I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
,
p
p
.
9
4
8
~
9
60
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
1
3
.
i
4
.
pp
948
-
9
60
948
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Ea
rly
det
ection
of
coro
na
ry
heart d
isea
se ba
sed o
n ri
sk facto
rs
using
int
erp
retab
le ma
chine l
ea
rni
ng
Wiha
rt
o
,
F
a
ra
h Na
da
M
ufida
h
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
c
s,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s
S
e
b
e
l
a
s
M
a
r
e
t
,
S
u
r
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
6
,
2
0
2
3
R
ev
is
ed
J
u
l 9
,
2
0
2
4
Acc
ep
ted
Au
g
2
5
,
2
0
2
4
Co
ro
n
a
r
y
h
e
a
rt
d
ise
a
se
(CHD
)
is t
h
e
lea
d
in
g
c
a
u
se
o
f
d
e
a
th
i
n
t
h
e
wo
rld
.
Th
e
risk
o
f
c
o
r
o
n
a
r
y
h
e
a
rt
d
ise
a
se
c
a
n
b
e
re
d
u
c
e
d
o
r
e
v
e
n
p
re
v
e
n
te
d
b
y
e
a
rly
d
e
tec
ti
o
n
.
Earl
y
d
e
tec
ti
o
n
o
f
CH
D
h
a
s b
e
e
n
wi
d
e
ly
d
e
v
e
l
o
p
e
d
u
si
n
g
m
a
c
h
in
e
lea
rn
in
g
,
b
u
t
t
h
e
m
a
c
h
in
e
lea
rn
in
g
a
l
g
o
ri
th
m
s
u
se
d
s
o
m
e
ti
m
e
s
h
a
v
e
lo
w
in
terp
re
tab
il
it
y
.
Lo
w
in
ter
p
re
tab
il
it
y
m
a
k
e
s
it
d
iffi
c
u
l
t
fo
r
u
se
rs
t
o
u
n
d
e
rs
tan
d
t
h
e
c
a
u
se
o
f
th
e
d
e
c
is
io
n
.
Re
fe
rri
n
g
t
o
t
h
is,
th
is
re
se
a
rc
h
a
ims
to
p
ro
p
o
se
a
n
e
a
rl
y
d
e
tec
ti
o
n
m
o
d
e
l
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
i
n
ter
p
re
tab
il
it
y
,
wh
ich
is
imp
lem
e
n
ted
u
si
n
g
t
h
e
C5
.
0
a
l
g
o
rit
h
m
a
n
d
i
n
terp
r
e
ted
u
sin
g
S
h
a
p
ley
a
d
d
it
i
v
e
e
x
p
lan
a
ti
o
n
s
(S
HA
P
)
.
Th
i
s
re
se
a
rc
h
m
e
th
o
d
is
d
i
v
id
e
d
in
t
o
3
sta
g
e
s,
n
a
m
e
ly
p
re
p
ro
c
e
ss
in
g
,
in
ter
p
re
tab
le
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
p
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
.
Th
is
stu
d
y
u
se
d
2
1
5
p
a
ti
e
n
t
d
a
ta
fro
m
Dr.
M
o
e
wa
rd
i
S
u
ra
k
a
rta
H
o
sp
i
tal.
Te
stin
g
t
h
e
re
su
lt
i
n
g
m
o
d
e
l
u
sin
g
t
h
e
k
-
fo
ld
s
c
ro
ss
-
v
a
li
d
a
t
io
n
m
e
th
o
d
.
Th
e
tes
t
re
su
lt
s
sh
o
w
t
h
a
t
t
h
e
ris
k
fa
c
to
rs
th
a
t
m
a
k
e
a
h
ig
h
c
o
n
tri
b
u
ti
o
n
t
o
th
e
o
u
t
p
u
t
o
f
t
h
e
c
o
r
o
n
a
r
y
h
e
a
rt
d
ise
a
se
d
e
tec
ti
o
n
m
o
d
e
l
a
re
s
y
sto
li
c
b
lo
o
d
p
re
ss
u
re
,
d
ias
to
li
c
b
l
o
o
d
p
re
ss
u
re
,
a
n
d
e
m
p
lo
y
m
e
n
t
lev
e
l,
with
t
h
e
re
su
lt
i
n
g
a
c
c
u
ra
c
y
p
e
rfo
rm
a
n
c
e
o
f
8
4
.
6
4
%
.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
c
a
n
b
e
a
n
a
lt
e
rn
a
ti
v
e
fo
r
e
a
rly
p
re
d
icti
o
n
o
f
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
se
wh
ich
can
e
x
p
lai
n
t
h
e
i
n
flu
e
n
c
e
o
f
e
a
c
h
se
lec
ted
r
isk
fa
c
to
r
o
n
th
e
m
o
d
e
l
o
u
t
p
u
t
.
K
ey
w
o
r
d
s
:
C
5
.
0
alg
o
r
ith
m
C
o
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e
E
ar
ly
d
etec
tio
n
I
n
t
er
p
r
etab
le
m
ac
h
in
e
lear
n
in
g
R
is
k
f
ac
to
r
s
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
ih
ar
to
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics,
Facu
lty
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
l
o
g
y
an
d
Data
Scien
ce
Un
iv
er
s
itas
Seb
elas M
ar
et
I
r
.
Su
tam
i
St.
,
No
.
3
6
A,
Ken
ti
n
g
an
,
J
eb
r
es,
Su
r
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail:
wih
ar
to
@
s
taf
f
.
u
n
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
o
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
(
C
HD
)
is
a
lead
in
g
g
lo
b
al
ca
u
s
e
o
f
d
ea
th
,
with
m
o
r
e
th
a
n
9
m
ill
io
n
d
ea
th
s
attr
ib
u
ted
to
C
HD
in
2
0
2
0
[
1
]
.
T
h
e
C
OVI
D
-
19
p
an
d
em
ic
h
as
wo
r
s
en
ed
th
is
alr
ea
d
y
d
ir
e
s
itu
atio
n
.
Alth
o
u
g
h
th
e
m
o
r
tality
r
ate
d
u
e
to
C
OVI
D
-
19
v
a
r
ies
wo
r
ld
wid
e,
r
an
g
in
g
f
r
o
m
1
-
2
%,
m
o
s
t
p
a
tien
ts
ca
n
r
ec
o
v
er
.
No
n
eth
eless
,
a
co
n
s
id
er
ab
le
a
m
o
u
n
t
o
f
ev
id
en
ce
in
d
icate
s
th
at
C
OVI
D
-
19
ca
n
ca
u
s
e
v
ar
i
o
u
s
lo
n
g
-
ter
m
h
ea
lth
is
s
u
es,
in
clu
d
in
g
o
n
e
th
at
h
e
ig
h
ten
s
th
e
p
o
s
s
ib
ilit
y
o
f
h
e
ar
t
p
r
o
b
lem
s
.
A
co
m
p
r
eh
e
n
s
iv
e
s
tu
d
y
o
f
h
ea
lth
r
ec
o
r
d
s
in
t
h
e
Un
ited
States
r
ev
ea
led
th
at
in
d
iv
id
u
als
wh
o
co
n
tr
ac
ted
C
OVI
D
-
19
h
av
e
a
5
5
%
g
r
ea
ter
c
h
an
ce
o
f
ex
p
er
ien
cin
g
ex
ten
d
ed
ca
r
d
io
v
ascu
lar
co
m
p
licatio
n
s
.
C
o
m
p
licatio
n
s
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
co
n
s
is
t
o
f
h
ea
r
t
r
h
y
th
m
d
is
tu
r
b
an
ce
s
,
h
e
ar
t
in
f
lam
m
atio
n
,
b
lo
o
d
cl
o
ts
,
s
tr
o
k
e,
h
ea
r
t
attac
k
,
h
ea
r
t
f
ai
lu
r
e,
an
d
p
o
s
s
ib
ly
d
ea
th
.
T
h
e
s
am
p
le
r
eg
is
tr
atio
n
s
y
s
tem
(
SR
S)
s
u
r
v
ey
f
r
o
m
2
0
1
4
d
eter
m
i
n
ed
th
at
c
o
r
o
n
a
r
y
h
ea
r
t d
is
ea
s
e
h
as th
e
s
ec
o
n
d
h
i
g
h
est
m
o
r
tality
r
ate
in
I
n
d
o
n
esia,
f
o
llo
win
g
s
tr
o
k
e,
with
a
to
tal
m
o
r
tality
r
at
e
o
f
1
2
.
9
%
o
f
all
r
ec
o
r
d
e
d
d
ea
th
s
.
C
o
r
o
n
ar
y
a
r
ter
y
d
is
ea
s
e
is
th
e
p
r
im
ar
y
a
n
d
m
o
s
t
p
r
ev
alen
t
ca
u
s
e
o
f
m
o
r
tality
in
I
n
d
o
n
esia,
ac
co
u
n
tin
g
f
o
r
2
6
.
4
%
o
f
all
d
e
ath
s
.
T
h
e
n
u
m
b
er
o
f
d
ea
t
h
s
attr
ib
u
ted
to
h
ea
r
t
d
is
ea
s
e
o
u
twei
g
h
s
th
e
n
u
m
b
er
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
a
r
ly
d
etec
tio
n
o
f c
o
r
o
n
a
r
y
h
e
a
r
t d
is
ea
s
e
b
a
s
ed
o
n
r
is
k
fa
cto
r
s
u
s
in
g
in
terp
r
eta
b
le
ma
ch
in
e
…
(
Wih
a
r
to
)
949
h
ea
r
t
an
d
b
lo
o
d
v
ess
el
s
p
ec
ialis
ts
b
y
a
s
ig
n
if
ican
t
m
ar
g
in
in
I
n
d
o
n
esia,
with
o
n
ly
6
0
0
cu
r
r
en
tly
p
r
ac
ticin
g
in
th
e
co
u
n
tr
y
.
C
o
r
o
n
ar
y
ar
ter
y
d
is
ea
s
e
(
C
A
D)
is
ca
u
s
ed
b
y
th
e
b
u
ild
u
p
o
f
p
laq
u
e
in
th
e
co
r
o
n
ar
y
ar
ter
i
es,
lead
in
g
to
d
ec
r
ea
s
ed
b
lo
o
d
f
lo
w
to
t
h
e
h
ea
r
t
an
d
in
cr
ea
s
in
g
th
e
r
is
k
o
f
h
ea
r
t
attac
k
s
an
d
ev
en
m
o
r
tality
.
E
ar
ly
awa
r
en
ess
o
f
a
p
er
s
o
n
'
s
lik
eli
h
o
o
d
o
f
ex
p
e
r
ien
cin
g
C
AD
ca
n
d
ec
r
ea
s
e
r
is
k
.
R
eg
u
lar
m
o
n
i
to
r
in
g
o
f
C
AD
r
is
k
f
ac
to
r
s
,
s
u
ch
as
ch
o
lest
er
o
l
lev
els,
b
lo
o
d
s
u
g
ar
,
b
lo
o
d
p
r
e
s
s
u
r
e,
an
d
weig
h
t,
is
h
elp
f
u
l
f
o
r
ea
r
ly
d
etec
tio
n
.
Po
p
u
latio
n
-
b
ased
C
AD
p
r
ed
ic
tio
n
m
o
d
els
h
av
e
b
ee
n
d
e
v
elo
p
ed
b
ased
o
n
r
is
k
f
ac
to
r
s
.
Ma
n
y
p
o
p
u
latio
n
-
b
ased
m
o
d
els
h
av
e
b
ee
n
d
ev
elo
p
ed
f
o
r
t
h
e
ea
r
l
y
p
r
ed
ictio
n
o
f
C
HD,
in
clu
d
in
g
th
e
Fra
m
in
g
h
a
m
r
is
k
s
co
r
e
(
FR
S),
p
r
o
s
p
ec
tiv
e
ca
r
d
io
v
ascu
lar
M
ü
n
s
ter
(
PR
OC
A
M)
,
an
d
s
y
s
tem
atic
co
r
o
n
ar
y
r
is
k
ev
alu
atio
n
(
SC
OR
E
)
.
