I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
9
,
No
.
1
,
Ju
ly
2
0
2
5
,
p
p
.
387
~
3
9
8
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijeecs.v
3
9
.i
1
.
pp
387
-
3
9
8
387
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Co
ntext de
pende
nt
bidir
ectiona
l d
eep learning
and
B
a
y
esia
n
g
a
uss
ia
n auto
-
enco
der f
o
r pr
edict
io
n of kidn
ey
disea
se
J
a
y
a
s
hree
M
1,
2
,
Anitha
N
3
1
Ea
st
P
o
i
n
t
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
V
i
sv
e
sv
a
r
a
y
a
Te
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
s
i
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
C
M
R
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
B
a
n
g
a
l
o
r
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
B
N
M
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
a
n
g
a
l
o
r
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
J
u
l
31
,
2
0
2
4
R
ev
is
ed
Feb
26
,
2
0
2
5
Acc
ep
ted
Mar
26
,
2
0
2
5
Ch
ro
n
ic
k
id
n
e
y
d
ise
a
se
(CKD
)
h
a
s
e
m
e
rg
e
d
a
s
a
si
g
n
ifi
c
a
n
t
g
lo
b
a
l
h
e
a
lt
h
issu
e
,
lea
d
in
g
to
m
il
li
o
n
s
o
f
p
re
m
a
tu
re
d
e
a
th
s
a
n
n
u
a
ll
y
.
Early
p
r
e
d
ictio
n
o
f
CKD
is
c
ru
c
ial
f
o
r
ti
m
e
ly
d
iag
n
o
sis
a
n
d
p
re
v
e
n
ti
v
e
m
e
a
su
re
s.
W
h
i
le
v
a
rio
u
s
d
e
e
p
lea
rn
in
g
(DL)
m
e
th
o
d
s
h
a
v
e
b
e
e
n
in
tr
o
d
u
c
e
d
fo
r
CKD
p
re
d
ictio
n
,
a
c
h
iev
in
g
r
o
b
u
st
q
u
a
n
ti
f
ica
ti
o
n
re
su
lt
s
re
m
a
in
s
c
h
a
ll
e
n
g
i
n
g
.
To
a
d
d
re
ss
th
is,
we
p
ro
p
o
se
t
h
e
c
o
n
tex
t
-
d
e
p
e
n
d
e
n
t
b
i
-
d
irec
ti
o
n
a
l
DL
a
n
d
Ba
y
e
sia
n
g
a
u
ss
ian
a
u
to
e
n
c
o
d
e
r
(
CDBD
P
-
BG
A)
m
e
th
o
d
fo
r
CKD
p
re
d
icti
o
n
.
Th
is
a
p
p
ro
a
c
h
u
ti
li
z
e
s
c
li
n
ica
l
p
a
ra
m
e
ter
s
a
n
d
sy
m
p
to
m
s
fr
o
m
a
str
u
c
tu
re
d
d
a
tas
e
t.
By
in
c
o
r
p
o
ra
ti
n
g
c
o
n
tex
t
d
e
p
e
n
d
e
n
c
e
in
to
t
h
e
bi
-
d
irec
ti
o
n
a
l
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(
Bi
-
LS
TM
)
m
o
d
e
l,
C
DBD
P
-
BG
A
e
fficie
n
tl
y
re
d
istri
b
u
tes
t
h
e
re
p
re
se
n
tatio
n
o
f
i
n
fo
rm
a
ti
o
n
,
e
n
h
a
n
c
in
g
it
s
m
o
d
e
li
n
g
c
a
p
a
b
il
i
ti
e
s.
F
e
a
tu
re
se
lec
ti
o
n
is
o
p
t
imiz
e
d
u
si
n
g
a
BG
A
-
b
a
s
e
d
a
lg
o
ri
th
m
,
w
h
ich
e
m
p
lo
y
s
th
e
Ba
y
e
sia
n
g
a
u
ss
ian
fu
n
c
ti
o
n
.
T
h
e
S
o
ftM
a
x
a
c
ti
v
a
ti
o
n
fu
n
c
ti
o
n
c
las
sifies
CKD
in
to
fi
v
e
d
isti
n
c
t
sta
g
e
s
b
a
se
d
o
n
e
stim
a
ted
-
g
lo
m
e
ru
lar
f
il
t
ra
ti
o
n
-
r
a
te
(e
G
F
R),
c
o
n
sid
e
rin
g
b
o
th
s
y
m
p
t
o
m
s
(t
e
x
tu
re
a
n
d
n
u
m
e
rica
l
fe
a
tu
re
s)
a
n
d
c
li
n
ica
l
p
a
ra
m
e
ters
(a
g
e
,
se
x
,
a
n
d
c
re
a
ti
n
in
e
).
S
im
u
latio
n
re
su
lt
s
u
sin
g
two
d
a
tas
e
ts
d
e
m
o
n
stra
te
t
h
a
t
CDBD
P
-
BG
A
o
u
tp
e
rf
o
rm
s
c
o
n
v
e
n
ti
o
n
a
l
m
e
th
o
d
s,
a
c
h
iev
in
g
9
7
.
4
%
a
c
c
u
ra
c
y
wit
h
o
u
t
e
G
F
R
a
n
d
9
8
.
7
%
wit
h
e
G
F
R.
K
ey
w
o
r
d
s
:
C
h
r
o
n
ic
k
id
n
ey
d
is
ea
s
e
C
o
n
tex
t d
ep
en
d
en
t
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Pre
d
ictio
n
So
f
tMa
x
ac
tiv
atio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
ay
s
h
r
ee
M
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Scien
ce
E
n
g
in
ee
r
in
g
,
E
ast Po
in
t Co
lleg
e
o
f
E
n
g
i
n
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
Vis
v
esv
ar
ay
a
T
ec
h
n
o
l
o
g
ical
Un
iv
er
s
ity
B
elag
av
i,
Kar
n
atak
a,
I
n
d
ia
E
m
ail: ja
y
a.
r
ajen
d
r
a
2
0
2
4
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
h
r
o
n
ic
k
id
n
e
y
d
is
e
ase
(
C
KD)
r
ef
er
s
to
k
id
n
ey
d
am
ag
e
r
esu
ltin
g
f
r
o
m
t
h
e
in
ab
ilit
y
to
f
ilter
b
lo
o
d
p
r
o
p
er
l
y
.
T
h
e
k
id
n
ey
’
s
p
r
im
a
r
y
f
u
n
ctio
n
is
to
r
em
o
v
e
ex
ce
s
s
wate
r
an
d
waste
f
r
o
m
th
e
b
lo
o
d
,
wh
ich
ar
e
th
en
ex
cr
eted
v
ia
u
r
in
e.
Du
e
to
a
lack
o
f
ea
r
ly
d
is
ea
s
e
d
ia
g
n
o
s
is
,
th
e
m
o
r
tality
r
ate
ass
o
ciate
d
with
C
KD
h
as
r
ec
en
tly
in
c
r
ea
s
ed
.
Var
io
u
s
m
eth
o
d
s
h
a
v
e
b
ee
n
d
ev
elo
p
e
d
to
ass
is
t
d
o
cto
r
s
in
m
in
im
izin
g
m
o
r
tality
b
y
em
p
lo
y
in
g
s
o
p
h
is
ticated
co
m
p
u
ter
-
b
ased
d
etec
tio
n
tech
n
iq
u
es.
E
ar
ly
d
etec
tio
n
o
f
C
KD
i
s
o
f
u
tm
o
s
t
im
p
o
r
tan
ce
i
n
th
e
f
ield
o
f
r
e
s
ea
r
ch
,
as
th
e
d
is
ea
s
e
f
r
eq
u
e
n
tly
p
r
esen
ts
its
elf
o
n
ly
a
f
ter
s
u
b
s
tan
tial
k
id
n
ey
d
am
ag
e
h
as
tak
en
p
lace
.
T
h
is
ea
r
ly
d
etec
tio
n
h
as
th
e
p
o
ten
tial
to
s
av
e
n
u
m
er
o
u
s
liv
es
a
n
d
g
r
ea
tly
d
ec
r
ea
s
e
m
o
r
tality
r
ates
ass
o
ciate
d
w
i
th
C
KD.
Saif
et
a
l.
[
1
]
ex
p
lain
ed
,
a
d
ee
p
en
s
em
b
le
m
eth
o
d
was
p
r
o
p
o
s
ed
,
em
p
lo
y
in
g
a
m
ajo
r
ity
v
o
tin
g
f
u
n
ctio
n
f
o
r
p
r
e
d
ictio
n
o
u
tc
o
m
es,
r
esu
ltin
g
in
s
u
b
s
tan
tial
im
p
r
o
v
em
en
ts
i
n
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
Desp
ite
th
ese
im
p
r
o
v
e
m
en
ts
in
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
ac
c
u
r
ac
y
,
th
e
tr
ain
in
g
tim
e
f
o
r
ea
r
ly
d
etec
tio
n
was
n
o
t
ad
d
r
ess
ed
.
T
o
tack
le
th
is
,
a
p
ip
elin
e
p
r
o
ce
s
s
in
g
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
s
(
E
HR
s
)
u
s
in
g
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
was
d
esig
n
ed
to
p
r
ed
ict
C
KD
p
r
o
g
r
ess
io
n
th
r
o
u
g
h
d
is
tin
ct
s
tag
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
387
-
3
9
8
388
T
h
is
m
eth
o
d
,
ca
lled
lo
n
g
-
s
h
o
r
t
ter
m
-
m
em
o
r
y
(
L
STM
)
R
NN
o
r
k
id
n
ey
d
is
ea
s
e
p
r
o
g
r
ess
io
n
[
2
]
,
ac
h
iev
ed
h
ig
h
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
Ho
wev
er
,
wh
ile
im
p
r
o
v
em
en
ts
wer
e
o
b
s
er
v
ed
in
th
e
p
r
ec
is
io
n
-
r
ec
al
l
cu
r
v
e,
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
o
f
b
in
ar
y
class
if
icatio
n
was
n
o
t
an
aly
ze
d
.
Du
e
to
d
ataset
len
g
th
an
d
r
e
d
u
n
d
a
n
cy
,
m
a
n
y
ex
is
tin
g
ap
p
r
o
ac
h
es
p
r
o
d
u
ce
in
co
r
r
ec
t
p
r
ed
ictio
n
s
,
d
iag
n
o
s
in
g
in
d
iv
i
d
u
als
with
m
ild
C
KD
s
y
m
p
to
m
s
as
s
ev
er
e
ca
s
es
an
d
ad
m
in
is
ter
in
g
in
a
p
p
r
o
p
r
i
at
e
th
er
ap
ies.
T
o
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
,
d
ata
m
in
i
n
g
with
s
elf
-
tu
n
in
g
s
p
ec
tr
al
clu
s
ter
in
g
u
s
in
g
K
-
m
o
d
e
was
p
r
o
p
o
s
ed
in
[
3
]
.
Ho
wev
er
,
r
ea
l
-
tim
e
d
ep
l
o
y
m
en
t
ch
allen
g
es
ar
is
e
as
p
atien
t
d
ata
co
n
tin
u
o
u
s
ly
u
p
d
ates,
with
n
o
ef
f
icien
t
m
eth
o
d
to
in
co
r
p
o
r
ate
n
ew
d
ata
[
4
]
.
T
o
ad
d
r
ess
th
is
,
a
n
o
v
el
s
elf
-
co
r
r
ec
tin
g
m
ec
h
a
n
is
m
f
o
r
R
NN
was
in
tr
o
d
u
ce
d
,
r
esu
ltin
g
in
im
p
r
o
v
ed
r
ec
eiv
er
o
p
e
r
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
e
p
er
f
o
r
m
a
n
ce
.
