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
.
5
,
Octo
b
er
2
0
2
5
,
p
p
.
4
0
1
7
~
4
0
3
1
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
5
.
p
p
4
0
1
7
-
4
0
3
1
4017
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Dete
c
tion o
f
c
hro
nic kidney
disea
se ba
sed o
n ensem
b
le
a
ppro
a
ch wit
h op
tima
l f
ea
tu
re sele
ction using
ma
chi
ne learning
D
e
e
p
i
ka
A
mo
l
A
j
a
l
ka
r
1
,
J
y
o
t
i
Y
o
g
e
s
h
D
es
h
mu
kh
2
,
M
a
y
u
ra
V
i
s
h
a
l
Sh
e
l
ke
3
,
S
h
a
li
ni
V
a
ib
h
a
v
W
a
n
kh
a
d
e
4
,
Sh
wet
a
l
K
is
ho
r
P
a
t
il
5
1
D
e
p
a
r
t
me
n
t
o
f
C
y
b
e
r
S
e
c
u
r
i
t
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
G
.
H
.
R
a
i
s
o
n
i
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
M
a
n
a
g
e
me
n
t
,
A
f
f
i
l
a
t
e
d
t
o
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
M
a
r
a
t
h
w
a
d
a
M
i
t
r
a
man
d
a
l
’
s I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
C
o
mp
u
t
i
n
g
,
M
I
T
A
r
t
,
D
e
si
g
n
a
n
d
T
e
c
h
n
o
l
o
g
y
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
I
n
d
i
a
4
D
e
p
a
r
t
m
e
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
V
i
s
h
w
a
k
a
r
m
a
I
n
s
t
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
A
f
f
i
l
a
t
e
d
t
o
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
s
i
t
y
,
P
u
n
e
,
I
n
d
i
a
5
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
M
a
r
a
t
h
w
a
d
a
M
i
t
r
a
m
a
n
d
a
l
’
s
I
n
s
t
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
s
i
t
y
,
P
u
n
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
9
2
0
2
4
R
ev
is
ed
J
u
l 1
,
2
0
2
5
Acc
ep
ted
Au
g
6
,
2
0
2
5
Ch
ro
n
ic
k
i
d
n
e
y
d
ise
a
se
(CKD
)
p
o
se
s
a
sig
n
ifi
c
a
n
t
h
e
a
lt
h
risk
g
lo
b
a
ll
y
,
n
e
c
e
ss
it
a
ti
n
g
e
a
rly
a
n
d
a
c
c
u
ra
te
d
e
tec
ti
o
n
to
e
n
su
re
ti
m
e
ly
in
ter
v
e
n
ti
o
n
a
n
d
e
ffe
c
ti
v
e
trea
tme
n
t.
Th
is
stu
d
y
p
re
se
n
ts
a
n
a
d
v
a
n
c
e
d
e
n
se
m
b
le
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
p
p
r
o
a
c
h
c
o
m
b
i
n
e
d
with
o
p
ti
m
a
l
fe
a
tu
re
se
lec
ti
o
n
t
o
e
n
h
a
n
c
e
th
e
d
e
tec
ti
o
n
o
f
CKD
.
Us
in
g
f
iv
e
b
a
se
li
n
e
M
L
c
las
sifiers
li
k
e
g
ra
d
ien
t
b
o
o
st
in
g
(G
B)
,
ra
n
d
o
m
fo
re
st
(
RF
)
,
K
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(KN
N
)
,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
(S
VM)
,
a
n
d
d
e
c
i
sio
n
tree
(DT)
,
a
n
d
u
ti
li
z
i
n
g
g
rid
se
a
rc
h
fo
r
h
y
p
e
r
p
a
ra
m
e
ter
tu
n
i
n
g
,
th
e
p
r
o
p
o
se
d
e
n
se
m
b
le
m
o
d
e
l
c
a
p
it
a
li
z
e
s
o
n
t
h
e
stre
n
g
th
s
o
f
e
a
c
h
a
lg
o
rit
h
m
.
Ou
r
a
p
p
ro
a
c
h
wa
s
tes
ted
o
n
a
p
u
b
li
c
b
e
n
c
h
m
a
rk
CKD
d
a
tas
e
t
fro
m
Ka
g
g
le.
T
h
e
e
x
p
e
rime
n
tal
re
su
lt
s
d
e
m
o
n
stra
t
e
th
a
t
t
h
e
e
n
se
m
b
le
m
o
d
e
l
c
o
n
siste
n
tl
y
o
u
t
p
e
rfo
rm
s
i
n
d
i
v
id
u
a
l
c
las
sifiers
a
n
d
e
x
isti
n
g
m
e
th
o
d
s,
a
c
h
iev
i
n
g
9
7
.
5
%
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
a
n
F
1
-
sc
o
re
o
f
9
7
.
4
%
.
T
h
is
su
p
e
rio
r
p
e
rf
o
rm
a
n
c
e
u
n
d
e
rsc
o
re
s
th
e
e
n
se
m
b
l
e
m
o
d
e
l'
s
p
o
ten
ti
a
l
a
s
a
re
li
a
b
le
e
a
rly
CKD
d
e
tec
ti
o
n
t
o
o
l.
I
n
teg
ra
ti
n
g
ML
in
to
CKD
d
iag
n
o
stics
e
n
h
a
n
c
e
s
a
c
c
u
ra
c
y
.
It
fa
c
il
it
a
tes
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
u
to
m
a
ted
,
sc
a
lab
le d
iag
n
o
st
ic t
o
o
ls,
a
id
i
n
g
h
e
a
lt
h
c
a
re
p
ro
fe
ss
io
n
a
ls i
n
m
a
k
i
n
g
in
fo
rm
e
d
d
e
c
isio
n
s a
n
d
u
lt
ima
tely
imp
ro
v
in
g
p
a
ti
e
n
t
o
u
tco
m
e
s
.
K
ey
w
o
r
d
s
:
C
h
r
o
n
ic
k
id
n
ey
d
is
ea
s
e
E
ar
ly
d
etec
tio
n
E
n
s
em
b
le
lear
n
in
g
Hy
p
er
p
ar
a
m
eter
tu
n
in
g
Ma
ch
in
e
lear
n
in
g
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
:
Ma
y
u
r
a
Vis
h
al
Sh
elk
e
Dep
ar
tm
en
t Co
m
p
u
ter
Scien
ce
an
d
E
n
g
in
ee
r
in
g
,
Sch
o
o
l o
f
C
o
m
p
u
tin
g
MI
T
Ar
t,
Desig
n
an
d
T
ec
h
n
o
lo
g
y
Un
iv
e
r
s
ity
Pu
n
e,
I
n
d
ia
E
m
ail: m
ay
u
r
a.
s
h
elk
e@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
to
d
ay
'
s
wo
r
ld
,
ch
r
o
n
ic
k
id
n
ey
d
is
ea
s
e
(
C
KD)
is
a
r
ap
id
ly
ex
p
an
d
i
n
g
illn
ess
th
at
af
f
ec
ts
th
o
u
s
an
d
s
o
f
p
eo
p
le
d
u
e
to
th
e
lack
o
f
ea
r
ly
in
d
icato
r
s
a
n
d
ac
ce
s
s
ib
le
m
ed
ical
tr
ea
tm
en
t.
M
o
s
t
p
e
o
p
l
e
w
i
t
h
C
K
D
a
r
e
f
r
o
m
m
i
d
d
l
e
-
c
l
a
s
s
a
n
d
l
o
w
e
r
-
c
l
a
s
s
n
a
t
i
o
n
s
[
1
]
,
[
2
]
.
A
p
p
r
o
x
i
m
a
t
e
l
y
1
b
i
l
l
i
o
n
p
e
o
p
l
e
d
i
e
d
f
r
o
m
C
K
D
i
n
2
0
1
7
[
3
]
.
C
KD
is
m
o
r
e
co
m
m
o
n
in
d
e
v
elo
p
ed
co
u
n
tr
ies.
I
n
lo
wer
-
t
o
m
id
d
le
-
in
co
m
e
n
atio
n
s
,
th
e
r
e
ar
e
3
9
0
.
6
b
illi
o
n
p
eo
p
le
with
C
KD
o
v
er
all,
wit
h
1
7
8
b
illi
o
n
m
e
n
an
d
2
1
1
b
ill
io
n
wo
m
en
[
4
]
.
T
h
ese
d
ata
s
h
o
w
th
at
a
s
ig
n
if
ican
t
p
r
o
p
o
r
tio
n
o
f
th
e
p
o
p
u
latio
n
i
n
em
er
g
in
g
n
atio
n
s
h
as
C
KD,
an
d
th
is
p
r
o
p
o
r
tio
n
s
ee
m
s
to
g
r
o
w
d
aily
.
Mu
c
h
r
esear
ch
h
as
b
ee
n
c
o
n
d
u
cted
o
n
ea
r
l
y
s
cr
ee
n
in
g
to
ad
d
r
ess
C
KD
at
its
ea
r
lies
t
s
tag
es.
T
h
is
p
ap
er
e
m
p
h
asizes
th
e
p
o
ten
tial
o
f
p
r
ec
is
io
n
in
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
p
r
ed
i
ctiv
e
alg
o
r
ith
m
s
f
o
r
C
KD.
M
L
,
with
its
ab
ilit
y
to
en
ab
le
co
m
p
le
x
an
aly
s
is
,
r
ed
u
ce
h
u
m
a
n
er
r
o
r
,
an
d
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
,
o
f
f
er
s
h
o
p
e
in
th
e
f
i
g
h
t
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
.
5
,
Octo
b
er
2
0
2
5
:
4
0
1
7
-
4
0
3
1
4018
a
g
a
i
n
s
t
C
KD
.
W
h
e
n
t
h
e
t
w
o
k
i
d
n
e
y
s
b
e
c
o
m
e
d
a
m
a
g
e
d
,
a
c
o
m
m
o
n
t
y
p
e
o
f
k
i
d
n
e
y
i
l
l
n
e
s
s
k
n
o
w
n
a
s
C
K
D
d
e
v
e
l
o
p
s
,
c
a
u
s
i
n
g
l
o
n
g
-
t
e
r
m
s
y
m
p
t
o
m
s
.
T
h
i
s
k
i
d
n
e
y
d
i
s
o
r
d
er
,
w
h
i
c
h
m
a
y
l
e
a
d
t
o
p
o
o
r
k
i
d
n
e
y
f
u
n
c
t
i
o
n
a
l
i
t
y
,
i
s
r
e
f
e
r
r
e
d
t
o
a
s
k
i
d
n
e
y
f
a
il
u
r
e
.
A
m
e
d
i
c
al
c
o
n
d
i
t
i
o
n
o
r
a
d
e
f
i
ci
e
n
c
y
i
n
n
e
c
ess
a
r
y
n
u
t
r
i
e
n
ts
,
s
u
c
h
a
s
a
d
e
c
r
e
as
e
i
n
t
h
e
g
l
o
m
e
r
u
l
a
r
f
il
t
r
a
ti
o
n
r
a
t
e
(
G
FR
)
[
5
]
,
m
i
g
h
t
b
e
t
h
e
r
e
s
u
l
t
.
