I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
,
p
p
.
361
~
3
7
2
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
14
.
i
2
.
pp
361
-
3
7
2
361
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
A review
on ische
mic hea
rt
disea
se
prediction
f
ra
me
wo
rks usin
g
ma
chine learning
K
a
bo
Clif
f
o
rd
B
hend
e,
T
s
hi
a
m
o
Sig
wele
,
Cha
nd
a
piwa
M
o
k
g
et
hi,
Ao
ne
M
a
eng
e,
Venu Ma
d
ha
v
K
utha
di
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
i
n
g
a
n
d
I
n
f
o
r
m
a
t
i
c
s,
F
a
c
u
l
t
y
o
f
P
u
r
e
a
n
d
A
p
p
l
i
e
d
S
c
i
e
n
c
e
,
B
o
t
sw
a
n
a
I
n
t
e
r
n
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
P
a
l
a
p
y
e
,
B
o
t
sw
a
n
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
19
,
2
0
2
4
R
ev
is
ed
Feb
22
,
2
0
2
5
Acc
ep
ted
Mar
28
,
2
0
2
5
Isc
h
e
m
ic
h
e
a
rt
d
ise
a
se
(IHD
)
is
a
lea
d
in
g
c
a
u
se
o
f
m
o
rtalit
y
w
o
rld
wi
d
e
,
c
a
ll
in
g
fo
r
a
d
v
a
n
c
e
d
p
re
d
icti
v
e
m
o
d
e
ls
fo
r
ti
m
e
ly
i
n
terv
e
n
ti
o
n
.
Cu
rre
n
t
li
tera
tu
re
re
v
iew
s
o
n
m
a
c
h
in
e
lea
rn
in
g
(
ML
)
-
b
a
se
d
IHD
p
re
d
ictio
n
fra
m
e
wo
rk
s
o
ften
fo
c
u
s
o
n
p
re
d
i
c
ti
v
e
a
c
c
u
ra
c
y
b
u
t
lac
k
d
e
p
th
i
n
a
re
a
s
li
k
e
d
a
tas
e
t
d
iv
e
rsity
,
m
o
d
e
l
i
n
terp
re
t
a
b
il
it
y
,
a
n
d
p
riv
a
c
y
c
o
n
sid
e
ra
ti
o
n
s.
Ex
isti
n
g
IHD
p
re
d
ictio
n
fra
m
e
wo
rk
s
fa
c
e
li
m
it
a
ti
o
n
s,
i
n
c
lu
d
in
g
re
li
a
n
c
e
o
n
sm
a
ll
,
h
o
m
o
g
e
n
o
u
s
d
a
tas
e
ts,
li
m
it
e
d
c
rit
ica
l
a
n
a
ly
sis,
a
n
d
issu
e
s
w
it
h
m
o
d
e
l
tran
sp
a
re
n
c
y
,
re
d
u
c
in
g
th
e
ir
c
li
n
i
c
a
l
u
ti
li
ty
.
Th
is
re
v
iew
a
d
d
re
ss
e
s
th
e
se
g
a
p
s
th
ro
u
g
h
a
sy
ste
m
a
ti
c
,
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
o
f
p
o
p
u
lar
M
L
m
o
d
e
l
s,
su
c
h
a
s
ra
n
d
o
m
f
o
re
st
(RF
)
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
s
(S
VM)
,
n
o
ti
n
g
th
e
ir
stre
n
g
th
s
a
n
d
li
m
it
a
ti
o
n
s.
Ke
y
c
o
n
tri
b
u
ti
o
n
s
i
n
c
lu
d
e
a
q
u
a
li
tativ
e
e
x
a
m
in
a
ti
o
n
o
f
p
re
v
a
len
t
to
o
ls,
d
a
tas
e
ts,
a
n
d
e
v
a
lu
a
ti
o
n
m
e
tri
c
s,
id
e
n
ti
fica
ti
o
n
o
f
g
a
p
s
i
n
d
a
t
a
se
t
d
iv
e
rsity
a
n
d
i
n
terp
re
tab
i
li
ty
;
a
n
d
re
c
o
m
m
e
n
d
a
ti
o
n
s fo
r
imp
r
o
v
in
g
m
o
d
e
l
tran
sp
a
re
n
c
y
a
n
d
d
a
ta p
ri
v
a
c
y
.
M
a
jo
r
fin
d
i
n
g
s
re
v
e
a
l
a
tren
d
t
o
wa
rd
e
n
se
m
b
le
m
o
d
e
ls
fo
r
a
c
c
u
ra
c
y
b
u
t
h
ig
h
li
g
h
t
th
e
n
e
e
d
fo
r
e
x
p
lai
n
a
b
le
a
rti
fi
c
ial
in
telli
g
e
n
c
e
(
AI
)
to
su
p
p
o
rt
c
li
n
ica
l
d
e
c
isio
n
s.
F
u
tu
re
d
irec
ti
o
n
s
i
n
c
lu
d
e
u
sin
g
fe
d
e
ra
ted
lea
rn
in
g
to
e
n
h
a
n
c
e
d
a
ta
p
riv
a
c
y
,
i
n
teg
ra
ti
n
g
u
n
stru
c
tu
re
d
d
a
ta
f
o
r
c
o
m
p
re
h
e
n
si
v
e
p
re
d
ic
ti
o
n
,
a
n
d
a
d
v
a
n
c
in
g
e
x
p
lai
n
a
b
le
AI
t
o
b
u
il
d
tru
st
a
m
o
n
g
h
e
a
lt
h
c
a
re
p
r
o
v
id
e
rs.
B
y
a
d
d
re
ss
in
g
t
h
e
se
a
re
a
s,
th
is
re
v
i
e
w
a
ims
to
g
u
id
e
fu
t
u
re
re
se
a
rc
h
t
o
wa
rd
d
e
v
e
lo
p
in
g
r
o
b
u
st,
tran
sp
a
re
n
t
M
L
fra
m
e
wo
rk
s
t
h
a
t
c
a
n
b
e
m
o
re
e
ffe
c
ti
v
e
ly
d
e
p
lo
y
e
d
i
n
c
li
n
ica
l
se
tt
in
g
s.
K
ey
w
o
r
d
s
:
E
ar
ly
d
etec
tio
n
Hea
lth
ca
r
e
I
s
ch
em
ic
d
is
ea
s
e
p
r
ed
ictio
n
Ma
ch
in
e
lear
n
in
g
Pre
d
ictio
n
f
r
am
ewo
r
k
s
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
s
h
iam
o
Sig
wele
Dep
ar
tm
en
t o
f
C
o
m
p
u
tin
g
an
d
I
n
f
o
r
m
atics,
Facu
lty
o
f
Pu
r
e
a
n
d
Ap
p
lied
Scien
ce
B
o
ts
wan
a
I
n
ter
n
atio
n
al
Un
iv
e
r
s
ity
o
f
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
Plo
t 1
0
0
7
1
,
B
o
s
eja,
Palap
y
e,
B
o
ts
wan
a
E
m
ail:
s
ig
wele
t
@
b
iu
s
t.a
c.
b
w
1.
I
NT
RO
D
UCT
I
O
N
I
s
ch
em
ic
h
ea
r
t
d
is
ea
s
e
(
I
HD
)
is
a
lead
in
g
ca
u
s
e
o
f
m
o
r
tality
wo
r
ld
wid
e
am
o
n
g
ca
r
d
i
o
v
a
s
cu
lar
d
is
ea
s
es
(
C
V
D)
,
r
esp
o
n
s
ib
le
f
o
r
ap
p
r
o
x
im
ately
9
m
illi
o
n
d
e
ath
s
an
n
u
ally
[
1
]
.
Hea
r
t
d
is
ea
s
es c
an
g
o
u
n
n
o
ticed
u
n
til
a
h
ea
r
t
attac
k
o
cc
u
r
s
,
wh
ich
m
ay
th
en
ca
u
s
e
s
y
m
p
t
o
m
s
s
u
ch
as
d
is
co
m
f
o
r
t
in
t
h
e
ch
est,
a
b
u
r
n
in
g
s
en
s
atio
n
lik
e
h
ea
r
tb
u
r
n
,
d
i
g
e
s
tiv
e
u
p
s
et,
d
if
f
icu
lty
b
r
ea
th
in
g
,
a
r
ac
in
g
o
r
i
r
r
eg
u
la
r
h
ea
r
tb
ea
t,
an
d
s
w
ellin
g
in
ar
ea
s
lik
e
th
e
f
ee
t,
an
k
les,
o
r
ab
d
o
m
e
n
[
2
]
.
E
ar
l
y
d
etec
tio
n
an
d
p
r
ed
ictio
n
o
f
I
HD
ar
e
cr
u
cial
to
ef
f
ec
tiv
ely
ad
d
r
ess
th
e
n
ee
d
s
o
f
in
d
iv
id
u
als
at
r
is
k
f
o
r
ca
r
d
io
v
ascu
lar
illn
ess
es.
Dete
ctin
g
o
r
p
r
ed
ictin
g
I
HD
ea
r
ly
p
r
esen
ts
a
s
ig
n
if
ican
t
ch
alle
n
g
e
in
h
ea
lth
ca
r
e
[
2
]
.