An
o
t
h
er
s
tu
d
y
e
m
p
lo
y
ed
a
n
L
STM
-
R
NN
f
o
c
u
s
in
g
o
n
th
e
er
r
o
r
f
ac
to
r
[
5
]
.
Mo
r
eo
v
er
,
a
r
ev
iew
o
f
en
s
em
b
le
tech
n
iq
u
es
f
o
r
C
KD
p
r
ed
i
ctio
n
was
co
n
d
u
cted
in
[
6
]
,
a
n
d
an
o
th
er
p
r
ed
ictiv
e
m
o
d
el
f
o
r
k
i
d
n
ey
tr
an
s
p
lan
t
en
d
p
o
in
ts
was
p
r
ese
n
ted
in
[
7
]
.
Diab
etic
k
id
n
e
y
d
is
ea
s
e
p
r
o
g
r
ess
io
n
u
s
in
g
b
io
m
ar
k
er
s
a
n
d
d
ee
p
lear
n
in
g
(
DL
)
was
p
r
o
p
o
s
ed
in
[
8
]
,
an
d
a
s
u
r
v
ey
o
f
C
KD
p
r
ed
ictio
n
o
u
tco
m
e
s
alo
n
g
with
p
atien
t
r
eq
u
i
r
em
e
n
ts
an
d
p
r
ef
e
r
en
ce
s
was
co
n
d
u
cted
in
[
9
]
.
Z
h
u
et
a
l.
[
1
0
]
s
tates
,
a
r
eg
r
ess
io
n
m
o
d
el
an
al
y
ze
d
tem
p
o
r
al
tr
e
n
d
s
to
r
e
d
u
ce
C
KD
in
cid
e
n
c
e.
An
o
th
er
s
tu
d
y
f
o
c
u
s
ed
o
n
b
o
n
e
d
is
o
r
d
er
s
a
n
d
C
KD
[
1
1
]
,
wh
ile
a
p
r
o
g
n
o
s
tic
m
o
d
el
f
o
r
C
KD
an
d
ty
p
e
2
d
iab
etes w
as p
r
esen
ted
in
[
1
2
]
.
A
r
ev
iew
o
f
ex
is
tin
g
m
eth
o
d
s
an
d
f
u
tu
r
e
d
ir
ec
tio
n
s
was
co
n
d
u
cted
in
[
1
3
]
,
an
d
a
n
ea
r
ly
C
KD
p
r
ed
ictio
n
m
o
d
e
l
was
p
r
o
p
o
s
ed
in
[
1
4
]
,
s
h
o
win
g
im
p
r
o
v
ed
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
th
r
o
u
g
h
r
eg
r
ess
io
n
an
aly
s
is
.
Giv
en
th
e
in
cr
ea
s
in
g
g
lo
b
al
s
ig
n
if
ican
ce
o
f
C
KD
as
a
m
o
r
tality
s
o
u
r
ce
,
d
esig
n
in
g
a
co
m
p
u
ter
-
aid
ed
d
ia
g
n
o
s
tic
(
C
AD)
m
eth
o
d
f
o
r
au
to
m
atic
C
KD
d
iag
n
o
s
is
is
e
s
s
en
tial.
R
a
ih
an
et
a
l.
[
1
5
]
,
th
e
ex
tr
em
e
g
r
a
d
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
clas
s
if
ier
alg
o
r
ith
m
ac
cu
r
ately
an
d
p
r
ec
is
ely
p
r
ed
icted
C
KD
p
r
esen
ce
.
New
m
ar
k
er
s
lik
e
eGFR
wer
e
u
s
ed
in
[
1
6
]
f
o
r
ea
r
ly
C
KD
p
r
ed
ictio
n
,
an
aly
zin
g
th
e
r
elatio
n
s
h
ip
b
etwe
e
n
p
atien
t
d
ata
v
ec
to
r
s
an
d
o
u
tco
m
es.
Desp
ite
im
p
r
o
v
em
e
n
ts
in
ac
cu
r
ac
y
a
n
d
p
r
ec
is
io
n
u
s
in
g
d
ee
p
en
s
em
b
le
an
d
R
NN,
th
e
tr
ain
in
g
tim
e
in
v
o
lv
in
g
clin
ical
p
ar
am
eter
s
an
d
s
y
m
p
to
m
s
in
k
id
n
ey
d
is
ea
s
e
p
r
ed
ictio
n
r
e
m
ain
s
a
ch
allen
g
e.
Hen
ce
,
th
e
co
n
tr
ib
u
tio
n
o
f
th
e
wo
r
k
ar
e
as f
o
llo
ws
:
−
T
o
ad
d
r
ess
th
e
is
s
u
es
wh
ich
th
e
e
x
is
tin
g
ap
p
r
o
ac
h
es
f
ail
ed
,
th
is
wo
r
k
p
r
esen
ts
a
co
n
tex
t
d
ep
e
n
d
en
t
bi
-
d
ir
ec
tio
n
al
DL
an
d
B
ay
esian
g
au
s
s
ian
au
to
e
n
co
d
e
r
(
C
DB
DP
-
B
GA)
f
o
r
r
o
b
u
s
t
q
u
a
n
tific
atio
n
o
f
p
r
ed
ictio
n
o
f
k
i
d
n
ey
d
is
ea
s
e.
−
C
o
n
tex
t
-
d
ep
en
d
en
t
Bi
-
L
STM
(
C
D
-
Bi
-
L
STM
)
n
etwo
r
k
is
in
tr
o
d
u
ce
d
with
co
n
tex
t
d
ep
en
d
e
n
cy
f
ac
to
r
f
o
r
tex
tu
al
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
d
e
m
o
n
s
tr
atin
g
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
e
n
ts
ag
ain
s
t
m
u
ltip
le
ex
is
tin
g
m
eth
o
d
s
an
d
l
o
wer
in
g
tr
ain
in
g
tim
e.
C
D
-
Bi
-
L
STM
n
etwo
r
k
is
ca
p
a
b
le
o
f
tr
a
d
in
g
o
f
f
b
et
wee
n
d
etec
tio
n
ac
cu
r
ac
y
an
d
tr
ain
in
g
tim
e
th
a
n
d
ee
p
e
n
s
em
b
le
m
eth
o
d
an
d
L
STM
-
R
NN.
−
T
o
s
elec
t o
p
tim
al
n
u
m
er
ical
f
e
atu
r
es a
m
o
n
g
th
e
ess
en
tial f
ea
tu
r
es o
f
C
KD,
B
G
A
-
b
ased
n
u
m
er
ical
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
is
p
r
esen
te
d
.
−
T
h
e
p
er
f
o
r
m
an
ce
o
f
p
r
ed
icti
o
n
was
ass
es
s
ed
u
s
in
g
v
ar
io
u
s
m
etr
ics
i.e
.
,
p
r
ec
is
io
n
,
r
ec
all,
F
-
m
ea
s
u
r
e,
ac
cu
r
ac
y
an
d
tr
ain
in
g
t
im
e.
R
esu
lts
ar
e
d
is
cu
s
s
ed
b
y
ev
alu
a
tin
g
C
DB
DP
-
B
GA
an
d
co
m
p
ar
in
g
s
tate
-
of
-
th
e
-
ar
t w
o
r
k
an
d
u
s
in
g
th
e
s
a
m
e
d
atasets
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
C
KD
is
a
cr
u
cial
an
d
c
o
m
p
r
eh
en
s
iv
e
p
u
b
lic
h
ea
lt
h
co
n
c
er
n
.
Ov
e
r
th
e
p
ast
f
ew
y
ea
r
s
,
its
h
ig
h
o
cc
u
r
r
e
n
ce
r
ate,
r
ate
o
f
h
o
s
p
i
talizatio
n
,
co
s
t
ass
o
ciate
d
with
m
ed
icatio
n
an
d
its
p
o
o
r
p
r
o
g
n
o
s
is
,
h
as
h
a
d
an
ex
ten
s
iv
e
in
f
l
u
en
ce
o
n
p
atien
t
’
s
q
u
ality
o
f
life
.
A
d
e
ep
en
s
em
b
le
m
eth
o
d
was
p
r
o
p
o
s
ed
,
e
m
p
lo
y
in
g
a
m
ajo
r
ity
v
o
tin
g
f
u
n
ctio
n
f
o
r
p
r
e
d
ictio
n
o
u
tco
m
es,
r
esu
ltin
g
in
s
u
b
s
tan
tial
i
m
p
r
o
v
em
en
ts
in
p
r
e
d
i
ctio
n
ac
cu
r
ac
y
[
1
]
.
Desp
ite
th
ese
im
p
r
o
v
em
en
ts
i
n
p
r
ec
is
io
n
,
r
ec
all,
an
d
ac
c
u
r
a
cy
,
th
e
tr
ain
in
g
tim
e
f
o
r
ea
r
ly
d
etec
tio
n
was
n
o
t
ad
d
r
ess
ed
.
T
o
tack
le
th
is
,
a
p
i
p
elin
e
p
r
o
ce
s
s
in
g
E
HR
s
u
s
in
g
R
NN
wa
s
d
esig
n
ed
to
p
r
ed
ict
C
KD
p
r
o
g
r
ess
io
n
th
r
o
u
g
h
d
is
tin
ct
s
tag
es.
T
h
is
m
eth
o
d
,
ca
lled
L
STM
-
R
NN
o
r
k
id
n
ey
d
is
ea
s
e
p
r
o
g
r
ess
io
n
[
2
]
,
ac
h
iev
ed
h
ig
h
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
Ho
wev
er
,
wh
ile
im
p
r
o
v
em
en
ts
wer
e
o
b
s
er
v
ed
in
th
e
p
r
ec
is
io
n
-
r
ec
al
l
cu
r
v
e,
th
e
o
v
er
all
p
er
f
o
r
m
an
ce
o
f
b
in
ar
y
class
if
icatio
n
was
n
o
t
an
aly
ze
d
.
K
id
n
ey
p
r
ed
ictio
n
was
ev
alu
ated
b
y
u
tili
zin
g
B
er
d
en
class
if
icatio
n
to
p
r
ed
ict
th
e
r
is
k
o
f
e
n
d
s
tag
e
[
1
7
]
.
E
m
p
lo
y
in
g
t
h
is
class
if
icatio
n
m
o
d
el
r
esu
lted
in
th
e
im
p
r
o
v
em
e
n
t o
f
R
OC
.
Hy
b
r
id
tech
n
iq
u
e
ca
lled
Pear
s
o
n
co
r
r
elatio
n
f
o
r
f
ea
tu
r
e
s
elec
tio
n
an
d
h
y
b
r
id
class
if
ier
s
was
em
p
lo
y
ed
in
[
1
8
]
b
y
th
e
im
p
r
o
v
em
e
n
t
o
f
ac
cu
r
ac
y
s
co
r
e
in
an
e
x
ten
s
iv
e
m
an
n
er
.
A
r
ev
iew
o
n
p
r
esen
ce
an
d
o
n
s
et
o
f
C
KD
was
p
r
esen
ted
in
[
1
9
]
with
DL
.
T
h
e
s
tu
d
y
[
2
0
]
an
d
[
2
1
]
,
a
s
y
s
tem
atic
r
ev
iew
f
o
r
d
etec
tio
n
an
d
p
r
e
d
ictio
n
m
eth
o
d
s
in
C
KD
p
r
o
g
r
ess
io
n
was
an
aly
ze
d
in
d
etail.
A
p
r
ed
ictio
n
m
eth
o
d
with
q
u
an
titativ
e
r
is
k
r
ep
r
esen
tativ
es f
o
r
d
etec
tin
g
C
KD
at
th
e
ea
r
lies
t stag
e
was p
r
esen
ted
in
[
2
2
]
.
