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.
14
,
No
.
4
,
A
u
g
u
s
t 2
0
2
5
,
p
p
.
2
8
9
9
~
2
9
0
8
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
4
.
p
p
2
8
9
9
-
2
9
0
8
2899
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Predic
tion
of
sid
e
effects
of
drug
r
e
sis
tant
tu
berculo
s
is
drug
s
using
multi
-
la
be
l
ra
ndo
m
forest
Siti
Sy
a
hid
a
t
ul
H
elm
a
1
,4
,
Wi
s
nu
A
na
nta
K
us
um
a
1
,
M
us
h
t
ho
f
a
M
us
h
t
h
o
fa
1
,
Dia
h
H
a
nd
a
y
a
ni
2,
3
1
D
e
p
a
r
t
me
n
t
of
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
of
M
a
t
h
e
ma
t
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s
,
I
n
st
i
t
u
t
P
e
r
t
a
n
i
a
n
B
o
g
o
r
,
B
o
g
o
r
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
of
P
u
l
mo
n
o
l
o
g
y
a
n
d
R
e
s
p
i
r
a
t
o
r
y
M
e
d
i
c
i
n
e
,
F
a
c
u
l
t
y
of
M
e
d
i
c
i
n
e
,
U
n
i
v
e
r
si
t
a
s
I
n
d
o
n
e
s
i
a
,
D
e
p
o
k
,
I
n
d
o
n
e
si
a
3
C
e
n
t
r
a
l
F
r
i
e
n
d
s
h
i
p
G
e
n
e
r
a
l
H
o
s
p
i
t
a
l
,
Jak
a
r
t
a
,
I
n
d
o
n
e
si
a
4
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
C
a
l
t
e
x
R
i
a
u
P
o
l
y
t
e
c
h
n
i
c
,
P
e
k
a
n
b
a
r
u
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
5
,
2
0
2
4
R
ev
is
ed
Ap
r
8
,
2
0
2
5
Acc
ep
ted
J
u
n
8
,
2
0
2
5
D
r
u
g
-
r
e
s
i
s
ta
n
t
t
u
b
e
r
c
u
l
o
s
i
s
(
D
R
-
T
B
)
h
a
s
b
e
c
o
m
e
a
c
o
n
c
e
r
n
b
e
c
a
u
s
e
a
n
t
i
-
t
u
b
e
r
c
u
l
o
s
i
s
d
r
u
g
s
(
A
T
D
)
u
se
d
to
t
r
e
a
t
it
can
c
a
u
s
e
s
i
d
e
e
ff
e
c
t
s
in
p
a
t
ie
n
t
s
.
T
h
i
s
s
t
u
d
y
a
i
m
e
d
to
p
r
e
d
i
c
t
t
h
e
p
o
t
e
n
t
i
a
l
s
i
d
e
e
f
f
e
c
ts
of
A
T
D
u
s
i
n
g
a
m
u
l
t
i
-
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
w
i
t
h
a
r
a
n
d
o
m
f
o
r
e
s
t
(
R
F
)
a
l
g
o
r
i
t
h
m
.
T
h
i
s
st
u
d
y
u
s
e
d
660
m
e
d
i
c
a
l
r
e
c
o
r
d
d
a
t
a
,
i
n
c
l
u
d
i
n
g
t
h
e
14
A
T
D
t
r
e
a
t
m
e
n
t
s
p
r
e
sc
r
ib
e
d
to
t
h
e
p
a
t
i
e
n
t
s
a
n
d
t
h
e
s
i
x
s
i
d
e
e
f
f
e
c
t
s
e
x
p
e
r
i
e
n
c
e
d
by
p
a
t
i
e
n
t
s
.
T
h
e
m
o
d
e
l
w
a
s
t
r
a
i
n
e
d
u
s
i
n
g
t
h
e
b
e
s
t
p
a
r
a
m
e
t
e
rs
b
a
s
e
d
on
t
h
e
h
y
p
e
r
p
a
r
a
m
e
te
r
t
u
n
i
n
g
p
r
o
c
e
s
s
.
T
h
e
r
e
s
u
l
t
s
s
h
o
w
t
h
a
t
t
h
e
RF
m
u
l
t
i
-
l
a
b
e
l
a
l
g
o
r
i
t
h
m
can
be
an
a
l
t
e
rn
a
t
i
v
e
f
o
r
b
u
i
l
d
i
n
g
A
T
D
s
i
d
e
e
f
fe
c
t
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
b
e
c
a
u
s
e
it
p
r
o
d
u
c
e
s
t
h
e
m
o
s
t
o
p
t
i
m
a
l
p
e
r
f
o
r
m
a
n
c
e
v
a
l
u
e
c
o
m
p
a
r
e
d
to
t
h
e
d
e
c
i
s
i
o
n
t
r
e
e
(
D
T
)
a
n
d
e
x
t
r
e
m
e
g
r
a
d
i
e
n
t
b
o
o
s
t
i
n
g
(
X
G
B
o
o
s
t
)
.
T
h
e
a
r
e
a
u
n
d
e
r
t
h
e
c
u
r
v
e
(
A
U
C
)
s
c
o
r
e
of
a
l
l
RF
m
u
l
t
i
-
l
a
b
e
l
m
o
d
e
l
s
is
a
b
o
v
e
0
.
8
,
w
h
i
c
h
m
e
a
n
s
t
h
a
t
a
l
l
RF
m
u
l
t
i
-
l
a
b
e
l
m
o
d
e
l
s
a
r
e
c
o
n
s
i
d
e
r
e
d
a
c
c
e
p
t
a
b
l
e
a
n
d
a
p
p
l
i
c
a
b
l
e
f
o
r
A
T
D
s
i
d
e
e
f
f
e
c
t
p
r
e
d
i
c
t
i
o
n
.
In
a
d
d
i
t
i
o
n
,
e
i
g
h
t
f
e
a
t
u
r
e
s
i
n
f
l
u
e
n
c
e
d
t
h
e
m
o
d
e
l
s
b
a
s
e
d
on
t
h
e
a
v
e
r
a
g
e
f
e
a
t
u
r
e
i
m
p
o
r
t
a
n
c
e
s
c
o
re
of
t
h
e
RF
m
o
d
e
l
s
.
T
h
i
s
s
t
u
d
y
is
e
x
p
e
c
t
e
d
to
h
e
l
p
p
r
e
d
i
c
t
t
h
e
s
i
d
e
e
f
fe
c
t
s
of
A
TD
u
s
e
d
to
t
r
e
a
t
DR
-
TB
b
a
s
e
d
on
A
T
D
t
r
e
a
t
m
e
n
t
a
n
d
d
e
t
e
r
m
i
n
e
t
h
e
m
o
s
t
p
r
o
m
i
s
i
n
g
t
r
e
e
-
b
a
s
e
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
p
r
e
d
i
c
t
i
n
g
A
T
D
s
i
d
e
e
f
fe
c
ts
.
K
ey
w
o
r
d
s
:
Dr
u
g
s
id
e
ef
f
ec
ts
Dr
u
g
-
r
esis
tan
t
tu
b
er
c
u
lo
s
is
Mu
lti
-
lab
el
class
if
icatio
n
T
r
ee
-
b
ased
lear
n
i
n
g
T
u
b
er
cu
l
o
s
is
T
h
is
is
an
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC
BY
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
is
n
u
An
an
ta
Ku
s
u
m
a
Dep
ar
tm
en
t
of
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lty
of
Ma
th
em
atics
an
d
Natu
r
al
Scien
ce
s
,
I
n
s
titu
t P
er
tan
ian
B
o
g
o
r
B
o
g
o
r
R
eg
en
cy
,
W
est
J
av
a
16680
,
I
n
d
o
n
esia
E
m
ail:
an
an
ta@
ap
p
s
.
ip
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
u
b
er
cu
l
o
s
is
(
T
B
)
h
as
b
ee
n
d
ec
lar
ed
by
t
h
e
W
o
r
ld
H
ea
lth
Or
g
an
izatio
n
(
W
HO)
as
one
of
th
e
d
ea
d
lies
t
d
is
ea
s
es
in
th
e
w
o
r
ld
an
d
a
t
h
r
ea
t
to
p
u
b
lic
h
ea
lth
.
It
h
as
b
ec
o
m
e
a
h
ig
h
p
r
i
o
r
ity
ch
allen
g
in
g
to
tr
ea
t
T
B
,
esp
ec
ially
d
r
u
g
-
r
esis
tan
t
tu
b
er
c
u
lo
s
is
(
DR
-
T
B
)
[
1
]
.
DR
-
TB
ca
u
s
es
p
r
o
b
lem
s
in
te
r
m
s
of
t
o
ler
an
ce
to
an
ti
-
t
u
b
er
cu
l
o
s
is
d
r
u
g
s
(
AT
D)
,
an
d
it
was
p
r
ed
icted
th
at
th
e
r
e
wer
e
4
6
5
,
0
0
0
DR
-
TB
ca
s
e
s
in
2
0
1
9
[
2
]
.
T
h
e
tr
ea
tm
en
t
of
DR
-
TB
is
co
m
p
licated
b
ec
au
s
e
it
is
n
ec
ess
ar
y
to
m
o
n
ito
r
an
d
m
an
a
g
e
s
id
e
ef
f
ec
ts
p
r
o
p
e
r
ly
,
wh
ich
af
f
ec
ts
p
atien
t
ad
h
er
e
n
ce
[
3
]
,
[
4
]
.
E
ac
h
i
n
d
iv
id
u
al
h
as
v
ar
io
u
s
r
esp
o
n
s
es
in
th
e
DR
-
TB
tr
ea
tm
en
t
th
er
ap
y
p
r
o
ce
s
s
with
AT
D.
Ho
wev
er
,
tr
ea
tm
e
n
t
ca
n
n
o
t
be
s
to
p
p
ed
b
ec
a
u
s
e
of
r
ea
ctio
n
s
f
r
o
m
th
e
d
r
u
g
s
co
n
s
u
m
ed
.
Du
r
in
g
DR
-
TB
tr
ea
tm
en
t
th
er
a
p
y
,
it
is
n
ec
ess
ar
y
to
m
o
n
ito
r
s
id
e
ef
f
ec
ts
b
e
ca
u
s
e
all
AT
D
can
p
o
ten
tially
ca
u
s
e
v
ar
i
o
u
s
s
id
e
ef
f
ec
ts
in
p
atien
ts
[
5
]
.
R
eg
u
lar
clin
ical
m
o
n
ito
r
i
n
g
,
l
ab
o
r
ato
r
y
a
n
aly
s
is
,
an
d
a
m
u
l
tid
is
cip
lin
ar
y
ap
p
r
o
ac
h
ar
e
es
s
en
tial
f
o
r
th
e
f
o
llo
w
-
up
tr
ea
tm
e
n
t
of
DR
-
TB
p
atien
ts
[
6
]
.
C
o
m
p
u
tati
o
n
al
ap
p
r
o
ac
h
es
can
be
u
s
ed
to
m
o
n
ito
r
th
e
s
id
e
ef
f
ec
ts
of
d
r
u
g
s
,
in
clu
d
in
g
th
eir
p
r
ed
ictio
n
s
.
T
h
is
s
tu
d
y
u
s
ed
DR
-
TB
d
ata
f
r
o
m
th
e
I
n
d
o
n
esian
TB
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
8
9
9
-
2
9
0
8
2900
in
f
o
r
m
atio
n
s
y
s
tem
(
SIT
B
)
.
A
p
r
ev
io
u
s
s
tu
d
y
by
Z
h
ao
et
al
.
[
7
]
on
d
r
u
g
s
id
e
ef
f
ec
t
p
r
ed
ic
tio
n
was
p
u
b
lis
h
ed
u
s
in
g
f
iv
e
ty
p
es
of
h
eter
o
g
e
n
eo
u
s
d
r
u
g
in
f
o
r
m
atio
n
.
T
h
is
s
tu
d
y
lim
ited
th
e
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
p
r
o
b
lem
to
b
in
ar
y
class
if
icatio
n
u
s
in
g
r
an
d
o
m
f
o
r
est
(
R
F)
to
d
eter
m
in
e
wh
eth
er
a
d
r
u
g
an
d
it
s
s
id
e
ef
f
ec
ts
wer
e
ass
o
ciate
d
.
If
th
e
r
esu
ltin
g
p
r
e
d
ictio
n
is
p
o
s
itiv
e,
th
e
d
r
u
g
is
co
n
s
id
er
ed
to
h
av
e
a
s
id
e
ef
f
ec
t
an
d
v
ice
v
er
s
a.
Au
th
o
r
s
in
[
8
]
,
[
9
]
m
o
d
elled
th
e
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
p
r
o
b
lem
as
a
m
u
lti
-
lab
el
class
if
i
ca
tio
n
task
b
ec
au
s
e
each
d
r
u
g
can
p
o
ten
tially
h
av
e
more
th
a
n
o
n
e
s
id
e
ef
f
ec
t.
Mu
lti
-
lab
el
lear
n
in
g
p
r
o
v
id
es
a
p
o
ten
tial
s
o
lu
tio
n
if
each
s
am
p
le
in
th
e
d
ataset
h
as
more
th
an
one
la
b
el
[
1
0
]
.
T
h
e
s
tu
d
y
by
Ko
u
ch
a
k
i
et
a
l
.
[
1
0
]
on
TB
d
r
u
g
r
esis
tan
ce
clas
s
if
icatio
n
an
d
m
u
tatio
n
r
an
k
in
g
with
m
u
lti
-
lab
el
RF
p
r
o
d
u
ce
d
b
ett
er
p
er
f
o
r
m
an
ce
th
an
s
in
g
le
-
lab
el
R
F,
wh
er
e
m
u
lti
-
lab
el
R
F
can
im
p
r
o
v
e
th
e
p
er
f
o
r
m
an
ce
of
co
n
v
en
ti
o
n
al
clin
ical
m
eth
o
d
s
by
1
8
.
1
0
%
co
m
p
ar
ed
to
s
in
g
le
-
la
b
el
R
F
,
w
h
ich
is
o
n
ly
0
.
9
1
%.
R
esear
ch
by
Z
h
ao
et
al
.
