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.
10
,
No
.
3
,
Dec
em
b
e
r
2
0
2
1
,
p
p
.
1
8
2
~
1
8
7
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct.
v
10
i
3
.
p
p
182
-
1
8
7
182
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Electron
ic
hea
lth
record to p
redic
t
a
heart att
a
ck
use
d data
mining
wit
h
Na
ïv
e
Ba
y
es
metho
d
J
o
ha
nes
F
er
na
nd
es An
dry
1
,
F
a
bio
M
a
ng
a
t
a
s
Sil
a
en
2
,
H
endy
T
a
nn
a
dy
3
,
K
ev
in H
a
di S
a
pu
t
ra
4
1,
2,
4
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
S
y
ste
m
,
Un
iv
e
rsitas
Bu
n
d
a
M
u
li
a
,
J
a
k
a
rta,
In
d
o
n
e
sia
3
De
p
a
rtme
n
t
o
f
M
a
n
a
g
e
m
e
n
t,
Un
i
v
e
rsitas
P
e
m
b
a
n
g
u
n
a
n
Ja
y
a
,
Ba
n
t
e
n
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
1
3
,
2
0
21
R
ev
is
ed
Sep
1
,
2
0
21
Acc
ep
ted
Oct
11
,
2
0
21
A
h
e
a
rt
a
tt
a
c
k
is
a
m
e
d
ica
l
e
m
e
r
g
e
n
c
y
.
A
h
e
a
rt
a
tt
a
c
k
u
su
a
ll
y
o
c
c
u
rs
wh
e
n
a
b
lo
o
d
c
lo
t
b
l
o
c
k
s
th
e
f
lo
w
o
f
b
l
o
o
d
to
th
e
h
e
a
rt.
Ca
rd
io
v
a
sc
u
lar
d
ise
a
se
is
a
v
a
riety
o
f
d
ise
a
se
s
th
a
t
a
tt
a
c
k
th
e
b
o
d
y
'
s
c
a
rd
io
v
a
sc
u
lar
sy
ste
m
in
c
lu
d
i
n
g
th
e
h
e
a
rt
a
n
d
b
l
o
o
d
v
e
ss
e
ls.
Ca
rd
i
o
v
a
sc
u
lar
d
ise
a
se
s
(CVD
)
in
c
lu
d
e
a
n
g
in
a
,
a
rrh
y
th
m
ia,
h
e
a
rt
a
tt
a
c
k
,
h
e
a
rt
fa
il
u
re
,
a
t
h
e
ro
sc
lero
sis,
stro
k
e
,
a
n
d
so
o
n
.
To
re
so
lv
in
g
(CVD
)
is
t
o
e
v
a
l
u
a
te
l
a
rg
e
sc
o
re
s
o
f
d
a
tas
e
ts,
t
o
c
o
m
p
a
re
fo
r
a
n
y
in
fo
rm
a
ti
o
n
th
a
t
c
a
n
b
e
u
se
d
t
o
fo
re
c
a
st,
to
tak
e
c
a
re
o
f
o
rg
a
n
ize
.
Th
e
m
e
th
o
d
u
se
d
Na
ïv
e
Ba
y
e
s
c
las
sifica
ti
o
n
b
e
c
a
u
se
th
a
t
m
e
th
o
d
c
a
n
d
e
term
in
e
targ
e
t
wh
ich
c
a
n
b
e
u
se
d
to
a
n
sw
e
r
so
m
e
q
u
e
stio
n
s
li
k
e
wh
e
th
e
r
th
e
p
a
ti
e
n
t
h
a
s
t
h
e
p
o
ten
ti
a
l
fo
r
h
e
a
rt
d
ise
a
se
.
Aft
e
r
d
a
ta
a
n
a
ly
st,
a
u
th
o
rs
c
a
n
u
se
d
a
ta
to
e
lec
tro
n
ic h
e
a
lt
h
re
c
o
rd
s (E
HR)
.
K
ey
w
o
r
d
s
:
C
ar
d
io
v
ascu
lar
d
is
ea
s
es
Data
m
in
in
g
E
lectr
o
n
ic
h
ea
lth
r
ec
o
r
d
Hea
r
t a
ttack
Naïv
e
B
ay
es
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
J
o
h
an
es Fer
n
an
d
es An
d
r
y
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Sy
s
tem
,
Un
iv
er
s
itas
B
u
n
d
a
Mu
lia
J
l.
An
co
l Bar
at
I
V,
R
T
.
1
2
/R
W
.
2
,
An
co
l,
Kec
.
Pad
em
an
g
an
,
D.
K.
I
J
ak
ar
ta
1
4
4
3
0
,
I
n
d
o
n
esi
a
E
m
ail:
jan
d
r
y
@
b
u
n
d
am
u
lia.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
ar
d
io
v
ascu
lar
d
is
ea
s
e
(
C
VD
)
is
th
e
n
u
m
b
er
o
n
e
d
ea
d
lies
t
d
is
ea
s
e
in
th
e
wo
r
ld
an
d
is
o
n
th
e
r
is
e
in
Asi
a.
T
h
er
e
ar
e
a
n
u
m
b
e
r
o
f
f
ac
to
r
s
th
at
ca
u
s
e
an
in
cr
ea
s
e
in
C
VD
s
u
ch
as
s
ed
en
tar
y
life
s
ty
le,
u
n
h
ea
lth
y
d
iet,
an
d
s
m
o
k
in
g
.
B
u
t y
o
u
ca
n
ch
a
n
g
e
y
o
u
r
life
an
d
r
ed
u
ce
y
o
u
r
r
is
k
o
f
C
VD
an
d
im
p
r
o
v
e
y
o
u
r
q
u
ality
o
f
life
[
1
]
.
Ath
er
o
s
cler
o
s
is
is
a
ch
r
o
n
ic
in
f
lam
m
ato
r
y
d
is
ea
s
e;
it’s
d
escr
ib
ed
th
e
p
atch
y
i
n
tr
am
u
r
al
th
ick
en
in
g
o
f
th
e
s
u
b
in
tim
a
[
2
]
.
C
ar
d
io
v
ascu
lar
d
is
ea
s
e
(
C
VD)
cir
cu
lato
r
y
s
y
s
tem
wh
ich
in
clu
d
es
th
e
h
ea
r
t
an
d
b
lo
o
d
v
ess
els.
T
h
e
cir
c
u
lato
r
y
s
y
s
tem
is
i
m
p
o
r
tan
t
f
o
r
k
ee
p
in
g
th
e
b
o
d
y
'
s
o
r
g
an
s
f
u
n
ctio
n
in
g
b
y
t
r
an
s
p
o
r
tin
g
o
x
y
g
e
n
,
n
u
tr
ien
ts
,
elec
tr
o
l
y
tes,
an
d
h
o
r
m
o
n
es
th
r
o
u
g
h
o
u
t
th
e
b
o
d
y
.
B
u
t
wh
en
th
er
e
is
a
d
is
tu
r
b
an
ce
o
r
b
l
o
ck
ag
e
in
th
e
h
ea
r
t
o
r
b
lo
o
d
v
ess
els,
it
will
af
f
ec
t
b
lo
o
d
ci
r
cu
latio
n
an
d
ca
u
s
e
co
m
p
licatio
n
s
s
u
ch
as
h
ea
r
t
d
is
ea
s
e
o
r
s
tr
o
k
e
[
3
]
.
Acu
te
m
y
o
ca
r
d
ial
in
f
ar
ctio
n
(
AM
I
)
,
o
r
o
f
te
n
r
ef
er
r
ed
to
as
a
h
ea
r
t
attac
k
,
is
a
d
ec
r
ea
s
e
in
b
lo
o
d
f
lo
w
in
th
e
co
r
o
n
ar
y
ar
ter
ies
d
u
e
to
o
cc
lu
s
io
n
,
wh
ich
is
m
o
s
tly
ca
u
s
ed
b
y
th
e
p
r
o
ce
s
s
o
f
ath
er
o
s
cler
o
s
is
.
Me
an
wh
ile,
r
is
k
f
ac
to
r
s
ca
n
b
e
d
is
tin
g
u
is
h
ed
b
etwe
en
m
o
d
if
iab
le
r
is
k
f
a
cto
r
s
an
d
n
o
n
-
m
o
d
if
iab
le
r
is
k
f
ac
to
r
s
[
4
]
.
T
h
e
u
s
e
o
f
b
ig
d
ata
f
r
o
m
d
atas
ets ca
n
im
p
r
o
v
e
s
er
v
ices to
p
a
tien
ts
,
d
etec
t th
e
s
p
r
ea
d
o
f
d
is
ea
s
e
ea
r
ly
,
g
en
er
ate
n
ew
in
s
ig
h
ts
in
to
d
i
s
ea
s
e
m
ec
h
an
is
m
s
,
m
o
n
ito
r
th
e
q
u
ality
o
f
m
ed
ical
an
d
h
e
alth
in
s
titu
tio
n
s
an
d
p
r
o
v
id
e
b
etter
tr
ea
tm
en
t
m
eth
o
d
s
[
5
]
.
C
ar
d
io
v
ascu
lar
d
is
ea
s
e
h
as
r
is
k
f
ac
to
r
s
.
R
is
k
f
ac
to
r
s
ar
e
a
m
ea
s
u
r
e
to
d
eter
m
in
e
th
e
lik
elih
o
o
d
,
ca
n
b
e
s
ee
n
in
T
ab
le
1
.
