I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
r
m
a
t
ics a
nd
Co
mm
u
n
ica
t
io
n
T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
8
,
No
.
1
,
A
p
r
il
201
9
,
p
p
.
56
~
62
I
SS
N:
2252
-
8776
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
i
ct.
v
8
i1
.
p
p
5
6
-
62
56
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JI
C
T
Predic
ting
hea
rt
a
il
m
en
t
in
pa
tien
t
s w
ith
v
a
ry
ing
nu
m
be
r of
f
ea
tures
using
dat
a
m
ining
t
ech
niq
ues
T
R
Ste
lla
M
a
r
y
, S
ho
ney
Seba
s
t
ia
n
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Ch
rist
U
n
iv
e
rsity
,
T
a
i
w
a
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
0
,
2018
R
ev
i
s
ed
J
an
2
0
,
2
0
1
9
A
cc
ep
ted
Feb
3
,
2
0
1
9
Da
ta
m
in
in
g
c
a
n
b
e
d
e
f
in
e
d
a
s
a
p
ro
c
e
ss
o
f
e
x
tra
c
ti
n
g
u
n
k
n
o
w
n
,
v
e
ri
f
iab
le
a
n
d
p
o
ss
ib
ly
h
e
lp
f
u
l
d
a
ta
f
ro
m
in
f
o
rm
a
ti
o
n
.
Am
o
n
g
th
e
v
a
rio
u
s
a
il
m
e
n
ts,
h
e
a
rt
a
il
m
e
n
t
is
o
n
e
o
f
th
e
p
rim
a
r
y
r
e
a
so
n
b
e
h
in
d
d
e
a
th
o
f
in
d
iv
i
d
u
a
ls
a
ro
u
n
d
th
e
g
lo
b
e
,
h
e
n
c
e
i
n
o
rd
e
r
to
c
u
rb
th
is,
a
d
e
tailed
a
n
a
ly
sis
is
d
o
n
e
u
sin
g
Da
ta
M
in
i
n
g
.
M
a
n
y
a
ti
m
e
s
we
li
m
it
o
u
rse
lv
e
s
w
it
h
m
in
ima
l
a
tt
rib
u
t
e
s
th
a
t
a
re
re
q
u
ired
to
p
re
d
ict
a
p
a
ti
e
n
t
w
it
h
h
e
a
rt
d
ise
a
se
.
By
d
o
in
g
s
o
w
e
a
re
m
issin
g
o
n
a
lo
t
o
f
im
p
o
rtan
t
a
tt
rib
u
tes
th
a
t
a
re
m
a
in
c
a
u
se
s
f
o
r
h
e
a
rt
d
ise
a
se
s.
He
n
c
e
,
th
is
re
se
a
rc
h
a
i
m
s
a
t
c
o
n
sid
e
rin
g
a
l
m
o
st
a
ll
th
e
i
m
p
o
rtan
t
fe
a
tu
re
s
a
ff
e
c
ti
n
g
h
e
a
rt
d
ise
a
se
a
n
d
p
e
rf
o
rm
s
th
e
a
n
a
ly
sis
st
e
p
b
y
ste
p
w
it
h
m
in
im
a
l
to
m
a
x
i
m
u
m
s
e
t
o
f
a
tt
rib
u
tes
u
sin
g
Da
ta
M
in
in
g
tec
h
n
i
q
u
e
s
to
p
r
e
d
ict
h
e
a
rt
a
il
m
e
n
ts.
T
h
e
v
a
rio
u
s
c
las
si
f
ica
ti
o
n
m
e
th
o
d
s
u
se
d
a
re
Na
ïv
e
Ba
y
e
s
c
las
si
f
ier,
Ra
n
d
o
m
F
o
re
st
a
n
d
Ra
n
d
o
m
T
re
e
w
h
ich
a
re
a
p
p
li
e
d
o
n
t
h
re
e
d
a
tas
e
ts
w
it
h
di
f
fe
re
n
t
n
u
m
b
e
r
o
f
a
tt
rib
u
tes
b
u
t
w
it
h
a
c
o
m
m
o
n
c
las
s
l
a
b
e
l
.
F
ro
m
th
e
a
n
a
ly
sis
p
e
rf
o
r
m
e
d
,
it
sh
o
w
s
th
a
t
th
e
re
is
a
g
ra
d
u
a
l
i
n
c
re
a
se
in
p
re
d
ictio
n
a
c
c
u
ra
c
ies
w
it
h
th
e
in
c
re
a
se
in
th
e
a
tt
rib
u
tes
irres
p
e
c
ti
v
e
o
f
th
e
c
las
si
f
iers
u
se
d
a
n
d
Na
ïv
e
Ba
y
e
s
a
n
d
Ra
n
d
o
m
F
o
re
st
a
lg
o
rit
h
m
s
c
o
m
p
a
ra
ti
v
e
l
y
o
u
t
p
e
rf
o
rm
s
w
it
h
th
e
se
se
ts o
f
d
a
t
a
.
K
ey
w
o
r
d
s
:
Data
m
i
n
i
n
g
Hea
r
t a
il
m
e
n
ts
Naïv
e
b
a
y
e
s
class
if
ier
R
an
d
o
m
f
o
r
est
R
an
d
o
m
tr
ee
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
R
Stella M
ar
y
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
C
h
r
i
s
t
Un
iv
er
s
it
y
,
T
ai
w
a
n
1.
I
NT
RO
D
UCT
I
O
N
Data
m
i
n
in
g
in
v
o
l
v
es
th
e
e
x
p
lo
r
atio
n
o
f
h
u
g
e
d
atasets
in
o
r
d
er
to
m
i
n
e
u
n
k
n
o
w
n
,
v
er
if
iab
le,
r
elatio
n
s
h
ip
s
,
k
n
o
w
led
g
e
a
n
d
p
o
s
s
ib
l
y
h
elp
f
u
l
d
ata
f
r
o
m
in
f
o
r
m
atio
n
[
1
-
2
]
.
I
t
in
v
o
l
v
e
s
v
ar
io
u
s
s
tep
s
i
n
co
n
v
er
ti
n
g
a
r
a
w
d
ata
i
n
to
a
d
ata
w
i
th
u
s
e
f
u
l
i
n
f
o
r
m
atio
n
.
T
h
is
co
m
p
le
te
p
r
o
ce
s
s
in
v
o
lv
e
s
v
ar
io
u
s
s
tep
s
s
u
c
h
as
d
ata
clea
n
i
n
g
,
i
n
teg
r
atio
n
,
tr
an
s
f
o
r
m
atio
n
,
s
elec
tio
n
,
m
in
in
g
,
e
v
al
u
atio
n
o
f
p
atter
n
an
d
r
ep
r
esen
tatio
n
o
f
k
n
o
w
led
g
e.
T
h
is
h
as
m
ad
e
d
ata
m
in
i
n
g
f
i
n
d
its
ap
p
licatio
n
s
in
th
e
f
ield
s
o
f
h
ea
lth
ca
r
e,
b
u
s
i
n
es
s
,
ed
u
ca
tio
n
,
m
ed
ia,
w
ea
th
er
a
n
al
y
s
is
,
b
io
-
i
n
f
o
r
m
atics a
n
d
m
a
n
y
m
o
r
e.
I
n
h
ea
lth
ca
r
e,
d
ata
m
i
n
i
n
g
h
as
g
a
in
ed
w
id
e
in
ter
e
s
t
a
n
d
i
m
p
o
r
t
an
ce
a
n
d
h
a
s
b
ec
o
m
e
th
e
m
o
s
t
ef
f
icien
t
m
ea
n
s
i
n
d
iag
n
o
s
i
n
g
p
atien
ts
w
it
h
v
ar
io
u
s
ai
l
m
e
n
t
s
.
Me
d
ical
d
ata
is
r
ic
h
i
n
i
n
f
o
r
m
atio
n
b
u
t
lac
k
s
i
n
ter
m
s
o
f
to
o
ls
an
d
tec
h
n
o
lo
g
ies
to
ex
tr
ac
t
t
h
e
u
s
e
f
u
l
p
att
er
n
s
a
n
d
k
n
o
w
led
g
e
f
r
o
m
t
h
e
m
.
A
l
m
o
s
t
all
th
e
h
ea
lt
h
ca
r
e
in
d
u
s
tr
ie
s
to
d
a
y
al
l
s
tr
ea
m
in
g
o
u
t
a
lo
t
o
f
h
u
g
e
d
ata
as
i
n
,
d
ata
p
er
tain
i
n
g
to
p
a
tien
t
s
,
d
iag
n
o
s
is
o
f
v
ar
io
u
s
ai
l
m
e
n
t
s
,
p
atien
t
r
ec
o
r
d
s
in
elec
tr
o
n
ic
f
o
r
m
,
d
ata
ex
ca
v
ated
f
r
o
m
m
ed
ical
d
ev
ices
etc.
T
h
is
h
u
g
e
a
m
o
u
n
t
o
f
d
ata
i
s
p
r
o
ce
s
s
ed
a
n
d
an
al
y
ze
d
to
e
x
tr
ac
t
u
s
e
f
u
l
p
atter
n
s
w
h
ic
h
h
elp
s
i
n
f
a
s
t
d
i
ag
n
o
s
is
o
f
ail
m
e
n
ts
an
d
w
h
ic
h
ev
e
n
aid
s
i
n
co
s
t r
ed
u
ctio
n
.
Am
o
n
g
t
h
e
v
ar
io
u
s
ail
m
en
ts
,
h
ea
r
t
ail
m
e
n
t
i
s
o
n
e
a
m
o
n
g
t
h
e
m
ain
r
ea
s
o
n
f
o
r
d
ea
th
o
f
h
u
m
an
b
ei
n
g
s
all
ar
o
u
n
d
th
e
w
o
r
ld
in
las
t
d
ec
ad
e
b
y
th
e
W
HO.
T
h
e
E
u
r
o
p
ea
n
p
u
b
lic
h
ea
l
th
allia
n
ce
r
ep
o
r
ted
th
at
o
v
er
4
1
%
o
f
all
d
ea
t
h
s
w
er
e
ca
u
s
ed
b
y
s
tr
o
k
es,
h
ea
r
t
attac
k
s
,
a
n
d
o
th
er
ch
r
o
n
ic
d
is
ea
s
e
s
[
3
]
.
As
i
n
d
icate
d
b
y
t
h
e
Am
er
ica
n
Hea
r
t
Ass
o
ciatio
n
,
m
o
r
e
t
h
an
7
m
il
lio
n
Am
er
ica
n
s
h
a
v
e
s
u
ff
er
ed
a
h
ea
r
t
ail
m
e
n
t
in
t
h
eir
lif
et
i
m
e
.
