
h
is
is
m
o
s
t
p
r
o
m
in
en
tly
m
an
if
ested
at
th
e
7
a
n
d
9
g
/d
L
le
v
els
o
f
ch
o
lin
ester
ase
in
th
e
b
lo
o
d
,
wh
er
e
th
er
e
is
a
n
o
tab
le
co
n
ce
n
tr
atio
n
o
f
co
n
f
ir
m
e
d
ca
s
es.
I
t
is
im
p
o
r
tan
t
to
hi
g
h
lig
h
t
th
at,
i
n
g
en
e
r
al
ter
m
s
,
a
m
ea
n
o
f
7
.
5
g
/d
L
o
f
b
l
o
o
d
ch
o
lin
ester
ase
is
ev
id
en
t
in
th
ese
ca
s
es.
T
h
is
f
in
d
in
g
r
ein
f
o
r
ce
s
th
e
ass
o
ciatio
n
b
etwe
en
th
e
l
o
w
p
r
esen
ce
o
f
ch
o
lin
ester
ase
an
d
a
p
r
ed
is
p
o
s
itio
n
to
co
n
tr
ac
t
h
ep
atitis
,
h
ig
h
lig
h
tin
g
th
e
r
ele
v
an
ce
o
f
m
o
n
ito
r
in
g
an
d
ad
d
r
ess
in
g
th
e
lev
els
o
f
th
is
en
zy
m
e
as a
cr
u
cial
f
ac
to
r
in
th
e
p
r
ev
e
n
tio
n
an
d
d
ia
g
n
o
s
i
s
o
f
th
e
d
is
ea
s
e.
L
ik
ewise,
i
n
Fig
u
r
e
8
(
b
)
,
we
n
o
te
a
r
elatio
n
s
h
ip
b
etwe
en
b
lo
o
d
ch
o
lest
er
o
l
lev
els
an
d
th
e
p
r
o
b
ab
ilit
y
o
f
co
n
tr
ac
tin
g
h
ep
a
titi
s
.
T
h
is
p
atter
n
r
ev
ea
ls
th
a
t
as
th
e
am
o
u
n
t
o
f
ch
o
lest
er
o
l
in
th
e
b
lo
o
d
d
ec
r
ea
s
es,
th
e
p
r
o
b
ab
ilit
y
o
f
co
n
t
r
ac
tin
g
th
is
d
is
ea
s
e
in
cr
ea
s
es.
I
t
is
p
ar
ticu
lar
ly
n
o
tewo
r
th
y
th
at
a
s
ig
n
if
ican
tl
y
h
ig
h
er
co
n
ce
n
tr
atio
n
o
f
ca
s
es
in
th
e
3
t
o
5
g
/
d
L
b
lo
o
d
ch
o
lest
er
o
l
r
an
g
e
was
id
en
tifie
d
.
Mo
r
e
s
p
ec
if
ically
,
th
e
m
ea
n
ch
o
lest
er
o
l
in
t
h
is
r
an
g
e
is
o
b
s
er
v
ed
t
o
b
e
4
.
5
g
/
d
L
.
T
h
ese
f
in
d
i
n
g
s
u
n
d
er
lin
e
t
h
e
im
p
o
r
tan
ce
o
f
co
n
s
id
er
in
g
ch
o
lest
er
o
l le
v
els as a
r
elev
an
t f
ac
to
r
in
th
e
in
cid
en
ce
o
f
h
e
p
atitis
.
(
a)
(
b
)
Fig
u
r
e
8
.
T
a
r
g
et
v
a
r
iab
le
an
d
b
lo
o
d
test
s
;
(
a)
tar
g
et
v
ar
iab
le
an
d
am
o
u
n
t o
f
ch
o
lin
ester
ase
i
n
th
e
b
lo
o
d
a
n
d
(
b
)
tar
g
et
v
ar
i
ab
le
a
n
d
am
o
u
n
t
o
f
ch
o
lest
er
o
l in
th
e
b
l
o
o
d
I
n
Fig
u
r
e
9
,
th
e
im
p
ac
t
o
f
t
wo
ad
d
itio
n
al
ch
ar
ac
ter
is
tics
o
f
lab
o
r
ato
r
y
d
ata
o
n
p
atie
n
t
h
ea
lth
i
s
ex
am
in
ed
.
I
n
Fig
u
r
e
9
(
a)
,
we
co
n
tr
ast
liv
er
s
tatu
s
with
p
atie
n
ts
’
ag
e
an
d
b
lo
o
d
ch
o
lin
ester
ase
co
n
ce
n
tr
atio
n
.