B
ig
d
ata
is
a
v
er
y
lar
g
e
an
d
q
u
ite
co
m
p
le
x
way
o
f
c
o
llectin
g
d
ata
wh
er
e
co
n
v
en
tio
n
al
d
ata
p
r
o
ce
s
s
in
g
m
eth
o
d
s
ar
e
n
o
t
g
o
o
d
e
n
o
u
g
h
.
T
h
er
ef
o
r
e,
b
ig
d
ata
will
b
e
an
aly
ze
d
s
o
th
at
p
atter
n
s
,
o
r
o
th
e
r
h
a
b
its
,
r
elate
d
to
th
e
o
r
g
a
n
izatio
n
o
r
cu
s
t
o
m
er
s
ca
n
b
e
o
b
ta
in
ed
[
6
]
.
B
ig
d
ata
an
aly
s
is
r
ef
er
s
to
p
r
o
p
er
an
d
g
o
o
d
an
aly
s
is
s
o
th
at
it
ca
n
b
e
en
s
u
r
ed
th
at
t
h
e
d
ec
is
io
n
-
m
a
k
in
g
p
r
o
ce
s
s
ca
n
b
e
m
o
r
e
ac
cu
r
ate
an
d
t
h
e
r
esu
lts
o
f
g
o
o
d
p
er
f
o
r
m
an
ce
a
g
ain
[
7
]
.
C
h
ar
ac
ter
is
tics
o
f
d
ig
d
ata
is
s
h
o
wn
in
T
ab
le
2
.
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
E
lectro
n
ic
h
ea
lth
r
ec
o
r
d
to
p
r
ed
ict
a
h
ea
r
t a
tta
ck
u
s
ed
d
a
ta
min
in
g
w
ith
…
(
Jo
h
a
n
es F
ern
a
n
d
es A
n
d
r
y
)
183
T
ab
le
1
.
R
is
k
f
ac
to
r
s
ca
n
b
e
m
o
d
if
iab
le
an
d
n
o
n
m
o
d
if
iab
le
M
o
d
i
f
i
a
b
l
e
N
o
n
m
o
d
i
f
i
a
b
l
e
•
S
h
e
o
r
h
e
t
o
sm
o
k
e
o
r
v
a
p
e
e
n
v
i
r
o
n
m
e
n
t
a
l
,
•
O
b
e
si
t
y
a
r
e
i
s
a
n
e
x
c
e
ssi
v
e
a
c
c
u
m
u
l
a
t
i
o
n
o
f
f
a
t
d
u
e
t
o
a
n
i
mb
a
l
a
n
c
e
b
e
t
w
e
e
n
e
n
e
r
g
y
i
n
t
a
k
e
a
n
d
e
n
e
r
g
y
u
se
d
•
l
i
f
e
s
t
y
l
e
o
f
S
e
d
e
n
t
a
r
y
(
r
a
r
e
l
y
p
h
y
si
c
a
l
a
c
t
i
v
i
t
y
)
,
•
D
i
a
b
e
t
e
s
d
i
se
a
se
,
a
c
h
r
o
n
i
c
d
i
sea
s
e
c
h
a
r
a
c
t
e
r
i
z
e
d
b
y
h
i
g
h
b
l
o
o
d
su
g
a
r
(
g
l
u
c
o
se)
l
e
v
e
l
s
•
H
i
g
h
c
h
o
l
e
st
e
r
o
l
i
s
c
o
n
d
i
t
i
o
n
w
h
e
n
c
h
o
l
e
st
e
r
o
l
l
e
v
e
l
s
i
n
t
h
e
b
l
o
o
d
e
x
c
e
e
d
n
o
r
m
a
l
l
i
mi
t
s.
•
H
y
p
e
r
t
e
n
si
o
n
i
s c
o
n
d
i
t
i
o
n
w
h
e
n
b
l
o
o
d
p
r
e
ss
u
r
e
i
s
a
t
1
3
0
/
8
0
mm
H
g
o
r
mo
r
e
•
G
e
n
d
e
r
,
ma
n
is
m
o
r
e
a
t
r
i
s
k
o
f
c
o
r
o
n
a
r
y
h
e
a
r
t
d
i
s
e
a
se
t
h
a
n
w
o
me
n
.
R
i
s
k
f
a
c
t
o
r
s
i
n
w
o
m
e
n
w
i
l
l
i
n
c
r
e
a
se
a
f
t
e
r
e
x
p
e
r
i
e
n
c
i
n
g
me
n
o
p
a
u
se
•
A
g
e
,
a
p
e
r
so
n
's
r
i
s
k
i
n
c
r
e
a
s
e
s
w
i
t
h
a
g
e
.
U
su
a
l
l
y
a
t
t
h
e
a
g
e
o
f
4
0
y
e
a
r
s,
a
p
e
r
so
n
i
s
a
d
v
i
s
e
d
t
o
s
t
a
r
t
c
h
e
c
k
i
n
g
h
i
s
h
e
a
r
t
h
e
a
l
t
h
•
G
e
n
f
a
c
t
o
r
,
h
e
r
e
d
i
t
y
f
r
o
m
a
f
a
mi
l
y
w
h
o
h
a
s
h
a
d
a
h
e
a
r
t
a
t
t
a
c
k
T
ab
l
e
2
.
B
ig
d
ata
c
h
ar
ac
ter
is
tics
N
o
.
B
i
g
d
a
t
a
f
e
a
t
u
r
e
Ex
p
l
a
n
a
t
i
o
n
I
l
l
u
st
r
a
t
i
o
n
1
V
o
l
u
me
C
a
p
a
c
i
t
y
o
f
d
a
t
a
A
mo
u
n
t
o
f
d
a
t
a
c
o
l
l
e
c
t
e
d
a
n
d
st
o
r
e
d
.
C
a
p
a
c
i
t
y
i
n
M
B
,
G
B
,
a
n
d
T
B
[
8
]
.
2
V
e
l
o
c
i
t
y
S
p
e
e
d
o
f
d
a
t
a
Th
e
t
r
a
n
sf
e
r
r
a
t
e
o
f
d
a
t
a
a
m
o
n
g
r
e
s
o
u
r
c
e
a
n
d
o
b
j
e
c
t
i
v
e
[
9
]
.
3
V
a
r
i
e
t
y
K
i
n
d
o
f
d
a
t
a
D
i
f
f
e
r
e
n
t
t
y
p
e
o
f
d
a
t
a
l
i
k
e
i
ma
g
e
,
m
o
v
i
e
,
a
n
d
s
o
u
n
d
[
1
0
]
.
4
V
a
l
u
e
I
mp
o
r
t
a
n
c
e
o
f
d
a
t
a
I
t
’
s
i
n
d
i
c
a
t
e
d
t
h
e
b
u
si
n
e
ss
v
a
l
u
e
d
e
r
i
v
e
d
f
r
o
m
b
i
g
d
a
t
a
[
1
1
]
.
5
V
a
r
i
a
b
i
l
i
t
y
D
a
t
a
d
i
f
f
e
r
e
n
t
i
a
t
i
o
n
I
t
’
s i
n
d
i
c
a
t
e
d
t
o
c
h
a
n
g
e
s
i
n
d
a
t
a
d
u
r
i
n
g
p
r
o
c
e
ss
i
n
g
a
n
d
l
i
f
e
c
y
c
l
e
[
1
2
]
.
6
V
e
r
a
c
i
t
y
Q
u
a
l
i
t
y
o
f
d
a
t
a
I
t
’
s i
n
d
i
c
a
t
e
d
2
a
s
p
e
c
t
s:
c
o
n
si
s
t
e
n
c
y
o
f
d
a
t
a
a
n
d
t
r
u
s
t
w
o
r
t
h
i
n
e
ss
o
f
d
a
t
a
[
1
3
]
.
Af
ter
th
ese
p
atter
n
s
ar
e
f
o
u
n
d
,
th
ey
ca
n
b
e
u
s
ed
to
m
a
k
e
ce
r
tain
d
ec
is
io
n
s
f
o
r
f
u
r
th
er
b
u
s
in
ess
d
ev
elo
p
m
e
n
t
[
1
4
]
.
So
m
e
o
f
th
e
s
tep
s
in
v
o
lv
ed
in
it a
r
e:
−
T
o
ex
p
lo
r
e
o
f
d
ata:
T
h
e
d
ata
is
clea
n
ed
in
th
e
s
en
s
e
th
at
n
o
th
in
g
is
lo
s
t
an
d
tr
an
s
f
o
r
m
ed
in
to
a
d
if
f
er
e
n
t
fo
r
m
s
o
th
at
o
th
e
r
im
p
o
r
tan
t
v
ar
iab
les
wh
ich
th
en
ty
p
e
th
e
d
ata
b
ased
o
n
th
e
p
r
o
b
lem
h
av
e
b
ee
n
d
eter
m
in
ed
.
−
Patter
n
id
en
tific
atio
n
:
Fo
r
m
p
atter
n
id
en
tific
atio
n
.
I
d
en
tif
y
an
d
ch
o
o
s
e
th
e
p
atter
n
wh
ich
m
ak
e
th
e
b
est
p
r
ed
ictio
n
.