A
t
t
h
e
p
o
in
t
w
h
en
p
laq
u
e
is
w
o
r
k
ed
i
n
s
id
e
th
e
co
r
o
n
ar
y
s
u
p
p
l
y
r
o
u
tes,
t
h
e
y
li
m
i
t
th
e
s
e
v
ein
s
m
a
k
i
n
g
t
h
e
m
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
P
r
ed
ictin
g
h
ea
r
t a
ilmen
t in
p
a
tien
ts
w
ith
va
r
yin
g
n
u
mb
er o
f
fea
tu
r
es u
s
in
g
d
a
ta
…
(
T R
S
te
lla
Ma
r
y
)
57
u
n
f
it
to
co
n
v
e
y
o
x
y
g
en
a
ted
b
lo
o
d
to
th
e
h
ea
r
t
m
u
s
cle
ca
u
s
in
g
t
h
e
o
u
t
s
ta
n
d
in
g
m
a
n
i
f
esta
tio
n
s
o
f
C
A
D,
f
o
r
ex
a
m
p
le,
ch
e
s
t
to
r
m
en
t
(
an
g
i
n
a)
a
n
d
s
h
o
r
tn
es
s
o
f
b
r
ea
th
[
4
-
5
]
.
T
h
er
e
ar
e
m
an
y
k
i
n
d
s
o
f
ca
r
d
io
v
a
s
cu
lar
d
is
ea
s
es
w
h
ich
i
n
clu
d
e
s
th
e
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e
s
(
C
H
D)
,
s
tr
o
k
e,
in
tr
in
s
ic
h
ea
r
t,
f
r
i
n
g
e
v
ein
,
r
h
e
u
m
atic
h
ea
r
t,
p
r
o
v
o
ca
tiv
e
h
ea
r
t
s
ic
k
n
es
s
an
d
h
y
p
er
te
n
s
i
v
e
co
r
o
n
ar
y
ill
n
es
s
[
6
-
8
]
.
T
h
e
ex
tr
e
m
e
r
ea
s
o
n
s
f
o
r
h
ea
r
t
illn
e
s
s
ar
e
to
b
ac
co
u
tili
za
tio
n
,
p
h
y
s
ica
l
laten
c
y
,
an
u
n
d
esira
b
l
e
ea
tin
g
r
e
g
i
m
e
n
a
n
d
cu
s
to
m
ar
y
u
s
e
o
f
l
iq
u
o
r
[
9
]
.
Me
d
ical
d
iag
n
o
s
i
s
is
an
i
m
p
o
r
tan
t
an
d
co
m
p
licated
tas
k
as
it
m
u
s
t
en
s
u
r
e
ac
cu
r
ate
r
esu
lt
s
an
d
n
ee
d
to
b
e
ex
ec
u
ted
p
r
ec
is
el
y
.
No
t
all
d
o
cto
r
s
ar
e
co
m
p
letel
y
w
el
l
v
er
s
ed
in
th
e
ir
v
ar
io
u
s
s
ec
to
r
s
an
d
t
h
er
e
i
s
lac
k
o
f
p
r
o
p
er
d
iag
n
o
s
is
.
T
h
is
p
av
e
s
w
a
y
f
o
r
an
d
t
h
e
s
tr
ea
m
o
f
d
ata
m
i
n
i
n
g
to
ea
s
e
t
h
e
tas
k
s
a
n
d
w
h
ich
is
ca
p
ab
le
o
f
p
er
f
o
r
m
i
n
g
t
h
e
d
ia
g
n
o
s
is
an
d
g
en
er
ate
t
h
e
r
es
u
lt
s
ac
cu
r
atel
y
w
it
h
le
s
s
h
u
m
a
n
i
n
ter
f
er
en
ce
a
n
d
le
s
s
in
v
e
s
t
m
e
n
t b
o
th
in
ter
m
s
o
f
m
o
n
e
y
an
d
ti
m
e
[
1
0
]
.
I
n
r
ea
l ti
m
e
th
er
e
ar
e
s
ev
er
al
t
ests
ta
k
e
n
to
p
r
ed
ict
an
d
d
iag
n
o
s
e
p
atien
ts
w
it
h
h
ea
r
t d
i
s
ea
s
e
s
w
h
ich
i
n
tu
r
n
g
i
v
e
s
t
h
e
ac
c
u
r
ate
r
es
u
lt
s
b
u
t t
u
r
n
s
o
u
t to
b
e
t
i
m
e
co
n
s
u
m
i
n
g
an
d
co
s
t e
f
f
ec
ti
v
e.
Me
a
n
w
h
ile
in
au
to
m
ated
ap
p
r
o
ac
h
p
e
o
p
le
aim
at
r
ed
u
cin
g
t
h
e
attr
ib
u
te
s
w
h
ic
h
in
t
u
r
n
r
ed
u
ce
s
th
e
ti
m
e
tak
e
n
b
u
t
lack
s
in
ac
cu
r
ac
y
s
in
ce
a
n
e
x
tr
a
ca
r
e
h
as
to
b
e
tak
en
to
en
s
u
r
e
t
h
at
a
p
atien
t
is
s
u
f
f
er
in
g
f
r
o
m
h
ea
r
t
ail
m
en
t
p
r
o
v
id
in
g
a
d
etailed
an
al
y
s
is
i
s
d
o
n
e
in
al
l
th
e
p
er
s
p
ec
tiv
es.
Kee
p
in
g
t
h
is
i
n
m
in
d
th
at
m
o
s
t
o
f
th
e
f
ea
t
u
r
es
af
f
ec
tin
g
h
ea
r
t
d
is
ea
s
e
m
u
s
t
b
e
co
n
s
id
er
ed
,
a
p
r
ed
icti
v
e
an
al
y
s
is
is
d
o
n
e
to
s
ee
h
o
w
th
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
v
ar
y
w
it
h
v
er
y
f
e
w
a
n
d
m
ax
i
m
u
m
f
ea
t
u
r
es
tak
e
n
.
T
h
i
s
p
ap
er
aim
s
at
p
r
o
v
id
in
g
a
m
o
r
e
e
f
f
icie
n
t
ap
p
r
o
ac
h
to
w
a
r
d
s
th
e
p
r
ed
ictio
n
o
f
h
ea
r
t
ail
m
en
ts
i
n
p
atie
n
ts
w
i
t
h
t
h
e
m
o
s
t
i
m
p
o
r
ta
n
t
attr
ib
u
te
s
af
f
ec
ti
n
g
t
h
e
p
atien
t
s
t
h
at
le
ad
s
to
h
ea
r
t
d
is
ea
s
e
an
d
an
al
y
ze
t
h
e
d
ata
as
to
h
o
w
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
f
l
u
c
tu
a
te
w
ith
m
i
n
i
m
al
an
d
m
a
x
i
m
al
attr
ib
u
te
s
tak
e
n
in
to
co
n
s
id
er
atio
n
u
s
in
g
t
h
e
d
ata
m
i
n
in
g
ap
p
r
o
ac
h
.
Nu
m
er
o
u
s
s
tu
d
ie
s
h
a
v
e
b
ee
n
p
er
f
o
r
m
ed
w
it
h
t
h
e
ai
m
o
f
e
f
f
icien
t
d
iag
n
o
s
i
s
an
d
p
r
ed
ictio
n
o
f
h
ea
r
t
ail
m
e
n
t.
Mo
s
t
o
f
th
e
a
u
t
h
o
r
s
h
av
e
ap
p
lied
d
if
f
er
en
t
d
ata
m
in
i
n
g
m
et
h
o
d
s
f
o
r
p
r
ed
ictio
n
an
d
h
a
v
e
co
m
e
u
p
w
it
h
d
i
f
f
er
e
n
t p
r
o
b
ab
ilit
ies o
f
ac
cu
r
ac
ies
f
o
r
d
if
f
er
e
n
t c
las
s
if
ier
s
.
R
an
d
a
E
l
-
B
ial
y
et
al.
,
[
1
1
]
d
ep
icts
th
a
t
h
e
ter
o
g
en
ei
t
y
d
ata
s
ets
g
i
v
es
i
n
h
eter
o
g
e
n
eit
y
d
ata
t
y
p
es,
b
ased
o
n
t
h
is
it
co
m
b
i
n
es
f
o
u
r
d
atasets
w
it
h
s
a
m
e
cla
s
s
lab
el
n
a
m
el
y
th
e
C
le
v
ela
n
d
h
ea
r
t
d
is
ea
s
e,
H
u
n
g
ar
ia
n
h
ea
r
t
d
is
ea
s
e,
V.
A
.
h
ea
r
t
d
is
e
ase
an
d
Statlo
g
p
r
o
j
ec
t
h
ea
r
t
d
is
ea
s
e
w
ith
1
3
f
ea
t
u
r
es
f
r
o
m
UC
I
r
ep
o
s
ito
r
y
an
d
ap
p
lies
C
4
.
5
an
d
Fa
s
t
Dec
i
s
i
o
n
tr
ee
i
n
o
r
d
er
to
co
n
s
tr
u
ct
d
ec
is
io
n
tr
ee
f
o
r
ea
ch
d
atas
et
an
d
co
m
p
ar
e
t
h
e
ac
cu
r
ac
ies
i
n
W
E
K
A
.
Ou
t
o
f
w
h
ic
h
f
i
v
e
co
m
m
o
n
f
ea
tu
r
e
s
a
r
e
s
elec
ted
an
d
ar
e
in
te
g
r
ated
in
to
a
n
e
w
d
ata
s
et,
o
n
w
h
ic
h
t
h
e
t
w
o
m
o
d
el
s
ar
e
ap
p
lied
ag
ain
,
w
h
ich
r
es
u
lt
s
i
n
t
h
e
f
o
u
r
m
o
s
t
co
m
m
o
n
l
y
o
c
cu
r
r
in
g
f
ea
tu
r
es
(
ca
,
ag
e,
cp
,
th
al)
w
ith
h
i
g
h
e
s
t
i
n
f
o
r
m
atio
n
g
ai
n
.
T
h
is
i
n
d
icate
s
th
at
t
h
ese
f
o
u
r
f
ea
tu
r
e
s
ar
e
th
e
m
o
s
t
i
m
p
o
r
tan
t
f
ea
t
u
r
es f
o
r
th
e
p
r
ed
ictio
n
o
f
h
ea
r
t d
is
ea
s
e.
Vik
as
C
h
au
r
as
ia
[
1
2
]
u
s
es
t
h
r
ee
d
ata
m
i
n
i
n
g
alg
o
r
it
h
m
s
C
A
R
T
,
I
D3
an
d
Dec
is
io
n
ta
b
le
o
n
th
e
C
lev
e
lan
d
h
ea
r
t
d
is
ea
s
e
d
atas
e
t
w
it
h
1
1
attr
ib
u
te
s
o
u
t
o
f
1
3
attr
ib
u
tes.
