I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
A
I
)
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
2021
, pp.
4
3
~
5
0
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
10
.i
1
.pp
4
3
-
5
0
43
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
E
xp
e
r
t
sys
t
e
m
f
or
h
e
ar
t
d
i
se
ase
b
ase
d
on
e
l
e
c
t
r
oc
a
r
d
i
ogr
am
d
at
a u
si
n
g c
e
r
t
ai
n
t
y f
ac
t
or
w
i
t
h
m
u
l
t
i
p
l
e
r
u
l
e
S
u
m
ia
t
i
1
,
H
oga S
ar
agi
h
2
,
T
it
ik
K
h
aw
a
A
b
d
u
l
R
ah
m
an
3
,
A
g
u
n
g T
r
ia
yu
d
i
4
1
Information
and Commu
nication Tech
nology, Un
iversitas
Serang Raya
,
Indonesia
2
Information
and Commu
nication
Technology
,
Universitas Bakrie,
Indonesia
1,
3
Department of School
and Graduate
,
Asia e University,
Malasyia
4
Informatic Depart
ment
,
Universitas Nasion
al, Indonesia
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
A
pr
1
7
, 20
20
R
e
vi
s
e
d
D
e
c
2
3
, 20
2
0
A
c
c
e
pt
e
d
J
a
n
2, 20
21
Limited
public
health
services
in
remote
areas,
where
the
l
ack
of
transporta
tion
infrastruc
ture,
facilities,
communication
facilities
and
minimal
medical
personnel,
especially
for
areas
with
underdeve
loped,
foremost,
and
regular
(3T)
status.
The
limitat
ion
of
medi
cal
personnel
is
one
of
the
factors
for
the
high
mortality
rate
of
heart
disease.
On
the
other
ha
nd,
the
development
of
information
technology,
especially
in
the
field
of
com
puting,
is
very
fast
in
the
era
of
the
industrial
revolution
4.0,
but
not
y
et
used
optimally,
especially
in
the
health
sector.
This
study
aims
to
dev
elop
a
system
or
software
that
can
replace
a
doctor
for
the
process
of
iden
tifying
heart
defects
based
on
an
expert
system.
Expert
system
developed
with
the
certainty
factor
with
multi
ple
r
ule
approach.
System
testing
is
carr
ied
out
from
the
results
of
the
system
validity
with
experts,
so
that
the
syst
em
test
results
produce
a
certainty
factor
value
for
a
normal
heart
of
0.95
and
an
accuracy
level
of
95%,
while
the
certainty
factor
(CF)
valu
e
for
an
ab
normal
heart is 0.99 and produces an a
ccuracy rate
of 99%.
K
e
y
w
o
r
d
s
:
A
c
c
ur
a
c
y
C
e
r
ta
in
ty
f
a
c
to
r
E
xpe
r
t
s
ys
te
m
s
H
e
a
r
t
di
s
e
a
s
e
M
ul
ti
pl
e
r
ul
e
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
S
um
ia
ti
D
e
pa
r
tm
e
nt
of
S
c
hool
a
nd G
r
a
dua
te
A
s
ia
e
U
ni
ve
r
s
it
y
W
is
m
a
S
uba
ng J
a
y
a
, N
o.106, J
a
l
a
n s
s
15/
4 S
uba
ng
J
a
ya
, 47500
S
e
la
ngor
,
M
a
la
ys
ia
E
m
a
il
:
s
um
ia
ti
ha
r
to
yo52@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
T
he
de
ve
lo
pm
e
nt
of
in
f
or
m
a
ti
on
te
c
hnol
ogy
a
t
th
e
ti
m
e
of
th
e
i
ndus
tr
ia
l
r
e
vol
ut
io
n
4.0
w
a
s
gr
ow
in
g
r
a
pi
dl
y,
w
hi
c
h
c
a
n
b
e
s
e
e
n
f
r
om
va
r
io
us
s
c
ie
nc
e
s
,
e
s
pe
c
i
a
ll
y
da
ta
m
in
in
g,
e
xpe
r
t
s
y
s
te
m
s
,
f
uz
z
y
lo
gi
c
a
nd
ot
he
r
s
[
1]
.
A
pa
r
t
f
r
om
th
e
f
ie
ld
of
e
duc
a
ti
on
in
th
e
onl
in
e
le
a
r
n
in
g
pr
oc
e
s
s
,
be
s
id
e
s
th
a
t,
th
e
he
a
lt
h
s
e
c
to
r
c
a
n
a
ls
o
be
us
e
d
f
or
th
e
di
a
gnos
is
of
a
di
s
e
a
s
e
u
s
in
g
a
s
ys
te
m
th
a
t
c
a
n
r
e
pl
a
c
e
a
n
e
xpe
r
t
known
a
s
a
n
e
xpe
r
t
s
ys
te
m
[
2
-
4]
.
T
he
pr
obl
e
m
in
th
is
s
tu
dy
li
e
s
in
th
e
li
m
it
a
ti
ons
of
c
om
m
uni
ty
he
a
lt
h
s
e
r
vi
c
e
s
in
r
e
m
ot
e
a
r
e
a
s
,
w
he
r
e
is
th
e
la
c
k
of
t
r
a
ns
por
ta
ti
on
in
f
r
a
s
tr
uc
tu
r
e
,
f
a
c
il
it
ie
s
,
m
e
a
ns
of
c
om
m
uni
c
a
ti
on
a
nd
m
in
im
a
l
m
e
di
c
a
l
pe
r
s
onne
l,
e
s
pe
c
ia
ll
y
f
or
a
r
e
a
s
w
it
h
unde
r
de
ve
lo
pe
d,
f
r
ont
ie
r
a
nd
r
e
gul
a
r
(
3T
)
s
ta
tu
s
.
F
a
c
to
r
s
of
li
m
it
e
d
m
e
di
c
a
l
pe
r
s
onne
l,
is
one
of
th
e
f
a
c
to
r
s
c
a
us
in
g
th
e
hi
gh
num
b
e
r
of
pa
ti
e
nt
s
t
o
di
e
f
r
om
he
a
r
t
di
s
e
a
s
e
.
O
n
th
e
ot
he
r
ha
nd,
th
e
de
ve
lo
pm
e
nt
of
in
f
or
m
a
ti
on
te
c
hnol
ogy,
e
s
pe
c
ia
ll
y
in
th
e
f
ie
ld
of
c
om
put
in
g,
is
gr
ow
in
g
ve
r
y
r
a
pi
dl
y,
but
not
us
e
d
opt
im
a
ll
y,
e
s
pe
c
ia
ll
y
in
th
e
he
a
lt
h
s
e
c
to
r
.
I
n
a
ddi
ti
on,
th
e
pr
ob
le
m
s
th
a
t
e
xi
s
t
w
it
h
th
e
EK
G
de
vi
c
e
a
r
e
not
c
ur
r
e
nt
ly
a
bl
e
to
a
na
ly
z
e
a
nd
id
e
nt
if
y
th
e
pa
ti
e
nt
'
s
he
a
r
t,
E
C
G
to
ol
s
onl
y
di
s
pl
a
y
g
r
a
phs
,
not
di
s
pl
a
yi
ng
th
e
f
in
a
l
r
e
s
ul
ts
of
he
a
r
t
a
bnor
m
a
li
ti
e
s
,
s
o
it
s
ti
ll
r
e
qui
r
e
s
a
c
a
r
di
ol
ogi
s
t
to
be
a
bl
e
to
pr
e
s
e
nt
th
e
r
e
s
ul
ts
of
th
e
E
C
G
m
e
di
c
a
l
r
e
c
or
d
[
5]
.
S
o
th
a
t
w
it
h
e
xi
s
t
in
g
pr
obl
e
m
s
it
is
ve
r
y
ne
c
e
s
s
a
r
y
to
m
a
ke
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
4
3
-
5
0
44
s
ys
te
m
th
a
t
c
a
n
r
e
pl
a
c
e
th
e
pos
it
io
n
of
a
n
e
xp
e
r
t,
w
he
r
e
th
is
s
y
s
te
m
is
a
bl
e
to
a
dopt
th
e
e
xpe
r
ti
s
e
of
a
n
e
xp
e
r
t
in
to
a
s
y
s
te
m
,
w
it
h
th
e
e
xpe
r
t
s
ys
te
m
is
a
bl
e
to
ov
e
r
c
om
e
th
e
p
r
obl
e
m
o
f
s
hor
ta
ge
s
of
s
pe
c
ia
li
s
ts
in
th
e
h
e
a
lt
h
s
e
c
to
r
,
e
s
pe
c
ia
ll
y
he
a
r
t
di
s
e
a
s
e
.