T
h
es
e
m
o
d
els
p
r
o
v
id
e
v
a
lu
a
b
le
in
s
ig
h
t
in
to
C
HD
r
is
k
an
d
ca
n
ass
is
t
h
ea
lth
ca
r
e
p
r
o
v
id
er
s
in
d
eter
m
in
in
g
ap
p
r
o
p
r
iate
p
r
ev
en
tiv
e
m
ea
s
u
r
es.
Ho
we
v
e
r
,
it
is
im
p
o
r
tan
t
t
o
r
ec
o
g
n
ize
th
e
lim
itatio
n
s
o
f
s
u
ch
m
o
d
e
ls
an
d
th
e
n
ee
d
f
o
r
o
n
g
o
in
g
r
esear
ch
in
th
is
f
ie
ld
.
Ho
wev
er
,
ce
r
tain
p
o
p
u
lat
i
on
-
b
ased
m
o
d
els
ar
e
u
n
s
u
itab
le
f
o
r
d
etec
tin
g
d
is
ea
s
es
in
p
o
p
u
latio
n
s
d
if
f
er
e
n
t
f
r
o
m
th
e
o
n
e
th
at
th
e
m
o
d
el
r
ep
r
esen
ts
.
Fo
r
in
s
tan
ce
,
FR
S
is
n
o
t
ap
p
r
o
p
r
iate
f
o
r
d
etec
tin
g
h
ea
r
t
d
is
ea
s
e
i
n
J
ap
an
ese
an
d
Ko
r
ea
n
s
,
wh
ile
Ko
r
ea
n
s
ca
n
n
o
t
u
s
e
PR
O
C
AM
an
d
S
C
OR
E
m
o
d
el
s
.
Ad
d
itio
n
ally
,
m
o
d
els
b
ased
o
n
u
r
b
a
n
p
o
p
u
latio
n
s
p
r
o
v
e
in
ef
f
ec
tiv
e
wh
en
ap
p
lied
to
r
u
r
al
p
o
p
u
latio
n
s
[
2
]
,
[
3
]
.
T
h
e
a
s
s
ig
n
ed
r
is
k
s
co
r
e
an
d
QR
I
SK3
s
co
r
e
m
o
d
e
ls
ar
e
co
m
p
a
r
ab
le
to
PR
OC
A
M,
wh
ich
h
as
o
n
ly
b
ee
n
v
alid
ate
d
f
o
r
t
h
e
Ger
m
an
p
o
p
u
latio
n
.
T
h
e
r
ef
o
r
e
,
it
m
ay
n
o
t
b
e
s
u
itab
le
f
o
r
o
th
e
r
p
o
p
u
latio
n
s
.
T
h
e
C
UO
R
E
ri
s
k
s
co
r
e
m
o
d
el
is
also
o
n
ly
ap
p
r
o
p
r
iate
f
o
r
th
e
p
o
p
u
latio
n
in
I
taly
[
4
]
.
T
h
e
r
ap
id
d
ev
elo
p
m
en
t
o
f
a
r
tific
ial
in
tellig
en
ce
,
p
ar
ticu
l
ar
ly
in
th
e
d
o
m
ain
o
f
m
ac
h
i
n
e
lea
r
n
in
g
,
h
as
r
esu
lted
in
t
h
e
cr
ea
ti
o
n
o
f
n
u
m
er
o
u
s
p
r
ed
ictio
n
m
o
d
els
th
a
t
r
ely
o
n
m
ac
h
in
e
lear
n
in
g
d
a
tasets
p
er
tain
in
g
to
r
is
k
f
ac
to
r
s
o
f
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e.
C
HD
p
r
ed
ictio
n
r
esear
ch
u
tili
zin
g
a
d
u
o
o
u
tp
u
t
ar
tific
ial
n
eu
r
al
n
etwo
r
k
e
n
s
em
b
le
(
DOAN
NE
)
h
as
ac
h
ie
v
ed
a
n
ac
c
u
r
ac
y
lev
el
o
f
8
6
%
[
5
]
.
T
h
is
ac
cu
r
ac
y
r
ate
is
b
ased
o
n
th
e
u
s
e
o
f
1
2
r
is
k
f
ac
to
r
s
.
Similar
r
esear
ch
h
as
em
p
l
o
y
ed
a
co
m
b
in
atio
n
o
f
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
[
6
]
to
p
r
ed
ict
ea
r
l
y
C
HD.
T
h
e
s
tu
d
y
id
en
tifie
d
9
o
u
t
o
f
th
e
1
2
test
ed
r
is
k
f
ac
to
r
s
as
in
f
lu
en
tial.
T
h
e
m
o
d
el
ac
h
iev
e
d
a
s
en
s
itiv
ity
p
er
f
o
r
m
a
n
ce
o
f
8
4
.
2
%.
Su
b
s
eq
u
en
t
d
e
v
elo
p
m
e
n
ts
,
r
ef
er
en
cin
g
FR
S,
wer
e
m
o
d
el
ed
u
s
in
g
a
M
am
d
an
i
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
.
T
h
e
m
o
d
el
e
m
p
lo
y
ed
a
G
m
ed
ical
ce
n
ter
d
ataset
f
r
o
m
Ko
r
ea
,
p
r
o
v
id
i
n
g
a
n
ac
c
u
r
ac
y
p
er
f
o
r
m
an
ce
o
f
6
9
%
[
3
]
.
A
s
tu
d
y
s
im
ilar
to
th
e
af
o
r
em
en
tio
n
ed
r
esear
ch
was
co
n
d
u
cted
u
tili
zin
g
th
e
FR
S
.
A
p
r
ed
ictiv
e
m
o
d
el
was
estab
lis
h
ed
u
s
in
g
th
e
class
if
icatio
n
an
d
r
e
g
r
ess
io
n
t
r
ee
(
C
AR
T
)
alg
o
r
ith
m
to
cr
ea
te
r
u
les,
wh
ich
wer
e
s
u
b
s
eq
u
e
n
tly
m
o
d
eled
u
s
in
g
f
u
zz
y
r
u
le
-
b
ased
m
eth
o
d
s
.
T
h
e
r
esu
ltin
g
m
o
d
el
was
test
ed
th
r
o
u
g
h
T
h
e
Ko
r
ea
Natio
n
al
H
ea
lth
an
d
Nu
t
r
itio
n
E
x
am
in
atio
n
Su
r
v
ey
-
VI
(
KN
HANE
S
-
VI
)
d
ataset,
also
k
n
o
wn
as
th
e
Ko
r
ea
n
Natio
n
al
Hea
lth
an
d
Nu
tr
itio
n
E
x
am
in
atio
n
Su
r
v
e
y
VI
.
Ko
r
e
an
Natio
n
al
Hea
lth
an
d
Nu
tr
iti
o
n
E
x
am
in
atio
n
Su
r
v
ey
VI
ac
h
iev
ed
an
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
o
f
6
9
.
5
1
%
an
d
a
s
en
s
itiv
ity
o
f
9
3
.
1
%.
Un
f
o
r
tu
n
ately
,
C
5
.
0
cu
r
r
en
tly
o
u
tp
er
f
o
r
m
s
th
e
C
AR
T
alg
o
r
ith
m
[
7
]
.
A
m
o
d
el
f
o
r
th
e
ea
r
ly
d
etec
ti
o
n
o
f
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
h
as
b
ee
n
d
ev
elo
p
ed
u
s
in
g
9
r
is
k
f
ac
to
r
s
an
d
So
u
th
Af
r
ican
h
ea
r
t
d
is
ea
s
e
d
ata
-
k
n
o
wled
g
e
ex
tr
ac
tio
n
b
ased
o
n
ev
o
lu
tio
n
a
r
y
lear
n
i
n
g
(
KE
E
L
)
[
8
]
.
T
h
e
m
o
d
el
ev
alu
ated
th
r
ee
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
:
J
4
8
,
Naïv
e
B
ay
esian
,
an
d
SVM.
T
h
e
Naïv
e
B
ay
esian
m
o
d
el
s
h
o
we
d
h
ig
h
er
s
en
s
itiv
ity
with
a
6
3
%
v
alu
e
c
o
m
p
a
r
e
d
to
J
4
8
a
n
d
SVM
wh
ich
r
ec
o
r
d
ed
less
th
a
n
5
0
%
r
esp
ec
tiv
ely
.
T
h
er
e
was
n
o
s
ig
n
if
ican
t
d
if
f
e
r
en
ce
in
s
p
ec
if
i
city
v
alu
e
am
o
n
g
th
e
th
r
ee
alg
o
r
ith
m
s
.
A
m
o
d
el
h
as
b
ee
n
d
ev
el
o
p
ed
u
tili
zin
g
th
e
C
AR
T
alg
o
r
ith
m
an
d
f
u
z
zy
lo
g
ic
to
d
etec
t
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
in
th
e
Ko
r
ea
n
p
o
p
u
latio
n
.
T
h
e
m
o
d
e
l
em
p
lo
y
s
n
in
e
r
is
k
f
ac
to
r
s
an
d
was
test
ed
with
r
esu
lt
s
in
d
icatin
g
an
ac
cu
r
ac
y
v
alu
e
o
f
6
9
.
5
1
%,
a
s
en
s
itiv
ity
o
f
9
3
.
1
%,
a
s
p
ec
if
icity
o
f
2
5
.
6
4
%,
a
p
o
s
itiv
e
p
r
ed
icti
o
n
v
alu
e
(
PP
V)
o
f
6
9
.
9
5
%,
a
n
eg
ativ
e
p
r
e
d
ictio
n
v
alu
e
(
NPV)
o
f
6
6
.
6
7
%,
a
n
d
an
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC)
o
f
0
.
5
9
4
[
9
]
.
Siv
ap
r
asad
et
al
.
[
1
0
]
co
n
d
u
ct
ed
a
s
tu
d
y
o
n
th
e
d
e
v
elo
p
m
e
n
t
o
f
d
ee
p
lear
n
in
g
,
s
p
ec
if
icall
y
tr
an
s
f
er
lear
n
in
g
,
an
d
co
m
p
a
r
ed
th
e
r
esu
lts
with
SVM,
n
eu
r
al
n
etwo
r
k
s
,
an
d
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
s
.
I
n
ad
d
itio
n
,
Sar
m
a
et
a
l.
[
1
1
]
an
d
Gh
asem
ieh
et
a
l.
[
1
2
]
d
ev
elo
p
e
d
a
C
HD
d
etec
tio
n
m
o
d
el
u
s
in
g
en
s
em
b
le
s
tack
in
g
an
d
d
ee
p
lear
n
in
g
tech
n
i
q
u
es.
T
h
e
d
ev
el
o
p
m
e
n
t
o
f
m
ac
h
in
e
lear
n
in
g
m
o
d
els
f
o
r
d
etec
tin
g
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
h
as
n
o
t
b
ee
n
a
b
le
to
ex
p
lain
th
e
d
ec
is
io
n
-
m
ak
i
n
g
p
r
o
ce
s
s
th
at
it
p
r
o
d
u
ce
s
,
co
m
m
o
n
ly
r
e
f
er
r
e
d
to
as
b
lack
-
b
o
x
.