T
h
e
p
r
o
p
o
s
e
d
f
o
r
e
c
as
t
i
n
g
a
p
p
r
o
a
c
h
u
s
e
s
a
n
e
n
s
e
m
b
l
e
t
ec
h
n
i
q
u
e
w
i
t
h
f
i
v
e
M
L
c
l
a
s
s
i
f
i
e
r
s
:
g
r
a
d
i
e
n
t
b
o
o
s
t
in
g
(
G
B
)
,
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
in
e
(
S
V
M
)
,
r
a
n
d
o
m
f
o
r
e
s
t
(
RF
)
,
d
e
c
is
i
o
n
t
r
ee
(
DT
)
,
a
n
d
K
-
n
e
a
r
e
s
t
n
ei
g
h
b
o
r
s
(
K
NN
)
a
s
b
as
e
l
i
n
e
l
e
a
r
n
e
r
s
t
o
f
o
r
e
ca
s
t
o
u
t
c
o
m
es
b
a
s
e
d
o
n
m
e
d
i
c
a
l
d
at
a
i
n
p
u
t
.
M
L
is
b
e
c
o
m
i
n
g
m
o
r
e
c
r
it
i
c
a
l
i
n
i
d
e
n
t
i
f
y
i
n
g
m
e
d
i
c
al
c
o
n
d
i
ti
o
n
s
b
e
c
a
u
s
e
i
t
e
n
a
b
les
c
o
m
p
l
e
x
a
n
a
l
y
s
is
,
r
e
d
u
c
e
s
h
u
m
a
n
e
r
r
o
r
,
a
n
d
i
m
p
r
o
v
e
s
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
.
M
L
a
l
g
o
r
ith
m
s
a
r
e
c
o
n
s
i
d
e
r
e
d
t
r
u
s
t
w
o
r
t
h
y
f
o
r
p
r
e
d
i
c
ti
n
g
g
a
s
t
r
o
i
n
t
e
s
ti
n
a
l
d
is
e
as
e
,
c
a
r
d
i
o
v
as
c
u
l
a
r
d
i
s
e
as
e
,
t
y
p
e
2
d
i
a
b
e
t
es
,
a
n
d
c
a
n
c
e
r
s
[
6
]
.
Var
io
u
s
h
ea
lth
ca
r
e
d
ata
af
f
ec
t
th
e
p
r
o
d
u
ce
d
m
o
d
el'
s
s
tab
ilit
y
an
d
ad
ap
tab
ilit
y
a
n
d
lea
d
to
d
ec
ep
tiv
e
g
u
id
elin
es
an
d
r
ep
ea
tab
le
clin
ical
m
o
d
els;
it
co
m
es
with
s
ev
er
al
d
is
ad
v
an
tag
es.
As
a
r
esu
lt,
th
e
lear
n
in
g
p
r
o
ce
d
u
r
e
in
d
ee
p
lear
n
in
g
(
DL
)
m
ay
r
esu
lt
in
a
h
ig
h
-
v
ar
ian
ce
n
etwo
r
k
an
d
f
ail
to
a
cc
o
m
p
lis
h
o
p
tim
al
p
ar
am
eter
s
au
to
m
atica
lly
.
A
v
ar
iety
o
f
DL
f
r
am
ew
o
r
k
s
co
u
ld
b
e
u
s
ed
to
ad
d
r
ess
th
is
d
i
f
f
icu
lty
.
W
e
r
e
f
e
r
t
o
t
h
i
s
p
r
o
c
e
d
u
r
e
a
s
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
,
a
p
o
w
e
r
f
u
l
a
p
p
r
o
a
c
h
t
h
a
t
c
o
m
b
i
n
e
s
t
h
e
b
e
n
e
f
i
t
s
f
r
o
m
c
o
n
v
e
n
t
i
o
n
a
l
a
n
d
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
t
o
o
v
e
r
c
o
m
e
t
h
e
l
i
m
i
t
a
t
i
o
n
s
o
f
i
n
d
i
v
i
d
u
a
l
m
o
d
e
l
s
a
n
d
p
r
o
v
i
d
e
a
n
i
n
c
r
e
a
s
e
d
a
d
a
p
t
a
b
i
l
i
t
y
a
n
d
b
r
o
a
d
l
y
a
p
p
l
i
c
a
b
l
e
a
p
p
r
o
a
c
h
[
7
]
.
E
s
s
e
n
t
i
a
l
l
e
a
r
n
e
r
s
a
n
d
v
a
r
i
a
t
i
o
n
a
r
e
t
h
e
t
w
o
p
r
i
m
a
r
y
t
y
p
e
s
o
f
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
[
8
]
.
I
n
itially
,
co
m
b
in
in
g
v
a
r
io
u
s
d
ata
s
ets
lead
s
to
h
o
m
o
g
en
e
o
u
s
lear
n
i
n
g
.
Seco
n
d
ly
,
u
s
in
g
m
u
ltip
le
f
r
am
ewo
r
k
s
,
d
iv
er
s
e
d
e
v
elo
p
m
en
t
ca
n
b
e
ac
co
m
p
lis
h
ed
.
Am
o
n
g
th
e
s
ev
er
al
co
n
f
ig
u
r
a
tio
n
s
u
s
ed
to
b
u
ild
en
s
em
b
le
m
o
d
els
ar
e
s
tack
in
g
[
9
]
,
b
o
o
s
tin
g
[
1
0
]
,
an
d
b
ag
g
in
g
[
1
1
]
.
T
h
e
s
tack
ed
en
s
e
m
b
le
m
o
d
el
o
f
f
er
s
a
v
er
s
atile,
r
esil
ien
t,
an
d
f
lex
ib
le
ap
p
r
o
ac
h
to
th
e
in
v
esti
g
atio
n
.
Nu
m
er
o
u
s
r
esear
ch
h
as
s
h
o
wn
th
at
en
s
em
b
le
m
o
d
elin
g
p
r
o
d
u
ce
s
a
r
eliab
le
a
n
d
ef
f
icien
t
f
r
am
ewo
r
k
,
r
ea
s
s
u
r
in
g
u
s
ab
o
u
t th
e
r
o
b
u
s
tn
ess
o
f
th
e
ap
p
r
o
ac
h
.
T
h
ey
s
elec
ted
th
e
b
est
f
ea
tu
r
e
s
elec
tio
n
,
u
s
u
ally
th
e
f
i
r
s
t
s
tep
to
war
d
s
cr
ea
tin
g
an
ef
f
ec
tiv
e
m
o
d
el.
I
n
th
e
f
ield
o
f
ML
,
s
elec
tin
g
f
ea
tu
r
es
was
th
o
r
o
u
g
h
ly
s
tu
d
ied
,
s
h
o
win
g
p
r
o
m
is
e
f
o
r
u
s
e
in
m
ed
ical
f
ield
s
.
T
h
r
ee
p
r
im
ar
y
ca
teg
o
r
ies
o
f
f
ea
tu
r
e
s
elec
tio
n
s
ex
is
t:
wr
ap
p
in
g
,
f
ilter
in
g
,
an
d
em
b
e
d
d
in
g
[
1
2
]
.
T
h
e
r
esear
ch
team
u
s
ed
f
o
u
r
f
ea
tu
r
e
ev
alu
atio
n
t
ec
h
n
iq
u
es
to
p
ick
th
e
b
est
f
ea
tu
r
e
s
elec
tio
n
.
T
h
e
p
r
im
ar
y
g
o
al
was
to
cr
ea
te
an
en
s
em
b
le
m
o
d
el
to
en
h
an
ce
p
r
ed
ictiv
e
ef
f
ec
tiv
en
ess
wh
ile
u
tili
zin
g
th
e
b
est
f
ea
tu
r
e
s
u
b
s
et.
C
o
m
p
ar
ed
with
th
e
p
r
esen
t
m
eth
o
d
s
,
th
e
s
u
g
g
ested
f
ea
tu
r
e
s
h
o
ws
g
r
ea
t
p
r
o
m
is
e
in
th
e
ea
r
lier
d
iag
n
o
s
is
o
f
C
KD
f
r
o
m
a
m
ed
ical
ap
p
r
o
ac
h
,
e
n
co
u
r
ag
in
g
u
s
ab
o
u
t th
e
p
o
ten
tial im
p
ac
t o
f
th
e
r
esear
c
h
.
T
h
e
r
e
f
o
r
e
,
t
o
a
d
d
r
e
s
s
a
g
a
p
i
n
t
h
i
s
a
r
e
a
,
w
e
w
i
l
l
e
x
p
l
o
r
e
m
u
l
t
i
p
l
e
M
L
t
e
c
h
n
i
q
u
e
s
i
n
t
h
i
s
s
t
u
d
y
a
l
o
n
g
w
i
t
h
a
n
e
n
s
e
m
b
l
e
s
t
r
a
t
e
g
y
t
o
c
o
m
b
i
n
e
t
h
e
s
e
a
l
g
o
r
i
t
h
m
s
.
C
o
n
s
e
q
u
e
n
t
l
y
,
t
h
i
s
p
a
p
e
r
'
s
p
r
i
m
a
r
y
c
o
n
t
r
i
b
u
t
i
o
n
s
a
r
e
a
s
f
o
l
l
o
w
s
:
‒
T
o
p
r
o
p
o
s
e
an
ML
-
b
ased
en
s
em
b
le
m
o
d
el
b
ased
o
n
a
m
ajo
r
ity
v
o
tin
g
a
p
p
r
o
ac
h
to
co
m
b
in
e
f
iv
e
ML
m
o
d
els
as
a
b
aselin
e
cla
s
s
if
ie
r
(
GB
,
SVM,
KNN,
R
F,
an
d
DT
)
with
f
in
e
tu
n
in
g
u
s
in
g
g
r
id
s
ea
r
ch
to
en
h
an
ce
d
etec
tio
n
an
d
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
‒
T
o
ex
am
in
e
th
e
b
en
ef
its
an
d
d
r
awb
ac
k
s
o
f
ea
ch
p
r
ed
ictio
n
a
p
p
r
o
ac
h
,
ev
alu
ate
its
ef
f
ec
tiv
e
n
ess
th
r
o
u
g
h
a
r
an
g
e
o
f
m
ea
s
u
r
es.
T
h
e
o
u
tco
m
es
ar
e
co
n
tr
asted
with
th
o
s
e
o
f
th
e
cu
r
r
en
t
tech
n
iq
u
es
to
illu
s
tr
ate
th
e
p
o
wer
o
f
th
e
s
u
g
g
ested
m
o
d
el
s
o
n
th
e
d
atasets
.
T
h
e
p
a
p
er
'
s
o
r
g
an
izatio
n
is
as
f
o
llo
ws:
s
ec
tio
n
1
p
r
esen
ts
a
n
o
v
e
r
v
iew
o
f
C
KD.
Sectio
n
2
d
is
cu
s
s
ed
th
e
p
r
ev
io
u
s
C
KD
p
r
ed
ictio
n
an
d
class
if
icatio
n
liter
atu
r
e.
T
h
e
s
tep
-
by
-
s
tep
m
eth
o
d
o
lo
g
y
is
ex
p
lain
ed
in
th
e
s
ec
tio
n
3
in
d
etail.
Sectio
n
4
m
ea
s
u
r
es
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
u
g
g
ested
m
o
d
els
an
d
co
m
p
ar
es
th
e
f
in
al
r
esu
lts
.
Sectio
n
5
d
is
cu
s
s
es th
i
s
s
tu
d
y
'
s
co
n
clu
s
io
n
an
d
f
u
t
u
r
e
d
ir
ec
tio
n
.
2.
RE
L
AT
E
D
WO
RK
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
alg
o
r
it
h
m
-
r
elate
d
in
v
esti
g
atio
n
s
an
d
ev
alu
ates
s
p
ec
if
ic
s
tr
ateg
ies
b
ased
o
n
th
eir
p
er
f
o
r
m
an
ce
.