T
he
s
y
s
te
m
bui
lt
f
or
th
e
id
e
nt
if
ic
a
ti
on
of
he
a
r
t
de
f
e
c
t
s
is
known
a
s
a
n
e
xpe
r
t
s
ys
te
m
w
it
h
a
c
e
r
ta
in
ty
f
a
c
to
r
a
ppr
oa
c
h
w
it
h
m
ul
ti
pl
e
r
ul
e
s
,
th
e
c
e
r
ta
in
ty
f
a
c
to
r
m
e
th
od
is
a
s
im
pl
e
c
om
put
a
ti
ona
l
m
ode
l
th
a
t
a
ll
ow
s
e
xpe
r
ts
t
o e
s
ti
m
a
te
c
onf
id
e
nc
e
i
n c
onc
lu
s
io
ns
.
A
n
e
xpe
r
t
s
ys
te
m
th
a
t
is
bui
lt
r
e
qui
r
e
s
a
b
a
s
ic
knowle
dge
pr
oc
e
s
s
,
w
he
r
e
th
e
ba
s
ic
knowl
e
dge
of
a
n
e
xpe
r
t
c
a
n
be
a
dopt
e
d
in
to
a
n
a
ppl
ic
a
ti
on
[
6
-
7]
.
T
he
knowle
dge
a
c
qui
s
it
io
n
pr
oc
e
s
s
i
s
a
n
e
xt
r
a
c
ti
on
pr
oc
e
s
s
,
w
ho
is
a
bl
e
to
g
a
th
e
r
e
xpe
r
t
knowle
dge
f
r
om
one
or
m
or
e
s
ou
r
c
e
s
,
s
o
th
a
t
th
e
r
e
s
ul
ts
of
da
ta
e
xt
r
a
c
ti
on
c
a
n
a
f
f
e
c
t
th
e
out
put
of
a
s
ys
te
m
.
E
xpe
r
t
s
ys
te
m
is
a
br
e
a
kt
hr
ough
in
th
e
de
ve
lo
pm
e
nt
of
in
f
or
m
a
ti
on
te
c
hnol
ogy
w
hi
c
h
w
a
s
de
ve
lo
p
e
d
w
it
h
th
e
a
im
of
a
dopt
in
g
th
e
a
bi
li
ty
of
a
n
e
xpe
r
t
to
di
a
gnos
e
a
di
s
e
a
s
e
[
8
-
10]
.
E
xpe
r
t
s
ys
te
m
c
a
n
he
lp
a
pa
ti
e
nt
a
nd
a
la
ym
a
n
to
be
a
bl
e
to
c
om
m
uni
c
a
te
a
bout
a
di
s
e
a
s
e
w
it
hout
be
in
g
li
m
it
e
d
by
di
s
ta
nc
e
a
nd
ge
ogr
a
phi
c
a
l
c
ondi
ti
ons
of
th
e
c
ount
r
y
[
11
-
12]
.
T
he
us
e
r
w
il
l
be
a
s
s
is
te
d
or
f
ol
lo
w
e
d
by
in
s
tr
uc
ti
ons
f
r
om
t
he
s
ys
te
m
t
o c
onve
y i
n de
ta
il
a
nd i
n
s
ta
ge
s
.
I
n ge
ne
r
a
l,
t
he
a
ppl
ic
a
ti
on of
e
xpe
r
t
s
ys
te
m
s
i
s
w
id
e
ly
us
e
d i
n t
he
he
a
lt
h s
e
c
to
r
f
or
t
he
di
a
gnos
is
of
a
di
s
e
a
s
e
,
s
uc
h
a
s
th
e
us
e
of
m
ul
ti
p
le
r
ul
e
c
e
r
ta
in
ty
f
a
c
to
r
s
f
or
th
e
di
a
gnos
is
of
in
te
r
na
l
di
s
e
a
s
e
[
13
-
14]
,
E
C
G
di
a
gnos
is
us
in
g
th
e
s
upe
r
vi
s
e
d
le
a
r
ni
ng
a
lg
or
it
hm
s
a
ppr
oa
c
h
[
15
-
17]
,
he
a
r
t
di
a
gnos
is
w
it
h
a
da
ta
m
in
in
g
m
e
th
od
a
ppr
oa
c
h
[
18
-
21]
,
di
a
gnos
is
of
he
a
r
t
di
s
e
a
s
e
w
it
h
th
e
a
ppr
oa
c
h
of
s
t
a
ti
s
ti
c
a
l
a
na
ly
s
ts
[
22]
,
di
a
gnos
is
of
he
a
r
t
di
s
e
a
s
e
u
s
in
g
a
de
c
is
io
n
tr
e
e
a
ppr
oa
c
h
[
23]
,
di
a
gnos
is
of
he
a
r
t
di
s
e
a
s
e
u
s
in
g
th
e
P
e
a
r
s
on
c
or
r
e
la
ti
on
c
oe
f
f
ic
ie
nt
m
e
th
od
[
24]
,
id
e
nt
i
f
y
c
a
r
di
a
c
a
bnor
m
a
li
ti
e
s
ba
s
e
d
on
e
xpe
r
t
s
ys
te
m
s
a
nd
te
le
m
e
di
c
in
e
[
25
-
28]
,
s
in
g
le
le
a
d
E
C
G
c
la
s
s
if
ic
a
ti
on
w
it
h
de
e
p
le
a
r
ni
ng
m
e
th
od
a
ppr
oa
c
h
[
29
-
31]
,
D
e
te
c
ti
ng
he
a
r
t
r
a
te
w
it
h
m
a
c
hi
ne
le
a
r
ni
ng
a
ppr
oa
c
h
[
32
-
36]
,
s
of
twa
r
e
f
or
E
C
G
c
la
s
s
if
i
c
a
ti
on
a
na
ly
s
is
ba
s
e
d
on
f
uz
z
y
c
ogni
ti
ve
m
a
p
[
37
-
38]
,
im
p
r
ove
th
e
di
a
gnos
is
of
he
a
r
t
di
s
e
a
s
e
w
it
h
t
he
P
S
O
e
vol
ut
io
na
r
y
a
lg
or
it
hm
a
ppr
oa
c
h
a
nd
ne
ur
a
l
ne
twor
k
[
39]
,
E
C
G
c
la
s
s
if
ic
a
ti
on
us
e
s
th
e
k
-
ne
a
r
e
s
t
ne
ig
bor
(
K
N
N
)
a
ppr
oa
c
h
[
40]
.
T
hi
s
r
e
s
e
a
r
c
h
ha
s
th
e
a
im
a
nd
m
ot
iv
a
ti
on
to
de
ve
lo
p
a
s
y
s
te
m
or
s
of
twa
r
e
th
a
t
c
a
n
r
e
pl
a
c
e
a
doc
to
r
f
or
th
e
pr
oc
e
s
s
of
id
e
nt
if
yi
ng
he
a
r
t
de
f
e
c
ts
ba
s
e
d
on
a
n
e
xpe
r
t
s
y
s
te
m
w
it
h
th
e
c
e
r
ta
in
ty
f
a
c
to
r
w
i
th
m
ul
ti
pl
e
r
ul
e
m
e
th
od
a
ppr
oa
c
h,
s
o
th
a
t
th
is
s
of
twa
r
e
is
a
bl
e
to
id
e
nt
if
y
he
a
r
t
de
f
e
c
ts
,
a
nd
c
a
n
c
ont
r
ib
ut
e
in
th
e
he
a
lt
h
s
e
c
to
r
in
pa
r
ti
c
ul
a
r
,
s
o
th
a
t
th
is
e
xpe
r
t
s
ys
te
m
pr
ovi
de
s
c
onve
ni
e
nc
e
in
th
e
c
ons
ul
ta
ti
on
pr
oc
e
s
s
be
twe
e
n
doc
to
r
s
(
e
xpe
r
ts
)
a
nd
pa
ti
e
nt
s
.
W
it
h
th
e
e
xpe
r
t
s
ys
te
m
w
il
l
pr
ovi
de
a
s
ol
ut
io
n
to
e
ve
r
y
c
om
pl
a
in
t
o
f
c
om
pl
a
in
ts
f
e
lt
by
pa
ti
e
nt
s
,
s
o
th
a
t
th
e
e
xpe
r
t
s
ys
te
m
is
a
bl
e
to
pr
ovi
de
s
ol
ut
io
ns
to
pr
obl
e
m
s
c
ont
a
in
in
g
u
nc
e
r
ta
in
ty
a
s
f
r
om
th
e
s
ym
pt
om
s
of
a
di
s
e
a
s
e
w
it
h ot
he
r
di
s
e
a
s
e
s
.