T
h
is
is
s
u
p
p
o
r
ted
b
y
a
s
tu
d
y
co
n
d
u
cted
b
y
Fra
n
k
lin
an
d
Mu
th
u
k
u
m
ar
[
1
3
]
,
wh
ich
s
h
o
we
d
th
at
m
an
y
o
f
th
e
d
ev
elo
p
e
d
d
etec
tio
n
m
o
d
els
s
till
r
ely
h
ea
v
ily
o
n
b
lac
k
-
b
o
x
m
eth
o
d
s
,
in
clu
d
i
n
g
th
e
u
s
e
o
f
d
ee
p
lear
n
in
g
an
d
n
eu
r
al
n
etwo
r
k
s
.
Mo
n
d
al
et
a
l
.
[
1
4
]
a
n
d
Kim
et
a
l
.
[
1
5
]
p
r
o
p
o
s
ed
a
m
o
d
el
f
o
r
d
etec
tin
g
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
u
s
in
g
en
s
em
b
le
lear
n
in
g
an
d
a
s
tatis
tical
d
ee
p
b
elief
n
etwo
r
k
f
o
r
ca
r
d
i
o
v
ascu
lar
r
is
k
p
r
ed
ictio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
els
d
o
n
o
t
u
s
e
in
ter
p
r
etab
le
m
ac
h
in
e
lear
n
in
g
.
T
h
is
m
ak
es
th
e
m
o
d
el
u
n
ab
le
to
ex
p
lain
th
e
r
elatio
n
s
h
ip
b
etwe
en
m
o
d
el
in
p
u
t
an
d
m
o
d
el
o
u
tp
u
t.
T
h
e
r
esu
lt
o
f
th
is
co
n
d
itio
n
will
m
ak
e
th
e
r
esu
ltin
g
m
o
d
el
n
o
t
g
et
f
u
ll
tr
u
s
t
b
y
th
e
u
s
er
[
1
6
]
,
[
1
7
]
.
T
r
u
s
t
is
th
e
m
ain
way
to
i
n
cr
ea
s
e
u
s
er
c
o
n
f
id
en
ce
in
u
s
in
g
m
ac
h
in
e
lear
n
i
n
g
[
1
8
]
,
as
well
as
th
eir
c
o
m
f
o
r
t
wh
e
n
u
s
in
g
a
n
d
m
an
a
g
in
g
it
[
1
9
]
.
T
r
u
s
t
is
r
elate
d
to
th
e
eth
ics
an
d
in
ten
s
ity
o
f
r
eg
u
lato
r
y
ac
ti
v
ities
.
T
o
b
e
ab
le
to
p
r
o
v
i
d
e
a
h
ig
h
lev
el
o
f
co
n
f
id
en
ce
in
th
e
m
o
d
el,
an
in
ter
p
r
eta
b
le
m
ac
h
in
e
lear
n
in
g
(
I
ML
)
m
o
d
el
was
d
ev
elo
p
ed
.
T
h
e
im
p
lem
e
n
tatio
n
o
f
I
M
L
is
b
y
u
s
in
g
a
n
u
m
b
er
o
f
m
ac
h
in
e
lear
n
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
948
-
9
60
950
alg
o
r
ith
m
s
co
m
b
i
n
ed
with
i
n
ter
p
r
etab
le
m
eth
o
d
s
,
s
u
ch
a
s
S
h
ap
ley
a
d
d
itiv
e
ex
p
la
n
atio
n
s
(
SHAP),
lo
ca
l
in
ter
p
r
etab
le
m
o
d
el
-
a
g
n
o
s
tic
ex
p
lan
atio
n
s
(
L
I
ME
)
,
an
d
cla
s
s
ac
tiv
atio
n
m
ap
p
i
n
g
(
C
AM
)
[
2
0
]
,
[
2
1
]
.
SHAP,
L
I
ME
,
an
d
C
AM
ar
e
ab
le
to
e
x
p
lain
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
s
o
th
at
t
h
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
in
p
u
t
an
d
o
u
tp
u
t
o
f
th
e
m
o
d
el
ca
n
b
e
u
n
d
er
s
to
o
d
.
T
h
e
t
h
r
ee
m
eth
o
d
s
h
a
v
e
t
h
eir
r
esp
ec
tiv
e
ad
v
an
tag
es,
th
e
C
AM
m
eth
o
d
is
wid
ely
ap
p
lied
to
e
x
p
lain
im
ag
e
p
r
o
b
lem
s
,
L
I
M
E
f
o
r
s
o
m
e
class
if
ica
tio
n
p
r
o
b
lem
s
,
wh
ile
SHA
P
ca
n
b
e
u
s
ed
f
o
r
v
ar
io
u
s
p
r
o
b
lem
s
,
n
o
t
o
n
ly
lim
ited
to
cla
s
s
if
icatio
n
[
2
2
]
.
I
n
ad
d
itio
n
,
SHAP
h
as
a
s
tr
o
n
g
th
eo
r
etica
l
ex
p
lan
atio
n
ab
ilit
y
,
an
d
a
f
air
d
is
tr
ib
u
tio
n
in
its
p
r
ed
ictio
n
s
[
2
3
]
–
[
2
5
]
.
T
h
e
u
s
e
o
f
SHAP
is
al
s
o
wid
ely
ap
p
lied
in
v
ar
io
u
s
f
ield
s
,
o
n
e
o
f
w
h
ich
is
h
ea
lth
[
2
6
]
.
R
ef
er
r
in
g
to
a
n
u
m
b
e
r
o
f
s
tu
d
ies
th
at
h
av
e
b
ee
n
ca
r
r
ied
o
u
t,
th
is
s
tu
d
y
d
ev
elo
p
ed
a
m
o
d
el
f
o
r
ea
r
l
y
d
etec
tio
n
o
f
co
r
o
n
a
r
y
h
ea
r
t
d
i
s
ea
s
e
u
s
in
g
in
ter
p
r
etab
le
m
ac
h
in
e
lear
n
in
g
.
T
h
e
in
ter
p
r
etab
le
m
ac
h
in
e
lear
n
in
g
m
o
d
el
is
im
p
lem
en
ted
u
s
in
g
a
co
m
b
in
atio
n
o
f
C
5
.
0
an
d
in
te
r
p
r
eted
u
s
in
g
SHAP.
T
h
e
ea
r
ly
d
etec
tio
n
m
o
d
el
was
d
ev
elo
p
e
d
u
s
in
g
r
is
k
f
ac
to
r
m
e
d
ical
r
ec
o
r
d
d
ata.
T
h
e
r
is
k
f
ac
to
r
s
u
s
ed
wer
e
tak
e
n
at
D
r
.
M
o
ewa
r
d
i
H
o
s
p
ital Su
r
ak
ar
ta,
I
n
d
o
n
esia.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
T
h
is
s
tu
d
y
u
tili
ze
s
m
ed
ical
r
ec
o
r
d
s
o
f
p
atien
ts
f
r
o
m
th
e
Hea
r
t
an
d
Vascu
lar
D
is
ea
s
e
P
o
ly
clin
ic
at
Dr
.
Mo
ewa
r
d
i
H
o
s
p
ital
in
Su
r
ak
ar
ta,
I
n
d
o
n
esia.
T
h
e
d
ataset
co
n
s
is
ted
o
f
2
1
5
p
atien
ts
,
with
1
3
3
d
iag
n
o
s
ed
with
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
an
d
8
2
with
o
u
t.
No
n
-
m
o
d
if
iab
le
an
d
m
o
d
i
f
iab
le
r
is
k
f
ac
to
r
s
wer
e
in
v
esti
g
ated
,
r
esu
ltin
g
in
1
2
r
is
k
f
ac
to
r
s
w
h
ich
ar
e
ca
te
g
o
r
ized
in
T
a
b
le
1
.
T
h
e
d
ata
f
o
r
th
ese
r
is
k
f
ac
t
o
r
s
wer
e
s
ep
ar
ated
in
to
two
ty
p
es,
ca
teg
o
r
ical
an
d
n
u
m
er
ical.
T
ab
le
1
.
R
ep
r
esen
tatio
n
o
f
cli
n
ical
d
ata
f
o
r
r
is
k
f
ac
to
r
s
N
o
.
R
i
s
k
F
a
c
t
o
r
s
C
a
t
e
g
o
r
y
N
u
mb
e
r
(
%)
Me
a
n
±
S
D
N
A
(
%)
1.
A
g
e
5
9
.
1
1
±
1
4
.
0
7
2.
G
e
n
d
e
r
M
a
l
e
F
e
mal
e
1
2
1
(
5
6
.
2
8
)
9
4
(
4
3
.
7
2
)
3.
Emp
l
o
y
me
n
t
l
e
v
e
l
Li
g
h
t
M
e
d
i
u
m
H
e
a
v
y
9
6
(
4
4
.
6
5
)
8
5
(
3
9
.
5
3
)
3
0
(
1
3
.
9
5
)
4
(
1
.
8
6
)
4.
To
t
a
l
c
h
o
l
e
s
t
e
r
o
l
1
6
9
.
1
7
±
4
5
.
4
7
5.
Lo
w
-
d
e
n
s
i
t
y
l
i
p
o
p
r
o
t
e
i
n
(
LD
L)
1
1
0
.
1
8
±
3
5
.
8
8
6.
H
i
g
h
-
d
e
n
s
i
t
y
l
i
p
o
p
r
o
t
e
i
n
(
H
D
L)
3
5
.
8
7
±
1
2
.
5
5
7.
Tr
i
g
l
y
c
e
r
i
d
e
1
2
8
.
6
2
±
8
7
.
1
8
8.
S
y
st
o
l
i
c
b
l
o
o
d
p
r
e
ss
u
r
e
1
3
8
.
6
1
±
2
4
.
6
7
9.
D
i
a
st
o
l
i
c
b
l
o
o
d
p
r
e
ss
u
r
e
8
6
.
9
6
±
1
4
.
6
5
1
0
.
O
b
e
si
t
y
2
0
.
7
0
±
7
.
6
5
1
1
.
S
mo
k
i
n
g
Y
e
s
No
7
2
(
2
4
.
1
8
)
1
4
3
(
3
4
.
0
6
)
1
2
.
D
i
a
b
e
t
e
s
h
i
s
t
o
r
y
Y
e
s
No
3
0
(
3
2
.
9
7
)
5
4
(
5
9
.
3
4
)
2
.
2
.
M
et
ho
d
T
h
e
s
tu
d
y
was
ca
r
r
ied
o
u
t
i
n
th
r
ee
p
h
ases
:
p
r
e
-
p
r
o
ce
s
s
in
g
,
in
ter
p
r
eta
b
le
m
ac
h
in
e
lea
r
n
in
g
,
an
d
p
er
f
o
r
m
an
ce
ev
alu
atio
n
.
Fig
u
r
e
1
d
is
p
lay
s
a
co
m
p
lete
o
v
er
v
iew
o
f
th
ese
p
h
ases
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
co
n
tain
ed
a
m
is
s
in
g
v
alu
e
im
p
u
tatio
n
p
r
o
ce
s
s
an
d
d
ata
n
o
r
m
aliza
tio
n
.
T
h
e
m
is
s
in
g
v
alu
e
im
p
u
tatio
n
p
r
o
ce
s
s
ap
p
lied
th
e
s
in
g
le
ce
n
ter
im
p
u
tatio
n
f
r
o
m
th
e
m
u
ltip
le
c
h
a
in
ed
eq
u
atio
n
s
(
SICE)
alg
o
r
it
h
m
[
2
7
]
.
T
h
e
SICE
alg
o
r
ith
m
is
an
ex
ten
s
io
n
o
f
th
e
m
u
ltip
le
im
p
u
tatio
n
b
y
ch
ain
ed
eq
u
atio
n
s
(
MI
C
E
)
alg
o
r
ith
m
[
2
7
]
,
[
2
8
]
.
Alg
o
r
ith
m
1
s
h
o
ws th
e
MI
C
E
alg
o
r
ith
m
,
a
n
d
Alg
o
r
ith
m
2
p
r
esen
ts
th
e
SICE
alg
o
r
ith
m
.