T
h
ese
s
3
cla
s
s
i
f
i
er
s
ar
e
i
m
p
le
m
e
n
ted
o
n
W
E
KA
w
it
h
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
A
d
etailed
r
esu
lt
i
n
ter
m
s
o
f
ti
m
e
tak
e
n
to
b
u
ild
th
e
m
o
d
el,
co
r
r
ec
tly
an
d
in
co
r
r
ec
tl
y
cla
s
s
i
f
ied
in
s
t
an
ce
s
,
er
r
o
r
r
ate,
co
n
f
u
s
io
n
m
atr
ic
es
a
n
d
ac
cu
r
ac
ies
ar
e
an
al
y
ze
d
f
o
r
all
th
e
th
r
ee
clas
s
i
f
ier
s
a
n
d
f
i
n
all
y
d
e
p
icts
th
at
C
AR
T
o
u
t
p
er
f
o
r
m
s
f
r
o
m
t
h
e
o
t
h
er
t
w
o
clas
s
if
ier
s
w
it
h
an
ac
cu
r
ac
y
o
f
8
3
.
4
9
%.
Fu
r
th
er
th
e
i
m
p
o
r
t
an
ce
o
f
ea
ch
attr
ib
u
te
is
a
n
al
y
ze
d
w
it
h
C
h
i
-
s
q
u
ar
ed
test
,
I
n
f
o
r
m
at
io
n
g
a
in
a
n
d
Gain
r
atio
test
w
h
ic
h
d
ep
icts
t
h
at
cp
attr
ib
u
tes i
m
p
ac
ts
t
h
e
o
u
tp
u
t t
h
e
m
o
s
t.
C
h
ai
tr
ali
S.
Dan
g
ar
e
an
d
S
u
la
b
h
a
S.
A
p
te
[
1
3
]
an
aly
s
es
th
e
C
lev
ela
n
d
h
ea
r
t
d
is
ea
s
e
d
ataset
w
i
th
3
class
i
f
ier
s
n
a
m
el
y
t
h
e
Ne
u
r
al
Net
w
o
r
k
s
,
Dec
is
io
n
tr
ee
s
a
n
d
Naïv
e
B
a
y
e
s
alg
o
r
it
h
m
s
.
T
o
t
h
is
e
x
is
tin
g
d
atase
t
t
w
o
m
o
r
e
attr
ib
u
te
s
o
b
esit
y
an
d
to
b
ac
co
ar
e
in
clu
d
ed
w
h
ich
m
a
k
es
u
p
f
o
r
th
e
n
e
x
t
d
ataset.
I
n
itiall
y
t
h
e
class
i
f
ier
s
ar
e
ap
p
lied
to
th
e
f
ir
s
t
d
ataset
w
i
th
1
3
attr
ib
u
tes
an
d
th
e
s
a
m
e
clas
s
i
f
ier
s
ar
e
ap
p
lied
to
th
e
n
e
x
t
d
ataset
w
i
th
1
5
attr
ib
u
tes.
F
in
all
y
,
a
d
etailed
an
al
y
s
is
o
f
th
eir
co
n
f
u
s
io
n
m
atr
ice
s
an
d
ac
cu
r
ac
ies
ar
e
co
m
p
ar
ed
b
et
w
ee
n
t
h
e
t
w
o
d
atasets
w
h
ic
h
d
ep
icts
t
h
at
f
o
r
th
e
d
ataset
w
i
th
1
3
attr
ib
u
te
s
Neu
r
al
Ne
t
w
o
r
k
o
u
tp
er
f
o
r
m
s
w
it
h
9
9
.
2
5
%
ac
cu
r
ac
y
a
n
d
f
o
r
th
e
d
ataset
w
it
h
1
5
attr
ib
u
tes
ag
ai
n
Neu
r
al
N
et
w
o
r
k
o
u
tp
er
f
o
r
m
s
w
it
h
1
0
0
%
ac
cu
r
ac
y
.
T
h
e
y
c
o
n
clu
d
e
t
h
at
Neu
r
al
Ne
t
w
o
r
k
alg
o
r
ith
m
o
u
tp
er
f
o
r
m
s
i
n
b
o
th
th
e
ca
s
es
a
n
d
h
a
s
r
elativ
el
y
h
i
g
h
er
ac
cu
r
ac
y
w
i
t
h
1
5
attr
ib
u
tes.
M.
A
n
b
ar
asi
et
al.
,
[
1
4
]
o
b
j
ec
tiv
e
w
as
to
d
ec
r
ea
s
e
t
h
e
n
u
m
b
er
o
f
attr
ib
u
te
s
f
o
r
w
h
ich
t
h
e
y
p
la
y
o
u
t
th
e
a
n
al
y
s
i
s
o
n
t
h
e
C
lev
ela
n
d
h
ea
r
t
d
i
s
ea
s
e
d
ata
s
et
w
i
th
1
3
attr
ib
u
tes.
Feat
u
r
e
s
u
b
s
et
s
el
ec
tio
n
i
s
p
er
f
o
r
m
ed
o
n
th
e
d
ataset
u
s
i
n
g
t
h
e
Gen
et
ic
alg
o
r
ith
m
w
h
ich
r
es
u
lt
s
w
it
h
6
attr
ib
u
tes
o
n
w
h
ich
t
h
e
cla
s
s
i
f
ier
s
ar
e
ap
p
lied
.
T
h
e
class
i
f
ier
s
u
s
ed
h
er
e
ar
e
Dec
is
io
n
tr
ee
,
Naïv
e
B
a
y
es
an
d
C
la
s
s
i
f
icatio
n
v
ia
C
lu
s
te
r
in
g
.
Fu
r
t
h
er
w
h
ile
co
m
p
ar
i
n
g
a
m
o
n
g
all
th
e
c
la
s
s
i
f
ier
s
w
it
h
t
h
eir
co
r
r
esp
o
n
d
in
g
co
n
f
u
s
io
n
m
atr
ices
a
n
d
a
cc
u
r
ac
ies,
Dec
i
s
io
n
tr
ee
o
u
tp
er
f
o
r
m
s
w
it
h
a
n
ac
cu
r
ac
y
o
f
9
9
.
2
%.
J
y
o
ti
R
o
h
i
lla
a
n
d
P
r
ee
ti
Gu
l
ia
[
1
5
]
p
er
f
o
r
m
s
t
h
e
a
n
al
y
s
is
o
n
th
e
C
le
v
elan
d
h
ea
r
t
d
is
ea
s
e
d
a
taset
w
i
th
1
1
attr
ib
u
tes
b
y
ap
p
l
y
i
n
g
t
h
e
class
i
f
ier
s
o
n
a
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
p
r
o
ce
s
s
.
T
h
e
d
if
f
er
en
t
class
if
ier
s
u
s
ed
ar
e
Naïv
e
B
ay
e
s
,
B
ag
g
i
n
g
,
I
D3
,
J
4
8
,
Sim
p
le
C
ar
t,
L
o
g
is
tic
R
e
g
r
es
s
io
n
a
n
d
R
E
PT
R
E
E
alg
o
r
ith
m
s
.
C
o
m
p
ar
ativ
e
l
y
t
h
e
Dec
is
io
n
t
r
ee
class
if
ier
I
D3
o
u
tp
er
f
o
r
m
s
w
ith
a
n
ac
cu
r
ac
y
o
f
8
8
%
an
d
w
i
th
a
m
in
i
m
u
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
8
,
No
.
1
,
A
p
r
il
20
1
9
:
5
6
–
62
58
er
r
o
r
.
Hen
ce
it
co
n
clu
d
es
th
at
th
e
Dec
i
s
io
n
tr
ee
m
et
h
o
d
th
a
t
is
I
D3
o
u
tp
er
f
o
r
m
s
w
h
en
co
m
p
ar
ed
to
all
o
t
h
er
class
i
f
ier
s
.
R
.
T
am
ilar
asi
a
n
d
Dr
.
R
.
P
o
r
k
o
d
i
[
1
6
]
aim
s
at
p
r
o
v
id
i
n
g
a
co
s
t
e
f
f
ec
t
iv
e
au
to
m
ated
s
y
s
te
m
i
n
p
r
ed
ictio
n
o
f
h
ea
r
t
ail
m
e
n
t
i
n
p
atien
ts
f
o
r
w
h
ich
t
h
e
a
d
ataset
w
it
h
1
3
attr
ib
u
tes
ar
e
co
n
s
id
er
ed
.
T
h
e
y
ev
e
n
s
p
ec
if
y
th
e
r
i
s
k
f
ac
to
r
s
o
f
h
ea
r
t
d
is
ea
s
e
w
h
ich
ar
e
s
m
o
k
in
g
,
ch
o
lest
er
o
l,
o
b
esit
y
a
n
d
lack
o
f
p
h
y
s
ical
e
x
er
cise.
T
o
an
aly
ze
t
h
is
d
atase
t
6
clas
s
if
ier
s
n
a
m
el
y
t
h
e
Naï
v
e
B
a
y
es,
KNN
alg
o
r
it
h
m
,
J
4
8
,
C
AR
T
,
A
NN
an
d
SM
O
ar
e
ap
p
lied
to
s
ee
w
h
ich
p
e
r
f
o
r
m
s
co
m
p
ar
ati
v
el
y
b
etter
in
ter
m
s
o
f
co
r
r
ec
tl
y
a
n
d
in
co
r
r
ec
tly
cla
s
s
i
f
ied
in
s
ta
n
ce
s
an
d
t
h
e
er
r
o
r
r
ate.
Hen
ce
,
it
co
n
cl
u
d
es
t
h
at
t
h
e
K
-
n
ea
r
est
n
ei
g
h
b
o
r
alg
o
r
it
h
m
o
u
tp
er
f
o
r
m
s
w
it
h
a
n
ac
cu
r
ac
y
o
f
1
0
0
%.
Sh
ab
ad
A
d
a
m
P
attek
ar
i
a
n
d
As
m
a
P
ar
v
ee
n
[
1
7
]
b
u
ilt
a
p
r
o
to
t
y
p
e
s
y
s
te
m
w
it
h
a
m
o
d
el
b
u
il
t
w
it
h
t
h
e
class
i
f
ier
s
n
a
m
el
y
Dec
i
s
io
n
t
r
ee
s
,
Naïv
e
B
a
y
e
s
a
n
d
A
r
tifi
cial
Neu
r
al
Ne
t
w
o
r
k
s
.
A
r
ea
l
ti
m
e
w
eb
s
ite
w
a
s
d
ev
elo
p
ed
ca
lled
th
e
Hea
r
t
D
is
ea
s
e
P
r
ed
ictio
n
S
y
s
te
m
(
H
DP
S)
w
h
er
e
in
it
r
etr
iev
e
s
th
e
d
ata
s
to
r
ed
in
th
e
d
atab
ase
an
d
p
r
ed
icts
if
th
e
p
a
tien
t
h
ad
h
ea
r
t d
is
ea
s
e
u
s
i
n
g
t
h
e
tr
ain
ed
d
ataset.