M
E
T
H
O
D
E
xpe
r
t
s
ys
te
m
s
E
xpe
r
t
s
ys
te
m
s
is
a
br
a
nc
h
of
s
c
ie
nc
e
th
a
t
a
dopt
s
one
'
s
e
xp
e
r
ti
s
e
in
to
a
n
a
ppl
ic
a
ti
on,
w
h
e
r
e
th
e
in
f
or
m
a
ti
on
pr
ovi
de
d
by
a
n
e
xpe
r
t
r
e
g
a
r
di
ng
knowle
dge
c
a
n
b
e
us
e
d
f
or
th
e
c
on
s
ul
ta
ti
on
pr
oc
e
s
s
.
W
it
h
th
e
e
xi
s
te
nc
e
of
e
xpe
r
t
s
ys
te
m
s
c
a
n
he
lp
or
di
na
r
y
pe
opl
e
to
s
ol
ve
e
xi
s
ti
ng
pr
obl
e
m
s
,
s
o
th
a
t
w
it
h
th
e
e
xpe
r
t
s
ys
te
m
s
c
a
n m
a
ke
de
c
is
io
ns
t
ha
t
a
r
e
us
ua
ll
y
m
a
de
by
a
n e
xpe
r
t,
but
s
ti
ll
c
ons
ul
t
a
n
e
xpe
r
t
[
41]
.
H
e
a
r
t
d
is
e
a
s
e
H
e
a
r
t
di
s
e
a
s
e
is
a
c
ondi
ti
on
w
he
n
th
e
m
a
in
bl
ood
ve
s
s
e
ls
a
r
e
da
m
a
ge
d
w
hi
le
s
uppl
yi
ng
bl
ood
to
th
e
he
a
r
t
(
c
or
ona
r
y
a
r
te
r
ie
s
)
. H
e
a
r
t
a
tt
a
c
k i
s
a
n i
m
pl
ic
a
ti
on o
f
he
a
r
t
di
s
e
a
s
e
, w
hi
le
c
a
r
di
ova
s
c
ul
a
r
i
t
s
e
lf
i
s
a
bl
ood
ve
s
s
e
l
th
a
t
s
uppl
ie
s
bl
ood
to
th
e
he
a
r
t.
H
e
a
r
t
c
ondi
ti
ons
c
a
n
b
e
de
te
r
m
in
e
d
th
r
ough
a
he
a
r
t
te
s
t
th
r
ough
a
n
e
le
c
tr
oc
a
r
di
a
gr
a
m
(
E
K
G
)
to
de
te
r
m
in
e
nor
m
a
l
a
nd
a
bnor
m
a
l
he
a
r
t
c
ondi
ti
ons
[
42]
,
th
e
f
ol
lo
w
in
g
is
a
n
e
xpl
a
na
ti
on of
nor
m
a
l
a
nd a
bnor
m
a
l
he
a
r
t.
N
or
m
a
l
h
e
a
r
t
A
pe
r
s
on'
s
he
a
lt
h
c
ondi
ti
on
to
s
e
e
th
e
h
e
a
lt
h
c
ondi
ti
on
of
th
e
h
e
a
r
t,
by
doi
ng
a
phys
ic
a
l
e
xa
m
in
a
ti
on
of
th
e
he
a
r
t,
a
phys
ic
a
l
e
xa
m
in
a
ti
on
of
th
e
he
a
r
t,
a
C
T
s
c
a
n
of
th
e
he
a
r
t,
a
nd
e
c
hoc
a
r
di
ogr
a
phy.
E
c
hoc
a
r
di
ogr
a
phy
pr
oc
e
s
s
to
d
e
te
r
m
in
e
a
nd
s
e
e
bl
ood
f
lo
w
,
w
h
e
r
e
a
s
w
it
h
th
e
C
T
s
c
a
n
p
r
oc
e
s
s
of
th
e
he
a
r
t
to
f
in
d
out
th
e
a
na
to
m
ic
a
l
c
ondi
ti
on
of
th
e
he
a
r
t,
w
hi
le
nor
m
a
l
h
e
a
r
t
s
ounds
c
a
n
be
he
a
r
d
dur
in
g
th
e
s
te
th
os
c
ope
e
xa
m
in
a
ti
on
pr
oc
e
s
s
,
he
a
r
t
s
ound
s
c
a
n
be
u
s
e
d
a
s
a
m
e
a
s
ur
e
t
o
de
te
r
m
in
e
a
pe
r
s
on'
s
he
a
r
t
he
a
lt
h
c
ondi
ti
on
[
43]
. T
he
ge
ne
r
a
l
pi
c
tu
r
e
of
t
he
nor
m
a
l
s
ig
na
l
pa
tt
e
r
n of
t
he
huma
n he
a
r
t
is
s
how
n i
n F
ig
ur
e
1.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
x
pe
r
t
s
y
s
t
e
m
f
or
he
a
r
t
di
s
e
a
s
e
bas
e
d on
e
le
c
tr
o
c
ar
di
ogr
a
m
da
ta
us
in
g c
e
r
ta
in
ty
f
ac
to
r
w
it
h
... (
Sum
ia
ti
)
45
F
ig
ur
e
1
.
N
or
m
a
l
he
a
r
t
pa
tt
e
r
n
A
bnor
m
a
l
h
e
a
r
t
A
n
ove
r
vi
e
w
of
th
e
a
bnor
m
a
l
s
ig
na
l
pa
tt
e
r
n
of
th
e
hum
a
n
he
a
r
t.
A
or
ti
c
r
e
gur
gi
ta
ti
on
is
r
e
gur
gi
ta
ti
on
of
th
e
a
or
ti
c
va
lv
e
is
th
e
r
e
tu
r
n
of
bl
ood
to
th
e
le
f
t
ve
nt
r
ic
le
f
r
om
th
e
a
or
ta
dur
in
g
di
a
s
to
le
.
A
bnor
m
a
l
he
a
r
tb
e
a
t
th
e
r
hyt
hm
c
a
n
s
ound
ir
r
e
gul
a
r
,
a
nd
s
om
e
ti
m
e
s
th
e
r
e
is
a
n
a
ddi
ti
ona
l
he
a
r
tb
e
a
t
s
ound
or
noi
s
e
out
s
id
e
of
t
he
m
a
in
he
a
r
tb
e
a
t
s
ound, the
p
a
tt
e
r
n i
s
a
s
s
how
n i
n
F
ig
ur
e
2.
F
ig
ur
e
2. A
or
ti
c
r
e
gur
ti
ta
ti
on c
a
r
di
a
c
E
C
G
r
hyt
hm
pa
tt
e
r
n
C
e
r
ta
in
ty
F
a
c
to
r
T
he
c
e
r
ta
in
ty
f
a
c
to
r
(
C
F
)
m
e
th
od i
s
a
m
e
a
s
ur
e
of
c
e
r
ta
in
ty
a
ga
i
ns
t
e
vi
de
nc
e
or
r
ul
e
s
.
T
he
C
F
m
e
th
od
ha
s
th
e
a
dv
a
nt
a
ge
of
m
e
a
s
ur
in
g
de
f
in
it
e
or
unc
e
r
ta
in
ty
in
th
e
di
s
e
a
s
e
di
a
gnos
i
s
pr
oc
e
s
s
.
T
h
e
a
ppl
ic
a
ti
on
of
th
e
C
F
m
e
th
od
to
a
n
e
xpe
r
t
s
y
s
te
m
r
e
qui
r
e
s
s
e
ve
r
a
l
r
ul
e
s
in
th
e
f
or
m
of
va
r
ia
bl
e
s
a
nd
w
e
ig
ht
va
lu
e
s
gi
v
e
n
by
th
e
e
xpe
r
t.
T
he
not
a
ti
on c
e
r
ta
in
ty
f
a
c
to
r
s
a
r
e
e
xpl
a
in
e
d:
[
ℎ
,
]
=
[
ℎ
,
]
−
[
ℎ
,
]
(
1)
T
he
c
onf
id
e
nc
e
pr
opa
g
a
ti
on f
or
a
r
ul
e
w
it
h one
pr
e
m
is
e
i
s
obt
a
i
ne
d by the
f
or
m
ul
a
:
(
ℎ
,
)
=
(
)
∗
(
)
(
2)
T
he
r
e
a
r
e
two
ki
nds
of
li
a
is
on
w
it
h
s
e
ve
r
a
l
pr
e
m
is
e
s
,
na
m
e
ly
r
ul
e
s
w
it
h
c
onj
unc
ti
ons
a
nd
r
ul
e
s
w
it
h
di
s
ju
nc
ti
ons
, t
he
a
ppr
oa
c
he
s
us
e
d a
r
e
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
4
3
-
5
0
46
(
,
1
2
.
.
.
)
=
{
(
)
}
∗
(
)
(
3)
R
ul
e
w
it
h di
s
ju
nc
ti
on, t
he
a
ppr
oa
c
h u
s
e
d i
s
:
(
ℎ
,
1
2
.
.
.