[
7
]
,
wh
ich
u
s
ed
a
b
in
ar
y
class
if
icatio
n
ap
p
r
o
ac
h
with
th
e
RF
a
lg
o
r
ith
m
to
p
r
e
d
ict
d
r
u
g
s
id
e
ef
f
ec
ts
,
d
id
n
o
t
y
et
r
ef
lect
th
e
m
u
ltip
le
s
id
e
ef
f
ec
t
s
th
at
th
e
d
r
u
g
m
ig
h
t
h
a
v
e.
T
h
er
ef
o
r
e
,
th
is
s
tu
d
y
u
s
ed
a
m
u
lti
-
lab
el
class
if
icati
o
n
ap
p
r
o
ac
h
to
b
u
ild
an
AT
D
s
id
e
ef
f
ec
ts
p
r
ed
ictio
n
m
o
d
el
u
s
in
g
RF
[
1
0
]
.
We
also
u
s
ed
d
ec
is
io
n
tr
ee
(
DT
)
an
d
ex
tr
e
m
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t)
.
T
h
ese
alg
o
r
ith
m
s
ar
e
wid
ely
u
s
ed
b
ec
au
s
e
th
ey
can
p
r
o
d
u
ce
r
ea
l
is
tic
o
u
tp
u
ts
an
d
ar
e
ea
s
y
to
in
ter
p
r
et
an
d
in
tu
itiv
e
[
1
1
]
,
[
1
2
]
.
T
h
is
s
tu
d
y
a
im
ed
to
p
r
e
d
ict
th
e
s
id
e
ef
f
ec
ts
of
AT
D
b
ased
on
an
AT
D
t
r
ea
tm
en
t
r
e
g
im
en
with
a
m
u
lti
-
lab
el
p
r
o
b
lem
tr
an
s
f
o
r
m
atio
n
ap
p
r
o
ac
h
u
s
in
g
th
e
RF
alg
o
r
ith
m
co
m
p
ar
ed
with
DT
an
d
XGBo
o
s
t.
T
h
e
r
esu
lts
of
th
is
s
tu
d
y
ar
e
ex
p
ec
ted
to
h
elp
id
en
tif
y
th
e
s
id
e
ef
f
ec
ts
of
DR
-
TB
d
r
u
g
s
an
d
d
eter
m
i
n
e
th
e
m
o
s
t
s
u
itab
le
an
d
ac
cu
r
ate
tr
ee
-
b
ased
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
f
o
r
p
r
e
d
ictin
g
AT
D
s
id
e
ef
f
ec
ts
.
2.
M
E
T
H
O
D
T
h
e
r
esear
ch
was
d
i
v
id
ed
in
t
o
s
ev
er
al
m
ain
s
tag
es,
as
Fig
u
r
e
1
d
ep
icts
.
T
h
e
f
i
r
s
t
s
tag
e
was
th
e
co
llectio
n
of
r
esear
ch
d
ata
th
at
f
o
r
m
e
d
th
e
b
asis
of
th
e
an
aly
s
is
.
T
h
e
co
llected
d
ata
is
p
r
o
ce
s
s
ed
th
r
o
u
g
h
a
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
to
en
s
u
r
e
d
ata
q
u
ality
.
T
h
e
d
ata
m
o
d
elin
g
an
d
h
y
p
er
p
a
r
am
eter
tu
n
in
g
s
tag
es
ar
e
p
er
f
o
r
m
ed
u
s
in
g
th
r
ee
tr
ee
-
b
ased
lear
n
in
g
alg
o
r
ith
m
s
.
T
h
e
last
s
tag
e
in
clu
d
es
ca
lcu
lat
in
g
an
d
an
aly
zin
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
to
o
b
tain
o
p
tim
al
r
esu
lts
.
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
o
l
o
g
y
2
.
1
.
Resea
rc
h
da
t
a
T
h
is
s
tu
d
y
u
s
ed
s
ec
o
n
d
ar
y
d
ata
f
r
o
m
SIT
B
an
d
th
e
m
ed
i
ca
l
r
ec
o
r
d
s
of
DR
-
TB
p
atien
ts
f
r
o
m
th
e
Per
s
ah
ab
atan
Natio
n
al
R
esp
ir
ato
r
y
R
ef
er
r
al
H
o
s
p
ital
in
J
ak
ar
ta
f
r
o
m
J
an
u
ar
y
2
0
1
8
to
De
ce
m
b
er
2
0
2
1
.
T
h
is
s
tu
d
y
was
ap
p
r
o
v
ed
by
th
e
Ho
s
p
ital
an
d
E
th
ics
C
o
m
m
ittee
of
th
e
Facu
lty
of
Me
d
ic
in
e,
Un
iv
er
s
ity
of
I
n
d
o
n
esia
(
eth
ics
n
u
m
b
er
:
KE
T
-
1
3
2
6
/UN2
/F1
/ET
I
K/PP
M.
0
0
.
0
2
/2
0
2
2
)
.
T
h
e
d
ataset
is
d
iv
id
ed
in
to
two
p
ar
ts
:
e
ach
d
r
u
g
g
iv
e
n
r
ep
r
esen
t
d
at
a
f
ea
tu
r
es
co
n
s
is
t
of
clo
f
az
im
in
e
(
C
f
z)
;
b
ed
a
q
u
ilin
e
(
B
d
q
)
;
k
an
a
m
y
cin
(
Km
)
;
lev
o
f
lo
x
ac
in
(
L
f
x
)
;
m
o
x
i
f
lo
x
ac
in
(
Mf
x
)
;
lin
ez
o
lid
(
L
z
d
)
;
cy
clo
s
er
in
e
(
C
s
)
;
eth
am
b
u
to
l
(E);
is
o
n
iazid
(
H)
;
eth
io
n
am
id
e
(
E
to
)
;
d
elam
an
id
(
Dlm
)
;
p
y
r
az
in
am
id
e
(Z);
P
-
a
m
in
o
s
alicy
lic
ac
id
(
PAS);
an
d
also
s
tr
ep
to
m
y
cin
(
S)
an
d
each
s
id
e
ef
f
ec
t
r
e
p
r
esen
t
d
ata
lab
els
or
class
es
co
n
s
is
t
of
g
astro
in
test
in
al
;
n
eu
r
o
p
s
y
c
h
iatr
ic;
ca
r
d
io
v
as
cu
lar
; m
u
s
cu
lo
s
k
eleta
l; a
n
em
ia;
an
d
o
t
h
er
s
id
e
ef
f
e
cts
.
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
Data
p
r
ep
r
o
ce
s
s
in
g
aim
s
to
f
o
r
m
a
n
u
m
er
ical
f
ea
t
u
r
e
v
ec
t
o
r
to
be
u
s
ed
as
in
p
u
t
d
ata
f
o
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els
[
1
3
]
.
T
h
e
p
r
e
p
r
o
ce
s
s
in
g
f
lo
w
is
illu
s
tr
ated
in
Fig
u
r
e
2.
T
h
e
e
x
is
tin
g
d
ata
wer
e
th
en
clea
n
ed
by
r
e
f
er
r
in
g
to
th
e
r
esu
lts
o
b
t
ain
ed
d
u
r
in
g
th
e
ex
p
lo
r
ato
r
y
d
ata
an
aly
s
is
s
tag
e.
T
h
e
d
ata
t
r
an
s
f
o
r
m
atio
n
s
tag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f sid
e
effec
ts
o
f d
r
u
g
r
esis
ta
n
t tu
b
ercu
lo
s
is
d
r
u
g
s
u
s
in
g
mu
lti
-
la
b
el
…
(
S
iti S
y
a
h
id
a
tu
l H
elma
)
2901
was
th
en
p
er
f
o
r
m
e
d
to
o
b
tai
n
n
u
m
er
ical
v
alu
es
u
s
in
g
th
e
one
-
hot
e
n
co
d
in
g
tech
n
iq
u
e,
wh
ich
p
r
o
d
u
ce
d
a
b
in
ar
y
d
ata
ar
r
ay
f
o
r
ea
c
h
f
ea
t
u
r
e
an
d
la
b
el.
B
in
ar
y
d
ata
c
o
n
s
is
ted
of
a
v
alu
e
of
1,
in
d
icati
n
g
th
at
th
e
p
atie
n
t
r
ec
eiv
ed
ea
c
h
d
r
u
g
an
d
h
ad
s
id
e
ef
f
ec
ts
,
a
n
d
a
v
alu
e
of
0,
in
d
icatin
g
th
at
th
e
p
atien
t
d
id
not
r
ec
eiv
e
th
e
d
r
u
g
an
d
h
a
d
no
s
id
e
e
f
f
ec
ts
.
Fig
u
r
e
2
.
Flo
w
of
p
r
e
p
r
o
ce
s
s
in
g
to
o
b
tain
f
ea
tu
r
es
an
d
lab
el
s
2
.
3
.
M
ulti
-
la
bel
ra
nd
o
m
f
o
r
est
m
o
delin
g
Mu
ltil
ab
el
class
if
icatio
n
is
a
p
ar
t
of
s
u
p
er
v
is
ed
lear
n
in
g
t
h
at
aim
s
to
m
ap
each
d
ataset
in
to
more
th
an
one
lab
el
or
class
[
1
4
]
.
T
h
er
e
ar
e
s
ev
er
al
tech
n
iq
u
es
f
o
r
m
u
lti
-
lab
el
class
if
icati
o
n
u
s
in
g
p
r
o
b
lem
tr
an
s
f
o
r
m
atio
n
m
eth
o
d
s
,
n
am
e
ly
,
class
if
ier
ch
ain
(
C
C
)
,
b
in
a
r
y
r
ele
v
an
ce
(
B
R
)
,
an
d
lab
el
p
o
wer
s
et
(
L
P)
[
1
5
]
.
In
th
is
s
tu
d
y
,
g
iv
en
a
s
et
of
m
AT
D,
wh
er
e
=
{
1
,
…
,
}
,
with
,
=
1
,
…
,
,
an
d
th
er
e
is
a
s
et
of
n
s
id
e
ef
f
ec
t
lab
els,
wh
er
e
=
{
1
,
…
,
}
,
with
,
=
1
,
…
,
.
E
ac
h
r
ec
o
r
d
in
D
is
a
s
s
o
ciate
d
with
one
or
more
s
id
e
ef
f
ec
t
la
b
els
in
L
.
RF
is
an
en
s
em
b
le
class
if
icatio
n
m
et
h
o
d
b
ased
on
b
u
ild
in
g
m
u
ltip
le
in
d
e
p
en
d
e
n
t
DT
clas
s
if
ier
s
on
d
if
f
er
en
t
s
u
b
s
ets
of
a
d
ataset
by
co
n
s
id
er
in
g
th
e
co
m
b
in
atio
n
of
each
class
if
icatio
n
o
u
t
p
u
t
to
im
p
r
o
v
e
th
e
f
i
n
al
p
r
ed
ictio
n
p
er
f
o
r
m
an
ce
[
1
6
]
.
T
h
e
RF
m
o
d
el
can
be
ex
ten
d
e
d
to
s
tu
d
y
a
n
d
p
r
ed
ict
s
id
e
ef
f
ec
ts
of
TB
d
r
u
g
s
by
co
n
s
id
er
in
g
a
c
o
m
b
in
e
d
s
co
r
e
(
Gin
i
in
d
ex
)
.
T
h
e
p
r
o
ce
s
s
of
ca
lcu
latin
g
th
e
Gin
i
in
d
e
x
,
as
s
h
o
wn
in
(
1
)
,
is
p
er
f
o
r
m
ed
by
ca
lcu
latin
g
each
DT
f
o
r
each
p
air
(
,
)
of
f
ea
tu
r
e
(
)
an
d
v
alu
e
(
f
ea
tu
r
e
v
alu
e)
with
lab
el
(
s
id
e
ef
f
ec
ts
)
at
n
o
d
e
(
)
[
1
0
]
.
Gin
i
in
d
ex
(
,
,
)
=
∑
(
,
,
)
∈
(
1
)
T
h
e
v
ar
iab
le
r
ep
r
esen
ts
th
e
n
u
m
b
er
of
lab
els
or
s
id
e
ef
f
ec
ts
in
th
e
an
aly
s
is
.
T
h
e
an
d
ar
e
th
e
co
m
b
in
ed
an
d
p
e
r
-
lab
el
Gin
i
in
d
ices,
r
esp
ec
tiv
ely
.
T
h
ese
two
in
d
ices
p
lay
an
im
p
o
r
tan
t
r
o
le
in
ca
lcu
latin
g
th
e
im
p
o
r
tan
ce
of
f
ea
tu
r
es.
T
h
e
ca
lcu
latio
n
is
ca
lcu
lated
by
av
er
ag
in
g
t
h
e
im
p
u
r
ity
r
ed
u
cti
o
n
ass
o
ciate
d
with
each
f
ea
tu
r
e.
To
i
m
p
r
o
v
e
t
h
e
f
i
n
a
l
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
,
F
i
g
u
r
e
3
s
h
o
w
s
t
h
a
t
RF
c
o
m
b
i
n
e
s
t
h
e
o
u
tp
u
t
of
each
s
e
l
e
ct
e
d
i
n
d
e
p
e
n
d
e
n
t
t
r
e
e
u
s
i
n
g
v
o
t
i
n
g
or
m
a
j
o
r
i
t
y
t
e
c
h
n
i
q
u
es
.
T
h
e
d
at
a
s
e
t
was
d
i
v
i
d
e
d
i
n
to
t
r
a
i
n
i
n
g
d
a
t
a
t
h
a
t
w
e
r
e
u
s
e
d
f
o
r
t
r
a
i
n
i
n
g
a
n
d
m
o
d
e
l
v
a
l
i
d
a
ti
o
n
,
a
n
d
t
es
t
d
at
a
t
h
at
w
e
r
e
u
s
e
d
to
t
e
s
t
t
h
e
m
o
d
el
.
T
h
e
t
r
a
i
n
i
n
g
p
r
o
c
es
s
was
c
o
n
d
u
c
t
e
d
u
s
i
n
g
a
c
r
o
s
s
-
v
a
l
i
d
a
t
i
o
n
te
c
h
n
i
q
u
e
w
it
h
k=
5
to
e
v
a
l
u
a
t
e
t
h
e
p
e
r
f
o
r
m
a
n
c
e
of
t
h
e
m
o
d
e
l
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
8
9
9
-
2
9
0
8
2902
Fig
u
r
e
3
.