W
e
o
b
s
er
v
e
th
at
as
a
g
e
in
c
r
ea
s
es
an
d
th
e
am
o
u
n
t
o
f
ch
o
lin
e
s
ter
ase
in
th
e
b
lo
o
d
d
ec
r
ea
s
es,
th
e
lik
elih
o
o
d
o
f
d
ev
elo
p
in
g
cir
r
h
o
s
is
in
cr
ea
s
es
s
ig
n
if
ican
tly
.
C
o
n
v
er
s
ely
,
w
h
en
th
e
p
r
esen
ce
o
f
c
h
o
lin
ester
ase
is
h
ig
h
er
b
u
t
th
e
p
atien
t
’
s
ag
e
is
lo
wer
,
th
e
ch
an
ce
s
o
f
co
n
tr
ac
tin
g
h
ep
atitis
in
cr
ea
s
e
s
ig
n
if
ican
tly
.
L
ik
ewise,
f
o
r
ag
es
b
etwe
en
2
0
an
d
7
0
y
ea
r
s
,
an
d
with
an
av
er
ag
e
ch
o
lin
ester
ase
lev
el
o
f
1
0
,
th
e
o
d
d
s
o
f
f
ib
r
o
s
is
in
cr
ea
s
e.
I
n
Fig
u
r
e
9
(
b
)
,
it is
h
ig
h
lig
h
te
d
th
at
wh
en
th
e
am
o
u
n
t o
f
alb
u
m
in
in
th
e
b
lo
o
d
r
an
g
es b
etwe
en
4
0
a
n
d
5
0
g
/d
L
,
an
d
th
e
a
m
o
u
n
t
o
f
alk
alin
e
p
h
o
s
p
h
atase
in
th
e
b
lo
o
d
is
lo
w,
th
e
p
r
o
b
ab
ilit
ies
o
f
h
ep
atitis
ar
e
h
ig
h
e
r
,
s
h
o
win
g
a
b
eh
av
io
r
s
im
ilar
to
th
at
o
f
f
ib
r
o
s
is
.
On
th
e
o
th
er
h
an
d
,
wh
en
th
e
b
lo
o
d
alb
u
m
in
co
n
ce
n
tr
atio
n
is
lo
wer
,
th
e
o
d
d
s
o
f
cir
r
h
o
s
is
ar
e
h
ig
h
er
,
r
eg
a
r
d
less
o
f
th
e
am
o
u
n
t
o
f
alk
alin
e
p
h
o
s
p
h
atase
in
th
e
b
lo
o
d
.
As
f
o
r
Fig
u
r
e
9
(
c)
,
it
is
o
b
s
er
v
ed
th
at
th
e
lo
wer
th
e
alan
in
e
tr
an
s
am
in
ase
co
n
ce
n
tr
atio
n
a
n
d
th
e
lo
wer
th
e
am
o
u
n
t
o
f
asp
ar
tate
am
in
o
tr
an
s
f
er
ase
i
n
th
e
p
atien
t
’
s
b
lo
o
d
,
th
e
g
r
ea
ter
th
e
lik
elih
o
o
d
o
f
d
e
v
elo
p
in
g
cir
r
h
o
s
is
.
T
h
is
p
atter
n
is
s
im
i
lar
ly
r
ep
ea
ted
in
ca
s
es
o
f
h
ep
atitis
a
n
d
f
ib
r
o
s
is
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
a
co
m
p
lex
r
elatio
n
s
h
ip
b
etwe
en
th
e
v
a
r
iab
les
an
aly
ze
d
a
n
d
liv
e
r
h
ea
lth
,
h
ig
h
lig
h
tin
g
t
h
e
im
p
o
r
ta
n
ce
o
f
co
n
s
id
er
in
g
m
u
ltip
le
f
ac
to
r
s
to
u
n
d
er
s
tan
d
an
d
p
r
e
v
en
t liv
er
d
is
ea
s
e.
(
a)
(
b
)
(
c)
Fig
u
r
e
9
.
Ho
w
liv
e
r
h
ea
lth
is
a
f
f
ec
ted
b
y
two
ch
ar
ac
te
r
is
tics
:
(
a)
ag
e
a
n
d
ac
ety
lch
o
lin
ester
ase
;
(
b
)
b
lo
o
d
alb
u
m
in
an
d
alk
alin
e
p
h
o
s
p
h
at
ase
;
an
d
(
c)
alan
in
e
tr
an
s
am
in
ase
an
d
asp
ar
tate
tr
an
s
am
in
ase
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
374
-
3
8
6
382
3.
2
.
4
.