)
=
{
(
)
}
∗
(
)
(
4)
R
ul
e
w
it
h
th
e
s
a
m
e
c
onc
lu
s
io
n,
th
e
r
e
f
or
e
th
e
r
e
m
us
t
be
a
m
e
c
ha
ni
s
m
to
c
om
bi
ne
th
e
s
e
s
e
ve
r
a
l
hypothe
s
e
s
to
be
c
om
e
one
hypothe
s
i
s
onl
y
, a
s
s
how
n i
n (
5.a
-
5c
)
.
(
1
,
2
)
=
1
+
2
(
1
−
1
)
;
1
2
ℎ
(
5.
a
)
(
1
,
2
)
=
1
+
2
(
1
+
1
)
;
1
2
ℎ
(
5.
b
)
(
1
,
2
)
=
1
+
2
(
1
+
1
)
;
1
2
ℎ
(
5.
c
)
I
n t
hi
s
s
tu
dy, we
c
a
r
r
ie
d out t
he
pr
oc
e
s
s
of
c
om
bi
ni
ng s
e
ve
r
a
l
h
ypot
he
s
e
s
, w
hi
le
f
or
a
s
in
gl
e
pr
e
m
is
e
, w
e
us
e
d
a
c
onj
unc
ti
on a
ppr
oa
c
h, t
he
va
lu
e
of
C
F
e
nt
e
r
e
d b
e
twe
e
n 0 a
nd
1.
2.
R
E
S
E
A
R
C
H
M
E
T
H
O
D
T
he
obj
e
c
t
of
r
e
s
e
a
r
c
h
i
s
h
e
a
r
t
de
f
e
c
t
s
(
a
bnor
m
a
l)
a
nd
nor
m
a
l.
L
it
e
r
a
tu
r
e
s
tu
di
e
s
a
r
e
c
a
r
r
ie
d
out
w
it
h
va
r
io
us
a
ppr
oa
c
he
s
w
he
r
e
t
he
knowle
dge
of
a
n e
xpe
r
t
(
e
xpe
r
t)
, e
s
pe
c
ia
ll
y i
n t
he
f
ie
ld
of
t
he
he
a
r
t,
i
s
us
e
d a
s
a
s
our
c
e
of
knowle
dge
,
w
he
r
e
th
e
s
our
c
e
of
ba
s
ic
knowle
dg
e
is
ba
s
e
d
on
th
e
r
e
s
ul
t
s
of
a
c
a
r
di
ol
ogi
s
t'
s
e
xa
m
in
a
ti
on
a
nd
i
s
s
uppor
te
d
by
th
e
r
e
s
ul
ts
of
th
e
e
x
a
m
in
a
ti
on
of
th
e
e
le
c
tr
oc
a
r
di
ogr
a
m
m
e
di
c
a
l
r
e
c
or
d,
w
he
r
e
t
he
r
e
s
ul
t
of
th
e
e
le
c
tr
oc
a
r
di
ogr
a
m
i
s
a
he
a
r
t
r
hyt
hm
r
e
c
o
r
d. T
he
s
ta
ge
s
i
n t
he
de
ve
l
opm
e
nt
t
o di
a
gnos
e
he
a
r
t
de
f
e
c
ts
w
it
h
th
e
c
e
r
ta
in
ty
f
a
c
to
r
a
ppr
oa
c
h
w
it
h
m
ul
ti
pl
e
r
ul
e
s
.
T
hi
s
r
e
s
e
a
r
c
h
c
a
r
r
ie
d
out
s
e
ve
r
a
l
s
ta
ge
s
,
na
m
e
ly
by
c
onduc
ti
ng
a
li
te
r
a
tu
r
e
s
tu
dy,
da
ta
c
ol
le
c
ti
on
f
r
om
e
le
c
tr
oc
a
r
di
ogr
a
m
m
e
di
c
a
l
r
e
c
or
d
da
ta
,
a
nd
in
it
ia
l
c
la
s
s
if
ic
a
ti
on
of
e
le
c
tr
oc
a
r
di
ogr
a
m
m
e
di
c
a
l
r
e
c
or
d
da
ta
.
D
a
ta
a
nd
in
f
or
m
a
ti
on
f
r
om
a
n
e
xpe
r
t
(
he
a
r
t
s
pe
c
ia
li
s
t)
obt
a
in
e
d
a
s
m
a
te
r
ia
l
f
or
knowle
dge
,
w
he
r
e
th
e
da
t
a
in
c
lu
de
s
th
e
va
lu
e
of
th
e
in
te
r
va
l
f
r
om
th
e
r
e
s
ul
ts
of
th
e
e
le
c
tr
oc
a
r
di
ogr
a
m
m
e
di
c
a
l
r
e
c
or
d
a
nd
th
e
ty
p
e
of
he
a
r
t
d
is
or
de
r
(
a
bnor
m
a
l)
a
nd
no
r
m
a
l.
I
nf
or
m
a
ti
on
a
ls
o
in
c
lu
de
s
th
e
C
F
va
lu
e
f
or
e
a
c
h
s
ym
pt
om
ba
s
e
d
on
th
e
le
ve
l
of
c
onf
id
e
nc
e
in
th
e
knowle
dge
a
c
qui
s
it
io
n pr
oc
e
s
s
.
3.
R
E
S
U
L
T
S
A
ND
D
I
S
C
U
S
S
I
O
N
T
he
r
e
pr
e
s
e
nt
a
ti
on
of
knowle
dge
in
th
e
f
or
m
of
r
ul
e
s
r
e
s
ul
t
s
i
n
c
onc
lu
s
io
n
s
in
th
e
f
or
m
of
he
a
r
t
de
f
e
c
ts
(
a
bnor
m
a
l)
a
nd
nor
m
a
l.
B
a
s
e
d
on
th
e
r
e
s
ul
ts
of
knowle
dge
a
c
qui
s
it
io
n,
th
e
r
e
s
ul
ts
of
th
e
de
c
i
s
io
n
tr
e
e
a
r
e
a
s
s
is
t
e
d by
r
a
pi
dm
in
e
r
s
of
twa
r
e
.
A
ppl
ic
a
ti
on de
ve
lo
pe
d by a
s
ys
te
m
t
ha
t
is
a
bl
e
t
o r
e
pl
a
c
e
a
doc
to
r
f
or
t
h
e
id
e
nt
if
ic
a
ti
on
pr
oc
e
s
s
of
he
a
r
t
de
f
e
c
ts
ba
s
e
d
on
a
n
e
xpe
r
t
s
ys
t
e
m
.
E
xpe
r
t
s
ys
te
m
de
ve
lo
pe
d
w
it
h
a
c
e
r
ta
in
ty
f
a
c
to
r
a
ppr
oa
c
h
w
it
h
m
ul
ti
pl
e
r
ul
e
s
.
T
he
s
y
s
te
m
de
s
ig
ne
d
i
s
v
e
r
y
us
e
r
f
r
ie
ndl
y
a
nd
in
te
r
a
c
ti
ve
,
w
he
r
e
u
s
e
r
s
don'
t
ne
e
d
a
ye
s
or
no
a
ns
w
e
r
.
O
n
th
e
c
on
s
ul
ta
ti
on
pa
ge
,
th
e
s
y
m
pt
om
s
th
a
t
a
r
e
f
e
lt
in
c
e
r
ta
in
pa
r
ts
a
pp
e
a
r
on
th
e
s
ys
te
m
,
a
nd
on
th
e
us
e
r
c
ons
ul
ta
ti
on
pa
ge
pr
ovi
de
C
F
va
lu
e
s
a
c
c
or
di
ng
to
c
onf
id
e
nc
e
,
th
e
n
th
e
C
F
va
lu
e
of
th
is
C
F
va
lu
e
is
c
a
lc
ul
a
te
d
w
it
h
th
e
C
F
va
lu
e
in
th
e
kno
w
le
dge
ba
s
e
.
F
ol
lo
w
in
g
a
r
e
th
e
s
ta
g
e
s
of
th
e
pr
oc
e
s
s
e
xpe
r
t
s
ys
t
e
m
f
or
he
a
r
t
di
s
e
a
s
e
ba
s
e
d
on
e
le
c
tr
oc
a
r
di
o
gr
a
m
da
ta
us
in
g
c
e
r
ta
in
ty
f
a
c
to
r
w
it
h
m
u
lt
ip
le
r
ul
e
a
s
s
how
n i
n
F
ig
ur
e
3:
−
S
e
le
c
t
th
e
s
ym
pt
om
s
of
he
a
r
t
f
a
il
ur
e
−
C
a
lc
ul
a
te
t
he
C
F
R
ul
e
−
C
a
lc
ul
a
te
t
he
C
F
va
lu
e
of
e
a
c
h r
ul
e
ba
s
e
us
in
g c
om
bi
ne
d
C
F
A
knowle
dge
b
a
s
e
bui
lt
in
th
e
e
a
r
ly
s
ta
g
e
s
of
r
e
s
e
a
r
c
h
f
or
a
s
ys
te
m
f
or
di
a
gno
s
in
g
a
bnor
m
a
l
a
nd
nor
m
a
l
he
a
r
ts
.
