I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
,
p
p
.
20
7
~
21
6
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
5
i
1
.
pp
20
7
-
21
6
207
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Cla
ss
ificatio
n and
regress
io
n t
r
ee m
o
del f
o
r diabe
tes
prediction
F
a
ra
h Na
j
ida
h No
o
riza
n
1
,
N
ur
Anid
a
J
um
a
di
1,
2
,
L
i Mu
n
Ng
1
1
F
a
c
u
l
t
y
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
i
Tu
n
H
u
sse
i
n
O
n
n
M
a
l
a
y
s
i
a
(
U
TH
M
)
,
P
a
r
i
t
R
a
j
a
,
M
a
l
a
y
si
a
2
A
d
v
a
n
c
e
d
M
e
d
i
c
a
l
I
mag
i
n
g
a
n
d
O
p
t
i
c
s (A
d
M
e
d
i
c
)
,
U
n
i
v
e
r
s
i
t
i
T
u
n
H
u
ss
e
i
n
O
n
n
M
a
l
a
y
s
i
a
(
U
TH
M
)
.
P
a
r
i
t
R
a
j
a
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
2
,
2
0
2
5
R
ev
is
ed
Oct
2
9
,
2
0
2
5
Acc
ep
ted
No
v
5
,
2
0
2
5
Dia
b
e
tes
m
e
ll
it
u
s
is
c
h
a
ra
c
teriz
e
d
b
y
e
x
c
e
ss
iv
e
b
lo
o
d
g
l
u
c
o
se
th
a
t
o
c
c
u
rs
wh
e
n
th
e
p
a
n
c
re
a
s
m
a
lfu
n
c
ti
o
n
s
wh
il
e
p
ro
d
u
c
i
n
g
i
n
su
li
n
.
H
ig
h
b
lo
o
d
g
lu
c
o
se
le
v
e
ls
c
a
n
c
a
u
se
c
h
r
o
n
ic
d
a
m
a
g
e
to
o
rg
a
n
s,
p
a
rti
c
u
larly
th
e
e
y
e
s
a
n
d
k
id
n
e
y
s.
Dia
b
e
tes
p
re
d
ictio
n
m
o
d
e
ls
trad
it
io
n
a
ll
y
u
se
a
v
a
riety
o
f
m
a
c
h
in
e
lea
rn
in
g
(M
L)
a
lg
o
r
it
h
m
s
b
y
c
o
m
b
in
i
n
g
d
a
ta
fro
m
th
e
g
l
u
c
o
se
lev
e
ls,
p
a
ti
e
n
t
h
e
a
lt
h
p
a
ra
m
e
ters
,
a
n
d
o
t
h
e
r
b
io
m
a
rk
e
rs.
P
r
io
r
re
se
a
rc
h
o
n
d
iab
e
tes
p
re
d
ictio
n
u
si
n
g
v
a
ri
o
u
s
a
lg
o
rit
h
m
s,
su
c
h
a
s
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
isio
n
tree
(DT)
m
o
d
e
ls,
d
e
m
o
n
stra
tes
a
n
a
c
c
u
ra
c
y
ra
te
o
f
a
p
p
ro
x
ima
tely
7
0
%
,
wh
ic
h
is
re
l
a
ti
v
e
ly
m
o
d
e
st.
Th
e
re
fo
re
,
in
th
i
s
stu
d
y
,
a
c
las
sifica
ti
o
n
a
n
d
re
g
re
ss
io
n
tre
e
(CART)
m
u
lt
icla
ss
ifi
e
r
m
o
d
e
l
h
a
s
b
e
e
n
p
ro
p
o
se
d
t
o
imp
r
o
v
e
th
e
a
c
c
u
ra
c
y
o
f
d
iab
e
tes
p
re
d
icti
o
n
,
w
h
ich
is
b
a
se
d
o
n
th
re
e
c
las
se
s
:
n
o
n
-
d
iab
e
ti
c
,
p
re
-
d
iab
e
ti
c
,
a
n
d
d
iab
e
ti
c
.
T
h
e
stu
d
y
i
n
v
o
lv
e
d
d
a
ta
p
re
p
ro
c
e
ss
in
g
ste
p
s,
h
y
p
e
rp
a
ra
m
e
ter
tu
n
in
g
,
a
n
d
e
v
a
l
u
a
ti
o
n
o
f
p
e
rfo
rm
a
n
c
e
m
e
tri
c
s.
Th
e
m
o
d
e
l
a
c
h
iev
e
d
9
7
%
a
c
c
u
ra
c
y
wh
il
e
u
ti
li
z
in
g
th
e
v
a
lu
e
o
f
5
fo
r
th
e
n
u
m
b
e
r
o
f
l
e
a
v
e
s
p
e
r
n
o
d
e
,
t
h
e
v
a
lu
e
o
f
1
0
fo
r
th
e
m
a
x
imu
m
n
u
m
b
e
r
o
f
s
p
li
ts,
a
n
d
d
e
v
ian
c
e
a
s
th
e
sp
li
t
c
rit
e
ri
o
n
,
wh
ich
a
ls
o
re
su
lt
e
d
i
n
a
p
re
c
isio
n
o
f
9
8
%
,
re
c
a
ll
o
f
9
7
%
,
a
n
d
F
1
-
sc
o
re
o
f
9
8
%
,
sh
o
win
g
th
a
t
th
e
p
ro
p
o
se
d
m
u
lt
icla
ss
ifi
e
r
m
o
d
e
l
c
a
n
a
c
c
u
ra
tely
p
re
d
ict
d
iab
e
tes
.
In
c
o
n
c
lu
sio
n
,
th
e
p
ro
p
o
se
d
C
ART
m
o
d
e
l
wit
h
t
h
e
b
e
st
h
y
p
e
rp
a
ra
m
e
ter
se
tt
in
g
c
a
n
e
n
a
b
le t
h
e
h
i
g
h
e
st ac
c
u
ra
c
y
in
p
re
d
ict
in
g
d
ia
b
e
tes
c
las
s
e
s.
K
ey
w
o
r
d
s
:
C
AR
T
Diab
etes m
ellitu
s
E
v
alu
atio
n
m
etr
ics
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
:
Nu
r
An
id
a
J
u
m
ad
i
Facu
lty
o
f
E
lectr
ical
an
d
E
lectr
o
n
ic
E
n
g
in
ee
r
in
g
,
Un
iv
e
r
s
iti T
u
n
Hu
s
s
ein
On
n
Ma
lay
s
ia
(
U
T
HM
)
Par
it R
aja,
B
atu
Pah
at,
8
6
4
0
0
,
Ma
lay
s
ia
E
m
ail:
an
id
a@
u
th
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Diab
etes
m
ellitu
s
is
a
m
etab
o
lic
co
n
d
itio
n
ch
ar
ac
ter
iz
ed
b
y
ex
ce
s
s
iv
e
b
lo
o
d
g
lu
co
s
e
an
d
h
y
p
er
g
ly
ce
m
ia.
T
h
is
s
ick
n
ess
o
cc
u
r
s
wh
en
th
e
p
an
c
r
ea
s
,
wh
ich
p
r
o
d
u
ce
s
in
s
u
lin
,
m
alf
u
n
ct
io
n
s
,
o
r
wh
e
n
ce
lls
d
o
n
o
t
a
d
eq
u
ately
r
esp
o
n
d
to
th
e
in
s
u
lin
co
m
p
o
s
itio
n
[
1
]
,
[
2
]
.
T
h
e
I
n
ter
n
atio
n
al
Diab
etes
Fed
er
atio
n
d
e
f
in
es
d
iab
etes
m
ellitu
s
as
a
ch
r
o
n
ic
co
n
d
itio
n
th
at
s
u
b
s
tan
tially
im
p
ac
ts
g
lo
b
al
h
ea
lth
.
Ap
p
r
o
x
im
ately
5
3
7
m
illi
o
n
ad
u
lts
(
ag
ed
2
0
t
o
7
9
)
a
r
e
d
ia
g
n
o
s
ed
with
d
iab
etes,
a
n
d
a
n
esti
m
ated
6
.
7
m
illi
o
n
d
iab
etes
p
atien
ts
wo
r
ld
wid
e
d
ied
in
2
0
2
1
.
T
h
e
n
u
m
b
er
o
f
d
iab
etic
in
d
iv
id
u
als
is
ex
p
ec
te
d
to
r
is
e
b
y
4
6
%
b
y
2
0
4
5
[
3
]
,
[
4
]
.
T
h
er
e
is
as
y
et
n
o
c
u
r
e,
a
n
d
th
e
p
r
ev
ale
n
ce
is
s
till
in
cr
ea
s
in
g
.
Hig
h
b
lo
o
d
g
lu
co
s
e
lev
els,
ch
a
r
ac
ter
ized
b
y
d
iab
etes,
an
d
lo
n
g
-
ter
m
h
y
p
er
g
ly
ce
m
ia
ca
n
ca
u
s
e
ch
r
o
n
ic
d
am
a
g
e
to
v
ar
io
u
s
o
r
g
an
s
,
p
ar
ticu
lar
ly
th
e
ey
es,
k
i
d
n
ey
s
,
h
ea
r
t,
b
lo
o
d
v
ess
els,
an
d
n
er
v
o
u
s
s
y
s
tem
[
5
]
,
[
6
]
.
Diab
etes
is
f
r
eq
u
en
tly
s
elf
-
m
an
ag
ed
b
y
p
atien
ts
th
r
o
u
g
h
m
an
y
ass
ess
m
en
t
s
o
f
th
e
g
lu
co
s
e
lev
el
th
r
o
u
g
h
o
u
t
th
e
d
ay
,
as
well
as in
s
u
lin
ad
m
in
is
tr
atio
n
v
ia
in
je
ctio
n
o
r
p
u
m
p
,
wh
ich
ca
n
b
e
d
if
f
icu
lt
f
o
r
p
atien
ts
wh
o
f
ac
e
n
u
m
er
o
u
s
ch
allen
g
es
in
th
eir
ev
er
y
d
ay
liv
es
[
7
]
.
A
co
n
v
en
ti
o
n
al
b
lo
o
d
g
l
u
co
s
e
d
ev
ice
u
s
es
d
is
p
o
s
ab
le
s
tr
ip
s
o
f
g
lu
co
s
e
o
x
id
ase
b
io
s
en
s
o
r
s
to
m
ea
s
u
r
e
g
lu
co
s
e
co
n
ce
n
tr
atio
n
f
r
o
m
th
e
ac
q
u
ir
ed
f
in
g
er
tip
b
lo
o
d
[
8
]
,
[
9
]
.
Diab
etes
p
r
ed
i
ctio
n
m
o
d
els
tr
ad
itio
n
ally
u
s
e
a
v
ar
iety
o
f
m
ac
h
in
e
lear
n
in
g
(
ML
)
alg
o
r
ith
m
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
20
7
-
21
6
208
in
clu
d
in
g
d
ec
is
io
n
tr
ee
(
DT
)
,
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
S
VM
)
,
with
v
ar
i
o
u
s
f
ea
tu
r
e
s
ets
an
d
d
atasets
,
s
u
c
h
as
g
lu
co
s
e
lev
els,
h
ea
lth
p
ar
am
eter
s
,
an
d
o
th
er
b
io
m
ar
k
er
s
[
1
0
]
.
Pre
v
io
u
s
r
esear
ch
o
n
d
iab
etes
p
r
e
d
ictio
n
u
s
in
g
v
a
r
io
u
s
ML
alg
o
r
ith
m
s
,
in
clu
d
in
g
SVM
an
d
DT
m
o
d
els,
h
as
s
h
o
wn
an
ac
cu
r
ac
y
r
ate
o
f
r
o
u
g
h
ly
7
0
%,
wh
ich
is
r
ath
er
m
o
d
est.