Ap
p
ly
in
g
t
h
e
d
ata
m
in
in
g
a
p
p
r
o
ac
h
to
t
h
e
s
p
ec
ialized
ex
am
in
atio
n
o
f
h
ea
lth
ca
r
e
r
ec
o
r
d
s
p
r
o
v
id
es
a
v
alu
a
b
le
ap
p
r
o
ac
h
to
in
v
esti
g
atio
n
[
1
3
]
.
C
o
m
p
ar
ed
with
th
e
n
aïv
e
B
ay
es
(
NB
)
tech
n
iq
u
e
,
th
e
DT
ap
p
r
o
ac
h
ac
h
iev
e
d
a
9
2
%
a
cc
u
r
ac
y
s
co
r
e,
9
3
%
s
p
ec
if
icity
,
an
d
9
4
%
s
en
s
itiv
ity
f
o
r
class
if
y
in
g
d
iab
etic
d
atasets
.
Ad
d
itio
n
ally
,
r
esear
ch
er
s
d
is
co
v
er
ed
th
at
m
in
i
n
g
h
elp
s
r
ec
o
v
er
co
r
r
elatio
n
s
b
et
wee
n
tr
aits
th
at
ar
e
n
o
lo
n
g
er
p
r
ed
ictiv
e
o
f
th
e
o
u
tco
m
es
th
ey
attem
p
t
t
o
f
o
r
ec
ast.
Pre
d
ictiv
e
alg
o
r
ith
m
s
u
s
i
n
g
ML
ap
p
r
o
ac
h
es,
s
u
ch
as
lo
g
is
tic
r
e
g
r
ess
io
n
(
L
R
)
,
SVM,
KNN,
an
d
DT
clas
s
if
icatio
n
alg
o
r
ith
m
s
f
o
r
C
KD
f
o
r
ec
asti
n
g
,
wer
e
d
is
cu
s
s
ed
b
y
in
v
esti
g
ato
r
s
[
1
4
]
.
T
h
e
s
tu
d
y
d
em
o
n
s
tr
ated
th
at
th
e
SVM
alg
o
r
ith
m
h
ad
th
e
h
ig
h
est
ac
cu
r
ac
y
s
co
r
e,
r
ea
ch
in
g
9
7
%.
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e'
s
lear
n
in
g
an
d
test
in
g
y
ield
ed
th
e
h
ig
h
est
s
en
s
itiv
ity
r
esu
lts
f
o
r
SVM.
B
a
s
ed
o
n
th
is
an
aly
s
is
,
it
is
p
o
s
s
ib
le
to
co
n
clu
d
e
th
at
ch
r
o
n
ic
k
id
n
ey
f
ailu
r
e
ca
n
b
e
p
r
ed
icted
u
s
in
g
th
e
SVM
alg
o
r
ith
m
.
T
h
e
r
esear
ch
s
elec
ted
an
d
an
aly
ze
d
th
r
ee
d
is
tin
ct
tech
n
iq
u
es
[
1
5
]
t
o
o
b
tain
an
ap
p
r
o
p
r
iate
p
r
ed
ictio
n
r
ate
ac
r
o
s
s
th
e
d
a
taset.
T
h
e
s
tu
d
y
u
s
ed
th
e
G
B
class
if
ier
,
wh
ich
p
r
o
d
u
ce
d
th
e
m
o
s
t
ef
f
e
ctiv
e
r
esu
lts
.
W
h
ile
Ad
aBo
o
s
t
an
d
l
in
ea
r
d
is
cr
im
in
an
t
an
aly
s
is
(
L
DA)
ac
h
iev
ed
a
9
6
%
p
er
f
o
r
m
an
ce
s
co
r
e,
th
e
GB
class
if
ier
ac
h
iev
ed
a
9
8
%
p
er
f
o
r
m
a
n
ce
s
co
r
e.
Ad
d
itio
n
al
ly
,
co
m
p
ar
ed
to
o
t
h
er
ML
class
if
ier
s
,
th
e
GB
class
if
ier
r
eq
u
ir
es
m
o
r
e
tim
e
t
o
p
r
o
d
u
ce
a
f
o
r
ec
ast
b
u
t
p
r
o
v
id
es
b
etter
-
p
r
e
d
icted
r
esu
lts
o
n
b
o
t
h
th
e
r
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
is
tic
(
R
OC
)
an
d
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
AUC)
s
co
r
es.
T
h
er
ef
o
r
e,
ac
cu
r
ate
p
r
ed
ictio
n
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
Dete
ctio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
i
s
ea
s
e
b
a
s
ed
o
n
esemb
le
a
p
p
r
o
a
ch
w
ith
…
(
Dee
p
ika
A
mo
l
A
ja
lka
r
)
4019
d
ep
en
d
s
h
ea
v
ily
o
n
th
e
in
itial
p
r
o
ce
s
s
in
g
p
lan
,
an
d
p
r
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
wer
e
u
s
ed
ca
u
tio
u
s
ly
to
ac
h
iev
e
th
e
ex
p
ec
ted
o
u
tco
m
es
p
r
o
p
er
ly
.
I
n
v
esti
g
ato
r
s
p
r
ed
icted
C
KD
u
s
in
g
a
n
o
v
el
s
elec
tio
n
m
eth
o
d
[
1
6
]
.
B
y
ap
p
ly
in
g
ce
r
tain
class
if
icatio
n
s
an
d
ap
p
r
o
p
r
iately
ass
ess
in
g
th
e
o
v
e
r
all
o
u
tco
m
e,
C
KD
is
p
r
o
jecte
d
to
b
e
u
s
ed
in
th
is
wo
r
k
.
T
h
e
NB
,
R
F,
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
A
NN
)
[
1
7
]
class
if
ier
s
wer
e
ev
alu
ated
,
an
d
it
was
f
o
u
n
d
th
at
th
e
R
F
o
u
tp
er
f
o
r
m
s
th
e
o
th
er
m
o
d
els.
T
h
e
v
a
lu
e
o
f
C
KD
p
r
ed
ictio
n
h
as
in
cr
ea
s
ed
o
v
er
tim
e.
I
m
p
lem
en
tin
g
s
ev
er
al
f
ea
s
ib
le
ad
ap
tiv
e
s
tr
ateg
ies
ca
n
en
h
an
ce
th
e
r
ec
o
m
m
en
d
e
d
class
i
f
ier
s
'
p
er
f
o
r
m
an
ce
.
NB
,
R
F,
an
d
KNN
wer
e
u
s
e
d
to
f
o
r
ec
ast
C
KD.
T
h
e
ea
r
ly
id
en
tific
atio
n
o
f
C
KD
aid
s
i
n
p
r
o
m
p
tly
tr
ea
tin
g
p
eo
p
le
af
f
licted
an
d
s
to
p
s
th
e
illn
ess
f
r
o
m
wo
r
s
en
in
g
.
An
ML
p
r
ed
ictiv
e
tech
n
i
q
u
e
f
o
r
ea
r
ly
id
en
tific
atio
n
o
f
C
KD
was
cr
ea
ted
i
n
[
1
8
]
.
T
h
e
p
r
e
d
ictiv
e
m
o
d
els
h
av
e
b
ee
n
ass
ess
ed
an
d
v
er
if
ied
f
o
r
th
e
in
itial
f
ea
tu
r
es
p
r
o
v
id
ed
b
y
th
e
d
ataset,
wh
ich
co
n
tain
s
in
p
u
t
f
ea
tu
r
es
co
llected
th
r
o
u
g
h
th
e
C
KD
d
ataset.
DT
,
R
F,
an
d
S
VM
class
if
ier
s
wer
e
b
u
ilt
to
d
iag
n
o
s
e
C
KD.
T
h
e
p
r
ed
ictiv
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
c
e
s
co
r
e
s
er
v
ed
as
th
e
b
asis
f
o
r
ev
alu
atin
g
th
e
m
o
d
els'
p
er
f
o
r
m
an
ce
an
aly
s
is
.
I
n
co
n
tr
ast,
th
e
s
tu
d
y
'
s
f
in
d
in
g
s
d
em
o
n
s
tr
ated
th
at
th
e
R
F
m
o
d
el
o
u
tp
er
f
o
r
m
s
DT
an
d
SVM
m
o
d
els
r
eg
ar
d
in
g
C
KD
p
r
ed
ictio
n
.
I
n
ad
d
itio
n
to
b
ein
g
n
ec
ess
ar
y
f
o
r
elim
in
at
in
g
im
p
u
r
ities
f
r
o
m
th
e
h
u
m
a
n
b
o
d
y
,
th
e
k
id
n
e
y
s
also
r
eg
u
late
B
P,
th
e
b
o
d
y
'
s
p
er
ce
p
tio
n
o
f
th
e
p
H
le
v
el,
an
d
its
lev
el
o
f
elec
tr
o
ly
te.
I
n
b
etwe
en
m
alf
u
n
ctio
n
in
g
in
ea
ch
b
o
d
y
o
r
g
a
n
,
d
y
s
f
u
n
ctio
n
co
n
tr
ib
u
tes
to
m
in
o
r
to
f
atal
d
is
o
r
d
er
s
.
C
o
n
s
eq
u
en
tly
,
s
cien
tis
t
s
f
r
o
m
all
ar
o
u
n
d
h
u
m
an
ity
h
av
e
d
ev
o
ted
th
eir
ef
f
o
r
t
s
to
d
ev
elo
p
in
g
m
eth
o
d
s
f
o
r
p
r
ec
is
ely
d
iag
n
o
s
in
g
an
d
tr
ea
tin
g
C
KD.
T
h
e
n
u
m
b
er
o
f
h
ea
lth
co
n
d
itio
n
s
th
at
M
L
class
if
ier
s
ca
n
id
en
tify
in
cl
u
d
es
C
KD,
as
th
ese
alg
o
r
ith
m
s
ar
e
b
ei
n
g
u
tili
ze
d
m
o
r
e
a
n
d
m
o
r
e
in
m
ed
ical
r
es
ea
r
ch
f
o
r
id
en
tific
atio
n
.
T
h
e
p
r
o
ce
s
s
an
d
o
u
tc
o
m
e
ac
cu
r
ac
y
h
av
e
g
r
ad
u
ally
im
p
r
o
v
ed
d
u
e
to
r
esear
ch
in
to
u
s
in
g
ML
tech
n
i
q
u
es
to
i
d
en
tify
C
KD.
Ou
t
o
f
all
th
e
class
if
icatio
n
m
eth
o
d
s
,
in
v
esti
g
ato
r
s
s
u
g
g
ested
th
at
th
e
R
F
m
o
d
el
ac
h
iev
es
a
9
9
%
ac
cu
r
a
cy
s
co
r
e,
wh
ich
was
th
e
m
o
s
t
ef
f
icien
t.
T
h
e
r
esear
ch
s
h
o
ws
h
o
w
to
ef
f
ec
tiv
ely
h
an
d
le
th
e
ab
s
en
ce
o
f
v
al
u
es
in
d
ata
u
s
in
g
f
o
u
r
d
if
f
er
en
t
ap
p
r
o
ac
h
es:
s
tatis
tical
p
r
o
ce
d
u
r
es.
A
d
d
itio
n
ally
,
it
ass
es
s
es
h
o
w
well
ML
m
o
d
els
wo
r
k
in
two
s
ce
n
ar
io
s
,
o
n
e
i
n
wh
ich
th
e
h
y
p
er
p
ar
am
eter
s
a
r
e
tu
n
e
d
an
d
t
h
e
o
th
er
in
wh
ic
h
th
ey
ar
e
n
o
t
,
an
d
f
in
d
s
th
at
t
h
e
alg
o
r
ith
m
s
'
ef
f
ec
tiv
en
ess
h
as
s
ig
n
if
ican
tly
im
p
r
o
v
ed
,
as
s
h
o
wn
in
[
1
9
]
.
