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
6
,
No
.
1
,
Octo
b
er
20
24
,
p
p
.
6
7
2
~
6
8
4
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
1
.
pp
672
-
6
8
4
672
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Experime
ntal st
u
dy
of a medica
l d
a
ta a
na
ly
sis
mo
del bas
ed on
co
mpa
ra
tive perf
o
rma
nce of class
if
ica
tion a
lg
o
rithms
Aig
er
im
I
s
m
uk
ha
m
edo
v
a
1
,
I
nd
ira
Uv
a
liy
ev
a
2
,
Z
henis
g
ul
Ra
k
hm
et
ull
ina
2
1
S
c
h
o
o
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
D
.
S
e
r
i
k
b
a
y
e
v
Ea
st
K
a
z
a
k
h
st
a
n
Te
c
h
n
i
c
a
l
U
n
i
v
e
r
s
i
t
y
,
O
s
k
e
m
e
n
,
K
a
z
a
k
h
st
a
n
2
S
c
h
o
o
l
o
f
D
i
g
i
t
a
l
Te
c
h
n
o
l
o
g
y
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
ms,
D
.
S
e
r
i
k
b
a
y
e
v
Ea
s
t
K
a
z
a
k
h
s
t
a
n
Te
c
h
n
i
c
a
l
U
n
i
v
e
r
si
t
y
,
O
s
k
e
m
e
n
,
K
a
z
a
k
h
s
t
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
28
,
2
0
2
4
R
ev
is
ed
J
u
n
5
,
2
0
2
4
Acc
ep
ted
J
u
n
25
,
2
0
2
4
Th
is
a
rti
c
le
c
e
n
ters
a
ro
u
n
d
th
e
d
e
v
e
lo
p
m
e
n
t
a
n
d
a
n
a
ly
sis
o
f
m
a
c
h
in
e
lea
rn
in
g
(
M
L)
a
n
d
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls
a
ime
d
a
t
e
n
h
a
n
c
in
g
d
iab
e
tes
d
iag
n
o
sis.
I
n
th
e
sw
ift
ly
e
v
o
l
v
i
n
g
lan
d
sc
a
p
e
o
f
d
a
ta
tec
h
n
o
l
o
g
ies
,
i
t
b
e
c
o
m
e
s
c
ru
c
ial
to
e
x
p
lo
re
th
e
a
p
p
li
c
a
ti
o
n
s
o
f
th
e
se
m
e
th
o
d
s
f
o
r
a
c
c
u
ra
te
p
re
d
ictio
n
s
a
n
d
imp
ro
v
e
d
m
e
d
ica
l
d
e
c
isio
n
-
m
a
k
in
g
.
Ou
r
re
se
a
rc
h
e
n
c
o
m
p
a
ss
e
s
d
iv
e
rse
d
a
tas
e
ts,
lev
e
ra
g
in
g
sta
te
-
of
-
t
h
e
-
a
rt
a
lg
o
rit
h
m
s
a
n
d
tec
h
n
o
lo
g
ies
fo
r
m
o
d
e
l
train
in
g
a
n
d
tes
ti
n
g
.
T
h
e
p
rima
ry
e
m
p
h
a
sis
li
e
s
in
e
v
a
lu
a
ti
n
g
t
h
e
a
c
c
u
ra
c
y
,
se
n
siti
v
it
y
,
a
n
d
s
p
e
c
ifi
c
it
y
o
f
m
o
d
e
ls
with
i
n
th
e
re
a
lm
o
f
d
iab
e
tes
d
iag
n
o
sis.
Th
e
stu
d
y
re
su
lt
s
re
v
e
a
l
si
g
n
ifi
c
a
n
t
a
d
v
a
n
c
e
m
e
n
ts
in
d
ise
a
se
p
re
d
ictio
n
,
u
n
d
e
rsc
o
ri
n
g
t
h
e
p
o
ten
ti
a
l
o
f
M
L
a
n
d
d
e
e
p
lea
rn
i
n
g
i
n
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s.
Th
is
wo
r
k
in
tr
o
d
u
c
e
s
fre
sh
p
e
rsp
e
c
ti
v
e
s
o
n
th
e
u
ti
li
z
a
ti
o
n
o
f
c
o
m
p
u
tati
o
n
a
l
m
e
th
o
d
s
i
n
h
e
a
lt
h
c
a
re
a
n
d
se
rv
e
s
a
s
a
fo
u
n
d
a
ti
o
n
fo
r
p
ro
s
p
e
c
ti
v
e
r
e
se
a
rc
h
in
th
is d
o
m
a
in
.
K
ey
w
o
r
d
s
:
Di
ab
etes p
r
ev
alen
ce
Dig
ital h
ea
lth
ca
r
e
E
lectr
o
n
ic
h
ea
lth
s
y
s
tem
Hea
lth
in
f
o
r
m
atics
Hea
lth
ca
r
e
r
eso
u
r
ce
allo
ca
tio
n
I
n
tellig
en
t d
ec
is
io
n
s
u
p
p
o
r
t
Me
d
ical
d
ata
r
esear
ch
Su
p
p
o
r
t
o
f
m
ed
ical
d
ec
is
io
n
s
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
:
I
n
d
ir
a
Uv
aliy
e
v
a
Sch
o
o
l o
f
Dig
ital
T
ec
h
n
o
lo
g
y
an
d
I
n
tellig
en
t Sy
s
tem
s
D.
Ser
ik
b
ay
ev
E
ast Ka
za
k
h
s
tan
T
ec
h
n
ical
Un
iv
e
r
s
ity
Osk
em
en
,
E
ast Ka
za
k
h
s
tan
,
K
az
ak
h
s
tan
E
m
ail: in
d
ir
au
v
aliev
a@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
e
ev
o
lv
in
g
lan
d
s
ca
p
e
o
f
m
o
d
er
n
h
ea
lth
ca
r
e,
t
h
e
m
a
n
a
g
em
en
t
a
n
d
an
aly
s
is
o
f
h
ea
lth
d
ata
h
av
e
b
ec
o
m
e
p
iv
o
tal.
T
h
e
in
tr
o
d
u
ct
io
n
o
f
th
e
elec
tr
o
n
ic
h
ea
lth
p
a
s
s
p
o
r
t
(
E
HP)
r
e
p
r
esen
ts
a
leap
to
war
d
s
e
n
h
an
ci
n
g
p
atien
t
d
ata
h
an
d
lin
g
,
o
f
f
er
in
g
a
co
m
p
r
e
h
en
s
iv
e
to
o
l
f
o
r
t
h
e
co
llectio
n
,
s
to
r
ag
e,
an
d
p
r
o
ce
s
s
in
g
o
f
h
ea
lth
in
f
o
r
m
atio
n
.
T
h
is
in
n
o
v
atio
n
alig
n
s
with
th
e
W
o
r
ld
Hea
lth
O
r
g
an
izatio
n
'
s
(
W
HO)
G
lo
b
al
S
tr
ateg
y
f
o
r
Dig
ital
Hea
lth
2
0
2
0
-
2
0
2
5
[
1
]
,
[
2
]
wh
ich
asp
ir
es
to
u
n
iv
er
s
ally
im
p
r
o
v
e
h
ea
lth
ca
r
e
v
ia
d
ig
ital
tech
n
o
lo
g
ies
[
3
]
,
[
4
]
with
an
em
p
h
asis
o
n
eq
u
ity
[
5
]
an
d
in
clu
s
io
n
[
6
]
.
Desp
ite
th
ese
ad
v
an
ce
s
,
th
e
im
p
lem
en
tatio
n
o
f
s
u
ch
s
tr
ateg
ies ac
r
o
s
s
v
ar
y
in
g
n
atio
n
al
lan
d
s
ca
p
es p
o
s
es c
o
n
s
id
er
ab
le
ch
allen
g
es.
B
a
c
k
g
r
o
u
n
d
:
T
h
e
f
o
u
n
d
a
t
i
o
n
f
o
r
c
o
n
s
t
r
u
c
t
i
n
g
s
y
s
te
m
s
t
h
a
t
g
a
t
h
e
r
,
s
t
o
r
e
,
a
n
d
a
n
a
l
y
ze
m
e
d
i
c
a
l
i
n
f
o
r
m
a
t
i
o
n
f
r
o
m
p
a
t
i
e
n
t
s
a
c
r
o
s
s
v
a
r
i
o
u
s
c
o
u
n
t
r
i
es
g
l
o
b
a
l
l
y
l
ie
s
i
n
t
h
e
r
e
a
l
m
o
f
e
x
t
e
n
s
i
v
e
d
a
t
a
.
P
r
o
c
e
s
s
i
n
g
t
h
is
v
a
s
t
a
m
o
u
n
t
o
f
d
a
t
a
,
c
o
m
m
o
n
l
y
r
e
f
e
r
r
e
d
t
o
a
s
b
i
g
d
a
t
a,
e
m
p
o
w
e
r
s
u
s
t
o
f
o
r
m
u
l
a
t
e
m
e
t
h
o
d
o
l
o
g
i
e
s
f
o
r
a
n
t
i
c
i
p
a
ti
n
g
f
a
c
t
o
r
s
s
u
c
h
as
il
l
n
e
s
s
r
a
t
es
,
m
o
r
t
al
i
t
y
,
c
o
m
p
l
i
c
at
io
n
s
,
a
n
d
b
e
y
o
n
d
[
7
]
.
B
i
g
d
a
t
a
p
r
o
c
e
s
s
i
n
g
h
a
s
m
a
d
e
i
t
p
o
s
s
i
b
l
e
t
o
d
e
v
el
o
p
i
n
t
el
l
i
g
en
t
d
e
c
is
i
o
n
-
m
a
k
i
n
g
s
y
s
t
e
m
s
,
i
n
c
l
u
d
i
n
g
i
n
m
e
d
i
ci
n
e
[
8
]
–
[
1
2
]
.
A
u
t
h
o
r
s
c
o
n
t
e
n
d
t
h
at
t
h
e
a
p
p
l
i
c
at
i
o
n
o
f
a
r
t
i
f
i
ci
a
l
i
n
t
el
l
i
g
e
n
c
e
(
AI
)
a
n
d
m
a
c
h
i
n
e
le
a
r
n
i
n
g
(
M
L
)
h
a
s
c
o
n
t
r
i
b
u
t
e
d
t
o
en
h
a
n
c
i
n
g
o
u
t
c
o
m
e
s
i
n
t
h
e
d
i
a
g
n
o
s
is
,
t
r
e
at
m
e
n
t
,
a
n
d
p
r
o
g
n
o
s
i
s
f
o
r
C
h
r
o
n
i
c
L
i
m
b
-
T
h
r
e
a
t
e
n
i
n
g
I
s
c
h
e
m
ia
(
C
L
T
I
)
p
at
i
e
n
ts
[
1
3
]
.
T
h
e
ef
f
icac
y
o
f
em
p
lo
y
in
g
ML
tech
n
o
l
o
g
ies
in
m
ed
icin
e
is
s
u
b
s
tan
tiated
b
y
n
u
m
e
r
o
u
s
s
tu
d
ies
ac
r
o
s
s
v
ar
io
u
s
m
ed
ical
f
ield
s
.
I
n
th
eir
ex
am
in
atio
n
o
f
th
e
d
ia
g
n
o
s
tic
p
r
o
p
er
ties
o
f
ML
alg
o
r
ith
m
s
in
p
er
ip
h
er
al
ar
te
r
y
d
is
ea
s
e,
th
e
au
th
o
r
s
co
n
clu
d
e
th
at
ML
en
ab
les
m
o
r
e
p
r
ec
is
e
class
if
icatio
n
an
d
p
r
ed
ictio
n
o
f
th
e
d
is
ea
s
e
[
1
4
]
.
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:
2
5
0
2
-
4
7
52
E
xp
erimen
ta
l stu
d
y
o
f a
med
ic
a
l d
a
ta
a
n
a
lysi
s
mo
d
el
b
a
s
ed
o
n
co
mp
a
r
a
tive
…
(
A
ig
erim I
s
mu
kh
a
med
o
v
a
)
673
ML
m
eth
o
d
o
lo
g
ies
ar
e
em
p
lo
y
ed
to
p
r
ed
ict
b
io
lo
g
ical
ag
e
b
y
u
tili
zin
g
d
ata
lin
k
ed
to
i
d
en
t
if
iab
le
m
en
tal
tr
aits
th
at
ar
e
c
o
r
r
elate
d
with
ac
ce
l
er
ated
ag
in
g
[
1
5
]
.
T
h
e
au
th
o
r
s
o
f
s
tu
d
ies
o
n
Par
k
in
s
o
n
'
s
d
is
ea
s
e
[
1
6
]
,
h
ig
h
-
f
a
t
a
l
it
y
c
a
n
c
e
r
s
[
1
7
]
–
[
2
0
]
,
a
n
d
i
n
h
e
r
i
t
e
d
a
r
r
h
y
t
h
m
i
a
s
y
n
d
r
o
m
e
s
[
2
1
]
r
e
a
c
h
t
h
e
s
a
m
e
c
o
n
c
l
u
s
i
o
n
.