−
Dep
lo
y
m
en
t: Patter
n
s
ar
e
d
e
p
l
o
y
ed
f
o
r
th
e
d
esire
d
o
u
tco
m
e.
Data
m
in
in
g
is
th
e
p
r
o
ce
s
s
o
f
an
aly
zin
g
d
ata
f
r
o
m
d
if
f
e
r
e
n
t
an
g
les
an
d
s
u
m
m
ar
izin
g
r
esu
lts
in
to
u
s
ef
u
l
in
f
o
r
m
atio
n
[
1
5
]
.
Dat
a
m
in
in
g
is
an
au
to
m
a
te
d
d
ata
an
aly
s
is
tech
n
iq
u
es
to
u
n
co
v
er
p
r
ev
i
o
u
s
ly
u
n
d
etec
ted
r
elatio
n
s
h
ip
s
am
o
n
g
d
ata
item
s
.
Data
m
in
in
g
al
s
o
o
f
ten
in
v
o
lv
es
th
e
an
aly
s
is
o
f
d
ata
s
to
r
ed
i
n
a
d
ata
war
eh
o
u
s
e
[
1
6
]
.
Data
m
i
n
in
g
tech
n
iq
u
es
ca
n
b
e
a
p
p
lie
d
in
v
a
r
io
u
s
asp
ec
ts
b
ec
au
s
e
d
ata
o
b
tain
e
d
f
r
o
m
d
if
f
er
en
t
s
o
u
r
ce
s
ca
n
b
e
d
i
f
f
er
en
t
an
d
o
u
t
o
f
s
y
n
c
.
Sp
ec
if
ic
t
ec
h
n
iq
u
e
is
ap
p
lied
f
o
r
s
p
ec
if
i
c
ty
p
es o
f
p
r
o
b
lem
s
to
r
eso
lv
e
ef
f
icien
tly
[
1
7
]
.
T
ec
h
n
iq
u
e’
s
d
ata
m
in
in
g
[
1
8
]
:
−
C
las
s
if
icatio
n
,
th
is
tech
n
iq
u
e
u
s
u
ally
u
s
es
m
ac
h
in
e
lear
n
in
g
o
r
m
ac
h
in
e
lear
n
in
g
t
ec
h
n
iq
u
es.
T
h
is
tech
n
iq
u
e
class
if
ies
item
s
o
r
v
ar
iab
les
in
a
d
ata
s
et
in
to
p
r
ed
eter
m
in
ed
g
r
o
u
p
s
o
r
class
es.
I
t
u
s
es
lin
ea
r
p
r
o
g
r
a
m
m
in
g
,
s
tatis
tics
,
d
ec
is
i
o
n
tr
ee
s
,
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
,
am
o
n
g
o
th
e
r
tech
n
iq
u
es.
−
C
lu
s
ter
in
g
,
in
clu
s
ter
in
g
t
h
e
d
ata
lab
e
lin
g
p
r
o
ce
s
s
is
n
o
t
d
eter
m
in
ed
at
th
e
b
e
g
in
n
in
g
,
i
n
co
n
tr
ast
to
th
e
d
ata
g
r
o
u
p
lab
elin
g
class
if
icatio
n
th
at
h
as
b
ee
n
d
eter
m
i
n
ed
p
r
ev
io
u
s
ly
.
E
x
a
m
p
les
o
f
clu
s
t
er
in
g
m
eth
o
d
s
ar
e
K
-
m
ea
n
s
,
C
-
m
ea
n
s
)
.
−
R
eg
r
ess
io
n
is
a
tech
n
iq
u
e
u
s
ed
f
o
r
d
eter
m
in
in
g
th
at
th
er
e
is
a
r
elatio
n
s
h
ip
b
etwe
en
th
e
v
ar
iab
le
th
at’
s
wan
tin
g
to
p
r
ed
ict
(
th
e
d
ep
en
d
en
t v
ar
iab
le)
a
n
d
o
th
er
v
a
r
iab
l
es (
th
e
in
d
ep
e
n
d
en
t
v
ar
iab
le)
.
B
ig
d
ata,
in
m
ed
ical
r
esear
ch
,
is
u
s
ed
f
o
r
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
(
E
HR
)
c
o
n
s
id
er
ed
“r
e
lev
an
t”
to
th
e
u
n
d
er
s
tan
d
in
g
o
f
h
ea
lth
an
d
d
is
ea
s
e,
in
clu
d
in
g
clin
ic
al,
im
ag
in
g
,
o
m
ics
,
d
ata
f
r
o
m
in
ter
n
et
u
s
e
a
n
d
wea
r
ab
le
d
ev
ices,
an
d
o
th
er
s
[
1
9
]
.
I
n
h
ea
lth
ca
r
e
in
s
titu
tio
n
s
,
d
ata
m
in
in
g
to
o
l
s
an
s
wer
th
e
q
u
esti
o
n
r
ap
id
l
y
,
th
at
ar
e
tr
ad
itio
n
ally
tim
e
-
c
o
n
s
u
m
in
g
a
n
d
t
o
o
c
o
m
p
lex
to
r
eso
lv
e
[
2
0
]
.
E
lectr
o
n
ic
h
ea
l
th
r
ec
o
r
d
(
E
HR
)
is
f
ac
ilit
ated
s
er
v
ices
in
ter
m
s
o
f
p
atien
t
m
e
d
ical
r
ec
o
r
d
s
.
T
h
e
E
MR
s
y
s
tem
o
r
elec
tr
o
n
ic
m
ed
ical
r
ec
o
r
d
is
a
s
y
s
tem
atic
co
llectio
n
o
f
elec
tr
o
n
ic
-
b
ased
h
ea
lth
in
f
o
r
m
ati
o
n
th
at
is
c
o
n
n
ec
te
d
an
d
in
teg
r
ated
with
th
e
in
f
o
r
m
atio
n
s
y
s
tem
in
th
e
h
o
s
p
ital
n
etwo
r
k
[
2
1
]
.
Me
d
ic
al
r
ec
o
r
d
s
ar
e
wr
itten
o
r
r
ec
o
r
d
ed
in
f
o
r
m
atio
n
r
eg
ar
d
in
g
id
en
tity
,
h
is
to
r
y
tak
in
g
,
p
h
y
s
ical
d
eter
m
in
atio
n
,
l
ab
o
r
ato
r
y
,
d
iag
n
o
s
is
o
f
all
m
ed
ical
s
er
v
ices
an
d
ac
tio
n
s
p
r
o
v
id
ed
to
p
atien
ts
an
d
tr
ea
tm
en
t,
b
o
th
in
p
atie
n
ts
,
o
u
tp
atien
ts
an
d
th
o
s
e
r
ec
eiv
in
g
em
er
g
e
n
cy
s
er
v
ices.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
wo
r
k
in
g
o
f
th
e
m
eth
o
d
is
d
escr
ib
ed
i
n
a
s
tep
b
y
s
tep
[
2
2
]
:
(
a)
Data
Selectio
n
:
o
b
ta
in
th
e
d
a
ta
r
eso
u
r
ce
s
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
.
(
b
)
Data
p
r
ep
r
o
ce
s
s
in
g
:
is
r
ef
er
to
m
a
n
ip
u
latio
n
o
r
d
r
o
p
p
i
n
g
o
f
d
ata
b
ef
o
r
e
it
is
u
s
ed
in
o
r
d
er
to
e
n
s
u
r
e
o
r
e
n
h
an
ce
p
er
f
o
r
m
a
n
ce
a
n
d
is
an
im
p
o
r
tan
t
s
tep
in
t
h
e
d
ata
m
i
n
in
g
p
r
o
ce
s
s
f
r
o
m
th
e
d
ataset.
(
c)
Data
an
aly
s
t:
o
n
e
o
f
d
ata
m
in
in
g
tech
n
iq
u
es
ar
e
ap
p
lied
to
g
et
r
esu
lts
.
(
d
)
I
m
p
lem
en
tatio
n
:
th
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.
10
,
No
.
3
,
Dec
em
b
er
20
2
1
:
1
8
2
–
1
8
7
184
r
esu
lts
f
r
o
m
ap
p
lied
d
ata
m
i
n
in
g
tech
n
i
q
u
es
in
R
ap
id
Min
er
ap
p
licatio
n
.
T
h
e
s
tep
o
f
r
esear
ch
m
eth
o
d
as
s
h
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
o
l
o
g
y
s
tep
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
elec
t
io
n
B
ig
d
ata
in
h
ea
lth
ca
r
e
r
e
f
er
s
to
th
e
v
ast
q
u
a
n
titi
es
o
f
d
at
a
-
cr
ea
ted
b
y
th
e
m
ass
ad
o
p
ti
o
n
o
f
th
e
I
n
ter
n
et
a
n
d
d
ig
itizatio
n
o
f
a
ll
s
o
r
ts
o
f
in
f
o
r
m
atio
n
,
in
clu
d
in
g
h
ea
lth
r
ec
o
r
d
s
-
to
o
lar
g
e
o
r
co
m
p
lex
f
o
r
tr
ad
itio
n
al
tech
n
o
lo
g
y
to
m
a
k
e
s
en
s
e
o
f
.
