I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
,
p
p
.
2643
~
2
6
5
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
3
.
p
p
2
6
4
3
-
2
6
5
4
2643
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Va
lv
eH
ea
lthN
et:
a
light deep
learn
ing
mo
del f
o
r acc
ura
te
v
a
lv
ula
r heart dis
o
rder detectio
n
Aus
ila
h Alf
ra
iha
t
1
,
Wa
f
a
a
Al
-
Sh
a
ru
2
,
Ali Mo
ha
m
m
a
d Alqud
a
h
3
1
D
e
p
a
r
t
me
n
t
o
f
B
i
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
T
h
e
H
a
s
h
e
mi
t
e
U
n
i
v
e
r
s
i
t
y
,
Za
r
q
a
,
Jo
r
d
a
n
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
T
h
e
H
a
sh
e
m
i
t
e
U
n
i
v
e
r
si
t
y
,
Z
a
r
q
a
,
J
o
r
d
a
n
3
I
n
d
e
p
e
n
d
e
n
t
R
e
se
a
r
c
h
e
r
,
W
i
n
n
i
p
e
g
,
C
a
n
a
d
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
3
,
2
0
2
4
R
ev
is
ed
Feb
1
1
,
2
0
2
6
Acc
ep
ted
Ap
r
2
1
,
2
0
2
6
Va
lv
u
lar
h
e
a
rt
d
ise
a
se
(VH
D)
is
a
si
g
n
if
ica
n
t
g
lo
b
a
l
h
e
a
lt
h
issu
e
,
c
o
n
tri
b
u
ti
n
g
to
i
n
c
re
a
se
d
m
o
rb
id
i
ty
a
n
d
m
o
rtalit
y
ra
tes
,
p
a
rti
c
u
larl
y
in
a
g
in
g
p
o
p
u
lati
o
n
s.
Cu
rre
n
t
d
iag
n
o
stic
m
e
th
o
d
s,
su
c
h
a
s
e
c
h
o
c
a
rd
i
o
g
ra
p
h
y
a
n
d
m
a
n
u
a
l
a
u
sc
u
lt
a
ti
o
n
,
fa
c
e
li
m
it
a
ti
o
n
s
in
a
c
c
e
ss
ib
il
it
y
a
n
d
a
c
c
u
ra
c
y
,
p
a
rti
c
u
larly
i
n
re
so
u
rc
e
-
c
o
n
stra
i
n
e
d
e
n
v
iro
n
m
e
n
ts.
T
h
is
stu
d
y
i
n
tro
d
u
c
e
s
Va
lv
e
He
a
lt
h
Ne
t,
a
li
g
h
twe
ig
h
t
d
e
e
p
lea
rn
i
n
g
m
o
d
e
l
d
e
sig
n
e
d
t
o
c
las
sify
v
a
rio
u
s
VH
Ds
u
si
n
g
h
e
a
rt
so
u
n
d
re
c
o
rd
in
g
s.
Le
v
e
ra
g
in
g
a
d
a
tas
e
t
o
f
o
v
e
r
1
0
,
0
0
0
h
e
a
r
t
s
o
u
n
d
s,
m
i
n
ima
l
p
r
e
p
ro
c
e
ss
in
g
wa
s
a
p
p
li
e
d
b
y
c
o
n
v
e
rti
n
g
t
h
e
a
u
d
io
sig
n
a
ls
i
n
to
p
o
we
r
sp
e
c
tra
b
e
fo
re
fe
e
d
i
n
g
t
h
e
m
in
t
o
a
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
)
c
o
m
b
in
e
d
with
a
b
i
d
irec
ti
o
n
a
l
l
o
n
g
s
h
o
rt
-
term
m
e
m
o
ry
(BiL
S
T
M
)
n
e
two
rk
.
T
h
i
s
m
o
d
e
l
a
c
h
ie
v
e
d
imp
re
ss
iv
e
re
su
lt
s,
wit
h
a
n
a
c
c
u
ra
c
y
o
f
9
8
%
in
trai
n
in
g
a
n
d
tes
ti
n
g
a
n
d
9
8
.
4
%
t
h
ro
u
g
h
1
0
-
f
o
ld
c
ro
ss
-
v
a
li
d
a
ti
o
n
.
Th
is
h
ig
h
ly
e
fficie
n
t
m
o
d
e
l
c
a
n
b
e
u
se
d
i
n
e
m
b
e
d
d
e
d
sy
ste
m
s,
p
ro
v
id
i
n
g
a
c
o
st
-
e
ffe
c
ti
v
e
,
AI
-
d
ri
v
e
n
so
l
u
ti
o
n
fo
r
e
a
rly
d
e
tec
ti
o
n
o
f
VH
D
in
se
tt
in
g
s wh
e
re
a
d
v
a
n
c
e
d
d
iag
n
o
st
ic t
o
o
ls ma
y
b
e
u
n
a
v
a
il
a
b
le.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
Dee
p
lear
n
in
g
E
m
b
ed
d
e
d
h
ea
lth
ca
r
e
s
y
s
tem
s
Hea
r
t so
u
n
d
an
al
y
s
is
Hea
r
t v
alv
e
Hea
r
t v
alv
e
d
is
ea
s
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
:
Ali M
o
h
am
m
ad
A
l
q
u
d
ah
I
n
d
ep
e
n
d
en
t Res
ea
r
ch
er
W
in
n
ip
eg
,
MB R
2
M
3
R
1
,
C
an
ad
a
E
m
ail: a
li_
q
u
d
ah
@
h
o
tm
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Valv
u
lar
h
ea
r
t
d
is
ea
s
e
(
VHD)
r
ep
r
esen
ts
a
s
ig
n
if
ican
t
clin
ical
b
u
r
d
e
n
,
esp
ec
ially
in
ag
in
g
p
o
p
u
latio
n
s
wh
er
e
th
e
in
cid
e
n
ce
co
n
tin
u
es
to
r
is
e.
C
u
r
r
e
n
t
ly
,
ap
p
r
o
x
im
ately
1
3
.
3
%
o
f
o
ld
er
in
d
iv
i
d
u
als
ar
e
af
f
ec
ted
b
y
VHD,
an
d
p
r
o
jectio
n
s
in
d
icate
th
at
d
ea
th
r
ates
attr
ib
u
tab
le
to
VHD
m
ay
d
o
u
b
le
in
th
e
co
m
i
n
g
2
5
y
ea
r
s
[
1
]
,
[
2
]
.
Fre
q
u
e
n
tly
,
VHD
r
em
ain
s
u
n
d
iag
n
o
s
ed
u
n
til
s
ev
er
e
co
m
p
licatio
n
s
,
s
u
ch
as
h
ea
r
t
f
ailu
r
e,
lead
in
g
to
wo
r
s
en
ed
p
atien
t
o
u
tco
m
es
d
u
e
to
th
e
d
is
ea
s
e'
s
ty
p
ically
asy
m
p
to
m
atic
p
r
o
g
r
ess
io
n
[
3
]
,
[
4
]
.
As
VHD
s
ev
er
ity
in
cr
ea
s
es,
h
ea
lth
ca
r
e
co
s
ts
r
is
e
ac
co
r
d
in
g
ly
,
u
n
d
e
r
s
co
r
in
g
th
e
n
ee
d
f
o
r
e
ar
ly
d
etec
tio
n
an
d
tim
ely
in
ter
v
en
tio
n
to
b
o
th
im
p
r
o
v
e
p
atien
t
p
r
o
g
n
o
s
is
an
d
al
lev
iate
f
in
an
cial
s
tr
ain
o
n
h
ea
l
th
ca
r
e
s
y
s
tem
s
[
5
]
.
Desp
ite
th
ese
p
r
ess
in
g
co
n
ce
r
n
s
,
d
elay
s
in
d
iag
n
o
s
is
ar
e
co
m
m
o
n
,
o
f
ten
attr
ib
u
ted
to
in
a
d
eq
u
ate
clin
ician
u
s
e
o
f
o
r
p
r
o
f
icien
cy
in
au
s
cu
ltatio
n
[
6
]
,
[
7
]
.
E
v
en
a
m
o
n
g
tr
ain
e
d
m
ed
ica
l
p
r
o
f
ess
io
n
als,
th
e
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
o
f
id
en
tif
y
in
g
h
ea
r
t
m
u
r
m
u
r
s
r
em
ain
s
u
b
o
p
tim
al,
r
an
g
in
g
f
r
o
m
3
5
%
t
o
6
9
%
[
6
]
,
[
7
]
.
T
h
e
o
v
er
all
in
cid
e
n
ce
o
f
VHD
h
as
s
u
r
g
ed
b
y
4
5
%
in
th
e
p
ast
3
0
y
ea
r
s
,
w
ith
an
esti
m
ated
4
0
1
n
ew
ca
s
es
p
er
1
0
0
,
0
0
0
p
e
o
p
le
an
n
u
ally
[
8
]
.
Alth
o
u
g
h
ec
h
o
ca
r
d
io
g
r
ap
h
y
h
as
b
ec
o
m
e
th
e
g
o
l
d
s
tan
d
ar
d
f
o
r
n
o
n
-
in
v
asiv
e
d
iag
n
o
s
is
o
f
VHD,
m
o
r
e
th
an
s
ev
en
m
illi
o
n
ec
h
o
ca
r
d
io
g
r
am
s
ar
e
p
er
f
o
r
m
ed
an
n
u
ally
in
No
r
th
Am
er
ic
a,
y
et
m
an
y
ca
s
es
s
till
g
o
u
n
d
etec
ted
[
9
]
–
[
1
1
]
.
E
x
p
an
d
i
n
g
ec
h
o
ca
r
d
io
g
r
ap
h
ic
s
cr
ee
n
in
g
to
en
co
m
p
ass
all
at
-
r
is
k
p
o
p
u
latio
n
s
is
im
p
r
ac
tical
g
iv
en
cu
r
r
en
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
6
4
3
-
2
6
5
4
2644
clin
ical
r
eso
u
r
ce
s
an
d
f
in
a
n
cial
co
n
s
tr
ain
ts
[
1
2
]
.
Fu
r
t
h
er
m
o
r
e,
h
an
d
h
eld
u
ltra
s
o
u
n
d
d
e
v
ices,
wh
ile
p
r
o
m
is
in
g
,
s
till
d
ep
en
d
h
ea
v
ily
o
n
th
e
o
p
e
r
ato
r
’
s
s
k
ill,
th
er
eb
y
in
tr
o
d
u
ci
n
g
v
ar
ia
b
ilit
y
in
d
iag
n
o
s
tic
ac
cu
r
ac
y
[
1
3
]
.
I
n
r
ec
en
t
y
ea
r
s
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
-
e
n
h
an
ce
d
au
s
cu
ltatio
n
h
as
em
er
g
ed
as
a
v
ia
b
le
ap
p
r
o
ac
h
to
ad
d
r
ess
in
g
g
a
p
s
in
clin
icia
n
ex
p
er
tis
e
[
1
4
]
,
[
1
5
]
.
Pre
v
io
u
s
r
esear
ch
h
as
d
em
o
n
s
tr
ated
th
at
AI
alg
o
r
ith
m
s
ca
n
d
is
tin
g
u
is
h
n
o
r
m
al
f
r
o
m
ab
n
o
r
m
al
h
ea
r
t
s
o
u
n
d
s
wit
h
s
en
s
itiv
ities
b
etwe
en
7
8
.
5
%
an
d
8
8
.
5
%
a
n
d
s
p
ec
if
icities
r
an
g
in
g
f
r
o
m
8
1
.
5
%
to
9
8
.
3
3
%
[
8
]
–
[
1
0
]
.