E
n
s
em
b
le
lear
n
i
n
g
u
s
in
g
b
o
o
s
tin
g
tech
n
iq
u
es
was
p
r
o
p
o
s
e
d
in
[
2
3
]
tak
in
g
in
to
co
n
s
id
er
atio
n
s
th
e
c
lin
ical
p
ar
am
eter
s
f
o
r
C
KD
p
r
ed
ictio
n
.
en
s
em
b
le
lear
n
i
n
g
r
esu
lted
in
th
e
im
p
r
o
v
em
e
n
t
o
f
ac
cu
r
ac
y
an
d
m
in
im
ized
th
e
r
u
n
tim
e
in
a
s
ig
n
if
ican
t
m
an
n
er
.
An
in
-
d
e
p
th
an
aly
s
is
o
f
clin
ical
o
u
tco
m
es
in
p
atien
ts
with
C
KD
an
d
eGFR
was
p
r
esen
te
d
in
[
2
4
]
.
Yet
an
o
t
h
er
tim
e
-
v
a
r
y
in
g
co
x
m
o
d
el
was
a
p
p
lied
i
n
[
2
5
]
f
o
r
an
al
y
zin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
n
text
d
ep
en
d
e
n
t b
id
ir
ec
tio
n
a
l d
ee
p
lea
r
n
in
g
a
n
d
B
a
ye
s
ia
n
g
a
u
s
s
ia
n
a
u
to
-
en
c
o
d
er
…
(
Ja
ya
s
h
r
ee
M
)
389
th
e
o
cc
u
r
r
en
ce
o
f
C
KD.
E
ar
ly
C
KD
d
etec
tio
n
was
p
r
esen
ted
in
[
2
6
]
b
y
c
o
m
b
in
atio
n
o
f
p
ar
allel
ca
teg
o
r
izatio
n
alg
o
r
ith
m
.
An
in
-
d
e
p
th
v
alid
a
tio
n
o
f
eGFR
f
o
r
C
KD
is
em
p
lo
y
ed
u
s
in
g
th
e
p
r
o
g
r
ess
io
n
m
ec
h
an
is
m
in
[
2
7
]
.
An
elab
o
r
atio
n
r
ev
iew
o
n
u
n
s
u
p
er
v
is
ed
lear
n
in
g
o
f
C
KD
was
in
v
esti
g
ated
in
[
2
8
]
.
A
s
y
s
tem
atic
r
ev
iew
o
n
m
o
r
tality
p
r
ed
ictio
n
am
o
n
g
k
id
n
ey
p
atien
t
was
p
r
esen
ted
in
[
2
9
]
.
Yet
an
o
th
e
r
in
tellig
en
ce
d
iag
n
o
s
is
m
ec
h
an
is
m
em
p
lo
y
in
g
DL
class
if
ier
was
p
r
o
p
o
s
ed
in
[
3
0
]
to
f
o
cu
s
o
n
th
e
p
r
ec
is
io
n
an
d
r
ec
all
asp
ec
ts
.
I
n
[
3
1
]
,
p
r
esen
ted
an
ap
p
r
o
ac
h
f
o
r
f
illi
n
g
n
u
ll
v
alu
es
in
m
i
s
s
in
g
d
ata
u
s
in
g
d
if
f
er
en
t
m
ac
h
in
e
le
ar
n
in
g
(
ML
)
ap
p
r
o
ac
h
es,
wh
er
XGBo
o
s
t
p
r
o
v
id
ed
b
etter
r
esu
lts
ac
h
ie
v
in
g
F
-
s
co
r
e
o
f
9
7
%.
J
ay
ash
r
e
e
an
d
An
ith
a
[
3
2
]
,
p
r
esen
ted
an
ap
p
r
o
ac
h
f
o
r
k
id
n
ey
d
is
ea
s
e
d
etec
tio
n
wh
er
e
v
ar
io
u
s
ML
ap
p
r
o
ac
h
es
wer
e
ap
p
lied
.
T
h
e
f
i
n
d
in
g
s
s
h
o
w
th
at
th
e
XGBo
o
s
t
p
r
o
v
i
d
ed
b
ette
r
r
esu
lts
ac
h
iev
in
g
9
8
3
3
%
ac
cu
r
ac
y
.
Mo
tiv
ate
d
b
y
ab
o
v
e
m
en
tio
n
ed
wo
r
k
s
in
liter
atu
r
e,
th
o
u
g
h
th
e
r
ev
iew
o
n
C
KD
d
etec
tio
n
ac
cu
r
ac
y
asp
ec
ts
wer
e
co
n
s
id
er
ed
,
h
o
wev
er
f
o
cu
s
o
n
th
e
tr
ain
in
g
tim
e
asp
ec
ts
wer
e
lim
ited
.
C
er
tain
r
ev
iews
d
esp
ite
m
ak
in
g
a
th
o
r
o
u
g
h
s
t
u
d
y
o
n
co
n
s
id
er
in
g
th
e
tr
ain
in
g
tim
e
f
o
r
d
is
ea
s
e
d
ete
ctio
n
,
th
e
p
r
ec
is
io
n
an
d
ac
cu
r
ac
y
asp
ec
ts
wer
e
n
o
t
m
ea
s
u
r
ed
.
T
o
ad
d
r
ess
o
n
th
ese
asp
ec
ts
C
DB
DP
-
B
G
A
was
ap
p
lied
co
n
s
id
er
in
g
clin
i
ca
l
p
ar
am
eter
s
.
E
lab
o
r
ate
d
es
cr
ip
tio
n
o
f
C
DB
DP
-
B
GA
m
eth
o
d
is
p
r
o
v
id
e
d
in
f
o
llo
win
g
s
ec
tio
n
s
.
3.
M
E
T
H
O
D
T
h
e
g
iv
e
n
m
et
h
o
d
o
lo
g
y
,
p
r
esen
ted
in
Fig
u
r
e
1
d
ep
icts
th
e
d
e
s
ig
n
wh
ich
was
u
tili
ze
d
to
ca
r
r
y
o
u
t
th
e
ex
p
er
im
en
ts
.
I
t
in
c
o
r
p
o
r
ated
d
ata
co
llectio
n
m
ad
e
f
r
o
m
s
t
r
u
ctu
r
ed
C
KD
tr
ain
in
g
an
d
u
n
s
tr
u
ctu
r
ed
T
witter
test
in
g
d
ataset,
tex
tu
al
f
ea
tu
r
e
ex
tr
ac
tio
n
,
n
u
m
e
r
ical
f
ea
tu
r
e
s
elec
tio
n
an
d
f
in
ally
,
class
if
ic
atio
n
u
s
in
g
clin
ical
p
ar
am
eter
s
r
elativ
e
to
th
e
s
y
m
p
to
m
s
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
e
y
d
is
ea
s
e
an
d
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
.
As
illu
s
tr
ated
in
Fig
u
r
e
1
,
th
e
s
tr
u
ctu
r
ed
C
KD
tr
ain
in
g
a
n
d
u
n
s
tr
u
ctu
r
ed
T
witter
test
in
g
d
atasets
wer
e
co
n
s
id
er
ed
as
in
p
u
t.
th
e
C
DB
DP
-
B
G
A
m
eth
o
d
u
n
d
er
wen
t
th
r
ee
s
tag
es:
f
ir
s
t,
tex
tu
a
l
f
ea
tu
r
e
ex
tr
ac
tio
n
was
p
er
f
o
r
m
e
d
em
p
lo
y
in
g
CD
-
Bi
-
L
STM
.
Seco
n
d
,
n
u
m
er
ica
l
f
ea
tu
r
e
s
elec
tio
n
was
d
o
n
e
u
s
in
g
B
GA
.
Fin
ally
,
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
e
ase,
b
o
th
th
e
tex
tu
al
f
ea
tu
r
e
an
d
n
u
m
er
ical
f
ea
tu
r
es
wer
e
co
m
b
in
ed
an
d
th
e
So
f
tMa
x
f
u
n
ctio
n
was
ap
p
lie
d
f
o
r
th
e
o
b
tain
ed
clin
ical
p
ar
am
eter
s
alo
n
g
with
th
e
s
y
m
p
to
m
s
to
m
ea
s
u
r
e
eGF
R
f
o
r
class
if
y
in
g
d
if
f
er
en
t
s
tag
es.
Fig
u
r
e
1
.
C
DB
DP
-
B
GA
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
e
y
d
is
ea
s
e
3
.
1
.
Da
t
a
s
et
T
h
e
s
tr
u
ctu
r
ed
tr
ain
in
g
d
ataset
u
s
ed
in
o
u
r
wo
r
k
f
o
r
p
r
ed
ic
tio
n
o
f
k
id
n
e
y
d
is
ea
s
e
at
an
e
ar
ly
s
tag
e
co
n
s
id
er
in
g
b
o
th
clin
ical
p
ar
am
eter
s
an
d
s
et
o
f
cr
itical
s
y
m
p
to
m
s
was
tak
en
f
r
o
m
h
ttp
s
://ar
ch
iv
e.
ics.u
ci.
ed
u
/d
ata
s
et/3
3
6
/ch
r
o
n
ic+
k
id
n
ey
+
d
is
ea
s
e.
C
KD
d
atase
t
was
o
b
tain
ed
o
v
er
a
y
ea
r
o
f
two
-
m
o
n
th
co
n
s
is
tin
g
o
f
4
0
0
d
if
f
er
en
t
s
am
p
le
in
s
tan
ce
s
.
Fr
o
m
th
e
o
v
e
r
all
4
0
0
d
if
f
er
en
t
s
am
p
le
in
s
tan
ce
s
,
2
5
0
d
if
f
er
en
t
s
am
p
le
in
s
tan
ce
s
wer
e
id
en
tifie
d
to
b
e
C
KD
p
atien
ts
an
d
o
n
th
e
o
th
e
r
h
an
d
,
1
5
0
d
if
f
er
en
t
s
am
p
le
in
s
tan
ce
s
wer
e
id
en
tifie
d
to
b
e
h
ea
lth
y
p
ar
ticip
a
n
ts
.
Als
o
,
ea
ch
s
am
p
le
in
s
tan
ce
co
n
s
is
ted
o
f
2
5
attr
ib
u
tes
b
ased
o
n
th
e
m
ea
s
u
r
e
d
d
ata
v
i
a
b
lo
o
d
test
.
Her
e,
th
e
f
ir
s
t
2
4
attr
ib
u
tes
wer
e
in
d
e
p
en
d
e
n
t
wh
er
ea
s
th
e
last
o
n
e
attr
ib
u
te
ws
a
d
ep
en
d
en
t
attr
ib
u
te
an
d
am
o
n
g
th
e
o
v
e
r
all
2
4
attr
ib
u
tes,
1
1
attr
ib
u
tes
ar
e
n
u
m
er
ic
wh
er
ea
s
o
th
er
r
e
m
ain
in
g
1
4
attr
i
b
u
tes
ar
e
ca
teg
o
r
ical.
T
h
e
u
n
s
tr
u
ctu
r
ed
d
ata
was
ac
q
u
ir
ed
f
r
o
m
h
ea
lth
-
n
ews
T
witter
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
387
-
3
9
8
390
d
ataset
f
r
o
m
h
ttp
s
://ar
ch
iv
e.
i
cs.u
ci.
ed
u
/
d
ataset/4
3
8
/h
ea
lth
+
n
ews+in
+twitter
.
T
h
is
h
ea
lth
n
ews
in
T
witter
d
ataset
co
n
s
is
ted
o
f
h
ea
lth
n
ews
ac
q
u
ir
ed
f
r
o
m
1
5
d
if
f
er
en
t
m
ajo
r
h
ea
lth
n
ews
ag
en
cies.
T
h
e
d
ataset
co
n
s
is
ted
o
f
5
8
,
0
0
0
in
s
tan
ce
s
.