T
r
ad
itio
n
al
I
HD
p
r
ed
ic
tio
n
m
eth
o
d
s
,
s
u
ch
as
th
e
Fra
m
in
g
h
am
r
is
k
s
co
r
e
(
FR
S)
,
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
m
o
d
els,
an
d
C
o
x
p
r
o
p
o
r
tio
n
al
h
az
ar
d
s
m
o
d
els,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
6
1
-
372
362
co
n
tr
ib
u
ted
s
ig
n
if
ican
tly
b
y
e
s
tab
lis
h
in
g
r
is
k
f
ac
to
r
-
b
ased
p
r
ed
ictio
n
,
allo
win
g
ea
r
ly
p
r
ev
en
tio
n
s
tr
ateg
ies.
Ho
wev
er
,
th
ey
h
av
e
lim
ited
a
cc
u
r
ac
y
,
ar
e
p
r
o
n
e
to
er
r
o
r
s
,
ar
e
co
s
tly
,
r
eso
u
r
ce
in
ten
s
iv
e,
an
d
d
ep
en
d
h
ea
v
il
y
o
n
clin
ical
ass
ess
m
en
ts
an
d
in
v
asiv
e
p
r
o
ce
d
u
r
es
an
d
all
th
is
ca
n
d
elay
ea
r
ly
in
ter
v
en
tio
n
,
in
cr
ea
s
in
g
m
o
r
talit
y
r
is
k
[
3
]
.
R
esear
ch
er
s
h
av
e
e
x
p
lo
r
ed
v
ar
i
o
u
s
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
d
iag
n
o
s
tic
m
eth
o
d
s
to
en
h
an
ce
I
HD
p
r
ed
ictio
n
a
n
d
p
r
o
g
n
o
s
is
ac
cu
r
ac
y
,
ad
d
r
ess
in
g
th
e
wea
k
n
ess
es
o
f
tr
ad
itio
n
al
ap
p
r
o
ac
h
es
b
u
t
th
er
e
s
till
ex
is
t
s
ig
n
if
ican
t sh
o
r
tco
m
in
g
s
with
p
er
s
is
t
e
n
t g
ap
s
an
d
u
n
r
eso
lv
ed
is
s
u
es.
T
ab
le
1
p
r
esen
ts
an
o
v
e
r
v
ie
w
o
f
s
o
m
e
o
f
th
e
p
r
ev
i
o
u
s
ly
p
u
b
lis
h
ed
liter
atu
r
e
r
e
v
iews
o
n
I
HD
d
iag
n
o
s
is
u
s
in
g
ML
ap
p
r
o
ac
h
es
co
m
p
ar
ab
le
to
o
u
r
p
r
o
p
o
s
ed
r
ev
iew.
T
h
e
m
ajo
r
f
in
d
in
g
s
in
d
icate
th
at
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
s
ef
f
ec
tiv
ely
s
u
p
p
o
r
t
I
HD
clin
ica
l
d
ec
is
io
n
s
,
with
v
ar
io
u
s
m
o
d
els
d
em
o
n
s
tr
atin
g
p
o
ten
tial
as
d
ec
is
io
n
aid
s
d
u
e
to
d
if
f
er
in
g
p
r
ed
ictio
n
ac
cu
r
a
cies.
I
n
ter
n
et
o
f
th
in
g
(
I
o
T
)
in
teg
r
atio
n
en
h
a
n
ce
s
p
r
ed
ictio
n
ac
cu
r
ac
y
in
C
VD
co
n
tex
ts
,
wh
ile
f
ea
tu
r
e
s
elec
tio
n
is
cr
itical
f
o
r
o
p
tim
izin
g
ML
m
o
d
els.
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NN
s
)
h
av
e
s
h
o
wn
p
ar
tic
u
lar
ly
h
ig
h
ac
c
u
r
ac
y
in
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
.
T
h
e
lim
itatio
n
s
o
f
th
ese
liter
a
tu
r
e
r
ev
iews
in
clu
d
e
i
n
s
u
f
f
ici
en
t
em
p
h
asis
o
n
I
HD
p
r
ed
icti
o
n
.
T
h
e
r
e
is
also
an
o
v
er
all
lack
o
f
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
o
f
th
e
g
ap
s
,
d
atasets
,
to
o
ls
,
ev
alu
atio
n
m
etr
ics,
an
d
p
er
f
o
r
m
an
ce
with
g
r
ap
h
ical
p
r
esen
tatio
n
s
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
liter
atu
r
e
r
ev
iews
o
n
ML
-
b
ased
I
HD
p
r
ed
ictio
n
f
r
am
ewo
r
k
s
A
u
t
h
o
r
O
b
j
e
c
t
i
v
e
M
o
d
e
l
s
D
a
t
a
s
e
t
s
o
u
r
c
e
C
o
n
t
r
i
b
u
t
i
o
n
s
Li
mi
t
a
t
i
o
n
s
a
nd
g
a
p
s
H
a
n
i
a
n
d
A
h
ma
d
[
2
]
A
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
o
f
M
L
a
l
g
o
r
i
t
h
ms f
o
r
I
H
D
p
r
e
d
i
c
t
i
o
n
s
p
e
c
i
f
i
c
a
l
l
y
.
n
a
ï
v
e
B
a
y
e
s,
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
ANN
)
,
d
e
c
i
si
o
n
t
r
e
e
s
D
a
t
a
s
e
t
s fr
o
m
S
c
i
e
n
c
e
D
i
r
e
c
t
,
P
u
b
M
e
d
,
C
I
N
A
H
L,
I
EEE
X
p
l
o
r
e
S
u
p
e
r
v
i
se
d
M
L
a
l
g
o
r
i
t
h
ms f
o
u
n
d
e
f
f
e
c
t
i
v
e
i
n
a
i
d
i
n
g
I
H
D
c
l
i
n
i
c
a
l
d
e
c
i
s
i
o
n
s.
N
o
c
o
m
p
r
e
h
e
n
si
v
e
a
n
a
l
y
si
s
o
f
g
a
p
s,
d
a
t
a
se
t
s,
t
o
o
l
s
,
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s
,
p
e
r
f
o
r
m
a
n
c
e
B
a
r
a
l
e
t
a
l
.
[
4
]
R
e
v
i
e
w
s
ML
m
o
d
e
l
s
f
o
r
c
a
r
d
i
o
v
a
s
c
u
l
a
r
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
.
S
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
(
S
V
M
)
,
A
N
N
,
d
e
c
i
s
i
o
n
t
r
e
e
s,
r
a
n
d
o
m
f
o
r
e
st
(
RF
)
C
l
i
n
i
c
a
l
d
a
t
a
s
e
t
s
w
i
t
h
p
a
t
i
e
n
t
d
e
m
o
g
r
a
p
h
i
c
s
a
n
d
d
i
a
g
n
o
st
i
c
t
e
s
t
s
D
i
f
f
e
r
e
n
t
M
L
m
o
d
e
l
s
h
a
v
e
sh
o
w
n
v
a
r
y
i
n
g
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
i
e
s
,
su
g
g
e
st
i
n
g
p
o
t
e
n
t
i
a
l
a
s
c
l
i
n
i
c
a
l
d
e
c
i
s
i
o
n
a
i
d
s.
Li
mi
t
e
d
d
i
s
c
u
ssi
o
n
o
n
I
H
D
,
l
a
c
k
s
a
n
a
l
y
s
i
s
o
f
g
a
p
s,
d
a
t
a
s
e
t
s
,
t
o
o
l
s
,
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s
,
a
n
d
p
e
r
f
o
r
m
a
n
c
e
.
R
a
o
a
n
d
M
u
n
e
e
sw
a
r
i
[
5
]
A
r
e
v
i
e
w
o
f
M
L
a
p
p
l
i
c
a
t
i
o
n
s f
o
r
h
e
a
r
t
d
i
s
e
a
se
p
r
e
d
i
c
t
i
o
n
v
i
a
I
o
T
X
G
B
o
o
st
,
S
V
M
,
A
d
a
B
o
o
st
,
RF
,
LR
U
C
I
h
e
a
r
t
d
i
se
a
se
d
a
t
a
se
t
,
C
l
e
v
e
l
a
n
d
d
a
t
a
se
t
,
a
n
d
h
o
s
p
i
t
a
l
d
a
t
a
H
i
g
h
l
i
g
h
t
s
I
o
T
i
n
t
e
g
r
a
t
i
o
n
o
n
i
mp
r
o
v
i
n
g
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
i
e
s
f
o
r
C
V
D
.
La
c
k
s
d
e
t
a
i
l
s
o
n
I
H
D
-
sp
e
c
i
f
i
c
p
r
e
d
i
c
t
o
r
s a
n
d
p
r
a
c
t
i
c
a
l
i
m
p
l
e
m
e
n
t
a
t
i
o
n
i
n
s
i
g
h
t
s.
N
a
ser
e
t
a
l
.
[
6
]
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
M
L
i
n
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
.