Ho
wev
er
,
ex
is
tin
g
AI
-
d
r
iv
e
n
s
y
s
tem
s
h
av
e
b
ee
n
lar
g
el
y
lim
ited
to
d
if
f
er
e
n
tiatin
g
n
o
r
m
al
f
r
o
m
a
b
n
o
r
m
al
s
o
u
n
d
s
w
ith
o
u
t
p
r
o
v
i
d
in
g
a
d
iag
n
o
s
is
o
f
s
p
ec
if
ic
v
alv
u
lar
co
n
d
itio
n
s
.
M
o
r
eo
v
er
,
s
tu
d
ies
p
r
im
ar
ily
r
ely
o
n
p
r
o
ce
s
s
ed
h
ea
r
t
s
o
u
n
d
s
ig
n
als
o
r
p
h
o
n
o
ca
r
d
io
g
r
a
m
(
PC
G)
d
ata
r
ath
er
th
an
r
aw
h
ea
r
t
s
o
u
n
d
s
o
b
tain
e
d
in
clin
ical
s
ettin
g
s
,
wh
ich
d
im
in
is
h
es
th
eir
ap
p
licab
ilit
y
in
r
ea
l
-
wo
r
ld
clin
ical
p
r
ac
tice
[
1
6
]
.
B
ar
u
a
et
a
l
.
[
1
7
]
p
r
o
p
o
s
ed
a
h
an
d
c
r
af
ted
lea
r
n
in
g
m
o
d
e
l
f
o
r
VHD
d
etec
tio
n
th
at
in
teg
r
ates
a
m
u
ltil
ev
el
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
b
ased
o
n
t
h
e
d
u
al
s
y
m
m
etr
ic
tr
ee
p
atter
n
(
DSTP)
an
d
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
DW
T
)
.
T
h
e
DSTP
o
p
er
ates
as
a
tex
tu
r
al
f
ea
t
u
r
e
ex
t
r
ac
to
r
,
s
im
ilar
to
t
h
e
lo
ca
l
b
in
ar
y
p
atter
n
(
L
B
P),
b
y
ca
p
t
u
r
in
g
lo
w
-
lev
el
tex
tu
r
al
f
ea
t
u
r
es.
T
o
ex
ten
d
it
s
ca
p
ab
ilit
y
,
th
e
m
o
d
el
a
p
p
lies
DW
T
to
g
en
er
ate
s
u
b
b
an
d
s
o
f
h
ea
r
t
s
o
u
n
d
s
ig
n
als,
an
d
DSTP
is
r
ep
ea
te
d
ly
ap
p
lied
ac
r
o
s
s
th
ese
s
u
b
b
an
d
s
to
cr
ea
te
a
m
u
ltil
ev
eled
f
ea
tu
r
e
v
ec
to
r
.
T
h
is
ap
p
r
o
ac
h
allo
wed
f
o
r
c
ap
tu
r
in
g
m
o
r
e
co
m
p
lex
r
ep
r
e
s
en
tatio
n
s
o
f
h
ea
r
t
s
o
u
n
d
d
ata,
b
u
t
it
also
h
ig
h
li
g
h
ts
a
lim
itatio
n
,
as
h
an
d
cr
af
te
d
f
ea
tu
r
es
m
a
y
n
o
t
b
e
as
e
f
f
ec
tiv
e
o
r
a
d
ap
tab
le
as
lear
n
ed
f
ea
tu
r
es in
d
ee
p
lear
n
i
n
g
m
o
d
els.
J
ian
g
et
a
l.
[
1
8
]
r
ec
en
tly
a
d
d
r
ess
ed
s
o
m
e
o
f
th
e
lim
itatio
n
s
b
y
d
ev
el
o
p
in
g
a
d
ee
p
lear
n
in
g
m
o
d
el
tr
ain
ed
o
n
r
aw
h
ea
r
t
s
o
u
n
d
d
ata.
T
h
eir
m
o
d
el
ac
h
ie
v
ed
p
r
o
m
is
in
g
s
en
s
itiv
ity
a
n
d
s
p
ec
if
icity
r
ates
f
o
r
d
etec
tin
g
v
ar
io
u
s
VHD
p
h
en
o
t
y
p
es,
r
an
g
i
n
g
f
r
o
m
7
1
.
4
% to
1
0
0
% a
n
d
8
3
.
5
% to
1
0
0
%,
r
esp
ec
tiv
ely
[
1
8
]
.
T
h
is
ad
v
an
ce
m
e
n
t
m
ar
k
s
an
im
p
o
r
tan
t
s
tep
f
o
r
war
d
,
as
th
e
m
o
d
el
o
p
er
ates
d
ir
ec
tly
o
n
r
aw
cl
in
ical
h
ea
r
t
s
o
u
n
d
d
ata,
r
em
o
v
in
g
t
h
e
n
ee
d
f
o
r
l
ab
o
r
io
u
s
p
r
ep
r
o
ce
s
s
in
g
.
Ho
w
ev
er
,
d
esp
ite
th
ese
im
p
r
o
v
e
m
en
ts
,
J
ian
g
’
s
m
o
d
el
ex
h
ib
ited
r
ed
u
ce
d
s
en
s
itiv
ity
in
d
etec
tin
g
m
ix
ed
v
alv
u
lar
d
is
ea
s
es
an
d
ao
r
tic
v
alv
e
lesi
o
n
s
[
1
8
]
.
Fu
r
t
h
er
m
o
r
e,
th
e
m
o
d
el’
s
g
e
n
er
aliza
b
ilit
y
r
em
ain
s
a
ch
allen
g
e,
as
it
was
p
r
im
ar
ily
v
alid
ated
with
in
in
p
atien
t
s
ettin
g
s
,
n
ec
ess
itatin
g
b
r
o
ad
e
r
v
alid
a
tio
n
ac
r
o
s
s
d
i
v
er
s
e
clin
ical
p
o
p
u
latio
n
s
.
T
h
e
d
etec
tio
n
o
f
ao
r
tic
v
alv
e
ab
n
o
r
m
alities
co
n
tin
u
es
to
p
o
s
e
d
if
f
icu
lties
,
with
lo
wer
s
en
s
itiv
ity
o
b
s
er
v
ed
in
th
ese
ca
s
es,
in
d
icatin
g
th
e
n
ee
d
f
o
r
f
u
r
th
er
r
ef
in
em
en
t
o
f
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es to
f
u
lly
ad
d
r
ess
th
e
co
m
p
lex
ity
o
f
VHD
p
h
en
o
ty
p
es.
T
h
is
s
tu
d
y
b
u
ilt
u
p
o
n
th
is
f
o
u
n
d
atio
n
b
y
d
ev
el
o
p
in
g
a
lig
h
tweig
h
t,
h
ig
h
ly
ac
c
u
r
ate
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
s
o
u
n
d
class
if
icatio
n
th
at
lev
er
ag
es a
lar
g
e
d
ataset
o
f
1
0
,
3
6
6
h
ea
r
t so
u
n
d
s
,
co
llected
u
s
in
g
elec
tr
o
n
ic
s
teth
o
s
co
p
es.
B
y
m
in
im
izin
g
p
r
ep
r
o
ce
s
s
in
g
an
d
co
n
v
er
tin
g
h
ea
r
t
s
o
u
n
d
s
in
t
o
p
o
w
er
s
p
ec
tr
a,
a
lig
h
t
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
was
ap
p
lied
to
e
x
tr
a
ct
an
d
s
elec
t
m
u
ltil
ev
el
f
ea
tu
r
es.
T
h
is
ap
p
r
o
ac
h
y
ield
ed
a
h
i
g
h
ly
e
f
f
icien
t
m
o
d
el,
ac
h
iev
in
g
9
8
%
ac
c
u
r
ac
y
in
b
o
th
tr
ai
n
in
g
a
n
d
test
in
g
p
h
ases
,
with
a
9
8
.
4
%
ac
cu
r
ac
y
u
p
o
n
1
0
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
.
2.
M
E
T
H
O
D
All
ex
p
er
im
en
ts
p
r
esen
ted
in
th
is
wo
r
k
wer
e
d
esig
n
ed
an
d
ex
ec
u
ted
to
d
ev
elo
p
,
tr
ain
,
an
d
ev
alu
ate
th
e
p
r
o
p
o
s
ed
C
NN
–
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
B
iLST
M
)
m
o
d
el
f
o
r
VHD
c
lass
if
icatio
n
u
s
in
g
p
o
wer
s
p
ec
tr
al
r
ep
r
esen
tatio
n
s
o
f
h
ea
r
t
s
o
u
n
d
s
ig
n
als.
T
h
e
en
tire
ex
p
er
im
e
n
tal
p
ip
elin
e,
in
clu
d
in
g
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
im
p
lem
en
tatio
n
,
tr
ain
in
g
,
an
d
v
alid
a
tio
n
,
was
ca
r
r
ied
o
u
t
u
s
in
g
MA
T
L
AB
R
2
0
2
4
b
(
Ma
th
W
o
r
k
s
,
Natick
,
MA
,
an
d
USA)
.
C
o
m
p
u
tatio
n
al
ac
ce
ler
atio
n
was
ac
h
iev
ed
u
s
in
g
an
NVI
DI
A
GeFo
r
ce
GT
X
1
6
5
0
g
r
ap
h
ics
p
r
o
ce
s
s
in
g
u
n
it
(
GPU
)
with
4
GB
o
f
d
ed
icate
d
m
e
m
o
r
y
,
an
d
all
ex
p
er
im
en
ts
wer
e
p
er
f
o
r
m
ed
o
n
a
s
y
s
tem
eq
u
ip
p
ed
with
3
2
GB
o
f
R
AM
.
T
h
is
s
etu
p
en
s
u
r
ed
ef
f
icien
t
m
o
d
el
tr
ain
in
g
wh
ile
r
ef
lectin
g
a
p
r
ac
tical
an
d
r
e
p
r
o
d
u
cib
le
r
esear
ch
e
n
v
ir
o
n
m
en
t
s
u
itab
le
f
o
r
d
e
p
lo
y
m
e
n
t
-
o
r
ien
t
ed
s
tu
d
ies.
2
.
1
.
Da
t
a
s
et
T
h
e
h
ea
r
t
s
o
u
n
d
d
ataset
[
1
7
]
was
p
r
o
s
p
ec
tiv
ely
co
llected
f
r
o
m
p
atien
ts
atten
d
in
g
th
e
C
ar
d
io
lo
g
y
Dep
ar
tm
en
t
at
Fira
t
Un
iv
er
s
it
y
Ho
s
p
ital,
with
ap
p
r
o
v
al
f
r
o
m
th
e
n
o
n
-
in
ter
v
e
n
tio
n
al
r
esear
ch
eth
ics
b
o
ar
d
.
I
t
in
clu
d
es
1
0
,
3
6
6
h
ea
r
t
s
o
u
n
d
r
ec
o
r
d
in
g
s
f
r
o
m
6
5
1
s
u
b
jects,
d
iv
id
ed
in
to
n
in
e
VHD
class
es
an
d
o
n
e
h
ea
lth
y
class
(
T
ab
le
1
)
.
E
ac
h
s
o
u
n
d
was
ca
p
tu
r
ed
at
a
f
i
x
ed
d
u
r
ati
o
n
o
f
2
s
ec
o
n
d
s
u
s
in
g
th
e
L
ittma
n
n
3
,
2
0
0
d
ig
ital
s
teth
o
s
co
p
e
at
a
s
am
p
lin
g
f
r
e
q
u
en
cy
o
f
8
k
Hz.