T
h
e
w
o
r
k
aim
s
to
in
v
esti
g
ate
th
e
s
u
itab
ilit
y
o
f
p
ar
ticu
lar
s
u
p
er
v
is
ed
ML
m
o
d
els
in
th
e
b
io
m
e
d
ical
d
o
m
ai
n
an
d
ass
ess
th
eir
ca
p
ac
ity
to
id
en
tify
v
ar
io
u
s
s
ev
er
e
illn
ess
es,
in
clu
d
in
g
th
e
ea
r
lier
d
etec
tio
n
o
f
C
KD
[
2
0
]
.
R
esear
ch
er
s
h
av
e
tr
ied
to
id
en
tify
k
id
n
ey
d
is
ea
s
e
ea
r
lier
o
n
o
r
f
o
r
ec
ast
its
em
er
g
en
ce
.
W
h
ile
d
is
ea
s
e
f
o
r
ec
asti
n
g
s
u
g
g
ests
th
e
u
n
d
e
r
ly
in
g
d
is
ea
s
e
ca
n
o
cc
u
r
th
r
o
u
g
h
o
u
t
th
e
f
u
tu
r
e,
d
is
ea
s
e
id
en
tific
atio
n
s
u
g
g
ests
th
e
in
d
iv
id
u
al
n
o
w
h
as
th
e
illn
ess
.
C
o
n
s
eq
u
en
tly
,
two
lin
es
o
f
r
esear
ch
h
av
e
b
ee
n
estab
l
is
h
ed
in
th
is
f
ield
:
id
en
tific
atio
n
an
d
f
o
r
ec
asti
n
g
.
W
ith
th
e
f
ir
s
t c
ateg
o
r
y
,
th
e
r
e
h
av
e
b
ee
n
a
lo
t o
f
i
n
v
esti
g
atio
n
s
in
th
is
ar
ea
[
2
1
]
.
Af
ter
ex
am
in
in
g
th
e
p
r
ev
io
u
s
s
tu
d
y
,
we
en
co
u
n
ter
e
d
s
ev
er
al
r
esear
ch
g
ap
s
:
−
T
h
e
d
ata
o
n
C
KD
r
em
ain
s
in
s
u
f
f
icien
t.
Me
d
ical
test
in
g
r
ec
o
r
d
s
b
ec
am
e
th
e
b
asis
f
o
r
ea
r
lier
r
esear
ch
,
b
u
t
th
ey
co
v
e
r
a
lim
ited
n
u
m
b
er
o
f
in
s
tan
ce
s
.
−
T
h
e
ea
r
lier
s
tu
d
ies f
o
c
u
s
ed
o
n
id
en
tify
in
g
t
h
e
d
is
ea
s
e
af
ter
it
h
ad
alr
ea
d
y
m
an
if
ested
.
−
T
h
e
r
esear
ch
in
th
is
ar
ea
h
as n
ev
er
b
ee
n
th
o
r
o
u
g
h
ly
in
v
esti
g
ated
b
ec
au
s
e
th
er
e
is
n
o
in
f
o
r
m
atio
n
.
−
A
s
i
n
g
l
e
p
r
i
o
r
s
t
u
d
y
a
t
t
e
m
p
t
e
d
t
o
f
o
r
e
c
a
s
t
i
l
l
n
e
s
s
b
e
f
o
r
e
h
a
n
d
.
N
o
n
e
t
h
e
l
e
s
s
,
t
h
i
s
s
t
u
d
y
'
s
a
c
c
u
r
a
c
y
w
a
s
l
a
c
k
i
n
g
.
−
T
h
e
C
DK
d
is
ea
s
e
d
ea
th
r
ate
p
r
o
life
r
ates b
ased
o
n
th
e
p
r
ec
ed
in
g
is
s
u
es.
3.
M
AT
E
R
I
AL
A
ND
M
E
T
H
O
DS
T
h
i
s
r
e
s
e
a
r
c
h
p
r
e
s
e
n
t
s
a
n
i
n
n
o
v
a
t
i
v
e
e
n
s
e
m
b
l
e
M
L
s
t
r
a
t
e
g
y
t
o
i
d
e
n
t
i
f
y
C
K
D
,
e
m
p
l
o
y
i
n
g
a
d
v
a
n
c
e
d
t
e
c
h
n
i
q
u
e
s
f
o
r
o
p
t
i
m
a
l
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
.
T
h
e
s
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
s
i
g
n
i
f
i
c
a
n
t
l
y
i
m
p
a
c
t
C
K
D
f
r
o
m
a
m
e
d
i
c
a
l
p
e
r
s
p
e
c
t
i
v
e
.
T
h
e
p
r
o
p
o
s
e
d
f
r
a
m
e
w
o
r
k
c
o
n
s
i
s
t
s
o
f
s
e
v
e
r
a
l
p
h
a
s
e
s
:
d
a
t
a
s
e
t
c
o
l
l
e
c
t
i
o
n
,
p
r
e
p
r
o
c
e
s
s
i
n
g
,
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
,
m
o
d
e
l
d
e
v
e
l
o
p
m
e
n
t
,
a
n
d
o
p
t
i
m
i
z
a
t
i
o
n
,
a
s
d
e
p
i
c
t
e
d
i
n
F
i
g
u
r
e
1
.
E
a
c
h
s
t
e
p
i
s
d
e
s
c
r
i
b
e
d
i
n
d
e
t
a
i
l
a
s
f
o
l
l
o
w
s
.
3
.
1
.
Da
t
a
s
et
des
cr
iptio
n
T
h
e
UC
I
r
v
in
e
Ma
ch
in
e
L
ea
r
n
in
g
L
ib
r
ar
y
p
r
o
v
id
ed
th
e
s
tan
d
ar
d
C
KD
d
ataset
u
s
ed
in
th
is
in
v
esti
g
atio
n
[
2
2
]
.
Ma
n
y
r
esear
ch
er
s
u
tili
ze
d
th
is
d
ataset
to
co
n
d
u
ct
e
x
p
er
im
e
n
ts
.
T
h
e
d
ataset
co
n
s
is
ts
o
f
4
0
0
ca
s
es,
2
5
0
with
n
o
C
KD
an
d
1
5
0
with
C
KD.
Fig
u
r
e
1
s
h
o
ws
th
at
ea
ch
class
lab
el
co
n
tain
s
two
v
alu
es:
1
an
d
0
f
o
r
C
KD
an
d
n
o
C
KD,
r
esp
ec
tiv
ely
.
Fig
u
r
e
2
s
h
o
ws t
h
e
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
in
t
h
e
d
ataset.
3
.
2
.
Da
t
a
prepro
ce
s
s
ing
H
e
a
l
t
h
c
a
r
e
i
n
f
o
r
m
a
t
i
o
n
c
o
n
t
a
i
n
s
n
o
r
m
a
l
,
a
b
n
o
r
m
a
l
,
o
r
n
u
l
l
v
a
l
u
e
s
d
u
e
t
o
t
h
e
i
n
s
t
r
u
m
e
n
t
,
n
e
t
w
o
r
k
,
o
r
r
e
c
o
r
d
e
n
t
r
y
o
p
e
r
a
t
o
r
.
C
h
a
l
l
e
n
g
e
s
w
i
t
h
d
a
t
a
s
e
t
s
h
a
v
e
a
d
e
t
r
i
m
e
n
t
a
l
i
m
p
a
c
t
o
n
t
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
a
n
M
L
m
o
d
e
l
.
T
h
i
s
s
t
a
g
e
'
s
p
r
i
m
a
r
y
g
o
a
l
i
s
t
o
h
a
n
d
l
e
o
u
t
l
i
e
r
s
a
n
d
m
i
s
s
i
n
g
n
u
m
b
e
r
s
t
o
i
m
p
r
o
v
e
t
h
e
q
u
a
l
i
t
y
o
f
t
h
e
h
e
a
l
t
h
c
a
r
e
d
a
t
a
s
e
t
.
3
.
2
.
1
.
Da
t
a
enco
din
g
T
h
e
d
ataset
we
wo
r
k
with
co
n
tain
s
b
o
th
ca
teg
o
r
ical
an
d
n
u
m
er
ic
v
ar
iab
les.
I
t'
s
cr
u
cial
to
u
n
d
er
s
tan
d
th
at
two
f
ea
tu
r
e
-
s
elec
tio
n
m
e
th
o
d
s
wo
r
k
b
etter
with
n
u
m
e
r
ical
ch
ar
ac
ter
is
tics
th
an
ca
te
g
o
r
ical
o
n
es:
ML
.
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
.
5
,
Octo
b
er
2
0
2
5
:
4
0
1
7
-
4
0
3
1
4020
T
h
er
ef
o
r
e,
all
ca
teg
o
r
ical
ch
a
r
ac
ter
is
tics
wer
e
en
co
d
ed
u
s
in
g
th
e
s
cik
it
lear
n
in
g
lib
r
ar
y
'
s
lab
elin
g
en
co
d
er
p
ac
k
ag
e,
a
k
ey
tec
h
n
ical
s
tep
i
n
o
u
r
p
r
o
ce
s
s
.
3
.
2
.
2
.
F
illi
ng
m
is
s
ing
v
a
lues
W
e
f
o
llo
w
a
m
eticu
lo
u
s
p
r
o
ce
s
s
wh
en
f
illi
n
g
in
m
is
s
in
g
d
ata.
Sev
er
al
tech
n
iq
u
es we
r
e
p
r
o
p
o
s
ed
,
an
d
th
e
ch
o
ice
d
e
p
en
d
s
o
n
h
o
w
m
u
ch
d
ata
an
d
f
ea
tu
r
es
ar
e
a
b
s
en
t.
W
h
en
th
e
am
o
u
n
t
o
f
m
is
s
in
g
d
ata
is
m
o
d
est
(
5
%
to
1
0
%),
t
r
ad
itio
n
al
s
tatis
tical
ap
p
r
o
ac
h
es
lik
e
m
ea
n
,
m
ax
im
u
m
,
an
d
m
o
d
e
f
u
n
cti
o
n
well.
Ho
wev
er
,
wh
en
th
e
p
e
r
ce
n
tag
e
o
f
m
is
s
in
g
v
alu
es
r
is
es
(
2
0
%
to
5
0
%),
ad
v
an
ce
d
m
eth
o
d
s
lik
e
ex
p
ec
tatio
n
m
a
x
im
izatio
n
ar
e
n
ee
d
ed
[
2
3
]
.
I
n
o
u
r
ca
s
e,
we
u
s
e
th
e
f
ea
tu
r
e
av
e
r
ag
es
t
o
im
p
u
te
th
e
m
is
s
in
g
v
al
u
es,
en
s
u
r
in
g
th
e
q
u
ality
an
d
in
teg
r
ity
o
f
o
u
r
d
ataset.
3
.
2
.
3
.
Rem
o
v
ing
o
utlier
s
W
e
tak
e
a
th
o
r
o
u
g
h
a
p
p
r
o
ac
h
to
id
en
tify
an
d
r
em
o
v
e
o
u
tlier
s
,
wh
ich
ar
e
p
ar
a
m
eter
s
th
at
s
ig
n
if
ican
tly
d
ev
iate
f
r
o
m
th
e
ty
p
ical
r
an
g
e
o
f
ev
er
y
f
ea
tu
r
e
v
alu
e.