T
h
e
u
t
i
l
i
z
a
t
i
o
n
o
f
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
r
e
d
u
c
e
s
t
h
e
l
i
k
e
li
h
o
o
d
o
f
a
f
a
l
s
e
-
po
s
i
t
i
v
e
d
i
a
g
n
o
s
i
s
,
t
h
e
r
e
b
y
e
l
i
m
in
a
t
i
n
g
t
h
e
n
e
g
a
t
i
v
e
p
s
y
c
h
o
l
o
g
i
c
a
l
i
m
p
a
ct
f
a
c
e
d
b
y
t
h
e
p
a
t
i
e
n
t
[
2
2
]
.
T
h
e
u
t
i
l
i
z
at
i
o
n
o
f
ML
m
e
t
h
o
d
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
i
n
d
i
a
g
n
o
s
i
n
g
C
O
V
I
D
-
1
9
c
o
n
t
r
i
b
u
t
e
d
t
o
b
r
i
n
g
i
n
g
t
h
e
p
a
n
d
e
m
i
c
u
n
d
e
r
c
o
n
t
r
o
l
[
2
3
]
-
[
3
5
]
.
ML
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
,
w
it
h
t
h
e
i
r
i
n
h
e
r
e
n
t
c
a
p
a
c
it
y
to
i
n
d
e
p
e
n
d
e
n
t
l
y
e
x
t
r
a
c
t
v
a
l
u
a
b
l
e
i
n
s
i
g
h
t
s
f
r
o
m
d
a
t
a
,
o
f
f
e
r
a
s
i
g
n
i
f
i
c
a
n
t
a
d
v
a
n
t
a
g
e
i
n
p
r
e
d
i
c
t
i
o
n
,
l
e
a
d
i
n
g
t
o
t
h
e
i
r
w
i
d
e
s
p
r
e
a
d
u
t
i
l
i
z
at
i
o
n
i
n
t
h
e
m
e
d
i
c
a
l
f
i
e
l
d
,
p
a
r
t
i
c
u
l
a
r
l
y
u
n
d
e
r
s
c
o
r
i
n
g
t
h
e
i
m
p
o
r
t
a
n
c
e
a
n
d
h
i
g
h
s
i
g
n
i
f
ic
a
n
c
e
o
f
DL
M
e
t
h
o
d
s
i
n
h
ea
l
t
h
c
a
r
e
[
3
6
]
–
[
3
9
]
.
A
n
a
l
y
z
i
n
g
p
a
t
i
e
n
t
r
e
c
o
r
d
s
a
n
d
s
e
l
e
c
t
i
o
n
c
r
i
te
r
i
a
f
o
r
d
e
v
e
l
o
p
e
d
m
o
d
e
l
s
e
n
a
b
l
e
s
p
r
e
d
i
c
t
io
n
s
o
f
c
o
n
t
a
g
i
o
n
,
s
u
r
v
i
v
a
b
i
l
it
y
,
a
n
d
t
h
e
r
i
s
k
o
f
cr
i
t
i
c
al
c
o
n
d
i
t
i
o
n
s
[
1
1
]
,
[
4
0
]
–
[
4
3
]
.
A
c
o
m
p
a
r
i
s
o
n
o
f
1
4
d
i
f
f
e
r
e
n
t
ML
a
l
g
o
r
i
t
h
m
s
r
e
v
e
a
l
e
d
a
n
a
cc
u
r
a
c
y
o
f
o
v
e
r
9
0
%
i
n
i
d
e
n
t
i
f
y
i
n
g
i
n
d
i
v
i
d
u
a
l
s
w
i
t
h
a
n
d
w
i
t
h
o
u
t
d
i
a
b
e
t
es
[
4
4
]
.
R
e
s
e
a
r
c
h
e
r
s
c
o
m
b
i
n
e
m
u
l
t
i
p
l
e
al
g
o
r
i
t
h
m
s
to
d
e
t
e
r
m
i
n
e
t
h
e
a
c
c
u
r
a
c
y
o
f
p
r
e
d
i
c
t
i
n
g
d
i
a
b
e
te
s
[
4
5
]
–
[
4
7
]
.
R
esear
ch
er
s
h
av
e
d
em
o
n
s
tr
at
ed
th
e
ef
f
icac
y
o
f
ML
m
o
d
el
s
in
d
is
ea
s
e
id
en
tific
atio
n
an
d
p
r
o
g
n
o
s
is
with
n
o
tab
le
ac
cu
r
ac
y
.
Yet,
th
e
u
tili
ty
o
f
th
ese
tech
n
o
lo
g
ies
in
th
e
n
u
an
ce
d
f
ield
o
f
d
iab
etes
p
r
ed
ictio
n
r
em
ain
s
u
n
d
er
e
x
p
lo
r
ed
.
T
h
is
o
cc
u
r
s
p
ar
tly
d
u
e
to
th
e
al
g
o
r
i
th
m
s
em
p
lo
y
ed
.
Fo
r
in
s
tan
ce
,
with
in
th
e
r
ea
lm
o
f
alter
n
ativ
e
ML
al
g
o
r
ith
m
s
,
c
o
n
v
en
tio
n
al
m
eth
o
d
s
lik
e
n
ai
v
e
B
ay
es,
lo
g
is
tic
r
e
g
r
ess
io
n
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es (
SV
Ms)
lead
to
ex
p
o
n
en
tial g
r
o
wth
i
n
co
m
p
u
tatio
n
al
co
m
p
lex
ity
d
u
e
to
d
ata
ex
p
an
s
io
n
,
r
esu
ltin
g
in
in
ad
eq
u
ate
o
u
tco
m
es
[
7
]
,
[
3
3
]
,
[
4
8
]
,
[
4
9
]
.
I
n
c
o
n
tr
ast,
tr
e
e
alg
o
r
ith
m
s
p
r
o
v
id
e
a
m
o
r
e
r
o
b
u
s
t
alter
n
ativ
e,
allev
iatin
g
ce
r
tain
lim
itatio
n
s
en
co
u
n
ter
e
d
b
y
tr
ad
iti
o
n
al
m
e
th
o
d
s
[
8
]
,
[
9
]
,
[
5
0
]
.
E
n
s
em
b
le
m
eth
o
d
s
an
d
th
e
d
ec
is
io
n
tr
ee
alg
o
r
it
h
m
in
ML
o
f
f
er
ap
p
r
o
ac
h
es
to
h
ig
h
-
p
r
ec
is
io
n
d
iag
n
o
s
is
an
d
p
r
o
g
n
o
s
is
f
o
r
b
r
ea
s
t
ca
n
ce
r
[
5
1
]
-
[
5
3
]
,
ca
r
d
i
o
v
ascu
lar
d
is
ea
s
e
[
5
4
]
,
[
5
5
]
,
an
d
C
OVI
D
-
1
9
[
5
6
]
.
T
h
e
p
r
o
b
lem
:
T
h
e
wid
esp
r
ea
d
ap
p
licatio
n
o
f
ML
ac
r
o
s
s
t
h
e
n
ex
u
s
o
f
m
e
d
icin
e
an
d
in
f
o
r
m
atio
n
tech
n
o
lo
g
y
h
as
s
ig
n
if
ican
tly
ad
v
an
ce
d
o
u
r
ca
p
ab
ilit
ies
to
ad
d
r
ess
v
ar
io
u
s
ch
allen
g
es.
Desp
ite
th
ese
ad
v
an
ce
m
e
n
ts
,
th
e
q
u
est
f
o
r
i
n
n
o
v
ativ
e
d
iag
n
o
s
tic
m
eth
o
d
o
lo
g
ies
th
r
o
u
g
h
th
e
m
eticu
lo
u
s
an
aly
s
is
o
f
p
atien
t
d
ata
r
em
ain
s
lar
g
ely
u
n
ex
p
lo
r
ed
.
Pre
v
ailin
g
liter
atu
r
e
u
n
d
er
s
co
r
es
th
e
in
cr
e
m
en
tal
ad
o
p
ti
o
n
o
f
d
ig
ital
h
ea
lth
tech
n
o
lo
g
ies,
with
s
tr
ateg
ic
o
b
jectiv
es
f
o
cu
s
in
g
o
n
g
o
v
e
r
n
an
ce
,
r
eso
u
r
ce
ca
p
ac
ity
,
a
n
d
d
ata
s
ec
u
r
ity
.
Ho
wev
er
,
liter
atu
r
e
r
ev
ea
ls
a
g
a
p
in
th
e
p
r
a
g
m
atic
an
aly
s
is
o
f
b
ig
d
ata
to
in
f
o
r
m
h
ea
lth
ca
r
e
d
eliv
er
y
.
E
x
is
tin
g
r
esear
ch
p
r
e
d
o
m
in
a
n
tly
r
elies o
n
estab
lis
h
ed
d
is
ea
s
e
m
ar
k
er
s
o
r
s
in
g
u
lar
ty
p
es o
f
m
e
d
ical
in
f
o
r
m
atio
n
.
T
h
e
p
r
o
p
o
s
e
d
s
o
l
u
t
i
o
n
:
I
n
c
o
n
tr
a
s
t
,
we
a
d
v
o
c
a
t
e
f
o
r
a
n
o
v
e
l
m
e
t
h
o
d
o
l
o
g
y
t
h
a
t
l
e
v
e
r
a
g
es
M
L
to
u
n
c
o
v
e
r
n
e
w
d
i
a
g
n
o
s
ti
c
i
n
d
i
c
at
o
r
s
.
T
h
i
s
a
p
p
r
o
a
c
h
a
i
m
s
t
o
el
u
ci
d
a
t
e
t
h
e
c
o
n
n
e
c
t
i
o
n
s
b
et
w
ee
n
d
i
s
e
as
es
a
n
d
a
c
o
m
p
r
e
h
e
n
s
i
v
e
a
r
r
a
y
o
f
p
a
t
i
e
n
t
m
e
d
i
c
a
l
d
a
t
a
,
e
n
c
o
m
p
a
s
s
i
n
g
p
r
i
o
r
i
l
l
n
e
s
s
es
a
n
d
a
l
l
a
v
a
il
a
b
l
e
h
e
a
l
t
h
i
n
f
o
r
m
a
t
i
o
n
.
S
u
c
h
a
s
t
r
at
e
g
y
i
s
n
o
t
o
n
l
y
p
i
v
o
t
a
l
b
u
t
a
ls
o
n
e
c
es
s
i
t
a
te
d
b
y
th
e
i
n
t
e
g
r
a
ti
o
n
o
f
c
u
tt
i
n
g
-
e
d
g
e
t
e
c
h
n
o
l
o
g
i
e
s
w
it
h
i
n
r
o
u
t
i
n
e
m
e
d
i
c
a
l
f
r
a
m
e
w
o
r
k
s
a
n
d
t
h
e
a
d
o
p
t
i
o
n
o
f
e
le
c
tr
o
n
i
c
h
e
a
l
t
h
p
as
s
p
o
r
ts
.
W
e
w
i
ll
e
l
u
c
i
d
at
e
o
u
r
m
e
t
h
o
d
o
l
o
g
y
,
c
o
m
b
i
n
i
n
g
v
a
r
i
o
u
s
ML
m
o
d
e
ls
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
s
s
i
f
i
ca
t
i
o
n
t
e
c
h
n
i
q
u
es
t
o
f
o
r
e
c
a
s
t
d
ia
b
e
t
es
p
r
e
s
e
n
c
e
.
T
h
e
r
e
s
e
a
r
c
h
wi
l
l
u
n
d
e
r
t
a
k
e
a
b
i
n
a
r
y
c
l
as
s
i
f
i
c
at
i
o
n
t
a
s
k
,
e
m
p
l
o
y
i
n
g
m
u
lt
i
p
l
e
e
v
a
l
u
a
t
i
o
n
c
r
i
t
e
r
i
a
a
n
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
t
o
f
o
r
g
e
r
o
b
u
s
t
a
l
g
o
r
i
t
h
m
s
.
T
h
r
o
u
g
h
m
e
t
i
c
u
l
o
u
s
d
a
t
a
p
r
e
p
r
o
c
e
s
s
i
n
g
,
w
e
w
i
l
l
a
ls
o
e
x
p
l
o
r
e
p
a
t
i
e
n
t
h
is
t
o
r
y
a
n
d
h
o
s
p
i
t
al
i
z
at
io
n
l
e
v
e
l
s
t
o
e
n
h
a
n
c
e
o
u
r
m
o
d
e
l'
s
p
r
e
d
i
c
ti
v
e
c
a
p
a
b
i
li
t
y
.
2.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
D
S
2
.
1
.
Resea
rc
h descript
io
n
T
h
e
s
tu
d
y
p
r
o
g
r
ess
es
th
r
o
u
g
h
m
eth
o
d
ical
s
tep
s
d
esig
n
ed
t
o
e
n
s
u
r
e
r
e
p
licab
ilit
y
an
d
r
o
b
u
s
tn
ess
o
f
th
e
f
in
d
in
g
s
.
B
elo
w
is
a
d
etailed
b
r
ea
k
d
o
wn
o
f
ea
c
h
p
h
ase.
A.