T
h
e
s
tr
u
ctu
r
ed
C
KD
d
ataset
was
u
s
ed
f
o
r
tr
ain
in
g
an
d
u
n
s
tr
u
ctu
r
ed
h
ea
lth
-
ne
ws
d
ataset
wa
s
u
s
ed
f
o
r
test
in
g
.
B
y
em
p
lo
y
in
g
s
tr
u
ctu
r
ed
C
KD
tr
ain
in
g
d
ataset
an
d
an
u
n
s
tr
u
ctu
r
ed
h
e
alth
n
ews
test
in
g
d
ataset,
th
e
p
r
o
p
o
s
ed
C
DB
DP
-
B
GA
f
o
r
th
e
p
r
ed
icti
o
n
o
f
k
id
n
e
y
d
is
ea
s
e
m
e
th
o
d
is
d
esig
n
ed
in
th
e
f
o
llo
win
g
s
ec
tio
n
s
.
3
.
2
.
Co
nte
x
t
depend
ent
bi
-
d
irec
t
io
na
l lo
ng
s
ho
rt
-
t
er
m
mem
o
ry
-
ba
s
ed
k
ey
wo
rd
ex
t
r
a
ct
io
n
I
n
s
o
ciety
,
p
eo
p
le
s
u
f
f
er
f
r
o
m
a
v
ar
iety
o
f
d
is
ea
s
es,
in
clu
d
i
n
g
d
iab
etes
an
d
k
i
d
n
ey
d
is
ea
s
e.
Am
o
n
g
t
h
ese,
k
id
n
e
y
d
is
ea
s
e
is
co
n
s
id
er
ed
a
g
l
o
b
al
h
ea
lth
is
s
u
e.
R
is
k
an
aly
s
is
f
o
r
k
id
n
ey
d
is
ea
s
e
h
as
b
ee
n
d
is
cu
s
s
ed
u
s
in
g
s
ev
er
al
m
eth
o
d
s
.
Mo
r
e
o
v
er
,
u
n
s
tr
u
ctu
r
ed
h
ea
lth
n
e
ws
test
in
g
d
atasets
,
o
f
ten
e
x
t
r
ac
ted
f
r
o
m
T
witter
,
ty
p
ically
co
n
tain
two
m
ain
ty
p
es
o
f
in
f
o
r
m
atio
n
:
tex
tu
al
e
x
p
lan
atio
n
s
an
d
v
ar
io
u
s
p
h
y
s
ical
r
u
les.
Key
wo
r
d
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
f
r
o
m
th
ese
u
n
s
tr
u
ctu
r
e
d
d
atasets
is
cr
u
c
ial
f
o
r
im
p
r
o
v
in
g
t
h
e
q
u
ality
o
f
k
id
n
ey
d
atasets
,
en
s
u
r
in
g
th
at
DL
m
o
d
els
ca
n
ef
f
icien
tly
lear
n
p
atter
n
s
an
d
m
ak
e
ac
c
u
r
ate
p
r
ed
i
ctio
n
s
.
R
NN
[
1
]
,
with
t
h
eir
f
ee
d
b
ac
k
lo
o
p
s
,
ar
e
p
ar
ticu
lar
ly
s
u
itab
le
f
o
r
p
r
o
ce
s
s
in
g
s
eq
u
en
tial
d
ata,
s
u
ch
as
n
ews
f
r
o
m
1
5
m
ajo
r
h
ea
lth
ag
en
cies,
an
d
ca
n
b
e
tr
ain
ed
u
s
in
g
b
ac
k
-
p
r
o
p
ag
atio
n
.
Ho
w
ev
er
,
th
e
y
f
ac
e
is
s
u
es
lik
e
g
r
a
d
ien
t
p
r
o
b
lem
wh
e
n
m
o
d
elin
g
lo
n
g
in
f
o
r
m
atio
n
s
eq
u
en
ce
s
.
T
o
a
d
d
r
ess
th
ese
ch
allen
g
es,
a
m
o
d
el
ca
lled
C
D
-
Bi
-
L
STM
n
etwo
r
k
h
as
b
ee
n
d
esig
n
ed
to
p
r
o
ce
s
s
u
n
s
tr
u
ctu
r
ed
h
ea
lth
n
ews
f
r
o
m
T
witter
d
atasets
,
as
p
r
esen
ted
in
Fig
u
r
e
2
.
T
h
is
m
o
d
el
aim
s
to
e
n
h
an
ce
th
e
a
cc
u
r
ac
y
a
n
d
ef
f
icien
cy
o
f
k
id
n
ey
d
i
s
ea
s
e
r
is
k
an
aly
s
is
b
y
e
f
f
ec
tiv
ely
h
a
n
d
lin
g
an
d
ex
tr
ac
tin
g
r
elev
a
n
t in
f
o
r
m
atio
n
f
r
o
m
th
ese
u
n
s
tr
u
ctu
r
ed
d
ata
s
o
u
r
ce
s
.
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
am
o
f
C
D
-
Bi
-
L
STM
-
b
ased
f
ea
tu
r
e
ex
t
r
ac
tio
n
m
o
d
el
I
n
th
e
p
r
o
p
o
s
ed
wo
r
k
o
f
C
D
-
Bi
-
L
STM
n
etwo
r
k
(
h
id
d
e
n
s
tate)
,
th
e
T
witter
in
f
o
r
m
a
tio
n
in
th
is
h
id
d
en
s
tate
ca
n
b
e
u
p
d
ated
b
y
g
ate
s
tr
u
ctu
r
e
in
a
c
o
n
s
tan
t
m
an
n
er
v
ia
co
n
tex
t
d
ep
e
n
d
e
n
cy
.
T
h
e
p
r
o
p
o
s
ed
CD
-
Bi
-
L
STM
n
etwo
r
k
is
u
s
e
d
f
o
r
p
r
o
ce
s
s
in
g
a
s
eq
u
e
n
ce
o
f
twee
t
d
ata
o
b
tain
e
d
f
r
o
m
1
5
m
ajo
r
h
ea
lth
n
ew
ag
en
cies.
I
t
co
n
tain
s
two
L
ST
M
lay
er
s
,
o
n
e
f
o
r
p
r
o
ce
s
s
in
g
in
p
u
t
(
i.e
.
,
in
p
u
t
v
ec
to
r
)
in
th
e
f
o
r
war
d
d
ir
ec
tio
n
an
d
th
e
o
th
er
f
o
r
p
r
o
ce
s
s
in
g
twee
t
in
f
o
r
m
atio
n
(
i.e
.
,
c
o
n
te
x
t
in
f
o
r
m
atio
n
)
i
n
th
e
b
ac
k
w
ar
d
d
ir
ec
tio
n
.
T
h
e
in
tu
itio
n
b
eh
in
d
th
is
m
o
d
el
is
th
at
b
y
p
r
o
ce
s
s
in
g
d
ata
in
b
o
th
f
o
r
war
d
a
n
d
b
ac
k
war
d
d
i
r
ec
tio
n
s
v
ia
co
n
tex
t
d
ep
en
d
e
n
cy
,
t
h
e
m
o
d
el
is
p
r
o
f
icien
t
in
co
m
p
r
eh
e
n
d
in
g
th
e
co
r
r
elatio
n
b
etwe
en
s
eq
u
en
ce
s
(
i.e
.
,
k
n
o
win
g
th
e
p
r
ev
io
u
s
an
d
s
u
cc
ee
d
in
g
twee
ts
in
a
T
witter
ac
co
u
n
t)
.
W
ith
th
e
u
n
s
tr
u
ctu
r
e
d
h
ea
lth
n
ews
test
in
g
d
ataset
e
x
tr
ac
ted
u
s
in
g
T
witter
d
ataset,
th
e
s
am
p
le
in
s
tan
ce
s
co
m
p
r
is
es
o
f
h
ea
lth
n
ews
o
b
tain
ed
f
r
o
m
m
o
r
e
t
h
an
1
5
m
ajo
r
h
ea
lth
n
ews a
g
en
cies,
t
o
n
am
e
a
f
ew
b
ein
g
B
B
C
an
d
C
NN.
T
h
e
s
am
p
le
in
s
tan
ce
s
ar
e
f
o
r
m
u
lated
with
in
in
p
u
t v
ec
to
r
m
atr
ix
as (
1
)
.
=
[
1
1
1
2
…
1
2
1
2
2
…
2
…
…
…
…
1
2
…
]
(
1
)
Fro
m
(
1
)
th
e
in
p
u
t
v
ec
to
r
m
atr
ix
‘
’
is
f
o
r
m
u
lated
b
y
t
ak
in
g
in
t
o
co
n
s
id
er
atio
n
s
th
e
s
am
p
le
in
s
tan
ce
s
‘
’
f
o
r
th
e
co
r
r
esp
o
n
d
in
g
twee
ts
‘
’
o
b
tain
ed
f
r
o
m
1
5
m
ajo
r
h
ea
lth
n
ews
ag
en
cie
s
o
f
d
if
f
er
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
n
text
d
ep
en
d
e
n
t b
id
ir
ec
tio
n
a
l d
ee
p
lea
r
n
in
g
a
n
d
B
a
ye
s
ia
n
g
a
u
s
s
ia
n
a
u
to
-
en
c
o
d
er
…
(
Ja
ya
s
h
r
ee
M
)
391
s
ize
an
d
v
ar
ied
n
ews.
Un
d
er
th
e
d
ef
in
ite
r
u
les,
th
r
ee
g
ate
s
tr
u
ctu
r
es
d
ec
id
es
wh
at
th
e
c
o
r
r
esp
o
n
d
in
g
twee
t
in
f
o
r
m
atio
n
is
s
to
r
ed
,
u
p
d
ated
o
r
f
o
r
g
o
tten
in
th
e
co
r
r
esp
o
n
d
in
g
in
ter
n
al
s
tate.
T
h
e
m
ath
e
m
atica
l
f
o
r
m
u
la
f
o
r
u
p
d
atin
g
th
ese
th
r
ee
g
ate
s
tr
u
c
tu
r
es is
g
iv
en
in
(
2
)
to
(
6
)
.
=
(
[
,
−
1
]
)
(
2
)
=
(
[
,
−
1
]
+
)
(
3
)
=
(
[
,
−
1
]
+
)
(
4
)
=
.
−
1
+
.
ta
n
h
(
[
,
−
1
]
+
)
(
5
)
=
.
ta
n
h
(
)
(
6
)
Fro
m
th
e
(2
)
to
(
6
)
‘
’
,
‘
’
,
an
d
‘
’
r
ep
r
esen
ts
th
e
in
p
u
t
s
tate,
h
id
d
en
s
tate
an
d
ce
ll
s
tate
a
t
ti
m
e
in
s
tan
ce
‘
’
with
tr
ain
ab
le
weig
h
t
m
atr
ices
d
en
o
ted
b
y
‘
’
,
‘
’
,
‘
’
,
an
d
‘
’
f
o
r
g
et
g
ate,
in
p
u
t
g
ate,
o
u
tp
u
t
g
ate
an
d
ce
ll
s
tate
in
ad
d
itio
n
t
o
b
iases
f
o
r
co
r
r
e
s
p
o
n
d
in
g
g
ates
d
en
o
te
d
as
‘
’
,
‘
’
,
‘
’
,
an
d
‘
’
ac
tiv
ated
b
y
s
ig
m
o
id
f
u
n
ctio
n
‘
’
r
esp
ec
tiv
ely
.
Mo
r
eo
v
er
,
th
e
s
tr
u
ctu
r
e
o
f
C
D
-
Bi
-
L
STM
n
etwo
r
k
is
d
esig
n
ed
to
m
o
d
el
th
e
c
o
n
te
x
t
d
ep
en
d
en
cy
f
r
o
m
th
e
p
r
e
ce
d
in
g
tex
t
an
d
th
e
s
u
cc
ee
d
in
g
tex
t.