I
n
th
e
SICE
alg
o
r
ith
m
p
r
esen
ted
in
Alg
o
r
ith
m
2
,
th
e
im
p
u
tat
io
n
p
r
o
ce
s
s
is
p
er
f
o
r
m
e
d
b
y
c
o
n
s
id
er
in
g
th
e
d
ata
ty
p
e
o
f
th
e
r
is
k
f
ac
to
r
.
I
f
th
e
r
is
k
f
ac
to
r
is
ca
teg
o
r
ical,
th
e
m
o
d
e
is
u
s
ed
f
o
r
ca
l
cu
latio
n
,
wh
ile
th
e
av
er
ag
e
is
u
s
ed
f
o
r
n
u
m
er
ical
d
ata.
Fo
llo
win
g
th
e
im
p
u
tati
o
n
p
r
o
ce
s
s
,
th
e
d
ata
n
o
r
m
aliz
atio
n
p
r
o
ce
d
u
r
e
is
ca
r
r
ied
o
u
t
to
r
escale
th
e
d
ata
b
etwe
en
0
-
1
[
5
]
.
T
h
e
n
o
r
m
al
izatio
n
p
r
o
ce
s
s
f
o
llo
ws
th
e
cr
iter
ia
p
r
esen
ted
in
T
ab
le
2
.
I
f
th
e
d
ata
m
ee
ts
th
e
cr
iter
ia
co
lu
m
n
,
th
e
n
o
r
m
al
izatio
n
o
u
tco
m
es
ar
e
th
en
d
is
p
lay
ed
in
th
e
v
alu
e
co
lu
m
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
a
r
ly
d
etec
tio
n
o
f c
o
r
o
n
a
r
y
h
e
a
r
t d
is
ea
s
e
b
a
s
ed
o
n
r
is
k
fa
cto
r
s
u
s
in
g
in
terp
r
eta
b
le
ma
ch
in
e
…
(
Wih
a
r
to
)
951
Fig
u
r
e
1
.
I
n
ter
p
r
etab
le
m
o
d
el
o
f
m
ac
h
in
e
lear
n
in
g
Alg
o
r
ith
m
1
.
MI
C
E
1.
Simp
le
m
ea
n
im
p
u
tatio
n
is
p
er
f
o
r
m
ed
f
o
r
ev
er
y
m
is
s
in
g
v
alu
e
wh
ich
is
r
ef
er
r
e
d
to
as p
lace
h
o
ld
er
s
.
2.
T
h
e
p
lace
h
o
l
d
er
m
ea
n
v
alu
e
f
o
r
o
n
e
v
ar
iab
le
is
s
et
b
ac
k
t
o
m
is
s
in
g
3.
Ap
p
r
o
p
r
iate
r
eg
r
ess
io
n
is
d
o
n
e
b
etwe
en
o
b
s
er
v
ed
v
alu
es
o
f
th
e
m
is
s
in
g
v
ar
iab
le
ag
ain
s
t
o
th
er
v
ar
iab
les.
4.
T
h
e
m
is
s
in
g
v
alu
e
is
th
en
p
r
ed
icted
u
s
in
g
a
r
e
g
r
ess
io
n
m
o
d
el
5.
I
F o
th
er
m
is
s
in
g
v
alu
e
,
T
HE
N
to
s
tep
2
E
L
SE
to
s
tep
6
6.
I
F iter
atio
n
en
d
T
HE
N
t
o
s
tep
7
E
L
SE
to
s
tep
2
7.
Re
s
u
lts
Alg
o
r
ith
m
2
.
SICE
I
NPUT
:
x
: in
s
tan
ce
s
with
m
is
s
in
g
v
alu
e
s
ca
teg
o
r
ical
an
d
n
u
m
er
ic
i
n
m
ed
ical
r
ec
o
r
d
s
y
: in
s
tan
ce
s
with
n
o
m
is
s
in
g
v
alu
e
d
ata
in
th
e
s
am
e
m
ed
ical
r
ec
o
r
d
.
m
: n
u
m
b
e
r
o
f
im
p
u
tatio
n
s
d
e
f
i
n
ed
b
y
th
e
u
s
er
.
OUT
PUT:
x
'
: u
p
d
ate
x
with
im
p
u
ted
m
is
s
in
g
d
ata
1.
FOR
ea
ch
m
is
s
in
g
v
alu
e
in
x
DO
2.
u
s
e
Alg
o
r
itm
a
1
to
f
in
d
t
h
e
m
i
s
s
in
g
v
alu
e;
3.
E
ND
4.
R
ep
ea
t f
o
r
m
tim
es;
5.
m
iceRes
u
lt[i]
=im
p
u
ted
d
ata
f
o
r
ith
m
is
s
in
g
v
alu
e;
6.
FOR
ea
ch
r
o
w
in
m
iceRes
u
lt DO
7.
I
F ty
p
e
d
ata
o
f
m
iceRes
u
lt[i]
is
n
u
m
er
ic
T
HE
N
8.
s
iceRe
s
u
lt=m
ea
n
(
m
iceRes
u
lt[i,
1
:m
]
)
9.
E
L
SE
10.
s
iceRe
s
u
lt=m
o
d
u
s
(
m
iceRes
u
lt
[
i,1
:m
]
)
11.
E
ND
12.
x
'
=x
u
p
d
ate
with
s
iceRes
u
lt
13.
E
ND
Af
ter
n
o
r
m
aliza
tio
n
,
th
e
n
ex
t
s
tep
in
v
o
lv
es
d
iv
id
in
g
th
e
d
at
a
in
to
tr
ain
in
g
an
d
test
in
g
s
ets
.
T
h
e
d
ata
d
iv
is
io
n
p
r
o
c
ess
ap
p
lies
k
-
f
o
ld
cr
o
s
s
-
va
lid
atio
n
,
wh
e
r
e
k
is
s
et
to
1
0
.
Su
b
s
eq
u
en
tly
,
th
e
d
iv
id
ed
d
ata
is
u
s
ed
t
o
co
n
s
tr
u
ct
a
m
o
d
el
th
at
in
c
o
r
p
o
r
ates
in
ter
p
r
eta
b
le
m
ac
h
i
n
e
l
ea
r
n
in
g
(
I
ML
)
.
B
y
u
s
in
g
I
ML
,
it
b
ec
o
m
es
s
im
p
ler
f
o
r
u
s
er
s
to
co
m
p
r
eh
e
n
d
t
h
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
.
T
h
e
a
lg
o
r
ith
m
u
s
ed
in
th
e
I
ML
m
o
d
el
is
a
co
m
b
i
n
atio
n
o
f
C
5
.
0
with
SHAP.
T
h
e
C
5
.
0
alg
o
r
ith
m
c
r
ea
tes
a
tr
ee
d
iag
r
am
m
o
d
el
th
at
clar
if
ie
s
th
e
in
p
u
t
-
o
u
tp
u
t
co
n
n
ec
tio
n
a
n
d
s
im
p
lifie
s
d
ec
is
io
n
-
m
ak
in
g
[
2
1
]
.
C
5
.
0
m
o
d
if
ies
th
e
iter
ativ
e
d
ich
o
to
m
is
er
3
(
I
D3
)
a
n
d
C
4
.
5
alg
o
r
ith
m
s
.
W
h
en
b
u
ild
in
g
th
e
d
ec
is
io
n
tr
ee
,
t
h
e
r
o
o
t
f
o
r
t
h
e
n
ex
t
n
o
d
e
is
s
elec
ted
b
ased
o
n
th
e
m
a
x
im
u
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
948
-
9
60
952
in
f
o
r
m
atio
n
g
ain
[
2
9
]
,
[
3
0
]
.
T
h
is
m
eth
o
d
b
e
g
in
s
b
y
c
o
n
s
id
e
r
in
g
all
d
ata
as
th
e
r
o
o
t
o
f
th
e
d
ec
is
io
n
tr
ee
,
with
th
e
ch
o
s
en
attr
ib
u
te
s
er
v
in
g
as
th
e
d
iv
id
in
g
f
ac
to
r
f
o
r
th
e
s
a
m
p
le
[
3
0
]
.
T
h
e
f
in
al
s
tag
e
in
v
o
lv
es
ev
alu
atin
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
r
esu
ltan
t
I
ML
m
o
d
el
b
y
r
e
f
er
e
n
cin
g
th
e
co
n
f
u
s
io
n
m
atr
ix
[
3
0
]
,
wh
ic
h
is
d
is
p
lay
ed
in
T
ab
le
3
.
Usi
n
g
T
ab
le
3
,
o
n
e
ca
n
ca
lc
u
late
th
e
p
e
r
f
o
r
m
an
ce
p
ar
am
eter
s
in
clu
d
in
g
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
ac
cu
r
ac
y
,
p
o
s
itiv
e
p
r
ed
ictio
n
v
alu
e
(
P
PV)
,
an
d
n
eg
ativ
e
p
r
ed
ictio
n
v
alu
e
(
NPV)
.
T
h
e
s
e
p
ar
am
eter
s
ar
e
co
m
p
u
ted
b
y
r
ef
er
e
n
cin
g
th
e
co
n
f
u
s
io
n
m
atr
ix
g
en
er
ated
d
u
r
in
g
th
e
test
in
g
p
h
ase
an
d
a
p
p
ly
in
g
(
1
)
-
(
5
)
f
o
r
p
ar
am
eter
ca
lcu
latio
n
.
A
c
c
ura
c
y
=
ACC
=
(
TP
+
TN
)
(
TP
+
TN
+
FP
+
FN
)
X
100%
(
1
)
Sp
e
c
ifi
c
ity
=
SEN
=
TN
(
TN
+
FP
)
×
100%
(
2
)
Se
n
s
itivit
y
=
SPE
=
TP
(
TP
+
FN
)
×
100%
(
3
)
PPV
=
TP
(
TP
+
FP
)
x100%
(
4
)
N
PV
=
(
TN
+
FN
)
×
100%
(
5
)
T
ab
le
2
.
Data
n
o
r
m
aliza
tio
n
r
e
q
u
ir
em
en
ts
No
R
i
s
k
F
a
c
t
o
r
s
C
r
i
t
e
r
i
a
V
a
l
u
e
No
R
i
s
k
F
a
c
t
o
r
s
C
r
i
t
e
r
i
a
V
a
l
u
e
1
A
g
e
<
4
1
41
–
50
51
–
60
61
–
70
71
–
80
≥
8
1
0
0
.
2
0
.
4
0
.
6
0
.
8
1
7
Tr
i
g
l
y
c
e
r
i
d
e
<
1
0
0
1
0
0
–
149
1
5
0
–
199
2
0
0
–
499
≥
5
0
0
0
0
.
2
5
0
.
5
0
.
7
5
1
2
G
e
n
d
e
r
M
a
l
e
F
e
mal
e
1
0
.
5
8
S
y
st
o
l
i
c
b
l
o
o
d
p
r
e
ss
u
r
e
<
1
2
0
1
2
0
–
129
1
3
0
–
139
1
4
0
–
159
1
6
0
–
179
≥
1
8
0
0
0
.
2
0
.
4
0
.
6
0
.
8
1
3
Emp
l
o
y
me
n
t
l
e
v
e
l
Li
g
h
t
M
e
d
i
u
m
H
e
a
v
y
0
0
.
5
1
9
D
i
a
st
o
l
i
c
b
l
o
o
d
p
r
e
ss
u
r
e
<
8
0
80
–
84
85
–
89
90
–
99
1
0
0
–
109
≥
1
1
0
0
0
.
2
0
.
4
0
.
6
0
.
8
1
4
To
t
a
l
c
h
o
l
e
s
t
e
r
o
l
<
2
0
0
2
0
0
–
239
≥
2
4
0
0
0
.
5
1
10
O
b
e
si
t
y
<
1
8
.