Selectio
n
an
d
p
r
e
p
ar
atio
n
o
f
d
ata:
−
E
x
p
lo
r
ato
r
y
d
ata
a
n
aly
s
is
(
E
DA)
is
co
n
d
u
cted
to
id
en
tify
an
d
ad
d
r
ess
d
ata
i
n
co
n
s
is
ten
cies,
m
is
s
in
g
v
alu
es,
an
d
o
u
tlier
s
.
−
Data
q
u
ality
is
r
ea
s
s
ess
ed
th
r
o
u
g
h
v
e
r
if
icati
o
n
p
r
o
to
c
o
ls
to
e
n
s
u
r
e
v
alid
ity
a
n
d
r
eliab
ilit
y
.
−
Stru
ctu
r
ed
d
ata
f
r
am
es
ar
e
c
o
n
s
tr
u
cted
f
o
r
test
in
g
a
n
d
tr
ain
in
g
p
r
ed
ictiv
e
m
o
d
els,
with
ca
r
ef
u
l
co
n
s
id
er
atio
n
o
f
f
ea
tu
r
e
s
elec
tio
n
to
b
ala
n
ce
th
e
in
f
o
r
m
ativ
e
v
alu
e
ag
ain
s
t c
o
m
p
u
tatio
n
al
ef
f
icien
cy
.
B.
Mo
d
elin
g
:
−
A
r
an
g
e
o
f
p
r
e
d
ictiv
e
m
o
d
els
ar
e
d
elin
ea
ted
,
in
cl
u
d
in
g
b
u
t n
o
t
lim
ited
to
,
d
ec
is
io
n
tr
ee
s
,
r
a
n
d
o
m
f
o
r
ests
,
an
d
SVMs
,
ea
ch
ch
o
s
en
f
o
r
t
h
eir
p
r
o
v
en
ef
f
icac
y
in
m
e
d
ical
d
ata
an
aly
s
is
[
3
8
]
,
[
3
9
]
,
[
5
6
]
,
[
5
7
]
.
−
Mo
d
el
p
er
f
o
r
m
an
ce
is
r
ig
o
r
o
u
s
ly
ev
alu
ated
ag
ain
s
t
k
e
y
m
etr
ics:
ac
cu
r
ac
y
,
F1
s
co
r
e,
p
r
ec
is
io
n
,
an
d
r
ec
all
to
en
s
u
r
e
a
c
o
m
p
r
e
h
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
ea
c
h
m
o
d
el's p
r
ed
ictiv
e
p
o
wer
.
C.
I
d
en
tific
atio
n
o
f
th
e
b
est m
o
d
e
l:
−
C
o
m
p
ar
ativ
e
an
aly
s
is
is
co
n
d
u
cted
to
d
eter
m
in
e
th
e
m
o
s
t
ef
f
ec
tiv
e
m
o
d
el.
T
h
is
in
v
o
lv
e
s
a
s
y
s
t
em
atic
r
ev
iew
o
f
p
er
f
o
r
m
an
ce
m
et
r
ics an
d
alig
n
m
en
t w
ith
t
h
e
s
p
ec
i
f
ic
n
u
an
ce
s
o
f
th
e
d
ataset.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
672
-
6
8
4
674
D.
Op
tim
izatio
n
o
f
th
e
m
o
d
el:
−
Mo
d
el
ac
cu
r
ac
y
is
en
h
an
ce
d
t
h
r
o
u
g
h
a
s
y
s
tem
atic
o
p
tim
izat
io
n
p
r
o
ce
s
s
u
tili
zin
g
Gr
id
Sea
r
ch
tech
n
iq
u
e
s
to
f
in
e
-
tu
n
e
h
y
p
er
p
a
r
am
eter
s
with
i
n
co
m
p
u
tatio
n
ally
f
ea
s
ib
l
e
b
o
u
n
d
s
.
E.
Ap
p
licatio
n
o
f
d
ee
p
lear
n
in
g
:
−
E
n
s
em
b
le
m
o
d
els
an
d
n
eu
r
al
n
etwo
r
k
s
ar
e
d
ep
lo
y
ed
,
s
elec
ted
f
o
r
th
eir
ca
p
ac
ity
t
o
m
o
d
el
co
m
p
lex
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
in
h
er
e
n
t in
m
ed
ical
d
ata
[
8
]
,
[
9
]
,
[
5
2
]
–
[
5
8
]
.
−
Hy
p
er
p
ar
a
m
eter
s
ar
e
ca
r
ef
u
lly
ch
o
s
en
b
ased
o
n
th
ei
r
i
m
p
ac
t
o
n
p
er
f
o
r
m
an
ce
,
wit
h
a
f
o
c
u
s
o
n
g
en
er
aliza
b
ilit
y
an
d
p
r
e
v
en
tio
n
o
f
o
v
er
f
itti
n
g
.
F.
Ob
tain
in
g
an
d
an
aly
zin
g
r
esu
l
ts
:
−
R
esu
lts
ar
e
ac
q
u
ir
ed
f
r
o
m
a
r
a
n
d
o
m
ized
d
ataset
to
en
s
u
r
e
th
e
r
o
b
u
s
tn
ess
o
f
f
i
n
d
in
g
s
.
−
Key
p
ar
am
ete
r
s
in
f
lu
e
n
cin
g
d
i
ag
n
o
s
is
ar
e
i
d
en
tifie
d
th
r
o
u
g
h
f
ea
tu
r
e
im
p
o
r
tan
ce
an
aly
s
is
,
w
h
ich
in
f
o
r
m
s
th
e
in
ter
p
r
etab
ilit
y
o
f
th
e
m
o
d
el.
−
C
o
llab
o
r
atio
n
with
d
o
m
ain
ex
p
er
ts
en
s
u
r
es th
e
clin
ical
r
elev
an
ce
o
f
th
e
d
ata
an
al
y
s
is
.
−
Ad
d
itio
n
al
test
in
g
is
co
n
d
u
cte
d
wh
e
r
e
p
o
s
s
ib
le,
u
s
in
g
d
atas
ets
f
r
o
m
m
ed
ical
in
s
titu
tio
n
s
to
v
alid
ate
th
e
m
o
d
el'
s
ap
p
licab
ilit
y
in
a
r
ea
l
-
wo
r
ld
s
ettin
g
.
Data
s
elec
tio
n
:
Data
s
elec
tio
n
f
o
r
o
u
r
s
tu
d
y
o
n
d
iab
etes
m
ellitu
s
f
o
llo
ws
d
iag
n
o
s
tic
an
d
tr
ea
tm
en
t
p
r
o
to
co
ls
,
ad
h
e
r
in
g
to
W
H
O
s
tan
d
ar
d
s
,
a
n
d
u
tili
ze
s
in
d
icato
r
s
lik
e
s
y
m
p
to
m
s
a
n
d
g
lu
co
s
e
lev
els
f
o
r
id
en
tific
atio
n
.
W
e
ex
tr
ac
ted
an
d
an
aly
ze
d
a
co
m
p
r
eh
en
s
iv
e
d
ataset
f
r
o
m
th
e
MI
MI
C
I
I
I
d
atab
ase,
co
v
er
in
g
v
ar
io
u
s
m
ed
ical
an
d
p
atien
t
-
r
e
lated
ca
teg
o
r
ies to
en
s
u
r
e
d
ata
in
teg
r
ity
.
Data
p
r
o
ce
s
s
in
g
an
d
m
o
d
el
tr
ain
in
g
: I
n
d
ata
p
r
o
ce
s
s
in
g
an
d
m
o
d
el
tr
ain
in
g
,
we
u
s
ed
a
b
r
o
ad
r
an
g
e
o
f
in
d
icato
r
s
in
clu
d
in
g
la
b
o
r
ato
r
y
a
n
d
p
atien
t
ex
am
in
atio
n
d
ata.
Ou
r
ap
p
r
o
a
ch
in
clu
d
ed
d
ata
clea
n
s
in
g
to
elim
in
ate
d
u
p
licates
a
n
d
a
n
o
m
alies,
f
o
llo
wed
b
y
d
ata
in
teg
r
atio
n
to
s
u
p
p
o
r
t o
u
r
r
esear
ch
o
b
jectiv
es.
I
n
s
ig
h
ts
wer
e
d
r
awn
f
r
o
m
s
p
ec
if
ic
MI
MI
C
d
atab
ase
tab
les
lik
e
'
ch
ar
tev
en
ts
'
an
d
'
n
o
teev
en
ts
'
to
en
h
an
ce
o
u
r
u
n
d
e
r
s
tan
d
in
g
o
f
p
atien
t statu
s
an
d
tr
ea
t
m
en
t e
f
f
icac
y
.
Op
tim
al
m
o
d
el
d
eter
m
i
n
atio
n
:
Su
b
s
eq
u
e
n
t
to
d
ata
p
r
e
p
ar
atio
n
,
we
em
p
lo
y
a
co
m
b
in
atio
n
o
f
ML
an
d
en
s
em
b
le
m
eth
o
d
s
to
id
en
tif
y
th
e
o
p
tim
al
m
o
d
el.
T
h
e
s
elec
tio
n
o
f
th
ese
m
et
h
o
d
s
is
ju
s
tifie
d
b
y
th
eir
r
o
b
u
s
tn
ess
in
h
an
d
lin
g
h
i
g
h
-
d
im
en
s
io
n
al
d
ata
an
d
th
eir
p
r
o
v
en
tr
ac
k
r
ec
o
r
d
i
n
m
ed
ical
d
ata
an
aly
s
is
.
2
.
2
.
ML
a
nd
ens
em
ble m
et
ho
ds
T
r
ad
itio
n
al
ML
m
o
d
els
lik
e
L
o
g
is
tic
R
eg
r
ess
io
n
u
s
e
a
lin
ea
r
d
ec
is
io
n
b
o
u
n
d
ar
y
,
wh
ich
m
a
y
s
tr
u
g
g
le
with
co
m
p
lex
,
h
i
g
h
-
d
im
e
n
s
io
n
al
d
ata.
T
o
ad
d
r
ess
th
is
,
en
s
e
m
b
le
m
eth
o
d
s
s
u
ch
as
R
an
d
o
m
Fo
r
ests
,
wh
ich
u
s
e
m
u
ltip
le
Dec
is
io
n
T
r
ee
s
,
an
d
B
ag
g
in
g
an
d
B
o
o
s
tin
g
tech
n
i
q
u
es
ar
e
u
s
ed
to
im
p
r
o
v
e
m
o
d
el
r
o
b
u
s
tn
ess
an
d
ac
cu
r
ac
y
.
B
ag
g
in
g
tr
ain
s
m
u
l
tip
le
m
o
d
els
o
n
d
if
f
e
r
en
t
d
ata
s
u
b
s
ets
an
d
ag
g
r
eg
ates
th
eir
p
r
ed
ictio
n
s
,
wh
ile
B
o
o
s
tin
g
s
eq
u
en
tially
co
r
r
ec
ts
th
e
p
r
ev
i
o
u
s
m
o
d
el'
s
er
r
o
r
s
,
weig
h
in
g
p
r
ed
ictio
n
s
b
ased
o
n
th
eir
ac
cu
r
ac
y
[
57
]
.
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
A
NNs),
in
clu
d
in
g
co
n
v
o
lu
tio
n
a
l
n
eu
r
al
n
etwo
r
k
s
(
C
NNs)
an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NNs)
[
59
]
-
[
61
]
,
u
s
e
la
y
er
s
o
f
n
e
u
r
o
n
s
to
p
r
o
ce
s
s
d
ata.
C
NNs
ar
e
ef
f
ec
tiv
e
f
o
r
au
to
m
atic
f
ea
tu
r
e
ex
tr
ac
tio
n
t
h
r
o
u
g
h
co
n
v
o
lu
tio
n
al
f
ilter
s
[
62
]
-
[
6
4
]
,
w
h
er
ea
s
R
NNs
h
an
d
le
s
eq
u
en
tial
d
ata,
with
o
u
tp
u
ts
f
r
o
m
o
n
e
lay
er
f
e
d
b
ac
k
in
t
o
th
e
s
am
e
lay
er
as
in
p
u
t
[
65
]
–
[
67
]
.
L
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
n
etwo
r
k
s
(
L
STM
s
)
i
m
p
r
o
v
e
R
N
Ns
b
y
m
a
n
a
g
i
n
g
in
f
o
r
m
a
t
i
o
n
f
l
o
w
w
i
t
h
g
at
e
s
t
h
at
r
e
g
u
l
a
t
e
i
n
p
u
t
,
o
u
t
p
u
t
,
a
n
d
f
o
r
g
e
t
f
u
n
c
t
i
o
n
s
[
6
8
]
.
Key
to
tr
ain
in
g
th
ese
n
etwo
r
k
s
is
m
in
im
izin
g
a
C
o
s
t
Fu
n
cti
o
n
[
69
]
,
o
f
ten
u
s
in
g
a
Gr
ad
ie
n
t
Descen
t
alg
o
r
ith
m
,
wh
ic
h
ad
ju
s
ts
p
ar
a
m
eter
s
to
r
ed
u
ce
p
r
ed
ictio
n
e
r
r
o
r
[
70
]
.