Da
t
a
prec
ess
ing
A
f
ter
co
m
p
letin
g
th
e
d
ata
an
al
y
s
is
,
we
d
iv
id
ed
th
e
d
ata
s
et
i
n
to
two
d
is
tin
ct
g
r
o
u
p
s
.
O
n
e
p
o
r
tio
n
was
ass
ig
n
ed
f
o
r
m
o
d
el
e
v
alu
atio
n
,
wh
ile
th
e
o
th
e
r
p
o
r
tio
n
was
f
o
r
m
o
d
el
tr
ain
in
g
.
Af
ter
s
p
litt
in
g
th
e
d
ata
s
et,
we
p
r
o
ce
ed
e
d
to
s
ca
le
th
e
d
ata
a
n
d
tr
ai
n
th
e
c
o
r
r
esp
o
n
d
in
g
m
o
d
els.
T
h
is
p
r
o
ce
s
s
en
s
u
r
es
a
d
eq
u
ate
p
er
f
o
r
m
an
ce
ev
alu
atio
n
an
d
ef
f
ec
tiv
e
tr
ain
in
g
o
f
th
e
m
o
d
els,
th
u
s
co
n
tr
ib
u
tin
g
to
t
h
e
r
o
b
u
s
tn
ess
an
d
ef
f
icien
cy
o
f
th
e
r
esu
lts
.
T
h
e
im
p
o
r
tan
ce
o
f
th
e
clin
ical
h
is
to
r
y
as
a
f
u
n
d
am
en
tal
v
ar
iab
le
an
d
t
h
e
tech
n
o
l
o
g
ical
in
ter
v
en
tio
n
in
tr
in
s
ic
to
th
e
m
o
d
elin
g
p
r
o
c
ess
m
ad
e
r
an
d
o
m
izatio
n
im
p
r
ac
tical.
R
eg
ar
d
in
g
b
lin
d
in
g
,
w
e
b
ec
am
e
awa
r
e
o
f
th
e
in
ter
n
al
co
m
p
lex
ity
o
f
ML
m
o
d
els,
s
o
we
ch
o
s
e
to
f
o
cu
s
o
n
tr
an
s
p
ar
en
cy
an
d
r
ep
r
o
d
u
cib
ilit
y
th
r
o
u
g
h
d
etailed
d
is
clo
s
u
r
e
o
f
th
e
m
o
d
el
ar
ch
itectu
r
e,
h
y
p
e
r
p
ar
am
eter
s
,
an
d
e
v
alu
atio
n
m
eth
o
d
s
.
T
h
ese
m
eth
o
d
o
l
o
g
ical
ch
o
ices
wer
e
b
ased
o
n
th
e
n
ee
d
to
ad
d
r
ess
t
h
e
s
p
ec
if
ic
lim
itatio
n
s
o
f
th
e
s
tu
d
y
,
with
t
h
e
aim
o
f
en
s
u
r
in
g
th
e
in
te
g
r
ity
an
d
e
th
ics o
f
th
e
r
esear
ch
.
4.
RE
SU
L
T
S
On
ce
th
e
an
aly
s
is
an
d
p
r
o
ce
s
s
in
g
o
f
th
e
d
ataset
wer
e
co
m
p
leted
,
we
p
r
o
ce
e
d
ed
to
tr
a
in
th
e
ML
m
o
d
els
f
o
cu
s
ed
o
n
h
ep
atitis
C
p
r
ed
ictio
n
.
T
h
e
L
R
,
DT
,
K
NN,
R
F
,
an
d
GB
m
o
d
els
wer
e
tr
ain
ed
,
t
o
id
en
tif
y
th
e
m
o
d
el
with
th
e
b
est
p
er
f
o
r
m
an
ce
in
p
r
ec
is
io
n
,
ac
c
u
r
a
cy
,
an
d
s
en
s
itiv
ity
wh
en
p
r
e
d
ictin
g
th
e
d
is
ea
s
e.
T
h
e
r
esu
lts
o
f
th
ese
tr
ain
in
g
s
ar
e
s
h
o
wn
in
T
a
b
le
3
.
T
h
e
L
R
,
R
F,
KNN,
DT
,
an
d
GB
m
o
d
els
ac
h
iev
ed
an
ac
c
u
r
ac
y
o
f
8
9
%,
9
3
%,
8
5
%,
9
5
%
an
d
9
4
%,
r
esp
ec
tiv
ely
.
L
ik
ewise,
in
t
h
e
ac
cu
r
ac
y
in
d
icato
r
,
th
e
m
o
d
els
r
eg
is
ter
ed
8
8
%,
9
4
%,
8
8
%,
8
8
%,
9
5
%
an
d
9
5
%,
r
esp
ec
tiv
ely
.