C
o
n
tex
t
-
d
ep
en
d
e
n
t
m
em
o
r
y
r
esu
lts
i
n
th
e
im
p
r
o
v
e
d
r
ec
all
wh
en
th
e
co
n
tex
t
d
u
r
in
g
s
to
r
ag
e
o
r
en
co
d
in
g
is
s
im
ilar
as
th
e
co
n
tex
t
d
u
r
in
g
r
etr
iev
al
o
r
d
ec
o
d
i
n
g
.
T
o
m
o
d
el
th
is
,
th
e
C
D
-
Bi
-
L
STM
n
etwo
r
k
em
p
lo
y
in
g
two
p
ar
allel
lay
er
s
b
o
th
in
f
o
r
war
d
an
d
b
a
ck
war
d
lay
e
r
s
,
th
e
h
id
d
e
n
u
n
it
is
f
o
r
m
u
lated
as
(
7
)
an
d
(
8
)
.
I
n
(
7
)
a
n
d
(
8
)
,
‘
⃗
⃗
⃗
⃗
’
an
d
‘
⃖
⃗
⃗
⃗
⃗
’
r
ep
r
esen
ts
th
e
o
u
tp
u
t
o
f
L
STM
in
th
e
f
o
r
war
d
lay
er
a
n
d
b
ac
k
war
d
lay
e
r
r
esp
ec
tiv
el
y
.
Fin
ally
,
th
es
e
t
w
o
o
u
t
p
u
t
s
o
f
L
ST
M
i
n
t
h
e
f
o
r
w
a
r
d
l
a
y
e
r
a
n
d
b
a
c
k
w
a
r
d
l
a
y
er
a
r
e
c
o
m
b
i
n
e
d
t
o
f
o
r
m
u
l
a
t
e
t
h
e
o
v
e
r
a
l
l
o
u
t
p
u
t
(
9
)
.
⃗
⃗
⃗
⃗
=
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
(
,
−
1
)
(
7
)
⃖
⃗
⃗
⃗
⃗
=
⃖
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
(
,
+
1
)
(
8
)
=
⃗
⃗
⃗
⃗
+
⃖
⃗
⃗
⃗
⃗
(
9
)
I
n
(
9
)
,
th
e
tex
tu
r
al
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
ar
e
ex
tr
ac
ted
ac
co
r
d
in
g
to
co
n
tex
t
d
ep
e
n
d
en
c
y
b
o
th
f
r
o
m
th
e
p
r
ec
ed
i
n
g
tex
t
a
n
d
t
h
e
s
u
cc
ee
d
in
g
tex
t.
I
n
t
h
is
m
an
n
er
,
b
y
em
p
lo
y
in
g
co
n
tex
t
d
e
p
en
d
en
cy
in
B
i
-
L
STM
ass
is
ts
in
d
escr
ib
in
g
th
e
b
asis
d
is
ea
s
e
s
y
m
p
to
m
s
wh
ich
in
t
u
r
n
aid
s
i
n
o
b
tain
in
g
u
s
ef
u
l
in
f
o
r
m
atio
n
b
eh
i
n
d
t
h
e
tex
ts
in
an
ac
cu
r
ate
m
an
n
er
.
T
h
e
Alg
o
r
ith
m
1
is
u
s
ed
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
As
g
iv
en
in
Alg
o
r
ith
m
1
,
u
s
in
g
th
e
u
n
s
tr
u
ctu
r
e
d
twee
t
d
ataset,
th
e
in
p
u
t
v
ec
to
r
is
s
u
b
je
cted
to
tex
tu
al
f
ea
tu
r
e
ex
tr
a
ctio
n
b
y
c
o
n
tex
tu
al
d
ep
en
d
e
n
cy
in
th
e
B
i
-
L
STM
n
etwo
r
k
m
o
d
el.
Alg
o
r
ith
m
1
.
C
D
-
Bi
-
L
STM
-
b
ased
tex
tu
al
f
ea
tu
r
e
e
x
tr
ac
tio
n
Input
Unstructured
dataset
‘
DS
’
,
Sa
mp
le
s
in
st
an
ce
s
‘
DSS={
1
,
2
,
…
,
}
’
,
Tw
ee
ts
‘
=
{
1
,
2
,
…
,
}
’
Output
Convergent
-
Efficient Context
-
Dependent Feature Extraction
‘
’
Step 1
Initialize
‘
N
’
,
‘
M
’
Step 2
Begin
Step 3
For
each Unstructured dataset
‘
DS
’
w
ith Samples instances
‘
DSS
’
Step 4
Formulate input vector matrix as given in (1)
Step 5
Formulate forget gate, input gate and output gate as given in (2), (3) and (4).
Step 6
Mathematically formulate cell state and hidden state as given in (5) and (6)
Step
7
Mathematically
formulate
two
parallel
layers
both
in
forward
and
backward
layers
as given in (7) and (8)
Step 8
Combine
the
two
outputs
of
LSTM
in
the
forward
layer
and
backward
l
ayer
to
generate
context
depende
nt
textual
feature
extra
ction
(i.e.,
repre
se
nt
at
io
n)
as
given in (9)
Step 9
Return textual feature extraction (i.e., representation)
‘
’
Step 10
End for
Step 11
End
3
.
3
.
B
a
y
esia
n
g
a
us
s
ia
n a
uto
enco
der
-
ba
s
ed
nu
m
er
ica
l f
ea
t
ure
s
elec
t
io
n
C
lin
ical
d
ata
o
f
ten
co
n
tain
n
u
m
er
ical
f
ea
tu
r
es
wh
er
e
s
o
m
e
v
alu
es
ar
e
h
ig
h
l
y
c
o
r
r
elate
d
w
h
ile
o
th
er
s
ar
e
n
o
t.
Usi
n
g
th
ese
v
al
u
es
d
ir
ec
tly
ca
n
n
eg
ativ
el
y
im
p
ac
t
ta
s
k
p
er
f
o
r
m
an
ce
.
Pre
v
i
o
u
s
wo
r
k
h
as
d
em
o
n
s
tr
ated
th
at
u
s
in
g
R
NN
f
o
r
k
id
n
e
y
d
is
ea
s
e
p
r
o
g
r
ess
io
n
[
2
]
ca
n
ac
h
ie
v
e
h
ig
h
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
Ho
wev
er
,
th
is
s
tu
d
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
387
-
3
9
8
392
d
id
n
o
t
ad
d
r
ess
d
im
en
s
io
n
ality
r
ed
u
ctio
n
o
r
th
e
h
an
d
lin
g
o
f
h
ig
h
ly
co
r
r
elate
d
n
u
m
er
ical
f
ea
tu
r
es.
B
y
lear
n
in
g
lo
w
-
d
im
en
s
io
n
al
r
ep
r
esen
tati
o
n
s
o
f
h
ig
h
-
d
im
e
n
s
io
n
al
d
at
a,
f
ea
tu
r
e
s
elec
tio
n
ca
n
r
etai
n
u
s
ef
u
l
n
u
m
e
r
ical
f
ea
tu
r
es
f
o
r
p
r
ed
ictin
g
k
i
d
n
ey
d
is
ea
s
e.
Yet,
s
elec
tin
g
u
s
ef
u
l
n
u
m
e
r
ical
f
ea
tu
r
es
f
r
o
m
h
ig
h
-
d
im
en
s
io
n
al
d
ata
r
em
ain
s
a
ch
allen
g
in
g
task
.
T
o
ad
d
r
ess
th
is
is
s
u
e,
we
em
p
lo
y
B
GA
in
th
is
wo
r
k
.
T
h
e
B
ay
esian
g
au
s
s
ian
f
u
n
ctio
n
is
in
tr
o
d
u
ce
d
in
a
s
p
e
cialize
d
h
id
d
e
n
lay
er
,
en
h
an
ci
n
g
p
r
ec
is
io
n
in
s
elec
tin
g
n
o
n
-
r
ed
u
n
d
an
t
f
ea
t
u
r
es.
T
h
er
ef
o
r
e,
we
u
s
e
th
is
B
GA
-
b
ased
n
u
m
e
r
ical
f
ea
tu
r
e
s
ele
ctio
n
m
o
d
el
t
o
id
en
tif
y
n
u
m
e
r
ical
f
ea
tu
r
es
with
h
ig
h
ly
co
r
r
elate
d
v
al
u
es.
Fig
u
r
e
3
illu
s
tr
ates
th
e
s
tr
u
ctu
r
e
o
f
th
e
B
GA
-
b
ased
n
u
m
e
r
ica
l
f
ea
tu
r
e
s
elec
tio
n
m
o
d
el.
Fig
u
r
e
3
.
Stru
ctu
r
e
o
f
B
GA
-
b
ased
n
u
m
er
ical
f
ea
tu
r
e
s
elec
tio
n
m
o
d
el
As
illu
s
tr
ated
in
th
e
Fig
u
r
e
3
,
an
au
to
en
co
d
e
r
co
m
p
r
is
es
o
f
two
p
ar
ts
,
an
en
co
d
er
f
u
n
ctio
n
‘
(
)
’
an
d
d
ec
o
d
er
f
u
n
ctio
n
‘
(
)
’
r
esp
ec
tiv
ely
,
wh
er
e
‘
’
is
th
e
in
p
u
t
v
ec
to
r
th
at
r
ep
r
esen
ts
th
e
s
et
o
f
f
ea
tu
r
es
an
d
‘
’
d
en
o
tes
th
e
s
et
o
f
r
ed
u
ce
d
f
e
atu
r
es.
I
n
ad
d
itio
n
,
an
in
p
u
t
lay
er
wh
er
e
th
e
in
p
u
t
v
ec
t
o
r
‘
’
f
o
r
m
s
as
th
e
in
p
u
t
an
d
i
n
th
e
h
id
d
en
la
y
er
(
i.e
.
,
two
h
i
d
d
en
lay
e
r
s
em
p
lo
y
ed
in
o
u
r
wo
r
k
)
th
e
p
r
o
ce
s
s
o
f
en
co
d
in
g
an
d
d
ec
o
d
in
g
is
p
er
f
o
r
m
e
d
to
g
e
n
er
ate
r
ed
u
ce
d
f
ea
tu
r
es
s
et
(
i.e
.
,
r
ed
u
ce
d
f
e
atu
r
es
s
elec
ted
)
.
Fin
ally
,
in
th
e
d
ec
o
d
er
s
id
e
r
ec
o
n
s
tr
u
ctio
n
is
p
er
f
o
r
m
e
d
with
m
in
im
al
r
ec
o
n
s
tr
u
ctio
n
lo
s
s
.
T
o
s
tar
t
with
th
e
au
to
en
co
d
er
is
ev
alu
ated
b
y
h
o
w
well
th
e
d
ec
o
d
er
r
ec
o
n
s
tr
u
cts th
e
d
ata
f
r
o
m
en
co
d
e
r
b
y
m
ea
n
s
o
f
a
lo
s
s
f
u
n
ctio
n
u
s
in
g
(
1
0
)
.
=
a
r
g
min
,
|
−
(
(
(
)
)
)
|
2
(
1
0
)
Fro
m
(
1
0
)
,
in
itially
th
e
r
ec
o
n
s
tr
u
ctio
n
lo
s
s
f
u
n
ctio
n
‘
’
,
is
m
o
d
eled
b
ased
o
n
‘
’
b
iases
o
f
en
co
d
er
as
well
as
d
ec
o
d
er
a
n
d
th
e
weig
h
ts
‘
’
r
esp
ec
tiv
el
y
f
o
r
ea
c
h
twee
t
in
t
h
e
c
o
r
r
e
s
p
o
n
d
in
g
T
witter
ac
co
u
n
t.