Min
i
-
b
atch
g
r
ad
ien
t
d
escen
t
en
h
an
ce
s
ef
f
icien
cy
b
y
u
s
in
g
s
u
b
s
ets
o
f
d
ata,
wh
ile
th
e
Ad
am
o
p
tim
izer
r
ef
in
es
p
ar
am
eter
u
p
d
a
tes
b
y
ad
ju
s
tin
g
th
e
lear
n
in
g
r
at
e
b
ased
o
n
g
r
a
d
ien
t
esti
m
ates
[
71
]
–
[
74
]
.
T
h
ese
m
eth
o
d
s
en
s
u
r
e
ef
f
e
ctiv
e
lear
n
in
g
an
d
co
n
v
er
g
en
ce
d
u
r
in
g
m
o
d
el
tr
ain
in
g
[
6
5
]
–
[
74]
.
2
.
3
.
O
pti
m
iza
t
io
n pro
ce
s
s
T
h
e
o
p
tim
izatio
n
p
r
o
ce
s
s
in
v
o
lv
ed
th
e
f
o
llo
win
g
s
tep
s
,
im
p
lem
en
ted
u
s
in
g
Gr
id
Sear
ch
C
V,
an
d
ex
p
lain
ed
th
r
o
u
g
h
m
ath
e
m
atica
l f
o
r
m
u
latio
n
s
:
−
Activ
atio
n
f
u
n
ctio
n
a
n
d
k
er
n
e
l
in
itializer
:
T
h
e
s
ca
led
ex
p
o
n
en
tial
lin
ea
r
u
n
it
(
SEL
U)
f
u
n
ctio
n
,
d
ef
in
ed
as in
(
1
)
:
{
>
0
−
≤
0
(
1
)
alo
n
g
with
th
e
L
eCu
n
n
o
r
m
al
in
itializatio
n
,
h
as
b
ee
n
e
m
p
lo
y
ed
to
in
itialize
weig
h
t
s
an
d
b
iases
.
SEL
U
f
ac
ilit
ates
s
elf
-
n
o
r
m
aliza
tio
n
b
y
en
s
u
r
i
n
g
a
m
ea
n
o
f
0
an
d
v
ar
ian
ce
o
f
1
ac
r
o
s
s
lay
er
s
,
w
h
ich
is
p
ar
ticu
lar
ly
ef
f
ec
tiv
e
in
d
ee
p
n
etwo
r
k
s
p
r
o
n
e
to
th
e
v
an
is
h
in
g
/ex
p
lo
d
in
g
g
r
ad
i
en
t p
r
o
b
lem
.
−
L
ea
r
n
in
g
r
ate
a
n
d
o
p
tim
izer
s
:
T
h
r
o
u
g
h
Gr
id
Sear
c
h
C
V,
th
e
lear
n
in
g
r
ate
η
an
d
o
p
tim
izer
s
lik
e
Nad
am
,
a
v
ar
ian
t o
f
Ad
am
in
c
o
r
p
o
r
atin
g
Nester
o
v
m
o
m
e
n
tu
m
,
wer
e
e
v
alu
ated
f
o
r
o
p
tim
al
p
er
f
o
r
m
a
n
ce
.
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:
2
5
0
2
-
4
7
52
E
xp
erimen
ta
l stu
d
y
o
f a
med
ic
a
l d
a
ta
a
n
a
lysi
s
mo
d
el
b
a
s
ed
o
n
co
mp
a
r
a
tive
…
(
A
ig
erim I
s
mu
kh
a
med
o
v
a
)
675
−
E
p
o
ch
s
an
d
b
atch
s
ize:
T
h
e
n
u
m
b
er
o
f
e
p
o
ch
s
an
d
th
e
m
in
i
-
b
atch
s
ize
m
wer
e
o
p
tim
ized
to
b
alan
ce
th
e
tr
ad
e
-
o
f
f
b
etwe
en
c
o
m
p
u
tatio
n
al
ef
f
icien
cy
a
n
d
m
o
d
el
p
e
r
f
o
r
m
an
ce
.
B
y
em
p
lo
y
in
g
Gr
id
Sear
c
h
C
V,
ea
ch
h
y
p
e
r
p
ar
am
ete
r
was
s
y
s
tem
atica
lly
v
ar
ied
an
d
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
was e
v
alu
ated
,
lead
in
g
t
o
th
e
s
elec
tio
n
o
f
th
e
h
y
p
e
r
p
ar
a
m
eter
s
th
at
y
ield
ed
th
e
b
est v
alid
ati
o
n
p
er
f
o
r
m
a
n
ce
.
2
.
4
.
E
v
a
lua
t
i
o
n m
et
rics f
o
r
cla
s
s
if
ica
t
io
n m
o
dels
I
n
ass
ess
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
class
if
icatio
n
m
o
d
els
with
in
ML
an
d
DL
.
Sev
er
al
k
e
y
m
etr
ics
ar
e
u
s
ed
:
p
r
ec
is
io
n
,
r
ec
all
[
75
]
,
F
1
-
s
co
r
e
[
75
]
,
[
76
]
,
ac
cu
r
ac
y
,
a
n
d
th
e
co
n
f
u
s
io
n
m
atr
ix
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
is
a
cr
u
cial
to
o
l
th
at
ca
teg
o
r
ize
s
p
r
ed
ictio
n
s
in
to
f
o
u
r
ty
p
es
(
Fig
u
r
e
1
)
:
T
r
u
e
Po
s
itiv
es
(
T
P),
T
r
u
e
Neg
ativ
es
(
T
N)
,
Fals
e
P
o
s
itiv
es (
FP
)
,
an
d
Fals
e
Neg
ativ
es (
FN)
.
Fig
u
r
e
1
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
r
co
n
tin
g
en
c
y
tab
le
T
h
ese
q
u
ad
r
a
n
ts
en
ab
le
u
s
to
c
o
m
p
u
te
th
e
f
o
llo
win
g
m
etr
ics:
A.
Acc
u
r
ac
y
:
T
h
e
o
v
er
all
co
r
r
ec
t
n
ess
o
f
th
e
m
o
d
el,
p
r
esen
ted
in
(
2
):
=
+
+
+
+
(
2
)
B.
Pre
cisi
o
n
:
th
e
r
atio
o
f
c
o
r
r
ec
t
p
o
s
itiv
e
p
r
ed
ictio
n
s
to
all
p
o
s
itiv
e
p
r
ed
ictio
n
s
,
p
r
esen
ted
in
(
3
):
=
+
(
3
)
C.
R
ec
all
(
Sen
s
itiv
ity
)
:
th
e
r
atio
o
f
ac
tu
al
p
o
s
itiv
es c
o
r
r
ec
tly
id
en
tifie
d
,
p
r
esen
ted
in
(
4
):
=
+
(
4
)
D.
F1
-
s
co
r
e:
a
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
p
r
esen
ted
in
(
5
):
1
−
=
2
×
×
+
(
5
)
T
o
s
y
s
tem
atize
th
ese
co
m
p
u
tatio
n
s
,
o
n
e
m
ay
d
ef
in
e
a
v
ec
to
r
y
r
ep
r
esen
tin
g
ac
t
u
al
class
la
b
els
an
d
a
v
ec
to
r
̂
f
o
r
p
r
ed
icted
lab
els.
T
h
ese
v
ec
to
r
s
s
er
v
e
as
in
p
u
ts
t
o
f
u
n
ctio
n
s
ca
lc
u
latin
g
ea
c
h
m
etr
ic,
ef
f
ec
tiv
el
y
tr
an
s
f
o
r
m
in
g
th
e
class
if
icatio
n
p
r
o
b
lem
in
to
a
m
at
h
em
atica
l
ev
alu
atio
n
.
I
t is p
r
esen
ted
in
(
6
):
(
,
̂
)
→
(
6
)
wh
er
e
th
e
f
u
n
ctio
n
"m
etr
ic"
c
o
u
ld
b
e
an
y
o
f
th
e
b
e
f
o
r
em
e
n
t
io
n
ed
m
etr
ics,
a
n
d
R
r
e
p
r
esen
t
s
th
e
r
ea
l
n
u
m
b
er
s
,
in
d
icatin
g
th
at
ea
ch
m
etr
ic
p
r
o
v
id
es a
r
ea
l
-
v
alu
e
d
o
u
tc
o
m
e
r
e
p
r
esen
ti
n
g
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
.
Fu
r
th
er
in
th
e
s
tu
d
y
we
will
b
u
ild
a
v
is
u
al
r
ep
r
esen
tatio
n
i
n
th
e
f
o
r
m
o
f
a
m
i
x
in
g
m
atr
i
x
u
s
in
g
th
e
Py
th
o
n
lib
r
ar
y
Ma
tp
l
o
tlib
o
r
Seab
o
r
n
,
wh
ich
allo
ws
an
im
m
ed
iate
g
r
ap
h
ical
in
ter
p
r
etatio
n
o
f
th
e
class
if
ier
r
esu
lts
.
I
n
p
r
ac
tice,
m
etr
ics ar
e
o
f
p
ar
a
m
o
u
n
t im
p
o
r
ta
n
ce
wh
e
n
f
in
e
-
tu
n
in
g
class
if
icatio
n
m
o
d
els,
esp
ec
ially
in
d
o
m
ain
s
with
u
n
b
ala
n
ce
d
d
at
asets
,
wh
er
e
ac
cu
r
ac
y
alo
n
e
m
ay
n
o
t
r
ef
lect
th
e
tr
u
e
p
r
e
d
ictiv
e
p
o
wer
o
f
th
e
m
o
d
el.
T
h
u
s
,
th
e
s
elec
tio
n
o
f
ap
p
r
o
p
r
iate
m
etr
ics
is
n
ec
ess
a
r
y
to
en
s
u
r
e
th
at
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
is
tr
u
ly
in
d
icativ
e
o
f
its
ab
ilit
y
to
g
en
er
alize
to
n
ew,
as
-
y
et
-
u
n
a
cq
u
ir
ed
d
ata.
2
.
5
.
Da
t
a
prepa
ra
t
i
o
n a
nd
pre
-
pro
ce
s
s
ing
Data
f
r
o
m
th
e
MI
MI
C
-
I
I
I
d
atab
ase
was
u
s
ed
,
f
o
cu
s
in
g
o
n
d
iab
etic
p
atien
t
r
ec
o
r
d
s
in
clu
d
in
g
d
em
o
g
r
a
p
h
ics,
m
ed
ical
h
is
to
r
y
,
m
ed
icatio
n
s
,
an
d
h
o
s
p
italiz
atio
n
s
.
T
h
e
b
r
o
a
d
s
co
p
e
o
f
th
e
d
ata,
b
ey
o
n
d
ju
s
t
d
iab
etes
-
r
elate
d
in
f
o
r
m
atio
n
,
was
co
n
s
id
er
ed
cr
u
cial
f
o
r
id
en
tify
in
g
n
ew
p
r
ed
ictiv
e
f
ac
t
o
r
s
.
Data
clea
n
s
in
g
in
v
o
lv
ed
r
em
o
v
in
g
r
ec
o
r
d
s
wi
th
m
is
s
in
g
ess
en
tial
in
f
o
r
m
ati
o
n
,
u
s
in
g
im
p
u
tatio
n
f
o
r
s
o
m
e
m
is
s
in
g
v
alu
es,
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
672
-
6
8
4
676
ex
clu
d
in
g
s
u
c
h
r
ec
o
r
d
s
en
tire
ly
.
Nu
m
er
ical
d
ata
was
s
tan
d
ar
d
ized
,
f
o
r
in
s
tan
ce
u
s
in
g
th
e
Z
-
tr
an
s
f
o
r
m
,
an
d
ca
teg
o
r
ical
d
ata
was
en
co
d
e
d
u
s
in
g
m
eth
o
d
s
lik
e
o
n
e
-
h
o
t
en
co
d
in
g
to
f
ac
ilit
ate
ML
p
r
o
ce
s
s
in
g
.
T
h
ese
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
en
s
u
r
ed
d
ata
q
u
ality
an
d
co
n
s
is
ten
cy
,
cr
itical
f
o
r
th
e
ac
cu
r
ac
y
o
f
ML
m
o
d
els.
Mo
d
e
l
s
elec
tio
n
was b
ased
o
n
d
ata
ch
ar
ac
ter
is
tics
r
elev
an
t to
d
iab
et
es c
lass
if
icat
io
n
task
s
.
Dec
is
io
n
tr
ee
,
r
an
d
o
m
f
o
r
est,
an
d
Ad
aBo
o
s
t
m
o
d
els
wer
e
u
s
ed
f
o
r
th
eir
u
n
iq
u
e
ad
v
an
tag
e
s
:
d
ec
is
io
n
tr
ee
s
f
o
r
in
ter
p
r
etab
ilit
y
,
r
an
d
o
m
f
o
r
ests
f
o
r
h
an
d
lin
g
la
r
g
e
d
atasets
an
d
r
esis
tan
ce
t
o
o
v
er
f
itti
n
g
,
an
d
Ad
aBo
o
s
t
f
o
r
b
o
o
s
tin
g
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
wea
k
e
r
class
if
ier
s
[
59
]
.