X
G
B
o
o
st
,
S
V
M
,
RF
,
C
N
N
,
l
o
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
M
u
l
t
i
p
l
e
d
a
t
a
b
a
ses
,
i
n
c
l
u
d
i
n
g
P
u
b
M
e
d
,
S
c
i
e
n
c
e
D
i
r
e
c
t
M
L
m
o
d
e
l
s
i
mp
r
o
v
e
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
,
w
i
t
h
c
a
l
l
s fo
r
f
e
a
t
u
r
e
sel
e
c
t
i
o
n
i
m
p
o
r
t
a
n
c
e
.
D
o
e
s
n
o
t
e
m
p
h
a
si
z
e
I
H
D
,
n
o
g
r
a
p
h
i
c
a
l
a
n
a
l
y
si
s
o
f
l
i
m
i
t
a
t
i
o
n
s,
mo
d
e
l
s,
t
o
o
l
s,
o
r
o
b
j
e
c
t
i
v
e
s
.
A
h
sa
n
a
n
d
S
i
d
d
i
q
u
e
[
7
]
R
e
v
i
e
w
s
M
L
a
p
p
r
o
a
c
h
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s i
n
C
V
D
d
i
a
g
n
o
si
s.
n
a
ï
v
e
B
a
y
e
s,
d
e
c
i
si
o
n
t
r
e
e
s
,
C
N
N
,
J
4
8
S
c
o
p
u
s
d
a
t
a
se
t
c
o
v
e
r
i
n
g
m
u
l
t
i
p
l
e
st
u
d
i
e
s
o
n
h
e
a
r
t
d
i
s
e
a
se
C
N
N
sh
o
w
s
h
i
g
h
a
c
c
u
r
a
c
y
i
n
h
e
a
r
t
d
i
s
e
a
se
.
N
o
a
n
a
l
y
si
s
o
f
g
a
p
s,
d
a
t
a
se
t
s,
t
o
o
l
s,
e
v
a
l
u
a
t
i
o
n
met
r
i
c
s,
o
r
p
e
r
f
o
r
ma
n
c
e
,
a
n
d
n
o
f
o
c
u
s
o
n
I
H
D
p
r
e
d
i
c
t
i
o
n
.
P
r
o
p
o
se
d
(
Th
i
s
r
e
v
i
e
w
)
C
o
m
p
r
e
h
e
n
si
v
e
,
C
o
m
p
a
r
a
t
i
v
e
,
Q
u
a
l
i
t
a
t
i
v
e
,
S
y
st
e
ma
t
i
c
,
a
nd
gr
a
p
h
i
c
a
l
a
n
a
l
y
t
i
c
a
l
r
e
v
i
e
w
o
f
M
L
-
b
a
se
d
I
H
D
p
r
e
d
i
c
t
i
o
n
s.
n
a
ï
v
e
B
a
y
e
s,
A
N
N
,
d
e
c
i
s
i
o
n
t
r
e
e
s
,
S
V
M
,
RF
,
X
G
B
o
o
st
,
A
d
a
B
o
o
st
,
C
N
N
J4
8
,
a
n
d
k
-
n
e
a
r
e
st
n
e
i
g
h
b
o
u
r
.
I
EEE
X
p
l
o
r
e
,
S
c
i
e
n
c
e
D
i
r
e
c
t
,
S
c
o
p
u
s
,
P
u
b
m
e
d
,
K
a
g
g
l
e
,
C
l
e
v
e
l
a
n
d
,
S
t
a
t
l
o
g
,
U
C
I
C
l
e
v
e
l
a
n
d
,
a
n
d
h
o
s
p
i
t
a
l
d
a
t
a
.
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
M
L
m
o
d
e
l
s
,
q
u
a
l
i
t
a
t
i
v
e
a
n
a
l
y
si
s
o
f
k
e
y
t
r
e
n
d
s
a
n
d
g
a
p
s
,
mo
st
a
d
o
p
t
e
d
t
o
o
l
s
a
n
d
met
r
i
c
s,
g
u
i
d
a
n
c
e
f
o
r
f
u
t
u
r
e
r
e
s
e
a
r
c
h
Ex
c
l
u
d
e
n
o
n
-
E
n
g
l
i
s
h
st
u
d
i
e
s w
h
i
c
h
ma
y
l
i
m
i
t
g
l
o
b
a
l
i
n
si
g
h
t
s
i
n
t
o
I
H
D
p
r
e
d
i
c
t
i
o
n
,
f
o
c
u
s
o
n
st
r
u
c
t
u
r
e
d
d
a
t
a
o
v
e
r
l
o
o
k
v
a
l
u
a
b
l
e
u
n
st
r
u
c
t
u
r
e
d
so
u
r
c
e
s f
o
r
p
r
e
d
i
c
t
i
o
n
.
W
ith
th
e
ex
is
ten
ce
o
f
u
n
s
o
l
v
ed
is
s
u
es
in
p
r
e
v
io
u
s
liter
atu
r
e
r
ev
iews,
th
er
e
is
a
n
ee
d
f
o
r
a
co
m
p
r
eh
e
n
s
iv
e,
co
m
p
a
r
ativ
e
,
an
d
an
aly
tical
r
ev
iew
of
I
HD
p
r
ed
ictio
n
f
r
am
ewo
r
k
s
.
T
h
is
r
esear
ch
will
aim
to
ad
d
r
ess
th
e
s
h
o
r
tco
m
in
g
s
of
e
ar
lier
liter
atu
r
e
r
ev
iews
b
y
p
e
r
f
o
r
m
in
g
a
co
m
p
r
eh
e
n
s
iv
e
lite
r
atu
r
e
r
ev
iew
with
cr
itical
an
aly
s
is
,
d
is
cu
s
s
io
n
s
,
co
m
p
ar
is
o
n
s
,
an
d
in
ter
p
r
etatio
n
s
,
th
en
d
ed
u
ci
n
g
tr
e
n
d
s
,
p
a
tte
r
ns
,
an
d
in
s
ig
h
ts
an
d
g
r
ap
h
ica
l
ly
s
u
m
m
ar
i
z
in
g
th
e
k
ey
f
in
d
i
n
g
s
to
g
eth
e
r
wi
th
f
in
d
in
g
r
am
if
icatio
n
s
an
d
s
tatin
g
th
e
r
esear
ch
h
an
d
in
ess
in
f
u
tu
r
e
.
Fu
r
th
e
r
m
o
r
e,
as
t
h
e
p
a
p
er
f
o
cu
s
es
o
n
ML
tech
n
iq
u
es,
co
m
p
ar
at
iv
e
an
aly
s
is
o
f
th
e
m
o
d
els,
g
ap
s
,
o
b
jectiv
es,
to
o
ls
,
d
atasets
,
co
n
tr
ib
u
tio
n
s
,
an
d
p
e
r
f
o
r
m
an
ce
o
f
v
a
r
io
u
s
ML
tech
n
iq
u
es
ar
e
s
u
m
m
ar
ized
in
tab
u
lar
f
o
r
m
.
Fin
ally
,
th
e
ar
ticle
o
f
f
er
s
s
o
m
e
p
o
ten
tial
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
in
ML
-
b
ased
I
HD
p
r
ed
ictio
n
.
T
h
e
f
o
llo
win
g
ar
e
th
e
co
n
tr
ib
u
tio
n
s
o
f
th
is
r
e
s
ea
r
ch
wo
r
k
:
i)
C
o
m
p
r
eh
en
s
iv
e
c
o
m
p
ar
ativ
e
an
aly
s
is
o
f
ML
m
o
d
els
,
t
h
is
r
ev
iew
th
o
r
o
u
g
h
ly
co
m
p
ar
e
s
p
o
p
u
lar
ML
m
o
d
els,
s
u
ch
a
s
RF
,
SVM
,
a
n
d
C
NN
,
as
s
es
s
in
g
th
eir
s
tr
e
n
g
th
s
,
lim
itatio
n
s
,
an
d
clin
ical
ap
p
licab
ilit
y
,
an
d
g
u
i
d
in
g
r
esear
ch
er
s
in
s
el
ec
tin
g
s
u
itab
le
m
o
d
els f
o
r
I
H
D
p
r
ed
ictio
n
.
ii)
Qu
alitativ
e
an
aly
s
is
o
f
k
ey
tr
en
d
s
an
d
g
a
p
s
,
t
he
p
ap
er
i
d
e
n
tifie
s
r
ec
u
r
r
in
g
g
ap
s
,
lik
e
lim
ited
d
ataset
d
iv
er
s
ity
,
in
ter
p
r
etab
ilit
y
ch
all
en
g
es,
an
d
p
r
iv
ac
y
is
s
u
es,
wh
ile
h
ig
h
lig
h
tin
g
r
esear
ch
o
b
je
ctiv
es
s
u
ch
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
r
ev
iew
o
n
is
ch
emic
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
fr
a
mewo
r
ks u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
K
a
b
o
C
liff
o
r
d
B
h
en
d
e
)
363
im
p
r
o
v
in
g
p
r
e
d
ictio
n
ac
c
u
r
a
cy
an
d
p
r
o
v
id
in
g
a
r
o
ad
m
a
p
f
o
r
a
d
d
r
ess
in
g
cr
itical
I
H
D
p
r
ed
ictio
n
ch
allen
g
es.
iii)
I
d
en
tific
atio
n
o
f
m
o
s
t
ad
o
p
te
d
to
o
ls
a
n
d
m
etr
ics
,
t
h
is
r
ev
iew
d
o
cu
m
en
ts
co
m
m
o
n
ly
u
s
ed
to
o
ls
(
e.
g
.