M.
Ak
h
ilj
ab
b
ar
et
al.
,
[
1
8
]
d
ev
elo
p
ed
an
e
f
f
icien
t
al
g
o
r
ith
m
u
s
i
n
g
t
h
e
g
en
et
ic
al
g
o
r
ith
m
ap
p
r
o
ac
h
k
n
o
w
n
as
t
h
e
A
s
s
o
ciat
iv
e
C
l
ass
i
f
icatio
n
alg
o
r
it
h
m
i
n
o
r
d
er
to
p
r
ed
ict
p
atien
ts
w
ith
h
ea
r
t
ail
m
en
t.
I
n
th
i
s
ap
p
r
o
ac
h
all
th
e
attr
ib
u
te
s
a
r
e
an
al
y
ze
d
an
d
m
ea
s
u
r
ed
i
n
ter
m
s
o
f
t
h
e
Gin
i
I
n
d
e
x
w
h
ic
h
i
n
t
u
r
n
g
iv
e
s
w
ei
g
h
tag
e
f
o
r
ea
ch
o
f
th
e
attr
i
b
u
tes
w
h
ich
h
elp
s
in
d
eter
m
i
n
in
g
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
f
ac
to
r
s
af
f
ec
ti
n
g
th
e
h
ea
r
t
d
is
ea
s
e.
T
h
en
th
e
Z
s
tati
s
tic
s
is
u
s
ed
to
an
al
y
ze
th
e
w
el
ln
e
s
s
o
f
th
e
r
u
le
o
b
tain
ed
.
Fi
n
all
y
,
b
ased
o
n
th
e
r
u
le
s
g
en
er
ated
t
h
e
class
if
ier
s
ar
e
b
u
ilt a
n
d
th
e
ac
cu
r
ac
y
o
f
t
h
e
d
ataset
is
m
ea
s
u
r
ed
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
A
ll
m
o
s
t
all
th
e
h
o
s
p
ital
s
to
d
ay
m
a
in
tai
n
v
as
t
a
m
o
u
n
t
o
f
h
ea
lt
h
ca
r
e
i
n
f
o
r
m
atio
n
o
b
tai
n
ed
f
r
o
m
p
atien
ts
,
f
r
o
m
elec
tr
o
n
ic
d
ev
i
ce
s
,
m
ed
ical
d
iag
n
o
s
i
s
etc.
T
h
is
h
u
g
e
a
m
o
u
n
t
o
f
d
ata
co
n
s
is
t
s
a
lo
t
o
f
u
s
ef
u
l
h
id
d
en
d
ata
i
n
t
h
e
m
w
h
ic
h
i
s
v
er
y
es
s
en
tial
i
n
d
ia
g
n
o
s
i
n
g
v
ar
io
u
s
a
il
m
e
n
t
s
w
it
h
a
m
i
n
i
m
u
m
n
u
m
b
er
o
f
m
ed
ical
test
s
an
d
m
a
k
e
th
e
d
iag
n
o
s
i
s
m
o
r
e
in
te
lli
g
en
t.
Ma
n
y
a
ti
m
es
w
e
li
m
it
o
u
r
s
elv
es
w
it
h
m
in
i
m
a
l
attr
ib
u
tes
t
h
at
ar
e
r
eq
u
ir
ed
to
p
r
ed
ict
a
p
atien
t
w
it
h
h
ea
r
t
d
is
ea
s
e.
B
y
d
o
in
g
s
o
w
e
ar
e
m
is
s
i
n
g
o
n
a
lo
t
o
f
i
m
p
o
r
tan
t
f
ea
tu
r
e
s
th
at
ar
e
m
ai
n
ca
u
s
es
f
o
r
h
ea
r
t d
is
ea
s
es.
T
ak
in
g
t
h
is
i
n
to
co
n
s
id
er
atio
n
,
an
ap
p
r
o
ac
h
is
p
r
o
p
o
s
ed
w
h
e
r
ein
all
th
e
attr
ib
u
tes
r
esp
o
n
s
i
b
le
f
o
r
th
e
h
ea
r
t
ail
m
e
n
t
i
n
p
atie
n
t
s
ar
e
co
n
s
id
er
ed
an
d
a
n
al
y
ze
d
in
a
s
tep
b
y
s
tep
p
r
o
ce
d
u
r
e
to
s
e
e
h
o
w
t
h
e
a
ttrib
u
te
s
p
lay
a
v
ital
r
o
le
in
p
r
ed
ictin
g
h
ea
r
t
ail
m
e
n
t
in
p
atie
n
ts
.
He
n
ce
,
th
e
p
r
e
-
d
o
m
i
n
an
t
o
b
j
ec
ti
v
e
is
to
p
r
o
v
id
e
a
m
o
r
e
ef
f
ic
ien
t
ap
p
r
o
ac
h
to
w
a
r
d
s
th
e
p
r
ed
ictio
n
o
f
h
ea
r
t
ail
m
en
ts
w
it
h
th
e
m
o
s
t
i
m
p
o
r
tan
t
attr
ib
u
te
s
ca
u
s
in
g
h
ea
r
t
ail
m
en
t
a
n
d
an
a
l
y
ze
t
h
e
d
ata,
as
to
h
o
w
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
f
lu
c
tu
ate
w
it
h
m
i
n
i
m
al
a
n
d
m
a
x
i
m
al
attr
ib
u
tes ta
k
en
i
n
to
co
n
s
id
er
atio
n
u
s
in
g
t
h
e
d
ata
m
i
n
i
n
g
ap
p
r
o
ac
h
.
Fo
r
w
h
ich
a
b
e
n
ch
m
ar
k
h
ea
r
t
ail
m
e
n
t
d
ataset
i.e
.
C
lev
e
lan
d
h
ea
r
t
d
is
ea
s
e
d
ataset
alo
n
g
w
it
h
it
t
w
o
m
o
r
e
m
i
n
i
m
al
d
atase
ts
w
i
th
s
a
m
e
clas
s
lab
el
ar
e
u
s
ed
.
Me
d
ical
ter
m
i
n
o
lo
g
ies
s
u
ch
a
s
s
ex
,
ch
e
s
t
p
ain
t
y
p
e,
an
d
ag
e
etc.
,
m
a
k
i
n
g
u
p
f
o
r
7
attr
ib
u
tes
i
n
f
ir
s
t
d
ataset,
1
0
attr
ib
u
tes
in
s
ec
o
n
d
d
ataset
an
d
1
3
attr
ib
u
tes
in
th
e
b
en
ch
m
ar
k
d
ataset
ar
e
u
s
ed
.
T
o
im
p
r
o
v
i
s
e
th
e
r
esu
lts
,
s
te
p
b
y
s
tep
ap
p
r
o
ac
h
is
f
o
llo
wed
in
i
n
cr
ea
s
i
n
g
t
h
e
n
u
m
b
er
o
f
attr
ib
u
tes
an
d
an
al
y
ze
to
s
ee
if
th
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
r
ed
u
ce
d
o
r
g
r
ad
u
ally
in
cr
ea
s
ed
.
T
h
e
d
ata
m
i
n
in
g
cla
s
s
i
f
icatio
n
m
et
h
o
d
s
u
s
ed
to
class
i
f
y
th
e
d
atase
ts
ar
e
Dec
is
io
n
T
r
ee
s
(
R
an
d
o
m
Fo
r
est
an
d
R
a
n
d
o
m
T
r
ee
)
an
d
Naiv
e
B
ay
e
s
ar
e
u
s
e
d
.
T
h
is
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
i
n
d
s
it
s
ap
p
licatio
n
i
n
p
r
ed
ictin
g
t
h
e
h
ea
r
t
ai
l
m
e
n
t
s
i
n
p
ati
en
ts
as
it
co
n
s
id
er
s
all
th
e
i
m
p
o
r
ta
n
t
att
r
ib
u
tes
o
r
f
ea
tu
r
es
r
esp
o
n
s
ib
le
in
ca
u
s
i
n
g
a
h
ea
r
t
ail
m
e
n
t.
I
t
r
ed
u
ce
s
th
e
s
e
v
er
al
test
s
an
d
t
i
m
e
ta
k
en
to
p
r
ed
ict
an
d
d
ia
g
n
o
s
e
p
atie
n
ts
w
it
h
h
ea
r
t
d
is
ea
s
es
an
d
i
s
al
s
o
co
s
t
ef
f
ec
ti
v
e.
T
h
e
d
if
f
er
e
n
t d
ata
m
i
n
i
n
g
class
i
f
ie
r
s
u
s
ed
ar
e
Naïv
e
B
a
y
e
s
,
Dec
i
s
io
n
tr
ee
s
R
an
d
o
m
Fo
r
est an
d
R
an
d
o
m
T
r
ee
.
2
.
1
.
Na
ï
v
e
B
a
y
es
T
h
is
alg
o
r
ith
m
h
as
its
b
as
is
f
r
o
m
t
h
e
B
a
y
e
s
t
h
eo
r
e
m
a
n
d
f
o
llo
w
s
th
e
co
n
ce
p
t
o
f
c
o
n
d
itio
n
al
in
d
ep
en
d
en
ce
i.e
.
,
it
co
n
s
id
er
s
an
attr
ib
u
te
v
alu
e
o
f
a
g
i
v
e
n
class
to
b
e
i
n
d
ep
en
d
en
t
o
f
o
t
h
er
attr
ib
u
tes
v
al
u
es.
T
h
e
m
ai
n
o
b
j
ec
tiv
e
is
to
m
a
x
i
m
ize
t
h
e
p
o
s
ter
io
r
p
r
o
b
ab
ilit
y
in
p
r
ed
ictin
g
th
e
cla
s
s
[
1
9
]
.
T
h
e
B
ay
es t
h
eo
r
e
m
is
a
s
f
o
llo
w
s
:
L
et
X=
{
x
1
,
x
2
,
.
.
.
.
.
,
x
m
}
b
e
a
s
et
o
f
m
attr
ib
u
te
s
.
I
n
B
a
y
esia
n
,
X
is
co
n
s
id
er
ed
as
ev
id
en
ce
an
d
H
b
e
s
o
m
e
h
y
p
o
th
e
s
is
t
h
at
t
h
e
d
ata
o
f
X
b
elo
n
g
s
to
s
p
ec
i
f
ic
clas
s
C
.
W
e
h
av
e
to
d
eter
m
i
n
e
P
(
H|
X)
,
th
e
p
r
o
b
ab
ilit
y
th
at
th
e
h
y
p
o
th
e
s
is
H
h
o
ld
s
g
i
v
en
t
h
e
e
v
id
en
ce
i.e
.
d
ata
s
a
m
p
le
X.