T
h
e
au
th
o
r
s
in
[
1
1
]
–
[
1
3
]
u
s
ed
v
ar
io
u
s
alg
o
r
ith
m
s
to
p
r
ed
ict
d
iab
etes
u
s
in
g
v
ar
i
o
u
s
f
ea
tu
r
e
s
,
s
u
ch
as
p
er
s
o
n
al
d
ata
a
n
d
h
ea
lth
p
ar
am
eter
s
,
in
clu
d
in
g
L
R
,
K
-
n
e
ar
est
n
eig
h
b
o
r
s
(
KNN)
,
N
aiv
e
B
ay
es
(
NB
)
,
DT
,
r
an
d
o
m
f
o
r
est
(
R
F),
ar
tific
ial
n
eu
r
al
n
etwo
r
k
,
an
d
SVM.
T
h
ese
m
o
d
els
’
ac
c
u
r
ac
y
is
s
lig
h
tly
lo
wer
,
r
an
g
in
g
f
r
o
m
7
0
% to
9
0
%.
Fu
r
th
er
m
o
r
e
,
th
e
au
th
o
r
s
in
[
1
4
]
–
[
1
7
]
p
r
ed
icted
d
i
ab
ete
s
u
s
in
g
s
ev
en
d
if
f
er
en
t
alg
o
r
ith
m
s
in
p
r
ed
ictin
g
d
iab
etes,
wh
ich
wer
e
SVM,
L
R
,
g
r
ad
ie
n
t
b
o
o
s
tin
g
m
ac
h
in
e
,
R
F,
DT
,
KNN,
an
d
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
m
o
d
el
(
XGBo
o
s
t)
,
a
n
d
d
is
co
v
er
ed
th
at
L
R
an
d
SVM
ar
e
u
s
ef
u
l
f
o
r
d
iab
etes
p
r
ed
ictio
n
.
I
n
ad
d
itio
n
,
[
1
8
]
d
ev
elo
p
e
d
s
ix
ML
alg
o
r
it
h
m
s
to
tr
ain
a
d
ataset
u
s
in
g
m
u
ltip
le
tech
n
iq
u
es
o
f
f
ea
tu
r
e
s
elec
tio
n
f
o
r
m
o
d
el
ac
cu
r
ac
y
im
p
r
o
v
em
en
ts
.
E
l
-
B
o
u
h
is
s
i
e
t
a
l.
[
1
9
]
d
esig
n
ed
a
m
o
d
el
f
o
r
g
estatio
n
al
d
iab
etes
m
ellitu
s
p
r
ed
ictio
n
u
s
in
g
th
e
class
if
ier
o
f
d
ee
p
n
eu
r
al
n
etwo
r
k
(
DNN)
,
S
VM
,
an
d
R
F,
wh
ich
p
r
o
d
u
c
ed
an
ac
cu
r
ac
y
o
f
ap
p
r
o
x
im
ately
9
0
% to
9
5
%.
T
h
e
au
th
o
r
s
in
[
2
0
]
–
[
2
2
]
p
r
o
p
o
s
ed
an
e
n
s
em
b
lin
g
class
if
ier
f
o
r
d
iab
etes
p
r
ed
ictio
n
b
ased
o
n
v
a
r
io
u
s
ML
class
if
ier
s
,
s
u
ch
as
KNN,
DT
,
R
F,
Ad
aBo
o
s
t,
NB
,
XGBo
o
s
t,
an
d
m
u
ltil
ay
er
p
e
r
ce
p
t
r
o
n
.
I
n
r
ec
en
t
y
ea
r
s
,
[
2
3
]
u
s
ed
J
u
p
y
ter
No
teb
o
o
k
t
o
cr
ea
te
a
n
ew
s
tack
in
g
en
s
e
m
b
le
m
o
d
el
f
o
r
d
iab
etes
p
r
ed
ictio
n
u
s
in
g
R
F
an
d
L
R
as
b
ase
lear
n
er
m
o
d
els,
w
h
ile
[
2
4
]
u
s
ed
R
F,
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
with
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
n
etwo
r
k
,
a
n
d
s
eq
u
e
n
tial
d
en
s
e
lay
er
s
as
b
ase
lear
n
er
m
o
d
els
,
wh
er
e
b
o
th
s
tu
d
ies
u
s
ed
th
e
XGBo
o
s
t
m
o
d
el
as
th
e
m
eta
-
lear
n
er
m
o
d
el.
All th
ese
m
o
d
els s
h
o
wed
an
ac
c
u
r
ac
y
o
f
8
3
% to
9
5
%.
T
h
is
p
r
e
s
e
n
t
r
e
s
ea
r
c
h
p
r
o
p
o
s
es
a
c
l
as
s
i
f
i
c
a
ti
o
n
a
n
d
r
e
g
r
es
s
io
n
t
r
e
e
(
C
AR
T
)
m
o
d
e
l
f
o
r
t
h
e
a
c
c
u
r
a
c
y
i
m
p
r
o
v
e
m
e
n
t
o
f
d
i
a
b
e
t
e
s
p
r
e
d
ic
t
i
o
n
.
T
h
e
m
o
d
e
l
e
m
p
l
o
y
s
G
i
n
i
,
d
e
v
i
a
n
c
e
,
a
n
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
t
o
i
d
e
n
t
i
f
y
t
h
e
o
p
t
i
m
a
l
s
p
l
i
ts
f
o
r
e
f
f
i
c
i
e
n
cy
,
a
c
c
u
r
a
c
y
,
a
n
d
o
v
e
r
f
i
t
t
i
n
g
a
v
o
i
d
a
n
c
e
.
C
o
n
t
r
a
r
y
t
o
t
h
e
t
r
a
d
it
io
n
a
l
DT
a
l
g
o
r
i
t
h
m
s
,
s
u
c
h
a
s
I
D
3
[
2
5
]
,
w
h
i
c
h
l
a
c
k
s
o
v
e
r
f
i
t
t
i
n
g
c
o
n
t
r
o
l
a
n
d
e
m
p
l
o
y
s
m
u
l
t
i
-
b
r
a
n
c
h
s
p
l
it
s
,
t
h
e
u
s
e
o
f
t
h
e
C
A
R
T
m
o
d
e
l
a
i
m
e
d
t
o
b
e
a
m
o
r
e
s
u
i
t
a
b
l
e
a
p
p
r
o
a
c
h
f
o
r
m
e
d
i
c
a
l
p
r
e
d
i
c
t
i
o
n
.
I
t
s
c
a
p
a
ci
t
y
t
o
p
e
r
f
o
r
m
c
l
a
s
s
i
f
i
c
at
i
o
n
a
n
d
r
e
g
r
e
s
s
i
o
n
t
a
s
k
s
w
as
u
t
il
i
z
e
d
t
o
i
m
p
r
o
v
e
i
t
s
e
f
f
ic
i
e
n
c
y
,
i
n
te
r
p
r
e
t
a
b
i
l
it
y
,
a
n
d
a
c
c
u
r
a
c
y
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
ct
i
o
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
A
d
iab
etes
d
ataset
was
co
llect
ed
f
r
o
m
t
h
e
lab
o
r
ato
r
y
o
f
a
m
ed
ical
city
h
o
s
p
ital,
wh
ich
co
n
tain
ed
th
e
d
ata
o
f
a
to
tal
o
f
1
,
0
0
0
s
u
b
jec
ts
[
2
6
]
.
T
h
er
e
wer
e
1
1
f
ea
tu
r
e
s
,
wh
ich
wer
e
g
en
d
er
,
ag
e,
u
r
ea
lev
el,
cr
ea
tin
in
e
r
atio
,
h
e
m
o
g
lo
b
in
lev
el,
c
h
o
lest
er
o
l
lev
el,
tr
ig
l
y
ce
r
id
e
le
v
el,
h
i
g
h
-
d
e
n
s
ity
lip
o
p
r
o
tein
lev
el,
lo
w
-
d
en
s
ity
lip
o
p
r
o
tein
le
v
el,
v
er
y
lo
w
-
d
en
s
ity
lip
o
p
r
o
tein
le
v
el,
an
d
b
o
d
y
m
ass
in
d
ex
(
B
M
I)
.
T
h
e
tar
g
et
o
u
tp
u
t
was
d
iv
id
ed
i
n
to
th
r
ee
class
es:
c
lass
0
f
o
r
n
o
n
-
d
iab
etic,
c
las
s
1
f
o
r
p
r
e
-
d
iab
etic,
an
d
c
lass
2
f
o
r
d
iab
etic.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
s
tar
ted
with
th
e
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
e
an
d
th
e
s
p
litt
in
g
o
f
th
e
d
ataset
in
to
tr
ain
in
g
an
d
test
in
g
u
s
in
g
an
8
0
:2
0
r
atio
.
T
h
e
C
AR
T
m
o
d
el
was
th
en
t
r
ain
ed
u
s
in
g
s
ev
er
al
h
y
p
er
p
ar
am
eter
tu
n
in
g
s
ettin
g
s
,
wh
ich
wer
e
th
e
n
u
m
b
e
r
o
f
le
av
es
p
er
n
o
d
e,
t
h
e
m
a
x
im
u
m
n
u
m
b
er
o
f
s
p
lits
,
an
d
th
e
s
p
lit
cr
iter
io
n
.
T
h
en
,
th
e
m
o
d
el
’
s
p
e
r
f
o
r
m
an
ce
wa
s
v
alid
ated
u
s
in
g
th
e
m
etr
ic
s
o
f
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
F1
-
s
co
r
e
,
an
d
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
-
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
R
OC
-
AUC
)
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
o
v
e
r
all
p
r
o
ce
s
s
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
’
s
d
ev
el
o
p
m
en
t.
A
m
o
d
el
d
e
p
lo
y
m
e
n
t
was
cr
ea
ted
to
v
is
u
alize
th
e
p
r
ed
icted
d
iab
etes
s
tatu
s
o
f
p
atien
ts
.
2
.
1
.
Da
t
a
prepro
ce
s
s
ing
Data
p
r
ep
r
o
ce
s
s
in
g
is
cr
itical
in
ML
an
d
d
ata
an
aly
tics
.
Pre
p
r
o
ce
s
s
in
g
im
p
r
o
v
es
a
d
ata
s
et
b
y
r
em
o
v
in
g
o
r
im
p
u
ti
n
g
m
is
s
in
g
v
alu
es,
s
cr
ee
n
in
g
o
u
tlier
s
,
an
d
elim
in
atin
g
n
o
is
e,
en
s
u
r
i
n
g
t
h
e
d
ata
ar
e
co
r
r
ec
t
an
d
r
eliab
le.
W
h
en
wo
r
k
i
n
g
w
ith
n
o
n
-
n
u
m
e
r
ic
d
ata,
ca
te
g
o
r
i
ca
l
p
r
o
ce
s
s
in
g
is
ess
en
tial
to
d
ata
p
r
ep
r
o
ce
s
s
in
g
.
ML
m
o
d
els,
s
u
ch
as
tr
ee
-
b
ased
m
o
d
els
an
d
class
if
icatio
n
m
etr
ics,
o
f
ten
d
em
an
d
n
u
m
er
ica
l
in
p
u
ts
;
th
er
ef
o
r
e,
ca
teg
o
r
ical
v
ar
iab
les m
u
s
t b
e
tr
an
s
lated
p
r
o
p
er
ly
b
ef
o
r
e
b
ein
g
f
ed
in
t
o
th
e
m
o
d
el.