T
a
bl
e
1
s
how
th
e
ty
pe
of
he
a
r
t
di
s
e
a
s
e
.
T
hi
s
in
f
or
m
a
ti
on
is
obt
a
in
e
d
a
s
a
r
e
s
ul
t
of
knowle
dge
a
c
qui
s
it
io
n. T
a
bl
e
1
s
ho
w
s
t
h
e
t
ype
s
of
he
a
r
t
de
f
e
c
t
s
(
a
bnor
m
a
l)
a
nd nor
m
a
l
he
a
r
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
x
pe
r
t
s
y
s
t
e
m
f
or
he
a
r
t
di
s
e
a
s
e
bas
e
d on
e
le
c
tr
o
c
ar
di
ogr
a
m
da
ta
us
in
g c
e
r
ta
in
ty
f
ac
to
r
w
it
h
... (
Sum
ia
ti
)
47
F
ig
ur
e
3. F
lo
w
c
ha
r
t
e
xpe
r
t
s
ys
te
m
c
ons
ul
ti
ng pr
oc
e
s
s
T
a
bl
e
1.
T
ype
of
he
a
r
t
di
s
e
a
s
e
C
ode
T
ype
of
di
s
e
a
s
e
P
01
H
e
a
r
t
de
f
e
c
t
s
(
a
bnor
m
a
l
)
P
02
N
or
m
a
l
H
e
a
r
t
C
onf
id
e
nc
e
le
ve
l
va
lu
e
s
w
it
h
C
F
va
lu
e
s
0
to
1,
th
e
m
or
e
c
onf
id
e
nt
th
e
us
e
r
is
w
it
h
th
e
s
ym
pt
om
s
e
xpe
r
ie
nc
e
d,
th
e
hi
ghe
r
th
e
pe
r
c
e
nt
a
ge
r
e
s
ul
t
va
lu
e
obt
a
in
e
d.
I
n
s
e
le
c
ti
ng
us
e
r
s
ym
pt
om
s
,
it
c
a
n
be
done
r
e
pe
a
te
dl
y
a
c
c
or
di
ng
to
th
e
s
ym
pt
om
s
e
xpe
r
ie
nc
e
d,
if
th
e
us
e
r
f
e
e
ls
c
onf
id
e
nt
a
bout
th
e
s
ym
pt
om
s
e
xpe
r
ie
nc
e
d,
it
is
n
e
c
e
s
s
a
r
y
to
s
e
a
r
c
h
th
r
ough
th
e
in
f
e
r
e
nc
e
p
r
oc
e
s
s
f
or
th
e
s
e
le
c
te
d
C
F
s
ym
pt
om
s
w
it
h
a
c
onf
id
e
nc
e
l
e
ve
l
va
lu
e
w
it
h t
he
C
F
va
lu
e
. F
or
e
xa
m
pl
e
,
us
e
r
c
o
ns
ul
ta
ti
on i
s
:
R
1:
I
F
H
R
≤ 104.5 A
N
D
S
V
1 >
-
0,526 AN
D
Q
R
S
>
84.5
A
N
D
Q
T
≤ 465.5 A
N
D
P
-
R
≤ 167.5
A
N
D
Q
T
C
>
436 AN
D
S
V
1 ≤ 0,595
T
H
E
N
A
B
N
O
R
M
A
L
T
he
i
ni
ti
a
l
r
ul
e
w
hi
c
h ha
s
7 pr
e
m
is
e
s
i
s
br
oke
n down into a r
ul
e
t
ha
t
ha
s
a
s
in
gl
e
pr
e
m
i
s
e
i
nt
o:
R
1.1
:
I
F
H
R
≤ 104.5(
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
R
1.2
:
I
F
S
V
1 >
-
0,526 (
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
R
1.3
:
I
F
Q
R
S
>
84.5 (
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
R
1.4
:I
F
Q
T
≤ 465.5 (
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,
8)
R
1.5
:
I
F
P
-
R
≤ 167.5 (
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
R
1.6
:
I
F
Q
T
C
>
436 (
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
R
1.7
:
I
F
S
V
1 ≤ 0,595 (
C
F
us
e
r
=
0,6)
T
H
E
N
A
B
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
T
he
n t
he
C
F
va
lu
e
i
s
c
a
lc
ul
a
t
e
d by mul
ti
pl
yi
ng t
he
ne
w
r
ul
e
s
C
F
E
xpe
r
t
w
it
h C
F
us
e
r
be
c
om
e
s
:
C
F
R
1.1
=
0,8 * 0,6 =
0,48
I
nput
t
he
s
ym
pt
om
s
of
t
he
he
a
r
t
di
s
or
de
r
s
ym
pt
om
s
S
e
l
e
c
t
t
he
s
ym
pt
om
s
of
he
a
r
t
f
a
i
l
ur
e
O
t
he
r
S
ym
t
om
s
of
he
a
r
t
f
a
i
l
ur
e
?
C
a
l
c
ul
a
t
e
t
he
C
F
R
ul
e
S
t
a
r
t
E
n
d
S
how
S
ym
pt
om
s
of
he
a
r
t
f
a
i
l
ur
e
Y
e
s
No
C
a
l
c
ul
a
t
e
t
he
C
F
va
l
ue
of
e
a
c
h
r
ul
e
ba
s
e
us
i
ng c
om
bi
ne
d C
F
S
how
D
i
a
gnos
i
s
H
e
a
r
t
di
s
e
a
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
4
3
-
5
0
48
C
F
R
1.2
=
0,8 * 0,6 =
0,48
C
F
R
1.3
=
0,8 * 0,6 =
0,48
C
F
R
1.4
=
0,8 * 0,6 =
0,48
C
F
R
1.5
=
0,8 * 0,6 =
0,48
C
F
R
1.6
=
0,8 * 0,6 =
0,48
C
F
R
1.7
=
0,8 * 0,6 =
0,48
C
om
bi
ne
C
F
R
1.1 with C
F
R
1.2 with t
he
f
ol
lo
w
in
g f
or
m
ul
a
CF
c
o
m
b
(
CF
R1
.
1
,
CF
R1
.
2
)
=
CF
R1
.
1
+
CF
R1
.
2
(
1
−
CF
R1
.
1
)
=
0
,
48
+
0
,
48
(
1
−
0
,
48
)
=
0
,
73
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R1
.
3
)
=
CF
o
l
d
+
CF
R1
.
3
(
1
−
CF
o
l
d
)
=
0
,
73
+
0
,
48
(
1
−
0
,
73
)
=
0
,
86
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R1
.
4
)
=
CF
o
l
d
+
CF
R1
.
4
(
1
−
CF
o
l
d
)
=
0
,
86
+
0
,
48
(
1
−
0
,
86
)
=
0
,
93
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R1
.
5
)
=
CF
o
l
d
+
CF
R1
.
5
(
1
−
CF
o
l
d
)
=
0
,
93
+
0
,
48
(
1
−
0
,
93
)
=
0
,
96
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R1
.
6
)
=
CF
o
l
d
+
CF
R1
.
6
(
1
−
CF
o
l
d
)
=
0
,
96
+
0
,
48
(
1
−
0
,
96
)
=
0
,
98
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R1
.
7
)
=
CF
o
ld
+
CF
R1
.
7
(
1
−
CF
o
l
d
)
=
0
,
98
+
0
,
48
(
1
−
0
,
98
)
=
0
,
99
C
onf
id
e
nc
e
pe
r
c
e
nt
a
ge
=
C
F
C
om
bi
ne
* 100%
=
99%
S
ys
te
m
te
s
ti
ng
is
c
a
r
r
ie
d
out
f
r
om
th
e
r
e
s
ul
ts
of
th
e
s
ys
te
m
va
li
di
ty
w
it
h
e
xpe
r
ts
,
s
o
th
a
t
th
e
s
ys
te
m
te
s
t
r
e
s
ul
ts
pr
oduc
e
a
c
e
r
ta
in
ty
f
a
c
to
r
va
lu
e
f
or
a
n a
bnor
m
a
l
he
a
r
t
of
0.99 a
nd a
n a
c
c
ur
a
c
y of
99%
.