T
h
e
r
esu
lts
h
ig
h
l
ig
h
t
th
e
DT
m
o
d
el
as
t
h
e
m
o
s
t
ef
f
ec
tiv
e
p
r
ed
icto
r
f
o
r
h
ep
ati
tis
C
,
ac
h
iev
in
g
a
p
er
f
o
r
m
an
ce
o
f
9
5
%
in
ac
cu
r
a
cy
,
p
r
e
cisi
o
n
,
s
en
s
itiv
ity
,
an
d
F1
-
s
co
r
e.
I
t
is
clo
s
ely
f
o
llo
we
d
b
y
th
e
GB
m
o
d
el,
with
9
4
%
in
ac
cu
r
ac
y
,
9
5
%
i
n
p
r
ec
is
io
n
,
9
4
%
in
s
en
s
itiv
ity
,
an
d
9
4
%
in
F1
-
s
co
r
e.
I
n
th
ir
d
p
lace
is
th
e
R
F
m
o
d
el,
with
9
3
%
i
n
ac
cu
r
ac
y
,
9
4
%
in
p
r
ec
is
io
n
,
an
d
9
3
%
i
n
s
en
s
itiv
ity
an
d
F1
-
s
co
r
e.
De
s
p
ite
n
o
t
ac
h
ie
v
in
g
m
etr
ics
ab
o
v
e
9
0
%,
th
e
o
th
er
m
o
d
els
also
o
b
t
ain
e
d
s
ig
n
if
i
ca
n
t
r
esu
lts
.
T
h
e
KNN
m
o
d
e
l
ac
h
iev
ed
8
5
%
in
ac
cu
r
ac
y
a
n
d
s
en
s
itiv
ity
,
8
8
%
in
p
r
ec
is
io
n
,
an
d
8
2
%
i
n
F1
-
s
co
r
e.
O
n
th
e
o
th
er
h
a
n
d
,
th
e
L
R
m
o
d
el
d
em
o
n
s
tr
ated
s
o
lid
p
er
f
o
r
m
a
n
ce
with
8
9
%
ac
cu
r
ac
y
,
8
8
%
in
p
r
ec
is
io
n
,
8
9
%
in
s
en
s
itiv
ity
,
an
d
8
7
%
in
F1
-
s
co
r
e.
T
ab
le
3
.
Mo
d
el
tr
ain
in
g
r
esu
lts
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
1
-
sc
o
r
e
S
u
p
p
o
r
t
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
0
.
8
9
0
.
9
8
0
.
9
3
99
1
0
.
8
6
0
.
5
0
0
.
6
3
24
a
c
c
u
r
a
c
y
0
.
8
9
1
2
3
mac
r
o
a
v
g
0
.
8
7
0
.
7
4
0
.
7
8
1
2
3
w
e
i
g
h
t
e
d
a
v
g
0
.
8
8
0
.
8
9
0
.
8
7
1
2
3
R
a
n
d
o
m
f
o
r
e
s
t
0
0
.
9
3
0
.
9
9
0
.
9
6
99
1
0
.
9
4
0
.
7
1
0
.
8
1
24
a
c
c
u
r
a
c
y
0
.
9
3
1
2
3
mac
r
o
a
v
g
0
.
9
4
0
.
8
5
0
.
8
9
1
2
3
w
e
i
g
h
t
e
d
a
v
g
0
.
9
4
0
.
9
3
0
.
9
3
1
2
3
K
N
N
0
0
.
8
5
1
.
0
0
0
.
9
2
99
1
1
.
0
0
0
.
2
5
0
.
4
24
a
c
c
u
r
a
c
y
0
.
8
5
1
2
3
mac
r
o
a
v
g
0
.
9
2
0
.
6
2
0
.
6
6
1
2
3
w
e
i
g
h
t
e
d
a
v
g
0
.
8
8
0
.
8
5
0
.
8
2
D
e
c
i
s
i
o
n
t
r
e
e
0
0
.
9
5
0
.
9
9
0
.
9
7
99
1
0
.
9
5
0
.
7
9
0
.
8
6
24
a
c
c
u
r
a
c
y
0
.
9
5
1
2
3
mac
r
o
a
v
g
0
.
9
5
0
.
8
9
0
.
9
2
1
2
3
w
e
i
g
h
t
e
d
a
v
g
0
.
9
5
0
.
9
5
0
.
9
5
1
2
3
G
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
0
0
.
9
3
1
.
0
0
0
.
9
7
99
1
1
.
0
0
0
.
7
1
0
.
8
3
24
a
c
c
u
r
a
c
y
0
.