,
Py
th
o
n
lib
r
a
r
ies
an
d
W
ek
a)
a
n
d
ev
alu
atio
n
m
etr
ics
(
e.
g
.
,
F1
-
s
co
r
e
an
d
s
en
s
itiv
ity
)
,
o
f
f
e
r
in
g
g
u
id
a
n
ce
o
n
ef
f
ec
tiv
e
r
eso
u
r
ce
s
a
n
d
m
etr
ic
s
,
p
r
o
m
o
tin
g
co
n
s
is
ten
cy
a
n
d
co
m
p
ar
ab
ilit
y
ac
r
o
s
s
ML
I
HD
s
tu
d
ies.
iv
)
Gu
id
an
ce
f
o
r
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
,
t
h
e
p
ap
er
s
u
g
g
ests
in
teg
r
atin
g
ex
p
lain
a
b
le
AI
tech
n
iq
u
es
f
o
r
tr
an
s
p
ar
en
cy
a
n
d
f
ed
er
ated
lear
n
i
n
g
f
o
r
d
ata
p
r
i
v
ac
y
,
e
n
h
a
n
cin
g
m
o
d
el
r
eliab
ilit
y
,
i
n
ter
p
r
etab
ilit
y
,
an
d
eth
ical
ap
p
licab
ilit
y
,
th
er
e
b
y
a
d
v
an
cin
g
th
e
clin
ical
r
elev
a
n
c
e
o
f
ML
m
o
d
els in
I
HD
p
r
e
d
ic
tio
n
.
T
h
e
p
ap
er
is
s
tr
u
ctu
r
ed
as
f
o
llo
ws:
th
e
m
eth
o
d
o
lo
g
y
s
ec
tio
n
p
r
o
v
i
d
es
a
d
etailed
ac
co
u
n
t
o
f
th
e
m
o
d
el
s
elec
tio
n
an
d
ev
al
u
atio
n
p
r
o
ce
s
s
es,
with
a
s
tr
o
n
g
em
p
h
asis
o
n
in
ter
p
r
eta
b
ilit
y
,
d
ata
p
r
e
p
r
o
ce
s
s
in
g
,
an
d
eth
ical
d
ata
h
an
d
lin
g
p
r
ac
ti
ce
s
.
T
h
e
r
esu
lts
s
ec
tio
n
p
r
esen
ts
a
co
m
p
ar
ativ
e
an
aly
s
is
o
f
ML
m
o
d
els,
u
n
d
er
s
co
r
i
n
g
t
h
eir
ac
c
u
r
ac
y
,
i
n
ter
p
r
etab
ilit
y
,
an
d
r
elev
a
n
ce
f
o
r
clin
ical
s
ettin
g
s
.
T
h
e
d
is
cu
s
s
io
n
th
en
e
x
p
lo
r
es
th
e
b
r
o
ad
e
r
im
p
licatio
n
s
o
f
th
ese
f
in
d
in
g
s
,
ad
d
r
ess
es
p
r
iv
ac
y
an
d
eth
ical
co
n
s
id
er
ati
o
n
s
,
an
d
s
u
g
g
ests
p
o
ten
tial f
u
tu
r
e
d
ir
ec
tio
n
s
f
o
r
ML
-
b
ased
I
HD
p
r
e
d
ictio
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
r
ev
iew
ad
o
p
ts
a
s
y
s
tem
atic
liter
atu
r
e
r
ev
iew
(
SLR)
m
et
h
o
d
o
lo
g
y
a
d
o
p
te
d
in
[
1
]
,
[
2
]
t
o
en
s
u
r
e
a
co
m
p
r
eh
e
n
s
iv
e,
u
n
b
iased
an
a
ly
s
is
o
f
ex
is
tin
g
ML
f
r
am
ew
o
r
k
s
ap
p
lied
to
I
HD
p
r
ed
icti
o
n
.
T
h
e
s
y
s
tem
atic
ap
p
r
o
ac
h
in
co
r
p
o
r
ates
b
o
th
es
tab
lis
h
ed
r
ev
iew
p
r
ac
tices
an
d
r
ec
en
t
ad
v
an
ce
m
en
ts
in
ML
r
esear
ch
to
ad
d
r
ess
th
e
r
esear
ch
q
u
esti
o
n
s
a
n
d
g
a
p
s
id
en
tifie
d
in
t
h
e
in
tr
o
d
u
cti
o
n
s
ec
tio
n
,
g
u
id
in
g
th
e
r
ea
d
e
r
lo
g
ically
in
to
th
e
r
esu
lts
s
ec
t
io
n
.
T
h
e
SLR’s
p
r
ef
er
r
ed
r
ep
o
r
tin
g
item
s
f
o
r
s
y
s
tem
atic
r
ev
iews
an
d
m
eta
-
an
aly
s
es
(
P
R
I
SMA
)
ap
p
r
o
ac
h
as
s
h
o
w
n
in
Fig
u
r
e
1
was
ch
o
s
en
d
u
e
to
its
s
tr
u
ct
u
r
ed
,
r
ep
licab
le
n
atu
r
e
,
allo
wi
n
g
f
o
r
a
co
n
s
is
ten
t
ass
es
s
m
en
t
ac
r
o
s
s
m
u
ltip
le
s
t
u
d
ies
an
d
en
ab
lin
g
a
clea
r
s
y
n
th
esis
o
f
tr
en
d
s
,
in
s
ig
h
ts
,
an
d
p
atter
n
s
in
ML
ap
p
licatio
n
s
f
o
r
I
HD.
PR
I
SMA
en
s
u
r
es
tr
an
s
p
ar
en
c
y
,
r
e
p
r
o
d
u
cib
ilit
y
,
an
d
r
ig
o
r
o
u
s
r
e
p
o
r
t
in
g
o
f
f
in
d
in
g
s
.
T
h
e
in
clu
s
io
n
o
f
v
is
u
al
s
u
m
m
ar
ies
lik
e
p
ie
ch
ar
ts
s
u
p
p
o
r
ts
th
is
ju
s
tific
atio
n
,
o
f
f
er
in
g
a
clea
r
a
n
d
ev
id
e
n
ce
-
b
ased
f
o
u
n
d
atio
n
f
o
r
u
n
d
er
s
tan
d
i
n
g
ML
’
s
p
o
ten
tial in
p
r
e
d
ictin
g
I
HD
an
d
g
u
id
i
n
g
f
u
tu
r
e
r
esear
ch
in
th
is
d
o
m
ai
n
.
Fig
u
r
e
1
.
PR
I
SMA
f
lo
w
d
iag
r
am
o
f
SLR
Fig
u
r
e
1
s
h
o
ws
th
e
p
r
o
p
o
s
ed
PR
I
SMA
f
lo
w
d
iag
r
am
f
o
r
th
e
SLR.
T
h
e
SLR
f
o
r
I
HD
p
r
ed
ictio
n
u
s
in
g
ML
in
v
o
l
v
ed
m
u
ltip
le
s
tr
u
ctu
r
ed
s
tep
s
.
First,
a
co
m
p
r
eh
en
s
iv
e
liter
atu
r
e
s
ea
r
ch
t
a
r
g
eted
s
tu
d
ies
f
r
o
m
th
e
last
f
iv
e
y
ea
r
s
ac
r
o
s
s
r
ep
u
tab
le
ac
ad
em
ic
d
atab
ases
s
u
ch
as
I
E
E
E
Xp
lo
r
e,
Scien
ce
Dir
ec
t,
Sp
r
in
g
er
L
in
k
,
Ass
o
ciatio
n
o
f
C
o
m
p
u
tin
g
M
ac
h
in
er
y
(
AC
M
)
d
ig
ital
lib
r
ar
y
,
an
d
W
eb
o
f
Scien
ce
.
Key
w
o
r
d
s
lik
e
“m
ac
h
in
e
lear
n
in
g
,
”
“
h
ea
r
t d
is
ea
s
e,
”
“isch
em
ic,
”
“c
ar
d
io
v
ascu
lar
,
”
an
d
“p
r
ed
ictio
n
”
wer
e
u
s
ed
in
v
a
r
io
u
s
co
m
b
in
atio
n
s
,
r
esu
ltin
g
in
9
9
5
in
itial
ar
ticles.
Nex
t,
in
clu
s
io
n
a
n
d
ex
cl
u
s
io
n
cr
iter
ia
wer
e
ap
p
lied
to
m
ai
n
tain
r
elev
an
ce
an
d
ac
cu
r
ac
y
.
Ar
ticles
wer
e
in
cl
u
d
ed
i
f
th
ey
f
o
c
u
s
ed
o
n
M
L
tech
n
i
q
u
es
f
o
r
I
HD
p
r
ed
i
ctio
n
an
d
ad
d
r
ess
ed
p
er
f
o
r
m
an
ce
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all.