I
ll
u
s
tr
atio
n
of
t
h
e
RF
m
o
d
el
2
.
4
.
H
y
perpa
ra
m
e
t
er
t
un
ing
T
h
i
s
s
t
u
d
y
u
s
e
s
a
g
r
i
d
s
e
a
r
c
h
t
e
c
h
n
i
q
u
e
to
p
e
r
f
o
r
m
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
.
G
r
i
d
s
e
a
r
c
h
w
o
r
k
s
by
t
r
y
i
n
g
a
l
l
p
o
s
s
i
b
l
e
c
o
m
b
i
n
a
t
i
o
n
s
b
a
s
e
d
on
p
r
e
d
e
f
i
n
e
d
p
a
r
a
m
e
t
e
r
v
a
l
u
e
s
.
T
h
i
s
p
r
o
c
e
s
s
a
i
m
s
to
s
e
l
e
c
t
o
p
t
i
m
a
l
p
a
r
a
m
e
t
e
r
s
t
h
a
t
s
u
p
p
o
r
t
m
a
x
i
m
u
m
m
o
d
e
l
p
e
r
f
o
r
m
a
n
c
e
[
1
8
]
.
S
e
v
e
r
a
l
p
a
r
a
m
e
t
e
r
s
a
r
e
r
e
q
u
i
r
e
d
to
b
u
i
l
d
m
o
d
e
l
s
.
A
l
i
s
t
of
t
e
s
t
e
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
s
is
p
r
o
v
i
d
e
d
in
h
t
t
p
s
:
/
/
d
r
i
v
e
.
g
o
o
g
l
e
.
c
o
m
/
f
i
l
e
/
d
/
1
B
h
X
O
y
p
k
G
J
A
X
r
4
h
I
i
J
X
l
h
L
M
f
J
x
w
w
i
U
2
w
7
/
v
i
e
w
.
2
.
5
.
M
o
del
ev
a
lua
t
i
o
n
T
h
e
p
ar
a
m
eter
s
u
s
ed
to
ca
lc
u
late
m
o
d
el
p
er
f
o
r
m
an
ce
we
r
e
b
ased
on
ac
c
u
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
F
-
s
co
r
e,
Fβ
,
an
d
Ham
m
in
g
l
o
s
s
v
alu
es.
Acc
u
r
ac
y
is
a
m
etr
i
c
u
s
ed
to
m
ea
s
u
r
e
th
e
co
r
r
ec
t
n
ess
r
atio
[
1
9
]
.
is
th
e
n
u
m
b
er
of
tr
ain
in
g
d
ata
to
be
test
ed
,
an
d
an
d
ℎ
(
)
ar
e
th
e
ac
t
u
al
an
d
p
r
ed
icted
d
ata
la
b
els,
r
esp
ec
tiv
ely
.
T
h
e
in
ter
s
ec
tio
n
of
with
ℎ
(
)
r
ep
r
esen
ts
th
e
co
r
r
ec
t
p
r
e
d
icted
lab
el,
an
d
th
e
u
n
io
n
of
with
ℎ
(
)
r
ep
r
esen
ts
th
e
co
m
b
in
atio
n
of
th
e
p
r
ed
icted
la
b
el
an
d
ac
tu
al
l
ab
el
[
2
0
]
as
in
(
2
)
.
=
1
∑
|
∩
ℎ
(
)
|
|
∩
ℎ
(
)
|
=
1
(
2
)
R
ec
all
is
th
e
ac
cu
r
ac
y
of
th
e
m
o
d
el
in
p
r
ed
ictin
g
p
o
s
itiv
e
c
lass
es
by
m
in
im
izin
g
m
is
p
r
ed
icted
p
o
s
itiv
e
da
ta,
an
d
p
r
ec
is
io
n
is
th
e
ac
c
u
r
ac
y
of
th
e
m
o
d
el
in
p
r
ed
ictin
g
p
o
s
itiv
e
class
es
by
m
in
im
izin
g
m
i
s
p
r
ed
icted
n
e
g
ativ
e
d
ata,
wh
er
e
is
th
e
n
u
m
b
er
of
t
est
d
ata
to
be
test
ed
,
,
,
an
d
th
e
in
ter
s
ec
tio
n
of
an
d
ar
e
th
e
ac
tu
al
d
ata
lab
el,
th
e
p
r
ed
icted
d
ata
lab
el,
an
d
th
e
in
ter
s
ec
tio
n
of
with
in
d
icate
s
th
e
lab
el
co
r
r
ec
tly
p
r
ed
icted
by
th
e
m
o
d
el
[
2
0
]
.
T
h
e
r
ec
all
an
d
p
r
e
cisi
o
n
in
(
3
)
a
n
d
(
4
)
,
r
esp
ec
tiv
ely
,
ar
e
as
f
o
llo
ws
:
=
1
∑
|
∩
|
|
|
=
1
(
3
)
=
1
∑
|
∩
|
|
|
=
1
(
4
)
As
s
h
o
wn
in
(
5
)
,
th
e
F1
-
s
co
r
e
is
a
weig
h
ted
av
e
r
ag
e
c
o
m
p
ar
is
o
n
of
t
h
e
p
r
ec
is
io
n
an
d
r
e
ca
ll
v
alu
es
u
s
ed
to
m
ea
s
u
r
e
th
e
o
v
er
all
m
in
o
r
ity
class
p
er
f
o
r
m
an
ce
[
2
1
]
,
wh
e
r
e
is
th
e
lab
el
in
th
e
m
u
lti
-
lab
el
m
o
d
el.
T
h
e
F1
-
s
c
o
r
e
c
o
n
s
i
d
e
r
s
ea
c
h
o
u
t
p
u
t
l
a
b
e
l
[
1
4
]
.
T
h
e
p
e
r
f
o
r
m
a
n
c
e
is
good
if
it
e
x
h
i
b
i
t
s
a
h
i
g
h
a
v
e
r
ag
e
c
l
a
s
s
v
a
l
u
e
[
1
5
]
.
1
−
=
1
×
2
×
×
+
(
5
)
is
a
m
etr
ic
th
at
m
ea
s
u
r
es
th
e
weig
h
ted
h
ar
m
o
n
ic
m
ea
n
of
r
e
ca
ll
or
p
r
ec
is
io
n
.
T
h
e
v
alu
e
of
β
d
eter
m
in
es
th
e
weig
h
ts
of
th
e
r
ec
all
an
d
p
r
e
cisi
o
n
.
If
th
e
r
ec
all
v
alu
e
is
g
r
ea
ter
,
β>1
.
C
o
n
v
er
s
ely
,
if
th
e
p
r
ec
is
io
n
v
alu
e
is
g
r
ea
ter
,
β<1
[
2
2
]
.
In
th
e
ca
s
e
of
s
id
e
ef
f
ec
t
p
r
e
d
ictio
n
,
m
in
im
izin
g
th
e
f
alse
-
n
eg
a
tiv
e
v
alu
e
is
co
n
s
id
er
ed
more
im
p
o
r
tan
t
th
an
m
in
im
iz
in
g
th
e
f
alse
-
p
o
s
itiv
e
v
alu
e.
T
h
er
ef
o
r
e
,
more
weig
h
t
was
g
iv
en
to
r
ec
all
u
s
in
g
β=2
to
em
p
h
asize
th
e
im
p
o
r
ta
n
ce
of
f
ewe
r
f
alse
-
n
eg
ativ
e
o
c
cu
r
r
en
ce
s
.
T
h
e
f
o
r
m
u
la
is
g
iv
en
by
(
6
)
[
2
3
]
.
=
1
∑
[
(
1
+
2
)
2
|
∩
|
2
|
|
+
|
|
]
=
1
(
6
)
T
h
e
Ham
m
in
g
lo
s
s
(
7
)
ca
lcu
lates
how
m
an
y
lab
els
s
h
o
u
ld
not
b
elo
n
g
to
an
in
s
tan
ce
b
u
t
ar
e
p
r
ed
icted
to
b
elo
n
g
to
th
at
in
s
tan
ce
or
v
ice
v
er
s
a.
T
h
e
f
ewe
r
th
e
m
is
p
r
ed
i
cted
lab
els,
th
e
s
m
aller
th
e
Ha
m
m
in
g
lo
s
s
v
alu
e,
wh
ich
in
d
icate
s
a
b
etter
p
e
r
f
o
r
m
an
ce
of
t
h
e
m
u
lti
-
lab
el
lear
n
in
g
m
o
d
el
[
2
4
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f sid
e
effec
ts
o
f d
r
u
g
r
esis
ta
n
t tu
b
ercu
lo
s
is
d
r
u
g
s
u
s
in
g
mu
lti
-
la
b
el
…
(
S
iti S
y
a
h
id
a
tu
l H
elma
)
2903
=
1
∑
∑
⟦
ℎ
≠
⟧
=
1
=
1
(
7
)
2
.
6
.
Ana
ly
s
is
of
i
m
po
rt
a
nt
f
ea
t
ures
of
t
he
mo
del
T
h
e
o
v
er
all
f
ea
t
u
r
e
im
p
o
r
tan
c
e
is
ca
lcu
lated
b
ased
on
th
e
d
ec
r
ea
s
e
in
im
p
u
r
ity
of
th
e
n
o
d
es
in
th
e
m
o
d
el.
T
h
is
d
ec
r
ea
s
e
is
weig
h
ted
ac
co
r
d
in
g
to
t
h
e
p
r
o
b
ab
i
lity
of
r
ea
ch
in
g
a
p
ar
tic
u
lar
n
o
d
e.
T
h
e
im
p
u
r
ity
v
alu
e
of
t
h
e
node
was
th
e
n
r
e
d
u
ce
d
u
n
til
it
r
ea
ch
ed
tr
ee
lev
el.
T
h
e
h
ig
h
er
th
e
f
ea
tu
r
e
s
c
o
r
e,
th
e
g
r
ea
ter
th
e
f
ea
tu
r
e
im
p
o
r
tan
ce
in
th
e
RF
m
o
d
el
[
2
5
]
.
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
prepro
ce
s
s
ing
We
co
m
b
in
ed
two
d
atasets
b
a
s
ed
on
SIT
B
an
d
s
id
e
ef
f
ec
t
d
ata
f
r
o
m
m
ed
ical
r
ec
o
r
d
s
,
th
e
r
e
wer
e
6
6
0
s
u
b
jects
elig
ib
le
f
o
r
th
is
s
tu
d
y
,
with
a
m
ea
n
a
g
e
of
43
y
e
ar
s
(
C
I
:
4
1
.
7
9
1
,
4
4
.
0
1
8
)
,
an
d
368
(
5
5
.
8
%)
wer
e
m
ale.
T
h
e
14
d
r
u
g
s
wer
e
u
s
ed
in
c
o
m
b
in
atio
n
as
a
r
e
g
im
en
.
E
ac
h
d
r
u
g
was
in
p
u
tted
as
a
f
ea
tu
r
e,
a
n
d
th
e
s
id
e
ef
f
ec
ts
wer
e
class
if
ied
in
to
s
ix
ty
p
es
of
s
id
e
ef
f
ec
ts
.
3
.
2
.
M
ulti
-
la
bel
m
o
delin
g
Mu
lti
-
lab
el
m
o
d
elin
g
was
ap
p
lied
to
th
e
R
F,
DT
,
an
d
X
GB
o
o
s
t
alg
o
r
ith
m
s
.
T
h
e
i
n
itial
m
o
d
elin
g
u
s
es
th
e
d
e
f
au
lt
p
ar
am
eter
s
of
each
alg
o
r
ith
m
.
T
h
e
n
,
m
o
d
eli
n
g
is
a
p
p
lied
u
s
in
g
th
e
p
ar
am
eter
s
th
at
h
a
v
e
b
ee
n
d
eter
m
in
ed
.
At
th
is
s
tag
e,
m
o
d
elin
g
u
s
es
80%
of
th
e
d
ata
f
r
o
m
th
e
t
o
tal
d
ataset.
T
h
e
o
p
t
im
al
p
ar
am
eter
s
f
o
r
each
m
u
lti
-
lab
el
m
o
d
el
ar
e
lis
ted
in
T
ab
le
1.
B
ased
o
n
th
e
tu
n
in
g
r
esu
lts
,
we
f
o
u
n
d
th
at
ea
ch
R
F
m
u
lti
-
lab
el
m
o
d
el
h
ad
d
if
f
e
r
en
t
s
ets
o
f
o
p
tim
al
p
ar
am
eter
s
.
T
h
e
d
if
f
e
r
en
ce
in
p
ar
am
eter
s
lies
in
th
e
v
alu
e
o
f
n
_
esti
m
ato
r
s
R
F,
wh
ich
is
5
0
in
R
F
-
C
C
an
d
2
5
in
R
F
-
B
R
an
d
R
F
-
L
P,
r
esp
ec
tiv
ely
.
T
h
e
m
ax
_
f
ea
tu
r
es
p
a
r
a
m
eter
is
s
q
r
t
in
R
F
-
C
C
an
d
R
F
-
B
R
an
d
n
o
n
e
in
R
F
-
L
P.
T
h
e
m
in
_
s
am
p
les_
s
p
l
it
p
ar
am
eter
is
2
f
o
r
R
F
-
C
C
a
n
d
R
F
-
B
R
an
d
1
0
f
o
r
R
F
-
L
P.
An
o
th
er
d
if
f
er
en
ce
is
in
th
e
m
a
x
_
leaf
_
n
o
d
es
p
ar
am
eter
,
wh
ich
is
th
r
ee
f
o
r
R
F
-
C
C
an
d
R
F
-
B
R
,
an
d
s
ix
f
o
r
R
F
-
L
P.
T
h
e
o
n
ly
d
if
f
er
en
ce
in
th
e
b
est
p
ar
am
et
er
s
in
th
e
DT
m
o
d
el
is
th
e
m
i
n
_
s
am
p
les_
leaf
p
ar
a
m
eter
,
w
h
ich
is
5
in
DT
-
CC
an
d
DT
-
B
R
an
d
4
in
DT
-
L
P,
a
n
d
th
e
b
est p
ar
am
eter
s
ar
e
th
e
s
am
e
in
all
XGBo
o
s
t m
o
d
els.