9
4
1
2
3
mac
r
o
a
v
g
0
.
9
7
0
.
8
5
0
.
9
0
1
2
3
w
e
i
g
h
t
e
d
a
v
g
0
.
9
5
0
.
9
4
0
.
9
4
1
2
3
5.
DIS
CU
SS
I
O
N
HC
V
is
a
d
is
ea
s
e
tr
an
s
m
itted
th
r
o
u
g
h
co
n
tact
with
co
n
tam
in
ated
b
lo
o
d
,
claim
in
g
m
illi
o
n
s
o
f
liv
es
an
n
u
ally
.
T
h
e
m
o
s
t
im
p
o
r
tan
t
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
in
d
ic
ate
th
at
ML
m
o
d
els
ca
n
b
e
ef
f
ec
tiv
e
to
o
ls
f
o
r
p
r
ed
ictin
g
h
e
p
atitis
C
.
T
h
e
L
R
,
DT
,
KNN,
R
F
,
an
d
G
B
m
o
d
els
wer
e
ev
alu
ated
.
T
h
is
ev
alu
atio
n
was
p
er
f
o
r
m
ed
u
s
in
g
p
er
f
o
r
m
an
ce
m
etr
ics
s
u
ch
as
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
s
en
s
itiv
ity
.
Acc
u
r
ac
y
m
ea
s
u
r
e
d
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
S
ee
kin
g
b
est p
erfo
r
ma
n
ce
:
a
c
o
mp
a
r
a
tive
ev
a
lu
a
tio
n
o
f m
a
c
h
in
e
…
(
Mich
a
el
C
a
b
a
n
illa
s
-
C
a
r
b
o
n
ell
)
383
p
er
ce
n
tag
e
o
f
co
r
r
ec
t
m
o
d
el
p
r
ed
ictio
n
s
o
v
er
to
tal
p
r
e
d
ictio
n
s
,
allo
win
g
u
s
to
ass
es
s
h
o
w
well
it
d
is
t
in
g
u
is
h
es
b
etwe
en
in
f
ec
ted
an
d
u
n
in
f
ec
ted
p
atien
ts
.
Acc
u
r
ac
y
in
d
icat
ed
th
e
r
eliab
ilit
y
o
f
th
e
p
o
s
itiv
e
p
r
ed
ictio
n
s
,
i.e
.
,
h
o
w
m
an
y
o
f
th
e
p
o
s
itiv
e
p
r
e
d
ictio
n
s
ar
e
ac
tu
ally
co
r
r
ec
t.
R
ec
all
m
ea
s
u
r
ed
th
e
p
r
o
p
o
r
ti
o
n
o
f
tr
u
e
p
o
s
itiv
es
co
r
r
ec
tly
i
d
en
tifie
d
b
y
t
h
e
m
o
d
el,
wh
ic
h
is
cr
u
cial
to
en
s
u
r
e
th
at
th
e
m
ajo
r
ity
o
f
h
e
p
atitis
C
ca
s
es
ar
e
d
etec
ted
,
m
in
im
izin
g
f
alse n
eg
ativ
es a
n
d
en
s
u
r
in
g
th
at
f
ew
in
f
ec
ted
p
eo
p
le
g
o
u
n
d
etec
te
d
.
T
h
e
b
e
n
ch
m
ar
k
in
g
p
r
o
ce
s
s
b
e
g
an
with
th
e
c
o
llectio
n
a
n
d
p
r
ep
ar
atio
n
o
f
th
e
d
ataset.
I
n
th
i
s
s
tu
d
y
,
a
d
ataset
with
6
1
5
r
ec
o
r
d
s
an
d
1
4
attr
ib
u
tes
was
u
s
ed
,
in
cl
u
d
in
g
p
atien
t
d
em
o
g
r
ap
h
ic
in
f
o
r
m
atio
n
an
d
th
e
r
esu
lts
o
f
clin
ical
ev
alu
atio
n
s
o
f
b
lo
o
d
an
d
liv
er
,
am
o
n
g
o
th
er
s
.
Su
b
s
eq
u
en
tly
,
th
e
L
R
,
DT
,
KNN,
R
F
an
d
G
B
m
o
d
els
wer
e
tr
ain
e
d
u
s
in
g
th
i
s
d
ataset.
T
h
e
tr
ain
in
g
in
v
o
lv
ed
ad
ju
s
tin
g
t
h
e
m
o
d
el
’
s
p
ar
a
m
eter
s
to
m
in
im
ize
er
r
o
r
in
th
e
p
r
e
d
ictio
n
s
.