5
1
8
.
5
–
2
2
.
9
23
–
2
4
.
9
25
–
2
9
.
9
≥
3
0
0
0
.
2
5
0
.
5
0
.
7
5
1
5
LD
L
<
1
0
0
1
0
0
–
129
1
3
0
–
159
1
6
0
–
189
≥
1
9
0
0
0
.
2
5
0
.
5
0
.
7
5
1
11
S
mo
k
i
n
g
Y
e
s
No
1
0
6
HDL
<
4
0
40
–
59
≥
6
0
0
0
.
5
1
12
D
i
a
b
e
t
e
s
h
i
s
t
o
r
y
Y
e
s
No
1
0
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
ix
A
c
t
u
a
l
C
l
a
ss
P
r
e
d
i
c
t
i
o
n
C
l
a
ss
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
Tr
u
e
p
o
si
t
i
v
e
(
TP
)
F
a
l
se
n
e
g
a
t
i
v
e
FN
N
e
g
a
t
i
v
e
F
a
l
se
p
o
si
t
i
v
e
(
FP
)
Tr
u
e
n
e
g
a
t
i
v
e
TN
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
a
r
ly
d
etec
tio
n
o
f c
o
r
o
n
a
r
y
h
e
a
r
t d
is
ea
s
e
b
a
s
ed
o
n
r
is
k
fa
cto
r
s
u
s
in
g
in
terp
r
eta
b
le
ma
ch
in
e
…
(
Wih
a
r
to
)
953
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Resul
t
s
E
ar
ly
d
etec
tio
n
m
o
d
el
f
o
r
c
o
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
u
tili
zi
n
g
I
ML
,
r
u
n
o
n
h
ar
d
war
e
with
C
P
U
s
p
ec
if
icatio
n
s
o
f
2
.
0
0
GHz
,
1
.
9
9
GHz
,
an
d
4
GB
R
AM
.
T
h
e
I
ML
m
o
d
el
was
im
p
lem
en
t
ed
u
s
in
g
th
e
lib
r
ar
y
in
v
er
s
io
n
4
.
2
.
2
o
f
th
e
R
p
r
o
g
r
am
m
in
g
la
n
g
u
a
g
e
with
R
Stu
d
io
v
e
r
s
io
n
2
0
2
2
.
0
7
.
2
B
u
ild
5
7
6
a
n
d
Mic
r
o
s
o
f
t
E
x
ce
l
v
er
s
io
n
2
2
1
0
B
u
ild
1
5
7
2
6
.
2
0
2
0
2
.
T
h
is
r
esear
ch
f
ir
s
t
p
er
f
o
r
m
ed
im
p
u
tatio
n
u
s
in
g
th
e
SICE
alg
o
r
ith
m
,
wh
ich
is
an
ev
o
lu
tio
n
o
f
MI
C
E
.
T
h
e
MI
C
E
p
r
o
ce
d
u
r
e
was
ex
ec
u
ted
u
tili
zin
g
th
e
m
ice
lib
r
ar
y
in
R
.
Alg
o
r
ith
m
1
d
is
p
lay
s
th
e
o
u
tli
n
e
o
f
th
e
MI
C
E
alg
o
r
ith
m
.
I
n
o
u
r
s
tu
d
y
,
MI
C
E
was
r
u
n
with
m
=3
5
an
d
iter
ated
f
o
u
r
tim
es
to
g
iv
e
3
5
ap
p
r
o
x
i
m
ated
v
alu
es
f
o
r
ea
ch
m
is
s
in
g
v
alu
e.
T
h
is
e
q
u
ates
to
3
5
MI
C
E
p
r
o
ce
s
s
es
ca
r
r
ied
o
u
t
o
n
th
e
d
ataset
an
d
ea
ch
p
r
o
ce
s
s
was
r
ep
ea
ted
f
o
u
r
tim
es.
T
h
e
f
r
eq
u
en
cy
d
is
tr
ib
u
tio
n
o
f
th
e
m
is
s
in
g
v
alu
es
f
o
r
ea
ch
r
is
k
f
ac
to
r
ca
n
b
e
f
o
u
n
d
in
Fig
u
r
e
2
.
T
h
e
im
p
u
tati
o
n
p
r
o
ce
s
s
is
ca
teg
o
r
ized
in
to
two
ty
p
es
o
f
r
is
k
f
ac
to
r
s
: c
ateg
o
r
ical
an
d
n
u
m
er
ical.
Fig
u
r
e
2
.
Nu
m
b
er
o
f
m
is
s
in
g
d
ata
v
alu
es
Fo
r
ca
teg
o
r
ical
d
ata,
s
u
c
h
as
e
m
p
lo
y
m
e
n
t
lev
el,
s
m
o
k
in
g
,
an
d
h
is
to
r
y
o
f
d
iab
etes,
m
is
s
in
g
v
alu
es
ar
e
im
p
u
ted
u
s
in
g
th
e
m
o
d
e
o
f
th
e
d
ata.
Af
ter
war
d
,
o
n
e
o
f
th
e
v
alu
es
is
ag
ain
s
e
lecte
d
to
b
e
m
is
s
in
g
.
T
h
en
,
all
d
ata
f
r
o
m
p
atien
ts
with
m
is
s
in
g
v
al
u
es
u
n
d
e
r
g
o
r
eg
r
ess
io
n
an
aly
s
is
u
s
in
g
th
e
p
o
ly
to
m
o
u
s
lo
g
is
tic
r
eg
r
ess
io
n
m
eth
o
d
[
2
7
]
f
o
r
em
p
lo
y
m
e
n
t
lev
el
d
ata,
a
n
d
t
h
e
lo
g
is
tic
r
e
g
r
ess
io
n
m
eth
o
d
f
o
r
s
m
o
k
i
n
g
a
n
d
d
ia
b
etes
h
is
to
r
y
d
ata.
T
h
is
r
esu
lts
in
an
esti
m
at
ed
v
alu
e
f
o
r
th
e
m
is
s
in
g
d
ata
p
o
in
t.
T
h
e
p
r
o
ce
d
u
r
e
was sy
s
t
em
atica
lly
ex
ec
u
ted
u
n
til
all
ab
s
en
t
v
alu
es
wer
e
p
o
p
u
lated
with
th
e
c
o
m
p
u
te
d
v
alu
es
f
r
o
m
th
e
r
eg
r
ess
io
n
.
Su
b
s
eq
u
en
tly
,
in
th
e
en
s
u
in
g
r
o
u
n
d
,
all
u
n
d
o
n
e
v
alu
es
wer
e
p
o
p
u
lated
with
th
e
m
o
d
e
f
r
o
m
th
e
p
r
ec
ed
in
g
r
o
u
n
d
’
s
o
u
tc
o
m
es.
T
h
is
co
m
p
lete
p
r
o
ce
s
s
was iter
ated
u
n
til th
e
ter
m
in
atio
n
o
f
t
h
e
ex
ec
u
tio
n
.
Miss
in
g
v
alu
es
in
n
u
m
er
i
ca
l
d
ata,
in
cl
u
d
in
g
to
tal
ch
o
lest
er
o
l,
L
DL
,
HDL
,
an
d
tr
ig
ly
c
er
id
es,
ar
e
r
ep
lace
d
with
th
ei
r
r
esp
ec
tiv
e
m
ea
n
.
Su
b
s
eq
u
en
tly
,
o
n
e
o
f
t
h
e
m
is
s
in
g
v
alu
es
is
ch
o
s
en
t
o
b
e
e
m
p
tied
a
g
ain
an
d
all
d
ata
f
r
o
m
th
e
p
atien
t
with
th
e
m
is
s
in
g
v
alu
e
is
r
eg
r
ess
ed
o
n
o
th
er
d
a
ta
u
s
in
g
t
h
e
p
r
ed
ictiv
e
m
ea
n
m
atch
in
g
m
eth
o
d
.
T
h
is
p
r
o
c
ess
is
r
ep
ea
ted
u
n
til
all
m
is
s
in
g
v
alu
es
ar
e
r
ep
lace
d
wit
h
p
r
e
d
icted
v
alu
es
o
b
tain
ed
th
r
o
u
g
h
p
r
ed
ictiv
e
m
ea
n
m
atch
in
g
[
2
7
]
.
T
h
e
n
,
i
n
ea
ch
s
u
b
s
eq
u
e
n
t
iter
atio
n
,
m
is
s
in
g
v
alu
es
ar
e
r
ep
lace
d
with
th
e
m
ea
n
o
f
t
h
e
p
r
ev
io
u
s
iter
atio
n
r
esu
lts
.
T
h
is
p
r
o
ce
s
s
is
r
ep
ea
ted
u
n
til
th
e
e
n
d
o
f
t
h
e
iter
atio
n
.
T
h
e
en
tire
p
r
o
ce
s
s
is
p
er
f
o
r
m
e
d
3
5
tim
es
s
im
u
ltan
eo
u
s
ly
,
d
e
n
o
ted
b
y
th
e
v
alu
e
o
f
m
,
r
esu
lt
in
g
in
3
5
co
m
p
lete
d
atasets
with
o
u
t a
n
y
m
is
s
in
g
v
alu
es.
T
h
e
s
tu
d
y
u
tili
ze
d
th
e
k
-
f
o
l
d
c
r
o
s
s
-
v
alid
atio
n
m
eth
o
d
with
k
=1
0
to
c
o
n
d
u
ct
test
in
g
.
T
a
b
le
4
d
is
p
lay
s
th
e
r
esu
lts
o
f
th
ese
tes
ts
,
in
cl
u
d
in
g
th
e
p
e
r
f
o
r
m
an
ce
o
f
ea
c
h
f
o
ld
o
u
t
o
f
1
0
to
tal.
T
h
e
9
t
h
f
o
ld
h
ad
th
e
b
est
p
er
f
o
r
m
an
ce
,
b
u
t o
v
er
all,
th
e
I
ML
m
o
d
el
in
co
r
p
o
r
atin
g
th
e
C
5
.
0
alg
o
r
ith
m
y
ield
e
d
an
8
4
.
6
4
% sen
s
itiv
ity
r
ate,
in
d
icatin
g
its
ab
ilit
y
to
ac
cu
r
at
ely
d
etec
t
p
o
s
itiv
e
ca
s
es
o
f
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
[
3
1
]
,
[
3
2
]
.
As
th
e
s
en
s
itiv
ity
o
f
th
e
I
ML
m
o
d
el
in
cr
ea
s
es,
m
o
r
e
p
o
s
itiv
e
C
HD
te
s
t r
esu
lt
s
ar
e
o
b
tain
ed
f
r
o
m
p
atien
ts
alr
ea
d
y
s
u
f
f
er
in
g
f
r
o
m
C
HD,
o
r
f
ewe
r
n
eg
ativ
e
C
HD
ca
s
es
ar
e
m
is
s
ed
in
th
is
g
r
o
u
p
.
T
h
e
9
th
f
o
ld
r
e
v
ea
ls
th
e
m
o
d
el'
s
n
o
tab
le
p
er
f
o
r
m
an
ce
in
ac
c
u
r
ately
d
et
ec
tin
g
C
HD
p
atien
ts
,
ac
h
iev
i
n
g
a
r
ate
o
f
9
3
.
3
3
%.
Alth
o
u
g
h
th
is
r
ate
is
h
ig
h
er
wh
en
ex
am
in
i
n
g
th
e
2
n
d
f
o
ld
s
,
o
th
er
p
er
f
o
r
m
an
ce
p
ar
am
eter
s
r
em
ain
lo
w.
T
esti
n
g
with
1
0
f
o
ld
s
also
g
e
n
er
ates
a
d
ec
is
io
n
tr
ee
m
o
d
el
f
o
r
ea
c
h
f
o
ld
.
T
h
e
d
ec
is
io
n
tr
ee
cr
ea
ted
with
th
e
C
5
.