T
ab
le
1.
L
is
t
of
b
est
p
ar
am
eter
s
in
R
F,
DT
,
an
d
XGBo
o
s
t
m
u
lti
-
lab
el
m
o
d
els
C
l
a
s
si
f
i
e
r
H
y
p
e
r
p
a
r
a
me
t
e
r
M
u
l
t
i
-
l
a
b
e
l
m
o
d
e
l
C
l
a
s
si
f
i
e
r
c
h
a
i
n
B
i
n
a
r
y
r
e
l
e
v
a
n
c
e
La
b
e
l
p
o
w
e
r
se
t
RF
n
_
e
st
i
ma
t
o
r
s
50
25
25
max
_
d
e
p
t
h
n
o
n
e
n
o
n
e
n
o
n
e
mi
n
_
sa
mp
l
e
s
sp
l
i
t
2
2
10
max
_
f
e
a
t
u
r
e
s
sq
r
t
sq
r
t
n
o
n
e
max
_
l
e
a
f
_
n
o
d
e
s
3
3
6
c
l
a
ss
w
e
i
g
h
t
n
o
n
e
n
o
n
e
n
o
n
e
DT
max
_
f
e
a
t
u
r
e
s
sq
r
t
sq
r
t
sq
r
t
max
_
d
e
p
t
h
n
o
n
e
n
o
n
e
n
o
n
e
mi
n
_
sa
mp
l
e
s
_
l
e
a
f
5
5
4
X
G
B
o
o
st
max
_
d
e
p
t
h
5
5
5
mi
n
_
c
h
i
l
d
_
w
e
i
g
h
t
1
1
1
su
b
s
a
m
p
l
e
0
.
1
0
.
1
0
.
1
c
o
l
sam
p
l
e
_
b
y
t
r
e
e
1
1
1
g
a
mm
a
0
0
0
l
e
a
r
n
i
n
g
r
a
t
e
0
.
2
0
.
2
0
.
2
3
.
3
.
M
o
del
perf
o
rma
nce
ev
a
lua
t
io
n
T
h
e
b
est
p
ar
am
eter
s
o
b
tain
ed
ar
e
ap
p
lied
to
each
ty
p
e
of
m
u
lti
-
lab
el
m
o
d
el.
T
h
is
p
r
o
ce
s
s
is
to
en
s
u
r
e
o
p
tim
al
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
e
r
esu
lts
of
tr
ai
n
in
g
th
e
m
o
d
els
with
th
e
b
est
p
a
r
am
eter
s
ar
e
co
m
p
ar
ed
ac
r
o
s
s
th
e
b
o
ar
d
.
T
ab
le
2
s
h
o
ws
th
e
p
er
f
o
r
m
a
n
ce
v
alu
es
f
o
r
each
m
o
d
el
b
ased
on
th
e
p
r
ed
ef
i
n
ed
m
etr
ics.
B
ased
on
th
e
p
er
f
o
r
m
an
ce
of
m
o
d
el
tr
ain
i
n
g
as
s
h
o
wn
in
T
a
b
le
2
,
th
e
b
est
ac
cu
r
ac
y
was
f
o
u
n
d
in
t
h
e
RF
-
CC
m
o
d
el,
an
d
th
e
lo
west
ac
cu
r
ac
y
was
f
o
u
n
d
in
th
e
DT
-
CC
m
o
d
el.
T
h
e
p
r
ec
is
io
n
of
all
m
o
d
els
was
s
im
ilar
,
d
em
o
n
s
tr
atin
g
t
h
eir
ab
ilit
y
to
p
r
o
d
u
ce
lo
w
f
alse
-
p
o
s
itiv
es.
T
h
e
DT
-
BR
m
o
d
el
h
ad
th
e
h
ig
h
est
p
r
ec
is
io
n
,
in
d
icatin
g
th
at
it
h
ad
th
e
h
ig
h
est
p
r
o
b
a
b
ilit
y
of
co
r
r
ec
tly
p
r
ed
ictin
g
p
o
s
itiv
e
s
id
e
ef
f
ec
ts
(
s
id
e
ef
f
ec
ts
)
a
g
ain
s
t
ad
v
er
s
e
s
id
e
ef
f
ec
ts
(
s
id
e
ef
f
e
cts
do
not
o
cc
u
r
)
.
R
ec
all
in
d
icate
s
th
e
ca
p
ab
ilit
y
to
m
in
im
ize
p
o
s
itiv
e
lab
els
(
s
id
e
ef
f
ec
ts
)
th
at
ar
e
in
co
r
r
ec
tly
p
r
ed
icted
as
n
eg
ativ
e
la
b
els.
T
h
e
b
est
r
ec
all
was
f
o
u
n
d
in
th
e
RF
-
LP
m
o
d
el,
in
d
icatin
g
th
at
it
h
as
th
e
h
ig
h
est
p
r
o
b
ab
ilit
y
of
c
o
r
r
ec
tly
p
r
e
d
i
ctin
g
s
id
e
ef
f
ec
ts
by
m
ea
s
u
r
in
g
th
e
p
er
ce
n
tag
e
of
s
id
e
ef
f
ec
ts
th
at
o
cc
u
r
(
tr
u
e
-
p
o
s
itiv
es)
f
r
o
m
all
s
id
e
ef
f
ec
ts
th
at
o
cc
u
r
(
tr
u
e
p
o
s
itiv
es+f
alse
n
eg
ativ
es).
In
c
o
m
p
ar
is
o
n
,
th
e
XG
B
o
o
s
t
-
BR
m
o
d
el
h
ad
th
e
lo
west
r
ec
a
ll,
wh
ich
in
d
icate
s
th
at
it
h
as
a
r
ea
s
o
n
ab
ly
p
o
o
r
ab
ilit
y
to
p
r
ed
ict
co
m
p
ar
ed
with
th
e
o
t
h
er
m
o
d
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
8
9
9
-
2
9
0
8
2904
T
ab
le
2.
Mo
d
el
p
er
f
o
r
m
a
n
ce
with
b
est
p
ar
am
eter
s
M
u
l
t
i
-
l
a
b
e
l
mo
d
e
l
p
e
r
f
o
r
m
a
n
c
e
(
%)
M
u
l
t
i
-
l
a
b
e
l
C
l
a
s
si
f
i
e
r
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
s
c
o
r
e
H
a
mm
i
n
g
l
o
ss
CC
RF
7
4
.
4
6
7
2
.
1
7
8
7
.
6
4
7
9
.
1
4
8
4
.
0
3
2
5
.
5
3
DT
7
2
.
2
5
7
1
.
3
9
8
3
.
6
7
7
6
.
9
4
8
0
.
8
1
2
7
.
7
5
X
G
B
o
o
st
7
3
.
6
1
7
2
.
1
3
8
5
.
3
4
7
8
.
1
2
8
2
.
2
8
2
6
.
3
9
BR
RF
7
4
.
4
0
7
2
.
0
8
8
7
.
7
0
7
9
.
1
1
8
4
.
0
4
2
5
.
6
0
DT
7
3
.
9
6
7
3
.
1
1
8
3
.
7
7
7
8
.
0
5
8
1
.
3
8
2
6
.
0
4
X
G
B
o
o
st
7
2
.
7
0
7
2
.
3
2
8
2
.
2
4
7
6
.
8
9
7
9
.
9
9
2
7
.
3
0
LP
RF
7
4
.
1
2
7
0
.
8
9
9
0
.
3
0
7
9
.
4
1
8
5
.
6
0
2
5
.
8
8
DT
7
2
.
9
5
7
0
.
8
7
8
7
.
2
0
7
8
.
0
8
8
3
.
2
7
2
7
.
0
5
X
G
B
o
o
st
7
3
.
4
2
7
1
.
2
0
8
7
.
3
5
7
8
.
4
3
8
3
.
5
4
2
6
.
5
8
B
ased
on
th
e
p
er
f
o
r
m
an
ce
m
e
tr
ics,
th
e
RF
m
o
d
el
o
u
tp
e
r
f
o
r
m
ed
th
e
o
th
er
m
o
d
els
with
th
e
ex
ce
p
tio
n
of
p
r
ec
is
io
n
.
RF
h
ad
th
e
lo
we
s
t
p
r
ec
is
io
n
in
th
e
RF
-
LP
m
o
d
el
but
also
p
r
o
d
u
ce
d
th
e
h
ig
h
e
s
t
r
ec
all
am
o
n
g
th
e
o
th
er
m
o
d
els.
T
h
e
F1
-
s
co
r
e
is
u
s
ed
to
m
ea
s
u
r
e
th
e
m
o
d
el's
ab
ilit
y
,
wh
ich
co
m
b
in
es
p
r
e
cisi
o
n
an
d
r
ec
all
to
o
v
er
co
m
e
f
alse
-
p
o
s
itiv
es
an
d
f
alse
-
n
eg
ativ
es
[
2
6
]
.
T
h
e
b
est
F1
-
s
co
r
e
was
o
b
tain
ed
u
s
in
g
th
e
RF
-
LP
m
o
d
el.
T
h
is
s
tu
d
y
f
o
u
n
d
th
e
b
est
Ham
m
in
g
lo
s
s
in
RF
-
CC,
in
d
ica
tin
g
th
at
th
e
m
o
d
el
co
r
r
ec
tly
p
r
ed
icted
each
s
id
e
ef
f
ec
t
as
an
ac
tu
al
lab
el
[
2
7
]
.
In
p
r
ed
ictin
g
s
id
e
ef
f
ec
ts
,
lo
w
f
alse
-
n
eg
ativ
e
v
alu
es
ar
e
more
lik
ely
th
a
n
f
alse
-
p
o
s
itiv
e
v
alu
es;
th
er
ef
o
r
e,
th
e
m
etr
ic
u
s
es
β=2
to
g
iv
e
more
weig
h
t
to
r
ec
all
[
2
8
]
,
wh
er
e
th
e
m
o
d
el
is
co
n
ce
r
n
e
d
with
r
ed
u
cin
g
f
alse
-
n
eg
ativ
es
r
ath
er
th
an
f
alse
-
p
o
s
itiv
e
er
r
o
r
s
.
In
th
is
s
tu
d
y
,
th
e
b
est
v
alu
e
was
also
f
o
u
n
d
in
th
e
RF
-
LP
m
o
d
e
l,
wh
ich
m
ea
n
s
th
at
it
can
m
in
im
ize
f
alse
-
n
eg
ativ
e
v
alu
es.
T
h
e
b
est
ac
cu
r
ac
y
a
n
d
Ham
m
i
n
g
lo
s
s
wer
e
o
b
tain
ed
f
o
r
RF
-
CC.
T
h
e
b
est
p
r
ec
is
io
n
was
o
b
s
er
v
ed
f
o
r
DT
-
BR,
wh
er
ea
s
th
e
lo
west
p
r
ec
is
io
n
was
o
b
s
er
v
ed
f
o
r
DT
-
L
P.
T
h
e
b
est
r
ec
all,
F1
-
s
co
r
e,
an
d
wer
e
f
o
u
n
d
in
RF
-
L
P.
T
h
e
RF
m
o
d
el
wa
s
th
e
b
est
o
v
e
r
all
an
d
o
p
tim
al
b
ec
au
s
e
it
p
r
o
d
u
ce
d
t
h
e
b
es
t
ev
alu
atio
n
v
alu
e
am
o
n
g
th
e
m
o
d
els.
Fu
r
th
er
a
n
aly
s
is
was
co
n
d
u
cted
by
ev
alu
atin
g
th
e
r
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
O
C
)
cu
r
v
e
f
o
r
each
RF
m
o
d
el
illu
s
tr
ated
in
Fig
u
r
e
4
.
T
h
e
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC)
v
alu
es
f
r
o
m
th
e
R
OC
cu
r
v
e
of
each
RF
m
o
d
el
wer
e
n
o
t
s
ig
n
if
ican
tly
d
if
f
er
en
t,
an
d
all
th
r
ee
h
ad
s
co
r
es
>0
.
8
.
It
ca
n
be
co
n
clu
d
e
d
th
at
th
e
o
v
er
all
RF
m
u
lti
-
lab
el
m
o
d
el
s
ar
e
co
n
s
id
er
ed
g
o
o
d
or
ex
c
ellen
t
[
2
9
]
an
d
can
be
a
p
p
lie
d
f
o
r
f
u
r
th
er
A
TD
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
.
Fig
u
r
e
4.
R
OC
cu
r
v
e
of
m
u
lti
-
lab
el
R
F
m
o
d
el
3
.
4
.
P
re
dict
io
n
of
AT
D
s
ide
ef
f
ec
t
s
wit
h
RF
m
o
del
T
h
e
RF
m
u
lti
-
lab
el
m
o
d
el
was
u
s
ed
to
p
r
ed
ict
T
h
e
AT
D
s
id
e
ef
f
ec
ts
.
Pre
d
ictio
n
s
wer
e
p
er
f
o
r
m
ed
on
20%
of
th
e
test
d
ata
tak
en
f
r
o
m
th
e
to
tal
d
ataset.
T
h
is
test
d
ata
ev
alu
ated
th
e
m
o
d
el'
s
ab
ilit
y
to
r
ec
o
g
n
ize
AT
D
s
id
e
ef
f
ec
ts
.
T
h
e
m
o
d
el
p
r
ed
ictio
n
p
er
f
o
r
m
a
n
ce
r
e
s
u
lts
wer
e
th
o
r
o
u
g
h
ly
an
aly
z
ed
.
T
h
e
p
r
e
d
ictio
n
p
er
f
o
r
m
an
ce
s
ar
e
p
r
esen
ted
in
T
ab
le
3
to
illu
s
tr
ate
th
e
e
v
alu
a
tio
n
r
esu
lts
.
T
h
e
p
er
f
o
r
m
an
ce
of
th
e
AT
D
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
r
esu
lts
u
s
in
g
RF
-
CC
an
d
RF
-
BR
p
r
o
d
u
ce
d
th
e
s
am
e
v
alu
es
f
o
r
all
th
e
m
etr
ics
.