Af
ter
tr
ain
in
g
,
ea
ch
m
o
d
el
was
ev
alu
ated
f
o
r
p
er
f
o
r
m
an
ce
u
s
in
g
a
test
d
atase
t,
ca
lcu
latin
g
th
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
s
en
s
itiv
ity
m
etr
ics
f
o
r
ea
ch
m
o
d
el
.
Su
b
s
eq
u
e
n
tly
,
th
e
r
esu
lts
wer
e
co
m
p
ar
ed
,
id
en
tify
i
n
g
th
e
o
n
e
with
th
e
b
est
p
er
f
o
r
m
a
n
ce
.
A
f
ter
tr
ain
in
g
,
th
e
m
o
d
els
ac
h
ie
v
ed
th
e
f
o
llo
win
g
r
esu
lts
in
ter
m
s
o
f
ac
cu
r
ac
y
:
L
R
(
8
9
%),
R
F
(
9
3
%),
KNN
(
8
5
%),
DT
(
9
5
%),
an
d
GB
(
9
4
%).
I
n
ter
m
s
o
f
ac
cu
r
ac
y
,
th
e
r
esu
l
ts
wer
e:
L
R
(
8
8
%),
R
F
(
9
4
%),
KNN
(
8
8
%),
DT
(
9
5
%),
a
n
d
GB
(
9
5
%)
.
Of
th
e
r
esu
lts
,
th
e
DT
m
o
d
el
s
h
o
wed
th
e
b
est
o
v
er
all
p
er
f
o
r
m
an
ce
with
9
5
%
in
th
e
m
etr
ics
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
s
en
s
itiv
ity
an
d
F1
-
s
co
r
e
.
T
h
ese
r
esu
lts
in
d
icate
th
at
th
e
DT
m
o
d
el
is
th
e
m
o
s
t
s
u
itab
le
f
o
r
p
r
e
d
ictin
g
h
e
p
atitis
C
co
m
p
ar
ed
to
th
e
o
th
er
m
o
d
el
s
ev
alu
ated
.
DT
’
s
h
ig
h
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
s
u
g
g
ests
th
at
it
ca
n
co
r
r
e
ctly
id
en
tify
b
o
th
in
f
ec
ted
an
d
u
n
i
n
f
ec
ted
p
atien
ts
,
wh
ich
is
c
r
u
cial
f
o
r
ea
r
ly
d
etec
tio
n
a
n
d
ef
f
ec
tiv
e
tr
ea
tm
en
t
o
f
th
e
d
is
ea
s
e.
T
h
is
r
esu
lt
is
co
n
s
is
ten
t
with
p
r
ev
io
u
s
s
tu
d
ies.
Fo
r
e
x
am
p
le
,
in
th
e
s
tu
d
y
f
r
o
m
Kar
ee
m
[
3
0
]
,
th
e
DT
m
o
d
el
ac
h
iev
ed
9
3
.
4
4
%
ac
c
u
r
ac
y
u
s
in
g
d
e
m
o
g
r
a
p
h
ic
d
ata
an
d
clin
ical
test
r
esu
lts
.
Ho
w
ev
er
,
in
th
at
s
tu
d
y
,
th
ey
d
if
f
er
e
d
in
d
ata
p
r
o
ce
s
s
in
g
an
d
o
p
t
im
izin
g
ML
m
o
d
el
s
.
Similar
ly
,
th
e
GB
m
o
d
el
in
o
u
r
s
tu
d
y
ac
h
ie
v
ed
9
4
%
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
a
n
d
F1
-
s
co
r
e
,
an
d
9
5
%
ac
cu
r
ac
y
,
co
m
p
ar
ed
to
th
e
s
tu
d
y
f
r
o
m
San
to
s
[
2
6
]
,
wh
er
e
th
e
m
o
d
el
ac
h
iev
e
d
9
3
.
5
0
%
ac
cu
r
ac
y
in
p
r
ed
ictin
g
Hep
atitis
C
.
On
e
o
f
th
e
co
in
cid
en
ce
s
with
th
is
s
tu
d
y
is
th
e
u
s
e
o
f
th
e
s
am
e
d
ataset,
b
u
t
d
i
f
f
er
en
tiatin
g
with
th
e
ap
p
licatio
n
o
f
5
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
.