A
cc
o
r
d
in
g
to
B
a
y
e
s
t
h
e
o
r
em
t
h
e
P
(
H
|
X)
i
s
ex
p
r
ess
ed
as
P
(
H|
X)
=
P
(
X|
H)
P
(
H)
/ P
(
X)
Naïv
e
B
a
y
es c
la
s
s
i
f
ier
p
er
f
o
r
m
s
r
elati
v
el
y
b
etter
w
i
th
n
o
m
i
n
al
d
ata
b
u
t n
o
t
w
it
h
n
u
m
e
r
ic
d
ata
[
2
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
P
r
ed
ictin
g
h
ea
r
t a
ilmen
t in
p
a
tien
ts
w
ith
va
r
yin
g
n
u
mb
er o
f
fea
tu
r
es u
s
in
g
d
a
ta
…
(
T R
S
te
lla
Ma
r
y
)
59
2
.
2
.
Ra
nd
o
m
T
re
e
I
t
u
s
es
th
e
co
n
ce
p
t
o
f
d
iv
id
e
an
d
co
n
q
u
er
in
o
r
d
er
to
b
u
ild
d
ec
is
io
n
tr
ee
s
[
2
1
]
.
A
t
ea
ch
n
o
d
e
o
f
th
e
tr
ee
,
th
e
al
g
o
r
ith
m
ta
k
es
u
p
a
f
ea
t
u
r
e
th
at
f
u
r
t
h
er
d
iv
id
es
t
h
e
d
ata
in
to
s
u
b
s
ets
w
i
th
th
e
h
elp
o
f
a
s
p
litt
i
n
g
alg
o
r
ith
m
[
2
2
]
.
E
v
er
y
p
r
ed
ictin
g
n
o
d
e
lead
s
to
a
cla
s
s
o
r
d
ec
is
io
n
r
u
le.
I
n
o
r
d
er
to
class
if
y
a
n
e
w
ite
m
,
i
t
s
h
o
u
ld
b
u
ild
a
d
ec
is
io
n
tr
ee
t
ak
in
g
in
to
co
n
s
id
er
atio
n
t
h
e
e
x
is
t
in
g
i
te
m
s
i
n
th
e
tr
ain
in
g
s
et.
W
ith
th
e
h
elp
o
f
in
f
o
r
m
atio
n
g
ai
n
it
f
i
n
d
s
th
e
d
ep
en
d
en
t
v
ar
iab
le
th
at
clea
r
l
y
d
i
s
cr
i
m
i
n
ate
s
o
th
er
in
s
tan
ce
s
.
No
w
a
m
o
n
g
t
h
e
p
o
s
s
ib
le
v
al
u
es
o
f
th
is
v
ar
iab
le
if
a
n
y
o
f
t
h
e
v
al
u
e
t
u
r
n
s
o
u
t
to
b
e
th
e
tar
g
et
v
al
u
e
o
r
leaf
n
o
d
e
an
d
w
e
ca
n
ter
m
i
n
ate
th
at
b
r
an
c
h
.
Hen
ce
w
e
f
o
llo
w
t
h
is
m
et
h
o
d
u
n
ti
l
w
e
g
et
th
e
d
ec
is
io
n
r
u
les
o
f
d
if
f
er
en
t
co
m
b
i
n
atio
n
o
f
f
ea
t
u
r
es lea
d
s
to
th
e
tar
g
et
v
alu
e.
2
.
3
.
Ra
nd
o
m
F
o
re
s
t
I
t
is
a
clas
s
i
f
ier
w
h
ich
co
n
s
i
s
ts
o
f
n
n
u
m
b
er
o
f
d
ec
is
io
n
tr
ee
s
w
h
er
e
i
n
ea
c
h
i
n
d
iv
id
u
al
r
esu
lt
is
d
ep
icted
as
a
s
ep
ar
ate
tr
ee
.
I
t
w
a
s
d
er
iv
ed
f
r
o
m
th
e
r
an
d
o
m
d
ec
is
io
n
o
f
f
o
r
est
th
a
t
w
a
s
p
r
o
p
o
s
ed
b
y
T
in
Kam
Ho
o
f
B
ell
L
ab
s
i
n
1
9
9
5
[
2
3
]
.
T
h
is
ap
p
r
o
ac
h
d
o
es
th
e
s
e
le
ctio
n
o
f
a
ttrib
u
te
s
r
an
d
o
m
l
y
i
n
o
r
d
er
to
b
u
ild
th
e
d
ec
is
io
n
tr
ee
s
b
u
t
w
ith
r
estri
cted
f
lu
ct
u
atio
n
s
.
Mu
lti
-
cla
s
s
if
ier
s
ar
e
th
e
af
ter
ef
f
ec
t
o
f
co
m
b
i
n
in
g
a
f
e
w
in
d
ep
en
d
en
t
cla
s
s
i
f
ier
s
a
n
d
s
e
ts
o
f
clas
s
i
f
ier
s
r
esp
o
n
s
ib
le
f
o
r
b
r
o
a
d
en
in
g
th
e
e
x
ec
u
tio
n
h
a
v
e
b
ee
n
d
ep
icted
in
Fig
u
r
e
1
[
2
4
]
.
Fig
u
r
e
1
.
A
r
ch
itectu
r
al
d
ia
g
r
am
o
f
p
r
o
p
o
s
ed
w
o
r
k
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
In
W
aik
ato
E
n
v
ir
o
n
m
e
n
t
f
o
r
Kn
o
w
led
g
e
An
al
y
s
is
(
W
E
K
A)
is
u
s
ed
f
o
r
a
n
al
y
z
in
g
a
n
d
ap
p
ly
in
g
t
h
e
d
if
f
er
e
n
t
clas
s
i
f
ier
s
o
n
th
e
d
at
asets
b
ec
au
s
e
o
f
i
ts
e
x
ce
lle
n
c
e
in
d
is
co
v
er
i
n
g
,
an
al
y
s
is
a
n
d
p
r
ed
ictin
g
e
f
f
icien
t
p
atter
n
s
[
2
5
]
.
A
d
etailed
a
n
al
y
s
i
s
i
s
d
o
n
e
i
n
W
ek
a
w
h
e
r
ein
T
ab
le
1
r
ep
r
esen
ts
t
h
e
r
esu
lt
s
o
b
tain
ed
b
y
ap
p
ly
i
n
g
th
e
cla
s
s
i
f
ier
s
o
n
a
d
ataset
o
f
7
attr
ib
u
tes.
T
ab
le
2
d
ep
icts
th
e
r
esu
lts
o
b
tain
e
d
b
y
ap
p
l
y
i
n
g
t
h
e
class
i
f
ier
s
o
n
a
d
ataset
o
f
1
0
attr
ib
u
tes
an
d
T
ab
le
3
d
ep
icts
th
e
r
esu
l
ts
o
b
tain
ed
b
y
ap
p
l
y
in
g
th
e
clas
s
i
f
ier
s
o
n
a
d
ataset
o
f
1
3
attr
i
b
u
tes.
Fig
u
r
e
2
d
ep
icts
th
e
g
r
ad
u
al
in
cr
ea
s
e
in
th
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
alo
n
g
w
it
h
t
h
e
in
cr
ea
s
e
i
n
th
e
attr
ib
u
tes.
T
ab
le
1
.
A
cc
u
r
ac
ies
A
c
h
ie
v
ed
w
it
h
7
A
ttrib
u
te
s
Ev
a
l
u
a
t
i
o
n
c
r
i
t
e
r
i
a
C
l
a
ssi
f
i
e
r
s
N
a
ï
v
e
B
a
y
e
s
Ra
n
d
o
m
F
o
r
e
st
Ra
n
d
o
m
T
re
e
T
i
me
t
a
k
e
n
t
o
b
u
i
l
d
mo
d
e
l
(
i
n
se
c
)
0
0
.
2
5
0
C
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
s
t
a
n
c
e
s
71
72
68
I
n
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
st
a
n
c
e
s
20
19
23
A
c
c
u
r
a
c
y
(
%)
7
8
.
0
2
2
%
7
9
.
1
2
0
9
%
7
4
.
7
2
5
3
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
8
,
No
.
1
,
A
p
r
il
20
1
9
:
5
6
–
62
60
T
ab
le
2
.
A
cc
u
r
ac
ies
A
c
h
ie
v
ed
w
it
h
1
0
A
t
tr
ib
u
tes
.
Ev
a
l
u
a
t
i
o
n
c
r
i
t
e
r
i
a
C
l
a
ssi
f
i
e
r
s
N
a
ï
v
e
B
a
y
e
s
Ra
n
d
o
m
F
o
r
e
st
Ra
n
d
o
m
T
re
e
T
i
me
t
a
k
e
n
t
o
b
u
i
l
d
mo
d
e
l
(
i
n
se
c
)
0
0
.
1
4
0
C
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
s
t
a
n
c
e
s
72
71
67
I
n
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
st
a
n
c
e
s
15
16
20
A
c
c
u
r
a
c
y
(
%)
8
2
.
7
5
8
6
%
8
1
.
6
0
9
2
%
7
7
.
0
1
1
5
%
T
ab
le
3
.
A
cc
u
r
ac
ies
A
c
h
ie
v
ed
w
it
h
1
3
A
t
tr
ib
u
tes
Ev
a
l
u
a
t
i
o
n
c
r
i
t
e
r
i
a
C
l
a
ssi
f
i
e
r
s
N
a
ï
v
e
B
a
y
e
s
Ra
n
d
o
m
F
o
r
e
st
Ra
n
d
o
m
T
re
e
T
i
me
t
a
k
e
n
t
o
b
u
i
l
d
mo
d
e
l
(
i
n
se
c
)
0
0
.
1
4
0
C
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
s
t
a
n
c
e
s
76
79
72
I
n
c
o
r
r
e
c
t
l
y
c
l
a
ssi
f
i
e
d
i
n
st
a
n
c
e
s
15
12
19
A
c
c
u
r
a
c
y
(
%)
8
3
.
5
1
6
5
%
8
6
.
8
1
3
2
%
7
9
.
1
2
0
9
%
Fig
u
r
e
2
.
Flu
ct
u
atio
n
s
in
p
r
ed
i
ctio
n
ac
cu
r
ac
ies.