T
h
is
clin
ical
ac
tiv
ity
p
r
o
d
u
ce
s
a
lar
g
e
n
u
m
b
er
o
f
p
r
in
ts
in
clu
d
in
g
p
atien
t r
ec
o
r
d
an
y
in
f
o
r
m
atio
n
,
d
iag
n
o
s
es,
tr
ea
tm
en
t sch
em
e
s
,
n
o
tes f
r
o
m
d
o
cto
r
s
,
a
n
d
s
en
s
o
r
d
ata
[
2
3
]
.
T
h
e
d
ataset
th
at
will
b
e
p
ast
in
th
is
r
esear
ch
is
th
e
“He
a
r
t
d
is
ea
s
e
U
C
I
”
d
ataset.
T
h
i
s
d
ataset
i
s
o
b
tain
ed
f
r
o
m
h
o
s
p
ital
in
I
n
d
o
n
esia.
T
h
is
d
ataset
co
n
tain
s
1
4
attr
ib
u
tes,
th
e
ex
p
lan
atio
n
o
f
ea
ch
attr
ib
u
te
ca
n
b
e
s
ee
n
T
ab
le
3
.
Ho
wev
er
,
th
is
d
ata
m
u
s
t
b
e
p
r
e
-
p
r
o
ce
s
s
ed
.
Data
p
r
e
-
p
r
o
ce
s
s
in
g
is
o
n
e
o
f
th
e
task
s
in
d
ata
m
in
in
g
,
in
cl
u
d
in
g
th
e
p
r
e
p
ar
at
io
n
an
d
co
n
v
er
s
io
n
o
f
d
ata
in
t
o
a
f
o
r
m
s
u
itab
le
f
o
r
m
in
in
g
p
r
o
ce
d
u
r
es
[
2
4
]
.
3
.
2
.
Da
t
a
prepro
ce
s
s
ing
I
n
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
th
e
s
o
f
twar
e
u
s
ed
in
th
is
m
eth
o
d
o
lo
g
y
is
R
ap
id
Min
er
.
B
y
u
tili
zin
g
R
ap
id
Min
er
,
th
e
d
ata
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
,
to
d
e
ter
m
in
e
th
e
v
ar
iab
les
t
h
at
will
b
e
u
s
ed
in
t
h
e
p
r
o
ce
s
s
o
f
g
r
o
u
p
in
g
d
ata,
to
clea
n
u
p
u
n
wan
ted
d
ata.
3
.3
.
Da
t
a
a
na
ly
s
t
Data
an
aly
s
is
lo
o
k
s
at
th
e
ex
i
s
tin
g
d
ata
an
d
im
p
le
m
en
ts
s
tatis
tical
an
d
v
is
u
aliza
tio
n
m
eth
o
d
s
to
test
h
y
p
o
th
eses
ab
o
u
t
th
e
d
ata
an
d
f
in
d
e
x
ce
p
tio
n
s
.
Data
m
in
in
g
lo
o
k
s
f
o
r
an
d
f
in
d
s
tr
en
d
s
in
th
e
d
ata,
wh
ic
h
ca
n
b
e
u
s
ed
f
o
r
f
u
r
th
er
an
al
y
s
is
i
n
th
e
f
u
tu
r
e.
C
lass
if
icatio
n
alg
o
r
ith
m
s
lear
n
th
e
lab
els
o
f
t
h
e
s
am
p
les
an
d
th
eir
n
o
m
in
al
an
d
/o
r
n
u
m
er
ic
v
alu
e
s
as
attr
ib
u
tes
an
d
th
ey
c
r
ea
te
a
m
o
d
el.
Af
ter
th
at,
th
e
y
m
ak
e
p
r
ed
ictio
n
s
ab
o
u
t
th
ese
g
en
er
ated
m
o
d
els
[
2
5
]
.
Naïv
e
B
ay
es
class
if
icatio
n
is
a
p
r
o
b
ab
ilis
tic
m
o
d
el
b
ase
d
o
n
Naïv
e
B
ay
es
th
eo
r
em
.
Naïv
e
B
ay
es
d
ef
in
e
d
as
a
s
tatis
tical
clas
s
if
icatio
n
.
Naïv
e
B
ay
es
u
s
ed
f
o
r
s
u
p
er
v
is
ed
lear
n
in
g
[
2
6
]
.
T
h
e
d
ata
m
i
n
in
g
ex
ten
s
io
n
(
DM
X)
q
u
er
y
lan
g
u
ag
e
is
u
s
ed
to
cr
ea
te
m
o
d
els,
m
o
d
el
tr
ain
in
g
,
m
o
d
e
l
p
r
ed
ictio
n
s
,
an
d
m
o
d
el
co
n
te
n
t
ac
ce
s
s
.
All
p
ar
am
eter
s
ar
e
s
et
to
d
ef
au
lt
s
ettin
g
s
ex
ce
p
t
f
o
r
th
e
p
ar
am
eter
s
“M
in
im
u
m
d
ep
en
d
en
c
y
p
r
o
b
ab
ilit
y
=
0
.
0
5
”
f
o
r
Naïv
e
B
ay
es
[
2
7
]
.
I
n
th
is
p
ap
er
,
we
u
s
e
th
e
Naïv
e
B
ay
e
s
class
if
icatio
n
alg
o
r
ith
m
.
T
h
e
Naïv
e
B
ay
es
is
a
s
im
p
le
p
r
o
b
ab
ilis
tic
class
if
ier
th
at
is
ea
s
y
to
ap
p
ly
a
n
d
it
p
er
f
o
r
m
s
ca
n
well
o
n
d
ata
s
ets with
a
h
ig
h
n
u
m
b
er
o
f
in
s
tan
c
es
[
2
8
]
.
T
h
e
r
u
les o
f
Naïv
e
B
ay
es
[
2
9
]
.
(
|
)
(
|
)
)
(
)
(
)
.
(
1
)
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
E
lectro
n
ic
h
ea
lth
r
ec
o
r
d
to
p
r
ed
ict
a
h
ea
r
t a
tta
ck
u
s
ed
d
a
ta
min
in
g
w
ith
…
(
Jo
h
a
n
es F
ern
a
n
d
es A
n
d
r
y
)
185
T
ab
le
3
.
Attr
ib
u
tes d
atasets
o
f
h
ea
r
t d
is
ea
s
e
A
g
e
Th
e
l
e
n
g
t
h
o
f
t
i
m
e
t
h
a
t
a
p
e
r
s
o
n
h
a
s
l
i
v
e
d
o
r
a
t
h
i
n
g
h
a
s
e
x
i
st
e
d
,
a
g
e
:
2
8
u
n
t
i
l
a
g
e
:
7
8
S
e
x
R
e
f
e
r
s
t
o
a
se
t
o
f
b
i
o
l
o
g
i
c
a
l
a
t
t
r
i
b
u
t
e
s
i
n
h
u
m
a
n
s
.
I
t
i
s
p
r
i
mari
l
y
a
ss
o
c
i
a
t
e
d
w
i
t
h
p
h
y
si
c
a
l
a
n
d
p
h
y
s
i
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
i
n
c
l
u
d
i
n
g
c
h
r
o
m
o
s
o
mes,
g
e
n
e
e
x
p
r
e
ss
i
o
n
,
h
o
r
mo
n
e
l
e
v
e
l
s
a
n
d
f
u
n
c
t
i
o
n
,
a
n
d
r
e
p
r
o
d
u
c
t
i
v
e
/
se
x
u
a
l
a
n
a
t
o
my
.
[
“
o
”
=
f
e
ma
l
e
a
n
d
“
1
”
=
m
a
l
e
]
CP
C
a
n
b
e
d
i
v
i
d
e
d
i
n
t
o
h
e
a
r
t
-
r
e
l
a
t
e
d
c
h
e
st
p
a
i
n
(
c
a
r
d
i
a
c
c
h
e
st
p
a
i
n
)
a
n
d
c
h
e
st
p
a
i
n
t
h
a
t
i
s
n
o
t
f
r
o
m
a
h
e
a
r
t
c
o
n
d
i
t
i
o
n
(
n
o
n
-
c
a
r
d
i
a
c
c
h
e
st
p
a
i
n
)
.
Tr
e
st
b
p
s
Th
e
p
r
e
s
su
r
e
o
f
c
i
r
c
u
l
a
t
i
n
g
b
l
o
o
d
a
g
a
i
n
st
t
h
e
w
a
l
l
s
o
f
b
l
o
o
d
v
e
sse
l
s.
M
o
s
t
o
f
t
h
i
s
p
r
e
ss
u
r
e
r
e
su
l
t
s
f
r
o
m
t
h
e
h
e
a
r
t
p
u
mp
i
n
g
b
l
o
o
d
t
h
r
o
u
g
h
t
h
e
c
i
r
c
u
l
a
t
o
r
y
sy
s
t
e
m
.
[
mi
n
.
B
p
=
9
2
,
ma
x
.
B
p
=
2
0
2
]
C
h
o
l
I
s
b
i
o
s
y
n
t
h
e
si
z
e
d
b
y
a
l
l
a
n
i
mal
c
e
l
l
s
a
n
d
i
s
a
n
e
ss
e
n
t
i
a
l
s
t
r
u
c
t
u
r
a
l
c
o
m
p
o
n
e
n
t
o
f
a
n
i
ma
l
c
e
l
l
me
mb
r
a
n
e
s.
I
t
i
s
a
y
e
l
l
o
w
i
sh
c
r
y
st
a
l
l
i
n
e
so
l
i
d
.
M
i
n
.