R
2:
I
F
H
R
≤
104.5AN
D
S
V
1
>
-
0,526
A
N
D
Q
R
S
>
84.5
A
N
D
Q
T
≤
465.5
A
N
D
P
-
R
≤
167.5
A
N
D
Q
T
C
≤
436 T
H
E
N
N
O
R
M
A
L
T
he
i
ni
ti
a
l
r
ul
e
w
hi
c
h ha
s
6 pr
e
m
is
e
s
i
s
br
oke
n down into a r
ul
e
t
ha
t
ha
s
a
s
in
gl
e
pr
e
m
i
s
e
i
nt
o:
R
2.1:
I
F
H
R
≤ 104.5
(
C
F
us
e
r
=
0,8)
T
H
E
N
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,6)
R
2.2:
I
F
S
V
1 >
-
0,526 (
C
F
us
e
r
=
0,6)
T
H
E
N
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,6)
R
2.3:
I
F
Q
R
S
>
84.5 (
C
F
us
e
r
=
0,6)
T
H
E
N
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,6)
R
2.4:
I
F
Q
T
≤ 465.5 (
C
F
us
e
r
=
0,6)
T
H
E
N
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,6)
R
2.5:
I
F
P
-
R
≤ 167.5 (
C
F
us
e
r
=
0,6)
T
H
E
N
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,6)
R
2.6:
I
F
Q
T
C
≤ 436 (
C
F
us
e
r
=
0,6)
T
H
E
N
N
O
R
M
A
L
(
C
F
E
xpe
r
t
=
0,8)
T
he
n t
he
C
F
va
lu
e
i
s
c
a
lc
ul
a
t
e
d by mul
ti
pl
yi
ng t
he
ne
w
r
ul
e
s
C
F
E
xpe
r
t
w
it
h C
F
us
e
r
B
e
c
om
e
s
:
C
F
R
2.1
=
0,6 * 0,8
=
0,48
C
F
R
2.2
=
0,6 * 0,6 =
0,36
C
F
R
2.3
=
0,6 * 0,6 =
0,36
C
F
R
2.4
=
0,6 * 0,6 =
0,36
C
F
R
2.5
=
0,6 * 0,6 =
0,36
C
F
R
2.6
=
0,8 * 0,6 =
0,48
C
om
bi
ne
C
F
R
2.1 with C
F
R
2.2 with t
he
f
ol
lo
w
in
g f
or
m
ul
a
:
CF
c
o
m
b
(
CF
R2
.
1
,
CF
R2
.
2
)
=
CF
R2
.
1
+
CF
R2
.
2
(
1
−
C
F
2
.
1
)
=
0
,
48
+
0
,
36
(
1
−
0
,
48
)
=
0
,
66
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R2
.
3
)
=
CF
o
l
d
+
CF
R2
.
3
(
1
−
CF
o
l
d
)
=
0
,
66
+
0
,
36
(
1
−
0
,
66
)
=
0
,
78
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R2
.
4
)
=
CF
o
l
d
+
CF
R2
.
4
(
1
−
CF
o
l
d
)
=
0
,
78
+
0
,
36
(
1
−
0
,
76
)
=
0
,
86
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R2
.
5
)
=
CF
o
l
d
+
CF
R2
.
5
(
1
−
CF
o
l
d
)
=
0
,
86
+
0
,
36
(
1
−
0
,
86
)
=
0
,
91
CF
c
o
m
b
(
C
F
o
l
d
,
CF
R2
.
6
)
=
CF
o
l
d
+
CF
R2
.
6
(
1
−
CF
o
l
d
)
=
0
,
91
+
0
,
48
(
1
−
0
,
91
)
=
0
,
95
C
onf
id
e
nc
e
pe
r
c
e
nt
a
ge
=
C
F
C
om
bi
ne
* 100%
=
95%
S
ys
te
m
te
s
ti
ng
is
c
a
r
r
ie
d
out
f
r
om
th
e
r
e
s
ul
ts
of
th
e
s
y
s
te
m
va
l
id
it
y
w
it
h
e
xpe
r
ts
,
s
o
th
a
t
th
e
s
ys
te
m
te
s
t
r
e
s
ul
ts
pr
oduc
e
a
c
e
r
ta
in
ty
f
a
c
to
r
va
lu
e
f
o
r
a
nor
m
a
l
he
a
r
t
of
0.95
a
nd
a
n
a
c
c
ur
a
c
y
le
ve
l
of
95%
.
T
a
bl
e
2
s
how
s
t
he
r
e
s
ul
ts
of
t
he
s
e
a
r
c
h f
or
a
n e
xpe
r
t
s
ys
te
m
w
it
h a
c
om
bi
na
ti
on va
lu
e
of
c
e
r
ta
in
ty
f
a
c
to
r
(
C
F
)
,
s
ys
te
m
te
s
ti
ng
is
c
a
r
r
ie
d
o
ut
f
r
om
th
e
r
e
s
ul
ts
of
s
ys
te
m
va
li
di
ty
w
it
h
e
xpe
r
ts
,
r
e
s
ul
ti
ng
in
th
e
c
e
r
ta
in
ty
f
a
c
to
r
(
C
F
)
va
lu
e
a
nd
th
e
v
a
lu
e
of
nor
m
a
l
a
nd a
bnor
m
a
l
he
a
r
t
a
c
c
ur
a
c
y
le
v
e
ls
is
:
t
hi
s
r
e
s
e
a
r
c
h
is
im
pl
e
m
e
nt
e
d
in
c
a
s
e
s
of
c
a
r
di
a
c
di
s
or
de
r
s
,
but
c
a
n
be
im
pl
e
m
e
nt
e
d
in
ot
he
r
c
a
s
e
s
s
uc
h
a
s
di
a
gnos
e
s
of
ot
he
r
di
s
e
a
s
e
s
.
T
he
r
e
s
e
a
r
c
h
r
e
s
ul
ts
obt
a
in
e
d
a
r
e
in
th
e
f
or
m
of
a
c
onf
id
e
nc
e
le
ve
l
va
lu
e
th
a
t
w
il
l
r
e
s
ul
t
in
de
te
r
m
in
in
g
a
good
f
in
a
l
r
e
s
ul
t,
w
he
r
e
th
e
s
ys
te
m
in
it
s
a
ppl
ic
a
ti
on
is
not
onl
y
to
pr
ovi
de
a
s
in
gl
e
di
a
gnos
is
r
e
s
ul
t,
but
it
c
a
n
pr
oduc
e
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
E
x
pe
r
t
s
y
s
t
e
m
f
or
he
a
r
t
di
s
e
a
s
e
bas
e
d on
e
le
c
tr
o
c
ar
di
ogr
a
m
da
ta
us
in
g c
e
r
ta
in
ty
f
ac
to
r
w
it
h
... (
Sum
ia
ti
)
49
di
a
gnos
is
w
it
h s
ym
pt
om
s
t
ha
t
a
r
e
f
e
lt
i
n a
c
c
or
da
nc
e
w
it
h t
he
c
a
lc
ul
a
ti
on of
t
he
c
om
bi
na
ti
on of
r
ul
e
s
(
m
ul
ti
pl
e
r
ul
e
s
)
.
T
a
bl
e
2. C
F
c
om
bi
na
ti
on va
lu
e
of
e
xp
e
r
t
s
ys
te
m
s
s
e
a
r
c
h r
e
s
ul
ts
H
e
a
r
t
D
i
s
e
a
s
e
C
F
va
l
ue
A
c
c
ur
a
c
y (
%)
N
or
m
a
l
0,95
95%
A
bnor
m
a
l
0,99
99%
4.
C
O
N
C
L
U
S
I
O
N
T
hi
s
s
tu
dy
a
im
s
to
de
ve
lo
p
a
s
ys
te
m
or
s
of
twa
r
e
th
a
t
c
a
n
r
e
pl
a
c
e
a
doc
to
r
f
or
th
e
pr
oc
e
s
s
of
id
e
nt
if
yi
ng
he
a
r
t
de
f
e
c
ts
ba
s
e
d
on
a
n
e
xpe
r
t
s
y
s
te
m
.
E
xpe
r
t
s
ys
te
m
s
d
e
ve
lo
pe
d
w
it
h
a
c
e
r
ta
in
ty
f
a
c
to
r
a
ppr
oa
c
h
w
it
h
m
ul
ti
pl
e
r
ul
e
s
,
w
he
r
e
th
e
pr
oc
e
s
s
of
e
xe
c
ut
in
g
r
ul
e
s
,
s
e
ve
r
a
l
r
ul
e
s
c
a
n
pr
oduc
e
a
hypothe
s
is
.
S
ys
te
m
te
s
ti
ng
is
c
a
r
r
ie
d
out
f
r
om
th
e
r
e
s
ul
ts
of
th
e
s
ys
te
m
va
li
di
ty
w
it
h
e
xpe
r
ts
,
s
o
th
a
t
th
e
s
ys
te
m
te
s
t
r
e
s
ul
ts
pr
oduc
e
t
he
c
e
r
ta
in
ty
f
a
c
to
r
(
C
F
)
va
lu
e
f
or
a
nor
m
a
l
he
a
r
t
of
0.95 a
nd a
n a
c
c
ur
a
c
y l
e
ve
l
of
95%
,
w
hi
le
th
e
c
e
r
ta
in
ty
f
a
c
to
r
(
C
F
)
va
lu
e
f
or
a
n a
bnor
m
a
l
he
a
r
t
is
0.99 a
nd pr
oduc
e
s
a
n a
c
c
ur
a
c
y l
e
ve
l
va
lu
e
99%
.