Hy
p
er
p
ar
a
m
eter
tu
n
i
n
g
was
ca
r
r
ied
o
u
t
u
s
in
g
Gr
id
Sear
ch
o
r
R
an
d
o
m
Sear
ch
t
o
o
p
tim
ize
m
o
d
el
s
ettin
g
s
,
f
o
cu
s
in
g
o
n
p
ar
am
et
er
s
lik
e
tr
ee
n
u
m
b
er
an
d
d
e
p
th
f
o
r
r
an
d
o
m
f
o
r
ests
,
an
d
iter
atio
n
co
u
n
t
an
d
lear
n
i
n
g
r
ate
f
o
r
Ad
aBo
o
s
t.
T
h
is
tu
n
in
g
h
elp
s
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
an
ce
an
d
a
d
d
r
ess
o
v
er
f
itti
n
g
o
r
u
n
d
e
r
f
i
ttin
g
.
Featu
r
e
im
p
o
r
tan
ce
a
n
aly
s
is
,
lik
e
th
e
f
ea
tu
r
e_
im
p
o
r
tan
ce
s
_
attr
ib
u
t
e
in
r
an
d
o
m
f
o
r
ests
,
was
u
tili
ze
d
to
id
en
tify
k
ey
p
r
ed
ict
o
r
s
s
u
ch
as
b
lo
o
d
g
lu
co
s
e
lev
el,
B
MI
,
ag
e,
an
d
g
en
d
er
,
aid
i
n
g
in
m
o
d
el
in
te
r
p
r
etatio
n
an
d
f
o
cu
s
in
g
o
n
cr
itica
l d
ata
asp
ec
ts
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
M
et
ho
ds
o
f
co
m
pa
riso
n a
nd
re
s
ults o
bta
ined
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
e
ls
was
as
s
ess
ed
u
s
in
g
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
F1
-
s
co
r
e
,
r
ec
all,
an
d
p
r
ec
is
io
n
.
T
h
is
en
ab
les
co
m
p
ar
is
o
n
o
f
th
e
m
o
d
els
b
o
th
in
o
v
er
all
ter
m
s
an
d
in
s
p
ec
if
ic
asp
ec
ts
o
f
class
if
icatio
n
.
T
h
e
f
o
llo
win
g
s
tep
s
wer
e
u
n
d
er
tak
en
:
A.
I
m
p
o
r
te
d
all
th
e
n
ec
ess
ar
y
lib
r
ar
ies:
−
p
an
d
as
−
numpy
−
m
atp
lo
tlip
−
s
ea
b
o
r
n
−
s
k
lear
n
B.
L
o
ad
ed
p
r
o
ce
s
s
ed
d
iab
etes
d
a
ta
f
r
o
m
th
e
Dis
ea
s
es
tab
le
an
d
an
o
n
y
m
ize
d
p
atien
t
d
ata
f
r
o
m
th
e
Patien
ts
tab
le.
W
e
al
s
o
m
er
g
ed
th
ese
d
ata
b
y
k
ey
co
lu
m
n
s
.
W
e
o
b
tain
ed
th
e
f
in
al
d
ataf
r
am
e
with
th
e
f
o
llo
win
g
d
im
en
s
io
n
s
:
−
Nu
m
b
er
o
f
Patien
ts
with
Diab
etes: (
5
5
2
3
3
6
,
1
3
)
−
Nu
m
b
er
o
f
Patien
ts
with
o
u
t D
iab
etes: (
1
5
9
6
9
,
1
3
)
−
Nu
m
b
er
o
f
Fin
al
b
alan
ce
d
Data
f
r
am
e:
(
3
1
9
3
8
,
1
3
)
C.
Nex
t,
we
b
eg
in
o
u
r
m
o
d
elin
g
−
I
m
p
o
r
tin
g
th
e
n
ec
ess
ar
y
lib
r
ar
ies.
T
h
e
co
d
e
s
tar
ts
b
y
im
p
o
r
tin
g
class
es
f
r
o
m
th
e
s
k
lear
n
lib
r
ar
y
u
s
ed
f
o
r
cr
o
s
s
-
v
alid
atio
n
an
d
v
ar
io
u
s
class
if
icatio
n
alg
o
r
ith
m
s
.
−
Set th
e
in
itial st
a
te
o
f
th
e
r
an
d
o
m
n
u
m
b
er
g
e
n
er
ato
r
.
R
an
d
o
m
_
s
tate
=
2
en
s
u
r
es r
ep
r
o
d
u
ci
b
ilit
y
o
f
r
esu
lts
b
y
s
ettin
g
th
e
in
itial st
ate
f
o
r
t
h
e
r
an
d
o
m
n
u
m
b
e
r
g
en
e
r
ato
r
.
−
C
r
ea
tin
g
a
lis
t
o
f
class
if
ier
s
.
Var
io
u
s
class
if
icatio
n
alg
o
r
i
th
m
s
ar
e
ad
d
ed
t
o
th
e
lis
t
o
f
class
if
ier
s
,
in
clu
d
in
g
d
ec
is
io
n
tr
ee
class
if
ie
r
an
d
en
s
em
b
le
m
eth
o
d
s
s
u
ch
as
Ad
aB
o
o
s
t
class
if
ier
,
r
an
d
o
m
f
o
r
est
class
if
ier
,
ex
tr
a
tr
ee
s
class
if
ier
,
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
class
if
ier
.
−
Usi
n
g
cr
o
s
s
-
v
alid
atio
n
with
f
i
v
e
p
ar
titi
o
n
s
(
k
f
o
ld
=
5
)
,
th
e
c
o
d
e
e
v
alu
ates
ea
ch
class
if
ier
o
n
th
e
tr
ain
in
g
d
ataset
X_
tr
ain
with
y
_
tr
ain
r
e
s
p
o
n
s
es u
s
in
g
th
e
ac
cu
r
ac
y
m
e
tr
ic.
−
Fo
r
ea
ch
class
if
ier
,
th
e
av
er
ag
e
ac
cu
r
ac
y
an
d
s
tan
d
a
r
d
d
ev
iatio
n
o
f
th
e
cr
o
s
s
-
v
alid
ati
o
n
r
esu
lts
ar
e
co
m
p
u
ted
.
−
A
b
ar
ch
ar
t
is
cr
ea
ted
th
at
s
h
o
ws
th
e
av
er
ag
e
ac
cu
r
ac
y
(
m
ea
n
o
f
th
e
cr
o
s
s
-
v
alid
atio
n
s
c
o
r
es)
f
o
r
ea
c
h
alg
o
r
ith
m
with
th
e
s
tan
d
ar
d
d
e
v
iat
io
n
o
f
t
h
e
er
r
o
r
s
.
T
h
e
b
ar
c
h
ar
t h
as b
ee
n
illu
s
tr
ated
in
Fig
u
r
e
2
.
T
h
e
d
iag
r
am
s
h
o
ws
th
at
g
r
ad
ien
t
b
o
o
s
tin
g
class
if
ier
h
as
th
e
h
ig
h
est
a
v
er
ag
e
ac
cu
r
ac
y
wh
ile
d
ec
is
io
n
tr
e
e
class
if
ier
h
as
th
e
lo
west.
T
h
is
s
u
g
g
ests
th
at
en
s
em
b
le
lear
n
i
n
g
b
ased
m
o
d
els
g
e
n
er
al
ly
o
u
tp
er
f
o
r
m
th
e
s
im
p
le
d
ec
is
io
n
tr
ee
class
if
ier
,
p
r
o
b
a
b
ly
d
u
e
to
th
eir
ab
ilit
y
to
g
en
er
alize
b
etter
an
d
r
e
d
u
ce
o
v
er
f
itt
in
g
.
T
h
e
Fig
u
r
e
3
d
elin
ea
tes
a
q
u
an
titativ
e
ev
alu
atio
n
o
f
f
iv
e
d
is
tin
ct
class
if
icatio
n
alg
o
r
ith
m
s
.
Per
f
o
r
m
an
ce
m
etr
ics
ar
e
ag
g
r
eg
ated
f
r
o
m
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
d
u
r
es,
wh
ich
ar
e
in
s
tr
u
m
en
tal
in
ass
ess
in
g
th
e
r
o
b
u
s
tn
ess
o
f
ea
ch
m
o
d
e
l.
T
h
e
m
etr
ics
co
n
s
id
er
ed
a
r
e
th
e
m
ea
n
ac
cu
r
ac
y
(
C
r
o
s
s
ValM
ea
n
s
)
an
d
th
e
ass
o
ciate
d
s
tan
d
ar
d
er
r
o
r
(
C
r
o
s
s
Vale
r
r
o
r
s
)
,
d
er
iv
ed
f
r
o
m
t
h
e
cr
o
s
s
-
v
alid
atio
n
s
co
r
es.
Var
iab
les d
escr
ib
ed
:
−
C
r
o
s
s
ValM
ea
n
s
:
T
h
is
co
lu
m
n
r
ep
r
esen
ts
th
e
m
ea
n
ac
cu
r
ac
y
s
co
r
e
o
b
tain
ed
f
r
o
m
th
e
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
s
s
.
Acc
u
r
ac
y
is
a
co
m
m
o
n
m
etr
ic
in
m
o
d
el
ev
alu
atio
n
,
in
d
icatin
g
th
e
r
ati
o
o
f
co
r
r
ec
tly
p
r
ed
icted
o
b
s
er
v
atio
n
s
to
th
e
to
tal
o
b
s
er
v
atio
n
s
.
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:
2
5
0
2
-
4
7
52
E
xp
erimen
ta
l stu
d
y
o
f a
med
ic
a
l d
a
ta
a
n
a
lysi
s
mo
d
el
b
a
s
ed
o
n
co
mp
a
r
a
tive
…
(
A
ig
erim I
s
mu
kh
a
med
o
v
a
)
677
−
C
r
o
s
s
Vale
r
r
o
r
s
:
T
h
is
co
lu
m
n
in
d
icate
s
th
e
s
tan
d
ar
d
er
r
o
r
o
f
th
e
m
ea
n
ac
cu
r
ac
y
s
co
r
es
ac
r
o
s
s
th
e
cr
o
s
s
-
v
alid
atio
n
f
o
ld
s
.
A
lo
wer
v
alu
e
h
er
e
s
u
g
g
ests
h
ig
h
er
s
tab
ilit
y
in
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
d
ata
s
u
b
s
ets.
Fig
u
r
e
2
.
T
h
e
d
iag
r
am
s
h
o
ws t
h
e
cr
o
s
s
-
v
alid
atio
n
r
esu
lts
f
o
r
ea
ch
o
f
th
e
alg
o
r
ith
m
s
Fig
u
r
e
3
.
C
o
m
p
a
r
ativ
e
p
e
r
f
o
r
m
an
ce
o
f
class
if
icatio
n
alg
o
r
ith
m
s
Fro
m
th
e
d
ata
p
r
o
v
id
ed
,
we
ca
n
in
f
er
t
h
e
f
o
llo
win
g
:
−
T
h
e
Ad
aBo
o
s
t
alg
o
r
ith
m
ex
h
ib
its
th
e
h
ig
h
est
m
ea
n
ac
cu
r
ac
y
(
0
.
9
1
5
4
5
9
)
with
a
s
tan
d
ar
d
er
r
o
r
o
f
0
.
0
0
4
5
4
3
,
s
u
g
g
esti
n
g
it
n
o
t
o
n
ly
p
er
f
o
r
m
s
well
o
n
av
er
ag
e
b
u
t
also
m
ain
tain
s
co
n
s
is
ten
t
p
er
f
o
r
m
an
c
e
ac
r
o
s
s
d
if
f
er
en
t su
b
s
ets o
f
th
e
d
ata.
−
T
h
e
Gr
ad
ie
n
tB
o
o
s
tin
g
alg
o
r
it
h
m
s
h
o
ws
s
ig
n
i
f
ican
tly
l
o
wer
m
ea
n
ac
c
u
r
ac
y
(
0
.
6
3
3
4
3
2
)
wi
th
a
r
elativ
ely
h
ig
h
er
s
tan
d
ar
d
er
r
o
r
(
0
.
0
0
4
9
4
4
)
,
wh
ic
h
co
u
ld
i
n
d
icate
less
r
eliab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
th
e
cr
o
s
s
-
v
alid
atio
n
f
o
l
d
s
.
−
T
h
e
r
em
ain
in
g
alg
o
r
ith
m
s
—
Dec
is
io
n
T
r
ee
,
R
an
d
o
m
Fo
r
est,
an
d
E
x
tr
a
T
r
ee
s
—
d
is
p
lay
m
o
d
er
ate
m
ea
n
ac
cu
r
ac
ies with
Dec
is
io
n
T
r
ee
h
av
in
g
t
h
e
least c
o
n
s
is
ten
cy
,
a
s
s
u
g
g
ested
b
y
th
e
h
ig
h
er
s
tan
d
ar
d
er
r
o
r
.
T
h
is
co
m
p
ar
is
o
n
is
cr
u
cial
f
o
r
m
o
d
el
s
elec
tio
n
in
a
d
ata
s
cien
ce
p
r
o
ject.