Fig
u
r
e
1
s
h
o
ws
th
e
m
o
d
el
’
s
d
ataset,
co
n
s
is
tin
g
o
f
1
1
in
p
u
t
f
ea
tu
r
es.
Gen
d
er
was
r
ep
r
esen
ted
as
ca
teg
o
r
ical
d
ata,
with
0
f
o
r
m
a
le
an
d
1
f
o
r
f
em
ale,
wh
ile
th
e
r
em
ain
in
g
d
ata
wer
e
class
if
ied
as n
u
m
er
ical
d
ata.
Asi
d
e
f
r
o
m
th
at,
t
h
e
tar
g
et
d
ata
wer
e
n
u
m
er
ical,
with
v
al
u
es
o
f
0
,
1
,
an
d
2
b
ein
g
u
s
ed
as
class
lab
els.
T
o
co
n
d
u
ct
th
e
class
if
icatio
n
task
s
,
th
e
class
lab
el
s
m
u
s
t
b
e
tu
r
n
ed
in
t
o
ca
teg
o
r
ical
d
ata
to
d
is
tin
g
u
is
h
th
eir
d
is
tin
ct
g
r
o
u
p
s
o
f
n
o
n
-
d
ia
b
etics
,
p
r
e
-
d
iab
etic,
a
n
d
d
ia
b
etic.
2
.
2
.
CART
T
h
e
C
AR
T
alg
o
r
ith
m
co
m
b
i
n
es
DT
s
an
d
r
eg
r
ess
io
n
to
s
o
lv
e
class
if
icatio
n
an
d
r
eg
r
ess
io
n
is
s
u
es.
I
t
d
iv
id
es
a
d
ataset
in
to
b
r
an
c
h
es
d
ep
e
n
d
in
g
o
n
f
ea
tu
r
e
v
alu
es,
u
s
in
g
Gin
i
im
p
u
r
ity
f
o
r
cl
ass
if
icatio
n
an
d
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
C
la
s
s
i
fica
tio
n
a
n
d
r
eg
r
ess
io
n
tr
ee
mo
d
el
fo
r
d
ia
b
etes p
r
ed
ic
tio
n
(
F
a
r
a
h
N
a
jid
a
h
N
o
o
r
iz
a
n
)
209
m
ea
n
s
q
u
ar
e
d
er
r
o
r
f
o
r
r
eg
r
e
s
s
io
n
[
2
7
]
.
Gin
i
an
d
d
e
v
ian
c
e
wer
e
s
u
itab
le
ap
p
r
o
ac
h
es
f
o
r
class
if
icatio
n
in
th
is
s
tu
d
y
.
A
Gin
i
in
d
e
x
ass
ess
es
th
e
im
p
u
r
ity
i
n
ca
teg
o
r
izatio
n
t
ask
s
b
y
ca
lcu
latin
g
th
e
p
r
o
b
ab
ilit
y
o
f
m
is
tak
en
ly
class
if
y
in
g
r
an
d
o
m
ly
ch
o
s
en
d
ata
f
r
o
m
t
h
e
s
p
lit.
Dev
ian
ce
,
o
n
th
e
o
th
er
h
an
d
,
m
ea
s
u
r
es
h
o
w
ef
f
ec
tiv
ely
a
s
p
lit
im
p
r
o
v
es
p
r
ed
ictio
n
ac
cu
r
ac
y
b
y
co
m
p
ar
i
n
g
a
m
o
d
el
’
s
lik
elih
o
o
d
b
e
f
o
r
e
an
d
af
ter
th
e
s
p
lit.
I
t
is
co
m
m
o
n
ly
em
p
lo
y
e
d
in
LR
o
r
clas
s
if
icatio
n
task
s
,
wh
er
e
a
lo
wer
d
ev
ian
ce
s
u
g
g
ests
a
b
etter
f
it
an
d
m
o
r
e
ac
cu
r
ate
p
r
e
d
icti
o
n
s
.
Fig
u
r
e
1
.
T
h
e
o
v
er
all
p
r
o
ce
s
s
o
f
th
e
C
AR
T
m
u
lticlas
s
if
ier
f
o
r
d
iab
etes p
r
ed
ictio
n
2
.
3
.
H
y
perpa
ra
m
e
t
er
t
un
ing
I
n
ML
,
h
y
p
e
r
p
ar
am
eter
tu
n
in
g
r
ef
er
s
to
d
eter
m
in
i
n
g
th
e
v
alu
e
o
f
a
p
ar
am
ete
r
b
ef
o
r
e
th
e
lear
n
in
g
p
r
o
ce
s
s
b
eg
in
s
[
2
8
]
.
C
AR
T
alg
o
r
ith
m
s
o
f
te
n
h
a
v
e
a
f
ix
e
d
s
et
o
f
h
y
p
er
p
ar
a
m
eter
s
,
s
u
ch
as
th
e
m
a
x
im
u
m
n
u
m
b
er
o
f
s
p
lits
.
T
h
e
n
u
m
b
er
o
f
leav
es
p
e
r
n
o
d
e
is
th
e
s
m
allest
n
u
m
b
er
o
f
o
b
s
er
v
a
tio
n
s
(
d
ata
p
o
i
n
ts
)
n
ec
ess
ar
y
in
a
leaf
n
o
d
e.
I
ts
p
u
r
p
o
s
e
is
to
p
r
ev
e
n
t
o
v
er
f
itt
in
g
b
y
p
r
o
h
ib
itin
g
th
e
tr
ee
f
r
o
m
s
p
litt
in
g
f
u
r
th
er
wh
en
th
e
n
u
m
b
e
r
o
f
s
am
p
les
in
a
n
o
d
e
is
s
m
aller
th
an
th
is
v
alu
e.
T
h
e
lar
g
er
n
u
m
b
er
s
r
esu
lt
in
a
s
im
p
ler
tr
ee
,
wh
ile
s
m
aller
n
u
m
b
er
s
allo
w
f
o
r
m
o
r
e
d
etailed
s
p
lits
.
T
h
e
p
ar
am
eter
o
f
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
s
p
lits
r
estricts
th
e
tr
ee
’
s
g
r
o
wth
,
lo
wer
in
g
co
m
p
lex
ity
an
d
lim
itin
g
o
v
e
r
f
itti
n
g
b
y
av
o
id
in
g
u
n
n
ec
ess
ar
y
b
r
an
ch
i
n
g
.
Sm
aller
n
u
m
b
er
s
r
esu
lt in
a
s
im
p
ler
tr
ee
,
b
u
t la
r
g
e
r
v
alu
es p
r
o
v
id
e
g
r
ea
ter
f
le
x
ib
ilit
y
.
Dev
ian
ce
is
f
r
eq
u
e
n
tly
u
tili
ze
d
in
a
C
AR
T
m
o
d
el
wh
en
wo
r
k
in
g
with
b
in
ar
y
o
u
tco
m
es
to
ass
es
s
th
e
g
o
o
d
n
ess
o
f
f
it o
f
class
if
icatio
n
m
o
d
els.
=
−
2
∑
∑
[
,
l
og
(
,
)
]
=
1
=
1
(
1
)
T
h
e
d
ev
iatio
n
in
(
1
)
is
ca
lcu
lated
u
s
in
g
th
e
lo
g
-
lik
elih
o
o
d
f
u
n
ctio
n
in
(
2
)
,
w
h
ich
ass
ess
e
s
th
e
f
it
q
u
ality
f
o
r
class
if
icatio
n
m
o
d
els.
l
og
(
)
=
∑
∑
[
,
l
og
(
,
]
=
1
=
1
(
2
)
W
h
er
e
n
is
th
e
n
u
m
b
e
r
o
f
o
b
s
er
v
atio
n
s
,
an
d
y
i,
c
is
th
e
ac
tu
al
class
lab
el,
wh
ich
eq
u
als 1
if
th
e
i
-
th
o
b
s
er
v
atio
n
b
elo
n
g
s
to
class
c
,
wh
ile
p
i,
c
is
th
e
p
r
ed
icted
p
r
o
b
ab
ilit
y
th
a
t
o
b
s
er
v
atio
n
i
b
elo
n
g
s
to
class
c
.
W
h
en
d
iv
i
d
in
g
n
o
d
es
in
to
a
C
AR
T
tr
ee
,
d
ev
ia
tio
n
is
ev
alu
ated
f
o
r
ea
ch
p
o
te
n
tial
s
p
lit,
an
d
th
e
s
p
lit
with
th
e
lar
g
est
r
ed
u
ctio
n
in
d
ev
ian
ce
is
s
elec
ted
as th
e
o
p
tim
al
d
ec
is
io
n
n
o
d
e.
T
h
e
Gin
i
in
d
e
x
is
a
s
tatis
tic
th
at
d
eter
m
in
es
h
o
w
m
ix
e
d
o
r
p
u
r
e
th
e
d
ata
is
in
a
DT
n
o
d
e.
I
t
is
co
m
p
u
ted
u
s
in
g
(
3
)
,
wh
e
r
e
C
is
th
e
n
u
m
b
er
o
f
class
es
in
th
e
tar
g
et
v
ar
iab
les
an
d
p
i
is
th
e
p
r
o
p
o
r
tio
n
o
f
co
m
p
o
n
en
ts
in
th
e
s
p
lit th
at
b
e
lo
n
g
to
class
i
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
20
7
-
21
6
210
=
1
−
∑
2
=
1
(
3
)
Dev
ian
ce
is
u
s
ed
as
th
e
s
p
lit
cr
iter
io
n
f
o
r
s
ev
er
al
r
e
aso
n
s
,
p
ar
ticu
lar
ly
w
h
en
a
d
ataset
’
s
class
es
ar
e
im
b
alan
ce
d
,
as
in
th
e
p
r
esen
t stu
d
y
’
s
d
iab
etes
d
ataset,
wh
ic
h
h
ad
a
h
ig
h
e
r
p
r
o
p
o
r
tio
n
o
f
c
lass
2
th
an
c
las
s
es
0
an
d
1
.
I
n
t
h
is
co
n
tex
t,
d
ev
ia
n
ce
ca
n
h
an
d
le
s
u
ch
s
ce
n
ar
i
o
s
m
o
r
e
ef
f
ec
tiv
ely
b
y
em
p
h
a
s
izin
g
p
r
o
b
ab
ilis
tic
s
ep
ar
atio
n
s
o
v
er
p
u
r
e
s
p
lits
.
2
.
4
.
P
er
f
o
r
m
a
nce
m
e
t
rics
C
las
s
if
icatio
n
ac
cu
r
ac
y
is
o
n
e
o
f
th
e
p
e
r
f
o
r
m
an
ce
ev
al
u
atio
n
m
etr
ics
th
at
d
is
p
lay
h
o
w
we
ll
a
m
o
d
el
p
r
ed
icts
in
s
tan
ce
s
b
ased
o
n
tr
ain
in
g
d
ata.
I
n
th
is
s
tu
d
y
,
th
e
p
er
f
o
r
m
an
ce
m
etr
ic
m
ea
s
u
r
e
m
en
ts
wer
e
d
i
v
id
ed
in
to
th
e
f
o
llo
win
g
m
et
r
ics,
wh
ich
wer
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
a
n
d
R
OC
-
AUC
cu
r
v
e,
as
ex
p
r
ess
ed
in
(
4
)
to
(
8
)
.
T
ab
le
1
r
ep
r
esen
ts
th
e
m
u
lticlas
s
co
n
f
u
s
io
n
m
at
r
ix
s
tr
u
ctu
r
e
,
wh
er
e
th
e
r
o
ws
r
ep
r
esen
t
th
e
tr
u
e
class
es,
an
d
th
e
co
lu
m
n
s
r
ep
r
esen
t
th
e
p
r
ed
icted
c
lass
es.