T
h
e
in
itial
d
ataset
(
Data
s
et
-
1
)
co
n
s
i
s
ts
o
f
7
attr
ib
u
te
s
m
a
k
i
n
g
u
p
f
o
r
3
0
0
r
ec
o
r
d
s
n
a
m
el
y
ag
e
w
h
ic
h
is
co
n
ti
n
u
o
u
s
attr
ib
u
te,
s
e
x
wh
ich
i
s
ca
teg
o
r
ical
attr
ib
u
te,
e
x
er
cise
in
d
u
ce
d
ag
i
n
a
w
h
ic
h
i
s
n
o
m
i
n
al
attr
ib
u
te,
d
ep
r
ess
io
n
in
d
u
ce
d
b
y
ex
er
ci
s
e
f
o
r
m
in
g
t
h
e
c
ate
g
o
r
ical
att
r
ib
u
te,
s
lo
p
e
o
f
p
ea
k
e
x
er
cise
ag
ai
n
a
ca
teg
o
r
ical
attr
ib
u
te,
n
u
m
b
er
o
f
m
aj
o
r
v
ess
els a
n
o
m
i
n
al
attr
ib
u
te
a
n
d
f
i
n
all
y
th
e
d
e
f
ec
t t
y
p
e
w
h
ich
i
s
ca
teg
o
r
ical
ag
ai
n
.
T
h
e
s
ec
o
n
d
d
ataset
(
Data
s
et
-
2
)
co
n
s
i
s
ts
o
f
al
l t
h
e
f
ir
s
t
d
atase
t a
ttrib
u
te
s
alo
n
g
w
it
h
ad
d
itio
n
al
3
m
o
r
e
attr
ib
u
tes
n
a
m
el
y
t
h
e
ch
es
t
p
ain
t
y
p
e
w
h
ich
i
s
a
ca
teg
o
r
ical
attr
ib
u
te,
ch
o
lest
er
o
l
w
h
ic
h
is
co
n
tin
u
o
u
s
an
d
r
esti
n
g
E
C
G
m
ea
s
u
r
e
ag
ai
n
ca
teg
o
r
ical
attr
ib
u
te
to
tall
y
m
a
k
in
g
u
p
f
o
r
2
9
0
r
ec
o
r
d
s
.
Data
s
et
-
1
an
d
Data
s
e
t
-
2
ar
e
co
llected
b
y
ta
k
i
n
g
in
to
co
n
s
id
er
atio
n
th
e
v
ar
io
u
s
h
ea
r
t
a
il
m
e
n
t
attr
ib
u
tes
t
h
r
o
u
g
h
a
s
u
r
v
e
y
d
o
n
e
w
it
h
t
h
e
p
atien
ts
.
F
in
al
l
y
,
t
h
e
t
h
ir
d
d
ataset
C
le
v
ela
n
d
Hea
r
t
Dis
ea
s
e
d
ataset
co
n
s
i
s
ts
o
f
3
0
3
r
ec
o
r
d
s
w
it
h
1
3
attr
ib
u
tes
is
u
s
ed
.
P
r
ed
ictab
le
attr
ib
u
te
(
n
u
m
)
is
a
co
m
m
o
n
cla
s
s
lab
el
f
o
r
all
th
e
th
r
ee
d
atasets
w
h
er
ein
,
Valu
e
=
0
: d
ep
icts
th
at
t
h
e
p
atien
t h
a
s
n
o
h
ea
r
t d
is
ea
s
e
Valu
e
=
1
: d
ep
icts
th
at
t
h
e
p
atien
t h
a
s
h
ea
r
t d
is
ea
s
e.
A
ll
t
h
e
d
ataset
ar
e
an
al
y
ze
d
an
d
th
e
clas
s
if
ier
s
ar
e
ap
p
lie
d
o
n
a
b
asis
o
f
7
0
%
s
p
lit
i.e
.
,
7
0
%
o
f
d
ataset
is
u
s
ed
as tr
ain
i
n
g
d
ata
an
d
3
0
% a
s
test
in
g
d
ata.
Ste
p
–
1:
P
r
e
-
p
r
o
ce
s
s
in
g
o
f
d
atasets
.
Data
s
et
-
1
w
it
h
7
a
ttrib
u
te
s
d
i
d
n
’
t
h
a
v
e
a
n
y
m
i
s
s
i
n
g
v
alu
e
s
an
d
s
o
d
o
es
th
e
s
ec
o
n
d
d
atas
et.
B
u
t
t
h
e
th
ir
d
Data
s
et
-
3
h
ad
m
is
s
in
g
v
alu
e
s
w
h
ic
h
w
a
s
r
ec
ti
f
ied
b
y
u
s
i
n
g
th
e
W
ek
a
f
ilter
R
ep
l
ac
eM
is
s
i
n
g
Val
u
es.
Sin
ce
t
h
e
cla
s
s
v
ar
iab
le
is
th
e
s
a
m
e
f
o
r
all
t
h
e
d
ataset
s
it i
s
c
o
n
v
er
ted
f
r
o
m
n
u
m
er
ic
to
n
o
m
i
n
al
u
s
i
n
g
th
e
f
i
lter
n
u
m
er
ic
to
n
o
m
i
n
al
u
n
d
er
t
h
e
u
n
s
u
p
er
v
is
ed
attr
ib
u
te
f
i
lter
s
i
n
o
r
d
er
to
m
a
k
e
f
e
w
o
f
t
h
e
cl
ass
i
f
ie
r
s
li
k
e
Naï
v
e
B
ay
e
s
an
d
Dec
i
s
io
n
tr
ee
s
to
b
e
ap
p
licab
le.
Fu
r
th
er
th
e
m
u
lti
-
clas
s
clas
s
i
f
icatio
n
i
n
t
h
e
th
ir
d
b
en
ch
m
ar
k
d
ataset
is
co
n
v
er
ted
t
w
o
-
clas
s
clas
s
i
f
icatio
n
.
t
h
is
s
ec
tio
n
,
i
t
is
ex
p
lai
n
ed
t
h
e
r
e
s
u
lt
s
o
f
r
esear
ch
a
n
d
at
th
e
s
a
m
e
ti
m
e
i
s
g
i
v
e
n
t
h
e
co
m
p
r
eh
en
s
iv
e
d
is
c
u
s
s
io
n
.
R
es
u
lt
s
ca
n
b
e
p
r
esen
ted
in
f
i
g
u
r
es,
g
r
ap
h
s
,
tab
les
a
n
d
o
th
er
s
th
at
m
a
k
e
th
e
r
ea
d
er
u
n
d
er
s
tan
d
ea
s
il
y
[
2
]
,
[
5
]
.
78.02%
79.12%
74.73%
82.76%
81.61%
77.01%
83.52%
86.81%
79.12%
N
A
ÏV
E
B
A
Y
E
S
R
A
N
DO
M
F
O
R
E
S
T
R
A
N
DO
M T
R
E
E
Flu
ctua
tion
in
p
r
e
d
ictio
n
acc
u
r
acie
s
Datas
e
t-1
Datas
e
t-2
Datas
e
t-3
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
I
C
T
I
SS
N:
2252
-
8776
P
r
ed
ictin
g
h
ea
r
t a
ilmen
t in
p
a
tien
ts
w
ith
va
r
yin
g
n
u
mb
er o
f
fea
tu
r
es u
s
in
g
d
a
ta
…
(
T R
S
te
lla
Ma
r
y
)
61
R
es
u
lts
ar
e
a
n
al
y
ze
d
b
y
ap
p
ly
in
g
t
h
e
t
h
r
ee
class
if
ier
s
Naï
v
e
B
a
y
es,
R
an
d
o
m
T
r
ee
an
d
R
an
d
o
m
Fo
r
est
o
n
all
th
e
th
r
ee
d
ata
s
et
s
to
s
ee
if
th
er
e
ar
e
f
lu
ct
u
atio
n
s
in
th
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
a
f
ter
ap
p
ly
in
g
t
h
e
m
to
b
u
ild
th
e
m
o
d
els.
Ste
p
–
2:
A
p
p
ly
t
h
e
3
class
if
ie
r
s
o
n
th
e
d
ataset
w
i
th
7
attr
ib
u
tes.
I
n
itiall
y
,
th
e
Data
s
et
-
1
w
it
h
7
attr
ib
u
tes
is
p
r
e
-
p
r
o
ce
s
s
ed
an
d
th
e
class
lab
el
is
co
n
v
er
ted
to
n
o
m
i
n
al
u
s
i
n
g
t
h
e
f
ilter
N
u
m
er
ic
to
No
m
i
n
al
o
n
w
h
ich
t
h
e
3
clas
s
i
f
ie
r
s
ar
e
ap
p
lied
.
I
t
is
e
v
id
en
t
f
r
o
m
T
ab
le
1
th
at
th
e
R
an
d
o
m
f
o
r
est al
g
o
r
ith
m
o
u
tp
er
f
o
r
m
s
w
i
th
7
attr
ib
u
te
s
.
Ste
p
–
3:
A
p
p
ly
t
h
e
3
class
if
ie
r
s
o
n
th
e
d
ataset
w
i
th
1
0
attr
ib
u
t
es.
Seco
n
d
l
y
,
th
e
Data
s
et
-
2
w
i
th
1
0
attr
i
b
u
tes
is
p
r
e
-
p
r
o
ce
s
s
ed
an
d
th
e
class
lab
el
is
co
n
v
er
ted
to
n
o
m
i
n
al
u
s
i
n
g
th
e
f
ilter
N
u
m
e
r
ic
to
No
m
i
n
al
o
n
w
h
ic
h
th
e
3
class
i
f
ier
s
ar
e
ap
p
lied
.
I
t
is
e
v
id
en
t
f
r
o
m
T
ab
le
2
th
at
th
e
Naï
v
e
B
a
y
e
s
al
g
o
r
ith
m
o
u
tp
er
f
o
r
m
s
a
n
d
t
h
e
ac
c
u
r
ac
ies
o
f
al
l
t
h
e
class
i
f
ier
s
ar
e
g
r
ad
u
all
y
in
cr
ea
s
ed
w
it
h
t
h
e
ad
d
itio
n
o
f
3
m
o
r
e
attr
ib
u
tes
c
h
est
p
ai
n
t
y
p
e,
ch
o
lest
er
o
l
an
d
E
C
G
m
ea
s
u
r
e
to
th
e
Data
s
et
-
1
.
Ste
p
–
4:
A
p
p
ly
t
h
e
3
class
if
ie
r
s
o
n
th
e
d
ataset
w
i
th
1
3
attr
ib
u
tes.
Fin
all
y
,
t
h
e
Data
s
e
t
-
3
w
ith
1
3
attr
ib
u
tes
is
p
r
e
-
p
r
o
ce
s
s
ed
an
d
th
e
class
lab
el
is
co
n
v
er
ted
to
n
o
m
in
a
l
u
s
i
n
g
t
h
e
f
ilter
N
u
m
er
ic
to
No
m
i
n
al
o
n
w
h
ich
t
h
e
3
clas
s
i
f
ie
r
s
ar
e
ap
p
lied
.