C
h
o
l
=
1
2
4
,
ma
x
.
C
h
o
l
=
5
6
6
]
F
B
S
A
b
l
o
o
d
sam
p
l
e
w
i
l
l
b
e
t
a
k
e
n
a
f
t
e
r
a
n
o
v
e
r
n
i
g
h
t
f
a
st
.
A
f
a
s
t
i
n
g
b
l
o
o
d
s
u
g
a
r
l
e
v
e
l
l
e
ss
t
h
a
n
1
0
0
m
g
/
d
l
t
h
a
n
1
2
0
m
g
/
d
l
su
g
a
r
=
o
n
e
,
i
f
n
o
t
=
z
e
r
o
.
R
e
st
i
n
g
El
e
c
t
r
o
c
a
r
d
i
o
g
r
a
p
h
i
c
Th
e
h
e
a
r
t
i
s
a
mu
s
c
u
l
a
r
o
r
g
a
n
w
h
i
c
h
p
u
m
p
s
b
l
o
o
d
t
h
r
o
u
g
h
r
h
y
t
h
mi
c
c
o
n
t
r
a
c
t
i
o
n
s
i
n
d
u
c
e
d
b
y
e
l
e
c
t
r
i
c
i
mp
u
l
s
e
s
g
e
n
e
r
a
t
e
d
b
y
t
h
e
s
i
n
u
s
n
o
d
e
,
t
h
e
h
e
a
r
t
's
n
a
t
u
r
a
l
p
a
c
e
m
a
k
e
r
.
0
=
n
o
r
mal
,
1
=
h
a
s
S
T
-
T
w
a
v
e
a
b
n
o
r
m
a
l
i
t
y
(
T
w
a
v
e
i
n
v
e
r
s
i
o
n
)
,
2
=
s
h
o
w
s
l
e
f
t
v
e
n
t
r
i
c
u
l
a
r
h
y
p
e
r
t
r
o
p
h
y
.
Th
a
l
a
c
I
s t
h
e
m
a
x
i
m
u
m
h
e
a
r
t
r
a
t
e
o
f
p
a
t
i
e
n
t
?
Ex
a
n
g
Ex
e
r
c
i
se
i
n
d
u
c
e
d
a
n
g
i
n
a
(
e
x
a
n
g
)
,
S
T
d
e
p
r
e
ss
i
o
n
i
n
d
u
c
e
d
b
y
.
E
x
e
r
c
i
se
r
e
l
a
t
i
v
e
t
o
r
e
st
(
o
l
d
p
e
a
k
)
,
t
h
e
sl
o
p
e
o
f
t
h
e
p
e
a
k
.
E
x
e
r
c
i
se
S
T
se
g
m
e
n
t
(
sl
o
p
e
)
,
n
u
mb
e
r
o
f
ma
j
o
r
v
e
sse
l
s.
I
f
Y
,
t
h
e
v
a
l
u
e
w
i
l
l
b
e
“
1
”
,
a
n
d
“
N
”
f
o
r
n
o
t
.
O
l
d
P
e
a
k
A
t
e
n
t
r
y
i
n
d
i
c
a
t
e
s
se
v
e
r
e
c
o
r
o
n
a
r
y
l
e
si
o
n
s
a
n
d
l
a
r
g
e
b
e
n
e
f
i
t
s
o
f
a
n
e
a
r
l
y
i
n
v
a
s
i
v
e
t
r
e
a
t
m
e
n
t
s
t
r
a
t
e
g
y
i
n
u
n
s
t
a
b
l
e
c
o
r
o
n
a
r
y
a
r
t
e
r
y
d
i
sea
s
e
b
e
t
w
e
e
n
0
a
n
d
6
.
2
.
S
l
o
p
e
I
n
a
c
a
r
d
i
a
c
s
t
r
e
ss
t
e
s
t
,
a
n
S
T
d
e
p
r
e
ssi
o
n
o
f
a
t
l
e
a
st
1
mm
a
f
t
e
r
a
d
e
n
o
s
i
n
e
a
d
m
i
n
i
st
r
a
t
i
o
n
i
n
d
i
c
a
t
e
s
a
r
e
v
e
r
s
i
b
l
e
i
sc
h
e
mi
a
,
w
h
i
l
e
a
n
e
x
e
r
c
i
s
e
st
r
e
ss
t
e
st
r
e
q
u
i
r
e
s
a
n
S
T
d
e
p
r
e
ssi
o
n
o
f
a
t
l
e
a
st
2
mm
t
o
si
g
n
i
f
i
c
a
n
t
l
y
i
n
d
i
c
a
t
e
r
e
v
e
r
si
b
l
e
i
s
c
h
e
mi
a
.
CA
F
l
u
o
r
o
s
c
o
p
y
i
s
a
t
y
p
e
o
f
me
d
i
c
a
l
i
m
a
g
i
n
g
t
h
a
t
sh
o
w
s
a
c
o
n
t
i
n
u
o
u
s
X
-
r
a
y
i
mag
e
o
n
a
mo
n
i
t
o
r
,
m
u
c
h
l
i
k
e
a
n
X
-
r
a
y
m
o
v
i
e
.
Th
a
l
A
t
h
a
l
l
i
u
m
st
r
e
ss
t
e
s
t
i
s
a
n
u
c
l
e
a
r
me
d
i
c
i
n
e
s
t
u
d
y
t
h
a
t
sh
o
w
s
y
o
u
r
p
h
y
si
c
i
a
n
h
o
w
w
e
l
l
b
l
o
o
d
f
l
o
w
s
t
h
r
o
u
g
h
y
o
u
r
h
e
a
r
t
m
u
sc
l
e
w
h
i
l
e
y
o
u
'r
e
e
x
e
r
c
i
si
n
g
o
r
a
t
r
e
s
t
.
3
.
4
.
I
m
ple
m
ent
a
t
io
n
T
h
e
class
if
icatio
n
tech
n
iq
u
e
i
s
u
s
ed
to
c
r
ea
te
a
m
o
d
el
th
at
ca
n
b
e
u
s
ed
t
o
p
r
ed
ict
wh
eth
e
r
a
p
atien
t
with
a
ce
r
tain
attr
ib
u
te
h
as
s
tr
o
k
e
o
r
n
o
t.
T
o
d
o
th
is
,
we
r
e
d
u
ce
d
th
e
attr
ib
u
tes
o
f
th
e
d
ataset
ac
co
r
d
in
g
to
th
e
s
tr
o
k
e
r
is
k
f
ac
to
r
s
m
en
tio
n
ed
ab
o
v
e.
T
h
e
attr
ib
u
tes ar
e
‘
a
g
e’
,
‘
g
en
d
er
’
,
‘
h
y
p
e
r
ten
s
io
n
’
,
‘
av
g
_
g
lu
c
o
s
e_
lev
el’
to
in
d
icate
wh
eth
er
s
o
m
eo
n
e
h
as
d
iab
etes,
‘
h
ea
r
t_
d
is
ea
s
e’
,
‘
B
o
d
y
m
ass
in
d
ex
(
B
MI
)
’
to
in
d
icate
wh
eth
er
s
o
m
eo
n
e
is
o
b
ese,
an
d
‘
s
m
o
k
in
g
s
tatu
s
es.
T
h
e
‘
s
tr
o
k
e
’
attr
i
b
u
te
is
also
in
clu
d
e
d
as
th
e
lab
el/class
.
Fig
u
r
e
2
s
h
o
ws
h
o
w
th
e
o
p
er
at
o
r
s
in
R
ap
id
Min
er
ar
e
co
n
f
ig
u
r
ed
to
b
u
ild
th
e
d
ec
is
io
n
tr
ee
m
o
d
el.
B
ef
o
r
e
th
e
o
p
tim
ize
p
ar
am
eter
,
o
p
er
at
o
r
is
t
h
e
co
n
f
ig
u
r
atio
n
f
o
r
clea
n
in
g
an
d
r
ed
u
cin
g
th
e
d
ataset.
T
h
is
o
p
er
ato
r
is
a
wr
ap
p
e
r
o
p
er
ato
r
u
s
ed
to
tu
n
e
th
e
p
a
r
a
m
eter
s
o
f
th
e
o
p
er
ato
r
i
n
s
id
e
it.
Af
ter
b
ein
g
p
lu
g
g
ed
in
to
th
e
o
p
tim
ize
p
ar
am
eter
o
p
er
ato
r
,
th
e
d
ataset
is
s
p
lit in
to
tr
ain
in
g
an
d
test
in
g
d
ata
with
7
:3
r
atio
r
esp
ec
tiv
ely
.
T
h
en
,
th
e
tr
ain
in
g
d
ata
is
p
lu
g
g
e
d
in
to
th
e
d
ec
is
io
n
tr
ee
o
p
er
ato
r
t
o
co
n
s
tr
u
ct
t
h
e
d
ec
is
io
n
tr
ee
m
o
d
el,
with
th
e
cr
iter
i
o
n
p
ar
a
m
eter
s
et
to
‘
in
f
o
r
m
atio
n
_
g
ai
n
’
.
Oth
er
p
ar
am
eter
s
s
u
ch
as
m
ax
im
a
l_
d
ep
th
,
m
in
im
al_
leaf
_
s
ize,
co
n
f
id
en
ce
,
an
d
‘
m
in
im
al_
s
ize_
f
o
r
_
s
p
lit
will
b
e
tu
n
ed
b
y
t
h
e
wr
ap
p
e
r
.