Au
to
e
n
co
d
e
r
in
o
u
r
wo
r
k
m
ap
s
th
e
n
u
m
er
ical
v
alu
es
v
ec
to
r
‘
’
in
to
a
h
i
d
d
en
r
e
p
r
esen
tatio
n
b
y
m
ea
n
s
o
f
an
en
co
d
e
r
f
u
n
ctio
n
u
s
in
g
(
1
1
)
.
Fo
llo
wed
b
y
wh
ic
h
th
e
r
ec
o
n
s
tr
u
ctio
n
p
er
f
o
r
m
e
d
b
y
th
e
d
ec
o
d
er
is
m
ath
em
atica
lly
f
o
r
m
u
lated
u
s
in
g
(
1
2
)
.
I
n
(
1
1
)
an
d
(
1
2
)
,
‘
ℎ
’
d
en
o
tes
th
e
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
wh
ic
h
s
elec
ts
th
e
m
o
s
t
n
o
n
-
r
ed
u
n
d
an
t
n
u
m
er
ical
f
ea
tu
r
es.
T
h
e
ch
alle
n
g
e
n
o
w
r
em
ain
s
in
ascer
tain
in
g
th
e
o
p
tim
al
‘
=
(
,
)
’
,
h
e
n
ce
,
B
ay
esian
g
au
s
s
ian
f
u
n
cti
o
n
is
u
s
ed
to
m
in
im
ize
r
ec
o
n
s
tr
u
ctio
n
lo
s
s
‘
’
u
s
in
g
(
1
3
)
.
ℎ
=
ℎ
(
)
(
)
ℎ
(
(
)
.
+
1
)
(
1
1
)
=
ℎ
(
)
(
)
ℎ
(
(
)
.
ℎ
(
)
(
)
)
(
1
2
)
(
|
Θ
)
=
1
2
e
xp
[
−
1
2
∑
(
−
(
−
′
)
)
=
1
]
(
1
3
)
I
n
(
1
3
)
,
th
e
p
r
o
b
a
b
ilit
y
o
f
m
i
n
im
izin
g
r
ec
o
n
s
tr
u
ctio
n
lo
s
s
‘
’
is
ev
alu
ated
b
y
m
ea
n
s
o
f
o
u
t
p
u
t
o
f
twee
ts
f
r
o
m
s
p
ec
if
ied
T
witter
ac
co
u
n
t
‘
(
−
′
)
’
f
o
r
‘
’
in
p
u
t
v
ec
to
r
f
ea
tu
r
es
r
ep
r
esen
te
d
b
y
‘
’
s
am
p
le
in
s
tan
ce
s
.
Fin
ally
,
we
o
b
tain
a
f
in
e
-
tu
n
ed
r
ep
r
esen
ta
tio
n
‘
ℎ
(
)
(
)
’
o
f
d
is
cr
ete
n
u
m
er
ical
v
alu
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
n
text
d
ep
en
d
e
n
t b
id
ir
ec
tio
n
a
l d
ee
p
lea
r
n
in
g
a
n
d
B
a
ye
s
ia
n
g
a
u
s
s
ia
n
a
u
to
-
en
c
o
d
er
…
(
Ja
ya
s
h
r
ee
M
)
393
o
r
r
ed
u
ce
d
n
u
m
er
ical
f
ea
tu
r
e
s
s
elec
tio
n
with
m
in
im
al
r
ec
o
n
s
tr
u
ctio
n
lo
s
s
.
T
h
e
Alg
o
r
it
h
m
2
is
u
s
ed
f
o
r
im
p
r
o
v
in
g
th
e
p
r
ec
is
io
n
an
d
a
cc
u
r
ac
y
r
ate
o
f
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e,
also
,
a
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
em
p
lo
y
in
g
B
GA
is
u
s
ed
.
Alg
o
r
ith
m
2
.
B
GA
-
b
ased
n
u
m
er
ical
f
ea
tu
r
e
s
elec
tio
n
Input
Unstructured
dataset
‘
DS
’
,
Sa
mp
le
s
in
st
an
ce
s
‘
=
{
1
,
2
,
…
,
}
’
,
Tw
ee
ts
‘
=
{
1
,
2
,
…
,
}
’
Output
Reconstruction Loss Minimized Reduced Features Selected
Step 1
Initialize
‘
N
’
,
‘
M
’
,
te
xt
ua
l
fe
at
ur
e
ex
tr
ac
ti
on
(i
.e
.,
re
pr
es
en
ta
ti
on
)
re
su
lt
s
‘
’
Step 2
Begin
Step 3
For
ea
ch
Un
st
ru
ct
ur
ed
da
t
as
et
‘
DS
’
wi
th
Sa
mp
le
s
in
st
an
ce
s
‘
DSS
’
an
d
te
xt
ua
l
feature
extraction (i.e., representation) results
‘
’
Step 4
//Input layer
Define number of input nodes i.e., from the input vector matrix
Step 5
//Hidden layer 1
–
encoder
Formulate reconstruction loss function as given in (10)
Step 6
Formulate encoder function as given in (11)
Step 7
//Hidden layer 2
–
decoder
Formulate decoder function as given in (12)
Step 8
Determine optimal
‘
θ
’
as given in (13)
Step 9
//Output layer
Return features selected
‘
’
(i.e., reduced feature
s)
Step 10
End for
Step 11
End
3
.
4
.
So
f
t
M
ax
a
c
t
iv
a
t
ed
predict
io
n o
f
k
idn
ey
dis
ea
s
e
Fin
ally
,
in
th
is
s
ec
t
io
n
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
at
an
ea
r
ly
s
tag
e
b
y
m
ea
n
s
o
f
clin
ical
p
ar
am
eter
s
with
s
y
m
p
to
m
s
b
ased
o
n
eG
FR
u
s
in
g
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
is
d
esig
n
ed
.
T
o
s
tar
t
with
th
e
tex
t
u
al
f
ea
tu
r
e
ex
tr
ac
tio
n
(
i.e
.
,
r
e
p
r
es
en
tatio
n
)
r
esu
lts
‘
’
an
d
n
u
m
er
ical
f
ea
tu
r
es
s
elec
ted
‘
’
(
i.e
.
,
r
ed
u
ce
d
f
ea
tu
r
es)
is
co
m
b
in
e
d
an
d
m
at
h
em
atica
lly
r
ep
r
esen
te
d
u
s
in
g
(
1
4
)
.
ℎ
=
[
]
(
1
4
)
Fro
m
(
1
4
)
,
u
s
in
g
R
eL
U,
th
e
co
m
b
in
ed
r
esu
lts
is
o
b
tain
ed
f
o
r
f
u
r
th
er
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e.
Fin
ally
,
em
p
lo
y
i
n
g
th
e
So
f
t
Ma
x
ac
tiv
atio
n
f
u
n
ctio
n
alo
n
g
with
th
e
clin
ical
p
ar
a
m
e
ter
s
an
d
with
th
e
s
y
m
p
to
m
s
ar
r
iv
ed
b
a
s
ed
o
n
th
e
th
r
ee
d
is
tin
ct
f
ea
tu
r
es,
i.e
.
,
ag
e,
s
ex
an
d
cr
ea
tin
in
e,
th
e
eq
u
atio
n
s
f
o
r
o
b
tain
in
g
f
iv
e
s
tag
es b
ased
o
n
th
e
eGFR
is
m
ath
em
atica
lly
f
o
r
m
u
lated
(
1
5
)
.
Fro
m
(
1
5
)
,
b
y
u
s
in
g
n
u
m
er
ical
f
ea
tu
r
es a
n
d
tex
tu
r
al
f
ea
tu
r
e
s
y
m
p
to
m
s
,
r
e
s
u
lts
alo
n
g
with
th
e
cli
n
ical
p
ar
am
eter
v
alu
es
o
b
tain
ed
,
e
GFR
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
at
an
ea
r
ly
s
ta
g
e
ar
e
s
aid
to
b
e
m
ad
e
b
o
th
p
r
ec
is
ely
an
d
ac
cu
r
ately
.
T
h
e
Alg
o
r
ith
m
3
is
u
s
ed
f
o
r
p
r
e
d
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
at
an
ea
r
ly
s
tag
e,
wh
er
e
th
e
tex
tu
al
f
ea
tu
r
es
an
d
n
u
m
er
ical
f
ea
tu
r
es
ar
e
co
m
b
in
ed
f
o
r
class
if
icatio
n
.
(
)
=
∑
=
1
,
(
=
1
,
2
,
.
.
,
)
(
1
5
)
Alg
o
r
ith
m
3
.
So
f
t
M
ax
ac
tiv
ate
d
p
r
ed
ictio
n
f
o
r
k
id
n
ey
d
is
ea
s
e
Input
Unstructured dataset
‘
DS
’
, Samples instances
‘
=
{
1
,
2
,
…
,
}
’
, Tweets
‘
=
{
1
,
2
,
…
,
}
’
Output
Robust Quantification
Step 1
Initialize
‘
N
’
,
‘
M
’
, textual feature extraction (i.e., representation) results
‘
’
, numerical features selected
‘
’
(i.e., reduced features)
Step 2
Begin
Step 3
For
each Unstructured da
taset
‘
DS
’
with Samples instances
‘
DSS
’
, textual feature
extraction (i.e., representation) results
‘
’
and numerical features selected
‘
’
Step 4
Formulate rectifier activation function by combining the textual feature
extraction and numeric
al features selected results as given in (13)
Step 5
Formulate SoftMax activation function along with the clinical parameters and
with the symptoms as given in (14)
Step 6
For female with
‘
creatinine <62 μmol/L
’
, eGFR (mL/min/1.73m
2
) =
‘
144*(Cr/61.6)^(
-
0.329)* (0.993)^Age
’
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
387
-
3
9
8
394
Step 7
For female with
‘
creatinine >62 μmol/L
’
, eGFR (mL/min/1.73m
2
) =
‘
144
∗
(
61
.
6
)
−
1
.
2
0
9
∗
(
0
.
9
93
)
’
Formulate decoder function as given in (12)
Step 8
For female with
‘
creatinine <80 μmol/L
’
, eGFR
(mL/min/1.73m
2
) =
‘
144
∗
(
79
.
2
)
−
0
.
411
∗
(
0
.
9
93
)
’
Step 9
For female with
‘
creatinine >80 μmol/L
’
, eGFR (mL/min/1.73m
2
) =
‘
144
∗
(
79
.
2
)
−
1
.
209
∗
(
0
.
9
93
)
’
Step 10
If
‘
eGFR≥90
’
Step 11
Then
patient is in Stage 1 (i.e., kidney damaged with normal)
Step
12
End if
Step 13
If
‘
eGFR is between 60 and 89
’
Step 14
Then
patient is in Stage 2 (i.e., kidney damaged with mildly decreased)
Step 15
End if
Step 16
If
‘
eGFR is between 30 and 59
’
Step 17
Then
patient is in Stage 3 (i.e., moderately decreased)
Step 18
End if
Step 19
If
‘
eGFR is between 15 and 29
’
Step 20
Then
patient is in Stage 4 (i.e., severely decreased)
Step 21
End if
Step 22
If
‘
eGFR <15
’
Step 23
Then
patient is in Stage 5 (i.e., kidney failure)
Step 24
End if
Step 25
End for
Step
26
End
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Fo
r
th
e
ex
p
e
r
im
en
tatio
n
o
f
C
DB
DP
-
B
G
A,
ex
p
er
im
en
tati
o
n
was
co
n
d
u
cted
in
a
n
I
n
te
l
C
o
r
e
i5
-
6
2
0
0
U
C
PU
@
2
.
3
0
GHz
4
co
r
es
with
4
Gig
ab
y
tes
o
f
DDR4
R
AM
.
Als
o
,
th
e
ex
is
tin
g
d
ee
p
-
en
s
em
b
le
ap
p
r
o
ac
h
[
1
]
an
d
R
NN
[
2
]
wer
e
also
ex
p
er
im
e
n
ted
o
n
t
h
e
s
am
e
p
latf
o
r
m
.