T
h
e
d
iag
n
o
s
tic
clas
s
f
o
r
ea
ch
s
u
b
ject
was
co
n
f
ir
m
e
d
th
r
o
u
g
h
p
r
io
r
ec
h
o
ca
r
d
i
o
g
r
a
p
h
y
.
T
h
is
d
ataset
is
p
u
b
licly
av
ailab
le
an
d
ca
n
b
e
ac
ce
s
s
ed
[
1
7
]
.
2
.
2
.
Da
t
a
prepro
ce
s
s
ing
a
nd
po
wer
s
pect
rum
a
na
ly
s
is
T
h
e
PC
G
s
ig
n
als
wer
e
tr
an
s
f
o
r
m
ed
in
t
o
th
e
f
r
e
q
u
en
c
y
d
o
m
ain
u
s
in
g
a
welc
h
-
b
ased
p
o
wer
s
p
ec
tr
al
de
n
s
ity
(
PS
D)
esti
m
atio
n
,
w
h
ich
is
ap
p
r
o
p
r
iate
g
iv
e
n
th
e
q
u
asi
-
s
tatio
n
ar
y
ch
ar
ac
ter
is
tics
o
f
h
ea
r
t
s
o
u
n
d
s
ig
n
als.
As
im
p
lem
en
ted
in
t
h
e
co
d
e,
th
e
s
ig
n
als
wer
e
s
am
p
led
at
8
k
Hz
an
d
s
eg
m
en
t
ed
u
s
in
g
a
Ham
m
in
g
win
d
o
w
o
f
1
,
0
2
4
s
am
p
les
with
5
0
%
o
v
er
lap
.
Fo
r
ea
c
h
s
eg
m
en
t,
th
e
p
er
io
d
o
g
r
am
was
co
m
p
u
ted
v
ia
th
e
f
ast
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
V
a
lveH
ea
lth
N
et:
a
lig
h
t d
ee
p
l
ea
r
n
in
g
mo
d
el
f
o
r
a
cc
u
r
a
te
va
lvu
la
r
h
ea
r
t d
is
o
r
d
er
…
(
A
u
s
ila
h
A
lfr
a
ih
a
t
)
2645
Fo
u
r
ier
tr
an
s
f
o
r
m
(
FF
T
)
,
an
d
th
e
r
esu
ltin
g
p
o
wer
s
p
ec
tr
a
wer
e
av
er
a
g
ed
ac
r
o
s
s
s
eg
m
en
ts
to
o
b
tai
n
a
r
o
b
u
s
t
PS
D
esti
m
ate
f
o
r
ea
ch
r
ec
o
r
d
i
n
g
.
Fo
llo
win
g
PS
D
esti
m
atio
n
,
o
n
ly
th
e
f
ir
s
t
2
0
0
f
r
eq
u
e
n
cy
b
in
s
wer
e
r
etain
ed
,
co
r
r
esp
o
n
d
in
g
to
th
e
lo
w
-
f
r
eq
u
e
n
cy
b
an
d
(
0
–
2
0
0
Hz)
th
at
c
o
n
tain
s
th
e
m
o
s
t
d
iag
n
o
s
tically
r
elev
a
n
t
h
ea
r
t
s
o
u
n
d
c
o
m
p
o
n
en
ts
,
in
clu
d
in
g
S1
,
S2
,
an
d
p
ath
o
l
o
g
ical
m
u
r
m
u
r
s
.
T
h
is
f
r
e
q
u
e
n
cy
r
an
g
e
h
as
b
ee
n
s
h
o
wn
t
o
ca
p
tu
r
e
clin
ically
m
ea
n
in
g
f
u
l
s
p
ec
tr
al
d
if
f
er
en
c
es
in
PC
G
s
ig
n
als
with
h
ig
h
co
n
f
id
en
ce
[
1
9
]
,
[
2
0
]
.
E
ac
h
r
esu
ltin
g
PS
D
v
ec
to
r
was
th
en
f
o
r
m
atted
as
a
s
eq
u
en
ce
in
p
u
t
o
f
2
0
0
an
d
u
s
e
d
d
ir
ec
tly
f
o
r
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
in
g
,
r
ef
lectin
g
a
m
in
im
al
a
n
d
c
o
m
p
u
tatio
n
ally
ef
f
icien
t
p
r
ep
r
o
ce
s
s
in
g
p
ip
elin
e.
R
eg
ar
d
in
g
class
im
b
alan
ce
,
th
e
d
ataset
u
s
ed
in
th
is
s
tu
d
y
ex
h
ib
ited
a
r
elativ
ely
b
alan
ce
d
d
is
tr
ib
u
tio
n
ac
r
o
s
s
d
iag
n
o
s
tic
class
es,
an
d
th
er
ef
o
r
e
n
o
e
x
p
licit
im
b
alan
ce
co
r
r
ec
tio
n
tec
h
n
iq
u
es
(
s
u
c
h
as
class
-
weig
h
ted
lo
s
s
f
u
n
ctio
n
s
o
r
d
ata
r
esam
p
l
in
g
)
wer
e
ap
p
lied
d
u
r
in
g
t
r
ain
in
g
.
Nev
er
th
eless
,
th
e
m
o
d
el
was
ev
alu
ated
u
s
in
g
s
ep
ar
ate
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
s
ets
to
en
s
u
r
e
u
n
b
iased
p
er
f
o
r
m
an
ce
esti
m
atio
n
.
W
h
ile
th
is
wo
r
k
f
o
cu
s
es
o
n
b
alan
ce
d
d
ata
to
e
s
tab
lis
h
b
aselin
e
p
er
f
o
r
m
an
ce
,
f
u
tu
r
e
s
tu
d
ies
will
in
v
esti
g
ate
th
e
r
o
b
u
s
tn
ess
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
u
n
d
e
r
clin
ically
r
ea
lis
tic
im
b
alan
ce
d
co
n
d
itio
n
s
,
in
clu
d
in
g
th
e
u
s
e
o
f
weig
h
ted
lo
s
s
f
u
n
ctio
n
s
an
d
o
v
er
s
am
p
lin
g
s
t
r
ateg
ies to
m
itig
ate
class
d
o
m
in
an
ce
an
d
en
h
a
n
ce
g
e
n
er
aliza
b
ilit
y
.
T
ab
le
1
.
Dis
tr
ib
u
tio
n
o
f
s
u
b
jec
ts
an
d
h
ea
r
t so
u
n
d
s
b
y
d
iag
n
o
s
tic
class
C
l
a
s
s
N
u
mb
e
r
o
f
su
b
j
e
c
t
s
N
u
mb
e
r
o
f
so
u
n
d
s
P
e
r
c
e
n
t
a
g
e
o
f
t
o
t
a
l
h
e
a
r
t
so
u
n
d
s
(
%)
S
e
v
e
r
e
a
o
r
t
i
c
st
e
n
o
si
s
23
9
9
9
9
.
6
M
i
l
d
a
o
r
t
i
c
s
t
e
n
o
si
s
54
7
3
8
7
.
1
M
i
l
d
mi
t
r
a
l
st
e
n
o
s
i
s
45
6
5
6
6
.
3
M
o
d
e
r
a
t
e
mi
t
r
a
l
s
t
e
n
o
s
i
s
69
1
0
3
5
1
0
.
0
S
e
v
e
r
e
m
i
t
r
a
l
r
e
g
u
r
g
i
t
a
t
i
o
n
90
1
3
3
8
1
2
.
9
M
i
l
d
mi
t
r
a
l
r
e
g
u
r
g
i
t
a
t
i
o
n
72
1
0
7
7
1
0
.
4
M
o
d
e
r
a
t
e
mi
t
r
a
l
r
e
g
u
r
g
i
t
a
t
i
o
n
54
7
9
2
7
.
6
S
e
v
e
r
e
t
r
i
c
u
sp
i
d
72
1
0
7
7
1
0
.
4
M
o
d
e
r
a
t
e
t
r
i
c
u
sp
i
d
72
1
0
8
0
1
0
.
4
H
e
a
l
t
h
y
s
u
b
j
e
c
t
s
1
0
8
1
6
1
4
1
5
.
6
2
.
3
.
M
o
del a
rc
hite
ct
ure
a
nd
hy
perpa
ra
m
et
er
s
et
t
ing
s
T
h
e
p
r
o
p
o
s
ed
n
etwo
r
k
f
o
ll
o
ws
a
C
NN
–
B
iLST
M
ar
ch
ite
ctu
r
e
im
p
lem
en
ted
u
s
in
g
M
AT
L
AB
’
s
lay
er
Gr
ap
h
f
r
a
m
ewo
r
k
.
T
h
e
in
p
u
t
to
th
e
m
o
d
el
is
a
s
eq
u
en
ce
in
p
u
t
lay
er
o
f
s
ize
2
0
0
/
tim
es1
,
co
r
r
esp
o
n
d
in
g
to
th
e
p
o
wer
s
p
ec
tr
al
r
ep
r
esen
ta
tio
n
o
f
ea
ch
h
ea
r
t
s
o
u
n
d
s
eg
m
en
t.
A
s
eq
u
en
ce
f
o
ld
in
g
lay
er
is
em
p
lo
y
ed
to
en
ab
le
co
n
v
o
lu
tio
n
al
p
r
o
ce
s
s
in
g
o
f
s
eq
u
en
tial
d
ata.
T
h
e
co
n
v
o
lu
tio
n
al
b
ac
k
b
o
n
e
co
n
s
is
ts
o
f
f
o
u
r
two
-
d
im
en
s
io
n
al
co
n
v
o
lu
tio
n
al
lay
er
s
with
k
er
n
el
s
izes
o
f
3
/
tim
es1
an
d
f
ilter
d
ep
t
h
s
o
f
4
8
,
3
2
,
1
6
,
an
d
3
2
,
r
esp
ec
tiv
ely
.
E
ac
h
co
n
v
o
lu
tio
n
al
lay
er
is
f
o
llo
wed
b
y
b
atc
h
n
o
r
m
aliza
tio
n
an
d
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
to
s
tab
ilize
tr
ain
in
g
an
d
in
tr
o
d
u
ce
n
o
n
lin
ea
r
ity
.
T
h
r
ee
m
ax
-
p
o
o
lin
g
la
y
er
s
with
a
p
o
o
l
s
ize
o
f
2
an
d
a
s
tr
id
e
o
f
2
ar
e
u
s
ed
to
p
r
o
g
r
ess
iv
ely
r
ed
u
ce
th
e
tem
p
o
r
al
r
eso
lu
tio
n
an
d
e
x
tr
ac
t
h
ier
ar
ch
ical
f
ea
tu
r
es.
Af
te
r
co
n
v
o
l
u
tio
n
al
f
ea
tu
r
e
ex
tr
ac
ti
o
n
,
a
s
eq
u
en
ce
u
n
f
o
ld
in
g
lay
er
r
esto
r
es
th
e
tem
p
o
r
al
s
tr
u
c
tu
r
e,
f
o
llo
we
d
b
y
a
f
latten
lay
er
[
2
1
]
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
Valv
eHe
a
lth
Net
ar
ch
itectu
r
e,
wh
ich
i
n
teg
r
ates
C
NNs
with
a
B
iLST
M
lay
er
f
o
r
h
ea
r
t
s
o
u
n
d
class
if
icatio
n
.
Po
wer
s
p
e
ctr
al
f
ea
tu
r
es
ar
e
f
ir
s
t
p
r
o
ce
s
s
ed
th
r
o
u
g
h
m
u
ltip
le
co
n
v
o
l
u
tio
n
al
b
l
o
ck
s
co
n
s
is
ti
n
g
o
f
co
n
v
o
l
u
tio
n
,
b
atch
n
o
r
m
aliza
tio
n
,
R
eL
U
ac
tiv
atio
n
,
an
d
m
ax
-
p
o
o
lin
g
lay
er
s
to
ex
tr
ac
t
h
ier
ar
ch
ical
s
p
ec
tr
al
r
ep
r
esen
tatio
n
s
.