On
th
e
o
th
er
h
a
n
d
,
th
e
R
F
m
o
d
el
h
ad
a
9
3
%
p
er
f
o
r
m
an
ce
in
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
an
d
F1
-
s
co
r
e
,
r
esu
lts
s
im
ilar
to
th
o
s
e
ac
h
iev
ed
in
th
e
s
tu
d
ies
[
2
0
]
,
[
2
3
]
,
[
2
6
]
,
wh
er
e
th
e
m
o
d
els
ac
h
iev
e
d
ab
o
u
t
9
4
%
in
ac
cu
r
ac
y
,
u
s
in
g
a
d
d
itio
n
al
tech
n
iq
u
es
s
u
ch
as
f
ea
tu
r
e
s
elec
tio
n
an
d
f
o
r
war
d
s
eq
u
en
tial
s
elec
tio
n
to
im
p
r
o
v
e
th
eir
m
o
d
els,
u
n
lik
e
o
u
r
s
tu
d
y
wh
er
e
s
u
ch
tech
n
iq
u
es
wer
e
n
o
t
em
p
lo
y
ed
.
T
h
e
L
R
m
o
d
el
i
n
th
is
s
tu
d
y
ac
h
ie
v
ed
a
p
er
f
o
r
m
an
ce
o
f
8
9
%
in
ac
cu
r
ac
y
an
d
s
en
s
itiv
ity
,
8
8
%
i
n
p
r
ec
is
io
n
,
a
n
d
8
7
%
in
F1
-
s
co
r
e
,
s
im
ilar
to
th
o
s
e
r
ec
o
r
d
ed
i
n
[
2
4
]
,
w
h
er
e
t
h
e
m
o
d
el
h
ad
a
p
er
f
o
r
m
an
ce
o
f
8
2
.
9
%
,
u
s
in
g
th
e
SMOT
E
o
v
er
s
am
p
lin
g
tech
n
i
q
u
e
to
g
en
e
r
ate
s
y
n
th
etic
d
ata
an
d
f
o
r
war
d
s
eq
u
en
tial
s
elec
tio
n
t
o
p
r
o
ce
s
s
th
e
d
ata,
t
h
ese
b
ein
g
th
e
m
ain
d
if
f
e
r
en
ce
with
o
u
r
s
tu
d
y
.
Fin
ally
,
th
e
KNN
m
o
d
el
was
o
n
e
o
f
th
e
la
s
t
m
o
d
els
with
th
e
lo
west
p
er
f
o
r
m
an
ce
,
with
8
5
%
ac
cu
r
ac
y
an
d
8
8
%
p
r
ec
is
io
n
.
T
h
is
is
s
im
ilar
to
th
e
s
tu
d
y
f
r
o
m
Ali
et
a
l.
[
2
4
]
,
wh
e
r
e
th
e
m
o
d
el
ac
h
iev
ed
8
3
%
in
ac
cu
r
ac
y
,
b
u
t
d
if
f
er
e
d
s
ig
n
if
ican
tly
in
s
tu
d
ies
s
u
ch
as
[
2
2
]
,
[
2
7
]
wh
e
r
e
th
e
m
o
d
el
ac
h
iev
ed
9
4
.
4
0
%
an
d
9
8
.
1
%
in
ac
cu
r
ac
y
,
r
esp
ec
tiv
ely
,
h
ig
h
lig
h
tin
g
th
e
u
s
e
o
f
o
p
tim
izatio
n
tec
h
n
iq
u
es
an
d
m
eth
o
d
s
th
at
wer
e
n
o
t
em
p
lo
y
ed
i
n
th
is
s
tu
d
y
.
Alth
o
u
g
h
th
e
ML
m
o
d
els
ev
alu
ated
ac
h
iev
ed
o
u
ts
tan
d
in
g
r
esu
lts
co
n
s
is
ten
t
with
p
r
ev
io
u
s
s
tu
d
ies,
it
is
clea
r
th
at
th
e
u
s
e
o
f
d
ata
o
p
tim
izatio
n
an
d
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
co
u
ld
f
u
r
t
h
er
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
o
f
th
ese
m
o
d
els.
Fu
tu
r
e
s
tu
d
ies
s
h
o
u
ld
co
n
s
id
er
th
e
in
teg
r
ati
o
n
o
f
t
h
ese
tech
n
iq
u
es
to
m
a
x
im
ize
ef
f
icac
y
i
n
p
r
ed
ictin
g
h
ep
atitis
C
.
I
t
’
s
im
p
o
r
tan
t
to
also
co
n
s
id
er
li
m
itatio
n
s
,
s
u
ch
as
th
e
s
ize
o
f
th
e
d
ataset
an
d
th
e
v
ar
iety
o
f
attr
ib
u
tes.
L
ar
g
e
r
,
m
o
r
e
d
iv
e
r
s
e
d
atasets
co
u
ld
im
p
r
o
v
e
m
o
d
el
g
e
n
er
aliza
b
ilit
y
.