T
h
e
m
o
d
el
th
e
n
p
ass
ed
to
th
e
a
p
p
ly
m
o
d
el
o
p
er
at
o
r
to
g
eth
er
with
th
e
test
in
g
d
ata.
W
h
ich
th
en
p
ass
ed
to
th
e
p
er
f
o
r
m
an
ce
o
p
er
ato
r
to
e
v
alu
ate
t
h
e
ac
cu
r
ac
y
o
f
th
e
d
ec
is
io
n
tr
ee
m
o
d
el.
T
h
e
ass
o
ciatio
n
tech
n
iq
u
e
is
u
s
ed
to
cr
ea
te
ass
o
ciatio
n
r
u
les
to
f
in
d
ass
o
ciatio
n
s
o
f
th
e
attr
ib
u
tes
in
th
e
d
ataset
th
at
a
r
e
r
elate
d
to
s
tr
o
k
e.
T
h
e
FP
-
Gr
o
wth
o
p
e
r
ato
r
we
u
s
ed
ac
c
ep
ts
attr
ib
u
tes
with
n
o
m
in
al
o
r
ca
teg
o
r
ical
v
al
u
es.
T
h
er
ef
o
r
e,
we
ch
o
s
e
t
h
e
attr
ib
u
tes
‘
g
en
d
er
’
,
‘
h
ea
r
t
_
d
is
ea
s
e’
,
‘
h
y
p
er
ten
s
io
n
’
,
‘
s
m
o
k
in
g
_
s
tatu
s
es,
an
d
‘
s
tr
o
k
e’
.
Fig
u
r
e
3
s
h
o
ws
th
e
co
n
f
ig
u
r
a
tio
n
o
f
th
e
o
p
er
ato
r
s
u
s
ed
to
cr
ea
te
th
e
ass
o
ciatio
n
r
u
les.
T
h
e
f
ir
s
t
5
o
p
er
ato
r
s
wer
e
th
e
s
am
e
as
th
e
o
n
e
u
s
ed
o
n
class
if
icatio
n
tech
n
iq
u
e,
with
e
x
ce
p
tio
n
o
f
th
e
s
elec
t
attr
ib
u
tes
o
p
er
ato
r
th
at
n
o
w
o
n
ly
s
elec
t
s
th
e
attr
ib
u
tes
m
en
ti
o
n
ed
ab
o
v
e.
T
h
e
r
e
d
u
ce
d
d
ataset
is
c
o
n
n
ec
ted
to
th
e
FP
-
g
r
o
wth
o
p
er
ato
r
with
th
e
p
ar
am
ete
r
m
in
_
s
u
p
p
o
r
t
is
s
et
to
0
.
3
an
d
o
th
er
p
a
r
am
eter
s
lef
t
d
ef
au
lt.
T
h
en
th
e
f
r
eq
u
e
n
t
item
s
et
f
r
o
m
th
e
o
p
e
r
ato
r
is
p
ass
ed
to
th
e
cr
ea
te
a
s
s
o
ciatio
n
r
u
les
o
p
er
ato
r
to
cr
ea
te
th
e
ass
o
ciatio
n
r
u
les.
T
h
e
p
a
r
am
eter
n
o
n
co
n
f
i
d
en
ce
is
s
et
to
0
.
5
,
an
d
o
th
er
p
ar
am
eter
s
a
r
e
also
lef
t d
ef
a
u
lt.
Fig
u
r
e
4
s
h
o
ws
th
e
clu
s
ter
s
m
ad
e
b
y
th
e
clu
s
ter
in
g
o
p
er
at
o
r
.
T
h
er
e,
we
ca
n
s
ee
th
e
2
cl
u
s
ter
s
with
th
e
av
er
a
g
e
v
alu
es
o
f
t
h
e
attr
i
b
u
tes
s
elec
ted
ab
o
v
e
.
T
h
e
f
ir
s
t
clu
s
ter
(
clu
s
ter
_
0
)
h
as
7
0
8
item
s
an
d
th
e
s
ec
o
n
d
(
clu
s
ter
_
1
)
h
as
4
2
3
4
it
em
s
.
A
s
we
ca
n
s
ee
,
th
e
f
ir
s
t
clu
s
ter
h
as
th
e
h
ig
h
est
r
elativ
e
p
r
o
p
o
r
tio
n
o
f
p
atien
ts
t
h
at
h
av
e
s
tr
o
k
e
at
1
2
%.
T
h
is
clu
s
ter
is
co
n
s
is
ted
o
f
p
atien
ts
with
an
av
e
r
ag
e
B
MI
o
f
3
1
,
a
g
e
o
f
5
8
,
an
d
av
er
ag
e
g
lu
co
s
e
lev
el
o
f
2
0
1
.
Fro
m
t
h
is
r
esu
lt,
we
ca
n
cr
ea
te
an
a
s
s
u
m
p
tio
n
th
at
eld
er
p
atien
ts
th
at
ar
e
co
n
s
id
er
ed
o
b
ese
an
d
h
av
e
d
iab
etes
a
r
e
m
o
r
e
lik
ely
to
h
av
e
s
tr
o
k
e.
I
n
th
e
s
ec
o
n
d
clu
s
ter
,
o
n
ly
3
,
7
%
o
f
th
e
4
2
3
4
p
atien
ts
h
av
e
s
tr
o
k
e.
W
h
ich
is
co
n
s
is
ted
o
f
p
atien
ts
with
in
th
e
ag
e
o
f
4
0
,
B
MI
o
f
2
7
,
a
n
d
a
v
er
ag
e
g
l
u
co
s
e
lev
el
o
f
9
0
.
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.
10
,
No
.
3
,
Dec
em
b
er
20
2
1
:
1
8
2
–
1
8
7
186
Fig
u
r
e
2
.
Op
e
r
ato
r
c
o
n
f
ig
u
r
ati
o
n
m
o
d
el
Fig
u
r
e
3
.
Op
e
r
ato
r
c
o
n
f
ig
u
r
ati
o
n
f
o
r
th
e
tech
n
iq
u
e
Fig
u
r
e
4
.
C
lu
s
ter
s
m
ad
e
b
y
th
e
clu
s
ter
in
g
o
p
e
r
ato
r
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
we
ca
n
p
r
e
d
ict
wh
eth
er
a
p
er
s
o
n
wo
u
l
d
p
o
ten
tially
h
av
e
h
ea
r
t
d
is
ea
s
e
o
r
n
o
t.
T
h
er
ef
o
r
e,
th
e
p
er
s
o
n
ca
n
b
e
tr
ea
ted
b
e
f
o
r
e
th
e
d
is
ea
s
e
g
ets
wo
r
s
e
o
r
ev
en
p
r
e
v
en
t
th
e
d
is
ea
s
e
f
r
o
m
h
ap
p
en
i
n
g
to
g
eth
er
.
C
lass
if
icatio
n
is
an
ap
p
r
o
p
r
iate
d
ata
m
in
in
g
tech
n
iq
u
e
f
o
r
p
r
o
ce
s
s
in
g
h
ea
r
t
d
is
ea
s
e
d
atasets
b
ec
a
u
s
e
th
e
d
ataset
u
s
ed
h
as
tar
g
et
v
a
r
iab
les
to
b
e
class
if
ied
.
C
lass
if
icatio
n
wi
ll
class
if
y
d
ata
in
t
o
g
r
o
u
p
s
o
f
class
es
th
at
alr
ea
d
y
ex
is
t.
T
h
er
e
will b
e
n
o
f
o
r
m
ati
o
n
o
f
n
ew
g
r
o
u
p
s
.
An
d
th
e
p
r
o
ce
s
s
is
s
u
p
er
v
is
ed
.
Dif
f
er
en
t
f
r
o
m
clu
s
ter
in
g
wh
i
ch
is
a
p
r
o
ce
s
s
f
o
r
g
r
o
u
p
in
g
d
ata
in
to
s
ev
er
al
clu
s
ter
s
o
r
g
r
o
u
p
s
s
o
th
at
th
e
d
ata
in
o
n
e
clu
s
ter
h
as si
m
ilar
ities
.
Alm
o
s
t
ev
er
y
d
ay
t
h
er
e
is
an
i
n
cr
ea
s
e
in
th
e
r
atio
o
f
th
e
ar
t
a
ttack
s
.
T
o
r
ed
u
ce
h
ea
r
t
d
is
ea
s
e
a
s
y
s
tem
is
n
ee
d
ed
to
d
etec
t
p
o
ten
tial
h
ea
r
t
attac
k
s
.
B
ig
d
ata
m
u
s
t
b
e
an
aly
ze
d
f
ir
s
t
b
ef
o
r
e
tak
in
g
a
p
atter
n
th
at
is
u
s
ef
u
l
f
o
r
d
ec
is
io
n
m
a
k
in
g
.
R
ap
id
Min
er
is
u
s
ed
in
th
is
s
tu
d
y
to
p
r
ed
ict
p
atien
ts
d
iag
n
o
s
e
d
with
a
h
ea
r
t
attac
k
u
s
in
g
d
ata
m
in
in
g
tech
n
iq
u
e
s
Naïv
e
B
ay
e
s
.