T
h
e
ter
m
C
0
r
ef
er
s
t
o
c
lass
0
,
C
1
r
ef
er
s
to
c
lass
1
,
C
2
r
ef
er
s
to
c
lass
2
,
a
n
d
C
n
r
ef
er
s
to
th
e
n
-
th
class
.
I
n
ad
d
itio
n
,
T
P
is
d
ef
i
n
ed
as
t
r
u
e
p
o
s
itiv
e
,
T
N
as
tr
u
e
n
eg
ativ
e
,
FP
as
f
alse p
o
s
it
iv
e
,
FN a
s
f
alse n
eg
ati
ve
,
R
i
is
th
e
r
ate
o
f
th
e
i
-
th
d
ata,
a
n
d
I
f
an
d
I
I
ar
e
n
eg
ativ
e
an
d
p
o
s
itiv
e
d
ata,
r
esp
ec
tiv
ely
.
T
ab
le
1
.
C
o
n
f
u
s
io
n
m
atr
ix
s
tr
u
ctu
r
e
f
o
r
m
u
lticlas
s
class
if
ica
tio
n
P
r
e
d
i
c
t
e
d
c
l
a
ss
A
c
t
u
a
l
c
l
a
ss
C
l
a
s
ses
C
0
C
1
C
2
C
n
C
0
TP
FP
TN
TN
C
1
FN
TP
FN
FN
C
2
TN
FP
TN
TN
C
n
TN
FP
TN
TN
T
h
e
ac
cu
r
ac
y
r
atio
is
th
e
n
u
m
b
er
o
f
tr
u
e
p
r
e
d
icted
in
s
tan
ce
s
,
p
o
s
itiv
e
an
d
n
eg
ativ
e
,
d
i
v
id
ed
b
y
th
e
to
tal
n
u
m
b
er
o
f
ca
s
es.
=
+
+
+
+
(
4
)
Pre
cisi
o
n
is
th
e
r
atio
o
f
ex
p
ec
t
ed
p
o
s
itiv
e
in
s
tan
ce
s
to
to
tal
p
r
ed
icted
p
o
s
itiv
e
in
s
tan
ce
s
.
=
+
(
5
)
R
ec
all
is
o
b
tain
ed
b
y
d
iv
id
in
g
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es
b
y
th
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es
p
lu
s
th
e
n
u
m
b
er
o
f
f
alse n
eg
ativ
es.
=
+
(
6
)
T
h
e
F1
-
s
co
r
e
is
u
s
ed
to
ass
ess
th
e
o
v
er
all
p
e
r
f
o
r
m
an
ce
.
I
t
weig
h
s
th
e
h
ar
m
o
n
ic
m
ea
n
in
g
o
f
p
r
ec
is
io
n
an
d
r
ec
all.
1
−
=
2
2
+
+
(
7
)
T
h
e
AUC
is
a
p
er
f
o
r
m
an
ce
m
etr
ic
f
o
r
a
b
i
n
ar
y
class
if
icatio
n
m
o
d
el,
wh
ic
h
ca
n
b
e
u
s
ed
to
d
if
f
e
r
en
tiat
e
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es.
T
h
e
AU
C
is
th
e
ar
ea
u
n
d
er
t
h
e
R
OC
cu
r
v
e,
wh
ich
co
m
p
ar
es
th
e
tr
u
e
p
o
s
itiv
e
r
ate
ag
ain
s
t th
e
f
alse
p
o
s
itiv
e
r
ate
at
d
if
f
er
en
t c
ateg
o
r
izatio
n
lev
els.
=
∑
(
)
−
(
+
1
)
/
2
+
(
8
)
2
.
5
.
M
o
del deplo
y
m
ent
A
d
ep
lo
y
m
e
n
t m
o
d
el
in
ML
in
teg
r
ates a
tr
ain
ed
ML
m
o
d
el
in
to
a
r
ea
l
-
wo
r
l
d
s
y
s
tem
o
r
ap
p
licatio
n
to
cr
ea
te
p
r
e
d
ictio
n
s
au
to
m
atica
lly
.
T
h
is
m
o
d
el
allo
ws
e
n
d
u
s
er
s
to
en
ter
d
ata
an
d
r
ec
eiv
e
p
r
ed
ictio
n
s
o
r
in
s
ig
h
ts
f
r
o
m
th
e
m
o
d
el.
Fig
u
r
e
2
r
e
p
r
esen
ts
th
is
s
tu
d
y
’
s
m
o
d
el
d
ep
l
o
y
m
en
t
f
o
r
d
iab
etes
p
r
ed
ictio
n
,
p
er
f
o
r
m
ed
u
s
in
g
MA
T
L
AB
s
o
f
twar
e.
T
h
is
m
o
d
el
d
eter
m
in
ed
o
r
f
o
r
ec
ast
a
p
atien
t
’
s
d
iab
etes
s
tatu
s
o
r
class
b
y
en
ter
in
g
p
er
s
o
n
al
in
f
o
r
m
atio
n
,
s
u
ch
as
g
en
d
er
,
ag
e,
B
MI
,
b
l
o
o
d
s
u
g
ar
,
ch
o
lest
er
o
l,
an
d
o
th
e
r
h
ea
lth
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
C
la
s
s
i
fica
tio
n
a
n
d
r
eg
r
ess
io
n
tr
ee
mo
d
el
fo
r
d
ia
b
etes p
r
ed
ic
tio
n
(
F
a
r
a
h
N
a
jid
a
h
N
o
o
r
iz
a
n
)
211
2
.
6
.
P
s
eudo
co
de
f
o
r
dia
bet
es pre
dict
io
n
us
i
ng
CART a
n
d
m
o
del deplo
y
m
ent
Ps
eu
d
o
co
d
e
is
a
s
im
p
lifie
d
,
h
ig
h
-
lev
el
r
ep
r
esen
tatio
n
o
f
a
p
r
o
g
r
am
o
r
alg
o
r
ith
m
th
at
co
m
b
in
es
n
o
r
m
al
lan
g
u
ag
e
a
n
d
p
r
o
g
r
am
m
in
g
id
ea
s
.
I
t
is
n
o
t
cr
ea
te
d
in
a
p
ar
ticu
lar
p
r
o
g
r
am
m
in
g
la
n
g
u
ag
e
an
d
d
o
es
n
o
t
ad
h
er
e
to
s
tr
ict
g
r
a
m
m
ar
co
n
s
tr
ain
ts
,
m
ak
in
g
it
ea
s
ier
to
u
n
d
er
s
tan
d
.
I
n
th
is
s
tu
d
y
,
m
o
d
el
p
r
ed
ictio
n
s
an
d
d
ep
lo
y
m
e
n
t
wer
e
im
p
lem
en
te
d
u
s
in
g
MA
T
L
AB
s
o
f
twar
e.
T
ab
le
2
p
r
esen
ts
th
e
p
s
eu
d
o
co
d
e
th
at
ex
p
lain
s
th
e
s
tep
s
f
o
r
d
ev
e
lo
p
in
g
t
h
e
m
o
d
e
l.
Fig
u
r
e
2
.
Mo
d
el
d
ep
l
o
y
m
e
n
t
T
ab
le
2
.
Ps
eu
d
o
c
o
d
e
f
o
r
d
ia
b
e
tes p
r
ed
ictio
n
u
s
in
g
C
AR
T
an
d
m
o
d
el
d
ep
lo
y
m
en
t
P
seu
d
o
c
o
d
e
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
C
A
R
T
I
n
p
u
t
:
Lo
a
d
a
n
d
r
e
a
d
t
h
e
d
a
t
a
s
e
t
o
f
1
1
f
e
a
t
u
r
e
s
(
g
e
n
d
e
r
,
a
g
e
,
u
r
e
a
,
c
r
e
a
t
i
n
i
n
e
r
a
t
i
o
,
H
b
A
1
c
,
c
h
o
l
e
st
e
r
o
l
,
t
r
i
g
l
y
c
e
r
i
d
e
(
Tr
)
,
H
D
L
,
LD
L,
V
LD
L
,
a
n
d
B
M
I
)
O
u
t
p
u
t
:
Ta
r
g
e
t
c
l
a
ss
1.
C
o
n
v
e
r
t
t
h
e
t
a
r
g
e
t
i
n
t
o
c
a
t
e
g
o
r
i
c
a
l
d
a
t
a
2.
S
p
l
i
t
t
h
e
d
a
t
a
s
e
t
i
n
t
o
t
r
a
i
n
i
n
g
(
8
0
%) a
n
d
t
e
st
i
n
g
(
2
0
%) s
u
b
s
e
t
s
3.
D
e
f
i
n
e
h
y
p
e
r
p
a
r
a
met
e
r
t
u
n
i
n
g
-
M
i
n
i
m
u
m
l
e
a
f
s
i
z
e
-
M
a
x
i
m
u
m
n
u
m
b
e
r
o
f
s
p
l
i
t
s
-
S
p
l
i
t
c
r
i
t
e
r
i
o
n
4.
Tr
a
i
n
t
h
e
C
A
R
T
m
o
d
e
l
u
si
n
g
t
h
e
t
r
a
i
n
i
n
g
f
e
a
t
u
r
e
s
a
n
d
t
a
r
g
e
t
w
i
t
h
t
h
e
d
e
f
i
n
e
d
h
y
p
e
r
p
a
r
a
met
e
r
s
5.
P
e
r
f
o
r
ma
n
c
e
o
f
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
b
a
se
d
o
n
e
v
a
l
u
a
t
i
o
n
met
r
i
c
s
:
-
Co
n
f
u
s
i
o
n
ma
t
r
i
x
-
A
c
c
u
r
a
c
y
:
t
h
e
o
v
e
r
a
l
l
c
o
r
r
e
c
t
p
r
e
d
i
c
t
i
o
n
s
-
P
r
e
c
i
s
i
o
n
:
e
m
p
h
a
si
z
e
s
t
h
e
a
c
c
u
r
a
c
y
o
f
p
o
si
t
i
v
e
p
r
e
d
i
c
t
i
o
n
s
-
R
e
c
a
l
l
:
t
h
e
a
b
i
l
i
t
y
t
o
f
i
n
d
a
l
l
p
o
si
t
i
v
e
c
a
ses
-
F1
-
sc
o
r
e
:
b
a
l
a
n
c
e
s
b
e
t
w
e
e
n
p
r
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
-
R
O
C
-
A
U
C
c
u
r
v
e
:
a
n
a
l
y
z
e
s m
o
d
e
l
p
e
r
f
o
r
man
c
e
a
t
v
a
r
i
o
u
s t
h
r
e
s
h
o
l
d
s
6.
S
a
v
e
a
n
d
si
m
u
l
a
t
e
t
h
e
t
r
a
i
n
e
d
m
o
d
e
l
7.
P
r
o
mp
t
t
h
e
u
ser
t
o
i
n
p
u
t
d
a
t
a
-
G
e
n
d
e
r
(
0
f
o
r
ma
l
e
,
1
f
o
r
f
e
mal
e
)
-
A
g
e
(
i
n
y
e
a
r
s)
-
U
r
e
a
l
e
v
e
l
(
i
n
m
g
d
l
/
L)
-
C
r
e
a
t
i
n
i
n
e
l
e
v
e
l
(
i
n
mm
o
l
/
L)
-
H
b
A
1
c
l
e
v
e
l
(
i
n
mm
o
l
/
L)
-
Tr
i
g
l
y
c
e
r
i
d
e
(
i
n
mm
o
l
/
L)
-
H
i
g
h
-
d
e
n
s
i
t
y
l
i
p
o
p
r
o
t
e
i
n
(
i
n
m
mo
l
/
L)
-
Lo
w
-
d
e
n
s
i
t
y
l
i
p
o
p
r
o
t
e
i
n
(
i
n
mm
o
l
/
L)
-
V
e
r
y
L
o
w
-
d
e
n
s
i
t
y
l
i
p
o
p
r
o
t
e
i
n
(
i
n
mm
o
l
/
L)
-
B
o
d
y
M
a
ss I
n
d
e
x
8.