R
E
F
E
R
E
N
C
E
S
[1]
Triayudi
A,
Fitri
I
,
“
Comparison
of
Parame
ter
-
Free
Agglomerative
Hi
erarchical
Clustering
Methods
,
”
Icic
Expres
s
Letters
,
v
ol. 12,
n
o.
10
, pp. 973
-
980
,
2018
, doi: 10.24507/icicel.12.10.973
.
[2]
Triayudi,
A.
and
Fitri,
I,
“
Alg
Clustering
To
Analyze
The
Behavio
ural
Patterns
Of
Online
Learning
Students
,
”
Journal
of
Theore
tical &
Applied
Inform
ation Te
chnolog
y
,
v
ol
96
,
n
o.
16, pp.5327
-
5337
,
2018
,
ISSN: 19
92
-
8645
.
[3]
Triayudi,
A.
and
Fitri,
I,
“
A
new
a
gglomerative
hierarchical
clu
stering
to
model
student
activity
in
online
learning
,
”
Telkom
nika
,
v
ol.
17
,
n
o.
3,
pp.1226
-
1235
,
2019
, doi: 10.12928/telkomnika.v17i3.9425
.
[4]
Niskanen,
V.A
,
“
Randomize
d
Statistical
System
for
Expert
Diagnosis
of
Vehicle
Damage
in
Wuling
Confero
Cars
Using
the
Certainty
Factor
Method
,
”
JsiI
Jurnal
Sistem
Informa
si
,
v
ol
7,
n
o.1
mar
ch
2020
63
-
64,
2020
,
doi.org/10.30656/jsii.v7i1.2107
.
[5]
Munandar
Tb
Ai,
Suherman,
Sumiati
,
“
The
Use
of
Certainty
Factor
With
Multiple
Rules
for
Diagnosing
Internal
Disease
,
”
Internati
onal
Journal
of
Applicati
on
or
Innovation
in
Eng
ineering
&
Management
(IJAIEM)
,
Volume
1,Issue 1, September 2012
,
ISSN 2319
-
4847
.
[6]
Sugianto
,
Sumiati
,
“
Expert
System
for
Diagnosing
Cancer
in
Children
using
the
Certainty
Factor
Method
,
”
Prosisko
Jurnal
Pengembang
an Riset
dan Obs
ervasi S
istem K
omputer
,
v
ol 3
,
n
o.1
,
2016
[7]
Kristyanto
K,
Sumiati
,
“
Expert
System
for
Diagnosing
Vehicle
Da
mage
on
Wuling
Confero
S
Cars
Using
the
Certainty
Factor
Method
,
”
Jurnal
Sistem I
nformas
i (
JSII
)
,
v
ol. 7
,
n
o.1
,
doi 10.30656/jsii.v7i1
,
2017
.
[8]
Setiabu
di,W,U
.,
Sugihar
ti,
E.,
Arini,
F,
Y
,
“
Expert
System
Diagn
osis
Dental
Disease
Using
Certainty
Factor
Method,
”
Science Journal of Informatics
,
v
ol 4,
n
o,1
,
pp.
43
-
50, 2017
, doi:
10.1088/1742
-
6596/1230/1/012063
.
[9]
Muslim, Much Aziz.
et al
.
,
“
Expert System Diagnosis Ch
ronic Kidney
Disease Based on Mamdani Fuzzy Inference
System
,
”
Journal
of
Theoreti
cal
and
Applied
Informat
ion
Technol
ogy
,
v
ol.
78
,
n
o.
1,
pp.
70
-
75
,
2015
,
doi:
10.15294/sji.v4i1.8463
.
[10]
Aji,
A.H.,
Furqon,
M.T.,
&
Widodo,
A.W
,
“
Expert
System
for
Diagnosing
Diseases
of
Pregnant
Women
Using
the
Certainty
Factor
(CF)
Method
,
”
Jurnal
Pengembangan
Teknologi
Informasi
dan
Ilmu
Komputer
,
v
ol.
10
,
n
o.
2,
pp.
2127
-
2134
,
2018
,
doi:
10.31849/digitalzone.v10i2.2781
.
[11]
Gunawan,
E.P.,
&
Wardoyo,
R
,
“
An
Expert
System
Using
Certainty
Factor
for
Determining
Insomnia
Acupoint
,
”
Indonesian
Journal
Computin
g
Cybernetics
System
(
IJCCS
)
,
v
ol.
12
,
n
o.
2,
pp.
119
,
2018
,
doi
:
10.22146/ijccs.26328
.
[12]
Barbed
a
J.
G.
A.
,
“
Expert
Systems
Applied
to
Plant
Disease
Diagn
osis:
Survey
and
Critical
View
,
”
IEEE
Latin
America Transactions,
v
ol. 14,
n
o
. 4, April 2016
,
doi
: 10.1109/TLA.
2016.7483534
.
[13]
Kirana,
C.,
Pradana,H,A
.,
Sulaiman,
R.,
“
Intestine
Disease
Diagnos
is
System
Using
Certainty
Factor
Method
,
”
Scientific Journal of Informatics
,
v
ol 6,
n
o.
1
, pp.
82
-
94
,
2019
,
DOI: 10.15294/s
ji.v6i1
.
[14]
Astuti,
I.,
&
Sutarno,
H
,
“
The
expert
system
of
children'
s
digestive
tr
act
diseases
diagnostic
using
combination
o
f
forward
chaining
and
certainty
factor
methods
,
”
3rd
Internation
al
Conference
on
Science
in
Information
Techno
logy (
ICSITe
ch)
,
pp. 608
-
612
, IEEE
,
2017
,
doi
: 10.1109/ICSITe
ch.2017.8257
185
.
[15]
Riza,
L.
S.,
Pradini
,
M.,
&
Rahman
,
E.
F
,
“
An
expert
system
for
diagnosis
of
sleep
disorder
using
fuzzy
rule
-
based
classifi
cation
systems
,
”
In
IOP
Conference
Series
,
Materials
Science
and
Engineering
,
v
ol.
185,
no.
1,
IOP
Publishing
,
2017
,
DOI:
10.1088/1757
-
899X/185/1/012011
.
[16]
Terri G. Monk, M.D.,
et al
.
,
“
Predic
tors
of Cog
nitive
Dysfu
nction
afte
r Majo
r Nonc
ardia
c Surg
ery
,
”
Anesthesiolog
,
v
ol. 108,
pp.
18
-
30
,
2008,
https://doi.org/10.1097/01.anes.0000296071.19434.1e
.
[17]
Bélaïd
Bouhemad,
M.D.
,
et
al
.
,
“
Echocardiographic
Doppler
Estimati
on
of
Pulmonary
Artery
Pressure
in
Critically
Ill
Patients
with
Severe
Hypoxemia
,
”
Anesthesiology,
v
ol.
108,
pp.
55
-
62
.
,
January
2008
,
doi:
10.1097/01.anes.0000296067.02462.34
.
[18]
Catherin
e
C.
Price.
,
et
al
.
,
“
Type
and
Severity
of
Cognitive
Decline
in
Older
Adults
after
Noncardiac
Surgery
,
”
Anesthesiology
,
v
ol. 108,
pp.
8
-
17
, 2008,
doi:
10.1097/01.anes
.0000296072.02527.18
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
,
V
ol
.
10
, N
o.
1
,
M
a
r
c
h
20
2
1
:
4
3
-
5
0
50
[19]
Santosh
I. Pate
l, M.
D., F.
R.
C.
A.
,
Michael J. Souter, M.
B., Ch.
B.,
F.
R.
C.
A
.,
David S.
Warner, M.
D.
,
Mark A.
Warner,
M.
D.
,
“
Equipment
-
related
Electrocardiographic
Artifacts:
Causes,
Characteristics,
Consequences,
an
d
Correc
tion
,
”
v
ol. 108,
pp.
138
-
148
, 201
8,
doi:
10.1097/01.anes.0000296537.62905.25
.
[20]
Aziz
A,
and
Rehman
A
U
,
“
Detection
of
Cardiac
Di
sease
usin
g
Data
Mining
Classification
Techniques
,
”
Internati
onal Journ
al of Adva
nced Comput
er Science and
Applicati
ons(IJACS
A)
,
v
ol.
8
,
n
o
.
7
,
pp
.
256
-
259
,
2017
[21]
Raihan
M
.
,
Mondal
S
.
,
More
A
.
,
Boni
P
.
K
.
,
and
Sagor
M
.
O
.
F
.