T
h
is
is
a
cr
u
cial
s
tep
in
th
e
cr
ea
tio
n
o
f
a
r
o
b
u
s
t
a
n
d
co
m
p
r
eh
en
s
iv
e
m
o
d
el
[
2
4
]
.
I
n
th
e
p
r
esen
t
in
v
esti
g
atio
n
,
we
f
ir
s
t
e
x
am
in
ed
all
d
ata
s
tatis
tically
an
d
th
en
v
er
if
ie
d
th
e
f
in
d
in
g
s
f
r
o
m
a
h
ea
lth
ca
r
e
p
er
s
p
ec
tiv
e.
An
y
o
u
tlier
s
id
en
tifie
d
in
t
h
e
d
ata
wer
e
s
u
b
s
titu
ted
with
th
e
f
ea
tu
r
e
a
v
er
ag
e,
en
s
u
r
in
g
th
e
r
o
b
u
s
tn
ess
o
f
o
u
r
m
o
d
el.
3
.
2
.
4
.
Da
t
a
s
t
a
nd
a
rdiza
t
io
n a
nd
no
rm
a
liza
t
io
n
T
h
e
s
tan
d
ar
d
Min
Ma
x
Scaler
(
)
f
u
n
ctio
n
was
e
m
p
lo
y
e
d
f
o
r
s
ca
lin
g
f
ea
tu
r
e
v
alu
es.
In
(
1
)
was
u
s
ed
f
o
r
s
ca
lin
g
th
e
n
u
m
er
ical
v
alu
es
f
o
r
b
atch
n
o
r
m
aliza
tio
n
an
d
s
ta
n
d
ar
d
izatio
n
.
I
n
th
is
ca
s
e,
th
e
s
tan
d
ar
d
d
ev
iatio
n
h
as b
ee
n
co
n
f
ig
u
r
ed
to
s
ix
,
an
d
th
e
d
ata
is
ass
u
m
ed
to
b
e
ze
r
o
.
(
)
=
∑
−
=
1
−
(
1
)
wh
er
e,
S
,
D
,
,
,
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
d
ata
i
n
s
tan
ce
s
in
d
ataset
,
is
th
e
av
er
ag
e
o
f
th
e
ch
ar
ac
ter
is
tics
,
th
e
lo
west a
n
d
m
ax
im
al
in
s
tan
ce
s
v
alu
es,
r
esp
ec
tiv
ely
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
f
r
am
ewo
r
k
to
p
r
ed
ict
C
KD
Fig
u
r
e
2
.
Dis
tr
ib
u
tio
n
o
f
d
ataset
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
Dete
ctio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
i
s
ea
s
e
b
a
s
ed
o
n
esemb
le
a
p
p
r
o
a
ch
w
ith
…
(
Dee
p
ika
A
mo
l
A
ja
lka
r
)
4021
3
.
3
.
F
e
a
t
ure
o
ptim
iz
a
t
io
n
Fig
u
r
e
3
d
em
o
n
s
tr
ates
p
o
s
itiv
e
r
elatio
n
s
h
ip
s
b
etwe
en
ea
c
h
f
ea
tu
r
e
.
C
o
n
v
er
s
ely
,
th
e
r
e
ar
e
s
o
m
e
n
eg
ativ
e
co
r
r
elatio
n
s
with
h
e
m
o
g
lo
b
i
n
,
p
o
tass
iu
m
,
r
ed
b
l
o
o
d
ce
ll
co
u
n
t,
an
d
wh
ite
b
l
o
o
d
ce
ll
co
u
n
t.
T
h
e
ass
o
ciatio
n
s
b
etwe
en
ea
ch
f
ea
t
u
r
e
ca
n
b
e
s
ee
n
b
y
e
x
am
in
in
g
th
e
h
ea
tm
ap
o
f
t
h
e
p
atien
t
in
f
o
r
m
atio
n
d
is
p
lay
ed
in
Fig
u
r
e
3.
Fig
u
r
e
4
an
aly
s
is
o
f
th
e
h
is
to
g
r
am
s
is
ess
en
tial
f
o
r
f
e
atu
r
e
s
elec
tio
n
,
as
it
h
el
p
s
id
en
tify
o
u
tlier
s
,
th
e
n
ee
d
f
o
r
n
o
r
m
aliza
tio
n
an
d
also
h
elp
s
to
s
h
o
ws
th
e
o
v
e
r
al
l im
p
o
r
tan
ce
o
f
ea
ch
f
ea
tu
r
e
i
n
d
etec
tin
g
C
KD.
Fig
u
r
e
3
.
Hea
tm
ap
o
f
t
h
e
p
atie
n
t in
f
o
r
m
atio
n
Fig
u
r
e
4
.
Hea
tm
ap
o
f
ea
c
h
f
ea
tu
r
e
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
.
5
,
Octo
b
er
2
0
2
5
:
4
0
1
7
-
4
0
3
1
4022
3
.
4
.
B
uil
d
m
a
chine le
a
rning
m
o
dels
C
las
s
if
icatio
n
tech
n
iq
u
es
ar
e
cr
u
cial
f
o
r
tr
ain
i
n
g
an
d
test
in
g
s
u
p
er
v
is
ed
lear
n
i
n
g
s
y
s
tem
s
.
B
aselin
e
ML
class
if
ier
s
u
tili
ze
d
ata
f
r
o
m
th
e
tr
ain
in
g
an
d
test
in
g
s
ets
to
ac
h
iev
e
t
h
e
d
esire
d
r
esu
lts
.
T
h
e
s
elec
tio
n
o
f
an
ap
p
r
o
p
r
iate
class
if
icatio
n
m
eth
o
d
is
cr
u
cial,
as
it
s
ig
n
if
ic
an
tly
im
p
ac
ts
th
e
ac
cu
r
ac
y
,
g
en
er
aliza
tio
n
,
a
n
d
o
v
er
all
p
er
f
o
r
m
a
n
ce
o
f
th
e
ML
s
y
s
tem
.
3
.
4
.
1
.
Dec
is
io
n t
re
e
T
h
e
DT
alg
o
r
ith
m
o
p
er
ates
lik
e
a
g
r
ap
h
o
r
tr
ee
-
lik
e
s
tr
u
ctu
r
e
co
n
tain
in
g
t
h
e
r
o
o
t
n
o
d
es
an
d
s
u
b
-
n
o
d
es,
lik
e
leav
es.
T
h
e
ch
ar
ac
ter
is
tics
in
th
is
ca
s
e
ar
e
th
e
s
u
b
-
n
o
d
es,
wh
ile
th
e
s
u
b
d
iv
i
s
io
n
s
r
ep
r
esen
t
th
e
r
esu
lts
o
f
ea
ch
ex
am
in
atio
n
o
n
ea
ch
n
o
d
e.
I
t
is
am
o
n
g
th
e
m
o
s
t
wid
ely
u
s
ed
alg
o
r
ith
m
s
f
o
r
ca
teg
o
r
izatio
n
s
in
ce
it m
ay
f
u
n
ctio
n
with
o
u
t
r
eq
u
ir
in
g
lo
ca
tio
n
b
ar
r
ier
s
o
r
a
wea
lth
o
f
f
ield
d
ata
[
2
5
]
.
3
.
4
.
2
.
Ra
nd
o
m
f
o
re
s
t
T
h
e
R
F
tech
n
iq
u
e
h
as
b
ec
o
m
e
th
e
m
o
s
t
ef
f
icien
t
am
o
n
g
th
e
s
ev
er
al
ML
tech
n
iq
u
es.
I
t
h
as
b
ee
n
ap
p
lied
to
f
o
r
ec
ast an
d
p
r
o
b
ab
ilis
tic
ca
lcu
latio
n
s
.
Nu
m
er
o
u
s
DT
s
m
ak
e
u
p
th
e
R
F c
lass
if
ier
.
3
.
4
.
3
.
K
-
nea
re
s
t
neig
hb
o
r
A
p
o
p
u
lar
s
u
p
e
r
v
is
ed
lear
n
i
n
g
tech
n
iq
u
e
f
o
r
h
an
d
lin
g
r
eg
r
ess
io
n
an
d
ca
teg
o
r
izatio
n
p
r
o
b
lem
s
in
clu
d
es
th
e
k
NN.
Selectin
g
th
e
n
u
m
er
ical
v
alu
e
o
f
t
h
e
i
n
s
tan
ce
(
k
)
,
wh
ic
h
is
n
ea
r
est
to
t
h
e
q
u
er
y
,
a
n
d
d
eter
m
in
in
g
th
e
E
u
clid
ian
d
i
s
tan
ce
s
am
o
n
g
ev
er
y
e
x
am
p
l
e
with
th
e
d
ata
ar
e
th
e
s
tep
s
in
v
o
l
v
ed
in
k
NN
d
ec
is
io
n
-
m
ak
in
g
.
Fro
m
th
er
e
,
th
e
m
o
r
e
f
r
e
q
u
en
t
lab
el
with
c
ateg
o
r
izatio
n
f
o
r
r
eg
r
ess
io
n
is
s
elec
ted
.
T
h
e
k
NN
ap
p
r
o
ac
h
'
s
p
er
f
o
r
m
an
ce
is
in
cr
ea
s
ed
b
y
r
a
n
d
o
m
l
y
s
elec
tin
g
th
e
v
alu
e
o
f
k
.
3
.
4
.
4
.
G
ra
dient
bo
o
s
t
ing
GB
u
s
es
DT
all
th
e
tim
e.
I
t
is
b
ased
o
n
th
e
id
ea
th
at
th
e
o
p
ti
m
al
f
u
tu
r
e
m
o
d
el
ca
n
d
ec
r
ea
s
e
th
e
to
tal
er
r
o
r
i
n
f
o
r
ec
asti
n
g
wh
e
n
co
m
b
in
ed
with
p
r
e
v
io
u
s
m
o
d
els.
T
h
e
c
r
itical
n
o
tio
n
b
ec
o
m
es
to
r
e
d
u
ce
e
r
r
o
r
s
b
y
s
p
ec
if
y
in
g
th
e
e
x
p
ec
ted
o
u
tco
m
es
f
o
r
th
is
n
ex
t
m
o
d
el.
T
h
e
d
esire
d
r
esu
lts
f
o
r
ev
e
r
y
in
s
ta
n
ce
ar
e
ascer
tain
ed
u
s
in
g
th
e
g
r
ad
ien
t o
f
th
e
er
r
o
r
r
ate
with
r
esp
ec
t to
th
e
f
o
r
ec
as
t.
3
.
4
.
5
.
S
u
pp
o
r
t
v
e
c
t
o
r
ma
c
h
i
ne
A
h
y
p
e
r
p
l
a
n
e
h
a
s
b
e
en
e
m
p
l
o
y
e
d
b
y
th
e
S
V
M
t
o
d
iv
id
e
t
h
e
d
a
t
a
s
e
t
i
n
to
t
w
o
g
r
o
u
p
s
.
T
h
e
t
e
c
h
n
iq
u
e
l
o
o
k
s
f
o
r
a
d
e
c
i
s
i
o
n
t
h
r
e
s
h
o
ld
to
o
p
t
i
m
i
ze
t
h
e
m
a
r
g
in
a
n
d
r
e
d
u
c
e
c
at
e
g
o
r
i
z
a
t
io
n
er
r
o
r
s
a
m
o
n
g
th
e
t
w
o
g
r
o
u
p
s
.
T
h
e
p
r
o
c
e
s
s
o
f
f
i
n
d
in
g
S
V
M
a
c
co
m
p
l
i
s
h
e
s
th
i
s
.