I
t
is
e
v
id
en
t
f
r
o
m
T
ab
le
3
th
at
th
e
R
an
d
o
m
Fo
r
est
alg
o
r
it
h
m
o
u
t
p
er
f
o
r
m
s
an
d
t
h
e
ac
cu
r
ac
ies
o
f
all
th
e
cla
s
s
i
f
ier
s
ar
e
g
r
ad
u
all
y
i
n
cr
ea
s
ed
w
it
h
th
e
ad
d
itio
n
o
f
3
m
o
r
e
attr
ib
u
t
es b
lo
o
d
p
r
ess
u
r
e,
f
as
tin
g
s
u
g
a
r
an
d
th
alac
h
to
t
h
e
Data
s
et
-
2
.
Fro
m
th
e
T
ab
le
4
it
is
ev
id
en
t
th
a
t
w
it
h
th
e
i
n
cr
ea
s
e
i
n
t
h
e
n
u
m
b
er
o
f
attr
ib
u
tes,
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
h
av
e
g
r
ad
u
all
y
in
cr
ea
s
ed
ir
r
esp
ec
tiv
e
o
f
t
h
e
clas
s
if
ier
s
u
s
ed
an
d
t
h
e
d
ataset
v
al
u
es.
Mo
r
eo
v
er
,
f
o
r
d
if
f
er
e
n
t
d
atasets
d
i
f
f
er
e
n
t
cla
s
s
i
f
ier
s
o
u
tp
er
f
o
r
m
s
i.e
.
,
in
ca
s
e
o
f
Data
s
et
-
1
w
ith
7
attr
ib
u
t
es
R
an
d
o
m
Fo
r
est
class
i
f
ier
o
u
tp
er
f
o
r
m
s
w
it
h
a
n
ac
cu
r
ac
y
o
f
7
9
.
1
2
0
9
%,
w
h
er
ea
s
f
o
r
Data
s
et
-
2
w
it
h
1
0
attr
i
b
u
tes
Naï
v
e
B
a
y
es
class
i
f
ier
o
u
tp
er
f
o
r
m
s
w
it
h
a
n
ac
cu
r
ac
y
o
f
8
2
.
7
5
8
6
%
an
d
f
in
al
l
y
f
o
r
th
e
Data
s
e
t
-
3
w
it
h
1
3
attr
ib
u
tes
t
h
e
R
an
d
o
m
Fo
r
est
attr
ib
u
te
o
u
t
p
er
f
o
r
m
s
.
He
n
ce
,
it
clea
r
l
y
s
h
o
w
s
th
at
co
n
s
id
er
atio
n
o
f
all
th
e
i
m
p
o
r
tan
t
attr
ib
u
tes o
r
f
ea
t
u
r
es c
o
n
tr
ib
u
t
e
to
a
b
etter
an
d
ac
cu
r
ate
p
r
e
d
ictio
n
o
f
h
ea
r
t d
is
ea
s
es i
n
p
atie
n
ts
.
Fro
m
th
e
Fi
g
u
r
e
2
it
is
ev
id
en
t
th
at
th
er
e
is
a
g
r
a
d
u
al
i
n
cr
ea
s
e
in
th
e
p
r
ed
ictio
n
ac
cu
r
ac
ies
an
al
y
ze
d
o
n
th
e
th
r
ee
d
atasets
w
it
h
d
if
f
er
en
t
n
u
m
b
er
o
f
attr
ib
u
tes
an
d
v
alu
es
u
s
i
n
g
th
e
ab
o
v
e
th
r
ee
class
i
f
ier
s
.
I
t
ev
en
d
ep
icts
th
at
i
n
ca
s
e
o
f
Data
s
et
-
1
R
a
n
d
o
m
f
o
r
est
alg
o
r
it
h
m
o
u
tp
er
f
o
r
m
s
,
f
o
r
Data
s
e
t
-
2
Naï
v
e
B
a
y
es
a
lg
o
r
it
h
m
o
u
tp
er
f
o
r
m
s
w
it
h
an
ac
cu
r
ac
y
o
f
8
2
.
7
5
%
an
d
f
o
r
Data
s
et
-
3
ag
ai
n
R
an
d
o
m
f
o
r
est
o
u
t
p
er
f
o
r
m
s
w
it
h
an
ac
cu
r
ac
y
o
f
8
6
.
8
1
%.
T
ab
le
4
.
A
cc
u
r
ac
y
Fl
u
ct
u
atio
n
s
a
m
o
n
g
t
h
e
3
Data
s
ets
D
a
t
a
se
t
s
C
l
a
ssi
f
i
e
r
s
N
a
ï
v
e
B
a
y
e
s
Ra
n
d
o
m
F
o
r
e
st
Ra
n
d
o
m
T
re
e
D
a
t
a
se
t
-
1
7
8
.
0
2
2
%
7
9
.
1
2
0
9
%
7
4
.
7
2
5
3
%
D
a
t
a
se
t
-
2
8
2
.
7
5
8
6
%
8
1
.
6
0
9
2
%
7
7
.
0
1
1
5
%
D
a
t
a
se
t
-
3
8
3
.
5
1
6
5
%
8
6
.
8
1
3
2
%
7
9
.
1
2
0
9
%
4.
CO
NCLU
SI
O
N
Fin
all
y
,
to
co
n
cl
u
d
e
f
r
o
m
t
h
e
r
esu
lt
s
an
d
an
a
l
y
s
is
p
er
f
o
r
m
e
d
in
th
i
s
p
ap
er
it
is
ev
id
e
n
t
th
at
ea
ch
an
d
ev
er
y
a
ttrib
u
te
co
n
tr
ib
u
te
u
n
iq
u
el
y
to
t
h
e
p
r
ed
ictio
n
ac
c
u
r
ac
y
a
n
d
h
e
n
ce
w
i
th
th
e
s
tep
b
y
s
tep
in
cr
ea
s
e
i
n
t
h
e
h
ea
r
t
ail
m
e
n
t
a
ttrib
u
te
s
,
t
h
e
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
h
ea
r
t
ail
m
en
t
g
r
ad
u
all
y
i
n
cr
ea
s
es
ir
r
esp
ec
tiv
e
o
f
th
e
class
i
f
ier
u
s
ed
to
b
u
ild
th
e
m
o
d
el.
A
d
d
in
g
to
th
is
it
is
also
ev
id
en
t
th
at
f
o
r
d
if
f
er
en
t
d
at
aset
w
i
th
d
if
f
er
en
t
v
alu
e
s
a
n
d
n
u
m
b
er
o
f
attr
ib
u
t
es
d
if
f
er
e
n
t
cla
s
s
i
f
ier
s
o
u
t
p
er
f
o
r
m
s
ea
c
h
t
i
m
e.
F
u
t
u
r
e
w
o
r
k
ca
n
b
e
e
x
p
an
d
ed
b
y
f
i
n
d
in
g
th
e
m
o
s
t
ap
p
r
o
p
r
iate
f
ea
tu
r
e
s
r
eq
u
ir
ed
f
o
r
p
r
ed
ict
io
n
o
f
h
ea
r
t
ail
m
e
n
t
a
n
d
u
s
e
o
th
er
d
ata
m
in
i
n
g
m
et
h
o
d
s
s
u
c
h
as
n
eu
r
al
n
et
w
o
r
k
s
,
r
eg
r
es
s
io
n
etc.
,
f
o
r
p
r
ed
ictio
n
o
f
h
ea
r
t d
is
ea
s
e.
RE
F
E
R
E
NC
E
S
[
1
]
Ya
n
,
H.,
J.
Z
h
e
n
g
,
e
t
a
l.
(
2
0
0
3
)
.
"
De
v
e
lo
p
m
e
n
t
o
f
a
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
f
o
r
h
e
a
rt
d
ise
a
se
d
iag
n
o
sis
u
si
n
g
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
.
"
Pro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
0
3
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
v
o
l.
5
:
p
p
.
V
-
7
0
9
-
V
-
7
1
2
.
[
2
]
S
a
n
d
h
y
a
,
J.,
P
.
De
e
p
a
S
h
e
n
o
y
,
e
t
a
l.
(2
0
1
0
).
"
Clas
si
f
ica
ti
o
n
o
f
Ne
u
ro
d
e
g
e
n
e
ra
ti
v
e
Diso
rd
e
rs
Ba
se
d
o
n
M
a
jo
r
Risk
F
a
c
to
rs
Em
p
lo
y
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s."
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
V
o
l
.
2
,
No
.
4
.
[
3
]
Ja
y
m
in
P
a
tel,
P
r
o
f
.
T
e
jalUp
a
d
h
y
a
y
a
n
d
Dr.
S
a
m
ir
P
a
tel,
"
He
a
rt
Dise
a
se
P
re
d
ictio
n
u
si
n
g
M
a
c
h
in
e
L
e
a
rn
in
g
a
n
d
Da
ta
M
in
i
n
g
T
e
c
h
n
iq
u
e
s
"
,
Nirm
a
Un
i
v
e
rsit
y
,
G
u
jara
t,
In
d
ia
IJ
CS
C
Vo
l
7
,
n
u
m
b
e
r
1
se
p
tem
b
e
r
2
0
1
5
-
m
a
r
c
h
2
0
1
6
p
p
.
1
2
9
-
1
3
7
.
[
4
]
W
e
b
m
d
.
c
o
m
.
”
Risk
f
a
c
to
rs
f
o
r
h
e
a
rt
d
ise
a
se
,
”
re
tri
e
v
e
d
2
0
/8
/
2
0
1
4
f
ro
m
h
tt
p
:/
/w
ww
.
we
b
m
d
.
c
o
m
/h
e
a
rt
-
d
ise
a
se
/ri
sk
-
f
a
c
to
rs
-
h
e
a
rt
-
d
ise
a
se
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
IJ
-
I
C
T
Vo
l.
8
,
No
.
1
,
A
p
r
il
20
1
9
:
5
6
–
62
62
[
5
]
Na
ti
o
n
a
l
He
a
rt,
L
u
n
g
,
a
n
d
B
lo
o
d
In
stit
u
te,
”
W
h
a
t
is
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
se
?
”
re
tri
e
v
e
d
2
0
/
8
/2
0
1
4
f
ro
m
h
tt
p
:
//
ww
w
.
n
h
lb
i
.
n
i
h
.
g
o
v
/h
e
a
lt
h
/h
e
a
lt
h
to
p
ics
/
to
p
ics
/ca
d
/.
[
6
]
Da
s,
R.
,
I.
T
u
rk
o
g
lu
,
e
t
a
l.
(2
0
0
9
)
.
"
E
ff
e
c
ti
v
e
d
iag
n
o
sis
o
f
h
e
a
rt
d
ise
a
se
th
ro
u
g
h
n
e
u
ra
l
n
e
tw
o
rk
s
e
n
se
m
b
les
.
"
Exp
e
r
t
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s,
El
se
v
i
e
r 3
6
(
2
0
0
9
):
7
6
7
5
–
7
6
8
0
.
[
7
]
P
a
n
z
a
ra
sa
,
S
.
,
S
.
Qu
a
g
li
n
i,
e
t
a
l.