T
h
e
AT
D
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
r
esu
lts
of
th
e
RF
-
LP
wer
e
s
lig
h
tly
h
ig
h
er
th
an
th
o
s
e
of
th
e
o
th
er
RF
m
o
d
el
s
f
o
r
t
h
e
F1
-
s
co
r
e
,
r
ec
all,
an
d
F
β
m
etr
ics,
an
d
th
e
ac
cu
r
a
cy
,
p
r
ec
is
io
n
,
a
n
d
Ham
m
in
g
l
o
s
s
m
etr
ics
wer
e
s
lig
h
tly
lo
wer
th
an
th
o
s
e
of
th
e
o
th
er
RF
m
u
lti
-
lab
el
m
o
d
els.
T
h
e
p
er
f
o
r
m
an
ce
r
esu
lts
of
th
e
AT
D
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
in
th
e
m
u
lti
-
lab
el
RF
-
LP
te
s
tin
g
m
o
d
el
ar
e
s
im
ilar
to
th
o
s
e
of
th
e
p
r
ev
io
u
s
RF
-
LP
tr
ain
in
g
m
o
d
e
l,
wh
ich
ex
ce
ls
in
r
ec
all,
F1
-
s
c
o
r
e,
an
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f sid
e
effec
ts
o
f d
r
u
g
r
esis
ta
n
t tu
b
ercu
lo
s
is
d
r
u
g
s
u
s
in
g
mu
lti
-
la
b
el
…
(
S
iti S
y
a
h
id
a
tu
l H
elma
)
2905
T
ab
le
3.
Sid
e
ef
f
ec
t
p
r
e
d
ictio
n
p
er
f
o
r
m
an
ce
with
RF
m
u
lti
-
la
b
el
m
o
d
el
S
i
d
e
e
f
f
e
c
t
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
w
i
t
h
RF
m
u
l
t
i
-
l
a
b
e
l
m
o
d
e
l
M
u
l
t
i
-
l
a
b
e
l
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
S
c
o
r
e
(
%)
(
%)
H
a
mm
i
n
g
l
o
ss
(
%)
CC
7
3
.
4
9
7
1
.
5
9
8
6
.
3
0
7
8
.
2
6
8
2
.
9
0
2
6
.
5
2
BR
7
3
.
4
9
7
1
.
5
9
8
6
.
3
0
7
8
.
2
6
8
2
.
9
0
2
6
.
5
2
LP
7
2
.
9
8
7
0
.
0
0
8
9
.
5
0
7
8
.
5
6
8
4
.
7
8
2
7
.
0
2
3
.
5
.
Ana
ly
s
is
of
i
m
po
rt
a
nt
f
ea
t
ures
of
t
he
RF
m
ulti
-
la
bel
m
o
del
T
h
e
ess
en
tial
f
ea
tu
r
es
of
th
e
AT
D
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
m
o
d
el
wer
e
an
aly
ze
d
by
ap
p
ly
in
g
th
e
f
ea
tu
r
e_
im
p
o
r
tan
ce
_
f
u
n
ctio
n
in
th
e
RF
s
k
lear
n
p
ac
k
a
g
e
in
Py
th
o
n
.
In
th
e
AT
D
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
m
o
d
el,
f
ea
tu
r
e
an
aly
s
is
can
be
u
s
ed
to
d
eter
m
in
e
th
e
lev
el
of
im
p
o
r
tan
ce
or
in
f
lu
e
n
ce
of
f
ea
tu
r
es
(
AT
D
s
id
e
ef
f
ec
ts
)
.
Fig
u
r
e
5
s
h
o
ws
th
e
f
ea
tu
r
e
im
p
o
r
tan
ce
of
each
RF
m
u
lti
-
lab
el
m
o
d
el.
B
ased
on
th
e
av
er
ag
e
f
ea
tu
r
e
im
p
o
r
tan
ce
s
co
r
e
of
th
e
t
h
r
ee
RF
m
u
lti
-
lab
el
m
o
d
els,
eig
h
t
f
ea
tu
r
es
h
ad
th
e
h
ig
h
est
le
v
e
l
of
im
p
ac
t
with
an
av
er
ag
e
s
co
r
e
v
al
u
e
g
r
ea
ter
t
h
an
or
eq
u
al
to
0
.
1
,
n
am
ely
C
f
z
,
B
d
q
,
an
d
Km
with
a
s
co
r
e
of
0
.
2
,
as
well
as
L
f
x
,
Mf
x
,
L
zd
,
Cs,
an
d
E
with
an
av
er
ag
e
s
co
r
e
of
0
.
1
.
T
h
e
f
e
atu
r
es
th
at
h
av
e
a
lo
w
lev
el
of
im
p
ac
t
with
an
av
er
ag
e
s
co
r
e
b
elo
w
0
.
1
ar
e
H,
E
to
,
Dlm
,
Z,
PAS,
an
d
S.
Fig
u
r
e
5.
Featu
r
e
im
p
o
r
ta
n
ce
of
RF
m
u
lti
-
lab
el
m
o
d
el
B
ased
on
f
ea
tu
r
e
im
p
o
r
tan
t,
C
f
z,
B
d
q
,
Km
wer
e
d
r
u
g
s
th
at
h
av
e
th
e
h
ig
h
est
im
p
o
r
ta
n
t
s
co
r
e
in
th
e
RF
-
CC
an
d
RF
-
LP
m
o
d
el,
an
d
also
Lfx
in
RF
-
BR
m
o
d
el.
T
h
ese
f
in
d
in
g
s
wer
e
co
n
s
is
ten
t
with
th
e
f
in
d
in
g
th
at
C
f
z
ca
u
s
es
s
k
in
d
is
co
lo
r
atio
n
a
n
d
g
astro
in
test
in
al
d
i
s
o
r
d
er
s
[
3
0
]
,
[
3
1
]
.
B
d
q
is
as
s
o
ciate
d
with
QT
c
in
ter
v
al
p
r
o
l
o
n
g
atio
n
in
ca
r
d
io
v
ascu
lar
[
3
2
]
,
n
eu
r
o
l
o
g
ical
a
n
d
g
astro
in
test
in
al
d
is
o
r
d
e
r
s
[
3
3
]
.
An
o
th
er
s
ev
er
e
s
id
e
ef
f
ec
t
is
o
to
to
x
icity
ca
u
s
ed
by
Km
,
wh
ich
co
u
ld
lead
to
h
ea
r
in
g
lo
s
s
.
In
th
is
s
tu
d
y
,
km
also
h
ad
h
ig
h
f
ea
tu
r
e
im
p
o
r
ta
n
ce
;
ev
en
in
th
e
n
ew
g
u
id
elin
es,
th
is
d
r
u
g
was
no
lo
n
g
er
u
s
ed
[
3
4
]
.
L
o
n
g
-
ter
m
Lfx
tr
ea
tm
en
t
h
as
m
an
y
s
id
e
e
f
f
ec
ts
,
in
clu
d
in
g
p
ar
al
y
s
is
in
v
o
lv
in
g
ten
d
o
n
s
,
m
u
s
cles,
jo
in
ts
,
n
er
v
es,
a
n
d
n
e
u
r
o
p
s
y
ch
iatr
ic
d
is
o
r
d
er
s
,
h
e
p
ato
to
x
icity
an
d
ca
r
d
io
v
ascu
lar
d
is
o
r
d
er
s
th
r
o
u
g
h
QT
c
p
r
o
lo
n
g
atio
n
,
an
d
p
h
o
to
t
o
x
ic
r
ea
ctio
n
s
s
u
ch
as
s
k
in
r
ed
n
ess
an
d
s
ev
er
e
b
u
llo
u
s
er
u
p
tio
n
s
[
3
5
]
,
[
3
6
]
.
Mf
x
can
ca
u
s
e
v
is
u
al
d
is
tu
r
b
a
n
ce
s
in
t
h
e
f
o
r
m
of
u
v
eitis
(
in
f
lam
m
atio
n
of
th
e
u
v
ea
l
lay
er
)
[
3
7
]
,
liv
er
d
is
o
r
d
er
s
s
u
ch
as
ac
u
te
liv
er
f
ailu
r
e
(
ac
u
te
liv
er
in
ju
r
y
)
De
s
c
r
ipt
ion:
C
f
z
=
C
lof
a
z
im
ine
;
B
dq
=
B
e
da
quil
ine
;
K
m
=
Ka
na
mycin
;
L
f
x
=
L
e
vo
f
loxac
in
;
M
f
x
=
M
oxif
loxac
in
;
L
z
d
=
li
ne
z
oli
d;
C
s
=
C
yc
l
os
e
r
ine
;
E
=
E
thamb
utol
;
H
=
I
s
oniaz
id
;
E
to
=
E
thi
ona
mi
de
;
Dl
m
=
De
lama
nid
;
Z
=
P
yr
a
z
i
na
mi
de
;
P
a
s
=
P
-
Am
inos
a
li
c
yli
c
Ac
id
;
a
nd
S
=
S
tr
e
pt
omycin
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
8
9
9
-
2
9
0
8
2906
[
3
8
]
,
an
d
m
etab
o
lic
d
is
o
r
d
er
s
s
u
ch
as
h
y
p
o
g
l
y
ce
m
ia
an
d
h
y
p
er
g
ly
ce
m
ia
[
3
5
]
.
Sin
ce
th
e
t
r
ea
tm
en
t
of
DR
-
TB
m
u
s
t
co
n
s
is
t
of
f
o
u
r
to
f
iv
e
d
r
u
g
s
,
all
s
id
e
ef
f
ec
ts
co
u
ld
o
cc
u
r
due
to
d
r
u
g
-
d
r
u
g
in
ter
ac
tio
n
s
(
DDI
)
an
d
can
be
a
n
aly
ze
d
well
u
s
in
g
th
e
RF
m
o
d
el.
In
t
h
i
s
s
t
u
d
y
,
we
f
o
u
n
d
t
h
at
Mf
x
,
L
z
d
,
C
s
,
H,
E,
E
t
o
,
D
l
m
,
Z,
P
AS
,
a
n
d
S
w
e
r
e
e
q
u
a
l
to
or
lo
w
e
r
t
h
an
0
.
1
,
e
v
e
n
t
h
o
u
g
h
m
a
n
y
s
t
u
d
i
es
f
o
u
n
d
t
h
a
t
a
ll
t
h
es
e
d
r
u
g
s
h
a
d
a
r
is
k
of
s
o
m
e
s
i
d
e
e
f
f
e
c
ts
.
T
h
e
r
e
f
o
r
e
,
we
can
c
o
n
s
i
d
e
r
t
h
e
m
an
a
lt
e
r
n
a
t
i
v
e
wh
e
n
d
e
s
i
g
n
i
n
g
a
r
e
g
i
m
e
n
to
r
e
d
u
c
e
s
i
d
e
e
f
f
e
ct
s
[
3
9
]
.
F
o
r
e
x
a
m
p
l
e
,
D
l
m
can
c
a
u
s
e
Q
T
c
i
n
t
e
r
v
al
p
r
o
l
o
n
g
a
t
i
o
n
,
an
o
r
e
x
i
a
,
m
a
l
a
is
e
,
g
as
t
r
i
ti
s
or
g
a
s
t
r
i
c
u
l
c
e
r
,
a
n
e
m
i
a
,
a
n
d
p
s
y
c
h
i
a
t
r
i
c
d
is
o
r
d
e
r
s
.
H
o
w
e
v
e
r
,
t
h
i
s
s
t
u
d
y
f
o
u
n
d
t
h
a
t
D
l
m
h
a
d
a
l
o
w
-
f
e
a
t
u
r
e
i
m
p
o
r
t
a
n
t
s
c
o
r
e
.
R
e
g
a
r
d
i
n
g
t
h
e
e
f
f
i
c
a
c
y
of
D
l
m
,
we
s
h
o
u
l
d
c
o
n
s
i
d
e
r
u
s
i
n
g
t
h
is
d
r
u
g
as
an
a
l
t
e
r
n
a
ti
v
e
to
a
v
o
i
d
s
ev
e
r
e
or
m
u
l
t
i
p
l
e
s
i
d
e
e
f
f
ec
ts
of
t
h
e
r
e
g
i
m
e
n
.
S
i
n
ce
s
i
d
e
e
f
f
e
c
ts
can
a
ls
o
a
r
is
e
due
to
D
D
I
,
we
h
a
d
to
c
o
n
s
i
d
e
r
u
s
in
g
t
h
e
s
e
p
r
e
d
i
c
ti
o
n
m
o
d
e
l
s
s
i
n
c
e
t
h
e
RF
al
g
o
r
i
t
h
m
c
o
u
l
d
s
i
m
u
l
a
t
e
t
h
e
d
r
u
g
i
n
t
e
r
a
c
t
i
o
n
p
r
o
c
e
s
s
.
T
h
e
l
i
m
i
t
a
ti
o
n
of
t
h
i
s
s
t
u
d
y
was
t
h
a
t
we
d
i
d
not
a
n
a
l
y
z
e
a
n
y
d
e
m
o
g
r
a
p
h
i
c
,
c
l
i
n
i
c
a
l
,
a
n
d
c
o
m
o
r
b
i
d
i
t
y
t
h
a
t
m
i
g
h
t
i
n
f
l
u
e
n
ce
s
i
d
e
e
f
f
e
c
ts
.
F
u
t
u
r
e
r
es
e
a
r
ch
e
n
d
e
a
v
o
r
s
c
o
u
l
d
i
n
c
o
r
p
o
r
a
t
e
a
more
n
u
a
n
c
e
d
e
x
a
m
i
n
a
t
i
o
n
of
t
h
es
e
d
e
m
o
g
r
a
p
h
ic
a
n
d
c
l
i
n
i
ca
l
f
a
ct
o
r
s
,
al
l
o
w
i
n
g
f
o
r
a
more
h
o
l
i
s
t
i
c
u
n
d
e
r
s
t
a
n
d
i
n
g
of
t
h
e
i
n
t
e
r
p
l
a
y
b
e
t
w
e
e
n
v
a
r
i
o
u
s
v
a
r
i
a
b
l
es
a
n
d
t
h
e
i
r
p
o
t
e
n
t
i
al
i
m
p
a
c
t
on
s
i
d
e
ef
f
e
c
t
s
.
4.