0
alg
o
r
ith
m
s
er
v
e
s
as
an
e
m
b
ed
d
ed
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
,
allo
win
g
th
e
al
g
o
r
ith
m
to
p
er
f
o
r
m
th
e
f
ea
tu
r
e
s
ele
ctio
n
p
r
o
ce
s
s
an
d
u
s
e
th
e
r
esu
lt
as
a
r
is
k
f
a
cto
r
in
co
m
p
ilin
g
th
e
d
ec
is
io
n
tr
ee
.
T
h
e
r
esu
ltin
g
d
ec
is
io
n
tr
ee
in
ea
ch
f
o
ld
co
n
tain
s
th
e
s
am
e
n
u
m
b
er
o
f
a
ttrib
u
tes,
b
u
t
th
e
s
elec
ted
r
is
k
f
ac
to
r
s
v
a
r
y
.
T
h
e
-5
5
15
25
35
4
8
1
6
4
32
7
T
h
e
n
u
m
b
e
r
o
f
mi
ss
i
n
g
v
al
u
e
s
T
h
e
r
i
sk
f
a
c
t
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
948
-
9
60
954
f
r
eq
u
e
n
cy
o
f
r
is
k
f
ac
to
r
s
elec
tio
n
in
ea
ch
f
o
ld
is
d
i
s
p
lay
ed
in
Fig
u
r
e
3
.
E
m
p
lo
y
m
en
t
le
v
el,
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e,
an
d
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e
ar
e
attr
ib
u
tes
p
r
esen
t
i
n
all
f
o
ld
s
.
I
f
a
s
am
p
le
is
tak
e
n
f
r
o
m
th
e
9
th
f
o
ld
,
it
y
ield
s
f
iv
e
s
ig
n
if
ican
t
attr
i
b
u
tes
o
u
t
o
f
th
e
a
v
ailab
le
twelv
e.
T
h
e
f
iv
e
attr
ib
u
tes
th
at
p
o
s
e
a
r
is
k
f
ac
to
r
a
r
e
s
m
o
k
in
g
,
ag
e,
em
p
l
o
y
m
en
t
l
ev
el,
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e,
an
d
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e.
R
ef
er
r
in
g
to
th
e
r
esu
lts
o
f
th
e
in
f
o
r
m
atio
n
g
ai
n
ca
lcu
latio
n
in
t
h
e
C
5
.
0
alg
o
r
ith
m
,
th
e
u
s
ef
u
ln
ess
lev
el
o
f
th
e
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e
att
r
ib
u
te
is
1
0
0
%,
th
e
u
s
ef
u
ln
ess
lev
el
o
f
th
e
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
attr
ib
u
te
is
4
8
.
9
7
%,
th
e
u
s
ef
u
ln
ess
lev
el
o
f
th
e
wo
r
k
le
v
el
attr
ib
u
te
is
3
7
.
1
1
%,
th
e
u
s
ef
u
ln
ess
lev
el
o
f
th
e
s
m
o
k
in
g
attr
ib
u
te
is
1
0
.
3
1
%,
an
d
th
e
u
s
ef
u
ln
ess
lev
el
o
f
th
e
ag
e
attr
ib
u
te
is
9
.
9
7
%.
T
ab
le
4
.
Per
f
o
r
m
an
ce
o
f
th
e
C
HD
ea
r
ly
d
etec
tio
n
m
o
d
el
N
o
.
F
o
l
d
S
EN
A
C
C
SPE
PPV
N
P
V
1
9
4
.
4
4
%
8
1
.
8
2
%
2
5
.
0
0
%
8
5
.
0
0
%
5
0
.
0
0
%
2
1
0
0
.
0
0
%
7
1
.
4
3
%
0
.
0
0
%
7
1
.
4
3
%
0
.
0
0
%
3
7
6
.
9
2
%
8
1
.
8
2
%
8
8
.
8
9
%
9
0
.
9
1
%
7
2
.
7
3
%
4
8
0
.
0
0
%
7
1
.
4
3
%
6
3
.
6
4
%
6
6
.
6
7
%
7
7
.
7
8
%
5
8
4
.
6
2
%
5
9
.
0
9
%
2
2
.
2
2
%
6
1
.
1
1
%
5
0
.
0
0
%
6
7
5
.
0
0
%
6
1
.
9
0
%
4
4
.
4
4
%
6
4
.
2
9
%
5
7
.
1
4
%
7
9
2
.
8
6
%
8
0
.
9
5
%
5
7
.
1
4
%
8
1
.
2
5
%
8
0
.
0
0
%
8
6
9
.
2
3
%
6
8
.
1
8
%
6
6
.
6
7
%
7
5
.
0
0
%
6
0
.
0
0
%
9
9
3
.
3
3
%
8
5
.
7
1
%
6
6
.
6
7
%
8
7
.
5
%
8
0
.
0
0
%
10
8
0
.
0
0
%
6
3
.
6
4
%
5
0
.
0
0
%
5
7
.
1
4
%
7
5
.
0
0
%
M
e
a
n
8
4
.
6
4
%
7
2
.
6
0
%
4
8
.
4
7
%
7
4
.
0
3
%
6
0
.
2
7
%
Fig
u
r
e
3
.
R
is
k
f
ac
to
r
s
in
f
l
u
en
c
in
g
C
HD
d
etec
tio
n
T
h
e
d
ec
is
io
n
tr
ee
d
e
p
icted
in
Fig
u
r
e
4
in
d
icate
s
th
at
th
e
d
ia
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
r
is
k
f
ac
t
o
r
attr
ib
u
te
s
er
v
es
as
th
e
r
o
o
t
with
attr
ib
u
t
e
v
alu
es
o
f
0
.
2
,
0
.
4
,
0
.
8
,
a
n
d
1
,
o
r
i
n
s
tan
d
ar
d
m
ea
s
u
r
em
e
n
t
u
n
its
.
T
h
is
lead
s
to
p
o
s
itiv
e
C
HD
p
r
ed
ictio
n
f
o
r
b
lo
o
d
p
r
ess
u
r
e
m
ea
s
u
r
em
en
ts
o
f
8
0
-
8
9
o
r
≥
1
0
0
,
r
esu
ltin
g
in
t
h
e
class
if
icatio
n
o
f
C
HD=
1
.
T
h
ese
f
in
d
in
g
s
ar
e
s
u
p
p
o
r
ted
b
y
7
6
p
o
s
itiv
e
ca
s
es
o
u
t
o
f
a
to
tal
o
f
9
9
ca
s
es,
with
a
c
o
n
f
id
e
n
ce
le
v
el
o
f
7
6
.
7
7
%.
Patien
ts
with
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e
r
is
k
f
ac
to
r
s
o
f
0
an
d
0
.
6
,
o
r
with
v
alu
e
s
<8
0
o
r
9
0
-
9
9
as
s
p
ec
if
ied
in
T
ab
le
2
,
s
h
o
u
ld
h
av
e
th
eir
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
ch
ec
k
ed
.
T
h
u
s
,
d
iast
o
lic
b
l
o
o
d
p
r
ess
u
r
e
v
alu
es
o
f
0
o
r
0
.
6
,
o
r
r
esu
lts
m
ea
s
u
r
in
g
<8
0
o
r
9
0
-
9
9
,
wo
u
ld
p
r
e
d
ict
th
at
p
atien
ts
with
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
r
is
k
f
ac
to
r
v
al
u
es
o
f
0
.
4
o
r
1
,
o
r
r
e
s
u
lts
m
ea
s
u
r
in
g
1
3
0
-
1
3
9
o
r
≥
1
8
0
,
wo
u
ld
h
av
e
a
n
e
g
ativ
e
p
r
e
d
ictio
n
o
f
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
o
r
b
e
p
lace
d
in
t
h
e
C
HD=
0
class
.
T
h
is
r
esu
lt
in
d
icate
s
a
co
n
f
id
en
ce
lev
el
o
f
8
6
.
9
6
%,
b
ased
o
n
2
0
ca
s
es
o
f
C
HD
n
eg
ativ
ity
a
m
o
n
g
2
3
p
atien
ts
with
id
en
tic
al
b
lo
o
d
p
r
ess
u
r
e
lev
els.
I
t
is
n
ec
ess
ar
y
to
ass
ess
th
e
o
cc
u
p
atio
n
al
r
is
k
f
ac
to
r
f
o
r
p
atien
ts
with
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
v
alu
es
o
f
0
,
0
.
2
,
0
.
6
,
a
n
d
0
.
8
,
o
r
wi
t
h
m
ea
s
u
r
em
en
ts
o
f
≤
1
2
9
o
r
1
4
0
-
1
7
9
.
W
h
en
a
p
atien
t'
s
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
is
f
o
u
n
d
to
b
e
≤
1
2
9
o
r
1
4
0
-
1
7
9
wh
ile
h
av
in
g
a
h
ea
v
y
o
r
wo
r
k
lev
el
attr
ib
u
te
wo
r
th
1
,
th
ey
will
lik
ely
tes
t
p
o
s
itiv
e
f
o
r
C
HD
o
r
b
e
class
if
ied
u
n
d
er
C
HD=
1
.
T
h
e
p
r
e
d
ictio
n
r
esu
lts
s
h
o
w
an
8
1
.
8
2
%
co
n
f
id
en
ce
lev
el,
b
ased
o
n
9
p
o
s
itiv
e
ca
s
es
o
f
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
o
u
t
o
f
1
1
to
tal
ca
s
es.
Fo
r
p
atien
ts
wi
th
lig
h
t
o
r
m
o
d
er
ate
wo
r
k
l
o
ad
s
,
o
r
s
y
s
to
lic
b
l
o
o
d
p
r
ess
u
r
e
v
alu
es
o
f
0
o
r
0
.
5
,
p
r
ed
ictio
n
s
will
b
e
m
ad
e
in
th
e
n
ex
t
s
tep
b
ased
o
n
th
e
r
is
k
f
ac
to
r
s
f
o
r
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e.
0
5
10
7
1
10
2
2
0
2
10
10
1
8
1
T
h
e
f
r
e
q
u
e
n
c
y
T
h
e
r
i
sk
f
a
c
t
o
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
a
r
ly
d
etec
tio
n
o
f c
o
r
o
n
a
r
y
h
e
a
r
t d
is
ea
s
e
b
a
s
ed
o
n
r
is
k
fa
cto
r
s
u
s
in
g
in
terp
r
eta
b
le
ma
ch
in
e
…
(
Wih
a
r
to
)
955
I
f
a
p
atien
t'
s
wo
r
k
lev
el
is
lig
h
t
o
r
m
o
d
e
r
ate,
o
r
if
th
eir
attr
ib
u
te
is
wo
r
th
0
o
r
0
.
5
an
d
th
ey
h
av
e
a
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
attr
ib
u
te
wo
r
th
0
.
2
,
o
r
if
th
eir
m
ea
s
u
r
em
en
t
r
esu
lts
ar
e
b
etwe
en
1
2
0
-
1
2
9
,
th
en
th
ey
wil
l
b
e
class
if
ied
as
C
HD=
0
o
r
p
r
ed
icted
n
eg
ativ
e
.
T
h
is
p
r
ed
ictio
n
h
as
a
6
2
.
5
%
co
n
f
id
e
n
ce
lev
el,
s
u
p
p
o
r
ted
b
y
1
0
n
eg
ativ
e
ca
s
es
o
u
t
o
f
a
to
tal
o
f
1
6
p
atien
t
ca
s
es
with
s
im
ilar
attr
ib
u
te
v
alu
es.
I
f
th
e
p
atien
t'
s
wo
r
k
lev
el
is
lig
h
t
o
r
m
o
d
er
ate,
o
r
if
th
e
attr
i
b
u
te
is
0
o
r
0
.