T
h
e
d
a
t
a
e
l
e
m
en
t
s
n
e
ar
es
t
t
o
t
h
e
d
e
c
i
s
i
o
n
b
o
r
d
e
r
ar
e
th
e
s
e
.
A
d
d
i
t
i
o
n
a
l
d
a
t
a
e
l
e
m
en
t
s
c
an
b
e
c
a
t
eg
o
r
iz
e
d
b
y
i
d
e
n
t
if
y
in
g
w
h
i
ch
p
a
r
t
o
f
t
h
e
h
y
p
e
r
p
l
a
n
e
i
t
c
o
r
r
e
s
p
o
n
d
s
t
o
a
f
t
er
t
h
e
h
y
p
er
p
l
an
e
h
a
s
b
ee
n
d
i
s
c
o
v
e
r
e
d
.
W
h
en
p
r
o
j
e
c
t
i
n
g
th
e
in
p
u
t
w
i
t
h
in
a
h
i
g
h
-
d
i
m
en
s
i
o
n
a
l
p
l
an
,
th
e
k
e
r
n
el
w
i
t
h
i
n
s
u
p
p
o
r
t
v
e
c
to
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
(
S
V
C
)
i
s
u
t
i
l
iz
e
d
f
o
r
h
an
d
l
in
g
n
o
n
-
l
i
n
e
a
r
ly
s
ep
a
r
a
t
ed
d
a
t
a
[
2
6
]
,
[
2
7
]
.
3
.
4
.
6
.
E
ns
em
ble m
o
del
T
o
b
u
ild
t
h
e
e
n
s
em
b
le
m
o
d
el
u
s
ed
,
f
iv
e
b
aselin
e
ML
class
if
ier
s
,
GB
,
R
F,
KNN,
SVM,
an
d
DT
,
wer
e
tr
ain
ed
u
s
in
g
g
r
id
s
ea
r
ch
to
o
p
tim
ize
h
y
p
er
p
ar
a
m
eter
s
C
KD
p
r
ed
ictio
n
m
o
d
els
an
d
ac
h
iev
ed
th
e
b
est
p
er
f
o
r
m
an
ce
.
E
ac
h
class
if
ier
was
tr
ain
ed
o
n
t
h
e
C
KD
d
atas
et,
an
d
th
eir
p
r
e
d
ictio
n
s
wer
e
u
s
ed
to
cr
ea
te
a
n
ew
d
ataset
th
at
co
n
tain
ed
th
ese
p
r
ed
ictio
n
s
as
f
ea
tu
r
es.
T
h
is
n
e
w
d
ataset
was
th
en
u
s
ed
to
tr
ain
a
m
eta
-
lear
n
e
r
,
s
p
ec
if
ically
an
R
F
m
o
d
el
o
p
t
im
ized
b
y
g
r
id
s
ea
r
ch
.
M
e
t
a
l
ea
r
n
er
c
o
m
b
in
e
d
th
e
p
r
ed
icti
o
n
s
o
f
t
h
e
b
aselin
e
class
if
ier
s
to
p
r
o
d
u
ce
a
f
in
al,
m
o
r
e
ac
cu
r
ate
p
r
e
d
ictio
n
.
T
h
is
en
s
em
b
le
ap
p
r
o
ac
h
lev
er
a
g
es
th
e
s
tr
en
g
th
s
o
f
m
u
ltip
le
m
o
d
els to
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
f
o
r
C
KD
d
etec
tio
n
.
T
h
e
p
r
o
p
o
s
ed
Ps
eu
d
o
c
o
d
e
1
o
u
tlin
es
th
e
c
o
n
s
tr
u
ctio
n
o
f
a
n
en
s
em
b
le
lear
n
in
g
m
o
d
el
u
s
in
g
C
KD
d
ataset
.
I
n
itially
,
m
u
ltip
le
b
aselin
e
m
o
d
els
(
GB
,
R
F,
KN
N,
SVM,
DT
)
ar
e
o
p
tim
ized
u
s
in
g
g
r
id
s
ea
r
c
h
an
d
tr
ain
ed
o
n
D.
T
h
eir
p
r
ed
ictio
n
s
ar
e
th
en
s
tack
ed
to
f
o
r
m
a
m
eta
-
d
ataset
′,
o
n
wh
ich
a
m
eta
-
lear
n
er
(
R
F)
is
tr
ain
ed
to
g
e
n
er
ate
th
e
f
in
al
en
s
em
b
le
m
o
d
el,
im
p
r
o
v
i
n
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
Ps
eu
d
o
c
ode
1
: E
n
s
em
b
le
m
o
d
el
Input:
=
{
(
1
,
1
)
,
(
2
,
2
)
.
.
.
.
.
(
,
)
}
ML Models
,
,
,
,
Output: Ensemble
Begin
Step
-
1: Grid Search and Train Baseline ML Models
Initialize hyperparameter grids for
,
,
,
,
Perform grid search and cross
-
validation for each model:
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
Dete
ctio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
i
s
ea
s
e
b
a
s
ed
o
n
esemb
le
a
p
p
r
o
a
ch
w
ith
…
(
Dee
p
ika
A
mo
l
A
ja
lka
r
)
4023
For model in
[
,
,
,
,
]
:
Perform Grid Search on model with dataset
Select best model
based
-
on grid search results
Train best model
on dataset
Save trained model
=
[
,
,
,
,
]
end for
Step
-
2: Create New Dataset
′
for Meta Learner
Initialize
′
=
[
]
For each sample
(
,
)
in dataset
:
Initialize feature vector
=
[
]
For each model
in
:
= Predict class label of
using
Append
to
Append
(
,
)
to
′
end for
Step
-
3: Train Meta Learner (RF) on D'
Perform Grid Search on RF with dataset D'
Select best RF model M_RF_meta based on grid search results
Train best RF model M_RF_meta on dataset D'
Step
-
4: Return the trained Ensemble Model
R
e
t
ur
n
M
_
RF
m
e
ta
End
3
.
5
.
L
o
s
s
f
un
ct
io
n
T
h
e
lo
s
s
f
u
n
ctio
n
f
o
r
a
n
en
s
em
b
le
m
o
d
el,
esp
ec
ially
o
n
e
u
s
in
g
a
m
eta
-
lear
n
e
r
lik
e
R
F,
ty
p
ically
in
v
o
lv
es
th
e
co
m
b
in
e
d
er
r
o
r
f
r
o
m
all
th
e
b
ase
lear
n
er
s
.
Simp
lifie
d
r
ep
r
esen
tatio
n
o
f
th
e
lo
s
s
f
u
n
ctio
n
f
o
r
s
u
ch
an
en
s
em
b
le
m
o
d
el:
‒
B
ase
lear
n
er
lo
s
s
f
u
n
ctio
n
:
f
o
r
ea
ch
b
ase
lear
n
er
,
th
e
lo
s
s
f
u
n
ctio
n
s
is
co
m
p
u
ted
o
n
th
e
tr
ain
in
g
d
ataset
.
‒
Me
ta
lear
n
er
lo
s
s
f
u
n
ctio
n
:
t
h
e
m
eta
lear
n
er
u
s
es
th
e
p
r
ed
icti
o
n
s
f
r
o
m
all
b
ase
lear
n
er
s
to
c
r
ea
te
a
n
ew
d
ataset
′.
T
h
e
lo
s
s
f
u
n
ctio
n
is
co
m
p
u
ted
o
n
th
is
n
ew
d
ataset.
‒
L
o
s
s
f
u
n
ctio
n
f
o
r
b
ase
lear
n
er
s
: f
o
r
ea
ch
b
ase
lear
n
er
a
.
=
1
2
∑
(
,
(
)
)
=
1
(
2
)
W
h
er
e
r
ep
r
esen
t
n
u
m
b
e
r
o
f
f
ea
tu
r
es,
is
th
e
tr
u
e
lab
el
f
o
r
f
ea
tu
r
es
,
(
)
is
th
e
p
r
ed
ictio
n
o
f
th
e
b
ase
lear
n
er
.
f
o
r
s
am
p
le
,
an
d
is
th
e
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ct
io
n
f
o
r
class
if
icatio
n
.
‒
L
o
s
s
f
u
n
ctio
n
f
o
r
m
eta
lear
n
er
: f
o
r
th
e
m
eta
lear
n
er
:
=
1
∑
(
,
(
)
)
=
1
(
3
)
W
h
er
e
r
ep
r
esen
t
n
u
m
b
er
o
f
f
ea
tu
r
es
in
th
e
n
ew
d
ataset
′
.
is
th
e
tr
u
e
lab
el
f
o
r
th
e
n
ew
f
ea
tu
r
e
v
ec
to
r
,
(
)
is
th
e
p
r
ed
ictio
n
o
f
th
e
m
eta
lear
n
e
r
m
eta
f
o
r
t
h
e
n
ew
f
ea
tu
r
e
v
ec
to
r
,
an
d
is
th
e
n
ew
f
ea
tu
r
e
v
ec
to
r
c
o
n
s
is
tin
g
o
f
p
r
ed
ictio
n
s
f
r
o
m
all
b
ase
lear
n
er
s
f
o
r
th
e
o
r
ig
in
al
s
am
p
le
‒
C
o
m
b
in
ed
lo
s
s
f
u
n
ctio
n
:
th
e
o
v
er
all
lo
s
s
f
u
n
ctio
n
f
o
r
th
e
en
s
em
b
le
m
o
d
el
ca
n
b
e
s
ee
n
as
th
e
co
m
b
in
atio
n
o
f
th
e
lo
s
s
es f
r
o
m
th
e
b
ase
lear
n
er
s
a
n
d
th
e
m
eta
lear
n
er
:
=
∑
+
(
4
)
W
h
er
e
an
d
r
ep
r
esen
ts
th
e
weig
h
ts
th
at
b
ala
n
ce
th
e
im
p
o
r
ta
n
ce
o
f
ea
ch
b
ase
lear
n
er
'
s
lo
s
s
an
d
th
e
m
eta
lear
n
er
'
s
lo
s
s
.
3
.
6
.
H
y
perpa
ra
m
e
t
er
s
et
t
ing
s
T
h
e
r
an
d
o
m
g
r
id
s
ea
r
ch
tec
h
n
iq
u
e
was
em
p
lo
y
ed
f
o
r
h
y
p
er
m
eter
co
n
f
ig
u
r
atio
n
to
attai
n
o
p
tim
al
p
er
f
o
r
m
an
ce
r
eg
ar
d
i
n
g
t
h
e
co
m
p
u
tatio
n
e
f
f
icien
cy
o
f
th
e
s
u
g
g
ested
b
aselin
e
ML
class
if
ier
s
an
d
en
s
em
b
le
m
o
d
el
as
s
h
o
w
n
o
n
T
a
b
le
1
.
Gr
id
s
ea
r
ch
allo
ws
f
o
r
s
y
s
tem
atica
lly
ex
am
in
in
g
d
if
f
er
en
t
v
a
r
iatio
n
s
o
f
h
y
p
er
p
ar
am
eter
s
b
y
p
r
o
v
id
in
g
a
s
eq
u
en
ce
o
f
v
al
u
es
co
r
r
esp
o
n
d
in
g
t
o
ev
er
y
p
ar
am
eter
.
T
h
is
g
u
ar
an
tees
th
at
ev
er
y
p
o
s
s
ib
ilit
y
is
ex
p
lo
r
ed
to
d
eter
m
in
e
th
e
h
y
p
er
p
a
r
am
eter
s
'
d
esire
d
v
alu
es.