P
r
e
p
a
r
i
n
g
d
a
t
a
f
o
r
p
r
e
d
i
c
t
i
o
n
-
N
o
r
mal
i
z
a
t
i
o
n
u
si
n
g
m
e
a
n
s
a
n
d
s
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
v
a
l
u
e
s
9.
D
i
sp
l
a
y
s t
h
e
p
r
e
d
i
c
t
i
o
n
r
e
s
u
l
t
t
o
t
h
e
u
s
er
-
0
:
N
o
n
-
d
i
a
b
e
t
i
c
,
1
:
P
r
e
-
d
i
a
b
e
t
i
c
,
2
:
D
i
a
b
e
t
i
c
1
0
.
En
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
20
7
-
21
6
212
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
o
v
er
all
f
in
d
in
g
s
an
d
co
r
r
esp
o
n
d
i
n
g
d
is
cu
s
s
io
n
.
Firstl
y
,
in
s
u
b
s
e
ctio
n
3
.
1
.
1
,
th
e
b
est
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
s
ettin
g
th
at
im
p
r
o
v
ed
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
is
d
is
cu
s
s
ed
.
I
n
s
u
b
s
ec
tio
n
3
.
1
.
2
,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
d
ev
el
o
p
ed
m
o
d
el
th
r
o
u
g
h
th
e
e
v
alu
atio
n
m
etr
ics
is
ex
p
lain
ed
.
Fi
n
ally
,
in
s
u
b
s
ec
tio
n
3
.
1
.
3
,
th
e
o
u
tco
m
es a
f
ter
in
s
er
tin
g
th
e
in
f
o
r
m
atio
n
in
to
th
e
m
o
d
el
d
e
p
lo
y
m
e
n
t a
r
e
d
is
cu
s
s
ed
.
3
.
1
.
Res
ults
T
h
is
s
tu
d
y
in
v
esti
g
ated
th
e
ef
f
ec
tiv
en
ess
o
f
d
iab
etes
p
r
e
d
ictio
n
u
s
in
g
a
n
ML
m
o
d
el
ap
p
r
o
ac
h
,
n
am
ely
th
e
C
AR
T
m
o
d
el.
Un
lik
e
th
e
p
r
io
r
r
esear
ch
,
wh
ich
h
ad
v
er
y
m
o
d
er
ate
p
er
f
o
r
m
a
n
ce
an
d
f
r
e
q
u
en
tl
y
f
o
cu
s
ed
o
n
b
in
a
r
y
class
if
icatio
n
,
th
is
s
tu
d
y
attem
p
ted
to
p
r
ed
ict
th
r
ee
s
ep
ar
ate
d
iab
ete
s
co
n
d
itio
n
s
:
n
o
n
-
d
iab
etic,
p
r
e
-
d
iab
etic,
an
d
d
ia
b
etic.
3
.
1
.
1
.
H
y
perpa
ra
m
et
er
t
uning
T
ab
le
3
s
h
o
ws
th
e
b
est
h
y
p
e
r
p
ar
am
eter
tu
n
in
g
s
ettin
g
f
o
r
th
e
m
o
d
el.
Valu
es
o
f
5
an
d
1
0
wer
e
s
elec
ted
f
o
r
th
e
n
u
m
b
er
o
f
leav
es
p
er
n
o
d
e
an
d
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
s
p
lits
,
r
esp
ec
tiv
ely
,
wh
ile
th
e
s
p
lit
cr
iter
io
n
m
etr
ic
was
d
ev
ia
n
ce
.
T
h
is
h
y
p
er
p
ar
am
eter
tu
n
in
g
ca
n
i
n
cr
ea
s
e
ac
cu
r
ac
y
a
n
d
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
m
u
ltip
le
ev
alu
atio
n
m
etr
ics.
T
ab
le
3
.
T
h
e
b
est h
y
p
er
p
ar
a
m
eter
tu
n
in
g
s
ettin
g
f
o
r
t
h
e
m
o
d
e
l
Th
e
b
e
st
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
p
a
r
a
met
e
r
s
N
u
mb
e
r
o
f
l
e
a
v
e
s
p
e
r
n
o
d
e
5
M
a
x
i
m
u
m
n
u
m
b
e
r
o
f
s
p
l
i
t
s
10
S
p
l
i
t
c
r
i
t
e
r
i
o
n
D
e
v
i
a
n
c
e
On
th
e
o
th
er
h
an
d
,
s
ettin
g
s
wi
th
th
e
co
m
b
in
atio
n
o
f
v
alu
es
o
th
er
th
an
5
an
d
1
0
,
as
well
as
o
th
er
th
an
d
ev
ian
ce
,
d
id
n
o
t
p
er
f
o
r
m
well,
with
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
r
an
g
i
n
g
f
r
o
m
8
5
%
to
9
3
%.
Fo
r
ex
am
p
le,
th
e
co
m
b
in
atio
n
o
f
th
e
v
alu
e
o
f
2
f
o
r
th
e
n
u
m
b
er
o
f
leav
es
p
er
n
o
d
e,
th
e
v
alu
e
o
f
2
0
f
o
r
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
s
p
lits
,
an
d
Gin
i
f
o
r
th
e
s
p
lit
cr
iter
io
n
s
h
o
ws
a
n
ac
cu
r
ac
y
o
f
9
1
.
6
7
%,
with
s
lig
h
tly
lo
w
er
r
ec
all
an
d
a
f
ew
m
is
class
if
icatio
n
s
f
o
r
class
1
an
d
class
2.
3
.
1
.
2
.
P
er
f
o
r
m
a
nce
o
f
ev
a
lua
t
io
n m
et
rics
I
n
th
is
s
u
b
s
ec
tio
n
,
th
e
ex
p
er
i
m
en
tal
r
esu
lts
o
b
tain
ed
af
ter
tr
ain
in
g
th
e
d
iab
etes
d
ataset
u
s
in
g
th
e
p
r
o
p
o
s
ed
C
AR
T
m
u
lticlas
s
if
ie
r
m
o
d
el
ar
e
d
escr
ib
e
d
.
T
a
b
le
4
r
ep
r
esen
ts
th
e
r
esu
lt
o
f
th
e
c
o
n
f
u
s
io
n
m
atr
ix
f
o
r
c
lass
0
,
wh
er
e
th
e
m
o
d
el
ac
c
u
r
ately
id
en
tifie
d
1
7
o
cc
u
r
r
e
n
ce
s
,
with
n
o
m
is
class
if
icatio
n
s
o
f
o
th
e
r
class
es.
I
n
ad
d
itio
n
,
1
0
o
cc
u
r
r
en
ce
s
in
c
lass
1
wer
e
ap
p
r
o
p
r
iately
cl
ass
if
ied
.
L
astl
y
,
th
e
m
o
d
el
co
r
r
ec
tly
id
en
tifie
d
2
0
s
am
p
les f
o
r
class
2
,
with
o
n
ly
o
n
e
m
is
class
if
ied
as c
lass
0.
T
ab
le
4
.
R
esu
lt f
o
r
m
u
lticlas
s
co
n
f
u
s
io
n
m
atr
ix
P
r
e
d
i
c
t
e
d
c
l
a
ss
Tr
u
e
c
l
a
ss
C
l
a
s
s
0
C
l
a
s
s
1
C
l
a
s
s
2
To
t
a
l
C
l
a
s
s
0
17
0
0
17
C
l
a
s
s
1
0
10
0
10
C
l
a
s
s
2
1
0
20
21
To
t
a
l
18
10
20
48
T
ab
le
5
r
ep
r
esen
ts
th
e
p
er
f
o
r
m
an
ce
m
ea
s
u
r
em
en
ts
o
f
th
e
C
AR
T
m
u
lticla
s
s
if
ier
m
o
d
el,
ev
alu
ated
ac
r
o
s
s
th
r
ee
class
es
(
0
,
1
,
an
d
2
)
b
ased
o
n
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
e
m
o
d
el
’
s
to
tal
ac
cu
r
ac
y
was
9
7
%,
s
u
g
g
esti
n
g
th
at
p
r
ed
ictio
n
s
f
o
r
a
ll
class
es
wer
e
co
r
r
ec
t.
Fo
r
c
lass
0
,
th
e
m
o
d
el
ac
h
iev
ed
9
4
%
p
r
ec
is
io
n
,
in
d
i
ca
tin
g
th
at
th
e
p
r
ed
ictio
n
was
co
r
r
ec
t.
R
ec
all
wa
s
p
er
f
ec
t
a
t
1
0
0
%,
in
d
icatin
g
th
at
th
e
m
o
d
el
ac
cu
r
ately
r
e
co
g
n
ized
all
in
s
tan
ce
s
o
f
c
lass
0
,
an
d
th
e
F1
-
s
co
r
e
was
9
7
%,
s
u
g
g
esti
n
g
a
b
alan
ce
d
p
er
f
o
r
m
a
n
ce
f
o
r
th
is
class
.
T
h
e
m
o
d
el
p
er
f
o
r
m
ed
v
er
y
well
f
o
r
c
lass
1
,
with
1
0
0
%
f
o
r
th
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
m
etr
ics,
s
u
g
g
esti
n
g
f
au
ltles
s
clas
s
if
ica
tio
n
f
o
r
f
alse
p
o
s
itiv
es
o
r
n
eg
ativ
es.
Fo
r
c
lass
2
,
th
e
m
o
d
el
o
b
tain
ed
a
p
r
ec
is
io
n
o
f
1
0
0
%,
i
n
d
icatin
g
t
h
at
all
ca
s
es
p
r
ed
icted
as
c
lass
2
wer
e
p
r
ec
is
e.
Al
th
o
u
g
h
th
e
r
ec
all
an
d
F1
-
s
co
r
e
v
alu
es
wer
e
a
l
ittl
e
lo
wer
,
ar
o
u
n
d
9
5
%
an
d
9
8
%,
r
esp
ec
tiv
ely
,
th
is
s
til
l
in
d
icate
d
a
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
in
th
is
class
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
C
la
s
s
i
fica
tio
n
a
n
d
r
eg
r
ess
io
n
tr
ee
mo
d
el
fo
r
d
ia
b
etes p
r
ed
ic
tio
n
(
F
a
r
a
h
N
a
jid
a
h
N
o
o
r
iz
a
n
)
213
T
ab
le
5
.
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
m
en
t
o
f
th
e
C
AR
T
m
u
lticlas
s
i
f
ier
m
o
d
el
C
l
a
s
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
-
sc
o
r
e
(
%)
0
94
1
0
0
97
1
97
1
0
0
1
0
0
1
0
0
2
1
0
0
95
98
Fig
u
r
e
3
d
ep
icts
th
e
r
esu
lt
o
f
t
h
e
R
OC
-
AU
C
cu
r
v
e
o
f
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
.
T
h
e
AUC
v
alu
e
f
o
r
c
lass
1
was
1
,
in
d
icatin
g
th
e
m
o
d
el
s
u
cc
ess
f
u
lly
d
if
f
er
e
n
t
iated
th
is
class
f
r
o
m
th
e
o
th
er
class
es
with
n
o
m
is
class
if
icatio
n
.
Als
o
,
th
e
v
alu
es
f
o
r
c
lass
0
an
d
c
lass
2
wer
e
0
.