CO
NCLU
SI
O
N
Mo
n
ito
r
in
g
an
d
ea
r
ly
id
en
tifi
ca
tio
n
of
th
e
ad
v
er
s
e
ef
f
ec
ts
of
DR
-
TB
d
r
u
g
s
ar
e
ess
en
tial
to
s
u
p
p
o
r
t
th
e
s
u
cc
ess
f
u
l
tr
ea
tm
en
t
of
DR
-
T
B
.
We
cr
ea
ted
AT
D
s
id
e
ef
f
ec
t
p
r
ed
ictio
n
m
o
d
els
u
s
in
g
tr
ee
-
b
ased
lear
n
in
g
alg
o
r
ith
m
s
,
wh
er
e
each
g
i
v
en
d
r
u
g
r
e
p
r
esen
ts
a
f
ea
tu
r
e,
an
d
each
s
id
e
ef
f
ec
t
m
ea
n
s
a
lab
el.
RF
m
u
lti
-
lab
el
alg
o
r
ith
m
s
with
p
r
o
b
lem
tr
an
s
f
o
r
m
atio
n
m
eth
o
d
s
ar
e
s
u
itab
l
e
p
o
ten
tial
m
o
d
els
f
o
r
p
r
ed
ictin
g
th
e
s
id
e
ef
f
ec
ts
of
AT
D
f
o
r
DR
-
TB
co
m
p
ar
ed
with
DT
an
d
XGBo
o
s
t,
w
i
th
o
u
tp
er
f
o
r
m
ed
p
e
r
f
o
r
m
an
ce
m
etr
ics
an
d
h
ig
h
AUC.
B
a
s
ed
on
f
ea
tu
r
e
im
p
o
r
tan
ce
,
C
f
z,
Km
,
B
d
q
,
a
n
d
L
f
x
h
ad
a
h
ig
h
er
r
is
k
f
o
r
m
u
ltip
le
s
id
e
ef
f
ec
ts
s
u
ch
as
g
astro
in
test
in
al,
n
eu
r
o
p
s
y
ch
ia
tr
ic,
ca
r
d
io
v
ascu
lar
,
m
u
s
cu
lo
s
k
eleta
l
,
an
d
o
th
er
s
.
Pre
d
ict
in
g
m
u
ltip
le
s
id
e
ef
f
ec
ts
u
s
in
g
a
m
u
lti
-
lab
el
RF
alg
o
r
ith
m
m
o
d
el
is
ess
en
tial
wh
en
d
esig
n
in
g
a
tr
ea
tm
en
t
r
eg
im
en
f
o
r
DR
-
TB
f
o
r
b
etter
p
atien
t
m
an
a
g
em
en
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
ed
b
y
th
e
Dir
ec
to
r
ate
o
f
Hig
h
er
E
d
u
ca
tio
n
,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
,
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
C
u
ltu
r
e,
R
esear
ch
,
an
d
T
ec
h
n
o
lo
g
y
b
y
th
e
co
n
tr
ac
t
f
o
r
th
e
I
m
p
lem
en
tatio
n
o
f
th
e
R
esear
ch
Pro
g
r
am
Yea
r
2
0
2
3
(
No
: 1
8
9
3
5
/I
T
3
.
D1
0
/PT.
0
1
.
0
3
/P/
B
/2
0
2
3
)
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS
ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
of
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Sit
i Sy
ah
id
atu
l H
elm
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
W
is
n
u
An
an
ta
Ku
s
u
m
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mu
s
h
th
o
f
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Diah
Han
d
ay
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
OF
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
t
h
at
th
er
e
ar
e
n
o
co
n
f
licts
o
f
in
ter
est
with
r
esp
ec
t
to
th
e
r
esear
ch
,
au
th
o
r
s
h
ip
,
an
d
p
u
b
licatio
n
o
f
th
is
ar
ticle
.
E
T
H
I
CAL
AP
P
RO
V
AL
T
h
is
s
tu
d
y
h
as
ca
r
ef
u
lly
r
e
v
iewe
d
an
d
ap
p
r
o
v
ed
b
y
t
h
e
E
th
ics
C
o
m
m
ittee
o
f
th
e
Facu
lty
o
f
Me
d
icin
e,
Un
iv
er
s
ity
o
f
I
n
d
o
n
esia (
Acta
No
: K
E
T
-
1
3
2
6
/UN
2
/F1
/ET
I
K/PP
M.
0
0
.
0
2
/2
0
2
2
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
P
r
ed
ictio
n
o
f sid
e
effec
ts
o
f d
r
u
g
r
esis
ta
n
t tu
b
ercu
lo
s
is
d
r
u
g
s
u
s
in
g
mu
lti
-
la
b
el
…
(
S
iti S
y
a
h
id
a
tu
l H
elma
)
2907
DATA
AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
is
s
tu
d
y
'
s
f
in
d
in
g
s
wer
e
o
b
tain
ed
f
r
o
m
th
e
Na
tio
n
al
T
u
b
er
cu
lo
s
i
s
R
eg
is
tr
y
u
n
d
er
th
e
a
u
th
o
r
ity
o
f
C
en
tr
al
Frie
n
d
s
h
ip
Gen
er
al
Ho
s
p
ital
an
d
wer
e
m
ad
e
av
ailab
le
ex
clu
s
iv
ely
f
o
r
th
is
r
esear
ch
.
An
y
f
u
r
th
er
u
s
e
o
f
th
e
d
ata
r
eq
u
ir
es
p
r
io
r
ap
p
r
o
v
al
f
r
o
m
t
h
e
Natio
n
al
T
u
b
er
cu
lo
s
is
Pro
g
r
am
,
Min
is
tr
y
o
f
Hea
lth
,
R
ep
u
b
lic
o
f
I
n
d
o
n
esia.
RE
F
E
R
E
NC
E
S
[
1
]
W
H
O
,
“
G
l
o
b
a
l
t
u
b
e
r
c
u
l
o
s
i
s
r
e
p
o
r
t
2
0
2
3
,
”
W
o
r
l
d
H
e
a
l
t
h
O
rg
a
n
i
z
a
t
i
o
n
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
i
r
i
s.wh
o
.
i
n
t
/
b
i
t
s
t
r
e
a
m
/
h
a
n
d
l
e
/
1
0
6
6
5
/
3
7
3
8
2
8
/
9
7
8
9
2
4
0
0
8
3
8
5
1
-
e
n
g
.
p
d
f
?
seq
u
e
n
c
e
=
1
[
2
]
Z.
Zh
u
a
n
g
e
t
a
l
.
,
“
Tr
e
n
d
s
a
n
d
c
h
a
l
l
e
n
g
e
s
o
f
m
u
l
t
i
-
d
r
u
g
r
e
si
s
t
a
n
c
e
i
n
c
h
i
l
d
h
o
o
d
t
u
b
e
r
c
u
l
o
si
s,”
Fr
o
n
t
i
e
rs
i
n
C
e
l
l
u
l
a
r
a
n
d
I
n
f
e
c
t
i
o
n
Mi
c
r
o
b
i
o
l
o
g
y
,
v
o
l
.
1
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
c
i
m
b
.
2
0
2
3
.
1
1
8
3
5
9
0
.
[
3
]
R
.
S
i
n
g
h
,
S
.
P
.
D
w
i
v
e
d
i
,
U
.
S
.
G
a
h
a
r
w
a
r
,
R
.
M
e
e
n
a
,
P
.
R
a
j
a
m
a
n
i
,
a
n
d
T.
P
r
a
sa
d
,
“
R
e
c
e
n
t
u
p
d
a
t
e
s
o
n
d
r
u
g
r
e
s
i
st
a
n
c
e
i
n
M
y
c
o
b
a
c
t
e
r
i
u
m
t
u
b
e
r
c
u
l
o
si
s,
”
J
o
u
r
n
a
l
o
f
Ap
p
l
i
e
d
Mi
c
ro
b
i
o
l
o
g
y
,
v
o
l
.
1
2
8
,
n
o
.
6
,
p
p
.
1
5
4
7
–
1
5
6
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
1
1
/
j
a
m.
1
4
4
7
8
.
[
4
]
N
.
D
o
o
k
i
e
,
S
.
R
a
m
b
a
r
a
n
,
N
.
P
a
d
a
y
a
t
c
h
i
,
S
.
M
a
h
o
m
e
d
,
a
n
d
K
.
N
a
i
d
o
o
,
“
E
v
o
l
u
t
i
o
n
o
f
d
r
u
g
r
e
s
i
st
a
n
c
e
i
n
M
y
c
o
b
a
c
t
e
r
i
u
m
t
u
b
e
r
c
u
l
o
s
i
s:
a
r
e
v
i
e
w
o
n
t
h
e
m
o
l
e
c
u
l
a
r
d
e
t
e
r
m
i
n
a
n
t
s
o
f
r
e
si
s
t
a
n
c
e
a
n
d
i
m
p
l
i
c
a
t
i
o
n
s
f
o
r
p
e
r
s
o
n
a
l
i
z
e
d
c
a
r
e
,
”
J
o
u
r
n
a
l
o
f
An
t
i
m
i
c
ro
b
i
a
l
C
h
e
m
o
t
h
e
ra
p
y
,
v
o
l
.
7
3
,
n
o
.
5
,
p
p
.
1
1
3
8
–
1
1
5
1
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
9
3
/
j
a
c
/
d
k
x
5
0
6
.
[
5
]
T.
W
.
Y
a
n
g
e
t
a
l
.
,
“
S
i
d
e
e
f
f
e
c
t
s
a
ss
o
c
i
a
t
e
d
w
i
t
h
t
h
e
t
r
e
a
t
me
n
t
o
f
mu
l
t
i
d
r
u
g
-
r
e
si
st
a
n
t
t
u
b
e
r
c
u
l
o
si
s
a
t
a
t
u
b
e
r
c
u
l
o
si
s
r
e
f
e
r
r
a
l
h
o
s
p
i
t
a
l
i
n
S
o
u
t
h
K
o
r
e
a
,
”
Me
d
i
c
i
n
e
,
v
o
l
.
9
6
,
n
o
.
2
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
9
7
/
M
D
.
0
0
0
0
0
0
0
0
0
0
0
0
7
4
8
2
.
[
6
]
T.
T
ö
r
ü
n
e
t
a
l
.
,
“
S
i
d
e
e
f
f
e
c
t
s
a
ss
o
c
i
a
t
e
d
w
i
t
h
t
h
e
t
r
e
a
t
m
e
n
t
o
f
mu
l
t
i
d
r
u
g
-
r
e
s
i
st
a
n
t
t
u
b
e
r
c
u
l
o
s
i
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
T
u
b
e
rc
u
l
o
si
s
a
n
d
L
u
n
g
D
i
se
a
se
,
v
o
l
.
9
,
n
o
.
1
2
,
p
p
.
1
3
7
3
–
1
3
7
7
,
2
0
0
5
.
[
7
]
X
.
Z
h
a
o
,
L.
C
h
e
n
,
a
n
d
J.
L
u
,
“
A
s
i
mi
l
a
r
i
t
y
-
b
a
se
d
me
t
h
o
d
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
d
r
u
g
s
i
d
e
e
f
f
e
c
t
s
w
i
t
h
h
e
t
e
r
o
g
e
n
e
o
u
s
i
n
f
o
r
mat
i
o
n
,
”
Ma
t
h
e
m
a
t
i
c
a
l
B
i
o
s
c
i
e
n
c
e
s
,
v
o
l
.
3
0
6
,
p
p
.
1
3
6
–
1
4
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
b
s.
2
0
1
8
.
0
9
.
0
1
0
.
[
8
]
W
.
Z
h
a
n
g
,
F
.
L
i
u
,
L
.
L
u
o
,
a
n
d
J.
Z
h
a
n
g
,
“
P
r
e
d
i
c
t
i
n
g
d
r
u
g
s
i
d
e
e
f
f
e
c
t
s
b
y
m
u
l
t
i
-
l
a
b
e
l
l
e
a
r
n
i
n
g
a
n
d
e
n
sem
b
l
e
l
e
a
r
n
i
n
g
,
”
BM
C
Bi
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
6
,
n
o
.
1
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
8
5
9
-
0
1
5
-
0
7
7
4
-
y.
[
9
]
O
.
C
.
U
n
e
r
,
H
.
I
.
K
u
r
u
,
R
.
G
.
C
i
n
b
i
s,
O
.
Ta
s
t
a
n
,
a
n
d
A
.
E.
C
i
c
e
k
,
“
D
e
e
p
S
i
d
e
:
a
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
r
u
g
si
d
e
e
f
f
e
c
t
p
r
e
d
i
c
t
i
o
n
,
”
I
E
EE/
AC
M
T
r
a
n
sa
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
Bi
o
l
o
g
y
a
n
d
B
i
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
0
,
n
o
.
1
,
p
p
.
3
3
0
–
3
3
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
B
B
.
2
0
2
2
.
3
1
4
1
1
0
3
.
[
1
0
]
S
.
K
o
u
c
h
a
k
i
e
t
a
l
.
,
“
M
u
l
t
i
-
l
a
b
e
l
r
a
n
d
o
m
f
o
r
e
s
t
mo
d
e
l
f
o
r
t
u
b
e
r
c
u
l
o
s
i
s
d
r
u
g
r
e
si
s
t
a
n
c
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
m
u
t
a
t
i
o
n
r
a
n
k
i
n
g
,
”
Fro
n
t
i
e
rs
i
n
M
i
c
r
o
b
i
o
l
o
g
y
,
v
o
l
.
1
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
m
i
c
b
.
2
0
2
0
.
0
0
6
6
7
.
[
1
1
]
M
.
C
.
E.
S
i
mse
k
l
e
r
,
N
.
H
.
A
l
h
a
s
h
mi
,
E.
A
z
a
r
,
N
.
K
i
n
g
,
R
.
A
.
M
.
A
.
L
u
q
ma
n
,
a
n
d
A
.
A
l
M
u
l
l
a
,
“
Ex
p
l
o
r
i
n
g
d
r
i
v
e
r
s
o
f
p
a
t
i
e
n
t
sat
i
sf
a
c
t
i
o
n
u
si
n
g
a
r
a
n
d
o
m
f
o
r
e
s
t
a
l
g
o
r
i
t
h
m,
”
B
MC
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
D
e
c
i
si
o
n
M
a
k
i
n
g
,
v
o
l
.