B
ec
au
s
e
g
r
id
s
ea
r
ch
s
ee
m
s
p
r
ed
ictab
le,
it
co
n
s
is
ten
tly
p
r
o
d
u
ce
s
id
en
tical
r
esu
lts
with
s
im
ilar
in
f
o
r
m
atio
n
an
d
p
ar
a
m
eter
s
.
T
h
is
f
ea
tu
r
e
m
ak
es
it
ea
s
ier
to
co
m
p
ar
e
d
at
a
r
ep
ea
ted
ly
,
p
r
o
m
o
tin
g
ac
cu
r
ate
an
aly
s
is
an
d
ev
al
u
atio
n
.
G
r
id
s
ea
r
ch
is
s
im
p
le
to
u
s
e
an
d
is
o
n
e
o
f
its
m
ain
b
en
ef
its
.
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
.
5
,
Octo
b
er
2
0
2
5
:
4
0
1
7
-
4
0
3
1
4024
T
ab
le
1
.
Hy
p
er
p
ar
a
m
eter
s
ettin
g
o
f
p
r
o
p
o
s
ed
b
aselin
e
ML
class
if
ier
s
an
d
en
s
em
b
le
m
o
d
el
C
l
a
s
si
f
i
e
r
s
P
a
r
a
me
t
e
r
s
GB
p
a
r
a
m
e
t
e
r
s_
g
r
i
d
_
g
b
=
{'
n
_
e
st
i
ma
t
o
r
s'
:
[
5
0
,
1
0
0
,
2
0
0
]
,
'l
e
a
r
n
i
n
g
_
r
a
t
e
'
:
[
0
.
0
1
,
0
.
1
,
0
.
2
]
,
'
ma
x
_
d
e
p
t
h
'
:
[
3
,
4
,
5
]
,
's
u
b
sam
p
l
e
':
[
0
.
7
,
0
.
8
,
0
.
9
]
}
S
V
M
p
a
r
a
m
e
t
e
r
s_
g
r
i
d
=
{'
k
e
r
n
e
l
'
:
[
'
p
o
l
y
'
,
'r
b
f
',
'
l
i
n
e
a
r
',
's
i
g
m
o
i
d
']
,
'C
'
:
[
0
.
1
,
1
,
1
0
,
1
0
0
,
1
0
0
0
]
,
'g
a
mm
a
':
[
's
c
a
l
e
',
'a
u
t
o
']
,
'sh
r
i
n
k
i
n
g
'
:
[
Tr
u
e
,
F
a
l
s
e
]
}
K
N
N
k
n
n
_
p
a
r
a
me
t
e
r
s
_
g
r
i
d
=
{'
n
_
n
e
i
g
h
b
o
r
s'
:
[
1
,
2
,
3
,
4
,
5
,
6
,
7
,
8
,
9
,
1
0
]
,
'w
e
i
g
h
t
s'
:
[
'u
n
i
f
o
r
m',
'd
i
s
t
a
n
c
e
']
,
'a
l
g
o
r
i
t
h
m'
:
[
'a
u
t
o
',
b
a
l
l
_
t
r
e
e
'
,
'k
d
_
t
r
e
e
',
'
b
r
u
t
e
']
,
'n
_
j
o
b
s':
[
1
,
-
1
]
}
DT
d
t
_
p
a
r
a
m
e
t
e
r
s_
g
r
i
d
=
{'
c
r
i
t
e
r
i
o
n
':
[
'g
i
n
i
',
'e
n
t
r
o
p
y
']
,
'sp
l
i
t
t
e
r
':
[
'
b
e
s
t
',
'r
a
n
d
o
m']
,
'mi
n
_
sam
p
l
e
s_
l
e
a
f
':
[
1
,
2
,
3
,
4
,
5
]
,
'max
_
f
e
a
t
u
r
e
s':
[
'a
u
t
o
',
's
q
r
t
'
,
'l
o
g
2
']
}
RF
r
f
_
p
a
r
a
me
t
e
r
s_
g
r
i
d
=
{'
n
_
e
st
i
ma
t
o
r
s':
[
1
0
,
3
0
,
4
0
,
5
0
,
6
0
,
7
0
,
8
0
,
9
0
,
1
0
0
]
,
'cri
t
e
r
i
o
n
'
:
[
'g
i
n
i
',
'e
n
t
r
o
p
y
']
,
'
mi
n
_
s
a
m
p
l
e
s_
s
p
l
i
t
'
:
[
1
.
0
,
2
,
3
,
4
,
5
]
,
'
ma
x
_
f
e
a
t
u
r
e
s':
[
'a
u
t
o
',
's
q
r
t
'
,
'l
o
g
2
']
}
En
se
mb
l
e
p
a
r
a
m
_
g
r
i
d
=
{'
n
_
e
st
i
ma
t
o
r
s':
[
1
0
,
5
0
,
1
0
0
]
,
'cri
t
e
r
i
o
n
':
[
'g
i
n
i
',
'
e
n
t
r
o
p
y
']
,
'm
i
n
_
sam
p
l
e
s
_
sp
l
i
t
':
[
2
,
5
,
1
0
]
,
'
ma
x
_
f
e
a
t
u
r
e
s'
:
[
'a
u
t
o
',
'sq
r
t
',
'
l
o
g
2
'
]
}
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
ef
f
e
ctiv
en
ess
o
f
th
e
s
u
g
g
ested
b
a
s
elin
e
ML
class
if
ier
s
an
d
th
e
s
u
g
g
ested
ML
-
b
ased
en
s
em
b
le
class
if
ier
in
d
etec
tin
g
an
d
class
if
y
in
g
th
e
C
KD
o
n
th
e
d
ataset
b
ased
o
n
th
e
f
ea
tu
r
e
o
p
tim
izatio
n
tech
n
iq
u
e.
All
th
e
b
aselin
e
ML
class
if
ier
s
wer
e
tu
n
ed
u
s
in
g
r
a
n
d
o
m
g
r
id
s
ea
r
ch
,
an
d
all
class
if
ier
s
wer
e
b
u
ilt
u
s
in
g
Ker
as
an
d
th
e
T
en
s
o
r
Flo
w
lib
r
ar
y
.
G
r
id
s
ea
r
ch
was
u
tili
ze
d
to
o
p
tim
ize
t
h
e
m
eta
-
lear
n
er
class
if
ier
.
Go
o
g
l
e
C
o
lab
o
r
ato
r
y
was
u
s
ed
t
o
c
o
n
d
u
ct
all
o
f
th
e
test
s
.
W
e
u
s
ed
th
e
C
KD
d
ataset
f
o
r
th
ese
e
x
p
er
im
e
n
ts
.
Usi
n
g
s
tr
atif
ied
s
am
p
lin
g
,
d
iv
id
e
th
e
d
ataset
in
to
two
s
ets:
7
0
%
tr
ain
in
g
with
2
8
0
s
am
p
les
an
d
3
0
%
test
in
g
with
1
2
0
s
am
p
les.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
ML
m
o
d
els
was
m
e
asu
r
ed
u
s
in
g
s
ev
er
al
ev
alu
atio
n
p
ar
a
m
eter
s
s
u
ch
a
s
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
r
u
e
p
o
s
itiv
e
(
T
P),
f
alse
p
o
s
itiv
e
(
FP
)
,
tr
u
e
n
eg
ativ
e
(
T
N)
,
a
n
d
f
alse n
eg
ativ
e
(
FN)
r
ep
r
esen
t t
h
e
u
n
its
o
f
ca
lc
u
latio
n
u
s
ed
f
o
r
all
o
f
th
em
.
=
_
+
_
_
+
_
+
_
+
_
(
5
)
=
_
_
+
_
(
6
)
=
_
_
+
_
(
7
)
1
−
=
2
×
×
+
(
8
)
T
a
b
l
e
2
s
h
o
w
s
t
h
e
p
e
r
f
o
r
m
a
n
c
e
a
n
a
l
y
s
i
s
o
f
v
a
r
i
o
u
s
b
a
s
e
l
i
n
e
M
L
c
l
a
s
s
i
f
i
e
r
s
a
n
d
a
n
e
n
s
e
m
b
l
e
m
o
d
e
l
b
a
s
e
d
o
n
t
h
e
i
r
m
e
t
r
i
c
s
.
T
h
e
G
B
a
n
d
R
F
b
o
t
h
a
c
h
i
e
v
e
a
h
i
g
h
a
c
c
u
r
a
c
y
o
f
9
7
.
5
%
,
w
i
t
h
G
B
h
a
v
i
n
g
a
p
r
e
c
i
s
i
o
n
o
f
9
5
.
4
%
a
n
d
r
e
c
a
l
l
o
f
9
7
.
6
%
,
r
e
s
u
l
t
i
n
g
i
n
a
n
F
1
-
s
c
o
r
e
o
f
9
6
.
5
%
.
R
F
d
e
m
o
n
s
t
r
a
t
e
s
p
e
r
f
e
c
t
r
e
c
a
l
l
a
t
1
0
0
%
,
s
l
i
g
h
t
l
y
l
o
w
e
r
p
r
e
c
i
s
i
o
n
a
t
9
4
.
7
%
,
a
n
d
t
h
e
h
i
g
h
e
s
t
F
1
s
c
o
r
e
a
t
9
7
.
3
%
.
K
N
N
s
h
o
w
s
t
h
e
l
o
w
e
s
t
a
c
c
u
r
a
c
y
a
t
9
2
.
5
%
,
p
r
e
c
i
s
i
o
n
o
f
9
3
.
0
%
,
r
e
c
a
l
l
o
f
9
1
.
4
%
,
a
n
d
a
n
F
1
-
s
c
o
r
e
o
f
9
2
.
1
%
.
S
V
M
p
e
r
f
o
r
m
s
w
e
l
l
w
i
t
h
9
5
.
8
%
a
c
c
u
r
a
c
y
,
9
4
.
7
%
p
r
e
c
i
s
i
o
n
,
9
6
.
4
%
r
e
c
a
l
l
,
a
n
d
a
9
5
.
6
%
F
1
s
c
o
r
e
.
D
T
a
c
h
i
e
v
e
s
9
3
.
3
%
a
c
c
u
r
a
c
y
,
8
9
.
5
%
p
r
e
c
i
s
i
o
n
,
9
6
.
2
%
r
e
c
a
l
l
,
a
n
d
a
9
2
.
7
%
F
1
s
c
o
r
e
.
T
h
e
e
n
s
e
m
b
l
e
m
o
d
e
l
c
o
n
s
i
s
t
e
n
t
l
y
p
e
r
f
o
r
m
s
c
o
n
s
i
s
t
e
n
t
l
y
a
c
r
o
s
s
a
l
l
m
e
t
r
i
c
s
,
a
c
h
i
e
v
i
n
g
9
7
.
5
%
a
c
c
u
r
a
c
y
,
p
r
e
c
i
s
i
o
n
,
a
n
d
r
e
c
a
l
l
a
n
d
a
n
e
a
r
l
y
p
e
r
f
e
c
t
F
1
-
s
c
o
r
e
o
f
9
7
.
4
%
.
T
a
b
l
e
s
3
t
o
8
s
h
o
w
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
p
o
r
t
o
f
e
a
c
h
b
a
s
e
l
i
n
e
M
L
m
o
d
e
l
.
I
t
i
s
i
n
d
i
c
a
t
e
d
t
h
a
t
e
a
c
h
m
o
d
e
l
p
e
r
f
o
r
m
e
d
b
e
t
t
e
r
,
w
i
t
h
a
m
a
x
i
m
u
m
a
c
c
u
r
a
c
y
s
c
o
r
e
o
f
9
7
.