9
8
an
d
0
.
9
9
,
r
esp
ec
t
iv
ely
,
s
u
g
g
esti
n
g
a
n
ea
r
ly
p
e
r
f
ec
t sep
ar
atio
n
with
a
s
m
all
p
o
s
s
ib
ilit
y
o
f
m
is
class
i
f
icatio
n
.
Fig
u
r
e
3
.
T
h
e
R
OC
-
AUC
c
u
r
v
e
3
.
1
.
3
.
Deplo
y
m
ent
o
utc
o
m
es
B
io
g
r
ap
h
ical
in
f
o
r
m
atio
n
an
d
h
ea
lth
d
ata
ca
n
b
e
u
s
ed
to
d
eter
m
in
e
th
is
m
o
d
el
’
s
f
u
n
cti
o
n
ality
in
id
en
tify
in
g
a
p
atien
t
’
s
d
iab
ete
s
s
tatu
s
.
I
n
th
is
s
u
b
s
ec
tio
n
,
th
e
r
esu
lt
o
f
th
e
d
e
p
lo
y
e
d
d
iab
ete
s
p
r
ed
ictio
n
m
o
d
el
af
ter
r
ec
eiv
in
g
u
s
er
in
p
u
t,
as
d
ep
icted
in
Fig
u
r
e
4
,
is
d
escr
i
b
ed
.
T
h
e
m
o
d
el
was
s
im
u
lated
u
s
in
g
d
ata
f
r
o
m
a
40
-
y
ea
r
-
o
ld
f
e
m
ale
p
atien
t,
with
a
B
MI
o
f
2
4
an
d
a
h
em
o
g
lo
b
in
lev
el
o
f
5
.
4
m
m
o
l/L.
T
h
e
r
esu
lt sh
o
ws a
cla
s
s
o
f
0
,
m
ea
n
in
g
t
h
at
th
e
p
atie
n
t
is
n
o
t
in
th
e
ca
teg
o
r
y
o
f
d
iab
etics.
I
n
ad
d
itio
n
,
th
is
p
r
ed
icted
s
ce
n
ar
io
o
f
non
-
d
iab
etic
ca
n
b
e
p
r
o
v
e
d
,
a
s
th
e
p
atien
t
’
s
n
o
r
m
al
g
l
u
co
s
e
lev
el
is
b
elo
w
5
.
7
m
m
o
l/L
a
n
d
th
e
B
MI
o
f
2
4
is
with
in
th
e
n
o
r
m
al
r
an
g
e.
Fig
u
r
e
4
.
T
h
e
d
e
p
lo
y
m
e
n
t o
u
t
co
m
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
20
7
-
21
6
214
3
.
2
.
Dis
cus
s
io
n
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
in
t
h
is
s
tu
d
y
was
s
h
o
wn
to
h
av
e
o
u
ts
tan
d
in
g
p
er
f
o
r
m
a
n
ce
in
p
r
ed
ictin
g
d
iab
etes
ac
r
o
s
s
th
e
th
r
ee
ca
teg
o
r
ies,
with
an
o
v
e
r
all
ac
cu
r
ac
y
o
f
9
7
%.
I
t
g
r
ea
tly
o
u
tp
er
f
o
r
m
e
d
o
th
er
ML
m
o
d
els,
s
u
ch
as
SVM,
KNN,
an
d
DT
,
w
h
ich
h
a
d
ac
cu
r
ac
y
r
ates
r
an
g
in
g
f
r
o
m
7
0
%
to
9
0
%
[
1
1
]
,
[
1
3
]
,
[
2
9
]
.
E
ac
h
cla
s
s
also
h
ad
s
tr
o
n
g
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
v
alu
es,
esp
ec
ially
c
lass
1
(
with
n
o
m
is
class
if
icatio
n
)
.
T
h
ese
f
in
d
i
n
g
s
s
u
p
p
o
r
t
th
e
m
o
d
el
’
s
ca
p
ac
ity
to
h
an
d
le
m
u
lticlas
s
clas
s
if
icatio
n
ef
f
ec
tiv
ely
,
p
ar
ticu
lar
ly
with
im
b
ala
n
ce
d
d
atasets
.
Pre
v
io
u
s
s
tu
d
ies
[
1
1
]
,
[
1
2
]
s
im
u
lated
th
e
d
ataset
u
s
in
g
a
tr
ain
in
g
an
d
test
in
g
s
p
lit,
as
well
as
a
v
alid
atio
n
s
tep
to
ev
alu
ate
th
e
m
o
d
el
’
s
p
er
f
o
r
m
a
n
ce
.
Ho
w
ev
er
,
th
ese
s
tu
d
ies
d
id
n
o
t
e
m
p
h
asize
s
y
s
tem
atic
tu
n
in
g
o
f
m
o
d
el
p
ar
a
m
eter
s
,
wh
ich
r
esu
lted
in
p
o
o
r
p
r
e
d
ic
tio
n
p
er
f
o
r
m
a
n
ce
.
T
h
er
ef
o
r
e,
o
u
r
s
tu
d
y
s
u
g
g
ests
th
at
ex
ce
llen
t
ac
cu
r
ac
y
an
d
b
a
lan
ce
d
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
class
e
s
ar
e
d
u
e
to
th
e
s
u
cc
ess
f
u
l
co
m
b
in
atio
n
o
f
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
o
p
tim
al
h
y
p
er
p
a
r
am
eter
tu
n
in
g
,
an
d
th
e
u
s
e
o
f
d
ev
iatio
n
as
th
e
s
p
lit
cr
iter
io
n
.
T
h
e
s
ettin
g
o
f
th
e
n
u
m
b
er
o
f
leav
es
a
n
d
th
e
m
ax
im
u
m
n
u
m
b
e
r
o
f
s
p
lits
ass
is
ts
in
cr
ea
tin
g
a
DT
t
h
at
is
n
eith
er
u
n
d
er
f
itted
n
o
r
o
v
e
r
f
itted
.
I
n
a
d
d
itio
n
,
d
e
v
ian
ce
,
wh
ich
is
r
ec
o
g
n
ized
f
o
r
d
ea
lin
g
with
u
n
e
v
en
class
d
is
tr
ib
u
tio
n
s
,
h
elp
s
th
e
m
o
d
el
to
d
is
cr
im
in
ate
b
et
wee
n
b
o
r
d
er
lin
e
in
s
tan
ce
s
.
T
h
is
s
tu
d
y
e
x
p
lo
r
ed
a
m
o
d
el
f
o
r
d
iab
etes
s
tatu
s
p
r
e
d
ictio
n
b
ased
o
n
clin
ical
d
ata,
w
h
ich
p
er
f
o
r
m
e
d
well
ac
r
o
s
s
th
r
ee
class
es.
Ho
wev
er
,
s
ev
er
al
c
o
n
s
tr
ain
ts
s
h
o
u
ld
b
e
c
o
n
s
id
er
ed
,
s
u
ch
as
th
e
f
ac
t
th
at
a
d
ataset
th
at
co
n
tain
s
m
an
y
s
u
b
ject
s
,
b
u
t
is
b
ased
o
n
a
s
in
g
le
p
o
p
u
lat
io
n
g
r
o
u
p
,
m
ay
lim
it
th
e
m
o
d
el
’
s
ap
p
licab
ilit
y
to
o
th
er
eth
n
icities
o
r
ar
ea
s
.
Fu
r
th
er
m
o
r
e,
e
x
clu
d
in
g
b
eh
a
v
io
r
al
o
r
life
s
ty
le
f
ac
to
r
s
m
ay
d
e
cr
ea
s
e
th
e
m
o
d
el
’
s
p
r
ed
ictiv
e
p
o
wer
.
Fin
ally
,
th
e
cu
r
r
en
t
d
ep
lo
y
m
en
t
ar
r
an
g
em
en
t
r
eq
u
ir
es
m
an
u
al
in
p
u
t
,
wh
ich
m
ig
h
t
b
e
im
p
r
o
v
e
d
with
au
to
m
atio
n
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
in
clin
ic
al
s
itu
atio
n
s
.
4.
CO
NCLU
SI
O
N
I
n
c
o
n
clu
s
io
n
,
th
is
s
tu
d
y
f
o
u
n
d
th
at
th
e
C
AR
T
m
u
lticlas
s
if
ier
m
o
d
el
is
a
d
e
p
en
d
a
b
le
an
d
ac
cu
r
ate
tech
n
iq
u
e
to
p
r
e
d
ict
d
iab
etes
s
ta
tu
s
u
s
in
g
clin
ical
ch
ar
ac
ter
i
s
tics
.
T
h
e
m
o
d
el
ac
h
iev
ed
g
r
e
at
o
v
er
all
ac
cu
r
ac
y
b
y
co
m
b
i
n
in
g
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
o
p
tim
al
h
y
p
er
p
ar
a
m
eter
tu
n
in
g
,
an
d
th
e
u
s
e
o
f
d
ev
i
atio
n
as
th
e
s
p
lit
cr
iter
io
n
.
T
h
e
m
o
d
el
’
s
r
e
m
ar
k
ab
le
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
v
ar
io
u
s
ev
alu
atio
n
p
ar
a
m
ete
r
s
u
n
d
er
lin
es
its
p
o
ten
tial
f
o
r
ea
r
ly
s
cr
ee
n
in
g
a
n
d
clin
ica
l d
ec
is
io
n
s
u
p
p
o
r
t.
I
n
th
e
f
u
tu
r
e,
th
is
p
r
o
ject
c
o
u
l
d
b
e
im
p
r
o
v
e
d
b
y
d
e
v
elo
p
in
g
a
u
s
er
-
f
r
ie
n
d
ly
g
r
ap
h
ical
u
s
er
in
ter
f
ac
e
(
GUI
)
to
b
o
o
s
t
th
e
o
p
er
atio
n
o
f
th
e
d
iab
etes
p
r
ed
ictio
n
m
o
d
el.
T
h
is
GUI
allo
ws
u
s
er
s
to
ea
s
ily
,
s
w
if
tly
,
an
d
s
y
s
tem
atica
lly
en
ter
all
th
eir
p
er
s
o
n
al
a
n
d
h
ea
lth
in
f
o
r
m
ati
o
n
to
in
s
tan
tly
d
eter
m
in
e
th
e
ir
d
iab
etes
s
tatu
s
.
Fu
r
th
er
m
o
r
e
,
a
v
is
u
al
in
ter
f
ac
e,
s
u
ch
as
f
u
tu
r
e
h
ea
lth
ca
r
e
-
r
e
lated
ac
tio
n
s
,
ca
n
b
e
ad
d
ed
,
m
ak
in
g
th
is
to
o
l
ev
e
n
m
o
r
e
b
e
n
ef
icial
to
th
e
h
ea
lth
c
ar
e
co
m
m
u
n
ity
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
is
r
esear
ch
was
s
u
p
p
o
r
ted
b
y
Un
iv
er
s
iti
T
u
n
Hu
s
s
ein
On
n
Ma
lay
s
ia
(
UT
HM
)
th
r
o
u
g
h
GPPS
(
v
o
t
Q6
4
4
)
a
n
d
L
ea
v
e
a
Nest C
o
.