,
“
Sm
artphone
Based
Heart
Attack
Risk
Prediction
System
with
Statistical
Anal
ysis
and
Data
Mining
Approaches
,
”
Adva
nces
in
Science
Technology
and
Engineerin
g
Systems Journal
,
v
ol.
2
,
n
o 3
,
pp
.
1815
-
1822
,
2017
.
[22]
Munandar
Tb
Ai.,
Sumiati.,
Rosalina,
V.,
“
Cardiova
scular
Disease
Cl
assifica
tion
Based
on
Echocardiography
and
Electrocardiogram
Data
Using
The
Decision
Tree
Classification
Ap
proach
,
”
Journal
Of
Theorical
and
Applied
Informati
on Technol
ogy
,
ISSN: 19
992
-
8645
,
pp.
50
-
59
,
2020.
[23]
Munandar
Tb
Ai.,
Sumiati.,
Rosalina,
V.,
“
Pattern
of
symptom
correl
ation
on
type
of
heart
disease
using
approach
of
pearson
correlation
coefficient
,
”
IOP
Conf.
Series
:
Materials
Science
and
Engineering
830
,
022086
IOP
Publishing
,
doi:10.1088/1757
-
899X/830/2/022086
,
2020.
[24]
Sumiati.,
Kuspria
nto.,
Hasba
llah.,
Sigit,
H
.
,
T
.
,
“
Design
Developm
ent
and
Implementation
Of
Android
base
d
Electrocardiogram
Reader
,
”
Internati
onal
Journal
Of
Advanced
Res
earch
in
Compouter
Science
,
v
ol
.
9,
n
o
.
5
,
doi.10.26483/ijarcs.v915.6285
,
2018.
[25]
Sumiati
et
al
.
,
“
Telemedicine
Systems
for
Electrokardiogram
to
Im
prove
Public
Health
Services
,
”
Internati
onal
Journal
of Co
mputer
Application
, (0975
-
8887)
,
vol.
176
,
n
o.
6
,
2017
.
[26]
Sumiati,
Sigit,H,T
.,
“
Design
of
Android
Application
for
Teleme
dicine
System
to
Improve
Public
Health
,
”
Services.MATEC Web of Conferences 218
, 03005, 2018,
doi:
10.10
51/matecconf/201821803005 ICIEE.
[27]
Steinbe
rg
,
et
al
,
“
2017
ISHNE
-
HRS
expert
consensus
statement
on
ambulatory
ECG
and
external
cardiac
monitoring/tele
metry
,
”
Heart Rhythm
,
doi:
http://dx.doi.org/10.1016/j.hrthm
,
2017.
[28]
Magri
,
et
al
.,
“
QT
spatial
dispersion
and
sudden
cardiac
death
in
hypertrophic
Cardiomyopathy
,
”
Journal
o
f
Cardiology
Time for re
appraisal
,
2017, doi:
doi.org/10.1016/j.jjcc.201
7.01.006 0914
-
5087/_ 2017 Japanese Col
lege
of Cardiology
,
Publishe
d by El
sevier
Ltd. A
ll right
s rese
rved
.
[29]
Mathews
,
et
al
.
,
“
A
novel
applicati
on
of
deep
learnin
g
for
single
-
lead
ECG
classification
,
”
doi:
doi.org/10.1016/j.compbiomed.2018.05.013
,
Publishe
d by El
sevier
Ltd
,
2018
.
[30]
Abdu,
A.
M.,
Mokhjii,
M.
M.
M.,
Sheikh,
U.
U.
U.,
“
Machine
Learning
for
Plant
Disease
Detection
,
”
An
Investigat
ive
Comparison
Between
Support
Vector
Machine
and
Deep
Learning
,
IAES
International
Journal
Of
Artificial Intellegent (IJ
-
AI)
,
v
ol
.
9
,
n
o. 4
,
2020
,
doi
: http://doi.org/10.1
1591/ijai.v9.i4.p
p%25p
.
[31]
Ramacha
ndran,
A.,
Ramesh,
A.,
Sukhlecha
,
A.,
Pandey,
A.,
Karuppi
ah,
A.,
“
Machine
learning
algorithms
for
fall
detection
using
kinematic
and
heart
rate
parameters
-
a
comprehensi
ve
analysis
,
”
IAES
International
Journal
O
f
Artificial Intellegent (IJ
-
AI)
,
v
ol
9
,
n
o. 4
,
2020
,
doi
:
http://doi.org/10.11591/ijai.v9.i4.pp772
-
780
.
[32]
S.
Zhao,
W.
Li,
W.
Niu,
R.
Gravina,
G.
Fortino,
“
Recognitio
n
of
human
fall
events
based
on
single
tri
-
axial
gyroscope,
”
IEEE
15th
International
Conference
on
Networking,
S
ensing
and
Control
(ICNSC)
,
pp.
1
-
6,
doi:
10.1109/ICNSC.2018.8361365
,
2018
.
[33]
A.
Ramachandran,
K.
R.
Anupama,
“
A
Survey
on
Recent
Advances
i
n
Wearable
Fall
Detection
Systems,
”
BioMed
Research International
, doi: 10.1155/2020/2167160
,
2020
.
[34]
Priyan
Malarvizhi
Kumar,
Usha
Devi
Gandhi,
“
A
nove
l
three
-
tier
I
nternet
of
Things
architecture
with
machine
learning
algorithm
for
early
detection
of
heart
diseases
,
”
Computers
and
Electric
al
Enginee
ring
,
v
ol.
65,
pp.
222
-
235, 2018
, http://
dx.doi.org/10.1016/j.compeleceng,2017.09.001
.
[35]
Patel
,
et
al
.,
“
Heart
Disease
Prediction
Usinh
Machine
Learning
and Data
Mining
Technique,
”
Journal
IJCSC
,
v
ol.
7,
n
o. 1, pp. 129
-
137,
doi:
10.090592/IJCSC.2016.018
,
2015
.
[36]
Gonzalo
N´apoles
,
Maikel
Leon
Espinosa
,
Isel
Grau
an
d
Koen
Vanho
of,
“
FCM
Expert:
Software
Tool
for
Scenario
Analysis
and
Pattern
Classification
Based
on
Fuzzy
Cognitive
Maps
,
”
Internati
onal
Journal
on
Artifici
a
l
Intelligen
ce Tools
,
v
ol. 27,
n
o. 7
,
pp.
25, World Scientific
Publishing
Company
,
doi
: 10.1142/S0218213
018600102
,
2018
.
[37]
Gerardo
,F,
Gonzalo
N´apoles
,
Rafae
l
“
A
Review
on
Methods
and
So
ftware
for
Fuzzy
Cognitive
Maps
,
”
Artificial
Intelligen
ce Review
,
2017, doi:
10.1007/s10462
-
017
-
9575
-
1
.
[38]
Feshki
,
et
al
.,
“
Improving
the
Heart
Disease
Diagnosis
by
Evoluti
onary
Algorithm
of
PSO
and
Feed
Forward
Neural Network
,
”
2016
,
doi
: 10.1109/RIOS.20
16.7529489
.
[39]
Fazilud
een
,
et
al
.
,
“
ECG
Beat
Classification
using
Evidential
K
-
Near
est
Neighbour
,
”
Twelfth
Internati
onal
Multi
-
Conferenc
e on In
formation P
rocessin
g
,
2016
,
doi: 10.1016/j.procs.2016.06.106
.
[40]
Hassan
and
Haque,
“
An
expert
system
for
automated
identification
of
obstructive
sleep
apneafrom
single
-
l
ead
ECG
using random under sampling boosting
,
”
Published by Elsevier B.V
,
2017
,
doi.org/10.1016/j.neucom.2016.12.062
.
[41]
J.
M
.,
et al
.,
“
The value
of the 12
-
lead
ECG for
evaluation and optimi
zation of cardiac r
esynchronization
therapy i
n
daily clinical practice
,
”
Journal
of
Electrocardiology 47
Elsevier Inc
.
, 2014,
doi.org/10.1016/j.jelectrocard
.
[42]
Lindow
M
.
D
.,
et
al
.,
“
A
patient
with
non
-
ST
-
segm
ent
elevation
acut
e
coronary
syndrome:
Is
it
possible
to
predict
the culprit c
oronary a
rtery
,
”
doi: 10.1016/
j.jelectro
card
,
2016
.
[43]
Ammar
Al
-
Dallal
,
et
al
.,
“
Predic
tion
of
Non
-
Communicab
le
Disease
s
Using
Class
Comparison
Data
Mining
,
”
Advances
in
Science,
Technology
and
Engineering
Systems
Journal
,
v
ol.
4,
n
o.
5,
193
-
206
,
2019
,
https://dx.doi.org/10.25046/aj040525
.
Evaluation Warning : The document was created with Spire.PDF for Python.