Ar
ticles
u
n
r
elate
d
to
ML
,
I
HD,
o
r
lack
in
g
P
o
t
e
nt
i
a
l
Ar
t
i
cl
e
s
(
N
=
2
1
4
)
E
x
cl
ude
d
Ar
t
i
cl
e
s
(
N
=
2
1
0
)
Ar
t
i
cl
e
s
I
de
nt
i
f
i
ca
t
i
on
(
N
=
9
9
5
)
D
a
t
a
ba
s
e
s
A
C
M
Di
g
it
a
l
L
ib
r
a
r
y
I
E
E
E
X
p
lo
r
e
Sc
ie
n
c
e
Dir
e
c
t
S
p
r
i
n
g
e
r
Li
n
k
E
x
c
lu
d
e
d
a
r
t
ic
le
s
a
ft
e
r
a
n
a
ly
s
is
o
f
t
it
l
e
s
,
a
b
s
t
r
a
c
t
s
,
k
e
y
w
o
r
d
s
:
(
N
=
7
8
1
)
•
I
n
a
d
e
q
u
a
t
e
M
o
d
e
l
t
e
r
m
s
•
L
a
c
k
C
lin
ic
a
l
A
p
p
lic
a
b
ilit
y
A
r
t
i
c
l
e
s
I
de
nt
i
f
i
e
d
w
i
t
h
k
e
y
w
o
r
d
M
a
c
h
in
e
L
e
a
r
n
in
g
A
N
D
I
s
c
h
e
m
ic
H
e
a
r
t
Dis
e
a
s
e
A
N
D
P
r
e
d
ic
t
io
n
(
N
=
9
9
5
)
O
R
T
e
r
m
s
u
s
e
d
w
h
e
n
n
o
r
e
s
u
lt
s
fo
u
n
d
O
R
A
r
t
ific
ia
l
I
n
t
e
lig
e
n
c
e
A
N
D
O
R
C
a
r
d
io
v
a
s
c
u
la
r
A
N
D
O
R
Dia
g
n
o
s
is
O
R
A
s
s
e
s
m
e
n
t
E
x
c
lu
d
e
d
a
r
t
ic
le
s
a
ft
e
r
a
n
a
ly
s
is
t
h
e
c
o
m
p
le
t
e
a
r
t
ic
le
:
(
N
=
1
9
0
)
•
N
o
fit
t
in
g
o
b
j
e
c
t
iv
e
s
•
N
o
r
e
la
t
io
n
w
i
t
h
r
e
s
e
a
r
c
h
t
o
p
ic
•
N
o
q
u
a
lit
y
e
v
a
lu
a
t
io
n
I
n
c
lu
d
e
d
A
r
t
ic
le
s
(
N
=
2
4
)
T
i
m
e
f
r
a
m
e
P
a
s
t
5
y
e
a
r
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
6
1
-
372
364
p
r
ed
ictiv
e
m
o
d
elin
g
f
o
cu
s
o
r
m
o
d
el
ev
alu
atio
n
m
etr
ics,
wer
e
ex
clu
d
ed
.
T
h
is
p
r
o
c
ess
n
ar
r
o
wed
d
o
wn
th
e
p
o
o
l
to
2
1
4
p
o
ten
tial
ar
ticles.
Data
ex
tr
ac
tio
n
f
o
llo
wed
,
g
ath
e
r
in
g
ess
en
tial
in
f
o
r
m
atio
n
o
n
a
u
th
o
r
s
,
p
u
b
licatio
n
y
ea
r
,
ML
m
o
d
els,
r
esear
ch
o
b
jectiv
es,
ev
alu
atio
n
m
etr
ics,
lim
itatio
n
s
,
d
atasets
,
an
d
to
o
ls
,
wh
ich
r
ed
u
ce
d
th
e
ar
ticles
f
u
r
th
er
to
2
4
an
d
t
h
is
d
ata
wa
s
th
e
n
ta
b
u
lated
.
Fin
ally
,
d
ata
a
n
aly
s
is
an
d
v
is
u
aliza
tio
n
wer
e
p
er
f
o
r
m
ed
.
Qu
a
n
titativ
e
an
aly
s
is
,
in
clu
d
in
g
p
ie
ch
ar
ts
,
h
ig
h
lig
h
ted
tr
en
d
s
in
ML
m
o
d
els,
d
atasets
,
an
d
p
er
f
o
r
m
an
ce
m
etr
ics,
wh
ile
q
u
alitativ
e
an
aly
s
is
id
en
tifie
d
g
ap
s
,
s
u
ch
as
lim
ited
d
at
aset
d
iv
er
s
i
ty
an
d
in
ter
p
r
etab
ilit
y
ch
allen
g
es.
T
h
is
s
tr
u
ctu
r
ed
ap
p
r
o
ac
h
en
s
u
r
ed
tr
an
s
p
ar
en
cy
an
d
r
e
p
licab
ilit
y
,
p
r
o
v
id
i
n
g
a
clea
r
r
o
ad
m
ap
f
o
r
f
u
tu
r
e
r
esear
ch
i
n
ML
ap
p
licatio
n
s
f
o
r
I
HD
p
r
e
d
ictio
n
.
3.
RE
L
AT
E
D
WO
RK
S O
N
M
L
-
B
AS
E
D
I
H
D
P
RE
D
I
CT
I
O
N
T
ab
le
2
p
r
o
v
id
es
a
co
n
cise
y
et
co
m
p
r
e
h
en
s
iv
e
o
v
er
v
iew
o
f
1
0
o
f
th
e
f
i
n
al
s
elec
tio
n
o
f
2
4
ar
ticles
o
r
g
an
ized
in
to
a
tab
le
f
o
r
m
a
t
to
en
ab
le
s
tr
u
ctu
r
ed
an
aly
s
i
s
later
.
Data
ex
tr
ac
tio
n
in
v
o
lv
ed
g
at
h
er
in
g
k
ey
d
etails
s
u
ch
as
au
th
o
r
n
am
es,
p
u
b
licatio
n
y
ea
r
,
ML
m
o
d
els,
r
esear
ch
o
b
jectiv
es,
e
v
alu
atio
n
m
etr
ics,
lim
itatio
n
s
,
d
atasets
,
an
d
to
o
ls
.
T
h
is
d
ata
was
s
y
s
tem
atica
l
ly
s
elec
ted
u
s
in
g
th
e
PR
I
SM
A
m
eth
o
d
,
f
ilter
in
g
ar
ticles b
ased
o
n
r
elev
a
n
ce
,
q
u
ality
,
an
d
f
o
cu
s
o
n
I
HD
p
r
ed
ic
tio
n
.
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
tab
u
lati
o
n
o
f
r
elate
d
wo
r
k
s
o
n
ML
-
b
a
s
ed
I
HD
p
r
ed
ictio
n
S
.
N
A
u
t
h
o
r
s
ML
m
o
d
e
l
R
e
se
a
r
c
h
o
b
j
e
c
t
i
v
e
s
Ev
a
l
u
a
t
i
o
n
me
t
r
i
c
s
a
n
d
p
e
r
f
o
r
m
a
n
c
e
G
a
p
s/
l
i
mi
t
a
t
i
o
n
s
D
a
t
a
s
e
t
a
n
d
t
o
o
l
s
1.
N
a
g
a
v
e
l
l
i
e
t
a
l
.
[
3
]
X
GB
o
o
st
Te
st
d
e
c
i
si
o
n
t
r
e
e
a
l
g
o
r
i
t
h
ms f
o
r
h
e
a
r
t
d
i
s
e
a
se
d
i
a
g
n
o
s
i
s.
A
c
c
u
r
a
c
y
(
9
5
.
9
)
,
p
r
e
c
i
si
o
n
(
9
7
.
1
)
,
r
e
c
a
l
l
(
9
4
.
6
7
)
,
F
1
-
me
a
su
r
e
(
9
5
.
3
5
)
Li
mi
t
e
d
d
a
t
a
s
e
t
s
st
a
n
d
a
r
d
met
r
i
c
s
a
n
d
n
e
e
d
t
o
c
o
n
si
d
e
r
mo
r
e
m
e
t
r
i
c
s
D
a
t
a
s
e
t
s
:
C
l
e
v
e
l
a
n
d
a
n
d
S
t
a
t
l
o
g
.
T
o
o
l
s:
u
n
-
n
a
me
d
w
e
b
a
p
p
l
i
c
a
t
i
o
n
2.
S
h
e
h
z
a
d
i
e
t
a
l
.
[
8
]
RF
D
e
v
e
l
o
p
a
h
i
g
h
l
y
a
c
c
u
r
a
t
e
m
o
d
e
l
.
A
c
c
u
r
a
c
y
(
9
9
)
,
p
r
e
c
i
s
i
o
n
(
1
0
0
)
,
r
e
c
a
l
l
(
1
0
0
)
,
F
1
-
mea
s
u
r
e
(
1
0
0
)
N
e
e
d
t
o
c
o
n
si
d
e
r
d
i
f
f
e
r
e
n
t
i
n
p
u
t
f
e
a
t
u
r
e
s
f
o
r
a
c
c
u
r
a
c
y
,
D
a
t
a
s
e
t
s
:
C
l
e
v
e
l
a
n
d
h
e
a
r
t
d
i
s
e
a
se
U
C
I
.
T
o
o
l
s:
v
a
r
i
o
u
s
l
i
b
r
a
r
i
e
s
3.