,
L
td
.
th
r
o
u
g
h
in
ter
n
atio
n
al
g
r
a
n
ts
(
v
o
t X
3
1
1
an
d
v
o
t X
3
2
4
)
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
f
u
n
d
in
g
in
f
o
r
m
atio
n
ca
n
b
e
r
ef
er
r
e
d
to
in
t
h
e
ac
k
n
o
wled
g
em
en
t sectio
n
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
t
es,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Far
ah
Najid
ah
No
o
r
iza
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nu
r
An
id
a
J
u
m
ad
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ng
L
i M
u
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
C
la
s
s
i
fica
tio
n
a
n
d
r
eg
r
ess
io
n
tr
ee
mo
d
el
fo
r
d
ia
b
etes p
r
ed
ic
tio
n
(
F
a
r
a
h
N
a
jid
a
h
N
o
o
r
iz
a
n
)
215
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
co
n
f
ir
m
th
at
th
e
i
s
n
o
co
n
f
lict
o
f
in
ter
est r
elate
d
to
th
e
m
an
u
s
cr
ip
t.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
e
n
ly
av
ailab
le
in
th
e
Me
n
d
eley
r
ep
o
s
ito
r
y
at
d
o
i: 1
0
.
1
3
7
1
/jo
u
r
n
al.
p
o
n
e.
0
3
0
0
7
8
5
.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
A
.
M
o
h
sh
i
m,
N
.
F
.
N
.
N
a
si
r
u
d
d
i
n
,
Z.
Z
a
k
a
r
i
a
,
H
.
M
.
D
e
sa
,
D
.
F
.
M
o
h
sh
i
m
,
a
n
d
M
.
F
.
F
a
d
z
i
r
,
“
N
o
n
-
i
n
v
a
si
v
e
b
l
o
o
d
g
l
u
c
o
s
e
mo
n
i
t
o
r
u
s
i
n
g
a
r
d
u
i
n
o
f
o
r
c
l
i
n
i
c
a
l
u
se,
”
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
T
e
c
h
n
o
p
re
n
e
u
rs
h
i
p
,
I
C
E2
T
2
0
2
3
,
p
p
.
2
1
9
–
2
2
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
E2
T
5
8
6
3
7
.
2
0
2
3
.
1
0
5
4
0
5
1
4
.
[
2
]
E.
U
.
D
e
w
i
,
N
.
P
.
W
i
d
a
r
i
,
N
u
r
sa
l
a
m
,
M
a
h
m
u
d
a
h
,
E
.
Y
.
S
a
r
i
,
a
n
d
Y
.
F
.
N
.
S
u
si
a
n
a
,
“
T
h
e
r
e
l
a
t
i
o
n
sh
i
p
b
e
t
w
e
e
n
d
i
a
b
e
t
e
s
se
l
f
-
c
a
r
e
man
a
g
e
me
n
t
a
n
d
b
l
o
o
d
g
l
u
c
o
se
l
e
v
e
l
a
m
o
n
g
t
y
p
e
2
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
p
a
t
i
e
n
t
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Pu
b
l
i
c
H
e
a
l
t
h
S
c
i
e
n
c
e
(
I
J
PH
S
)
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
1
1
6
5
–
1
1
7
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
p
h
s.
v
1
2
i
3
.
2
2
2
2
8
.
[
3
]
M
.
N
a
r
e
s
h
,
V
.
S
.
N
a
g
a
r
a
j
u
,
S
.
K
o
l
l
e
m,
J
.
K
u
mar
,
a
n
d
S
.
P
e
d
d
a
k
r
i
sh
n
a
,
“
N
o
n
-
i
n
v
a
s
i
v
e
g
l
u
c
o
s
e
p
r
e
d
i
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
N
I
R
t
e
c
h
n
o
l
o
g
y
w
i
t
h
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
8
7
2
0
.
[
4
]
E.
M
a
n
s
o
u
r
e
t
a
l
.
,
“
R
e
v
i
e
w
o
n
n
o
n
-
i
n
v
a
si
v
e
e
l
e
c
t
r
o
ma
g
n
e
t
i
c
a
p
p
r
o
a
c
h
e
s
f
o
r
b
l
o
o
d
g
l
u
c
o
se
mo
n
i
t
o
r
i
n
g
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
1
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
J
a
p
a
n
-
Af
r
i
c
a
C
o
n
f
e
re
n
c
e
o
n
E
l
e
c
t
r
o
n
i
c
s
,
C
o
m
m
u
n
i
c
a
t
i
o
n
s,
a
n
d
C
o
m
p
u
t
a
t
i
o
n
s,
J
A
C
-
EC
C
2
0
2
3
,
p
p
.
2
7
3
–
2
7
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JA
C
-
EC
C
6
1
0
0
2
.
2
0
2
3
.
1
0
4
7
9
6
2
0
.
[
5
]
B
.
C
h
i
t
r
a
d
e
v
i
,
S
u
p
r
i
y
a
,
N
.
S
.
C
h
a
n
d
r
a
,
T.
N
.
C
h
i
t
r
a
d
e
v
i
,
a
n
d
H
.
A
l
a
b
d
e
l
i
,
“
D
i
a
b
e
t
e
s
mel
l
i
t
u
s
p
r
e
d
i
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
f
i
r
e
f
l
y
o
p
t
i
mi
z
a
t
i
o
n
-
b
a
se
d
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
i
s
t
ri
b
u
t
e
d
C
o
m
p
u
t
i
n
g
a
n
d
O
p
t
i
m
i
z
a
t
i
o
n
T
e
c
h
n
i
q
u
e
s
,
I
C
D
C
O
T
2
0
2
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
C
O
T6
1
0
3
4
.
2
0
2
4
.
1
0
5
1
5
3
9
7
.
[
6
]
A
.
M
a
e
n
g
e
,
T
.
S
i
g
w
e
l
e
,
C
.
B
h
e
n
d
e
,
C
.
M
o
k
g
e
t
h
i
,
V
.
K
u
t
h
a
d
i
,
a
n
d
B
.
O
mo
g
b
e
h
i
n
,
“
O
p
t
i
m
i
z
i
n
g
d
i
a
b
e
t
e
s p
r
e
d
i
c
t
i
o
n
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
:
a
r
a
n
d
o
m
f
o
r
e
st
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
s
i
n
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
I
J
AA
S
)
,
v
o
l
.
1
4
,
n
o
.
2
,
p
.
4
5
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
a
s.
v
1
4
.
i
2
.
p
p
4
5
4
-
4
6
8
.
[
7
]
M
.
Te
j
e
d
o
r
,
A
.
Z.
W
o
l
d
a
r
e
g
a
y
,
a
n
d
F
.
G
o
d
t
l
i
e
b
se
n
,
“
R
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
i
n
d
i
a
b
e
t
e
s
b
l
o
o
d
g
l
u
c
o
se
c
o
n
t
r
o
l
:
a
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
1
0
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
t
me
d
.
2
0
2
0
.
1
0
1
8
3
6
.
[
8
]
L.
Ta
n
g
,
S
.
J.
C
h
a
n
g
,
C
.
J.
C
h
e
n
,
a
n
d
J.
T.
Li
u
,
“
N
o
n
-
i
n
v
a
si
v
e
b
l
o
o
d
g
l
u
c
o
s
e
m
o
n
i
t
o
r
i
n
g
t
e
c
h
n
o
l
o
g
y
:
a
r
e
v
i
e
w
,
”
S
e
n
so
rs (S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
2
3
,
p
p
.
1
–
3
2
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
2
3
6
9
2
5
.
[
9
]
A
.
S
.
B
o
l
l
a
a
n
d
R
.
P
r
i
e
f
e
r
,
“
B
l
o
o
d
g
l
u
c
o
se
m
o
n
i
t
o
r
i
n
g
-
a
n
o
v
e
r
v
i
e
w
o
f
c
u
r
r
e
n
t
a
n
d
f
u
t
u
r
e
n
o
n
-
i
n
v
a
si
v
e
d
e
v
i
c
e
s
,
”
D
i
a
b
e
t
e
s
a
n
d
Me
t
a
b
o
l
i
c
S
y
n
d
r
o
m
e
:
C
l
i
n
i
c
a
l
R
e
se
a
r
c
h
a
n
d
Re
v
i
e
w
s
,
v
o
l
.
1
4
,
n
o
.
5
,
p
p
.
7
3
9
–
7
5
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
s
x
.
2
0
2
0
.
0
5
.
0
1
6
.
[
1
0
]
K
.
Li
u
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
b
l
o
o
d
g
l
u
c
o
se
l
e
v
e
l
p
r
e
d
i
c
t
i
o
n
i
n
p
a
t
i
e
n
t
s
w
i
t
h
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
:
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
a
n
d
n
e
t
w
o
r
k
me
t
a
-
a
n
a
l
y
si
s
,
”
J
MIR
M
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
2
1
9
6
/
4
7
8
3
3
.
[
1
1
]
A
.
C
.
L
y
n
g
d
o
h
,
N
.
A
.
C
h
o
u
d
h
u
r
y
,
a
n
d
S
.
M
o
u
l
i
k
,
“
D
i
a
b
e
t
e
s d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s,”
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
0
I
EE
E
E
MB
S
C
o
n
f
e
re
n
c
e
o
n
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
S
c
i
e
n
c
e
s,
I
EC
B
ES
2
0
2
0
,
p
p
.
5
1
7
–
5
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
EC
B
ES
4
8
1
7
9
.
2
0
2
1
.
9
3
9
8
7
5
9
.
[
1
2
]
N
.
M
o
h
a
n
a
n
d
V
.
Ja
i
n
,
“
P
e
r
f
o
r
man
c
e
a
n
a
l
y
s
i
s
o
f
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
i
n
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
,
”
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
EC
A
4
9
3
1
3
.
2
0
2
0
.
9
2
9
7
4
1
1
.
[
1
3
]
L.
J.
M
u
h
a
mm
a
d
,
E
.
A
.
A
l
g
e
h
y
n
e
,
a
n
d
S
.
S
.
U
sm
a
n
,
“
P
r
e
d
i
c
t
i
v
e
s
u
p
e
r
v
i
se
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
d
i
a
b
e
t
e
s
mel
l
i
t
u
s,”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
,
n
o
.
5
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
0
2
0
-
0
0
2
5
0
-
8.
[
1
4
]
J.
J.
K
h
a
n
a
m
a
n
d
S
.
Y
.
F
o
o
,
“
A
c
o
m
p
a
r
i
s
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
,
”
I
C
T
E
x
p
ress
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
4
3
2
–
4
3
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
c
t
e
.
2
0
2
1
.
0
2
.
0
0
4
.
[
1
5
]
D
.
K
a
v
e
r
i
p
a
k
a
m
a
n
d
J
.
R
a
v
i
c
h
a
n
d
r
a
n
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
d
i
a
b
e
t
i
c
d
i
se
a
s
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
s
e
a
r
c
h
i
n
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
a
n
d
E
n
g
i
n
e
e
r
i
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
4
0
–
5
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
7
9
3
4
/
a
r
a
se
t
.
4
5
.
1
.
4
0
5
0
.
[
1
6
]
N
.
A
h
m
e
d
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
s
e
d
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
a
n
d
d
e
v
e
l
o
p
me
n
t
o
f
sm
a
r
t
w
e
b
a
p
p
l
i
c
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
,
p
p
.
2
2
9
–
2
4
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
c
c
e
.
2
0
2
1
.
1
2
.
0
0
1
.
[
1
7
]
L.
Zh
a
n
g
,
Y
.
W
a
n
g
,
M
.
N
i
u
,
C
.
W
a
n
g
,
a
n
d
Z
.
W
a
n
g
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
c
h
a
r
a
c
t
e
r
i
z
i
n
g
r
i
s
k
o
f
t
y
p
e
2
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
i
n
a
r
u
r
a
l
C
h
i
n
e
se
p
o
p
u
l
a
t
i
o
n
:
t
h
e
H
e
n
a
n
R
u
r
a
l
C
o
h
o
r
t
S
t
u
d
y
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
0
,
n
o
.
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
020
-
6
1
1
2
3
-
x.
[
1
8
]
S
.