T
h
e
Ad
aBo
o
s
t
m
o
d
el
wo
u
ld
b
e
a
s
tr
o
n
g
ca
n
d
id
ate
f
o
r
f
u
r
th
er
r
ef
i
n
em
en
t
a
n
d
test
in
g
,
g
iv
en
its
s
u
p
er
i
o
r
m
ea
n
ac
c
u
r
ac
y
an
d
c
o
n
s
is
ten
t
cr
o
s
s
-
v
alid
atio
n
p
er
f
o
r
m
an
ce
.
I
n
co
n
tr
ast,
th
e
lo
wer
ac
cu
r
a
cy
o
f
Gr
ad
ien
tB
o
o
s
tin
g
war
r
a
n
ts
an
in
v
esti
g
atio
n
in
to
wh
eth
er
th
e
m
o
d
el'
s
co
m
p
lex
ity
is
ap
p
r
o
p
r
iate
f
o
r
th
e
d
ata
o
r
if
its
p
ar
am
eter
s
n
ee
d
ad
ju
s
tm
en
t.
D.
Nex
t,
we
s
tar
ted
to
im
p
lem
e
n
t
h
y
p
e
r
p
ar
am
eter
s
elec
tio
n
f
o
r
v
ar
io
u
s
ML
alg
o
r
ith
m
s
u
s
in
g
Gr
id
Sear
ch
p
ar
am
eter
en
u
m
er
atio
n
an
d
esti
m
atio
n
u
s
in
g
cr
o
s
s
-
v
alid
atio
n
.
Deta
iled
d
escr
ip
tio
n
:
−
I
n
itializatio
n
o
f
E
s
tim
ato
r
Selectio
n
Help
er
(
E
s
tim
ato
r
Sel
ec
tio
n
Help
er
)
.
T
h
e
c
o
n
s
tr
u
cto
r
ac
ce
p
ts
d
ictio
n
ar
ies
with
m
o
d
els
an
d
th
eir
co
r
r
esp
o
n
d
in
g
h
y
p
er
p
a
r
am
eter
s
.
I
t
is
ch
ec
k
ed
th
at
p
ar
am
eter
s
ar
e
p
r
o
v
id
e
d
f
o
r
ea
ch
m
o
d
el.
−
F
i
t
f
u
n
c
t
i
o
n
.
A
G
r
i
d
S
e
a
r
c
h
C
V
i
s
e
x
e
c
u
t
e
d
f
o
r
e
a
c
h
m
o
d
e
l
,
w
h
i
c
h
s
y
s
t
e
m
a
t
i
c
a
l
l
y
w
o
r
k
s
t
h
r
o
u
g
h
t
h
e
c
o
m
b
i
n
a
t
i
o
n
s
o
f
p
a
r
a
m
e
t
e
r
s
p
r
o
v
i
d
e
d
i
n
p
a
r
a
m
s
,
e
v
a
l
u
a
t
i
n
g
e
a
c
h
c
o
m
b
i
n
a
t
i
o
n
u
s
i
n
g
c
v
f
o
l
d
c
r
o
s
s
-
v
a
l
i
d
a
t
i
o
n
.
−
Sco
r
e_
s
u
m
m
ar
y
f
u
n
ctio
n
.
C
o
llects
Gr
id
Sear
ch
C
V
r
esu
lts
an
d
cr
ea
tes
a
s
u
m
m
ar
y
tab
le
in
clu
d
in
g
th
e
m
in
im
u
m
,
m
ax
im
u
m
,
m
ea
n
,
a
n
d
s
tan
d
ar
d
d
ev
iatio
n
o
f
test
s
co
r
es.
T
h
e
tab
le
is
s
o
r
te
d
b
y
t
h
e
m
ea
n
s
co
r
e
(
o
r
o
th
er
s
p
ec
if
ied
c
r
iter
io
n
)
t
o
s
h
o
w
th
e
b
est co
m
b
in
atio
n
s
o
f
p
ar
a
m
eter
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
672
-
6
8
4
678
−
C
r
ea
tin
g
m
o
d
els
an
d
p
ar
am
s
.
I
n
m
o
d
els
an
d
p
ar
am
s
,
th
e
cla
s
s
if
ier
s
an
d
h
y
p
er
p
ar
am
eter
s
f
o
r
th
e
s
ea
r
c
h
ar
e
s
p
ec
if
ied
.
Fo
r
ex
am
p
le,
m
ax
_
d
ep
t
h
is
s
elec
ted
f
o
r
th
e
Dec
is
io
n
T
r
ee
C
lass
if
ier
an
d
lear
n
in
g
_
r
ate
a
n
d
n
_
esti
m
ato
r
s
ar
e
s
elec
ted
f
o
r
t
h
e
Ad
aBo
o
s
tC
lass
if
ier
.
−
An
in
s
tan
ce
o
f
E
s
tim
ato
r
Selec
tio
n
Help
er
is
cr
ea
ted
with
th
e
s
p
ec
if
ied
m
o
d
els an
d
p
ar
am
et
er
s
.
T
h
e
r
esu
lt
is
a
co
n
s
o
le
o
u
tp
u
t
o
f
m
o
d
el
n
am
es
an
d
a
tab
le
th
at
s
o
r
ts
th
e
m
o
d
els
b
y
th
eir
p
er
f
o
r
m
a
n
ce
g
iv
en
th
e
co
n
f
ig
u
r
e
d
h
y
p
er
p
ar
am
eter
s
.
T
h
is
tab
le
h
elp
s
to
d
eter
m
in
e
wh
ich
m
o
d
els
an
d
p
ar
am
eter
s
ets
wo
r
k
b
est
f
o
r
a
g
iv
en
class
if
icatio
n
task
.
T
h
is
tab
le
h
as
b
ee
n
illu
s
tr
ated
in
Fig
u
r
e
4
,
wh
ich
p
r
esen
ts
th
e
r
esu
lt
s
o
f
h
y
p
er
p
ar
a
m
eter
s
elec
tio
n
f
o
r
d
if
f
er
en
t
class
if
icatio
n
alg
o
r
ith
m
s
u
s
in
g
Gr
id
Sear
c
h
.
E
ac
h
r
o
w
o
f
th
e
tab
le
co
r
r
esp
o
n
d
s
to
a
p
a
r
ticu
lar
co
m
b
in
atio
n
o
f
p
a
r
am
eter
s
f
o
r
a
p
ar
ticu
lar
alg
o
r
ith
m
.
T
h
e
tab
le
p
r
o
v
id
es th
e
f
o
llo
wi
n
g
in
f
o
r
m
atio
n
o
n
t
h
e
h
y
p
er
p
a
r
am
eter
s
:
−
esti
m
ato
r
.
T
h
is
p
ar
am
eter
in
d
i
ca
tes th
e
class
if
ier
f
o
r
wh
ich
t
h
e
p
ar
am
eter
s
wer
e
f
itted
.
−
m
in
_
s
co
r
e,
m
ea
n
_
s
co
r
e,
m
ax
_
s
co
r
e.
T
h
ese
p
ar
am
eter
s
in
d
icate
th
e
m
in
im
u
m
,
m
ea
n
an
d
m
ax
im
u
m
ac
cu
r
ac
y
ac
h
ie
v
ed
b
y
th
e
m
o
d
el
o
n
th
e
cr
o
s
s
-
v
alid
atio
n
d
ata
s
ets.
−
s
td
_
s
co
r
e.
T
h
is
p
ar
am
eter
in
d
i
ca
tes
th
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
ac
cu
r
ac
y
,
r
ef
lectin
g
th
e
v
ar
iat
io
n
in
m
o
d
e
l
p
er
f
o
r
m
an
ce
o
n
d
if
f
er
en
t c
r
o
s
s
-
v
alid
atio
n
f
o
ld
s
.
−
lear
n
in
g
_
r
ate,
m
ax
_
d
ep
th
,
m
a
x
_
f
ea
tu
r
es.
T
h
ese
h
y
p
er
p
ar
am
eter
s
wer
e
p
ick
ed
u
p
d
u
r
in
g
t
h
e
Gr
id
Sear
ch
p
r
o
ce
s
s
.
NaN
v
alu
es m
ea
n
th
a
t th
e
p
ar
am
eter
was n
o
t a
p
p
lie
d
to
th
is
m
o
d
el.
T
h
e
tab
le
s
h
o
ws
th
at
g
r
a
d
ien
t
b
o
o
s
tin
g
class
if
ier
g
en
er
a
lly
p
er
f
o
r
m
s
b
etter
in
ter
m
s
o
f
m
ea
n
ac
cu
r
ac
y
(
m
ea
n
_
s
co
r
e
)
with
d
if
f
er
en
t
co
m
b
in
atio
n
s
o
f
h
y
p
e
r
p
ar
am
eter
s
.
Mo
d
els
with
a
m
ax
im
u
m
tr
ee
d
e
p
t
h
(
m
ax
_
d
e
p
th
)
o
f
9
an
d
m
ax
_
f
ea
tu
r
es
s
et
to
au
to
o
r
s
q
r
t
g
i
v
e
th
e
b
est
r
esu
lts
.
T
h
is
m
ay
in
d
icate
th
at
m
o
r
e
co
m
p
lex
m
o
d
els
p
e
r
f
o
r
m
b
ett
er
,
b
u
t
it
is
im
p
o
r
tan
t
to
k
ee
p
an
ey
e
o
n
o
v
er
tr
ai
n
in
g
.
T
h
e
lear
n
in
g
_
r
ate
a
n
d
m
ax
_
f
ea
tu
r
es
co
lu
m
n
s
d
o
n
o
t
ap
p
ly
to
all
m
o
d
els
d
u
e
to
th
e
s
p
ec
if
ic
n
atu
r
e
o
f
th
e
alg
o
r
i
th
m
s
.
Fo
r
ex
am
p
le,
m
ax
_
f
ea
tu
r
es d
o
es n
o
t a
p
p
ly
t
o
Ad
aBo
o
s
t c
lass
if
ier
an
d
d
ec
i
s
io
n
tr
ee
class
if
ier
in
th
is
s
etti
n
g
.
Fig
u
r
e
4
.
R
esu
lts
o
f
m
o
d
els an
d
s
elec
ted
h
y
p
e
r
p
ar
am
eter
s
E.
Su
b
s
eq
u
en
tly
,
we
co
n
d
u
cted
t
h
e
f
in
al
tu
n
in
g
a
n
d
ev
alu
atio
n
o
f
s
ev
er
al
class
if
icatio
n
m
o
d
els o
n
test
d
ata.
Utilizin
g
tr
ain
in
g
a
n
d
test
in
g
ac
cu
r
ac
y
d
ata,
as
well
as
p
r
ec
i
s
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
m
et
r
ics
f
o
r
m
o
d
el
co
m
p
ar
is
o
n
,
th
e
f
o
llo
win
g
p
r
o
ce
d
u
r
es we
r
e
ex
ec
u
ted
:
−
I
m
p
o
r
tat
io
n
o
f
t
h
e
m
etr
ics
lib
r
ar
y
.
T
h
e
co
d
e
c
o
m
m
en
c
es
with
th
e
im
p
o
r
tatio
n
o
f
f
u
n
ctio
n
s
f
o
r
co
m
p
u
tin
g
th
e
m
o
d
el'
s
q
u
ality
m
etr
ics.
−
I
n
itializatio
n
o
f
class
if
ier
s
with
s
p
ec
if
ic
h
y
p
er
p
ar
am
eter
s
.
A
li
s
t
o
f
clas
s
if
ier
s
i
s
g
en
er
ated
,
ea
c
h
eq
u
ip
p
e
d
with
th
e
o
p
tim
al
h
y
p
e
r
p
ar
am
eter
s
d
eter
m
i
n
ed
d
u
r
in
g
th
e
p
r
e
v
io
u
s
Gr
id
Sear
c
h
p
h
ase.
−
Mo
d
el
tr
ain
in
g
a
n
d
p
r
ed
ictio
n
.
E
ac
h
m
o
d
el
is
tr
ain
ed
o
n
th
e
tr
ain
in
g
d
ataset
(
X_
tr
ain
,
y
_
tr
ain
)
a
n
d
s
u
b
s
eq
u
en
tly
m
a
k
es p
r
ed
ictio
n
s
o
n
th
e
test
d
ataset
(
X_
test
)
.
−
C
alcu
latio
n
o
f
m
etr
ics.
Fo
r
ea
ch
m
o
d
el,
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ar
e
co
m
p
u
ted
b
o
th
o
n
th
e
tr
ain
in
g
a
n
d
th
e
test
d
atase
ts
.
−
R
ep
o
r
tin
g
o
f
r
esu
lts
.
T
h
e
ca
l
cu
lated
m
etr
ics
f
o
r
ea
ch
m
o
d
el
ar
e
o
u
tp
u
tted
,
al
o
n
g
with
a
class
if
icatio
n
r
ep
o
r
t a
n
d
co
n
f
u
s
io
n
m
atr
ix
.