M
a
i
n
i
e
t
a
l
.
[
9
]
RF
I
mp
r
o
v
e
e
f
f
i
c
i
e
n
c
y
i
n
p
r
e
d
i
c
t
i
n
g
h
e
a
r
t
a
t
t
a
c
k
r
i
sk
s
.
A
c
c
u
r
a
c
y
(
9
3
.
8
)
,
sen
s
i
t
i
v
i
t
y
(
9
2
.
8
)
,
sp
e
c
i
f
i
c
i
t
y
(
9
4
.
6
)
F
o
c
u
s
o
n
l
y
o
n
c
o
st
-
e
f
f
e
c
t
i
v
e
p
r
e
d
i
c
t
i
o
n
i
n
r
u
r
a
l
I
n
d
i
a
D
a
t
a
s
e
t
:
1
6
7
0
me
d
i
c
a
l
r
e
c
o
r
d
s
.
To
o
l
s:
P
y
t
h
o
n
l
i
b
r
a
r
i
e
s
4.
H
o
sse
n
e
t
a
l
.
[
1
0
]
LR
To
d
e
v
e
l
o
p
a
c
o
m
p
u
t
e
r
-
a
i
d
e
d
d
i
a
g
n
o
st
i
c
s
y
s
t
e
m
A
c
c
u
r
a
c
y
(
9
2
)
,
p
r
e
c
i
s
i
o
n
(
9
2
)
,
r
e
c
a
l
l
(
9
2
)
,
F
-
mea
s
u
r
e
(
9
2
)
Li
mi
t
e
d
d
a
t
a
s
e
t
,
a
f
f
e
c
t
e
d
b
y
l
i
f
e
s
t
y
l
e
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
f
a
c
t
o
r
s
D
a
t
a
s
e
t
s
:
U
C
I
C
l
e
v
e
l
a
n
d
.
To
o
l
s
:
n
o
t
s
p
e
c
i
f
i
e
d
5.
H
a
san
o
v
a
e
t
a
l
.
[
1
1
]
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
u
r
P
r
o
p
o
se
d
a
l
g
o
r
i
t
h
ms
f
o
r
e
f
f
i
c
i
e
n
t
d
e
t
e
c
t
i
o
n
.
A
c
c
u
r
a
c
y
(
8
8
.
7
)
,
p
r
e
c
i
si
o
n
(
9
1
)
,
r
e
c
a
l
l
(
8
8
)
,
F1
-
sc
o
r
e
(
8
5
)
H
i
g
h
o
p
e
r
a
t
i
o
n
a
l
c
o
st
s,
i
n
c
r
e
a
s
e
d
t
r
a
n
sa
c
t
i
o
n
s
,
a
n
d
p
o
o
r
a
c
c
u
r
a
c
y
D
a
t
a
s
e
t
s
:
C
l
e
v
e
l
a
n
d
h
e
a
r
t
d
i
s
e
a
se
U
C
I
r
e
p
o
si
t
o
r
y
.
To
o
l
s
:
n
o
t
s
p
e
c
i
f
i
e
d
6.
H
a
ssan
e
t
a
l
.
[
1
2
]
RF
I
d
e
n
t
i
f
y
k
e
y
f
e
a
t
u
r
e
s
,
f
o
r
I
H
D
p
r
e
d
i
c
t
a
b
i
l
i
t
y
A
c
c
u
r
a
c
y
(
9
6
.
2
8
)
,
sp
e
c
i
f
i
c
i
t
y
(
9
6
.
2
8
)
,
sen
s
i
t
i
v
i
t
y
(
9
5
.
3
7
)
Li
mi
t
e
d
d
a
t
a
s
e
t
s
a
n
d
l
i
mi
t
ed
e
v
a
l
u
a
t
i
o
n
me
t
r
i
c
s.
D
a
t
a
s
e
t
s
:
U
C
I
r
e
p
o
s
i
t
o
r
y
.
To
o
l
s
:
n
o
t
s
p
e
c
i
f
i
e
d
7.
S
a
y
a
d
i
e
t
a
l
.
[
1
3
]
LR
P
r
o
p
o
ses
a
n
e
w
mo
d
e
l
f
o
r
e
a
r
l
y
C
A
D
d
i
a
g
n
o
si
s.
A
c
c
u
r
a
c
y
(
9
5
.
4
5
)
,
sen
s
i
t
i
v
i
t
y
(
9
5
.
9
1
)
,
F
1
sco
r
e
(
9
6
.
9
0
)
I
n
a
d
e
q
u
a
t
e
d
a
t
a
se
t
s
D
a
t
a
s
e
t
s
:
Z
-
A
l
i
z
a
d
e
h
S
a
n
i
.
To
o
l
s
:
K
e
r
a
s
8.
M
u
h
a
mm
a
d
e
t
a
l
.
[
1
4
]
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
En
h
a
n
c
i
n
g
p
r
o
g
n
o
s
i
s
a
c
c
u
r
a
c
y
f
o
r
I
H
D
A
c
c
u
r
a
c
y
(
9
2
)
,
r
e
c
a
l
l
(
9
1
)
,
p
r
e
c
i
s
i
o
n
(
9
2
.
5
)
,
F
1
-
sco
r
e
(
9
2
)
,
A
U
C
(
9
0
)
S
mal
l
,
i
mb
a
l
a
n
c
e
d
d
a
t
a
s
e
t
a
n
d
n
o
c
o
m
p
a
r
i
s
o
n
w
i
t
h
t
r
a
d
i
t
i
o
n
a
l
m
o
d
e
l
s
D
a
t
a
s
e
t
s
:
K
a
g
g
l
e
,
U
C
I
r
e
p
o
si
t
o
r
y
.
To
o
l
s
:
S
e
a
b
o
r
n
M
a
t
p
l
o
t
l
i
b
9.
K
h
d
a
i
r
a
n
d
D
a
sari
.
[
1
5
]
S
V
M
C
o
m
p
a
r
e
M
L
t
e
c
h
n
i
q
u
e
s f
o
r
a
c
c
u
r
a
t
e
d
i
sea
s
e
p
r
e
d
i
c
t
i
o
n
.
A
c
c
u
r
a
c
y
(
7
3
.
8
)
,
p
r
e
c
i
si
o
n
(
6
7
.
9
)
,
r
e
c
a
l
l
(
4
6
.
3
)
,
F
1
-
m
e
a
s
u
r
e
(
5
5
)
,
sp
e
c
i
f
i
c
i
t
y
(
8
8
.
4
)
O
n
l
y
1
3
u
s
e
r
i
n
p
u
t
s f
o
r
p
r
e
d
i
c
t
i
o
n
,
i
n
a
d
e
q
u
a
t
e
d
a
t
a
se
t
s,
a
n
d
v
e
r
y
p
o
o
r
p
e
r
f
o
r
m
a
n
c
e
.
S
o
u
t
h
A
f
r
i
c
a
n
H
e
a
r
t
D
a
t
a
s
e
t
s
:
D
i
s
e
a
s
e
d
a
t
a
se
t
.
To
o
l
s
:
J
u
p
y
t
e
r
N
o
t
e
b
o
o
k
,
P
y
t
h
o
n
l
i
b
r
a
r
i
e
s,
1
0
.
B
a
k
a
r
e
t
a
l
.
[
1
6
]
RF
I
sch
e
mi
c
p
r
e
d
i
c
t
i
o
n
w
i
t
h
r
a
n
d
o
m f
o
r
e
s
t
A
c
c
u
r
a
c
y
(
9
0
)
,
se
n
si
t
i
v
i
t
y
(
7
6
.
5
)
,
sp
e
c
i
f
i
c
i
t
y
(
8
3
.
8
)
,
F
-
sco
r
e
(
7
5
.
3
7
)
N
e
e
d
f
o
r
m
o
r
e
c
o
mp
l
e
x
a
n
d
c
o
m
b
i
n
e
d
mo
d
e
l
B
e
h
a
v
i
o
u
r
a
l
r
i
sk
f
a
c
t
o
r
su
r
v
e
i
l
l
a
n
c
e
s
y
st
e
m
(
B
R
F
S
S
)
,
n
o
t
o
o
l
s.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
T
h
is
s
ec
tio
n
will
in
co
r
p
o
r
ate
i
n
s
ig
h
ts
f
r
o
m
T
ab
le
1
wh
ich
s
h
o
ws
a
r
ev
iew
o
f
o
t
h
er
liter
atu
r
e
r
ev
iews
co
m
p
ar
ed
with
th
e
p
r
o
p
o
s
ed
;
an
d
T
ab
le
2
wh
ich
s
h
o
ws
r
elate
d
wo
r
k
s
o
n
ML
-
b
ased
I
HD
p
r
ed
ict
io
n
s
,
co
v
er
in
g
k
ey
p
atter
n
s
,
co
m
p
a
r
is
o
n
s
,
cr
itical
d
is
cu
s
s
io
n
s
,
o
r
in
ter
p
r
etatio
n
s
ac
r
o
s
s
d
if
f
e
r
e
n
t
ML
m
o
d
els
f
o
r
I
HD
p
r
ed
ictio
n
.