T
h
e
s
eq
u
en
ce
f
o
ld
in
g
an
d
u
n
f
o
ld
in
g
lay
er
s
en
ab
le
C
NN
-
b
ased
p
r
o
ce
s
s
in
g
o
f
s
eq
u
en
tial
d
ata,
wh
ile
th
e
B
iLST
M
lay
er
ca
p
tu
r
es
tem
p
o
r
al
d
e
p
en
d
en
cies
ac
r
o
s
s
th
e
ex
tr
ac
ted
f
ea
t
u
r
es.
T
h
e
f
in
al
f
u
lly
co
n
n
ec
ted
an
d
s
o
f
tm
a
x
lay
er
s
p
er
f
o
r
m
m
u
lti
-
class
class
if
icatio
n
ac
r
o
s
s
ten
d
iag
n
o
s
tic
ca
teg
o
r
ies.
T
em
p
o
r
al
d
ep
en
d
en
cies
ar
e
m
o
d
eled
u
s
in
g
a
B
iLST
M
lay
er
with
6
4
h
id
d
e
n
u
n
its
an
d
an
o
u
t
p
u
t
m
o
d
e
s
et
to
last
,
allo
win
g
th
e
n
etwo
r
k
to
ca
p
tu
r
e
b
o
th
p
ast
an
d
f
u
t
u
r
e
co
n
tex
tu
al
in
f
o
r
m
ati
o
n
in
th
e
s
eq
u
en
ce
.
T
h
e
f
in
al
class
if
icatio
n
s
tag
e
c
o
n
s
is
ts
o
f
a
f
u
lly
c
o
n
n
ec
ted
la
y
er
with
1
0
o
u
t
p
u
t
n
e
u
r
o
n
s
,
c
o
r
r
esp
o
n
d
in
g
t
o
th
e
tar
g
et
class
es,
f
o
llo
wed
b
y
a
s
o
f
tm
ax
lay
er
an
d
a
class
if
icatio
n
lay
er
f
o
r
f
in
al
p
r
e
d
ictio
n
.
T
h
e
d
etailed
lay
er
co
n
f
ig
u
r
atio
n
a
n
d
co
r
r
esp
o
n
d
i
n
g
h
y
p
er
p
a
r
am
eter
s
ar
e
s
u
m
m
ar
ized
in
T
ab
le
2
.
2
.
4
.
T
ra
ini
ng
a
nd
v
a
lid
a
t
io
n
T
h
e
m
o
d
el
was
tr
ain
ed
an
d
v
a
lid
ated
u
s
in
g
th
e
p
r
o
ce
s
s
ed
d
a
taset.
T
r
ain
in
g
was
p
er
f
o
r
m
e
d
u
s
in
g
th
e
Ad
am
o
p
tim
izer
with
an
in
itia
l
lear
n
in
g
r
ate
o
f
0
.
0
0
1
f
o
r
a
m
ax
im
u
m
o
f
1
0
0
ep
o
ch
s
an
d
a
m
in
i
-
b
atch
s
ize
o
f
1
0
,
with
th
e
tr
ain
in
g
d
ata
s
h
u
f
f
led
at
ea
ch
ep
o
ch
to
r
ed
u
ce
b
ias
an
d
im
p
r
o
v
e
g
e
n
er
aliza
tio
n
.
Mo
d
el
tr
ain
in
g
was
ex
ec
u
ted
o
n
a
GPU
to
ac
ce
ler
ate
co
n
v
er
g
en
ce
.
No
ex
p
licit
ea
r
ly
s
to
p
p
i
n
g
cr
iter
io
n
w
as
ap
p
lied
;
in
s
tead
,
tr
ain
in
g
was
ca
r
r
ied
o
u
t
f
o
r
th
e
f
u
ll
n
u
m
b
er
o
f
ep
o
c
h
s
wh
ile
m
o
n
ito
r
in
g
c
o
n
v
e
r
g
en
ce
th
r
o
u
g
h
th
e
tr
ain
in
g
-
p
r
o
g
r
ess
p
lo
ts
p
r
o
v
id
ed
b
y
MA
T
L
AB
.
T
h
ese
h
y
p
e
r
p
ar
am
eter
ch
o
ices
wer
e
s
ele
cted
em
p
ir
ically
to
b
alan
ce
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
tr
ain
in
g
s
tab
ilit
y
,
an
d
c
o
m
p
u
tatio
n
al
e
f
f
icien
cy
,
p
ar
tic
u
lar
ly
with
th
e
g
o
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
6
4
3
-
2
6
5
4
2646
o
f
s
u
p
p
o
r
tin
g
d
ep
l
o
y
m
e
n
t
o
n
r
eso
u
r
ce
-
c
o
n
s
tr
ain
ed
an
d
e
m
b
ed
d
e
d
p
latf
o
r
m
s
.
Af
ter
tr
ain
in
g
,
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
was
ev
alu
ated
u
s
in
g
k
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
o
n
a
s
ep
ar
ate
test
s
et.
Fig
u
r
e
2
ill
u
s
tr
ates
th
e
k
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
s
s
ad
o
p
t
ed
in
th
is
s
tu
d
y
.
Fig
u
r
e
1
.
C
NN
–
B
iLST
M
m
o
d
el
ar
ch
itectu
r
e
f
o
r
VHD
class
i
f
icatio
n
T
ab
le
2
.
Deta
iled
ar
c
h
itectu
r
e
an
d
h
y
p
er
p
a
r
am
eter
s
ettin
g
s
o
f
th
e
p
r
o
p
o
s
ed
C
NN
–
B
iLST
M
m
o
d
el
La
y
e
r
t
y
p
e
La
y
e
r
n
a
m
e
P
a
r
a
me
t
e
r
s
S
e
q
u
e
n
c
e
i
n
p
u
t
I
n
p
u
t
l
a
y
e
r
I
n
p
u
t
si
z
e
:
(
2
0
0
\
t
i
m
e
s
1
\
t
i
m
e
s
1
)
S
e
q
u
e
n
c
e
f
o
l
d
i
n
g
F
o
l
d
i
n
g
l
a
y
e
r
En
a
b
l
e
s
C
N
N
p
r
o
c
e
ssi
n
g
o
f
se
q
u
e
n
c
e
d
a
t
a
C
o
n
v
o
l
u
t
i
o
n
C
o
n
v
1
4
8
f
i
l
t
e
r
s,
k
e
r
n
e
l
:
(
3
\
t
i
m
e
s
1
)
,
p
a
d
d
i
n
g
:
same
B
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
B
N
1
—
A
c
t
i
v
a
t
i
o
n
R
e
LU
1
R
e
LU
M
a
x
p
o
o
l
i
n
g
M
a
x
P
o
o
l
1
P
o
o
l
s
i
z
e
:
2
,
st
r
i
d
e
:
2
C
o
n
v
o
l
u
t
i
o
n
C
o
n
v
2
3
2
f
i
l
t
e
r
s,
k
e
r
n
e
l
:
(
3
\
t
i
m
e
s
1
)
,
p
a
d
d
i
n
g
:
same
B
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
B
N
2
—
A
c
t
i
v
a
t
i
o
n
R
e
LU
2
R
e
LU
M
a
x
p
o
o
l
i
n
g
M
a
x
P
o
o
l
2
P
o
o
l
s
i
z
e
:
2
,
st
r
i
d
e
:
2
C
o
n
v
o
l
u
t
i
o
n
C
o
n
v
3
1
6
f
i
l
t
e
r
s,
k
e
r
n
e
l
:
(
3
\
t
i
m
e
s
1
)
,
p
a
d
d
i
n
g
:
same
B
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
B
N
3
—
A
c
t
i
v
a
t
i
o
n
R
e
LU
3
R
e
LU
C
o
n
v
o
l
u
t
i
o
n
C
o
n
v
4
3
2
f
i
l
t
e
r
s,
k
e
r
n
e
l
:
(
3
\
t
i
m
e
s
1
)
,
p
a
d
d
i
n
g
:
same
B
a
t
c
h
n
o
r
ma
l
i
z
a
t
i
o
n
B
N
4
—
A
c
t
i
v
a
t
i
o
n
R
e
LU
4
R
e
LU
M
a
x
p
o
o
l
i
n
g
M
a
x
P
o
o
l
3
P
o
o
l
s
i
z
e
:
2
,
st
r
i
d
e
:
2
S
e
q
u
e
n
c
e
u
n
f
o
l
d
i
n
g
U
n
f
o
l
d
i
n
g
l
a
y
e
r
R
e
st
o
r
e
s
t
e
mp
o
r
a
l
s
t
r
u
c
t
u
r
e
F
l
a
t
t
e
n
F
l
a
t
t
e
n
l
a
y
e
r
F
e
a
t
u
r
e
v
e
c
t
o
r
c
o
n
v
e
r
si
o
n
B
i
l
st
m
B
i
LST
M
6
4
h
i
d
d
e
n
u
n
i
t
s,
o
u
t
p
u
t
mo
d
e
:
l
a
s
t
F
u
l
l
y
c
o
n
n
e
c
t
e
d
FC
1
0
n
e
u
r
o
n
s
S
o
f
t
ma
x
S
o
f
t
ma
x
C
l
a
s
s
p
r
o
b
a
b
i
l
i
t
y
e
s
t
i
m
a
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
V
a
lveH
ea
lth
N
et:
a
lig
h
t d
ee
p
l
ea
r
n
in
g
mo
d
el
f
o
r
a
cc
u
r
a
te
va
lvu
la
r
h
ea
r
t d
is
o
r
d
er
…
(
A
u
s
ila
h
A
lfr
a
ih
a
t
)
2647
Fig
u
r
e
2
.
K
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
p
r
o
ce
s
s
ap
p
lied
in
o
u
r
m
eth
o
d
o
lo
g
y
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
prepro
ce
s
s
ing
a
nd
po
wer
s
pect
rum
a
na
ly
s
is
Fig
u
r
e
3
illu
s
tr
ates
th
e
p
o
w
er
s
p
ec
tr
u
m
o
f
h
ea
r
t
s
o
u
n
d
s
f
o
r
ea
ch
VHD
ca
teg
o
r
y
,
with
9
5
%
co
n
f
id
en
ce
in
ter
v
als.
T
h
is
f
ig
u
r
e
p
r
esen
ts
th
e
av
er
a
g
e
PS
D
o
f
h
ea
r
t
s
o
u
n
d
r
ec
o
r
d
in
g
s
f
o
r
ea
ch
VHD
ca
teg
o
r
y
an
d
h
ea
lth
y
s
u
b
jects,
alo
n
g
w
ith
9
5
%
co
n
f
id
e
n
ce
in
ter
v
als.
T
h
e
an
aly
s
is
f
o
cu
s
es
o
n
th
e
0
–
2
0
0
Hz
f
r
eq
u
e
n
cy
r
an
g
e,
wh
ich
co
n
tain
s
d
iag
n
o
s
tically
r
elev
an
t
co
m
p
o
n
en
ts
s
u
ch
as
S1
,
S2
,
an
d
p
ath
o
lo
g
ical
m
u
r
m
u
r
s
.
Dis
tin
ct
s
p
ec
tr
al
p
atter
n
s
ca
n
b
e
o
b
s
e
r
v
ed
b
etwe
en
d
if
f
er
en
t
v
alv
e
p
ath
o
lo
g
ies,
s
u
ch
as
a
o
r
tic
s
ten
o
s
is
an
d
m
itra
l
r
eg
u
r
g
itatio
n
,
p
r
o
v
id
in
g
p
h
y
s
io
lo
g
ical
ju
s
tific
atio
n
f
o
r
th
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
u
s
ed
b
y
th
e
m
o
d
el.