All
th
e
co
d
es
wer
e
wr
itten
in
Py
th
o
n
.
T
h
e
s
tr
u
ctu
r
ed
C
KD
d
ataset
an
d
u
n
s
tr
u
ctu
r
e
d
h
ea
lt
h
-
n
ews
T
witter
d
ataset
wer
e
u
s
ed
f
o
r
ev
alu
ati
o
n
.
E
x
p
er
im
en
tal
e
v
alu
atio
n
s
wer
e
co
n
d
u
cte
d
co
n
s
id
er
i
n
g
f
i
v
e
p
er
f
o
r
m
an
ce
m
etr
ics,
p
r
ec
is
io
n
,
r
ec
all,
F
-
m
ea
s
u
r
e,
ac
cu
r
ac
y
an
d
tr
ain
in
g
tim
e.
T
o
en
s
u
r
e
f
air
co
m
p
ar
is
o
n
s
s
am
e
s
tr
u
ctu
r
ed
an
d
u
n
s
tr
u
ctu
r
e
d
d
ataset
was
ap
p
lied
to
th
e
th
r
ee
m
eth
o
d
s
,
C
DB
DP
-
B
GA
(
with
an
d
with
o
u
t
eG
FR
)
,
[
1
]
,
[
2
]
an
d
ev
alu
ated
f
o
r
an
a
v
er
ag
e
o
f
1
0
s
im
u
latio
n
r
u
n
s
.
4
.
1
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
o
f
t
ra
ini
ng
t
im
e
Tra
in
in
g
tim
e
o
r
tim
e
co
n
s
u
m
ed
in
tr
ain
in
g
th
e
s
am
p
les
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
with
b
o
th
clin
ical
p
ar
am
eter
s
an
d
s
y
m
p
to
m
s
wer
e
ev
alu
ate
d
u
s
in
g
(
1
6
)
.
I
n
(
1
6
)
th
e
tr
ain
in
g
tim
e
‘
’
is
m
ea
s
u
r
ed
b
ased
o
n
th
e
s
am
p
les
‘
’
an
d
t
h
e
tim
e
co
n
s
u
m
e
d
in
p
er
f
o
r
m
i
n
g
o
v
er
all
p
r
e
d
ictio
n
o
f
k
id
n
e
y
d
is
ea
s
e
is
‘
(
)
’
.
I
t is m
ea
s
u
r
ed
in
te
r
m
s
o
f
m
illi
s
ec
o
n
d
s
(
m
s
)
.
=
∑
=
1
∗
(
)
(
1
6
)
T
ab
le
1
lis
ts
th
e
tab
u
latio
n
r
es
u
lts
o
f
tr
ain
i
n
g
tim
e
b
y
s
u
b
s
titu
tin
g
th
e
v
alu
es
in
(
1
6
)
f
o
r
tw
o
ex
is
tin
g
m
eth
o
d
s
,
d
ee
p
e
n
s
em
b
le
[
1
]
R
NN
[
2
]
a
n
d
p
r
o
p
o
s
ed
C
DB
DP
-
B
GA.
was
r
ed
u
ce
d
u
s
in
g
th
e
p
r
o
p
o
s
ed
C
DB
DP
-
B
G
A
m
eth
o
d
b
y
2
9
% c
o
m
p
a
r
ed
to
[
1
]
an
d
3
8
% c
o
m
p
ar
ed
to
[
2
]
.
T
ab
le
1
.
T
a
b
u
latio
n
o
f
tr
ain
in
g
tim
e
u
s
in
g
p
r
o
p
o
s
ed
C
DB
D
P
-
B
GA
m
eth
o
d
,
d
ee
p
e
n
s
em
b
l
e
[
1
]
a
n
d
R
NN
[
2
]
S
a
mp
l
e
s
Tr
a
i
n
i
n
g
t
i
me
(
ms)
C
D
B
D
P
-
B
G
A
D
e
e
p
e
n
sem
b
l
e
R
N
N
5
0
0
1
2
5
1
6
5
2
4
0
1
,
0
0
0
1
4
5
2
0
0
2
5
5
1
,
5
0
0
1
5
5
2
1
5
2
7
0
2
,
0
0
0
1
6
8
2
4
5
2
8
5
2
,
5
0
0
1
8
5
2
8
0
3
1
5
3
,
0
0
0
2
0
5
3
1
5
3
3
0
3
,
5
0
0
2
2
5
3
3
8
3
4
5
4
,
0
0
0
2
4
0
3
5
5
3
7
5
4
,
5
0
0
2
8
5
3
8
0
3
9
0
5
,
0
0
0
3
1
5
4
0
5
4
1
5
5
0
0
1
2
5
1
6
5
2
4
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:
2502
-
4
7
5
2
C
o
n
text
d
ep
en
d
e
n
t b
id
ir
ec
tio
n
a
l d
ee
p
lea
r
n
in
g
a
n
d
B
a
ye
s
ia
n
g
a
u
s
s
ia
n
a
u
to
-
en
c
o
d
er
…
(
Ja
ya
s
h
r
ee
M
)
395
4
.
2
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
o
f
prec
is
io
n,
re
ca
ll,
a
cc
ura
cy
a
nd
F
-
m
ea
s
ure
T
h
e
p
er
f
o
r
m
an
ce
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
an
d
r
ec
all
wer
e
ap
p
lied
to
th
e
u
n
s
tr
u
ctu
r
ed
s
am
p
le
in
s
tan
ce
s
f
r
o
m
a
s
am
p
le
s
p
ac
e
.
Pre
cisi
o
n
an
d
r
ec
all
ar
e
f
o
r
m
u
lated
u
s
in
g
(
1
7
)
an
d
(
1
8
)
r
es
p
ec
tiv
ely
.
Fro
m
th
e
(
1
7
)
a
n
d
(
1
8
)
p
r
ec
is
io
n
‘
’
an
d
r
ec
all
‘
’
ar
e
ev
alu
ated
b
ased
o
n
th
e
tr
u
e
p
o
s
itiv
e
r
ate
(
i.
e.
,
d
is
ea
s
ed
p
atien
ts
id
en
tifie
d
as
d
is
ea
s
ed
)
‘
’
,
f
alse
p
o
s
itiv
e
r
ate
(
i.e
.
,
d
i
s
ea
s
ed
p
atien
ts
id
en
tifie
d
as
n
o
r
m
al
s
am
p
les)
‘
’
an
d
th
e
f
alse
n
eg
ativ
e
r
ate
(
i.e
.
,
n
o
r
m
al
s
am
p
les
id
en
tifie
d
as
d
is
ea
s
e
d
p
atien
ts
)
‘
’
r
esp
ec
tiv
ely
.
T
h
e
ef
f
icien
cy
o
f
class
if
ier
was
m
ea
s
u
r
ed
em
p
l
o
y
in
g
th
e
F
-
m
ea
s
u
r
e.
T
h
e
F
-
m
ea
s
u
r
e
was
m
ath
em
atica
lly
f
o
r
m
u
lated
an
d
is
p
r
esen
ted
u
s
in
g
(
1
9
)
.
I
n
(
1
9
)
F
-
m
ea
s
u
r
e
‘
−
’
,
is
ev
alu
ated
b
y
co
n
s
id
er
in
g
th
e
p
r
ec
is
io
n
‘
’
a
n
d
r
ec
all
‘
’
r
ate.
Fin
ally
,
ac
c
u
r
ac
y
o
r
p
r
ed
ictio
n
k
id
n
ey
d
is
ea
s
e
ac
cu
r
ac
y
i
s
ev
alu
ated
u
s
in
g
(
2
0
)
.
I
n
(
2
0
)
,
ac
cu
r
ac
y
‘
’
is
m
ea
s
u
r
ed
u
s
in
g
th
e
tr
u
e
p
o
s
itiv
e
r
ate
(
i.e
.
,
i.
e.
,
d
is
ea
s
ed
p
atien
ts
id
en
tifie
d
as d
is
ea
s
ed
)
‘
’
,
‘
’
in
d
icate
s
f
alse p
o
s
itiv
e
(
i.e
.
,
d
is
ea
s
ed
p
atien
ts
id
en
tifie
d
as n
o
r
m
al
s
am
p
les)
an
d
th
e
f
alse
n
eg
ativ
e
r
ate
(
i.e
.
,
n
o
r
m
al
s
am
p
les
id
en
tifie
d
as
d
is
ea
s
ed
p
atien
ts
)
‘
’
an
d
tr
u
e
n
eg
ativ
e
r
at
e
(
i.e
.
,
d
is
ea
s
ed
p
atien
ts
id
en
tifi
ed
as n
o
r
m
al
s
am
p
les)
‘
’
r
esp
ec
tiv
ely
.
=
+
∗
100
(
1
7
)
=
+
∗
100
(
1
8
)
−
=
2
∗
∗
+
(
1
9
)
=
+
+
+
+
(
2
0
)
Fig
u
r
e
4
g
iv
e
n
ab
o
v
e
s
h
o
w
s
th
e
g
r
ap
h
ical
r
ep
r
esen
tatio
n
s
o
f
p
r
ec
is
io
n
,
r
ec
all,
ac
c
u
r
ac
y
an
d
F
-
m
ea
s
u
r
e
with
eGFR
b
y
s
u
b
s
titu
tin
g
th
e
v
alu
es
i
n
(
1
7
)
to
(
2
0
)
.
Fro
m
th
e
Fig
u
r
e
4
it
is
in
f
er
r
ed
th
at
t
h
e
f
o
u
r
-
p
er
f
o
r
m
an
ce
m
etr
ics,
p
r
ec
is
io
n
,
r
ec
all,
ac
cu
r
ac
y
a
n
d
F
-
m
ea
s
u
r
e
with
eGFR
u
s
in
g
th
e
p
r
o
p
o
s
ed
C
DB
DP
-
B
GA
m
eth
o
d
is
f
o
u
n
d
to
b
e
c
o
m
p
a
r
ativ
ely
b
etter
th
an
[
1
]
a
n
d
[
2
]
.
Als
o
,
with
5
0
0
s
am
p
les
p
r
o
v
id
ed
as
in
p
u
t,
th
e
tr
u
e
p
o
s
itiv
e
r
ate
u
s
in
g
th
e
th
r
ee
m
eth
o
d
s
was
o
b
s
er
v
ed
t
o
b
e
4
8
5
,
4
7
0
,
an
d
4
5
5
.
I
n
a
s
im
ilar
m
an
n
e
r
,
th
e
f
alse
p
o
s
itiv
e
r
ate
u
s
in
g
th
e
th
r
ee
m
eth
o
d
s
with
eGFR
was
f
o
u
n
d
to
b
e
1
5
,
3
0
,
an
d
4
5
.
As
a
r
esu
lt
th
e
o
v
er
all
p
r
ec
is
io
n
with
eGFR
was
f
o
u
n
d
to
b
e
9
7
%,
9
4
%
,
an
d
9
1
%.
I
n
a
s
im
ilar
m
an
n
e
r
,
th
e
f
alse
n
eg
ativ
e
r
ate
u
s
in
g
th
e
th
r
ee
m
eth
o
d
s
was
f
o
u
n
d
t
o
b
e
5
0
,
6
5
,
an
d
1
0
0
,
t
h
er
ef
o
r
e
h
y
p
o
t
h
esizin
g
th
e
r
ec
all
r
ate
to
b
e
9
7
%,
8
7
.
5
%
,
an
d
8
1
.
9
8
%
r
esp
ec
tiv
ely
.
Fin
ally
,
th
e
ac
cu
r
ac
y
an
d
F
-
m
ea
s
u
r
e
with
eGFR
was
f
o
u
n
d
t
o
b
e
9
7
.
4
%,
9
6
.