T
h
e
im
p
licatio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
will
also
b
e
p
r
esen
te
d
,
co
n
tain
in
g
in
s
ig
h
ts
in
to
th
e
r
am
if
icatio
n
s
o
f
f
i
n
d
in
g
s
a
n
d
wh
at
wi
ll c
o
m
e
in
h
an
d
y
in
th
e
f
u
tu
r
e.
4
.
1
.
Crit
ica
l
a
na
ly
s
is
a
nd
t
re
nd
s
T
ab
le
1
p
r
o
v
i
d
es
a
co
m
p
ar
is
o
n
o
f
p
r
e
v
io
u
s
liter
atu
r
e
r
ev
i
ews
o
n
ML
f
r
am
ewo
r
k
s
ap
p
l
ied
to
I
HD
p
r
ed
ictio
n
,
h
ig
h
lig
h
tin
g
b
o
t
h
e
m
er
g
in
g
tr
en
d
s
an
d
s
ig
n
if
ican
t
g
ap
s
ac
r
o
s
s
s
tu
d
ies.
T
h
e
c
r
itical
an
aly
s
is
h
er
e
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
r
ev
iew
o
n
is
ch
emic
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
fr
a
mewo
r
ks u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
K
a
b
o
C
liff
o
r
d
B
h
en
d
e
)
365
th
at,
wh
ile
m
an
y
r
ev
iews
em
p
h
asize
th
e
p
r
ed
ictiv
e
ac
cu
r
a
cy
o
f
m
o
d
els
s
u
ch
as
RF
,
X
GB
o
o
s
t,
an
d
C
NN
,
th
er
e
is
a
d
is
p
r
o
p
o
r
tio
n
ate
f
o
cu
s
o
n
p
er
f
o
r
m
a
n
ce
m
etr
ics
lik
e
ac
cu
r
ac
y
an
d
p
r
ec
is
io
n
o
v
er
p
r
ac
tical
asp
ec
ts
lik
e
in
ter
p
r
eta
b
ilit
y
an
d
r
ea
l
-
wo
r
ld
ap
p
licab
ilit
y
.
T
h
is
o
v
er
em
p
h
asis
o
n
p
r
ed
ictiv
e
m
etr
ic
s
ca
n
h
in
d
er
clin
ical
ad
o
p
tio
n
,
as
p
r
ac
titi
o
n
er
s
r
e
q
u
ir
e
m
o
d
els
th
at
ar
e
b
o
t
h
ac
cu
r
ate
an
d
tr
a
n
s
p
ar
en
t.
M
o
s
t
r
ev
iews
r
ely
o
n
s
tan
d
ar
d
d
atasets
,
s
u
ch
as
C
lev
elan
d
an
d
UC
I
,
wh
ic
h
,
th
o
u
g
h
v
alu
a
b
le
f
o
r
i
n
itial
ev
alu
atio
n
s
,
lack
d
em
o
g
r
a
p
h
ic
d
iv
er
s
ity
an
d
lim
it
m
o
d
el
g
e
n
er
aliza
b
ilit
y
.
T
h
is
lim
itatio
n
r
aises
co
n
ce
r
n
ab
o
u
t
th
e
r
ele
v
an
ce
o
f
th
ese
m
o
d
els
in
d
iv
er
s
e
clin
i
ca
l
p
o
p
u
latio
n
s
,
p
a
r
ticu
lar
ly
wh
en
ad
d
r
ess
in
g
r
eg
i
o
n
-
s
p
ec
i
f
ic
h
ea
lth
p
atter
n
s
.
Fu
r
th
er
m
o
r
e
,
f
ew
r
ev
iews
d
is
cu
s
s
th
e
co
m
p
lex
ities
o
f
in
teg
r
atin
g
ML
m
o
d
els
in
to
clin
ica
l
wo
r
k
f
lo
ws,
wh
ic
h
is
ess
en
tial
f
o
r
p
r
ac
tical
im
p
lem
en
tatio
n
.
T
h
e
cr
itical
an
a
ly
s
is
h
er
e
is
th
at
th
e
a
b
s
en
c
e
o
f
I
HD
-
s
p
ec
if
ic
p
r
ed
icto
r
s
an
d
a
lack
o
f
f
o
cu
s
o
n
m
o
d
el
in
ter
p
r
etab
ilit
y
r
e
d
u
ce
th
e
p
r
ac
tical
u
tili
ty
o
f
th
e
s
e
r
ev
iews.
Fu
tu
r
e
liter
atu
r
e
r
ev
iews
s
h
o
u
l
d
ad
o
p
t
a
b
r
o
ad
er
p
er
s
p
ec
tiv
e,
ex
am
i
n
in
g
m
o
d
els
n
o
t
o
n
l
y
f
o
r
th
ei
r
ac
cu
r
ac
y
b
u
t
also
f
o
r
th
eir
t
r
an
s
p
ar
en
c
y
,
d
ataset
d
iv
er
s
ity
,
an
d
in
teg
r
atio
n
f
ea
s
ib
ilit
y
with
in
h
ea
lth
ca
r
e
e
n
v
ir
o
n
m
en
ts
.
T
ab
le
2
p
r
esen
ts
a
d
etailed
co
m
p
ar
is
o
n
o
f
in
d
iv
id
u
al
s
tu
d
ies
f
o
cu
s
in
g
o
n
s
p
ec
if
ic
ML
m
o
d
els
f
o
r
I
HD
p
r
ed
ictio
n
,
ex
a
m
in
in
g
o
b
jectiv
es,
d
atasets
,
ev
alu
atio
n
m
etr
ics,
an
d
lim
itatio
n
s
.
T
h
e
c
r
itical
an
aly
s
is
h
er
e
is
th
at,
wh
ile
en
s
em
b
le
m
o
d
e
ls
lik
e
RF
an
d
XGBo
o
s
t
ac
h
iev
e
h
ig
h
p
e
r
f
o
r
m
an
ce
(
a
cc
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
)
,
th
eir
“b
lack
b
o
x
”
n
atu
r
e
lim
its
in
ter
p
r
etab
ilit
y
,
a
v
it
al
f
ac
to
r
f
o
r
clin
ical
s
ettin
g
s
.
C
lin
ician
s
n
ee
d
to
u
n
d
er
s
tan
d
m
o
d
el
d
ec
is
io
n
-
m
ak
in
g
to
m
a
k
e
i
n
f
o
r
m
ed
p
atien
t
-
ce
n
ter
e
d
d
ec
is
io
n
s
,
an
d
th
is
lack
o
f
tr
an
s
p
ar
en
cy
p
o
s
es
a
b
ar
r
ier
to
ad
o
p
tio
n
,
d
esp
ite
h
ig
h
ac
cu
r
ac
y
m
etr
ics.
T
h
e
tab
le
al
s
o
r
ev
ea
ls
a
h
ea
v
y
r
elian
ce
o
n
d
atasets
s
u
ch
as
C
lev
elan
d
an
d
Statlo
g
,
wh
ich
r
estricts
th
e
m
o
d
els
'
ap
p
lica
b
ilit
y
ac
r
o
s
s
d
iv
er
s
e
p
o
p
u
latio
n
s
.
L
im
ited
d
ata
d
iv
e
r
s
ity
m
ea
n
s
th
at
m
o
d
els m
ay
n
o
t e
f
f
ec
tiv
ely
ca
p
tu
r
e
th
e
m
u
lt
if
ac
to
r
ial
n
atu
r
e
o
f
I
HD
in
d
if
f
er
e
n
t
d
em
o
g
r
a
p
h
ic
g
r
o
u
p
s
,
wh
ich
c
o
u
ld
lead
to
b
iases
in
p
r
ed
ictio
n
s
.
Ad
d
itio
n
ally
,
th
e
s
tu
d
ies
in
T
ab
le
2
o
f
te
n
o
v
er
lo
o
k
th
e
o
p
er
atio
n
al
ch
allen
g
es
ass
o
ciate
d
with
d
ep
lo
y
in
g
th
ese
m
o
d
el
s
in
clin
ical
s
ettin
g
s
,
s
u
ch
as
co
m
p
u
tatio
n
al
d
em
a
n
d
s
,
co
m
p
atib
ilit
y
with
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
s
,
a
n
d
th
e
n
ee
d
f
o
r
co
n
tin
u
o
u
s
m
o
d
el
u
p
d
ates.
T
h
e
cr
itical
an
aly
s
is
h
er
e
is
th
at,
alth
o
u
g
h
th
er
e
is
a
g
r
o
win
g
tr
en
d
to
w
ar
d
co
m
p
r
e
h
en
s
iv
e
ev
alu
atio
n
m
etr
ics
(
e.
g
.
,
F1
-
s
co
r
e,
AUC,
an
d
s
en
s
itiv
ity
)
,
t
h
ese
alo
n
e
d
o
n
o
t
ad
d
r
ess
th
e
f
u
n
d
am
en
tal
is
s
u
es
o
f
m
o
d
el
g
en
er
aliza
b
ilit
y
an
d
in
ter
p
r
etab
ilit
y
.