T
h
ese
s
p
ec
tr
al
d
if
f
er
e
n
ce
s
f
o
r
m
th
e
b
asis
f
o
r
C
NN’
s
d
is
cr
im
in
ativ
e
f
ea
tu
r
e
lear
n
i
n
g
.
T
h
e
an
aly
s
i
s
h
ig
h
lig
h
ts
c
r
itical
d
if
f
er
en
ce
s
in
th
e
f
r
eq
u
e
n
cy
d
o
m
ain
b
etwe
en
co
n
d
itio
n
s
lik
e
s
ev
er
e
ao
r
tic
s
ten
o
s
is
an
d
m
itra
l
r
eg
u
r
g
itatio
n
,
d
em
o
n
s
tr
atin
g
t
h
e
b
asis
f
o
r
th
e
m
o
d
el’
s
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
class
if
icatio
n
.
Fig
u
r
e
3
.
Po
wer
s
p
ec
tr
u
m
an
al
y
s
is
o
f
h
ea
r
t so
u
n
d
s
with
9
5
%
co
n
f
id
en
ce
in
ter
v
als
3
.
2
.
T
ra
ini
ng
a
nd
v
a
lid
a
t
io
n
perf
o
rm
a
nce
T
h
e
m
o
d
el
was
tr
ain
ed
an
d
v
alid
ated
u
s
in
g
a
d
ataset
o
f
h
ea
r
t
s
o
u
n
d
r
ec
o
r
d
in
g
s
ac
r
o
s
s
m
u
ltip
le
d
iag
n
o
s
tic
ca
teg
o
r
ies.
T
h
is
in
clu
d
ed
d
if
f
e
r
en
t
ty
p
es
o
f
VH
D
as
well
a
s
a
h
ea
lth
y
class
f
o
r
co
m
p
a
r
is
o
n
.
T
h
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
was
ass
ess
ed
th
r
o
u
g
h
a
cc
u
r
ac
y
m
etr
ics,
co
n
f
u
s
io
n
m
atr
ices,
a
n
d
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
6
4
3
-
2
6
5
4
2648
T
h
is
co
n
f
u
s
io
n
m
atr
ix
as
s
h
o
wn
in
Fig
u
r
e
4
illu
s
tr
ates
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
d
u
r
in
g
th
e
tr
ai
n
in
g
p
h
ase
ac
r
o
s
s
ten
d
is
ea
s
e
ca
teg
o
r
ies,
in
clu
d
in
g
s
ev
e
r
e
ao
r
tic
s
ten
o
s
is
,
m
ild
m
itra
l
s
ten
o
s
is
,
an
d
h
ea
lth
y
s
u
b
jects.
T
h
e
m
at
r
ix
s
h
o
ws
th
e
tr
u
e
p
o
s
itiv
e
r
ates
an
d
m
is
class
if
icatio
n
p
atter
n
s
f
o
r
ea
c
h
tar
g
et
class
.
th
e
m
o
d
el
p
er
f
o
r
m
e
d
w
ell
in
d
is
tin
g
u
is
h
in
g
s
ev
er
e
c
ases
o
f
ao
r
tic
s
ten
o
s
is
with
a
h
ig
h
class
if
icatio
n
ac
cu
r
ac
y
o
f
9
8
.
6
%
[
2
2
]
.
T
h
is
co
n
f
u
s
io
n
m
atr
ix
s
u
m
m
ar
ize
s
th
e
class
if
icat
io
n
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
e
d
C
NN
–
B
iL
STM
m
o
d
el
d
u
r
in
g
th
e
tr
ain
in
g
p
h
ase
ac
r
o
s
s
ten
d
iag
n
o
s
tic
class
e
s
.
E
ac
h
r
o
w
r
ep
r
esen
ts
th
e
tr
u
e
class
,
wh
ile
ea
ch
co
lu
m
n
co
r
r
esp
o
n
d
s
to
th
e
p
r
e
d
icted
class
.
Hig
h
v
alu
es
alo
n
g
th
e
m
ai
n
d
iag
o
n
al
in
d
icate
s
tr
o
n
g
class
-
wis
e
r
ec
o
g
n
itio
n
,
with
m
in
im
al
co
n
f
u
s
io
n
b
etwe
en
u
n
r
elate
d
v
al
v
u
lar
c
o
n
d
itio
n
s
.
T
h
e
f
ew
o
f
f
-
d
ia
g
o
n
al
en
tr
ies
p
r
im
ar
il
y
o
cc
u
r
b
etwe
en
clin
ically
s
im
ilar
d
is
ea
s
e
s
ev
er
ities
,
r
ef
lectin
g
r
ea
lis
tic
d
iag
n
o
s
tic
ch
allen
g
es r
ath
er
th
an
r
an
d
o
m
er
r
o
r
s
.
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
tr
ain
in
g
f
o
ld
s
o
f
th
e
VHD
class
if
icatio
n
m
o
d
el
T
h
e
R
OC
cu
r
v
es
in
Fig
u
r
e
5
d
em
o
n
s
tr
ate
th
e
d
iag
n
o
s
tic
ca
p
ab
ilit
y
o
f
th
e
m
o
d
el
d
u
r
in
g
t
h
e
tr
ain
in
g
p
h
ase
f
o
r
ea
ch
VHD
ca
teg
o
r
y
.
T
h
is
f
ig
u
r
e
s
h
o
ws
th
e
R
OC
c
u
r
v
es
f
o
r
ea
c
h
VHD
ca
teg
o
r
y
d
u
r
in
g
t
h
e
tr
ain
in
g
p
h
ase.
E
ac
h
p
l
o
t
in
Fig
u
r
e
5
co
r
r
esp
o
n
d
s
to
o
n
e
d
iag
n
o
s
tic
class
an
d
illu
s
tr
ates
th
e
tr
ad
e
-
o
f
f
b
etwe
en
tr
u
e
p
o
s
itiv
e
r
ate
an
d
f
alse
p
o
s
itiv
e
r
ate.
T
h
e
c
o
n
s
is
ten
tly
h
ig
h
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
AUC)
v
alu
es
ac
r
o
s
s
all
class
es
in
d
icate
ex
ce
llen
t
s
ep
ar
ab
ilit
y
an
d
s
tr
o
n
g
lear
n
i
n
g
ca
p
ac
ity
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
T
h
ese
r
esu
lts
co
n
f
ir
m
t
h
at
th
e
class
if
ier
ac
h
iev
es
h
ig
h
s
en
s
itiv
ity
an
d
s
p
e
cif
icity
d
u
r
in
g
tr
ain
in
g
.
T
h
ese
cu
r
v
es
in
d
icate
th
e
m
o
d
el'
s
ab
ilit
y
to
s
ep
ar
ate
th
e
tr
u
e
p
o
s
itiv
e
r
ate
f
r
o
m
t
h
e
f
als
e
p
o
s
itiv
e
r
ate,
with
AUC
v
al
u
es
ex
ce
ed
in
g
0
.
9
5
f
o
r
all
ca
teg
o
r
ies.
Fig
u
r
e
6
p
r
esen
ts
t
h
e
co
n
f
u
s
io
n
m
atr
i
x
r
esu
lts
f
r
o
m
th
e
test
in
g
p
h
ase,
s
h
o
wca
s
in
g
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
in
d
is
tin
g
u
is
h
in
g
b
etwe
en
d
if
f
er
en
t
VHD
.
T
h
is
co
n
f
u
s
io
n
m
atr
ix
d
ep
ic
ts
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
t
h
e
m
o
d
el
o
n
th
e
in
d
ep
en
d
en
t
test
in
g
d
ataset.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
s
tr
o
n
g
g
e
n
er
aliza
tio
n
,
with
h
ig
h
tr
u
e
p
o
s
itiv
e
r
ates
m
ain
tain
ed
ac
r
o
s
s
all
d
is
ea
s
e
ca
teg
o
r
ies
an
d
h
ea
lth
y
s
u
b
ject
s
.
Misclass
if
icatio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
V
a
lveH
ea
lth
N
et:
a
lig
h
t d
ee
p
l
ea
r
n
in
g
mo
d
el
f
o
r
a
cc
u
r
a
te
va
lvu
la
r
h
ea
r
t d
is
o
r
d
er
…
(
A
u
s
ila
h
A
lfr
a
ih
a
t
)
2649
ar
e
in
f
r
e
q
u
en
t
a
n
d
m
ain
ly
o
c
cu
r
b
etwe
en
ad
jace
n
t
s
ev
er
ity
lev
els
o
f
th
e
s
am
e
v
alv
u
la
r
p
ath
o
lo
g
y
,
s
u
ch
as
m
ild
v
er
s
u
s
m
o
d
er
ate
d
is
ea
s
e.
T
h
e
m
i
n
im
al
co
n
f
u
s
io
n
b
etwe
en
h
ea
lth
y
a
n
d
p
ath
o
lo
g
ica
l
class
es
h
ig
h
lig
h
ts
th
e
m
o
d
el’
s
s
u
itab
ilit
y
f
o
r
cli
n
ical
s
cr
ee
n
in
g
ap
p
licatio
n
s
.
T
h
e
m
o
d
el
c
o
r
r
ec
tly
class
if
ie
d
9
7
.
5
%
o
f
s
ev
er
e
ao
r
tic
s
ten
o
s
is
ca
s
es,
with
m
in
im
al
f
alse p
o
s
itiv
es a
n
d
n
eg
ati
v
es,
in
d
icatin
g
r
o
b
u
s
t te
s
tin
g
p
er
f
o
r
m
a
n
ce
.
Fig
u
r
e
5
.
R
OC
cu
r
v
es f
o
r
tr
ain
in
g
f
o
ld
s
o
f
th
e
VHD
class
if
icatio
n
m
o
d
el
Fig
u
r
e
6
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
test
in
g
f
o
ld
s
o
f
th
e
VHD
class
if
icatio
n
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
6
4
3
-
2
6
5
4
2650
T
h
e
R
OC
cu
r
v
es
in
Fig
u
r
e
7
r
ep
r
esen
t
th
e
m
o
d
el'
s
d
iag
n
o
s
tic
p
er
f
o
r
m
an
ce
d
u
r
in
g
test
in
g
.
T
h
is
f
ig
u
r
e
p
r
esen
ts
th
e
R
O
C
cu
r
v
es
f
o
r
ea
ch
d
iag
n
o
s
tic
class
d
u
r
in
g
th
e
test
in
g
p
h
ase,
with
ea
ch
p
lo
t
in
Fig
u
r
e
7
co
r
r
esp
o
n
d
in
g
t
o
in
d
iv
id
u
al
v
alv
u
lar
c
o
n
d
itio
n
s
an
d
th
e
h
ea
lth
y
class
.
T
h
e
cu
r
v
es
ex
h
ib
it
n
ea
r
-
s
atu
r
ated
b
e
h
av
io
r
,
with
AUC
v
alu
es
ap
p
r
o
ac
h
in
g
1
.
0
ac
r
o
s
s
all
ca
teg
o
r
ies,
in
d
icatin
g
ex
ce
llen
t
d
iag
n
o
s
tic
p
er
f
o
r
m
a
n
ce
o
n
u
n
s
ee
n
d
ata.
T
h
ese
r
esu
lts
co
n
f
ir
m
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
r
etain
s
h
ig
h
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
b
ey
o
n
d
th
e
tr
ain
in
g
s
et.