0
0
%
.
T
a
b
l
e
8
a
l
s
o
s
h
o
w
s
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
p
o
r
t
o
f
t
h
e
p
r
o
p
o
s
e
d
e
n
s
e
m
b
l
e
m
o
d
e
l
.
T
ab
le
2.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
p
r
o
p
o
s
ed
b
aselin
e
ML
an
d
en
s
em
b
le
m
o
d
el
C
l
a
s
si
f
i
e
r
s
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
GB
9
7
.
5
9
5
.
4
9
7
.
6
9
6
.
5
RF
9
7
.
5
9
4
.
7
1
0
0
9
7
.
3
K
N
N
9
2
.
5
9
3
.
0
9
1
.
4
9
2
.
1
S
V
M
9
5
.
8
9
4
.
7
9
6
.
4
9
5
.
6
DT
9
3
.
3
8
9
.
5
9
6
.
2
9
2
.
7
En
se
mb
l
e
9
7
.
5
9
7
.
5
9
7
.
5
9
7
.
4
T
ab
le
3
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
GB
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
9
7
1
.
0
0
0
.
9
8
84
1
1
.
0
0
0
.
9
2
0
.
9
6
36
A
c
c
u
r
a
c
y
0
.
9
7
1
2
0
M
a
c
r
o
A
v
g
0
.
9
8
0
.
9
6
0
.
9
7
1
2
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
8
0
.
9
7
0
.
9
7
1
2
0
T
ab
le
4
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
SVM
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
9
7
1
.
0
0
0
.
9
8
84
1
1
.
0
0
0
.
9
2
0
.
9
6
36
A
c
c
u
r
a
c
y
0
.
9
7
1
2
0
M
a
c
r
o
A
v
g
0
.
9
8
0
.
9
6
0
.
9
7
1
2
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
8
0
.
9
7
0
.
9
7
1
2
0
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
Dete
ctio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
i
s
ea
s
e
b
a
s
ed
o
n
esemb
le
a
p
p
r
o
a
ch
w
ith
…
(
Dee
p
ika
A
mo
l
A
ja
lka
r
)
4025
T
ab
le
5
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
KNN
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
9
5
0
.
9
8
0
.
9
6
84
1
0
.
9
4
0
.
8
9
0
.
9
1
36
A
c
c
u
r
a
c
y
0
.
9
5
1
2
0
M
a
c
r
o
A
v
g
0
.
9
5
0
.
9
3
0
.
9
4
1
2
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
5
0
.
9
5
0
.
9
5
1
2
0
T
ab
le
6
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
R
F
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
9
7
1
.
0
0
0
.
9
8
84
1
1
.
0
0
0
.
9
2
0
.
9
6
36
A
c
c
u
r
a
c
y
0
.
9
7
1
2
0
M
a
c
r
o
A
v
g
0
.
9
8
0
.
9
6
0
.
9
7
1
2
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
8
0
.
9
7
0
.
9
7
1
2
0
T
ab
le
7
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
DT
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
9
7
1
.
0
0
0
.
9
8
84
1
1
.
0
0
0
.
9
2
0
.
9
6
36
A
c
c
u
r
a
c
y
0
.
9
7
1
2
0
M
a
c
r
o
A
v
g
0
.
9
8
0
.
9
6
0
.
9
7
1
2
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
8
0
.
9
7
0
.
9
7
1
2
0
T
ab
le
8
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
en
s
em
b
le
m
o
d
el
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
9
7
1
.
0
0
0
.
9
8
84
1
1
.
0
0
0
.
9
2
0
.
9
6
36
A
c
c
u
r
a
c
y
0
.
9
7
1
2
0
M
a
c
r
o
A
v
g
0
.
9
8
0
.
9
6
0
.
9
7
1
2
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
8
0
.
9
7
0
.
9
7
1
2
0
Fig
u
r
e
5
s
h
o
ws
th
e
co
n
f
u
s
i
o
n
m
at
r
ix
o
f
th
e
p
r
o
p
o
s
ed
b
aselin
e
ML
an
d
e
n
s
em
b
le
m
o
d
el
f
o
r
ca
lcu
latin
g
th
e
T
P,
FN,
T
N,
an
d
FP
v
alu
es.
T
h
e
p
r
o
p
o
s
ed
GB
,
SVM,
DT
,
R
F,
an
d
e
n
s
em
b
le
m
o
d
els
all
ex
h
ib
it
s
im
ilar
p
r
ed
ictiv
e
v
alu
es
with
8
4
T
Ps
,
0
FN
s
,
3
3
T
Ns,
an
d
3
FP
s
,
in
d
icatin
g
p
er
f
e
ct
r
ec
all
d
u
e
to
th
e
ab
s
en
ce
o
f
FNs
an
d
h
ig
h
s
p
ec
if
icity
with
o
n
ly
3
FP
s
o
u
t
o
f
3
6
TN
s
.
KNN
s
h
o
ws
s
l
ig
h
tly
lo
wer
p
er
f
o
r
m
an
ce
with
8
2
T
Ps
,
2
FNs
,
3
2
T
Ns,
an
d
4
FP
s
,
s
til
l
m
ain
tain
in
g
h
ig
h
s
en
s
itiv
ity
b
u
t
s
lig
h
tly
d
ec
r
ea
s
in
g
s
p
ec
if
icity
.
T
h
is
an
aly
s
is
in
d
icate
s
th
at
all
m
o
d
els,
ex
ce
p
t
KNN,
p
r
o
v
i
d
ed
alm
o
s
t
id
en
tical
an
d
s
u
p
e
r
io
r
p
er
f
o
r
m
a
n
ce
in
id
en
tify
in
g
p
o
s
itiv
e
an
d
n
eg
ati
v
e
ca
s
es,
with
KNN
p
er
f
o
r
m
in
g
s
lig
h
tly
lo
wer
in
c
o
m
p
ar
is
o
n
.
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
p
r
o
p
o
s
ed
class
if
ier
s
F
i
g
u
r
e
s
6
to
1
1
s
h
o
w
t
h
e
3
D
p
l
o
t
s
f
o
r
G
B
,
S
V
M
,
K
N
N
,
DT
,
R
F
,
an
d
e
n
s
em
b
l
e,
wh
i
c
h
in
d
i
c
a
te
t
h
e
r
e
l
a
t
i
o
n
s
h
ip
b
e
t
w
e
en
v
a
r
io
u
s
h
y
p
er
p
ar
a
m
e
te
r
s
an
d
m
o
d
el
a
c
cu
r
a
cy
.
T
h
e
r
e
a
r
e
th
r
e
e
3
D
p
lo
t
s
o
f
ea
c
h
m
o
d
e
l
.
T
h
e
f
i
r
s
t
p
l
o
t
ex
a
m
in
es
t
h
e
e
f
f
ec
t
o
f
v
a
r
y
i
n
g
t
h
e
n
u
m
b
e
r
o
f
e
s
t
i
m
a
t
o
r
s
(
n
_
e
s
t
i
m
a
to
r
s
)
o
f
e
a
ch
m
o
d
e
l
a
n
d
t
h
e
s
u
b
s
a
m
p
l
e
r
a
t
io
o
n
ac
c
u
r
ac
y
,
w
i
th
a
s
p
ec
i
f
i
c
co
n
f
i
g
u
r
a
t
i
o
n
o
f
2
0
0
e
s
t
i
m
a
to
r
s
an
d
a
s
u
b
s
a
m
p
l
e
o
f
0
.
7
;
C
p
a
r
a
m
e
t
er
i
s
o
n
e
a
n
d
s
h
r
i
n
k
i
n
g
w
a
s
s
e
t
t
o
t
r
u
e
;
m
in
im
u
m
s
a
m
p
l
e
l
e
a
f
s
e
t
t
o
4
f
o
r
D
T
;
an
d
m
in
i
m
u
m
s
a
m
p
l
e
s
p
l
i
t
t
i
n
g
v
a
l
u
e
s
s
e
t
t
o
1
0
f
o
r
R
F
;
m
i
n
i
m
u
m
s
a
m
p
le
s
p
l
i
t
t
i
n
g
v
a
l
u
e
s
s
e
t
t
o
2
a
n
d
m
a
x
i
m
u
m
d
ep
t
h
i
s
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
.
5
,
Octo
b
er
2
0
2
5
:
4
0
1
7
-
4
0
3
1
4026
1
0
f
o
r
e
n
s
e
m
b
l
e
.
I
t
i
l
l
u
s
tr
a
t
e
s
h
o
w
th
e
a
c
cu
r
ac
y
ch
an
g
e
s
a
s
t
h
e
p
ar
a
m
e
t
e
r
s
ar
e
a
d
ju
s
t
e
d
,
s
h
o
w
i
n
g
p
o
t
e
n
t
ia
l
p
e
a
k
s
a
t
s
p
e
c
i
f
ie
d
v
a
lu
e
s
.
T
h
e
s
e
c
o
n
d
p
lo
t
e
x
p
l
o
r
e
s
t
h
e
ef
f
e
c
t
o
f
c
h
an
g
in
g
t
h
e
l
e
ar
n
in
g
r
a
t
e
an
d
s
u
b
s
am
p
l
e
r
a
t
i
o
o
n
t
h
e
a
c
cu
r
a
cy
s
e
t
t
o
a
l
e
a
r
n
in
g
r
a
t
e
o
f
0
.
1
an
d
a
s
u
b
s
a
m
p
le
o
f
0
.
7
f
o
r
G
B
.
T
h
e
b
e
s
t
p
a
r
am
e
t
e
r
g
a
m
m
a
i
s
o
n
e
,
a
n
d
s
h
r
i
n
k
i
n
g
i
s
t
r
u
e
f
o
r
S
V
M
,
e
m
p
h
a
s
i
z
in
g
h
o
w
a
cc
u
r
a
c
y
r
e
s
p
o
n
d
s
t
o
p
a
r
am
e
t
e
r
c
h
a
n
g
e
s
,
p
o
t
en
t
i
a
l
l
y
r
e
v
e
a
l
i
n
g
o
p
t
i
m
a
l
r
e
g
io
n
s
f
o
r
t
h
e
s
e
s
e
t
t
i
n
g
s
.
T
h
e
t
h
ir
d
p
lo
t
f
o
c
u
s
ed
o
n
t
h
e
in
t
e
r
a
c
t
io
n
b
e
t
w
e
en
t
h
e
l
e
a
r
n
i
n
g
r
a
te
a
n
d
t
h
e
n
u
m
b
e
r
o
f
e
s
t
i
m
a
t
o
r
s
a
t
l
e
a
r
n
i
n
g
r
a
t
e
s
b
e
t
we
e
n
0
.
1
a
n
d
2
0
0
e
s
t
i
m
a
t
o
r
s
an
d
h
o
w
t
h
e
s
e
p
ar
a
m
e
t
e
r
s
in
f
lu
e
n
ce
t
h
e
m
o
d
e
l
's
p
er
f
o
r
m
an
c
e,
h
e
l
p
i
n
g
t
o
i
d
en
t
i
f
y
t
h
e
b
e
s
t
c
o
m
b
i
n
a
t
io
n
f
o
r
m
a
x
i
m
u
m
a
c
cu
r
a
cy
.
Fig
u
r
e
6
.
3
D
p
lo
ttin
g
o
f
GB
Fig
u
r
e
7
.
3
D
p
lo
ttin
g
o
f
SVM
Fig
u
r
e
8
.
3
D
p
lo
ttin
g
o
f
KNN
Evaluation Warning : The document was created with Spire.PDF for Python.