W
e
u
s
e
n
aï
v
e
B
ay
es
clas
s
if
icatio
n
b
ec
au
s
e
in
n
a
ïv
e
B
ay
es
class
if
icatio
n
we
ca
n
d
eter
m
i
n
e
tar
g
et
wh
ich
ca
n
b
e
u
s
ed
to
an
s
wer
s
o
m
e
q
u
esti
o
n
s
lik
e
wh
eth
er
th
e
p
atien
t
h
as th
e
p
o
ten
tial f
o
r
h
ea
r
t d
is
ea
s
e.
Af
ter
d
ata
an
aly
s
t,
we
ca
n
u
s
e
d
ata
to
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
(
E
HR
)
.
RE
F
E
R
E
NC
E
S
[1
]
G
.
Vilah
u
r,
J.
J.
Ba
d
imo
n
,
R.
B
u
g
iard
i
n
i,
a
n
d
L.
Ba
d
imo
n
,
“
P
e
rsp
e
c
ti
v
e
s:
Th
e
b
u
r
d
e
n
o
f
c
a
rd
io
v
a
sc
u
lar
risk
fa
c
to
rs
a
n
d
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
se
in
Eu
r
o
p
e
a
n
d
w
o
rld
wi
d
e
,
”
Eu
ro
p
e
a
n
He
a
rt
J
o
u
rn
a
l
S
u
p
p
lem
e
n
ts
,
v
o
l.
1
6
,
n
o
.
s
u
p
p
l
A
,
p
p
.
A
7
–
A
1
1
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
9
3
/
e
u
rh
e
a
rtj
/su
t
0
0
3
.
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
E
lectro
n
ic
h
ea
lth
r
ec
o
r
d
to
p
r
ed
ict
a
h
ea
r
t a
tta
ck
u
s
ed
d
a
ta
min
in
g
w
ith
…
(
Jo
h
a
n
es F
ern
a
n
d
es A
n
d
r
y
)
187
[2
]
A.
M
a
ria
a
n
d
Y.
KS,
“
P
a
t
h
o
g
e
n
e
sis
o
f
Ath
e
ro
sc
lero
sis
A
Re
v
iew
,
”
M
e
d
ica
l
&
Cli
n
ic
a
l
Rev
iews
,
v
o
l.
2
,
n
o
.
3
,
2
0
1
6
,
d
o
i:
1
0
.
2
1
7
6
7
/2
4
7
1
-
2
9
9
x
.
1
0
0
0
0
3
1
.
[3
]
E.
Na
so
n
,
“
An
o
v
e
rv
iew
o
f
c
a
rd
io
v
a
sc
u
lar
d
ise
a
se
a
n
d
re
se
a
rc
h
,
”
2
0
0
7
.
[On
l
in
e
].
Av
a
il
a
b
le:
h
tt
p
s:/
/www
.
ra
n
d
.
o
rg
/co
n
te
n
t/
d
a
m
/ran
d
/p
u
b
s/wo
rk
i
n
g
_
p
a
p
e
rs/
2
0
0
7
/RAND
_
WR4
6
7
.
p
d
f.
[4
]
I.
Al
M
a
m
o
o
n
e
t
a
l
.
,
“
A
P
ro
p
o
sa
l
o
f
Bo
d
y
Im
p
lem
e
n
tab
le
Early
H
e
a
rt
Attac
k
De
tec
ti
o
n
S
y
ste
m
,
”
M
a
l
a
y
sia
J
a
p
a
n
In
ter
n
a
t
io
n
a
l
I
n
stit
u
e
o
f
T
e
c
h
n
o
lo
g
y
(M
J
IIT
)
,
n
o
.
1
–
4
,
p
p
.
1
–
4
,
2
0
1
3
.
[5
]
B.
Ristev
sk
i
a
n
d
M
.
C
h
e
n
,
“
Big
Da
ta An
a
ly
ti
c
s in
M
e
d
ici
n
e
a
n
d
He
a
lt
h
c
a
re
,
”
J
o
u
rn
a
l
o
f
in
teg
r
a
ti
v
e
b
io
i
n
fo
rm
a
t
ics
,
v
o
l.
1
5
,
n
o
.
3
,
p
.
2
0
1
7
0
0
3
0
,
M
a
y
2
0
1
8
,
d
o
i:
1
0
.
1
5
1
5
/
ji
b
-
2
0
1
7
-
0
0
3
0
.
[6
]
N.
Zu
l
k
a
rn
a
in
a
n
d
M
.
An
s
h
a
ri,
“
Big
d
a
ta:
C
o
n
c
e
p
t,
a
p
p
li
c
a
ti
o
n
s,
&
c
h
a
ll
e
n
g
e
s,”
2
0
1
6
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
M
a
n
a
g
e
me
n
t
a
n
d
T
e
c
h
n
o
l
o
g
y
(ICI
M
T
e
c
h
)
.
IEE
E,
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/i
c
imte
c
h
.
2
0
1
6
.
7
9
3
0
3
5
0
.
[7
]
H.
J.
Watso
n
,
“
T
u
to
r
ial:
Bi
g
Da
ta
An
a
ly
ti
c
s:
Co
n
c
e
p
ts,
Tec
h
n
o
lo
g
ies
,
a
n
d
Ap
p
li
c
a
ti
o
n
s,”
Co
mm
u
n
ica
ti
o
n
s
o
f
t
h
e
Asso
c
ia
ti
o
n
f
o
r In
fo
rm
a
t
io
n
S
y
ste
ms
,
v
o
l
.
3
4
,
2
0
1
4
,
d
o
i:
1
0
.
1
7
7
0
5
/
1
c
a
is.0
3
4
6
5
.
[8
]
D.
Ca
c
k
e
tt
,
“
In
fo
rm
a
ti
o
n
M
a
n
a
g
e
m
e
n
t
a
n
d
Big
d
a
ta:
A
Re
fe
re
n
c
e
Arc
h
it
e
c
tu
re
,
”
Or
a
c
le:
Red
wo
o
d
Cit
y
,
CA,
US
A
,
2
0
1
3
.
[9
]
B.
F
e
ld
m
a
n
,
E.
M
.
M
a
rti
n
,
a
n
d
T.
S
k
o
tn
e
s,
“
Bi
g
d
a
ta
i
n
h
e
a
lt
h
c
a
re
h
y
p
e
a
n
d
h
o
p
e
,
”
Dr
.
B
o
n
n
ie
,
v
o
l
.
3
6
0
,
p
p
.
1
2
2
–
1
2
5
,
2
0
1
2
.
[1
0
]
Z.
S
u
n
,
K.
S
tran
g
,
a
n
d
R.
Li
,
“
Big
Da
ta
wit
h
Ten
B
ig
Ch
a
ra
c
teristics
,
”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
g
Da
t
a
Res
e
a
rc
h
,
2
0
1
8
,
p
p
.
5
6
–
6
1
,
d
o
i:
1
0
.
1
1
4
5
/
3
2
9
1
8
0
1
.
3
2
9
1
8
2
2
.
[1
1
]
A.
Og
u
n
ti
m
il
e
h
in
a
n
d
E.
O.
A
d
e
m
o
la,
“
A
re
v
iew
o
f
b
ig
d
a
ta
m
a
n
a
g
e
m
e
n
t,
b
e
n
e
fit
s
a
n
d
c
h
a
ll
e
n
g
e
s,”
A
Rev
iew
o
f
Bi
g
Da
ta
M
a
n
a
g
e
me
n
t,
Be
n
e
fi
ts a
n
d
C
h
a
l
len
g
e
s
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
1
–
7
,
2
0
1
4
.
[1
2
]
A.
G
a
n
d
o
m
i
a
n
d
M
.
Ha
id
e
r,
“
Be
y
o
n
d
th
e
h
y
p
e
:
Bi
g
d
a
ta
c
o
n
c
e
p
ts
,
m
e
th
o
d
s,
a
n
d
a
n
a
ly
ti
c
s,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
M
a
n
a
g
e
me
n
t
,
v
o
l.
3
5
,
n
o
.
2
,
p
p
.
1
3
7
–
1
4
4
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/j
.
ij
in
f
o
m
g
t.
2
0
1
4
.
1
0
.
0
0
7
.
[1
3
]
S
.
S
a
m
i
a
n
d
N.
S
a
e
l,
“
E
x
trac
t
F
iv
e
Ca
teg
o
ries
CP
IVW
fr
o
m
th
e
9
V’s
C
h
a
ra
c
teristics
o
f
th
e
Big
Da
ta,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
7
,
n
o
.
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
4
5
6
9
/i
jac
sa
.
2
0
1
6
.
0
7
0
3
3
7
.
[1
4
]
M
.
Bh
a
ra
ti
a
n
d
M
.
Ra
m
a
g
e
ri,
“
D
a
ta m
in
in
g
tec
h
n
i
q
u
e
s a
n
d
a
p
p
li
c
a
ti
o
n
s,”
2
0
1
0
.
[1
5
]
K.
S
u
m
a
th
i,
S
.
Ka
n
n
a
n
,
a
n
d
K.
Na
g
a
ra
jan
,
“
Da
ta
M
in
in
g
:
An
a
ly
sis
o
f
stu
d
e
n
t
d
a
tab
a
se
u
sin
g
Clas
sifica
ti
o
n
Tec
h
n
iq
u
e
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Ap
p
li
c
a
ti
o
n
s
,
v
o
l.