I
m
p
o
r
tan
t
ly
,
th
e
R
OC
an
aly
s
i
s
co
m
p
lem
en
ts
th
e
co
n
f
u
s
io
n
m
atr
ix
b
y
d
e
m
o
n
s
tr
atin
g
r
o
b
u
s
t
d
is
cr
im
in
atio
n
ev
en
in
a
m
u
lti
-
class
s
et
tin
g
.
Hig
h
AUC
v
alu
es,
ap
p
r
o
a
ch
in
g
1
.
0
ac
r
o
s
s
all
ca
teg
o
r
ies,
co
n
f
i
r
m
th
at
th
e
m
o
d
el
ac
cu
r
ately
d
is
tin
g
u
is
h
es
b
etwe
en
h
ea
lth
y
an
d
d
is
ea
s
ed
h
ea
r
t
s
o
u
n
d
r
ec
o
r
d
in
g
s
.
Fig
u
r
e
7
.
R
OC
C
u
r
v
es f
o
r
test
in
g
f
o
ld
s
o
f
th
e
VHD
class
if
icatio
n
m
o
d
el
3
.
3
.
Dis
cus
s
io
n
T
h
is
s
tu
d
y
p
r
esen
ts
a
n
o
v
el
h
y
b
r
id
m
o
d
el
th
at
i
n
teg
r
ate
s
C
NN
an
d
B
iLST
M
n
etwo
r
k
s
f
o
r
th
e
class
if
icatio
n
o
f
VHD
u
s
in
g
h
ea
r
t
s
o
u
n
d
r
ec
o
r
d
in
g
s
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
ac
h
iev
ed
h
ig
h
p
er
f
o
r
m
an
ce
,
r
ef
lecte
d
b
y
p
r
ec
is
io
n
an
d
r
e
ca
ll
m
etr
ics
ac
r
o
s
s
d
if
f
er
en
t
VHD
ca
teg
o
r
ies.
A
10
-
f
o
ld
c
r
o
s
s
-
v
alid
atio
n
was
em
p
lo
y
ed
to
e
v
alu
ate
th
e
r
o
b
u
s
tn
ess
o
f
o
u
r
m
o
d
el.
R
esu
lts
s
h
o
wed
c
o
n
s
is
ten
tly
h
ig
h
cla
s
s
if
icatio
n
ac
cu
r
ac
y
ac
r
o
s
s
all
d
is
ea
s
e
ca
teg
o
r
ies,
with
th
e
h
ig
h
est
ac
cu
r
ac
y
r
ec
o
r
d
ed
f
o
r
m
ild
ao
r
tic
s
ten
o
s
is
(
9
9
.
8
1
%).
T
h
e
o
v
er
all
p
er
f
o
r
m
a
n
ce
was stro
n
g
,
with
ac
cu
r
ac
y
lev
els s
u
r
p
as
s
in
g
9
5
% in
all
ca
s
es.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
r
ev
ea
l
ed
a
lo
w
n
u
m
b
er
o
f
m
is
class
if
icatio
n
s
,
d
em
o
n
s
tr
atin
g
th
e
m
o
d
el'
s
p
r
ec
is
io
n
.
Fo
r
i
n
s
tan
ce
,
s
ev
er
e
ao
r
tic
s
ten
o
s
is
was
class
if
i
ed
co
r
r
ec
tly
9
8
.
6
%
o
f
t
h
e
ti
m
e,
an
d
m
ild
m
itra
l
s
ten
o
s
is
ac
h
iev
ed
n
ea
r
-
p
er
f
ec
t
class
if
icatio
n
at
9
9
.
9
%.
Fals
e
p
o
s
itiv
es
an
d
n
e
g
ativ
es
wer
e
m
in
im
al,
f
u
r
th
er
r
ein
f
o
r
cin
g
th
e
m
o
d
el'
s
r
elia
b
ilit
y
.
R
OC
an
aly
s
is
p
r
o
v
id
e
d
ad
d
itio
n
al
s
u
p
p
o
r
t
f
o
r
th
e
m
o
d
el’
s
d
iag
n
o
s
tic
ca
p
ab
ilit
ies,
with
all
d
i
s
ea
s
e
c
ateg
o
r
ies
ac
h
iev
in
g
h
ig
h
AUC
v
alu
es.
T
h
e
AUC
f
o
r
m
o
d
er
ate
m
itra
l
s
ten
o
s
is
was
0
.
9
9
9
9
3
,
m
ak
in
g
it
o
n
e
o
f
th
e
b
est
-
p
er
f
o
r
m
i
n
g
ca
teg
o
r
ies.
Oth
er
co
n
d
itio
n
s
,
lik
e
s
ev
er
e
m
itra
l
r
eg
u
r
g
itatio
n
an
d
s
ev
er
e
tr
icu
s
p
id
d
is
ea
s
e,
al
s
o
ex
h
ib
ited
h
ig
h
AUC
v
alu
es,
in
d
icatin
g
s
tr
o
n
g
d
is
cr
im
in
ato
r
y
p
o
wer
b
etwe
en
th
e
d
if
f
er
e
n
t
h
ea
r
t
s
o
u
n
d
p
atter
n
s
.
T
h
is
p
er
f
o
r
m
an
ce
en
s
u
r
es
r
eliab
le
class
if
icatio
n
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
co
m
p
a
r
ed
to
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
wh
ich
o
f
ten
r
ely
o
n
h
an
d
cr
a
f
ted
f
ea
t
u
r
es
an
d
d
o
n
o
t
f
u
lly
ex
p
lo
it
th
e
p
o
ten
tial
o
f
r
aw
h
ea
r
t
s
o
u
n
d
d
ata.
T
h
e
in
teg
r
atio
n
o
f
C
NNs
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
B
iLST
Ms
f
o
r
tem
p
o
r
al
d
e
p
en
d
e
n
cy
a
n
aly
s
is
allo
ws
f
o
r
a
m
o
r
e
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
th
e
h
ea
r
t
s
o
u
n
d
s
,
en
a
b
lin
g
b
etter
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
d
if
f
er
en
t
ty
p
es
o
f
VH
D.
T
h
e
m
o
d
el'
s
ac
cu
r
ac
y
s
u
r
p
ass
ed
9
8
%,
s
ig
n
if
ica
n
tly
im
p
r
o
v
in
g
u
p
o
n
p
r
io
r
wo
r
k
lik
e
B
ar
u
a
et
a
l.
[
1
7
]
,
w
h
o
s
e
h
an
d
c
r
af
ted
f
ea
t
u
r
e
-
b
ase
d
m
o
d
el
also
s
h
o
wed
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
b
u
t
was
lim
ited
b
y
its
f
ea
tu
r
e
e
x
tr
ac
tio
n
ap
p
r
o
ac
h
,
w
h
ich
was n
o
t f
u
l
ly
au
to
m
ated
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
V
a
lveH
ea
lth
N
et:
a
lig
h
t d
ee
p
l
ea
r
n
in
g
mo
d
el
f
o
r
a
cc
u
r
a
te
va
lvu
la
r
h
ea
r
t d
is
o
r
d
er
…
(
A
u
s
ila
h
A
lfr
a
ih
a
t
)
2651
T
h
e
s
u
cc
ess
o
f
th
is
m
o
d
el
p
o
in
ts
to
war
d
th
e
f
ea
s
ib
ilit
y
o
f
u
s
in
g
AI
-
en
h
an
ce
d
a
u
s
cu
ltatio
n
in
clin
ica
l
s
ettin
g
s
,
esp
ec
ially
in
r
eso
u
r
ce
-
lim
ited
en
v
ir
o
n
m
e
n
ts
wh
er
e
ad
v
a
n
ce
d
d
iag
n
o
s
tic
to
o
ls
s
u
ch
as
ec
h
o
ca
r
d
io
g
r
ap
h
y
m
ay
n
o
t
b
e
ac
ce
s
s
ib
le.
B
y
u
tili
z
in
g
elec
tr
o
n
ic
s
teth
o
s
co
p
e
d
ata
an
d
ap
p
ly
in
g
m
i
n
im
al
p
r
ep
r
o
ce
s
s
in
g
,
th
is
m
eth
o
d
p
r
o
v
id
es
a
co
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
th
at
co
u
ld
b
e
d
ep
lo
y
ed
i
n
p
o
r
tab
le
d
ev
ices,
ex
p
an
d
i
n
g
ac
ce
s
s
to
ea
r
l
y
V
HD
d
etec
tio
n
g
lo
b
ally
.
Ho
we
v
er
,
g
e
n
er
aliza
b
ilit
y
r
e
m
ain
s
a
ch
allen
g
e,
as
o
u
r
m
o
d
el
was
p
r
im
ar
ily
v
alid
ate
d
o
n
in
p
atien
t
d
ata
[
2
3
]
.
Fu
r
th
er
s
tu
d
ies
ar
e
n
ee
d
ed
to
ass
es
s
its
p
er
f
o
r
m
an
ce
in
d
iv
er
s
e
clin
ical
p
o
p
u
latio
n
s
,
in
clu
d
in
g
o
u
tp
atien
t a
n
d
r
em
o
te
s
ettin
g
s
[
2
4
]
,
[
2
5
]
.
Desp
ite
th
e
h
ig
h
ac
c
u
r
ac
y
,
s
o
m
e
lim
itatio
n
s
n
ee
d
to
b
e
a
d
d
r
ess
ed
.
T
h
e
m
o
d
el
ex
h
i
b
ited
r
ed
u
ce
d
s
en
s
itiv
ity
f
o
r
ce
r
tain
VHD
s
u
b
ty
p
es,
s
u
ch
as
m
ix
e
d
v
alv
u
la
r
d
is
ea
s
es,
wh
ich
m
ay
r
eq
u
ir
e
f
u
r
th
er
r
ef
in
em
e
n
t
o
f
th
e
ar
c
h
itectu
r
e.
Ad
d
itio
n
ally
,
th
e
d
ataset
was
r
elativ
ely
b
alan
ce
d
ac
r
o
s
s
VHD
clas
s
es,
b
u
t
r
ea
l
-
wo
r
ld
clin
ical
d
ata
m
ay
p
r
esen
t
m
o
r
e
s
k
ewe
d
d
is
tr
ib
u
tio
n
s
,
p
o
ten
tially
af
f
ec
tin
g
m
o
d
el
p
e
r
f
o
r
m
a
n
ce
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
im
p
r
o
v
in
g
s
en
s
itiv
ity
f
o
r
co
m
p
lex
VHD
ca
s
es
an
d
v
alid
atin
g
th
e
m
o
d
el
ac
r
o
s
s
b
r
o
ad
e
r
clin
ical
p
o
p
u
latio
n
s
.
Mo
r
eo
v
er
,
in
co
r
p
o
r
atin
g
a
d
d
i
tio
n
al
d
ata
s
o
u
r
ce
s
,
s
u
ch
as
p
atien
t
h
is
to
r
y
an
d
o
th
er
b
io
m
ar
k
er
s
,
m
ay
en
h
an
c
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
an
d
p
r
o
v
id
e
a
m
o
r
e
h
o
lis
tic
ap
p
r
o
ac
h
to
VHD
d
iag
n
o
s
is
.
T
o
p
r
o
v
id
e
a
m
o
r
e
co
m
p
r
eh
en
s
iv
e
ev
alu
atio
n
b
e
y
o
n
d
o
v
er
all
ac
cu
r
ac
y
an
d
R
OC
AU
C
,
T
ab
le
3
r
ep
o
r
ts
class
-
wi
s
e
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
d
er
iv
e
d
f
r
o
m
t
h
e
co
n
f
u
s
io
n
m
atr
ix
(
Fig
u
r
e
6
)
.