2
1
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
1
-
0
2
1
-
0
1
5
1
9
-
5.
[
1
2
]
T.
B
a
r
t
z
-
B
e
i
e
l
st
e
i
n
a
n
d
S
.
M
a
r
k
o
n
,
“
Tu
n
i
n
g
se
a
r
c
h
a
l
g
o
r
i
t
h
ms
f
o
r
r
e
a
l
-
w
o
r
l
d
a
p
p
l
i
c
a
t
i
o
n
s
:
a
r
e
g
r
e
ss
i
o
n
t
r
e
e
b
a
s
e
d
a
p
p
r
o
a
c
h
,
”
i
n
2
0
0
4
C
o
n
g
ress
o
n
E
v
o
l
u
t
i
o
n
a
ry
C
o
m
p
u
t
a
t
i
o
n
,
C
E
C
2
0
0
4
,
2
0
0
4
,
v
o
l
.
1
,
p
p
.
1
1
1
1
–
1
1
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
c
e
c
.
2
0
0
4
.
1
3
3
0
9
8
6
.
[
1
3
]
S
.
R
e
d
k
a
r
,
S
.
M
o
n
d
a
l
,
A
.
J
o
se
p
h
,
a
n
d
K
.
S
.
H
a
r
e
e
s
h
a
,
“
A
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
d
r
u
g
-
t
a
r
g
e
t
i
n
t
e
r
a
c
t
i
o
n
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
w
r
a
p
p
e
r
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
c
l
a
ss
b
a
l
a
n
c
i
n
g
,
”
M
o
l
e
c
u
l
a
r I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
3
9
,
n
o
.
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
m
i
n
f
.
2
0
1
9
0
0
0
6
2
.
[
1
4
]
X.
W
u
,
Y
.
G
a
o
,
a
n
d
D
.
Ji
a
o
,
“
M
u
l
t
i
-
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
a
se
d
o
n
r
a
n
d
o
m
f
o
r
e
s
t
a
l
g
o
r
i
t
h
m
f
o
r
n
o
n
-
i
n
t
r
u
si
v
e
l
o
a
d
m
o
n
i
t
o
r
i
n
g
sy
st
e
m,
”
Pr
o
c
e
sses
,
v
o
l
.
7
,
n
o
.
6
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
7
0
6
0
3
3
7
.
[
1
5
]
M
.
A
r
sl
a
n
a
n
d
C
.
C
r
u
z
,
“
I
mb
a
l
a
n
c
e
d
m
u
l
t
i
-
l
a
b
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
b
u
s
i
n
e
ss
-
r
e
l
a
t
e
d
t
e
x
t
w
i
t
h
m
o
d
e
r
a
t
e
l
y
l
a
r
g
e
l
a
b
e
l
s
p
a
c
e
s,
”
a
r
X
iv
-
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
p
p
.
1
–
9
,
2
0
2
3
.
[
1
6
]
Q
.
W
u
,
H
.
W
a
n
g
,
X
.
Y
a
n
,
a
n
d
X
.
Li
u
,
“
M
a
p
R
e
d
u
c
e
-
b
a
se
d
a
d
a
p
t
i
v
e
r
a
n
d
o
m
f
o
r
e
st
a
l
g
o
r
i
t
h
m
f
o
r
m
u
l
t
i
-
l
a
b
e
l
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
1
,
n
o
.
1
2
,
p
p
.
8
2
3
9
–
8
2
5
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
1
8
-
3
9
0
0
-
8.
[
1
7
]
H
.
W
a
n
g
,
Y
.
D
i
n
g
,
J.
Ta
n
g
,
Q
.
Z
o
u
,
a
n
d
F
.
G
u
o
,
“
I
d
e
n
t
i
f
y
R
N
A
-
a
sso
c
i
a
t
e
d
su
b
c
e
l
l
u
l
a
r
l
o
c
a
l
i
z
a
t
i
o
n
s b
a
s
e
d
o
n
mu
l
t
i
-
l
a
b
e
l
l
e
a
r
n
i
n
g
u
si
n
g
C
h
o
u
’
s
5
-
s
t
e
p
s ru
l
e
,
”
BM
C
G
e
n
o
m
i
c
s
,
v
o
l
.
2
2
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
6
4
-
0
2
0
-
0
7
3
4
7
-
7.
[
1
8
]
N
.
S
a
i
n
i
,
“
M
u
l
t
i
-
l
a
b
e
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
o
d
e
t
e
c
t
a
i
r
t
r
a
f
f
i
c
c
o
n
t
r
o
l
l
e
r
s’
d
r
o
w
si
n
e
ss
u
si
n
g
f
a
c
i
a
l
f
e
a
t
u
r
e
s,
”
M
.
Sc
.
Re
s
e
a
r
c
h
Pro
j
e
c
t
,
S
c
h
o
o
l
o
f
C
o
mp
u
t
i
n
g
,
N
a
t
i
o
n
a
l
C
o
l
l
e
g
e
o
f
I
r
e
l
a
n
d
,
D
u
b
l
i
n
,
I
r
e
l
a
n
d
,
2
0
1
9
.
[
1
9
]
X
.
Z
h
a
n
g
,
H
.
Zh
a
o
,
S
.
Zh
a
n
g
,
a
n
d
R
.
Li
,
“
A
n
o
v
e
l
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
f
o
r
m
u
l
t
i
-
l
a
b
e
l
c
h
r
o
n
i
c
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
,
”
Fro
n
t
i
e
rs
i
n
G
e
n
e
t
i
c
s
,
v
o
l
.
1
0
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
8
9
/
f
g
e
n
e
.
2
0
1
9
.
0
0
3
5
1
.
[
2
0
]
M.
S.
S
o
r
o
w
e
r
,
“
A
l
i
t
e
r
a
t
u
r
e
s
u
r
v
e
y
o
n
a
l
g
o
r
i
t
h
ms f
o
r
m
u
l
t
i
-
l
a
b
e
l
l
e
a
r
n
i
n
g
,
”
Re
se
a
r
c
h
G
a
t
e
,
p
p
.
1
–
2
5
,
2
0
1
0
.
[
2
1
]
K
.
B
.
L
i
n
,
W
.
W
e
n
g
,
R
.
K
.
L
a
i
,
a
n
d
P
.
L
u
,
“
I
m
b
a
l
a
n
c
e
d
a
t
a
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
S
V
M
a
n
d
c
l
u
s
t
e
r
i
n
g
f
u
n
c
t
i
o
n
,
”
i
n
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
d
u
c
a
t
i
o
n
,
I
C
C
C
S
E
2
0
1
4
,
2
0
1
4
,
p
p
.
5
4
4
–
5
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
S
E
.
2
0
1
4
.
6
9
2
6
5
2
1
.
[
2
2
]
H
.
A
l
a
i
z
-
M
o
r
e
t
o
n
,
J
.
A
v
e
l
e
i
r
a
-
M
a
t
a
,
J
.
O
n
d
i
c
o
l
-
G
a
r
c
i
a
,
A
.
L
.
M
u
ñ
o
z
-
C
a
s
t
a
ñ
e
d
a
,
I
.
G
a
r
c
í
a
,
a
n
d
C
.
B
e
n
a
v
i
d
e
s
,
“
M
u
l
t
i
c
l
a
s
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
r
o
c
e
d
u
r
e
f
o
r
d
e
t
e
c
t
i
n
g
a
t
t
a
c
k
s
o
n
M
Q
T
T
-
I
o
T
p
r
o
t
o
c
o
l
,
”
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
2
0
1
9
,
n
o
.
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
9
/
6
5
1
6
2
5
3
.
[
2
3
]
T.
Ü
st
ü
n
k
ö
k
a
n
d
M
.
K
a
r
a
k
a
y
a
,
“
S
S
-
M
LA
:
a
sem
i
s
u
p
e
r
v
i
se
d
me
t
h
o
d
f
o
r
mu
l
t
i
-
l
a
b
e
l
a
n
n
o
t
a
t
i
o
n
o
f
r
e
m
o
t
e
l
y
sen
s
e
d
i
ma
g
e
s,”
J
o
u
rn
a
l
o
f
Ap
p
l
i
e
d
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
5
,
n
o
.
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
1
7
/
1
.
j
r
s.
1
5
.
0
3
6
5
0
9
.
[
2
4
]
J.
D
u
a
n
,
X
.
Li
,
a
n
d
D
.
M
u
,
“
L
e
a
r
n
i
n
g
mu
l
t
i
l
a
b
e
l
s fr
o
m si
n
g
l
e
l
a
b
e
l
-
a
n
e
x
t
r
e
me
w
e
a
k
l
a
b
e
l
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
,
”
W
u
h
a
n
U
n
i
v
e
r
si
t
y
J
o
u
rn
a
l
o
f
N
a
t
u
ra
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
1
6
1
–
1
6
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
8
5
9
-
0
1
9
-
1
3
8
1
-
y.
[
2
5
]
H
.
A
l
sa
g
r
i
a
n
d
M
.
Y
k
h
l
e
f
,
“
Q
u
a
n
t
i
f
y
i
n
g
f
e
a
t
u
r
e
i
m
p
o
r
t
a
n
c
e
f
o
r
d
e
t
e
c
t
i
n
g
d
e
p
r
e
ss
i
o
n
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
6
2
8
–
6
3
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
0
.
0
1
1
0
5
7
7
.
[
2
6
]
D
.
D
e
C
l
e
r
c
q
,
N
.
F
.
D
i
o
p
,
D
.
J
a
i
n
,
B
.
Ta
n
,
a
n
d
Z
.
W
e
n
,
“
M
u
l
t
i
-
l
a
b
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
i
n
t
e
r
a
c
t
i
v
e
N
LP
-
b
a
se
d
v
i
su
a
l
i
z
a
t
i
o
n
o
f
e
l
e
c
t
r
i
c
v
e
h
i
c
l
e
p
a
t
e
n
t
d
a
t
a
,
”
W
o
rl
d
P
a
t
e
n
t
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
5
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
w
p
i
.
2
0
1
9
.
1
0
1
9
0
3
.
[
2
7
]
M
.
R
.
C
h
o
i
r
u
l
f
i
k
r
i
,
K
.
M
.
L
h
a
k
sam
a
n
a
,
a
n
d
S
.
A
l
F
a
r
a
b
y
,
“
A
mu
l
t
i
-
l
a
b
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
A
l
-
Q
u
r
a
n
v
e
r
ses
u
si
n
g
e
n
s
e
mb
l
e
met
h
o
d
a
n
d
n
a
ï
v
e
B
a
y
e
s
,
”
B
u
i
l
d
i
n
g
o
f
I
n
f
o
rm
a
t
i
c
s,
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
i
e
n
c
e
(
BI
T
S
)
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
4
7
3
–
4
7
9
,
2
0
2
2
,
d
o
i
:
1
0
.
4
7
0
6
5
/
b
i
t
s.
v
3
i
4
.
1
2
8
7
.
[
2
8
]
M
.
A
.
W
a
n
i
,
N
.
A
g
a
r
w
a
l
,
a
n
d
P
.
B
o
u
r
s,
“
S
e
x
u
a
l
-
p
r
e
d
a
t
o
r
d
e
t
e
c
t
i
o
n
sy
s
t
e
m
b
a
se
d
o
n
s
o
c
i
a
l
b
e
h
a
v
i
o
r
b
i
o
me
t
r
i
c
(
S
S
B
)
f
e
a
t
u
r
e
s,
”
Pro
c
e
d
i
a
C
I
RP
,
v
o
l
.
1
8
9
,
p
p
.
1
1
6
–
1
2
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
1
.
0
5
.
0
7
5
.
[
2
9
]
A
.
I
st
o
mi
n
,
A
.
M
a
sarw
a
h
,
R
.
V
a
n
n
i
n
e
n
,
H
.
O
k
u
m
a
,
a
n
d
M
.
S
u
d
a
h
,
“
D
i
a
g
n
o
st
i
c
p
e
r
f
o
r
ma
n
c
e
o
f
t
h
e
K
a
i
ser s
c
o
r
e
f
o
r
c
h
a
r
a
c
t
e
r
i
z
i
n
g
l
e
si
o
n
s
o
n
b
r
e
a
st
M
R
I
w
i
t
h
c
o
m
p
a
r
i
so
n
t
o
a
mu
l
t
i
p
a
r
a
m
e
t
r
i
c
c
l
a
ssi
f
i
c
a
t
i
o
n
s
y
st
e
m,”
E
u
ro
p
e
a
n
J
o
u
rn
a
l
o
f
Ra
d
i
o
l
o
g
y
,
v
o
l
.
1
3
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
j
r
a
d
.
2
0
2
1
.
1
0
9
6
5
9
.
[
3
0
]
J.
A
.
M
.
S
t
a
d
l
e
r
,
G
.
M
a
a
r
t
e
n
s,
G
.
M
e
i
n
t
j
e
s,
a
n
d
S
.
W
a
ss
e
r
ma
n
,
“
C
l
o
f
a
z
i
m
i
n
e
f
o
r
t
h
e
t
r
e
a
t
me
n
t
o
f
t
u
b
e
r
c
u
l
o
si
s
,
”
Fr
o
n
t
i
e
rs
i
n
Ph
a
rm
a
c
o
l
o
g
y
,
v
o
l
.
1
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
h
a
r
.
2
0
2
3
.
1
1
0
0
4
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t 2
0
2
5
:
2
8
9
9
-
2
9
0
8
2908
[
3
1
]
M
.
D
a
l
c
o
l
m
o
e
t
a
l
.
,
“
Ef
f
e
c
t
i
v
e
n
e
ss a
n
d
safe
t
y
o
f
c
l
o
f
a
z
i
m
i
n
e
i
n
m
u
l
t
i
d
r
u
g
-
r
e
si
st
a
n
t
t
u
b
e
r
c
u
l
o
s
i
s:
a
n
a
t
i
o
n
w
i
d
e
r
e
p
o
r
t
f
r
o
m
B
r
a
z
i
l
,
”
Eu
r
o
p
e
a
n
Re
s
p
i
r
a
t
o
r
y
J
o
u
rn
a
l
,
v
o
l
.
4
9
,
n
o
.
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
8
3
/
1
3
9
9
3
0
0
3
.