5
with
a
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
attr
ib
u
t
e
o
f
0
.
8
,
o
r
if
t
h
e
m
ea
s
u
r
em
en
t
r
esu
lt
f
alls
b
etw
ee
n
1
6
0
-
1
7
9
,
th
e
n
th
e
p
atien
t
is
p
r
ed
icted
to
b
e
p
o
s
itiv
e
f
o
r
C
HD=
1
o
r
to
h
a
v
e
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e.
T
h
is
p
r
ed
ictio
n
ca
r
r
ies
a
co
n
f
id
en
c
e
lev
el
o
f
8
3
.
3
3
%
wh
ich
is
b
ac
k
ed
b
y
5
p
o
s
itiv
e
ca
s
es
o
u
t
o
f
a
to
tal
o
f
6
p
atie
n
t
ca
s
es
with
th
e
s
am
e
attr
ib
u
te
v
alu
e.
Patien
ts
with
a
s
y
s
t
o
lic
b
lo
o
d
p
r
ess
u
r
e
attr
ib
u
te
v
alu
e
o
f
0
o
r
m
ea
s
u
r
em
en
t
r
esu
lts
<1
2
0
will
b
e
p
r
ed
icted
b
ased
o
n
th
eir
s
m
o
k
i
n
g
attr
ib
u
te
v
al
u
e.
T
h
i
s
is
d
u
e
to
th
e
s
m
o
k
in
g
r
is
k
f
ac
to
r
attr
ib
u
te
h
av
i
n
g
th
e
lar
g
est in
f
o
r
m
atio
n
g
ai
n
r
atio
v
a
lu
e
in
th
is
s
u
b
s
et
o
f
p
atien
t
d
ata.
Patien
ts
with
a
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
attr
ib
u
te
v
alu
e
o
f
0
.
6
o
r
a
m
ea
s
u
r
em
en
t
r
esu
lt
b
etwe
en
140
-
1
5
9
will
b
e
p
r
ed
icted
b
a
s
ed
o
n
th
eir
ag
e
attr
ib
u
te
v
al
u
e.
T
h
is
is
d
u
e
to
th
e
ag
e
attr
ib
u
te
h
av
in
g
t
h
e
h
ig
h
est in
f
o
r
m
atio
n
g
ai
n
r
atio
in
th
is
s
u
b
s
et
o
f
p
atien
t d
ata.
Fig
u
r
e
4
.
I
ML
m
o
d
el
f
o
r
c
o
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e
d
etec
tio
n
W
h
en
th
e
p
atien
t'
s
s
y
s
to
lic
b
l
o
o
d
p
r
ess
u
r
e
attr
ib
u
te
is
l
ess
th
an
1
2
0
an
d
th
e
p
atien
t
d
o
es
n
o
t
s
m
o
k
e
o
r
h
as
a
s
m
o
k
in
g
attr
ib
u
te
v
a
lu
e
o
f
0
,
th
e
y
ar
e
ca
teg
o
r
ize
d
in
to
th
e
C
HD=
0
p
r
e
d
ictio
n
class
,
in
d
icatin
g
a
n
eg
ativ
e
p
r
ed
ictio
n
f
o
r
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
T
h
is
p
r
ed
ict
io
n
h
as
a
c
o
n
f
id
e
n
ce
le
v
el
o
f
6
9
.
2
3
%,
s
u
p
p
o
r
te
d
b
y
9
n
e
g
ativ
e
ca
s
es
o
u
t
o
f
a
to
tal
o
f
1
3
ca
s
es
with
th
e
s
am
e
attr
ib
u
te
v
alu
e.
Me
a
n
wh
il
e,
if
th
e
p
atien
t
is
a
s
m
o
k
er
o
r
h
as
a
s
m
o
k
in
g
attr
i
b
u
te
v
alu
e
o
f
1
,
th
ey
will
b
e
p
r
ed
icted
p
o
s
itiv
ely
to
s
u
f
f
er
f
r
o
m
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
o
r
en
ter
th
e
C
HD
p
r
ed
ictio
n
class
=1
.
Patien
ts
with
a
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
att
r
ib
u
te
v
alu
e
o
f
0
.
6
(
1
4
0
-
1
4
9
)
an
d
an
ag
e
attr
i
b
u
t
e
v
alu
e
o
f
0
o
r
0
.
8
(
p
atie
n
ts
ag
ed
<4
1
y
ea
r
s
o
r
7
1
-
8
1
y
ea
r
s
)
will
b
e
in
clu
d
e
d
in
th
e
C
HD
p
r
ed
ictio
n
class
=0
o
r
p
r
ed
icted
to
b
e
"
n
eg
ativ
e"
f
o
r
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e.
T
h
is
p
r
ed
ictio
n
is
b
ased
o
n
6
ca
s
es
with
s
im
ilar
attr
ib
u
te
v
alu
es,
all
o
f
wh
o
m
test
e
d
n
eg
ativ
e
f
o
r
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e.
Ho
wev
er
,
p
atien
ts
ag
ed
4
1
-
7
0
o
r
≥
8
1
y
ea
r
s
o
ld
(
ag
e
attr
ib
u
te
v
alu
e
0
.
2
,
0
.
4
,
0
.
6
,
o
r
1
)
ar
e
lik
ely
to
test
p
o
s
itiv
e
f
o
r
c
o
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e
o
r
h
a
v
e
an
attr
ib
u
te
v
alu
e
o
f
1
f
o
r
t
h
e
C
HD
p
r
ed
ictio
n
class
.
T
h
i
s
p
r
ed
ictio
n
h
as
a
co
n
f
id
en
ce
lev
el
o
f
7
6
.
9
2
%
wh
ich
is
s
u
p
p
o
r
ted
b
y
1
0
p
o
s
itiv
e
ca
s
es
o
u
t
o
f
a
to
tal
o
f
1
3
p
atien
t
ca
s
es
with
s
im
ilar
attr
ib
u
te
v
alu
es.
T
h
e
I
ML
m
o
d
el
b
u
ilt
u
s
in
g
SHAP
ca
n
b
e
an
aly
ze
d
f
o
r
th
e
im
p
ac
t
o
f
ea
ch
f
ea
tu
r
e
o
n
th
e
o
u
tp
u
t
o
f
th
e
s
y
s
tem
m
o
d
el.
T
h
e
im
p
ac
t
o
f
ea
c
h
f
ea
t
u
r
e
ca
n
b
e
s
h
o
w
n
in
Fig
u
r
e
5
.
R
ef
er
r
i
n
g
t
o
Fi
g
u
r
e
6
,
it
c
an
s
h
o
w
th
e
co
n
tr
ib
u
tio
n
o
f
f
ea
tu
r
es
f
r
o
m
ea
ch
d
ata
to
th
e
s
y
s
t
em
m
o
d
el,
b
esid
es
th
at,
th
e
av
er
ag
e
s
h
ap
ley
v
alu
es
th
at
s
h
o
w
th
e
co
n
tr
ib
u
tio
n
o
f
f
ea
tu
r
es c
an
also
b
e
tak
en
,
as sh
o
wn
in
Fig
u
r
e
6
.
Fig
u
r
e
6
s
h
o
ws th
at
b
lo
o
d
p
r
ess
u
r
e,
b
o
th
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e
(
DB
P
)
an
d
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
(
SB
P
)
h
av
e
a
h
ig
h
im
p
ac
t
o
n
th
e
s
y
s
tem
m
o
d
el.
I
n
a
d
d
itio
n
to
t
h
ese
two
f
ea
tu
r
es,
th
e
em
p
l
o
y
m
en
t
r
a
te
f
ea
tu
r
e
also
h
as
a
h
ig
h
er
i
m
p
ac
t
th
an
ag
e
an
d
s
m
o
k
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
1
3
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
948
-
9
60
956
Fig
u
r
e
5
.
I
m
p
ac
t o
n
m
o
d
el
o
u
t
p
u
t
Fig
u
r
e
6
.
SHAP v
alu
e
(
a
v
er
ag
e
im
p
ac
t o
n
m
o
d
el
o
u
tp
u
t)
3
.
2
.
Di
s
cus
s
io
n
T
h
er
e
is
an
a
n
o
m
aly
in
th
e
p
r
e
d
ictio
n
p
atter
n
o
f
co
r
o
n
ar
y
h
e
ar
t
d
is
ea
s
e
in
th
e
d
e
v
elo
p
e
d
I
ML
m
o
d
el
.
Sp
ec
if
ically
,
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e
e
x
h
ib
its
a
h
ig
h
er
n
u
m
b
er
o
f
p
o
s
itiv
e
p
r
ed
ict
io
n
s
f
o
r
C
HD
th
an
ex
p
ec
ted
,
d
esp
ite
b
ein
g
b
el
o
w
th
e
u
s
u
al
th
r
esh
o
ld
.
T
h
is
p
atter
n
is
o
b
s
er
v
ed
in
o
v
er
5
0
ca
s
es.
T
h
e
u
s
e
o
f
b
lo
o
d
p
r
ess
u
r
e
co
n
t
r
o
l
m
e
d
icatio
n
s
i
n
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
p
atie
n
ts
m
ay
r
esu
lt
in
a
lo
w
d
iast
o
lic
b
lo
o
d
p
r
ess
u
r
e
r
ea
d
in
g
d
u
r
in
g
b
lo
o
d
p
r
ess
u
r
e
m
ea
s
u
r
em
en
t.
An
o
m
alies
als
o
o
cc
u
r
r
e
d
in
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
r
is
k
f
ac
to
r
s
,
with
2
0
-
4
9
ca
s
es
to
tal.
Hig
h
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
was
ass
o
ciate
d
with
n
eg
ativ
e
p
r
ed
icti
o
n
s
,
p
ar
tic
u
lar
ly
in
y
o
u
n
g
p
atien
ts
.
Hig
h
s
y
s
to
lic
b
lo
o
d
p
r
ess
u
r
e
in
p
atien
ts
wit
h
o
u
t c
o
r
o
n
ar
y
h
ea
r
t d
is
ea
s
e
m
ay
r
esu
lt f
r
o
m
er
r
o
r
s
d
u
r
in
g
b
l
o
o
d
p
r
ess
u
r
e
m
ea
s
u
r
em
en
t
wh
e
n
th
e
p
atien
t
is
n
o
t
ad
eq
u
ately
r
ested
.
Pro
p
er
d
ia
g
n
o
s
is
an
d
life
s
ty
le
m
o
d
if
icatio
n
s
ar
e
cr
u
cial
f
o
r
m
an
ag
in
g
h
ig
h
b
lo
o
d
p
r
ess
u
r
e.
I
n
y
o
u
n
g
er
p
atien
ts
wh
o
test
p
o
s
itiv
e
f
o
r
co
r
o
n
a
r
y
h
ea
r
t
d
is
ea
s
e,
h
er
ed
ity
an
d
an
u
n
h
ea
lth
y
life
s
ty
le
m
ay
b
e
ca
u
s
ativ
e
f
ac
t
o
r
s
.
I
n
p
atien
ts
with
h
ig
h
b
lo
o
d
p
r
ess
u
r
e,
th
o
s
e
wh
o
ar
e
y
o
u
n
g
er
h
a
v
e
a
h
i
g
h
er
p
r
o
b
ab
i
lity
o
f
d
ev
el
o
p
in
g
co
r
o
n
ar
y
h
e
ar
t d
is
ea
s
e
[
3
3
]
.
Fro
m
th
e
ca
lcu
lated
r
esu
lts
,
th
e
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
ea
r
ly
d
etec
tio
n
m
o
d
el
d
em
o
n
s
tr
ated
a
s
en
s
itiv
ity
o
f
8
4
.
6
4
%,
ac
cu
r
ac
y
o
f
7
2
.
5
9
7
%,
s
p
ec
if
icity
o
f
4
8
.