8
%,
9
6
.
4
%
a
n
d
9
7
%,
9
0
.
8
2
%,
8
6
.
2
5
%
r
esp
ec
tiv
ely
.
Fig
u
r
e
5
s
h
o
ws
p
icto
r
ial
r
e
p
r
esen
ta
tio
n
s
o
f
p
r
ec
is
io
n
,
r
ec
all,
ac
cu
r
ac
y
an
d
F
-
m
ea
s
u
r
e
with
o
u
t e
GFR
b
y
s
u
b
s
titu
tin
g
th
e
v
alu
es in
(
1
7
)
to
(
2
0
)
.
I
n
f
ig
u
r
e
,
f
o
u
r
p
ar
a
m
eter
s
o
f
C
DB
DP
-
B
G
A
m
eth
o
d
ar
e
b
et
ter
with
o
u
t
eGFR
b
etter
th
a
n
[
1
]
a
n
d
[
2
]
.
I
n
a
s
im
ilar
m
an
n
er
with
o
u
t
eGFR
,
th
e
p
r
ec
is
io
n
u
s
in
g
th
e
th
r
ee
m
eth
o
d
s
wer
e
o
b
s
er
v
e
d
to
b
e
9
4
%,
9
2
%,
9
0
%,
th
e
r
ec
all
r
ate
u
s
in
g
th
e
p
r
o
p
o
s
ed
C
DB
DP
-
B
G
A
m
eth
o
d
an
d
e
x
is
tin
g
m
eth
o
d
s
[
1
]
a
n
d
[
2
]
wer
e
f
o
u
n
d
to
b
e
8
2
.
4
5
%,
7
9
.
3
1
%
,
an
d
7
7
.
5
8
%.
Fin
ally
,
th
e
p
r
e
d
ictio
n
k
i
d
n
ey
d
is
ea
s
e
ac
cu
r
ac
y
with
o
u
t
eGF
R
f
o
r
th
e
th
r
ee
m
eth
o
d
s
wer
e
f
o
u
n
d
to
b
e
9
8
.
7
%,
9
8
%,
9
7
.
1
% with
an
F
-
m
ea
s
u
r
e
o
f
8
7
.
8
4
%,
8
5
.
1
8
%
,
an
d
8
3
.
3
2
%.
Fig
u
r
e
4
.
Gr
a
p
h
ical
r
ep
r
esen
tatio
n
s
o
f
p
r
ec
is
io
n
,
r
ec
all,
ac
cu
r
ac
y
a
n
d
F
-
m
ea
s
u
r
e
with
eGFR
Fig
u
r
e
5
.
Gr
a
p
h
ical
r
ep
r
esen
tatio
n
s
o
f
p
r
ec
is
io
n
,
r
ec
all,
ac
cu
r
ac
y
a
n
d
F
-
m
ea
s
u
r
e
with
o
u
t e
GFR
0
20
40
60
80
1
0
0
A
c
c
u
r
a
c
y
Pr
e
c
i
si
o
n
R
e
c
a
l
l
F-
M
e
a
su
r
e
(
%
)
Pe
r
f
o
r
m
a
n
c
e
M
e
t
h
o
d
s
P
e
r
f
or
m
anc
e
Ev
alu
at
i
on
w
i
t
h
out
e
GF
R
RNN
D
e
e
p
E
n
se
mbl
e
CD
B
DP-
B
GA
0
20
40
60
80
1
0
0
Acc
uracy
Pr
e
c
i
si
o
n
R
e
c
a
l
l
F-
M
e
a
su
r
e
(
%
)
Pe
r
f
o
r
m
a
n
c
e
M
e
t
r
i
c
s
P
e
r
f
or
m
an
c
e
E
v
al
u
at
i
on
w
i
t
h
e
G
F
R
RNN
D
e
e
p
E
n
se
mbl
e
C
D
B
D
P-
B
GA
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
9
,
No
.
1
,
Ju
ly
20
25
:
387
-
3
9
8
396
Fro
m
th
e
ab
o
v
e
Fig
u
r
e
4
an
d
Fig
u
r
e
5
two
in
f
er
e
n
ce
s
ar
e
m
ad
e.
First,
f
o
u
r
p
er
f
o
r
m
a
n
ce
e
v
alu
atio
n
m
etr
ics,
p
r
ec
is
io
n
,
r
ec
all,
F
-
m
ea
s
u
r
e
an
d
ac
cu
r
ac
y
with
eGF
R
ar
e
f
o
u
n
d
to
b
e
b
etter
th
an
with
o
u
t
ap
p
licatio
n
o
f
eGFR
.
Seco
n
d
,
f
o
u
r
p
er
f
o
r
m
an
ce
ev
alu
atio
n
m
etr
ics,
p
r
ec
is
io
n
,
r
ec
all,
f
-
m
ea
s
u
r
e
an
d
ac
cu
r
ac
y
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
ar
e
f
o
u
n
d
to
b
e
co
m
p
ar
ativ
ely
b
etter
u
s
in
g
p
r
o
p
o
s
ed
C
DB
DP
-
B
GA
m
eth
o
d
th
an
[
1
]
an
d
[
2
]
.
T
h
e
r
ea
s
o
n
b
eh
in
d
th
e
im
p
r
o
v
em
en
t
was
d
u
e
t
o
th
e
ap
p
licatio
n
o
f
id
en
tif
y
in
g
th
e
tex
tu
al
f
ea
tu
r
e
r
ep
r
esen
tatio
n
an
d
n
u
m
er
ical
f
ea
tu
r
e
s
elec
tio
n
s
ep
ar
ately
u
s
in
g
co
n
tex
tu
al
d
ep
en
d
en
t
B
i
-
L
STM
an
d
B
GA
.
Als
o
,
b
o
th
th
e
tex
tu
al
f
ea
tu
r
e
r
ep
r
esen
tatio
n
a
n
d
n
u
m
e
r
ical
f
ea
tu
r
e
s
elec
ted
r
esu
lts
wer
e
ap
p
lied
f
in
ally
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e.
I
n
th
e
class
if
icatio
n
s
tag
e,
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
alo
n
g
with
eGFR
an
d
th
e
clin
ical
p
ar
am
eter
s
(
i.e
.
,
t
h
e
n
u
m
er
ical
f
ea
tu
r
es
s
elec
ted
)
wer
e
em
p
lo
y
e
d
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e.
T
h
is
in
tu
r
n
f
in
ally
r
esu
lte
d
in
th
e
im
p
r
o
v
em
en
t
o
f
p
r
ec
is
io
n
,
r
ec
all,
F
-
m
ea
s
u
r
e
an
d
ac
c
u
r
a
cy
in
a
s
ig
n
if
ican
t
m
an
n
er
.
5.
CO
NCLU
SI
O
N
Pre
d
ictio
n
o
f
k
id
n
e
y
d
is
ea
s
e
with
b
o
th
clin
ical
p
ar
am
eter
s
an
d
s
y
m
p
to
m
s
p
a
v
e
way
f
o
r
ef
f
icien
cy
d
iag
n
o
s
is
.
Hen
ce
,
d
esira
b
le
wo
r
k
is
c
o
n
s
id
er
ed
th
at
m
ay
ass
is
t
in
an
aly
zin
g
th
e
p
r
ed
ictio
n
o
f
k
i
d
n
ey
illn
ess
,
th
er
ef
o
r
e
r
ed
u
cin
g
t
h
e
m
o
r
tality
to
a
g
r
ea
ter
e
x
te
n
t.
Pas
t
r
esear
ch
wo
r
k
s
u
n
d
er
s
co
r
e
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
em
p
lo
y
in
g
d
if
f
e
r
en
t
c
o
n
v
en
tio
n
al
an
d
n
o
n
-
c
o
n
v
e
n
tio
n
al
m
eth
o
d
s
,
to
n
am
e
a
f
ew
b
ein
g
,
ML
,
DL
,
an
d
s
o
o
n
.
I
n
th
is
wo
r
k
,
a
C
DB
D
P
-
B
GA
f
o
r
p
r
ed
ictio
n
o
f
k
id
n
ey
d
is
ea
s
e
i
s
p
r
o
p
o
s
ed
.
T
h
e
ex
p
e
r
im
en
tati
o
n
r
esu
lts
v
alid
ated
th
at
th
e
C
DB
DP
-
B
GA
m
eth
o
d
im
p
ar
ts
b
etter
r
es
u
lts
in
p
er
f
o
r
m
a
n
ce
m
etr
ics
li
k
e,
p
r
ec
is
io
n
,
r
ec
all,
f
-
m
ea
s
u
r
e,
ac
cu
r
ac
y
an
d
tr
ai
n
in
g
tim
e
co
m
p
ar
ed
to
th
e
co
n
v
en
tio
n
al
m
eth
o
d
s
.
I
n
f
u
tu
r
e,
th
e
d
if
f
er
en
t
p
r
ep
r
o
ce
s
s
in
g
is
u
tili
ze
d
to
esti
m
ate
m
is
s
in
g
d
ata
f
o
r
p
r
ed
ictio
n
o
f
k
i
d
n
ey
d
is
ea
s
e
i
n
ea
r
ly
s
tag
e
with
m
in
im
u
m
tim
e.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
wo
r
k
h
as n
o
t b
ee
n
f
u
n
d
e
d
b
y
a
n
y
s
o
u
r
ce
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
J
ay
ash
r
ee
M
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
An
ith
a
N
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
-
T
h
e
C
h
r
o
n
ic
Kid
n
ey
Dis
ea
s
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
ca
n
b
e
ac
ce
s
s
ed
f
r
o
m
th
e
UC
I
Ma
ch
in
e
L
ea
r
n
in
g
R
ep
o
s
ito
r
y
f
r
o
m
h
ttp
s
://ar
ch
iv
e.
ics.u
ci.
ed
u
/d
ataset/3
3
6
/ch
r
o
n
ic+
k
id
n
ey
+
d
is
ea
s
e
.
-
T
h
e
T
witter
Hea
lth
New
s
d
ataset
i
s
av
ailab
le
at
th
e
f
o
llo
win
g
lin
k
:
h
ttp
s
://ar
ch
iv
e.
ics.u
ci.
ed
u
/d
ata
s
et/4
3
8
/h
ea
lth
+n
ews+in
+twitter
.
-
T
h
e
c
o
m
p
a
r
is
o
n
r
esu
lts
p
r
esen
ted
in
th
is
s
tu
d
y
ar
e
b
ased
o
n
d
ata
f
r
o
m
R
ef
er
en
ce
[
1
]
an
d
R
ef
er
en
ce
[
2
]
.
RE
F
E
R
E
NC
E
S
[
1
]
D
.
S
a
i
f
,
A
.
M
.
S
a
r
h
a
n
,
a
n
d
N
.
M
.
El
sh
e
n
n
a
w
y
,
“
D
e
e
p
-
k
i
d
n
e
y
:
a
n
e
f
f
e
c
t
i
v
e
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
sea
s
e
p
r
e
d
i
c
t
i
o
n
,
”
H
e
a
l
t
h
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
S
y
st
e
m
s
,
v
o
l
.
1
2
,
n
o
.
1
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
7
5
5
-
0
2
3
-
0
0
2
6
1
-
8.
[
2
]
Y
.
Z
h
u
,
D
.
B
i
,
M
.
S
a
u
n
d
e
r
s,
a
n
d
Y
.
Ji
,
“
P
r
e
d
i
c
t
i
o
n
o
f
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
sea
se
p
r
o
g
r
e
ss
i
o
n
u
s
i
n
g
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
e
l
e
c
t
r
o
n
i
c
h
e
a
l
t
h
r
e
c
o
r
d
s,”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
3
,
n
o
.
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
023
-
4
9
2
7
1
-
2.
Evaluation Warning : The document was created with Spire.PDF for Python.