0
2
4
4
5
-
2
0
1
6
.
[
3
2
]
S
.
Es
p
o
s
i
t
o
,
S
.
B
i
a
n
c
h
i
n
i
,
a
n
d
F
.
B
l
a
si
,
“
B
e
d
a
q
u
i
l
i
n
e
a
n
d
d
e
l
a
ma
n
i
d
i
n
t
u
b
e
r
c
u
l
o
s
i
s,
”
E
x
p
e
rt
O
p
i
n
i
o
n
o
n
P
h
a
rm
a
c
o
t
h
e
ra
p
y
,
v
o
l
.
1
6
,
n
o
.
1
5
,
p
p
.
2
3
1
9
–
2
3
3
0
,
2
0
1
5
,
d
o
i
:
1
0
.
1
5
1
7
/
1
4
6
5
6
5
6
6
.
2
0
1
5
.
1
0
8
0
2
4
0
.
[
3
3
]
A
.
T.
D
e
s
h
k
a
r
a
n
d
P
.
A
.
S
h
i
r
u
r
e
,
“
B
e
d
a
q
u
i
l
i
n
e
:
a
n
o
v
e
l
d
i
a
r
y
l
q
u
i
n
o
l
i
n
e
f
o
r
mu
l
t
i
d
r
u
g
-
r
e
si
s
t
a
n
t
p
u
l
m
o
n
a
r
y
t
u
b
e
r
c
u
l
o
s
i
s,
”
C
u
r
e
u
s
,
v
o
l
.
1
4
,
n
o
.
8
,
2
0
2
2
,
d
o
i
:
1
0
.
7
7
5
9
/
c
u
r
e
u
s.
2
8
5
1
9
.
[
3
4
]
S
.
K
.
H
e
y
se
l
l
e
t
a
l
.
,
“
H
e
a
r
i
n
g
l
o
ss
w
i
t
h
k
a
n
a
my
c
i
n
t
r
e
a
t
m
e
n
t
f
o
r
mu
l
t
i
d
r
u
g
-
r
e
si
s
t
a
n
t
t
u
b
e
r
c
u
l
o
s
i
s
i
n
B
a
n
g
l
a
d
e
s
h
,
”
Eu
r
o
p
e
a
n
Re
sp
i
r
a
t
o
ry
J
o
u
r
n
a
l
,
v
o
l
.
5
1
,
n
o
.
3
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
8
3
/
1
3
9
9
3
0
0
3
.
0
1
7
7
8
-
2
0
1
7
.
[
3
5
]
A
.
J.
M
e
h
l
h
o
r
n
a
n
d
D
.
A
.
B
r
o
w
n
,
“
S
a
f
e
t
y
c
o
n
c
e
r
n
s
w
i
t
h
f
l
u
o
r
o
q
u
i
n
o
l
o
n
e
s,”
An
n
a
l
s
o
f
P
h
a
rm
a
c
o
t
h
e
r
a
p
y
,
v
o
l
.
4
1
,
n
o
.
1
1
,
p
p
.
1
8
5
9
–
1
8
6
6
,
2
0
0
7
,
d
o
i
:
1
0
.
1
3
4
5
/
a
p
h
.
1
K
3
4
7
.
[
3
6
]
A
.
R
u
su
,
A
.
-
C
.
M
u
n
t
e
a
n
u
,
E.
-
M
.
A
r
b
ă
n
a
s
,
a
n
d
V
.
U
i
v
a
r
o
si
,
“
O
v
e
r
v
i
e
w
o
f
si
de
-
e
f
f
e
c
t
s
o
f
a
n
t
i
b
a
c
t
e
r
i
a
l
f
l
u
o
r
o
q
u
i
n
o
l
o
n
e
s
:
n
e
w
d
r
u
g
s
v
e
r
s
u
s
o
l
d
d
r
u
g
s,
a
s
t
e
p
f
o
r
w
a
r
d
i
n
t
h
e
safe
t
y
p
r
o
f
i
l
e
?
,
”
P
h
a
rm
a
c
e
u
t
i
c
s
,
v
o
l
.
1
5
,
n
o
.
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
p
h
a
r
mac
e
u
t
i
c
s1
5
0
3
0
8
0
4
.
[
3
7
]
B
.
Ea
d
i
e
,
M
.
Et
m
i
n
a
n
,
a
n
d
F
.
S
.
M
i
k
e
l
b
e
r
g
,
“
R
i
s
k
f
o
r
u
v
e
i
t
i
s
w
i
t
h
o
r
a
l
mo
x
i
f
l
o
x
a
c
i
n
:
a
c
o
m
p
a
r
a
t
i
v
e
s
a
f
e
t
y
st
u
d
y
,
”
J
A
MA
O
p
h
t
h
a
l
m
o
l
o
g
y
,
v
o
l
.
1
3
3
,
n
o
.
1
,
p
p
.
8
1
–
8
4
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
0
1
/
j
a
ma
o
p
h
t
h
a
l
mo
l
.
2
0
1
4
.
3
5
9
8
.
[
3
8
]
Z
.
E
.
H
u
mm
a
a
n
d
P
.
P
a
t
e
l
,
M
o
x
i
f
l
o
x
a
c
i
n
,
Tr
e
a
s
u
r
e
I
sl
a
n
d
,
F
l
o
r
i
d
a
:
S
t
a
t
P
e
a
r
l
s Pu
b
l
i
s
h
i
n
g
,
2
0
2
4
.
[
3
9
]
W
.
X
.
W
a
n
g
,
F
.
Li
u
,
J
.
Y
.
Li
,
J.
X
u
e
,
Y
.
T.
L
i
,
a
n
d
R
.
M
.
Li
u
,
“
A
c
o
c
r
y
st
a
l
f
o
r
e
f
f
e
c
t
i
v
e
l
y
r
e
d
u
c
i
n
g
t
h
e
h
e
p
a
t
o
t
o
x
i
c
i
t
y
o
f
e
t
h
i
o
n
a
mi
d
e
,
”
J
o
u
r
n
a
l
o
f
M
o
l
e
c
u
l
a
r
S
t
ru
c
t
u
re
,
v
o
l
.
1
2
4
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
o
l
s
t
r
u
c
.
2
0
2
1
.
1
3
0
7
2
9
.
B
I
O
G
RAP
H
I
E
S
OF
AUTH
O
RS
S
iti
S
y
a
h
i
d
a
tu
l
H
e
lm
a
h
o
l
d
s
a
M
a
ste
r'
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
IP
B
Un
iv
e
rsity
.
S
h
e
a
lso
re
c
e
iv
e
d
an
u
n
d
e
r
g
ra
d
u
a
te
d
e
g
re
e
in
i
n
fo
rm
a
ti
o
n
sy
ste
m
s
fro
m
th
e
S
tate
Isla
m
ic
Un
iv
e
rsity
of
S
u
lt
a
n
S
y
a
r
if
Ka
sim
Riau
in
2
0
2
0
.
S
h
e
is
c
u
r
re
n
tl
y
p
a
rt
of
e
d
i
to
rial
tea
m
s
at
th
e
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
of
Artif
icia
l
In
telli
g
e
n
c
e
a
n
d
Da
ta
M
in
in
g
(IJA
IDM)
.
He
r
re
se
a
rc
h
in
c
lu
d
e
s
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
m
in
in
g
,
a
n
d
d
e
c
isi
o
n
su
p
p
o
rt
sy
s
tem
s
.
S
h
e
can
be
c
o
n
tac
ted
at
e
m
a
il
:
sy
a
h
id
a
h
3
1
3
@g
m
a
il
.
c
o
m
or
sy
a
h
i
d
a
tu
l
h
e
lma
@a
p
p
s.i
p
b
.
a
c
.
i
d
.
Wisn
u
An
a
n
t
a
K
u
su
m
a
e
a
rn
e
d
h
is
b
a
c
h
e
lo
r'
s
a
n
d
m
a
ste
r'
s
d
e
g
re
e
s
fro
m
th
e
Ba
n
d
u
n
g
I
n
stit
u
te
of
Tec
h
n
o
l
o
g
y
a
n
d
o
b
tain
e
d
h
is
P
h
.
D.
fr
o
m
th
e
To
k
y
o
I
n
stit
u
te
of
Tec
h
n
o
l
o
g
y
in
2
0
1
2
.
He
is
an
As
so
c
iate
P
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
at
IP
B
Un
iv
e
rsity
.
He
se
rv
e
s
as
th
e
Ex
e
c
u
t
iv
e
S
e
c
re
tary
of
th
e
I
n
stit
u
te
fo
r
In
tern
a
t
io
n
a
l
Re
se
a
rc
h
on
A
d
v
a
n
c
e
d
Tec
h
n
o
l
o
g
y
at
IP
B
U
n
iv
e
rsit
y
.
A
d
d
it
i
o
n
a
l
ly
,
he
c
o
o
r
d
in
a
tes
t
h
e
B
io
in
f
o
rm
a
ti
c
s
Wo
r
k
in
g
G
ro
u
p
at
th
e
F
a
c
u
lt
y
of
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
,
IP
B
Un
i
v
e
rsit
y
.
He
lea
d
s
th
e
B
io
i
n
fo
rm
a
ti
c
s
a
n
d
Hig
h
-
P
e
rfo
rm
a
n
c
e
Co
m
p
u
ti
n
g
Re
se
a
rc
h
G
ro
u
p
at
th
e
Ad
v
a
n
c
e
d
Re
se
a
rc
h
Lab
o
ra
to
ry
,
I
P
B
Un
iv
e
rsity
.
His
re
se
a
rc
h
fo
c
u
se
s
on
m
a
c
h
in
e
lea
rn
in
g
,
h
ig
h
-
p
e
rfo
rm
a
n
c
e
c
o
m
p
u
ti
n
g
,
a
n
d
b
io
i
n
fo
rm
a
ti
c
s
,
with
o
v
e
r
60
p
u
b
li
sh
e
d
a
rti
c
les
a
n
d
e
x
ten
siv
e
e
x
p
e
rien
c
e
re
v
iew
in
g
in
tern
a
ti
o
n
a
l
jo
u
r
n
a
ls.
He
a
lso
se
rv
e
s
as
th
e
Ch
a
irp
e
rso
n
of
t
h
e
In
d
o
n
e
sia
n
S
o
c
iety
of
B
io
i
n
fo
rm
a
ti
c
s
a
n
d
Bio
d
i
v
e
rsity
a
n
d
h
o
ld
s
a
p
o
sit
i
o
n
as
an
Ex
Co
M
e
m
b
e
r
of
t
h
e
As
ia
P
a
c
ifi
c
Bio
in
fo
rm
a
ti
c
s
Ne
two
rk
(APBi
o
Ne
t).
He
can
be
c
o
n
tac
ted
at
e
m
a
il
:
a
n
a
n
ta@
a
p
p
s.
ip
b
.
a
c
.
i
d
.
Mu
shth
o
f
a
h
o
ld
s
a
Ba
c
h
e
lo
r
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
IP
B
U
n
iv
e
rsity
,
I
n
d
o
n
e
sia
,
a
M
a
ste
r
of
S
c
ien
c
e
fro
m
Tec
h
n
i
c
a
l
Un
iv
e
rsity
of
Vie
n
n
a
,
Au
str
ia
a
n
d
a
Ph
.
D
.
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
G
h
e
n
t
U
n
iv
e
rsit
y
,
Be
lg
i
u
m
.
He
is
c
u
rre
n
tl
y
a
lec
tu
re
r
at
t
h
e
De
p
a
rtme
n
t
of
Co
m
p
u
ter
S
c
ien
c
e
,
IP
B
Un
i
v
e
rsity
,
Bo
g
o
r,
w
h
e
re
h
is
re
se
a
rc
h
in
tere
st
sp
a
n
s
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
b
i
o
i
n
fo
rm
a
ti
c
s
.
He
c
a
n
be
c
o
n
tac
ted
at
e
m
a
il
:
m
u
sh
@a
p
p
s.i
p
b
.
a
c
.
id
.
Dia
h
H
a
n
d
a
y
a
n
i
re
c
e
iv
e
d
a
m
e
d
ica
l
d
o
c
to
ra
te
fro
m
t
h
e
F
a
c
u
lt
y
of
M
e
d
icin
e
Un
iv
e
rsitas
In
d
o
n
e
sia
(F
M
UI).
S
h
e
e
a
rn
e
d
a
P
u
lmo
n
o
l
o
g
y
sp
e
c
ialist
at
F
M
UI
in
2
0
0
7
,
a
P
u
lmo
n
a
ry
I
n
fe
c
ti
o
n
Co
n
su
lt
a
n
t
Co
ll
e
g
i
u
m
P
u
lmo
n
o
lo
g
y
in
2
0
1
5
,
a
n
d
a
D
o
c
to
r
(
P
h
.
D.)
at
F
M
UI
in
2
0
2
1
.
S
h
e
is
c
u
rre
n
tl
y
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
of
P
u
lmo
n
o
lo
g
y
a
n
d
Re
sp
iro
l
o
g
y
M
e
d
ici
n
e
F
M
UI,
P
e
rsa
h
a
b
a
tan
H
o
sp
it
a
l,
a
n
d
Un
i
v
e
rsitas
In
d
o
n
e
sia
Ho
sp
it
a
l.
S
h
e
is
a
ls
o
He
a
d
of
th
e
e
d
u
c
a
ti
o
n
c
o
o
r
d
i
n
a
ti
o
n
c
o
m
m
it
tee
of
Un
i
v
e
rsitas
In
d
o
n
e
sia
Ho
sp
it
a
l
a
n
d
se
c
re
tary
of
Tu
b
e
rc
u
l
o
sis
R
e
se
a
rc
h
Li
n
k
e
d
(Je
jarin
g
Rise
t
TB,
Je
tS
e
t
TB).
S
h
e
h
a
s
a
u
th
o
re
d
m
a
n
y
a
rti
c
les
a
n
d
c
o
p
y
ri
g
h
ts
fo
c
u
se
d
on
t
u
b
e
rc
u
lo
sis
a
n
d
C
OV
ID
-
19.
S
h
e
can
be
c
o
n
tac
ted
at
e
m
a
il
:
d
iah
z
u
lfi
tri
@y
a
h
o
o
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.