4
6
7
%,
p
o
s
itiv
e
p
r
e
d
ictiv
e
v
a
lu
e
o
f
7
4
.
0
3
%,
an
d
n
eg
ativ
e
p
r
e
d
ictiv
e
v
alu
e
o
f
6
0
.
2
6
5
%.
T
h
e
m
o
d
el'
s
lo
w
s
p
e
cif
icity
an
d
n
eg
ativ
e
p
r
ed
ictiv
e
v
alu
es
s
te
m
f
r
o
m
an
im
b
alan
ce
b
etwe
en
C
HD
-
p
o
s
itiv
e
an
d
n
e
g
ativ
e
p
atien
t
d
a
ta
u
s
ed
in
th
e
ex
p
er
im
en
t,
with
a
r
atio
o
f
5
:3
.
As
a
r
esu
lt,
th
e
m
o
d
el
class
if
ies
m
an
y
n
eg
ativ
e
p
atien
ts
as
p
o
s
itiv
e,
lead
in
g
to
a
d
ec
r
ea
s
e
in
tr
u
e
n
e
g
ativ
e
v
alu
e
an
d
an
i
n
cr
ea
s
e
in
f
alse p
o
s
i
tiv
e
v
alu
e.
T
ab
le
4
s
h
o
ws
th
at
th
e
s
en
s
itiv
ity
m
o
d
el
d
e
v
elo
p
e
d
in
th
is
s
tu
d
y
o
u
tp
er
f
o
r
m
s
p
r
ev
io
u
s
s
t
u
d
ies
th
at
u
s
ed
d
ata
f
r
o
m
th
e
s
am
e
lo
ca
tio
n
an
d
o
n
l
y
co
n
s
id
er
ed
5
r
is
k
f
ac
to
r
s
.
Ho
wev
er
,
th
e
ac
cu
r
ac
y
o
f
o
u
r
m
o
d
el
is
lo
wer
th
an
th
at
o
f
p
r
ev
io
u
s
s
tu
d
ies
d
u
e
to
th
e
u
n
e
v
en
d
is
tr
ib
u
tio
n
o
f
p
atien
t
d
ata
b
etwe
e
n
p
o
s
itiv
e
C
HD
an
d
n
eg
ativ
e
C
HD
ca
s
es.
T
h
is
p
h
en
o
m
en
o
n
h
as
b
ee
n
o
b
s
er
v
ed
in
v
ar
io
u
s
s
tu
d
ies,
in
clu
d
in
g
r
esear
ch
co
n
d
u
cted
b
y
C
h
awla
et
a
l
.
[
3
4
]
,
T
h
ab
ta
h
et
a
l
.
[
3
5
]
,
an
d
L
u
q
u
e
et
a
l
.
[
3
6
]
.
T
h
e
s
tu
d
ies
em
p
h
asize
th
at
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
o
f
ten
p
r
io
r
itize
la
b
elin
g
th
e
m
ajo
r
ity
class
in
p
r
ed
ict
ed
d
ata,
lead
i
n
g
to
n
eg
l
ec
t
o
f
th
e
m
in
o
r
ity
class
.
As a
r
esu
lt,
th
ese
alg
o
r
ith
m
s
m
o
s
tly
g
en
er
ate
ac
c
u
r
ate
p
r
ed
ictio
n
s
f
o
r
th
e
m
aj
o
r
ity
cl
ass
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
E
a
r
ly
d
etec
tio
n
o
f c
o
r
o
n
a
r
y
h
e
a
r
t d
is
ea
s
e
b
a
s
ed
o
n
r
is
k
fa
cto
r
s
u
s
in
g
in
terp
r
eta
b
le
ma
ch
in
e
…
(
Wih
a
r
to
)
957
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
with
p
r
ev
io
u
s
r
e
s
ea
r
ch
in
I
n
d
o
n
esia
R
e
f
e
r
e
n
c
e
s
M
e
t
h
o
d
N
u
mb
e
r
o
f
D
a
t
a
#
R
i
sk
f
a
c
t
o
r
S
EN
A
C
C
[
6
]
P
C
A
+
S
V
M
1
2
0
9
8
4
.
2
0
%
7
8
.
6
1
%
[
5
]
DOANNE
1
2
0
12
-
8
6
.
8
7
%
P
r
o
p
o
se
d
I
M
L
(
C
5
.
0
+
S
H
A
P
)
2
1
5
5
8
4
.
6
4
%
7
2
.
5
9
7
%
Pre
v
io
u
s
r
esear
ch
u
s
in
g
th
e
P
C
A+
SVM
m
eth
o
d
r
esu
lted
in
9
r
is
k
f
ac
to
r
s
,
wh
e
r
ea
s
C
5
.
0
p
r
o
d
u
ce
d
5
r
is
k
f
ac
to
r
s
.
Fro
m
b
o
th
tech
n
iq
u
es,
th
e
C
5
.
0
alg
o
r
ith
m
elim
in
ated
4
r
is
k
f
ac
to
r
s
,
w
h
ich
in
clu
d
e
to
tal
ch
o
lest
er
o
l,
L
DL
,
tr
i
g
ly
ce
r
id
e
lev
els,
an
d
g
en
d
er
.
T
h
e
r
is
k
f
ac
to
r
s
f
o
r
to
tal
ch
o
lest
er
o
l,
L
DL
,
an
d
tr
ig
ly
ce
r
id
e
lev
els
ar
e
in
ter
co
n
n
ec
te
d
,
as
d
em
o
n
s
tr
ated
in
t
h
e
Frie
d
ewa
ld
f
o
r
m
u
la
[
3
7
]
p
r
esen
ted
in
(
6
)
an
d
th
e
Ma
r
tin
-
Ho
p
k
in
s
f
o
r
m
u
la
[
3
8
]
d
e
p
icted
in
(
7
)
.
W
h
en
u
tili
zin
g
th
e
P
C
A+
SVM
m
eth
o
d
to
elim
in
ate
HDL
r
is
k
f
ac
to
r
s
,
r
ef
er
en
ce
to
b
o
th
(
6
)
an
d
(
7
)
r
ev
ea
ls
th
at
all
th
r
ee
r
is
k
f
ac
to
r
s
ar
e
in
ter
co
n
n
ec
ted
an
d
ca
n
b
e
elim
in
ated
u
s
in
g
th
e
C
5
.
0
alg
o
r
ith
m
.
Desp
ite
th
e
r
em
o
v
al
o
f
all
ch
o
lest
er
o
l
-
r
elate
d
r
is
k
f
ac
to
r
s
,
th
e
C
5
.
0
al
g
o
r
ith
m
d
em
o
n
s
tr
ates
h
ig
h
er
s
en
s
itiv
ity
th
a
n
th
e
u
s
e
o
f
ch
o
lest
er
o
l
r
is
k
f
ac
to
r
s
al
o
n
e.
T
h
ese
r
esu
lts
h
ig
h
lig
h
t
th
e
I
ML
m
o
d
el'
s
ab
ilit
y
to
d
etec
t
C
HD
p
atien
ts
,
with
a
d
etec
tio
n
r
ate
o
f
8
4
.
6
4
%
f
o
r
C
5
.
0
co
m
p
ar
ed
t
o
8
4
.
2
%
f
o
r
PC
A+
S
VM
.
=
0
.
659
×
ℎ
+
0
.
182
×
−
0
.
117
×
+
18
.
03
(
6
)
=
ℎ
−
−
(
7
)
E
ar
ly
d
etec
tio
n
u
s
in
g
I
ML
,
w
h
ich
is
im
p
lem
en
ted
u
s
in
g
t
h
e
C
5
.
0
alg
o
r
ith
m
an
d
in
ter
p
r
e
ted
u
s
in
g
SHAP,
is
ab
le
to
p
r
o
v
id
e
an
ex
p
lan
atio
n
th
at
is
ea
s
y
f
o
r
u
s
er
s
to
u
n
d
er
s
tan
d
th
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
.
T
h
is
ab
ilit
y
is
b
etter
th
an
m
o
d
els
th
at
u
s
e
S
VM
an
d
DOAN
NE
alg
o
r
ith
m
s
in
p
r
ev
io
u
s
s
tu
d
ies.
T
h
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
ex
p
lain
th
e
d
e
cisi
o
n
-
m
ak
in
g
p
r
o
ce
s
s
will
m
ak
e
I
ML
with
C
5
.
0
,
tr
u
s
two
r
th
in
ess
,
ca
u
s
ality
,
tr
an
s
f
er
ab
ili
ty
,
in
f
o
r
m
ativ
e
n
ess
,
co
n
f
id
e
n
ce
,
an
d
f
air
n
ess
.
I
ML
m
o
d
el
ca
p
ab
ilit
y
ca
n
b
e
an
aly
ze
d
f
o
r
ea
ch
in
p
u
t
d
ata,
f
o
r
e
x
am
p
le
as
s
h
o
wn
in
Fig
u
r
e
7
.
I
n
Fig
u
r
e
7
,
ea
ch
lin
e
p
lo
tted
o
n
th
e
d
ec
is
io
n
p
lo
t
s
h
o
ws
h
o
w
s
tr
o
n
g
ly
ea
c
h
f
ea
tu
r
e
co
n
tr
ib
u
tes
to
a
s
in
g
le
m
o
d
el
p
r
e
d
ictio
n
,
t
h
u
s
ex
p
lain
in
g
wh
at
f
ea
tu
r
e
v
al
u
es
d
r
i
v
e
th
e
p
r
ed
ictio
n
.
Fo
r
th
e
r
e
d
lin
e
s
h
o
win
g
d
ata
with
p
o
s
itiv
e
C
HD,
th
e
r
ed
lin
e
s
h
o
ws
th
at
DB
P
h
as
a
h
ig
h
in
f
lu
en
ce
in
d
eter
m
in
in
g
th
e
m
o
d
el
o
u
tp
u
t,
as
well
as
S
B
P
.
T
h
e
b
lu
e
lin
e
s
h
o
w
s
wh
en
t
h
e
d
ata
is
n
eg
at
iv
e
C
HD,
it is
al
s
o
h
ig
h
ly
d
eter
m
in
ed
b
y
th
e
DB
P a
n
d
SB
P f
ea
tu
r
es.
Fig
u
r
e
7
.
T
esti
n
g
t
h
e
ef
f
ec
t
o
f
f
ea
tu
r
es f
r
o
m
o
n
e
p
atien
t'
s
d
ata
o
n
m
o
d
el
p
r
e
d
ictio
n
T
h
e
in
f
lu
e
n
ce
o
f
f
ea
tu
r
es o
n
p
r
ed
ictio
n
r
esu
lts
ca
n
also
b
e
r
e
p
r
esen
ted
in
a
f
ac
e
p
l
o
t
g
r
a
p
h
,
as
s
h
o
wn
in
Fig
u
r
e
s
8
an
d
9
.
Fig
u
r
e
8
s
h
o
ws h
o
w
m
u
ch
i
n
f
lu
en
ce
th
e
SB
P,
D
B
P,
an
d
em
p
lo
y
m
e
n
t r
ate
f
ea
tu
r
es h
av
e
o
n
p
r
ed
ictio
n
r
esu
lts
,
as
s
h
o
wn
in
r
ed
.
Fo
r
ag
e
an
d
s
m
o
k
in
g
f
ea
tu
r
es,
th
e
in
f
lu
e
n
ce
is
lo
w,
as
s
h
o
wn
in
b
l
u
e.
Fig
u
r
e
9
s
h
o
ws
th
e
d
ata
test
ed
f
o
r
C
HD
n
eg
ativ
e
d
ata,
w
h
er
e
th
e
r
esu
lts
s
h
o
w
th
at
DB
P
an
d
SB
P
h
av
e
a
lo
w
Evaluation Warning : The document was created with Spire.PDF for Python.