T
h
e
ca
lcu
lated
m
et
r
ics,
co
n
f
u
s
io
n
m
atr
ix
(
7
)
an
d
class
if
icatio
n
r
ep
o
r
t
as
s
h
o
wn
in
T
ab
le
1
f
o
r
Dec
is
io
n
T
r
ee
m
o
d
el
ar
e
r
ep
r
e
s
en
ted
b
elo
w:
−
Acc
u
r
ac
y
: 1
.
0
; F1
s
co
r
e:
1
.
0
;
R
ec
all: 1
.
0
; Pr
ec
is
io
n
: 1
.
0
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:
2
5
0
2
-
4
7
52
E
xp
erimen
ta
l stu
d
y
o
f a
med
ic
a
l d
a
ta
a
n
a
lysi
s
mo
d
el
b
a
s
ed
o
n
co
mp
a
r
a
tive
…
(
A
ig
erim I
s
mu
kh
a
med
o
v
a
)
679
[
3617
1165
2273
2527
]
(
7
)
T
ab
le
1
.
T
h
e
class
if
icatio
n
r
ep
o
r
t f
o
r
d
ec
is
io
n
tr
ee
m
o
d
el
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
F
a
l
se
0
.
6
1
0
.
7
6
0
.
6
8
4
7
8
2
Tr
u
e
0
.
6
8
0
.
5
3
0
.
6
0
4
8
0
0
a
c
c
u
r
a
c
y
0
.
6
4
9
5
8
2
mac
r
o
a
v
g
0
.
6
5
0
.
6
4
0
.
6
4
9
5
8
2
w
e
i
g
h
t
e
d
a
v
g
0
.
6
5
0
.
6
4
0
.
6
4
9
5
8
2
T
h
e
ca
lcu
lated
m
etr
ics,
co
n
f
u
s
io
n
m
atr
ix
(
8
)
an
d
class
if
icatio
n
r
ep
o
r
t
as
s
h
o
wn
in
T
ab
le
2
f
o
r
Ad
aBo
o
s
t m
o
d
el
ar
e
r
e
p
r
esen
t
ed
b
elo
w:
−
Acc
u
r
ac
y
: 1
.
0
; F1
s
co
r
e:
1
.
0
;
R
ec
all: 0
.
0
; Pr
ec
is
io
n
: 1
.
0
[
3526
1256
2720
2080
]
(
8
)
T
ab
le
2
.
T
h
e
class
if
icatio
n
r
ep
o
r
t f
o
r
Ad
aBo
o
s
t m
o
d
el
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
F
a
l
se
0
.
5
6
0
.
7
4
0
.
6
4
4
7
8
2
Tr
u
e
0
.
6
2
0
.
4
3
0
.
5
1
4
8
0
0
a
c
c
u
r
a
c
y
0
.
5
9
9
5
8
2
mac
r
o
a
v
g
0
.
5
9
0
.
5
9
0
.
5
8
9
5
8
2
w
e
i
g
h
t
e
d
a
v
g
0
.
5
9
0
.
5
9
0
.
5
8
9
5
8
2
T
h
e
ca
lcu
lated
m
etr
ics,
co
n
f
u
s
io
n
m
atr
ix
(
9
)
an
d
class
if
icatio
n
r
ep
o
r
t
as
s
h
o
wn
in
T
ab
le
3
f
o
r
R
an
d
o
m
Fo
r
est m
o
d
el
a
r
e
r
ep
r
esen
ted
b
elo
w:
−
Acc
u
r
ac
y
: 1
.
0
; F1
s
co
r
e:
1
.
0
;
R
ec
all: 1
.
0
; Pr
ec
is
io
n
: 1
.
0
[
3511
1271
1877
2923
]
(
9
)
T
ab
le
3
.
T
h
e
class
if
icatio
n
r
ep
o
r
t f
o
r
r
an
d
o
m
f
o
r
est m
o
d
el
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
F
a
l
se
0
.
6
5
0
.
7
3
0
.
6
9
4
7
8
2
Tr
u
e
0
.
7
0
0
.
6
1
0
.
6
5
4
8
0
0
a
c
c
u
r
a
c
y
0
.
6
7
9
5
8
2
mac
r
o
a
v
g
0
.
6
7
0
.
6
7
0
.
6
7
9
5
8
2
w
e
i
g
h
t
e
d
a
v
g
0
.
6
7
0
.
6
7
0
.
6
7
9
5
8
2
T
h
e
ca
lcu
lated
m
etr
ics,
co
n
f
u
s
io
n
m
atr
ix
(
10
)
an
d
class
if
icatio
n
r
ep
o
r
t
as
s
h
o
wn
in
T
ab
le
4
f
o
r
E
x
tr
aT
r
ee
s
m
o
d
el
a
r
e
r
ep
r
esen
ted
b
elo
w:
−
Acc
u
r
ac
y
: 1
.
0
; F1
s
co
r
e:
1
.
0
;
R
ec
all: 1
.
0
; Pr
ec
is
io
n
: 1
.
0
[
3462
1320
2097
2703
]
(
10
)
T
ab
le
4
.
T
h
e
class
if
icatio
n
r
ep
o
r
t f
o
r
E
x
tr
aT
r
ee
s
m
o
d
el
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
F
a
l
se
0
.
6
2
0
.
7
2
0
.
6
7
4
7
8
2
Tr
u
e
0
.
6
7
0
.
5
6
0
.
6
1
4
8
0
0
a
c
c
u
r
a
c
y
0
.
6
4
9
5
8
2
mac
r
o
a
v
g
0
.
6
5
0
.
6
4
0
.
6
4
9
5
8
2
w
e
i
g
h
t
e
d
a
v
g
0
.
6
5
0
.
6
4
0
.
6
4
9
5
8
2
T
h
e
ca
lcu
lated
m
etr
ics,
co
n
f
u
s
io
n
m
atr
ix
(
11
)
an
d
class
if
icatio
n
r
ep
o
r
t
as
s
h
o
wn
in
T
ab
le
5
f
o
r
Gr
ad
ien
tB
o
o
s
tin
g
m
o
d
el
a
r
e
r
ep
r
esen
ted
b
elo
w:
−
Acc
u
r
ac
y
: 1
.
0
; F1
s
co
r
e:
1
.
0
;
R
ec
all: 1
.
0
; Pr
ec
is
io
n
: 1
.
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
1
,
Octo
b
er
20
24
:
672
-
6
8
4
680
[
4655
127
675
4125
]
(
11
)
T
ab
le
5
.
T
h
e
class
if
icatio
n
r
ep
o
r
t f
o
r
g
r
ad
ie
n
t
b
o
o
s
tin
g
m
o
d
e
l
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
F
a
l
se
0
.
8
7
0
.
9
7
0
.
9
2
4
7
8
2
Tr
u
e
0
.
9
7
0
.
8
6
0
.
9
1
4
8
0
0
a
c
c
u
r
a
c
y
0
.
9
2
9
5
8
2
mac
r
o
a
v
g
0
.
9
2
0
.
9
2
0
.
9
2
9
5
8
2
w
e
i
g
h
t
e
d
a
v
g
0
.
9
2
0
.
9
2
0
.
9
2
9
5
8
2
−
C
r
ea
tin
g
an
d
o
u
tp
u
ttin
g
a
s
u
m
m
ar
y
tab
le,
r
ep
r
esen
ted
i
n
Fig
u
r
e
5
.
I
t
co
llects
in
f
o
r
m
atio
n
o
n
ea
ch
m
etr
i
c
f
o
r
all
m
o
d
els.
−
Gr
ap
h
co
n
s
tr
u
ctio
n
.
T
h
e
s
u
b
c
ateg
o
r
y
b
ar
f
u
n
ctio
n
is
u
s
ed
to
co
n
s
tr
u
ct
a
g
r
a
p
h
c
o
m
p
ar
i
n
g
th
e
m
o
d
els
o
n
d
if
f
er
en
t m
et
r
ics.
T
h
e
m
o
d
el
c
o
m
p
ar
is
o
n
is
r
ep
r
esen
ted
in
Fi
g
u
r
e
6
.
Fig
u
r
e
5
.
Su
m
m
ar
y
ta
b
le
o
f
ea
ch
m
etr
ic
f
o
r
all
m
o
d
els
Fig
u
r
e
6
.
Gr
a
p
h
co
m
p
ar
in
g
th
e
m
o
d
els o
n
d
if
f
er
e
n
t m
etr
ics
B
as
e
d
o
n
t
h
e
t
a
b
l
e
a
n
d
g
r
a
p
h
,
it
c
a
n
b
e
s
e
e
n
t
h
at
t
h
e
G
r
a
d
ie
n
tB
o
o
s
ti
n
g
C
la
s
s
i
f
i
e
r
m
o
d
e
l
h
as
th
e
h
i
g
h
e
s
t
a
c
c
u
r
a
c
y
o
n
t
h
e
t
es
t
d
at
a
s
e
t
,
a
s
w
e
ll
as
h
i
g
h
s
c
o
r
es
o
n
t
h
e
o
t
h
e
r
m
e
t
r
i
cs
,
m
a
k
i
n
g
i
t
t
h
e
p
r
e
f
e
r
r
e
d
m
o
d
e
l
f
o
r
r
e
al
-
w
o
r
l
d
a
p
p
l
i
c
a
ti
o
n
s
.
T
h
e
r
e
s
u
l
ts
i
n
t
h
e
c
o
n
s
o
le
,
w
h
i
c
h
s
h
o
w
a
c
c
u
r
a
c
y
,
F
1
-
s
c
o
r
e
,
c
o
m
p
l
et
en
e
s
s
,
a
n
d
p
r
e
c
is
i
o
n
e
q
u
a
l
t
o
1
.
0
,
a
r
e
l
i
k
e
l
y
t
h
e
r
e
s
u
l
t
o
f
p
r
e
d
i
c
t
i
o
n
o
n
t
h
e
t
r
a
i
n
i
n
g
d
a
t
a
s
e
t
(
t
r
a
i
n
p
r
e
d
i
ct
i
o
n
)
wh
e
r
e
t
h
e
m
o
d
e
l
h
a
s
a
l
r
e
a
d
y
s
e
e
n
a
ll
t
h
e
a
n
s
w
e
r
s
,
le
a
d
i
n
g
t
o
o
v
e
r
f
i
t
t
i
n
g
.
H
o
w
e
v
er
,
i
n
a
r
e
a
l
s
i
t
u
at
i
o
n
,
i
t
is
i
m
p
o
r
t
a
n
t
t
o
l
o
o
k
a
t
t
h
e
r
e
s
u
l
ts
o
f
t
h
e
t
es
t
d
at
a
s
et
(
p
r
e
d
ic
t
i
o
n
)
,
w
h
i
c
h
is
n
e
w
d
a
ta
t
h
a
t
w
a
s
n
o
t
i
n
v
o
l
v
e
d
i
n
t
r
a
i
n
i
n
g
t
h
e
m
o
d
e
l
.
3
.
2
.
Dis
cus
s
io
n o
f
t
he
lim
it
a
t
io
ns
o
f
curr
ent
m
et
ho
ds
T
h
e
cu
r
r
e
n
t
s
tu
d
y
u
tili
ze
d
co
m
p
u
ter
s
with
lim
ited
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
wh
ich
im
p
o
s
ed
lim
itatio
n
s
o
n
th
e
s
am
p
le
s
ize
to
b
e
p
r
o
ce
s
s
ed
an
d
th
e
c
o
m
p
lex
ity
o
f
th
e
ML
m
o
d
els
u
s
ed
.
I
n
tu
r
n
,
th
is
ca
n
lead
to
m
o
d
els
tr
ain
ed
o
n
s
m
a
ller
s
am
p
les
n
o
t
f
u
lly
r
ef
lecti
n
g
th
e
co
m
p
lex
ity
o
f
t
h
e
d
ata
in
lar
g
er
an
d
m
o
r
e
d
iv
er
s
e
s
ets,
wh
ich
ca
n
r
ed
u
ce
th
e
g
en
er
aliza
b
ilit
y
o
f
th
e
m
o
d
el
an
d
th
e
ac
cu
r
ac
y
o
f
t
h
e
p
r
e
d
ictio
n
s
.
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:
2
5
0
2
-
4
7
52
E
xp
erimen
ta
l stu
d
y
o
f a
med
ic
a
l d
a
ta
a
n
a
lysi
s
mo
d
el
b
a
s
ed
o
n
co
mp
a
r
a
tive
…
(
A
ig
erim I
s
mu
kh
a
med
o
v
a
)
681
L
i
m
i
t
at
i
o
n
s
o
f
t
h
e
c
h
o
s
e
n
m
o
d
e
l
,
i
.
e
.
t
h
e
a
l
g
o
r
i
t
h
m
s
u
s
e
d
,
s
u
c
h
a
s
d
e
c
i
s
i
o
n
t
r
e
es
a
n
d
r
a
n
d
o
m
f
o
r
e
s
t
,
a
l
t
h
o
u
g
h
g
o
o
d
a
t
c
la
s
s
i
f
i
ca
t
i
o
n
t
a
s
k
s
,
m
a
y
b
e
s
u
s
c
e
p
ti
b
l
e
t
o
o
v
e
r
t
r
a
i
n
i
n
g
a
n
d
m
a
y
n
o
t
c
a
p
t
u
r
e
a
l
l
t
h
e
n
u
a
n
c
es
i
n
t
h
e
d
a
t
a
,
w
h
i
c
h
i
s
p
a
r
ti
c
u
l
a
r
l
y
im
p
o
r
t
a
n
t
i
n
d
i
s
e
as
e
p
r
e
d
i
ct
i
o
n
.