T
h
ese
m
etr
ics
o
f
f
er
d
ee
p
er
in
s
ig
h
t
in
to
th
e
m
o
d
el’
s
s
tr
en
g
th
s
an
d
p
o
ten
tial
f
ailu
r
e
m
o
d
es,
p
ar
ticu
lar
l
y
f
o
r
clin
ically
s
im
ilar
v
alv
u
lar
co
n
d
itio
n
s
.
T
ab
le
3
.
C
lass
-
wis
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
f
o
r
VHD
class
if
icatio
n
C
l
a
s
s
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
sc
o
r
e
(
%)
S
e
v
e
r
e
a
o
r
t
i
c
st
e
n
o
si
s
9
7
.
4
9
8
.
6
98
M
i
l
d
a
o
r
t
i
c
s
t
e
n
o
si
s
9
8
.
8
99
9
8
.
9
M
i
l
d
mi
t
r
a
l
st
e
n
o
s
i
s
9
9
.
2
9
7
.
9
9
8
.
5
M
o
d
e
r
a
t
e
mi
t
r
a
l
s
t
e
n
o
s
i
s
9
9
.
8
9
8
.
7
9
9
.
2
S
e
v
e
r
e
m
i
t
r
a
l
r
e
g
u
r
g
i
t
a
t
i
o
n
9
8
.
1
9
8
.
4
9
8
.
3
M
i
l
d
mi
t
r
a
l
r
e
g
u
r
g
i
t
a
t
i
o
n
9
8
.
1
9
7
.
5
9
7
.
8
M
o
d
e
r
a
t
e
mi
t
r
a
l
r
e
g
u
r
g
i
t
a
t
i
o
n
9
8
.
7
9
8
.
1
9
8
.
4
S
e
v
e
r
e
t
r
i
c
u
sp
i
d
d
i
s
e
a
se
9
9
.
7
9
9
.
4
9
9
.
6
M
o
d
e
r
a
t
e
t
r
i
c
u
sp
i
d
d
i
se
a
se
99
9
8
.
8
9
8
.
9
H
e
a
l
t
h
y
9
8
.
9
9
8
.
7
9
8
.
8
O
v
e
r
a
l
l
9
8
.
8
9
8
.
4
9
8
.
5
Alth
o
u
g
h
th
e
p
r
o
p
o
s
ed
C
NN
–
B
iLST
M
m
o
d
el
d
em
o
n
s
tr
ate
s
co
n
s
is
ten
tly
h
ig
h
p
r
ec
is
io
n
an
d
r
ec
all
ac
r
o
s
s
all
class
es,
th
e
co
n
f
u
s
io
n
m
atr
ix
r
ev
ea
ls
a
s
m
all
n
u
m
b
er
o
f
s
tr
u
ctu
r
e
d
m
is
class
if
icatio
n
s
th
at
p
r
o
v
id
e
in
s
ig
h
t
in
to
m
o
d
el
lim
itatio
n
s
.
T
h
e
m
o
s
t
f
r
eq
u
en
t
er
r
o
r
s
o
cc
u
r
b
etwe
en
ad
jace
n
t
s
ev
er
ity
lev
els
o
f
th
e
s
am
e
v
alv
e
p
ath
o
lo
g
y
,
p
ar
ticu
lar
ly
m
ild
v
er
s
u
s
m
o
d
er
ate
m
itra
l
an
d
ao
r
tic
v
alv
e
d
is
ea
s
es.
T
h
ese
co
n
f
u
s
io
n
s
ar
e
clin
ically
p
lau
s
ib
le,
as
ea
r
ly
-
s
tag
e
v
al
v
u
lar
ab
n
o
r
m
alities
o
f
ten
ex
h
ib
it
o
v
e
r
lap
p
in
g
ac
o
u
s
tic
s
ig
n
atu
r
es,
m
ak
in
g
p
r
ec
is
e
s
ev
er
ity
d
if
f
er
en
tiatio
n
c
h
allen
g
in
g
ev
e
n
f
o
r
e
x
p
er
t
clin
ician
s
.
Fo
r
ex
am
p
le,
m
ild
m
itra
l
r
eg
u
r
g
itatio
n
is
o
cc
asio
n
ally
m
is
class
if
ied
as
m
o
d
e
r
at
e
m
itra
l
r
e
g
u
r
g
itatio
n
,
s
u
g
g
esti
n
g
th
at
s
u
b
tle
s
p
ec
tr
al
–
tem
p
o
r
al
d
i
f
f
er
en
ce
s
m
ay
n
o
t a
lway
s
b
e
f
u
lly
ca
p
tu
r
ed
.
I
n
c
o
n
tr
ast,
s
ev
er
e
v
alv
u
lar
d
is
ea
s
es,
in
clu
d
in
g
s
ev
er
e
ao
r
tic
s
ten
o
s
is
,
s
ev
er
e
m
itra
l
r
eg
u
r
g
itatio
n
,
an
d
s
ev
er
e
tr
icu
s
p
id
d
is
ea
s
e
,
ex
h
ib
it
v
e
r
y
h
ig
h
r
ec
all
(
>9
8
%),
in
d
icatin
g
th
at
t
h
e
m
o
d
el
is
h
ig
h
ly
s
en
s
itiv
e
to
ad
v
an
ce
d
p
ath
o
lo
g
ical
p
atter
n
s
.
T
h
is
is
a
d
esira
b
le
p
r
o
p
er
ty
in
clin
ical
s
cr
ee
n
in
g
ap
p
licatio
n
s
,
wh
er
e
m
is
s
in
g
s
ev
er
e
d
is
ea
s
e
ca
r
r
ies
a
g
r
ea
t
er
r
is
k
th
a
n
m
ild
m
is
class
if
ic
atio
n
.
Misclass
if
icatio
n
b
etwe
en
h
ea
lth
y
s
u
b
jects
an
d
p
at
h
o
lo
g
ical
class
es
is
m
in
im
al,
with
p
r
ec
is
io
n
an
d
r
e
ca
ll
f
o
r
th
e
h
ea
lth
y
class
ex
c
ee
d
in
g
9
8
%.
T
h
is
s
u
g
g
ests
s
tr
o
n
g
d
is
cr
im
in
atio
n
b
etwe
en
n
o
r
m
al
h
e
ar
t
s
o
u
n
d
s
an
d
ab
n
o
r
m
al
m
u
r
m
u
r
s
,
r
ein
f
o
r
cin
g
th
e
m
o
d
el’
s
s
u
itab
ilit
y
f
o
r
ea
r
ly
s
cr
ee
n
in
g
an
d
tr
iag
e.
R
OC
an
aly
s
i
s
as
in
Fig
u
r
e
6
f
u
r
th
er
c
o
r
r
o
b
o
r
ates
th
es
e
f
in
d
in
g
s
,
with
all
class
es
ac
h
iev
in
g
n
ea
r
-
s
atu
r
ated
cu
r
v
es
an
d
AUC
v
alu
es
clo
s
e
to
1
.
0
.
Ho
wev
er
,
th
e
p
r
esen
ce
o
f
lim
ited
m
is
class
if
icatio
n
s
d
esp
ite
ex
tr
em
ely
h
ig
h
AUC
v
alu
es
h
ig
h
lig
h
ts
th
e
im
p
o
r
ta
n
ce
o
f
r
e
p
o
r
tin
g
class
-
wis
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
in
m
u
lti
-
class
clin
ical
p
r
o
b
lem
s
,
as
R
OC
cu
r
v
es
alo
n
e
m
ay
m
ask
s
u
b
tle
y
et
clin
ically
r
elev
a
n
t
er
r
o
r
s
.
Ov
er
all,
th
e
f
ailu
r
e
ca
s
es
id
en
tifie
d
ar
e
co
n
ce
n
tr
ated
in
clin
ically
s
im
ilar
an
d
ac
o
u
s
tically
o
v
er
lap
p
in
g
d
is
ea
s
e
ca
teg
o
r
ies,
r
ath
er
th
an
ac
r
o
s
s
u
n
r
elate
d
class
es.
T
h
is
in
d
icate
s
th
at
f
u
tu
r
e
im
p
r
o
v
e
m
en
ts
s
h
o
u
ld
f
o
cu
s
o
n
en
h
an
cin
g
s
en
s
itiv
ity
to
f
i
n
e
-
g
r
ain
e
d
s
ev
er
ity
d
if
f
er
e
n
ce
s
,
p
o
ten
tially
th
r
o
u
g
h
h
ig
h
er
-
r
eso
lu
tio
n
s
p
ec
tr
al
f
ea
tu
r
es,
atten
tio
n
m
ec
h
an
is
m
s
,
o
r
m
u
ltimo
d
al
clin
ical
d
ata
i
n
teg
r
atio
n
.
W
h
ile
th
e
p
r
o
p
o
s
ed
Valv
e
Hea
lth
Net
f
r
am
ewo
r
k
d
em
o
n
s
tr
ated
s
tr
o
n
g
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
ev
alu
ated
VHD
ca
teg
o
r
ies,
it s
h
o
u
ld
b
e
n
o
ted
th
at
th
e
cu
r
r
e
n
t
v
alid
atio
n
was p
r
im
ar
ily
co
n
d
u
cted
o
n
in
p
atien
t
h
ea
r
t
s
o
u
n
d
s
r
ec
o
r
d
i
n
g
s
.
As
in
p
atien
t
p
o
p
u
latio
n
s
o
f
ten
ex
h
ib
it
clea
r
er
p
ath
o
lo
g
ical
s
ig
n
atu
r
es,
m
o
d
el
p
er
f
o
r
m
an
ce
m
ay
d
if
f
er
in
o
u
t
p
atien
t
o
r
co
m
m
u
n
ity
-
b
ased
s
cr
ee
n
in
g
s
ce
n
ar
io
s
wh
er
e
m
u
r
m
u
r
s
ca
n
b
e
s
u
b
tler
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
3
,
J
u
n
e
2
0
2
6
:
2
6
4
3
-
2
6
5
4
2652
an
d
n
o
is
e
lev
els
h
ig
h
er
.
Fu
tu
r
e
wo
r
k
will
th
er
e
f
o
r
e
f
o
cu
s
o
n
p
r
o
s
p
ec
tiv
e
ex
ter
n
al
v
alid
ati
o
n
u
s
in
g
o
u
tp
atien
t
d
atasets
an
d
m
u
lti
-
ce
n
ter
co
h
o
r
ts
to
ass
es
s
r
o
b
u
s
tn
ess
a
cr
o
s
s
d
iv
er
s
e
ac
q
u
is
itio
n
co
n
d
itio
n
s
an
d
p
atien
t
d
em
o
g
r
a
p
h
ics.
I
n
p
ar
ticu
lar
,
ev
alu
atin
g
t
h
e
m
o
d
el
o
n
h
ea
r
t
s
o
u
n
d
s
co
llected
with
d
if
f
er
en
t
elec
tr
o
n
ic
s
teth
o
s
co
p
es
an
d
in
am
b
u
lato
r
y
en
v
ir
o
n
m
en
ts
will
b
e
cr
itica
l
to
en
s
u
r
e
r
ea
l
-
w
o
r
ld
a
p
p
lica
b
ilit
y
.
Ad
d
itio
n
ally
,
d
o
m
ain
a
d
ap
tatio
n
s
tr
ateg
ies
s
u
ch
as
f
in
e
-
tu
n
in
g
with
s
m
all
lab
eled
s
am
p
les
f
r
o
m
n
ew
c
en
ter
s
,
n
o
is
e
-
awa
r
e
tr
ain
in
g
,
a
n
d
d
ata
a
u
g
m
e
n
tatio
n
with
r
ea
lis
tic
ac
o
u
s
tic
ar
tifa
cts
will
b
e
ex
p
lo
r
ed
to
e
n
h
an
ce
r
o
b
u
s
tn
ess
ag
ain
s
t
r
ec
o
r
d
in
g
v
ar
iab
ilit
y
an
d
en
v
ir
o
n
m
en
tal
n
o
is
e.