G
o
w
t
h
a
m
i
,
V
.
S
.
R
e
d
d
y
,
a
n
d
M
.
R
.
A
h
me
d
,
“
T
y
p
e
2
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s:
e
a
r
l
y
d
e
t
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
6
,
p
p
.
1
1
9
1
–
1
1
9
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
3
.
0
1
4
0
6
1
2
7
.
[
1
9
]
H
.
El
B
o
u
h
i
ssi
,
R
.
E.
A
l
-
Q
u
t
a
i
sh
,
A
.
Zi
a
n
e
,
K
.
A
mr
o
u
n
,
N
.
Y
a
y
a
,
a
n
d
M
.
La
c
h
i
,
“
To
w
a
r
d
s
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
p
r
e
d
i
c
t
i
o
n
b
a
se
d
o
n
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
rt
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
,
I
C
S
C
A
2
0
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
A
5
7
8
4
0
.
2
0
2
3
.
1
0
0
8
7
7
8
2
.
[
2
0
]
M
.
K
.
H
a
sa
n
,
M
.
A
.
A
l
a
m,
D
.
D
a
s,
E.
H
o
s
sai
n
,
a
n
d
M
.
H
a
sa
n
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
e
n
s
e
mb
l
i
n
g
o
f
d
i
f
f
e
r
e
n
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
7
6
5
1
6
–
7
6
5
3
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
8
9
8
5
7
.
[
2
1
]
R
.
S
a
x
e
n
a
,
S
.
K
.
S
h
a
r
m
a
,
M
.
G
u
p
t
a
,
a
n
d
G
.
C
.
S
a
mp
a
d
a
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
d
i
a
b
e
t
e
s
mel
l
i
t
u
s
:
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
8
2
0
3
6
0
.
[
2
2
]
B
.
N
a
t
a
r
a
j
a
n
,
S
.
R
.
D
i
w
a
k
a
r
,
R
.
A
n
n
a
ma
l
a
i
,
R
.
B
h
u
v
a
n
e
sw
a
r
i
,
a
n
d
S
.
S
.
H
u
sai
n
,
“
A
n
e
x
p
l
o
r
a
t
i
o
n
o
f
t
h
e
p
e
r
f
o
r
ma
n
c
e
u
si
n
g
e
n
s
e
mb
l
e
me
t
h
o
d
s
u
t
i
l
i
z
i
n
g
r
a
n
d
o
m
f
o
r
e
s
t
c
l
a
ssi
f
i
e
r
f
o
r
d
i
a
b
e
t
e
s
d
e
t
e
c
t
i
o
n
,
”
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
N
M
I
TC
O
N
5
8
1
9
6
.
2
0
2
3
.
1
0
2
7
6
3
4
8
.
[
2
3
]
A
.
A
.
A
l
z
u
b
a
i
d
i
,
S
.
M
.
H
a
l
a
w
a
n
i
,
a
n
d
M
.
Jarr
a
h
,
“
T
o
w
a
r
d
s
a
st
a
c
k
i
n
g
e
n
sem
b
l
e
m
o
d
e
l
f
o
r
p
r
e
d
i
c
t
i
n
g
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
u
si
n
g
c
o
m
b
i
n
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
1
2
,
p
p
.
3
4
8
–
3
5
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
3
.
0
1
4
1
2
3
6
.
[
2
4
]
A
.
A
.
A
l
z
u
b
a
i
d
i
,
S
.
M
.
H
a
l
a
w
a
n
i
,
a
n
d
M
.
J
a
r
r
a
h
,
“
I
n
t
e
g
r
a
t
e
d
e
n
sem
b
l
e
mo
d
e
l
f
o
r
d
i
a
b
e
t
e
s
me
l
l
i
t
u
s
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
5
,
n
o
.
4
,
p
p
.
2
2
3
–
2
3
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
4
.
0
1
5
0
4
2
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
20
7
-
21
6
216
[
2
5
]
P
.
T
h
o
t
a
d
,
G
.
R
.
B
h
a
r
a
m
a
g
o
u
d
a
r
,
a
n
d
B
.
S
.
A
n
a
mi
,
“
P
r
e
d
i
c
t
i
v
e
a
n
a
l
y
si
s
o
f
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
u
s
i
n
g
d
e
c
i
si
o
n
t
r
e
e
a
p
p
r
o
a
c
h
,
”
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
S
I
A
N
C
O
N
5
5
3
1
4
.
2
0
2
2
.
9
9
0
9
1
2
2
.
[
2
6
]
M
.
A
.
S
a
h
i
d
,
M
.
U
l
H
o
q
u
e
-
B
a
b
a
r
,
a
n
d
M
.
P
.
U
d
d
i
n
,
“
P
r
e
d
i
c
t
i
v
e
m
o
d
e
l
i
n
g
o
f
mu
l
t
i
-
c
l
a
ss
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
f
i
l
t
e
r
i
n
g
i
r
a
q
i
d
i
a
b
e
t
e
s
d
a
t
a
d
y
n
a
mi
c
s,
”
PL
o
S
O
N
E
,
v
o
l
.
1
9
,
n
o
.
5
M
a
y
,
2
0
2
4
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
3
0
0
7
8
5
.
[
2
7
]
I
.
D
.
M
i
e
n
y
e
a
n
d
N
.
J
e
r
e
,
“
A
s
u
r
v
e
y
o
f
d
e
c
i
si
o
n
t
r
e
e
s
:
c
o
n
c
e
p
t
s
,
a
l
g
o
r
i
t
h
ms,
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
8
6
7
1
6
–
8
6
7
2
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
4
1
6
8
3
8
.
[
2
8
]
M
o
n
i
c
a
a
n
d
P
.
A
g
r
a
w
a
l
,
“
A
S
u
r
v
e
y
o
n
H
y
p
e
r
p
a
r
a
m
e
t
e
r
o
p
t
i
mi
z
a
t
i
o
n
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
2
0
2
4
2
n
d
I
n
t
.
C
o
n
f
.
D
i
sr
u
p
t
i
v
e
T
e
c
h
n
o
l
.
I
C
D
T
2
0
2
4
,
p
p
.
1
1
–
1
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
T6
1
2
0
2
.
2
0
2
4
.
1
0
4
8
9
7
3
2
.
[
2
9
]
K
.
S
a
g
a
r
,
S
.
I
mt
i
y
a
z
,
A
.
A
r
v
i
n
d
h
,
A
.
S
.
N
a
g
a
r
a
j
u
,
C
.
R
.
P
r
a
s
a
d
,
a
n
d
P
.
K
.
K
u
mar
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
si
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
C
ET
6
1
5
1
6
.
2
0
2
4
.
1
0
5
9
3
3
6
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Fa
r
a
h
N
a
jid
a
h
No
o
r
iza
n
wa
s
b
o
rn
o
n
2
5
S
e
p
tem
b
e
r
1
9
9
9
i
n
Ke
d
a
h
,
M
a
lay
sia
.
S
h
e
p
u
rsu
e
d
h
e
r
d
ip
l
o
m
a
a
t
P
o
li
te
k
n
i
k
S
u
lt
a
n
S
a
lah
u
d
d
i
n
A
b
d
u
l
Az
iz
S
h
a
h
a
n
d
g
ra
d
u
a
te
d
wit
h
a
Dip
lo
m
a
in
M
e
d
ica
l
El
e
c
tro
n
i
c
En
g
in
e
e
rin
g
in
2
0
2
0
.
In
2
0
2
4
,
sh
e
re
c
e
iv
e
d
h
e
r
d
e
g
re
e
in
e
lec
tro
n
ic
e
n
g
i
n
e
e
rin
g
fro
m
Un
i
v
e
rsiti
Tu
n
Hu
ss
e
in
On
n
M
a
la
y
sia
(UTHM
).
S
h
e
is
n
o
w
c
o
n
ti
n
u
i
n
g
h
e
r
stu
d
ies
a
t
UTHM
fo
r
h
e
r
M
a
ste
r
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
.
He
r
m
a
in
re
se
a
rc
h
in
tere
sts
a
re
b
io
m
e
d
ica
l
e
n
g
i
n
e
e
rin
g
a
n
d
a
rti
ficia
l
in
tell
ig
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
fa
ra
h
n
a
ji
d
a
h
2
5
9
@g
m
a
il
.
c
o
m
.
Nur
Ani
d
a
J
u
m
a
d
i
is
a
n
a
s
so
c
iate
p
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
,
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
,
Un
iv
e
rsiti
T
u
n
H
u
ss
e
in
On
n
M
a
lay
sia
(UTHM
).
Bo
r
n
i
n
1
9
8
3
,
sh
e
o
b
tain
e
d
h
e
r
b
a
c
h
e
lo
r
’
s
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fro
m
Ko
lej
Un
iv
e
rsiti
T
u
n
H
u
ss
e
in
On
n
(KU
i
T
THO)
in
2
0
0
6
,
fo
ll
o
we
d
b
y
a
m
a
ste
r
’
s
d
e
g
re
e
in
m
e
d
ica
l
El
e
c
tro
n
ics
a
n
d
P
h
y
sic
s
fro
m
Qu
e
e
n
M
a
ry
,
U
n
iv
e
rsity
o
f
Lo
n
d
o
n
,
i
n
2
0
0
8
.
S
h
e
e
a
rn
e
d
h
e
r
P
h
.
D
.
in
El
e
c
tr
ica
l,
El
e
c
tro
n
ic,
a
n
d
S
y
ste
m
s
E
n
g
i
n
e
e
rin
g
fro
m
Un
i
v
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
lay
sia
(UK
M
)
in
2
0
1
5
.
S
h
e
sp
e
c
ialize
s
in
m
e
d
ica
l
d
iag
n
o
sis
a
n
d
p
r
o
g
n
o
sis
u
sin
g
a
rti
ficia
l
in
telli
g
e
n
c
e
,
f
o
c
u
sin
g
o
n
d
e
v
e
lo
p
in
g
n
o
n
-
in
v
a
siv
e
m
e
d
ica
l
d
e
v
ice
s
b
a
se
d
o
n
o
p
ti
c
a
l
se
n
so
rs
.
S
h
e
is
a
c
ti
v
e
l
y
e
n
g
a
g
e
d
i
n
a
d
v
a
n
c
in
g
h
e
a
lt
h
c
a
re
tec
h
n
o
l
o
g
y
t
h
ro
u
g
h
in
n
o
v
a
ti
v
e
re
se
a
rc
h
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
i
d
a
@u
t
h
m
.
e
d
u
.
m
y
.
Li
Mu
n
Ng
re
c
e
iv
e
d
h
e
r
first
d
e
g
re
e
fro
m
Un
i
v
e
rsiti
Tu
n
Hu
ss
e
in
On
n
M
a
lay
sia
(UTHM
),
b
a
c
h
e
l
o
r
o
f
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
with
Ho
n
o
u
rs
,
M
a
la
y
sia
,
in
2
0
1
8
.
S
h
e
a
lso
h
a
s
a
m
a
ste
r
’
s
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fr
o
m
UTHM,
M
a
la
y
sia
,
i
n
2
0
2
1
.
S
h
e
is
p
u
rsu
i
n
g
h
e
r
Ph
.
D
.
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
in
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
E
n
g
i
n
e
e
rin
g
,
UTHM.
He
r
m
a
in
re
se
a
rc
h
in
tere
sts
fo
c
u
s
o
n
b
io
m
e
d
ica
l
e
n
g
i
n
e
e
rin
g
,
si
g
n
a
l
p
r
o
c
e
ss
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
th
e
a
p
p
li
c
a
ti
o
n
o
f
fu
z
z
y
lo
g
ic.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
li
m
u
n
.
n
g
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.