(2
0
1
0
).
"
Da
ta
m
in
in
g
tec
h
n
iq
u
e
s
fo
r
a
n
a
ly
z
in
g
stro
k
e
c
a
r
e
p
ro
c
e
ss
e
s."
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
3
th
W
o
rl
d
C
o
n
g
re
ss
o
n
M
e
d
ica
l
I
n
fo
rm
a
t
ics
.
[
8
]
V
.
Ch
a
u
ra
sia
,
“
Earl
y
P
re
d
ictio
n
o
f
He
a
rt
Dise
a
se
s
Us
in
g
Da
ta
M
in
in
g
,
”
Ca
ri
b
b
e
a
n
J
o
u
r
n
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
,
p
p
.
2
0
8
–
2
1
7
,
2
0
1
3
.
[
9
]
S
rin
iv
a
s,
K.,
”
A
n
a
l
y
sis
o
f
c
o
ro
n
a
r
y
h
e
a
rt
d
ise
a
se
a
n
d
p
re
d
ictio
n
o
f
h
e
a
rt
a
tt
a
c
k
in
c
o
a
l
m
in
in
g
re
g
io
n
s
u
si
n
g
d
a
ta
m
in
in
g
tec
h
n
iq
u
e
s”
,
IE
EE
T
r
a
n
sa
c
ti
o
n
o
n
Co
mp
u
ter
S
c
ien
c
e
a
n
d
E
d
u
c
a
t
io
n
(
ICCS
E)
,
p
(
1
3
4
4
-
1
3
4
9
),
2
0
1
0
.
[
1
0
]
Ru
b
e
n
,
D.
C.
J
.
(2
0
0
9
).
"
Da
ta M
i
n
in
g
i
n
He
a
lt
h
c
a
re
:
Cu
rre
n
t
A
p
p
li
c
a
ti
o
n
s a
n
d
Iss
u
e
s."
[
1
1
]
Ra
n
d
a
El
-
Bialy
,
M
o
sta
f
a
A
.
S
a
la
m
a
y
,
O
m
a
r
H.
Ka
ra
m
a
n
d
M
.
Essa
m
Kh
a
li
fa
,
“
F
e
a
tu
re
A
n
a
l
y
sis o
f
Co
ro
n
e
ry
A
rter
y
He
a
rt
Dise
a
se
D
a
ta
S
e
ts”
,
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mm
u
n
i
c
a
ti
o
n
,
M
a
n
a
g
e
me
n
t
a
n
d
I
n
fo
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
(
ICCM
IT
2
0
1
5
)
,
P
ro
c
e
d
ia C
o
m
p
u
ter S
c
ien
c
e
6
5
(
2
0
1
5
)
4
5
9
–
4
6
8
[
1
2
]
V
.
C
h
a
u
ra
isa
a
n
d
S
.
P
a
l,
“
Da
ta
M
in
i
n
g
A
p
p
ro
a
c
h
t
o
De
tec
t
He
a
rt
Dise
a
se
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Co
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
IJ
ACS
IT
),
V
o
l.
2
,
No
.
4
,
2
0
1
3
,
p
p
5
6
-
6
6
.
[
1
3
]
Ch
a
it
ra
li
S
.
Da
n
g
a
re
a
n
d
S
u
lab
h
a
S
.
A
p
te,
“
I
m
p
ro
v
e
d
S
tu
d
y
o
f
H
e
a
rt
Dise
a
se
P
re
d
ictio
n
S
y
ste
m
u
si
n
g
Da
ta
M
in
in
g
Clas
sif
ic
a
ti
o
n
T
e
c
h
n
iq
u
e
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
Ap
p
li
c
a
ti
o
n
s
(
0
9
7
5
–
8
8
8
)
Vo
lu
m
e
4
7
–
N
o
.
1
0
,
Ju
n
e
2
0
1
2
.
[
1
4
]
M
.
A
n
b
a
ra
s
i,
E.
A
n
u
p
riy
a
a
n
d
N.CH.S
.
N.Iy
e
n
g
a
r,
“
En
h
a
n
c
e
d
P
re
d
ictio
n
o
f
He
a
rt
Dise
a
s
e
w
it
h
F
e
a
tu
re
S
u
b
se
t
S
e
lec
ti
o
n
u
si
n
g
G
e
n
e
ti
c
A
l
g
o
rit
h
m
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
Vo
l.
2
(1
0
),
2
0
1
0
,
5
3
7
0
-
5
3
7
.
[
1
5
]
J
y
o
ti
Ro
h
il
la
a
n
d
P
re
e
ti
G
u
li
a
,
“
A
n
a
l
y
si
s
o
f
Da
ta
M
in
i
n
g
T
e
c
h
n
iq
u
e
s
f
o
r
Dia
g
n
o
si
n
g
He
a
rt
Dise
a
se
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Res
e
a
rc
h
in
Co
mp
u
ter
S
c
ien
c
e
a
n
d
S
o
ft
w
a
re
En
g
i
n
e
e
rin
g
,
Vo
lu
m
e
5
,
Iss
u
e
7
,
Ju
ly
2
0
1
5
,
IS
S
N:
2
2
7
7
1
2
8
X .
[
1
6
]
R.
T
a
m
il
a
ra
si
a
n
d
Dr.
R.
P
o
rk
o
d
i,
“
A
S
tu
d
y
a
n
d
A
n
a
l
y
s
is
o
f
D
ise
a
se
P
re
d
ictio
n
T
e
c
h
n
iq
u
e
s
in
Da
ta
M
in
in
g
f
o
r
He
a
lt
h
c
a
re
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Eme
rg
in
g
Res
e
a
rc
h
in
M
a
n
a
g
e
me
n
t
&
T
e
c
h
n
o
lo
g
y
,
M
a
rc
h
2
0
1
5
,
I
S
S
N:
2
2
7
8
-
9
3
5
9
(
Vo
lu
m
e
-
4
,
Iss
u
e
-
3)
[
1
7
]
S
h
a
d
a
b
A
d
a
m
P
a
tt
e
k
a
ri
a
n
d
As
m
a
P
a
rv
e
e
n
,
p
re
d
ictio
n
sy
ste
m
fo
r
h
e
a
rt
d
ise
a
se
u
sin
g
n
a
ïv
e
b
a
y
e
s
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
C
o
mp
u
ter
a
n
d
M
a
t
h
e
ma
ti
c
a
l
S
c
ien
c
e
s,
2
0
1
2
.
[
1
8
]
M
.
A
k
h
il
jab
b
e
rs,
Dr.
p
rirt
i
Ch
a
n
d
ra
,
Dr.B.
L
De
e
k
sh
a
tu
lu
,
a
n
d
He
a
rt
Dise
a
se
P
re
d
icti
o
n
S
y
ste
m
u
s
in
g
A
ss
o
c
iativ
e
Clas
sif
ic
a
ti
o
n
a
n
d
G
e
n
e
ti
c
A
lg
o
ri
th
m
,
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Eme
rg
in
g
T
re
n
d
s
i
n
El
e
c
trica
l,
El
e
c
tro
n
ics
a
n
d
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
ies
,
2
0
1
2
.
[
1
9
]
M
.
Bra
m
e
r,
P
rin
c
i
p
les
o
f
Da
ta M
i
n
in
g
:
S
p
ri
n
g
e
r
-
Ver
la
g
,
2
0
0
7
.
[
2
0
]
R.
A
li
z
a
d
e
h
sa
n
i,
J.
Ha
b
ib
i,
B.
Ba
h
a
d
o
ria
n
,
H.
M
a
sh
a
y
e
k
h
i,
A
.
G
h
a
n
d
e
h
a
ri
o
u
n
,
a
n
d
R.
Bo
g
h
ra
t
i
,
e
t
a
l.
,
"
Dia
g
n
o
sis
o
f
c
o
ro
n
a
ry
a
rterie
s ste
n
o
sis u
sin
g
d
a
ta
m
in
in
g
,
"
J
M
e
d
S
ig
n
a
ls
S
e
n
s
,
v
o
l.
2
,
p
p
.
1
5
3
-
9
,
Ju
l
2
0
1
2
.
[
2
1
]
J.Na
h
a
r,
T
.
I
m
a
m
,
K.
S
.
T
ic
k
le,
a
n
d
Y.
-
P
.
P
.
C
h
e
n
,
“
Co
m
p
u
tati
o
n
a
l
In
telli
g
e
n
c
e
f
o
r
h
e
a
rt
d
ise
a
se
d
iag
n
o
sis:
A
m
e
d
ica
l
Kn
o
w
led
g
e
d
riv
e
n
a
p
p
ro
a
c
h
,
”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
li
c
a
ti
o
n
s,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
9
6
–
1
0
4
,
2
0
1
3
.
[
2
2
]
M
.
Ku
m
a
ri
a
n
d
S
.
G
o
d
a
ra
,
"
Co
m
p
a
ra
ti
v
e
stu
d
y
o
f
d
a
ta
m
in
in
g
c
las
si
f
ica
ti
o
n
m
e
th
o
d
sin
c
a
rd
io
v
a
sc
u
lar
d
ise
a
se
p
re
d
ictio
n
,
"
IJ
CS
T
v
o
l.
2
,
p
p
.
3
0
4
-
3
0
5
,
2
0
1
1
.
[
2
3
]
Y.
E.
S
h
a
o
,
C.
-
D.
Ho
u
,
a
n
d
C.
-
C.
Ch
iu
,
“
Hy
b
rid
in
telli
g
e
n
t
m
o
d
e
ll
in
g
,
sc
h
e
m
e
s
f
o
r
h
e
a
rt
d
ise
a
s
e
c
las
sif
i
c
a
ti
o
n
,
”
Ap
p
li
e
d
S
o
ft
Co
mp
u
ti
n
g
,
v
o
l.
1
4
,
p
p
.
4
7
–
5
2
,
2
0
1
4
.
[
2
4
]
P
.
V.
A
n
k
u
r
M
a
k
w
a
n
a
,
“
Id
e
n
ti
fy
th
e
p
a
ti
e
n
ts
a
t
h
ig
h
r
isk
o
f
re
-
a
d
m
is
sio
n
in
h
o
sp
it
a
l
in
t
h
e
n
e
x
t
y
e
a
r,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
c
e
a
n
d
Res
e
a
rc
h
,
v
o
l.
4
,
p
p
.
2
4
3
1
–
2
4
3
4
,
2
0
1
5
.
[
2
5
]
A
.
Az
iz,
N.
I
s
m
a
il
,
A
n
d
F
.
A
h
m
a
d
,
“
M
in
in
g
S
tu
d
e
n
ts’
a
c
a
d
e
m
i
c
P
e
rf
o
rm
a
n
c
e
.
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
r
e
ti
c
a
l
&
Ap
p
li
e
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
5
3
,
n
o
.
3
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.