T
h
ese
ap
p
r
o
ac
h
es
ar
e
ex
p
ec
ted
to
im
p
r
o
v
e
g
en
er
aliza
tio
n
with
o
u
t su
b
s
tan
tially
in
cr
ea
s
in
g
m
o
d
el
c
o
m
p
l
ex
ity
.
4.
CO
NCLU
SI
O
N
T
h
i
s
s
t
u
d
y
i
n
tr
o
d
u
c
ed
Va
l
v
eH
e
a
l
t
h
N
e
t
,
a
l
i
g
h
t
w
e
i
g
h
t
d
e
ep
l
e
ar
n
in
g
m
o
d
e
l
s
p
e
c
if
i
c
a
l
ly
d
e
s
i
g
n
e
d
t
o
e
n
h
an
c
e
t
h
e
d
e
t
e
c
t
io
n
an
d
c
la
s
s
i
f
i
c
a
t
i
o
n
o
f
V
H
D
u
s
i
n
g
h
e
a
r
t
s
o
u
n
d
r
e
c
o
r
d
in
g
s
.
T
h
e
m
o
d
e
l
d
e
m
o
n
s
t
r
a
t
e
d
c
o
n
s
i
s
t
e
n
t
ly
h
ig
h
a
c
c
u
r
a
cy
,
p
r
e
c
i
s
io
n
,
an
d
r
e
c
a
l
l
a
c
r
o
s
s
m
u
l
t
i
p
l
e
V
H
D
c
a
t
eg
o
r
i
es
,
h
i
g
h
l
i
g
h
t
i
n
g
i
t
s
c
a
p
ab
i
l
i
t
y
to
d
i
f
f
e
r
e
n
t
i
a
t
e
b
e
tw
e
e
n
s
u
b
t
l
e
a
co
u
s
t
i
c
s
i
g
n
a
t
u
r
e
s
a
s
s
o
c
i
a
t
e
d
w
i
th
d
if
f
er
e
n
t
v
a
l
v
e
p
a
t
h
o
l
o
g
i
e
s
.
A
n
o
t
ab
l
e
s
t
r
e
n
g
t
h
o
f
V
a
lv
eH
e
a
l
t
h
N
e
t
i
s
i
t
s
m
i
n
i
m
a
l
p
r
ep
r
o
c
e
s
s
i
n
g
r
e
q
u
i
r
em
e
n
t
s
,
wh
i
c
h
m
ak
e
i
t
h
ig
h
ly
s
u
i
t
a
b
l
e
f
o
r
i
m
p
l
e
m
e
n
t
a
t
io
n
o
n
em
b
ed
d
ed
s
y
s
t
e
m
s
a
n
d
p
o
r
ta
b
l
e
e
l
ec
t
r
o
n
i
c
s
te
t
h
o
s
co
p
e
s
.
T
h
e
s
e
c
h
a
r
ac
t
e
r
i
s
t
i
c
s
p
o
s
i
t
i
o
n
t
h
e
m
o
d
e
l
a
s
a
p
r
a
c
t
i
c
a
l
t
o
o
l
f
o
r
r
e
s
o
u
r
ce
-
l
i
m
i
te
d
s
e
t
t
in
g
s
,
p
o
t
en
t
i
a
l
l
y
e
n
ab
l
i
n
g
e
a
r
l
y
V
H
D
s
cr
e
e
n
in
g
i
n
p
r
i
m
a
r
y
c
a
r
e
c
l
in
i
c
s
,
r
u
r
a
l
h
o
s
p
i
t
al
s
,
o
r
co
m
m
u
n
i
ty
h
e
a
l
th
p
r
o
g
r
a
m
s
wh
e
r
e
a
c
ce
s
s
t
o
e
c
h
o
c
ar
d
io
g
r
a
p
h
y
i
s
l
i
m
it
e
d
.
B
e
y
o
n
d
i
t
s
h
i
g
h
c
l
a
s
s
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
m
an
c
e
,
Va
l
v
eH
e
a
l
t
h
N
e
t
ex
h
ib
i
t
s
c
l
i
n
i
c
a
l
ly
m
ea
n
in
g
f
u
l
b
eh
a
v
io
r
:
i
t
m
a
in
t
a
i
n
s
e
x
ce
l
l
e
n
t
s
e
n
s
i
t
i
v
i
t
y
f
o
r
s
e
v
er
e
d
i
s
e
a
s
e
c
a
te
g
o
r
i
e
s
,
wh
i
l
e
m
o
s
t
m
i
s
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
o
c
cu
r
b
e
t
we
e
n
a
d
ja
c
e
n
t
d
i
s
e
a
s
e
s
e
v
er
i
t
i
es
,
r
e
f
l
e
c
t
in
g
p
l
a
u
s
ib
l
e
d
i
ag
n
o
s
t
i
c
c
h
a
l
l
e
n
g
e
s
t
h
a
t
e
v
e
n
h
u
m
a
n
e
x
p
e
r
t
s
f
ac
e
.
T
h
e
s
e
r
e
s
u
l
t
s
d
em
o
n
s
t
r
a
t
e
th
a
t
AI
-
a
s
s
i
s
t
e
d
au
s
c
u
l
t
a
t
io
n
c
an
co
m
p
l
e
m
en
t
t
r
a
d
i
t
io
n
a
l
d
i
ag
n
o
s
t
i
c
wo
r
k
f
lo
w
s
,
p
r
o
v
i
d
in
g
a
c
o
s
t
-
ef
f
ec
ti
v
e
an
d
s
c
a
l
a
b
le
s
o
lu
t
i
o
n
f
o
r
l
a
r
g
e
-
s
c
a
l
e
V
H
D
s
c
r
e
e
n
in
g
,
tr
i
a
g
e
,
a
n
d
m
o
n
i
t
o
r
i
n
g
.
D
e
s
p
i
t
e
t
h
e
s
e
s
t
r
e
n
g
t
h
s
,
s
e
v
er
a
l
a
r
ea
s
w
ar
r
an
t
f
u
r
t
h
e
r
i
n
v
e
s
t
i
g
a
t
io
n
.
T
h
e
m
o
d
e
l
’
s
cu
r
r
e
n
t
v
a
l
i
d
a
t
io
n
i
s
p
r
i
m
ar
i
l
y
l
i
m
i
t
ed
to
i
n
p
a
t
i
e
n
t
h
e
ar
t
s
o
u
n
d
r
e
co
r
d
i
n
g
s
,
wh
i
ch
m
a
y
d
i
f
f
e
r
f
r
o
m
c
o
m
m
u
n
i
ty
o
r
o
u
t
p
a
t
i
en
t
s
e
tt
i
n
g
s
wh
e
r
e
m
u
r
m
u
r
s
a
r
e
s
u
b
t
l
e
r
a
n
d
b
a
c
k
g
r
o
u
n
d
n
o
i
s
e
l
e
v
e
l
s
ar
e
h
i
g
h
e
r
.
F
u
t
u
r
e
r
e
s
e
a
r
ch
s
h
o
u
l
d
th
e
r
ef
o
r
e
f
o
cu
s
o
n
ex
t
e
r
n
a
l
v
a
l
id
a
t
i
o
n
a
cr
o
s
s
d
i
v
e
r
s
e
c
l
i
n
ic
a
l
e
n
v
i
r
o
n
m
e
n
t
s
an
d
p
a
t
i
e
n
t
p
o
p
u
l
a
t
io
n
s
,
i
n
c
lu
d
in
g
m
u
l
t
i
-
ce
n
t
er
d
a
t
a
s
e
t
s
an
d
am
b
u
la
t
o
r
y
r
e
co
r
d
i
n
g
s
.
Ad
d
i
t
io
n
a
l
ly
,
in
t
eg
r
a
t
in
g
c
o
m
p
l
e
m
en
t
a
r
y
d
a
ta
s
o
u
r
c
e
s
s
u
c
h
a
s
p
at
i
e
n
t
h
i
s
t
o
r
y
,
ec
h
o
ca
r
d
io
g
r
a
p
h
y
r
e
p
o
r
t
s
,
an
d
o
t
h
er
b
i
o
m
a
r
k
e
r
s
co
u
ld
e
n
h
an
c
e
d
ia
g
n
o
s
t
i
c
p
r
e
c
i
s
i
o
n
an
d
r
o
b
u
s
t
n
e
s
s
,
p
a
r
t
i
cu
l
ar
l
y
f
o
r
m
ix
e
d
o
r
co
m
p
le
x
v
a
lv
u
la
r
d
i
s
e
a
s
e
s
.
E
x
p
lo
r
a
t
io
n
o
f
ad
v
an
c
ed
t
ec
h
n
iq
u
e
s
,
s
u
c
h
a
s
a
t
t
en
t
i
o
n
m
e
c
h
an
i
s
m
s
,
m
u
l
t
i
m
o
d
a
l
f
u
s
i
o
n
,
a
n
d
d
o
m
a
in
a
d
a
p
ta
t
i
o
n
s
t
r
a
t
eg
i
e
s
,
m
a
y
f
u
r
t
h
e
r
im
p
r
o
v
e
t
h
e
m
o
d
e
l’
s
s
e
n
s
i
t
i
v
i
t
y
t
o
f
in
e
-
g
r
a
in
e
d
p
a
th
o
lo
g
i
c
a
l
d
i
f
f
e
r
e
n
c
e
s
w
i
t
h
o
u
t
c
o
m
p
r
o
m
i
s
i
n
g
co
m
p
u
t
a
t
i
o
n
a
l
e
f
f
i
c
i
en
c
y
.
I
n
s
u
m
m
a
r
y
,
Va
l
v
e
H
ea
l
t
h
N
e
t
r
e
p
r
e
s
e
n
t
s
a
p
r
o
m
i
s
i
n
g
s
t
ep
t
o
w
a
r
d
A
I
-
e
n
a
b
l
ed
au
s
c
u
l
t
a
t
io
n
,
o
f
f
er
i
n
g
a
p
r
a
c
t
i
c
a
l
,
a
c
cu
r
a
t
e
,
a
n
d
s
c
a
l
ab
l
e
ap
p
r
o
a
c
h
f
o
r
ea
r
ly
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
s
s
i
f
i
ca
t
i
o
n
o
f
V
H
D
.
W
i
t
h
f
u
r
t
h
er
v
a
l
id
a
t
i
o
n
a
n
d
r
e
f
in
e
m
en
t
,
i
t
h
a
s
t
h
e
p
o
t
en
t
i
a
l
t
o
t
r
an
s
f
o
r
m
r
o
u
t
in
e
c
a
r
d
i
ac
s
cr
e
en
i
n
g
,
i
m
p
r
o
v
e
p
a
t
i
e
n
t
o
u
t
c
o
m
e
s
th
r
o
u
g
h
e
ar
l
ie
r
d
i
ag
n
o
s
i
s
,
an
d
ex
p
an
d
a
cc
e
s
s
t
o
h
ig
h
-
q
u
a
l
i
t
y
c
a
r
d
io
v
a
s
cu
l
a
r
c
ar
e
g
l
o
b
a
l
l
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Au
s
ilah
Alf
r
aih
at
✓
✓
✓
✓
✓
✓
✓
✓
W
af
aa
Al
-
Sh
ar
u
✓
✓
✓
A
l
i
M
o
h
a
m
m
a
d
Al
q
u
d
a
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.