S
u
g
g
e
s
t
i
o
n
s
f
o
r
m
o
d
e
l
i
m
p
r
o
v
e
m
e
n
t
:
−
I
m
p
r
o
v
ed
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
ar
e
ju
s
tifie
d
b
ec
au
s
e
th
e
u
s
e
o
f
m
o
r
e
p
o
wer
f
u
l
co
m
p
u
tatio
n
al
h
ar
d
war
e
will
allo
w
p
r
o
ce
s
s
in
g
o
f
lar
g
er
a
m
o
u
n
ts
o
f
d
a
ta,
wh
ich
will
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
a
n
d
r
eliab
ilit
y
o
f
ML
m
o
d
els.
−
Mo
r
e
p
o
wer
f
u
l
r
eso
u
r
ce
s
will
also
allo
w
th
e
u
s
e
o
f
m
o
r
e
s
o
p
h
is
ticated
m
o
d
els,
s
u
ch
a
s
d
ee
p
n
eu
r
a
l
n
etwo
r
k
s
,
wh
ich
ca
n
p
r
o
v
id
e
b
etter
p
er
f
o
r
m
an
ce
f
o
r
p
r
ed
ict
io
n
task
s
.
−
E
x
p
an
d
i
n
g
th
e
d
ataset.
Usi
n
g
a
lar
g
er
an
d
m
o
r
e
d
iv
e
r
s
e
d
ataset
wil
l
h
elp
im
p
r
o
v
e
th
e
g
en
e
r
aliza
b
ilit
y
o
f
m
o
d
els an
d
m
a
k
e
p
r
ed
ictio
n
s
m
o
r
e
ac
cu
r
ate
an
d
r
eliab
le.
−
Ap
p
licatio
n
o
f
d
i
m
e
n
s
io
n
ality
r
ed
u
ctio
n
tech
n
iq
u
es.
Dim
en
s
io
n
ality
r
ed
u
ctio
n
tech
n
iq
u
es
s
u
ch
as
PC
A
(
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
al
y
s
is
)
ca
n
h
elp
r
ed
u
ce
d
ata
co
m
p
lex
ity
a
n
d
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
o
n
lim
ited
co
m
p
u
tatio
n
al
r
eso
u
r
c
es.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
id
en
tifie
s
a
cr
u
cial
g
ap
:
t
h
e
lack
o
f
in
teg
r
ated
ML
an
d
d
ee
p
lear
n
i
n
g
a
p
p
r
o
ac
h
es
tailo
r
ed
f
o
r
th
e
p
r
e
d
ictio
n
o
f
d
iab
etes,
a
b
u
r
g
eo
n
in
g
g
lo
b
al
h
ea
lth
c
o
n
ce
r
n
.
E
x
is
tin
g
m
o
d
els
d
em
o
n
s
tr
ate
s
u
b
s
tan
tial
p
o
ten
tial,
y
et
th
ey
r
e
q
u
ir
e
r
e
f
in
em
en
t
to
en
h
a
n
ce
p
r
e
d
ictiv
e
ac
cu
r
ac
y
an
d
to
in
co
r
p
o
r
ate
d
iv
er
s
e
p
atien
t
d
atasets
.
Ou
r
s
tu
d
y
s
ee
k
s
to
b
r
id
g
e
th
is
g
ap
b
y
u
n
v
eilin
g
n
o
n
-
s
tan
d
ar
d
c
o
r
r
elatio
n
s
with
in
d
iab
etes
p
r
ed
ictio
n
m
o
d
els,
lev
er
ag
in
g
th
e
s
tr
en
g
th
s
o
f
b
o
th
ML
an
d
d
ee
p
lear
n
in
g
.
W
e
aim
to
tr
an
s
ce
n
d
tr
a
d
itio
n
al
d
iag
n
o
s
tic
m
o
d
els,
p
r
o
b
in
g
d
ee
p
er
in
to
th
e
p
ar
am
eter
s
th
at
g
o
v
er
n
th
em
an
d
u
n
v
eilin
g
n
ew
d
iag
n
o
s
tic
co
r
r
elatio
n
s
.
I
t
is
im
p
o
r
tan
t
to
n
o
te
th
at
th
e
in
co
r
p
o
r
atio
n
o
f
m
ac
h
in
e
a
n
d
d
ee
p
lear
n
in
g
m
eth
o
d
s
in
th
e
m
ed
ical
d
iag
n
o
s
is
o
f
d
iab
etes
s
ig
n
if
ies
a
n
o
tewo
r
th
y
ad
v
an
ce
m
en
t
in
th
e
r
ea
lm
o
f
p
r
ec
is
io
n
m
e
d
icin
e.
Ou
r
s
tu
d
y
'
s
f
in
d
in
g
s
u
n
d
er
s
co
r
e
th
at
s
o
p
h
is
ticated
ML
alg
o
r
ith
m
s
ca
n
attain
elev
ated
lev
els
o
f
ac
cu
r
a
cy
,
s
en
s
itiv
ity
,
an
d
s
p
ec
if
icity
in
p
r
ed
ictin
g
d
ia
b
etes.
T
h
is
,
in
tu
r
n
,
en
h
an
c
es
th
e
q
u
ality
o
f
h
ea
lth
ca
r
e
an
d
au
g
m
e
n
ts
th
e
ef
f
icien
cy
o
f
clin
ical
d
ec
is
io
n
-
m
ak
in
g
.
Nev
er
th
eless
,
it
is
im
p
er
ativ
e
to
em
p
h
asize
th
at
o
p
tim
al
r
esu
lts
n
ec
ess
itate
m
eticu
lo
u
s
d
ata
p
r
ep
ar
atio
n
an
d
p
r
e
-
p
r
o
ce
s
s
in
g
,
alo
n
g
with
co
n
s
id
er
atio
n
o
f
th
e
u
n
iq
u
e
ch
ar
ac
ter
is
tics
in
h
er
en
t
in
a
g
iv
en
clin
ical
s
itu
atio
n
.
I
n
co
n
cl
u
s
io
n
,
th
is
s
tu
d
y
d
o
es n
o
t m
er
ely
c
o
n
n
ec
t c
o
n
tem
p
o
r
ar
y
h
ea
lth
is
s
u
es with
b
u
r
g
e
o
n
in
g
W
HO
r
esear
ch
b
u
t
i
n
n
o
v
ativ
ely
ap
p
l
ies
ad
v
an
ce
d
c
o
m
p
u
tatio
n
al
te
ch
n
iq
u
es
to
d
iab
etes
p
r
e
d
ictio
n
.
T
h
e
im
p
licatio
n
s
o
f
o
u
r
f
in
d
i
n
g
s
m
ay
s
ig
n
if
ica
n
tly
r
ef
in
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es
in
m
ed
ical
p
r
ac
tice
an
d
p
r
o
v
i
d
e
a
s
ca
f
f
o
ld
f
o
r
f
u
tu
r
e
r
esear
c
h
in
p
r
ed
ictiv
e
h
ea
lth
ca
r
e
an
al
y
tics
.
T
o
en
h
an
ce
t
h
e
m
o
d
els
an
d
th
eir
p
r
ac
tical
ap
p
licatio
n
in
clin
ical
s
ettin
g
s
,
it
i
s
r
ec
o
m
m
en
d
ed
to
p
er
s
is
t
in
r
esear
ch
e
f
f
o
r
ts
in
t
h
is
d
o
m
ain
.
T
h
is
en
tails
d
elv
i
n
g
in
to
ex
ten
s
iv
e
d
atasets
an
d
cr
af
tin
g
alg
o
r
it
h
m
s
ca
p
ab
le
o
f
ad
a
p
tin
g
to
e
v
o
lv
in
g
co
n
d
itio
n
s
an
d
p
atien
t
-
s
p
ec
if
ic
ch
ar
ac
ter
is
tics
.
C
o
n
s
eq
u
en
tly
,
th
is
p
r
o
ject
s
ig
n
if
ican
tly
co
n
tr
i
b
u
tes
to
th
e
ad
v
an
ce
m
e
n
t
o
f
ar
tific
ial
in
tellig
en
ce
m
eth
o
d
s
in
m
ed
ici
n
e,
p
av
i
n
g
th
e
wa
y
f
o
r
n
ew
p
o
s
s
ib
ilit
ies in
th
e
d
iag
n
o
s
is
an
d
tr
ea
tm
en
t
o
f
c
h
r
o
n
i
c
d
is
ea
s
es.
ACK
NO
WL
E
DG
E
M
E
NT
T
h
is
r
esear
ch
was
f
u
n
d
e
d
b
y
t
h
e
Scien
ce
C
o
m
m
ittee
o
f
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
an
d
Sci
en
ce
o
f
th
e
R
ep
u
b
lic
o
f
Kaz
ak
h
s
tan
p
r
o
j
ec
t
n
u
m
b
e
r
AP2
2
6
8
3
3
1
6
“A
p
p
licatio
n
o
f
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
s
f
o
r
m
ed
ical
d
ec
is
io
n
s
u
p
p
o
r
t sy
s
tem
s
”.
DATA AV
AI
L
AB
I
L
I
T
Y
ST
AT
E
M
E
NT
Acc
ess
to
th
e
u
n
d
er
ly
in
g
alg
o
r
ith
m
s
an
d
co
m
p
u
tatio
n
al
p
r
o
ce
s
s
es
is
o
b
tain
ab
le
b
y
s
u
b
m
itti
n
g
a
r
eq
u
est
to
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
v
ia
th
e
a
u
th
o
r
'
s
em
ail,
with
th
e
p
r
o
v
id
ed
Git
Hu
b
h
an
d
le.
Up
o
n
ac
ce
p
tan
ce
o
f
th
e
p
ap
er
f
o
r
p
u
b
licatio
n
,
th
e
au
t
h
o
r
s
ar
e
co
m
m
itted
to
estab
lis
h
in
g
a
d
ed
icate
d
r
ep
o
s
ito
r
y
t
o
en
s
u
r
e
th
e
s
cien
tific
r
ep
r
o
d
u
ci
b
ilit
y
o
f
th
e
r
esu
lts
,
ac
ce
s
s
ib
le
to
an
y
in
ter
ested
p
ar
ties
.
I
t
is
im
p
er
ativ
e
to
n
o
te
th
at
th
e
r
ep
o
s
ito
r
y
its
elf
d
o
es
n
o
t
h
o
u
s
e
th
e
p
r
im
ar
y
d
ataset,
as
th
e
o
wn
er
s
h
ip
o
f
th
e
d
a
taset
d
o
es
n
o
t
b
elo
n
g
to
th
e
a
u
th
o
r
s
.
T
h
e
d
ata
ar
e
d
is
tr
ib
u
ted
u
n
d
e
r
th
e
ter
m
s
an
d
c
o
n
d
itio
n
s
s
p
ec
if
ie
d
in
th
e
Ph
y
s
io
Net
C
r
e
d
e
n
t
i
al
e
d
H
e
a
lt
h
D
a
t
a
Us
e
A
g
r
e
e
m
e
n
t
1
.
5
.
0
.
A
c
c
e
s
s
t
o
t
h
e
d
a
t
a
s
e
t
c
a
n
b
e
s
e
c
u
r
e
d
v
i
a
t
h
e
f
o
l
l
o
w
i
n
g
s
o
u
r
c
e
:
h
t
t
p
s
:/
/
d
o
i
.
o
r
g
/
1
0
.
1
3
0
2
6
/
C
2
XW
2
6
,
w
h
e
r
e
t
h
e
n
e
c
es
s
a
r
y
p
r
o
c
e
d
u
r
e
s
f
o
r
o
b
t
a
i
n
i
n
g
t
h
e
d
at
a
s
et
c
a
n
b
e
f
o
u
n
d
.
F
u
r
t
h
e
r
m
o
r
e
,
t
h
e
a
r
t
i
c
l
e
e
x
p
l
i
cit
l
y
r
e
f
e
r
e
n
c
e
s
t
h
e
u
t
i
l
iz
a
t
i
o
n
o
f
t
h
e
M
I
M
I
C
I
I
I
r
e
p
o
s
i
t
o
r
y
a
s
a
d
a
t
a
s
o
u
r
c
e
,
w
h
i
c
h
i
s
o
p
e
n
l
y
a
v
a
il
a
b
l
e
f
o
r
u
s
e
b
y
an
y
i
n
t
e
r
e
s
t
e
d
p
a
r
t
i
es
,
i
n
a
c
c
o
r
d
a
n
c
e
w
i
t
h
t
h
e
r
e
p
o
s
i
t
o
r
y
'
s
t
e
r
m
s
a
n
d
c
o
n
d
i
t
i
o
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.