1
4
1
,
n
o
.
8
,
p
p
.
2
2
–
2
7
,
2
0
1
6
,
d
o
i:
1
0
.
5
1
2
0
/
ij
c
a
2
0
1
6
9
0
9
7
0
3
.
[1
6
]
H.
S
a
h
u
,
S
.
S
h
rm
a
,
a
n
d
S
.
G
o
n
d
h
a
lak
a
r,
“
A
b
rief
o
v
e
rv
iew
o
n
d
a
ta
m
in
in
g
s
u
rv
e
y
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
T
e
c
h
n
o
lo
g
y
a
n
d
E
lec
t
ro
n
ics
E
n
g
i
n
e
e
rin
g
(IJ
CT
EE
)
,
v
o
l
.
1
,
n
o
.
3
,
p
p
.
1
1
4
–
1
2
1
,
2
0
1
1
.
[1
7
]
H.
A.
M
a
d
n
i,
Z.
An
wa
r,
a
n
d
M
.
A.
S
h
a
h
,
“
Da
ta
m
in
in
g
tec
h
n
i
q
u
e
s
a
n
d
a
p
p
li
c
a
ti
o
n
s
—
A
d
e
c
a
d
e
re
v
iew
,
”
2
0
1
7
2
3
rd
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Au
t
o
ma
t
io
n
a
n
d
Co
mp
u
t
in
g
(ICAC)
.
IE
EE
,
2
0
1
7
,
d
o
i:
1
0
.
2
3
9
1
9
/i
c
o
n
a
c
.
2
0
1
7
.
8
0
8
2
0
9
0
.
[1
8
]
F
.
Z
u
h
a
a
n
d
G
.
Ac
h
u
t
h
a
n
,
“
An
a
l
y
sis
o
f
Da
ta
M
in
i
n
g
Tec
h
n
i
q
u
e
s
a
n
d
it
s
Ap
p
li
c
a
ti
o
n
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
1
4
0
,
n
o
.
3
,
p
p
.
6
–
1
4
,
2
0
1
6
,
d
o
i:
1
0
.
5
1
2
0
/i
jca
2
0
1
6
9
0
9
2
4
9
.
[1
9
]
H.
He
m
in
g
wa
y
e
t
a
l.
,
“
Bi
g
d
a
t
a
fro
m
e
lec
tro
n
ic
h
e
a
lt
h
re
c
o
rd
s
fo
r
e
a
rly
a
n
d
late
tran
sla
ti
o
n
a
l
c
a
rd
io
v
a
sc
u
lar
re
se
a
rc
h
:
c
h
a
ll
e
n
g
e
s
a
n
d
p
o
ten
ti
a
l,
”
Eu
ro
p
e
a
n
h
e
a
rt
j
o
u
rn
a
l
,
v
o
l.
3
9
,
n
o
.
1
6
,
p
p
.
1
4
8
1
–
1
4
9
5
,
Ap
r.
2
0
1
8
,
d
o
i:
1
0
.
1
0
9
3
/e
u
rh
e
a
rtj
/eh
x
4
8
7
.
[2
0
]
S
.
T
h
a
n
k
a
c
h
a
n
a
n
d
S
u
c
h
it
h
ra
,
“
D
a
ta
M
in
i
n
g
&
Ware
h
o
u
sin
g
Al
g
o
rit
h
m
s
a
n
d
it
s
Ap
p
li
c
a
ti
o
n
i
n
M
e
d
ica
l
S
c
ien
c
e
-
A
S
u
rv
e
y
,
”
2
0
1
7
.
[2
1
]
P
.
C.
M
c
M
u
ll
e
n
e
t
a
l.
,
“
E
lec
tro
n
ic
M
e
d
ica
l
Re
c
o
rd
s
a
n
d
El
e
c
tro
n
ic
He
a
lt
h
Re
c
o
rd
s:
Ov
e
r
v
iew
fo
r
N
u
rse
P
ra
c
ti
ti
o
n
e
rs,”
T
h
e
J
o
u
rn
a
l
fo
r
Nu
rs
e
Pra
c
ti
ti
o
n
e
rs
,
v
o
l
.
1
0
,
n
o
.
9
,
p
p
.
6
6
0
–
6
6
5
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
1
6
/
j.
n
u
rp
ra
.
2
0
1
4
.
0
7
.
0
1
3
.
[2
2
]
E.
D.
M
a
d
y
a
tma
d
ja,
D.
J.
M
.
S
e
m
b
iri
n
g
,
S
.
M
.
B
.
P
.
An
g
i
n
,
D.
F
e
rd
y
,
a
n
d
J.
F
.
A
n
d
r
y
,
“
Bi
g
Da
ta
in
Ed
u
c
a
ti
o
n
a
l
In
stit
u
t
io
n
s
u
si
n
g
Ra
p
i
d
M
i
n
e
r
t
o
P
re
d
ict
Lea
rn
i
n
g
Eff
e
c
ti
v
e
n
e
ss
,
”
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
1
7
,
n
o
.
4
,
p
p
.
403
–
4
1
3
,
2
0
2
1
,
d
o
i:
1
0
.
3
8
4
4
/
jcs
sp
.
2
0
2
1
.
4
0
3
.
4
1
3
.
[2
3
]
L.
Ho
n
g
,
M
.
L
u
o
,
R.
Wan
g
,
P
.
Lu
,
W.
L
u
,
a
n
d
L.
Lu
,
“
Big
Da
ta
in
He
a
lt
h
Ca
re
:
Ap
p
li
c
a
ti
o
n
s
a
n
d
Ch
a
ll
e
n
g
e
s,”
Da
ta
a
n
d
In
fo
rm
a
t
io
n
M
a
n
a
g
e
me
n
t
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
1
7
5
–
1
9
7
,
2
0
1
8
,
d
o
i:
1
0
.
2
4
7
8
/d
im
-
2
0
1
8
-
0
0
1
4
.
[2
4
]
S
.
A.
Ala
sa
d
i
a
n
d
W.
S
.
B
h
a
y
a
,
“
Re
v
iew
o
f
d
a
ta
p
re
p
r
o
c
e
ss
in
g
tec
h
n
i
q
u
e
s
i
n
d
a
ta
m
i
n
in
g
,
”
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s
,
v
o
l.
1
2
,
n
o
.
1
6
,
p
p
.
4
1
0
2
–
4
1
0
7
,
2
0
1
7
.
[2
5
]
B.
Ko
l
u
k
isa
e
t
a
l.
,
“
Dia
g
n
o
sis
o
f
c
o
ro
n
a
ry
h
e
a
rt
d
ise
a
se
v
ia
c
las
si
fica
ti
o
n
a
lg
o
r
it
h
m
s
a
n
d
a
n
e
w
fe
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
o
lo
g
y
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
D
a
ta
M
i
n
in
g
S
c
ien
c
e
,
v
o
l.
1
,
n
o
.
1
,
p
p
.
8
–
1
5
,
2
0
1
9
.
[2
6
]
B.
Afe
n
i,
T
.
Aru
leb
a
,
a
n
d
I.
Olo
y
e
d
e
,
“
Hy
p
e
rten
sio
n
P
re
d
ictio
n
S
y
ste
m
Us
in
g
Na
iv
e
Ba
y
e
s
Clas
sifier,”
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s i
n
M
a
th
e
ma
ti
c
s a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
1
–
1
1
,
2
0
1
7
,
d
o
i:
1
0
.
9
7
3
4
/
jam
c
s/2
0
1
7
/
3
5
6
1
0
.
[2
7
]
S
.
P
a
lan
iap
p
a
n
a
n
d
R.
Aw
a
n
g
,
“
In
telli
g
e
n
t
h
e
a
rt
d
ise
a
se
p
re
d
ictio
n
sy
ste
m
u
si
n
g
d
a
ta
m
in
in
g
t
e
c
h
n
i
q
u
e
s,”
2
0
0
8
IEE
E/
ACS
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
m
p
u
ter
S
y
ste
ms
a
n
d
Ap
p
li
c
a
ti
o
n
s
.
IE
EE
,
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/aic
c
sa
.
2
0
0
8
.
4
4
9
3
5
2
4
.
[2
8
]
S
.
Nik
h
a
r
a
n
d
A.
M
.
Ka
ra
n
d
ik
a
r
,
“
P
re
d
ictio
n
o
f
h
e
a
rt
d
ise
a
se
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
r
it
h
m
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
En
g
in
e
e
rin
g
,
M
a
n
a
g
e
me
n
t
a
n
d
S
c
ien
c
e
,
v
o
l.
2
,
n
o
.
6
,
p
.
2
3
9
4
8
4
,
2
0
1
6
.
[2
9
]
T.
K
a
n
d
M
.
Wa
d
h
a
wa
,
“
An
a
l
y
sis
a
n
d
C
o
m
p
a
riso
n
S
t
u
d
y
o
f
Da
ta
M
in
in
g
Alg
o
rit
h
m
s
Us
in
g
Ra
p
id
M
in
e
r,
”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
t
e
r
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
A
p
p
li
c
a
ti
o
ns
,
v
o
l.
6
,
n
o
.
1
,
p
p
.
9
–
2
1
,
2
0
1
6
,
d
o
i
:
1
0
.
5
1
2
1
/
ij
c
se
a
.
2
0
1
6
.
6
1
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.