T
h
e
aim
o
f
th
is
s
tu
d
y
was
to
b
en
ch
m
ar
k
d
if
f
e
r
en
t
ML
m
o
d
els
f
o
r
h
ep
atitis
C
p
r
ed
ictio
n
,
in
o
r
d
er
t
o
d
eter
m
in
e
wh
ich
o
f
th
e
m
o
d
el
s
o
f
f
er
s
b
etter
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
a
n
d
s
en
s
itiv
ity
.
T
h
e
ab
ilit
y
to
p
r
ed
ict
h
ep
atitis
C
ac
cu
r
ately
an
d
e
ar
ly
is
cr
u
cial
t
o
im
p
r
o
v
in
g
d
etec
tio
n
an
d
tr
e
atm
en
t
r
ates
o
f
th
e
d
is
ea
s
e.
T
h
is
s
tu
d
y
u
n
d
er
s
co
r
es
th
e
im
p
o
r
tan
ce
o
f
im
p
lem
en
tin
g
ad
v
a
n
ce
d
p
r
ed
ictiv
e
to
o
ls
in
th
e
clin
ical
s
ettin
g
to
id
en
tify
in
f
ec
te
d
p
atien
ts
an
d
ad
m
in
is
ter
ap
p
r
o
p
r
iate
tr
ea
tm
en
ts
in
a
tim
e
ly
m
an
n
er
.
T
h
is
s
tu
d
y
co
n
tr
ib
u
tes
to
th
e
em
er
g
in
g
f
ield
o
f
d
ig
ital
h
ea
lth
,
d
em
o
n
s
tr
atin
g
h
o
w
ML
m
o
d
els
ca
n
b
e
in
teg
r
ated
in
to
clin
ical
p
r
ac
tice
to
im
p
r
o
v
e
d
i
ag
n
o
s
tic
ac
cu
r
ac
y
an
d
m
an
a
g
em
en
t
o
f
in
f
ec
tio
u
s
d
is
ea
s
es
s
u
ch
as
h
e
p
atitis
C
.
T
h
e
in
clu
s
io
n
o
f
o
th
er
ty
p
es
o
f
clin
ical
d
ata
an
d
b
io
m
a
r
k
er
s
in
f
u
tu
r
e
s
tu
d
ies
co
u
ld
f
u
r
th
er
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
an
d
u
s
ef
u
l
n
ess
o
f
p
r
e
d
ictiv
e
m
o
d
els.
6.
CO
NCLU
SI
O
N
HC
V
in
f
ec
tio
n
is
a
d
is
ea
s
e
with
n
o
cu
r
e
av
ailab
le
to
d
a
y
,
af
f
ec
tin
g
m
illi
o
n
s
o
f
p
eo
p
le
o
f
all
ag
es
ar
o
u
n
d
th
e
wo
r
ld
.
I
t
s
p
r
ea
d
s
m
ain
ly
th
r
o
u
g
h
co
n
tact
with
co
n
tam
in
ated
b
lo
o
d
,
th
r
o
u
g
h
in
jectio
n
s
,
tr
an
s
f
u
s
io
n
s
,
an
d
o
th
er
m
ea
n
s
.
Giv
en
th
at
u
p
t
o
7
0
% o
f
in
f
ec
ted
in
d
iv
id
u
als ca
n
a
ch
iev
e
a
s
u
cc
ess
f
u
l r
ec
o
v
er
y
if
th
ey
r
ec
eiv
e
tr
ea
tm
en
t
in
a
t
im
ely
m
an
n
er
,
it
is
cr
u
cial
to
d
e
v
elo
p
tech
n
i
q
u
es
th
at
m
ak
e
it
ea
s
ier
f
o
r
m
e
d
ical
p
r
o
f
ess
io
n
als
to
d
etec
t
th
is
p
ath
o
lo
g
y
ea
r
l
y
.
I
n
th
is
s
tu
d
y
,
f
iv
e
ML
m
o
d
els
f
o
cu
s
ed
o
n
th
e
p
r
ed
ictio
n
o
f
Hep
atitis
C
wer
e
d
ev
elo
p
ed
,
a
n
aly
ze
d
,
a
n
d
e
v
alu
ated
,
with
t
h
e
aim
o
f
d
ete
r
m
in
in
g
wh
ich
o
f
th
e
m
o
d
els o
f
f
er
s
th
e
b
est
p
er
f
o
r
m
an
ce
in
th
is
t
ask
.
Af
ter
an
aly
zin
g
,
p
r
o
ce
s
s
in
g
,
an
d
tr
ain
in
g
t
h
e
m
o
d
els,
t
h
e
r
esu
lts
s
h
o
wed
Evaluation Warning : The document was created with Spire.PDF for Python.