Fu
t
u
r
e
s
tu
d
ies
s
h
o
u
ld
p
r
i
o
r
itize
d
i
v
er
s
e
d
ata
s
ets,
ad
d
r
ess
m
o
d
el
tr
an
s
p
ar
en
cy
,
a
n
d
co
n
s
id
er
p
r
ac
tical
im
p
lem
en
tatio
n
asp
ec
ts
to
cr
ea
te
ML
m
o
d
els
th
at
a
r
e
m
o
r
e
ap
p
licab
le
an
d
b
e
n
ef
icial
in
r
ea
l
-
wo
r
ld
h
e
alth
ca
r
e
s
ettin
g
s
.
4
.
2
.
A
s
um
m
a
ry
o
f
m
a
j
o
r
f
i
nd
ing
s
T
h
e
k
ey
f
in
d
in
g
s
will
b
e
o
r
g
an
i
z
ed
in
to
th
e
m
o
s
t
ad
o
p
te
d
m
o
d
es
,
s
ig
n
if
ican
t
g
ap
s
,
ev
a
lu
atio
n
o
f
m
etr
ics
p
r
e
f
er
e
n
ce
,
a
n
d
p
r
iv
a
cy
co
n
ce
r
n
s
.
M
o
s
t
ad
o
p
ted
m
o
d
el
:
i
)
RF
em
er
g
ed
as
th
e
m
o
s
t
wid
ely
ad
o
p
ted
m
o
d
el
f
o
r
I
HD
p
r
ed
ictio
n
d
u
e
to
its
h
ig
h
ac
cu
r
ac
y
,
ac
h
iev
in
g
r
ates
u
p
to
9
9
%.
Ho
wev
e
r
,
it
is
lim
ited
b
y
a
lack
o
f
in
ter
p
r
etab
ilit
y
,
ess
en
t
ial
f
o
r
clin
ical
ad
o
p
tio
n
;
ii
)
S
ig
n
if
ican
t
g
a
p
:
th
e
lim
ited
d
i
v
er
s
ity
in
d
atasets
,
su
ch
as
th
e
f
r
eq
u
en
t
u
s
e
o
f
C
lev
elan
d
a
n
d
UC
I
h
ea
r
t
d
is
ea
s
e
d
atasets
,
r
estricts
m
o
d
el
g
e
n
er
aliza
b
ilit
y
.
T
h
is
h
ig
h
lig
h
ts
a
n
ee
d
f
o
r
d
iv
er
s
e
d
atasets
to
im
p
r
o
v
e
p
r
e
d
ictio
n
ac
cu
r
ac
y
ac
r
o
s
s
p
o
p
u
latio
n
s
;
iii
)
E
v
alu
atio
n
m
etr
ic
p
r
ef
er
en
ce
s
:
F1
-
s
co
r
e
an
d
ac
c
u
r
ac
y
ar
e
t
h
e
m
o
s
t
u
s
ed
m
etr
ics
f
o
r
I
HD
p
r
e
d
ictio
n
,
as
th
ey
ef
f
ec
tiv
el
y
b
alan
ce
p
r
ec
is
io
n
an
d
r
ec
all,
cr
u
cial
in
m
ed
ical
d
iag
n
o
s
is
.
Ho
wev
er
,
o
v
e
r
-
r
elian
ce
o
n
th
ese
m
etr
ics
m
ay
o
v
er
lo
o
k
p
r
ac
tical
asp
ec
ts
lik
e
in
ter
p
r
etab
ilit
y
;
an
d
iv
)
Pri
v
ac
y
co
n
ce
r
n
s
:
d
ata
p
r
i
v
ac
y
r
em
ain
s
a
p
r
ess
in
g
is
s
u
e,
esp
ec
ially
wh
en
in
teg
r
a
tin
g
p
atien
t
d
ata
f
r
o
m
m
u
ltip
l
e
s
o
u
r
ce
s
.
T
ec
h
n
iq
u
es
lik
e
f
e
d
er
ated
lea
r
n
in
g
ar
e
r
ec
o
m
m
en
d
ed
to
e
n
h
an
ce
d
ata
s
ec
u
r
ity
wh
ile
m
ain
tain
in
g
m
o
d
el
ac
cu
r
ac
y
an
d
ad
ap
ta
b
ilit
y
.
4
.
3
.
Ra
m
if
ica
t
io
ns
o
f
f
ind
ing
s
a
nd
f
utur
e
im
pli
ca
t
io
ns
T
h
e
f
in
d
in
g
s
h
ig
h
lig
h
t
th
at
wh
ile
en
s
em
b
le
m
o
d
els
lik
e
RF
a
n
d
XGBo
o
s
t
ex
ce
l
in
ac
cu
r
ac
y
f
o
r
I
HD
p
r
ed
ictio
n
,
th
eir
lim
ited
i
n
ter
p
r
etab
ilit
y
r
em
ain
s
a
b
ar
r
ier
t
o
clin
ical
ad
o
p
tio
n
.
T
h
e
r
elian
c
e
o
n
h
o
m
o
g
en
eo
u
s
d
atasets
r
ed
u
ce
s
m
o
d
el
g
en
e
r
aliza
b
ilit
y
,
u
n
d
er
s
co
r
in
g
t
h
e
n
ee
d
f
o
r
d
iv
er
s
e,
r
ep
r
esen
tativ
e
d
ata.
Fu
tu
r
e
r
esear
ch
s
h
o
u
l
d
f
o
cu
s
o
n
th
e
in
teg
r
atio
n
o
f
ex
p
lain
ab
le
AI
(
XAI
)
tech
n
iq
u
es,
s
u
ch
a
s
S
h
ap
ley
ad
d
itiv
e
ex
p
lan
atio
n
s
(
SHAP
)
v
alu
es
a
n
d
lo
ca
l
in
ter
p
r
etab
le
m
o
d
el
-
a
g
n
o
s
tic
ex
p
lan
atio
n
s
(
LIME
)
,
to
im
p
r
o
v
e
m
o
d
el
tr
an
s
p
ar
en
cy
a
n
d
f
o
s
ter
clin
ician
tr
u
s
t.
Ad
d
itio
n
ally
,
ex
p
a
n
d
in
g
to
u
n
s
tr
u
ctu
r
ed
d
ata
s
o
u
r
c
es,
s
u
ch
as
clin
ical
n
o
tes,
co
u
l
d
p
r
o
v
i
d
e
a
r
ich
er
f
o
u
n
d
atio
n
f
o
r
I
HD
p
r
e
d
ictio
n
.
A
d
d
r
ess
in
g
th
ese
ar
ea
s
c
o
u
ld
lea
d
to
m
o
r
e
r
eliab
le,
ap
p
licab
le,
a
n
d
eth
ica
lly
s
o
u
n
d
ML
m
o
d
els in
h
e
alth
ca
r
e.
4
.
4
.
Det
a
iled
inte
rpre
t
a
t
io
ns
o
f
T
a
ble 2
4
.
4
.
1
.
T
he
m
o
s
t
a
do
pte
d
ma
c
hin
e
lea
rning
m
o
dels
f
ro
m
lite
ra
t
ure
Fig
u
r
e
2
s
h
o
ws
th
e
m
o
s
t
ad
o
p
ted
ML
m
o
d
els
f
o
r
I
HD
p
r
e
d
ictio
n
,
with
RF
lead
in
g
at
3
6
.
4
%.
T
h
is
p
o
p
u
lar
ity
is
d
u
e
to
its
h
i
g
h
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
a
b
i
lity
to
h
a
n
d
le
lar
g
e
d
atasets
a
n
d
co
m
p
lex
f
ea
tu
r
e
in
ter
ac
tio
n
s
ef
f
ec
tiv
ely
.
SVM
(
2
2
.
7
%)
an
d
XGBo
o
s
t
(
1
3
.
6
%)
f
o
llo
w,
v
alu
ed
f
o
r
th
eir
p
r
ec
is
io
n
an
d
s
tr
o
n
g
p
er
f
o
r
m
an
ce
with
s
t
r
u
ctu
r
ed
d
ata.
LR
an
d
o
th
er
m
o
d
els
lik
e
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
an
d
n
aï
v
e
B
ay
es
ea
ch
h
o
ld
s
m
aller
s
h
ar
es,
r
ef
lectin
g
d
iv
er
s
e
ap
p
r
o
ac
h
es
b
u
t
h
ig
h
lig
h
tin
g
RF
'
s
p
r
o
m
in
en
ce
i
n
I
HD
p
r
e
d
ictio
n
ap
p
licatio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
6
1
-
372
366
Fig
u
r
e
2
.
Mo
s
t a
d
o
p
ted
ML
m
o
d
el
f
r
o
m
liter
atu
r
e
f
o
r
I
HD
p
r
ed
ictio
n
4
.
4
.
2
.
T
he
m
o
s
t
prev
a
lent
o
b
j
ec
t
iv
es f
ro
m
curr
ent
a
pp
ro
a
ches
Fig
u
r
e
3
s
h
o
ws
th
at
th
e
m
o
s
t
p
r
ev
alen
t
r
esear
ch
o
b
jecti
v
es
in
I
HD
p
r
e
d
ictio
n
ar
e
f
o
cu
s
ed
o
n
ap
p
ly
in
g
ML
al
g
o
r
ith
m
s
an
d
m
o
d
el
d
e
v
elo
p
m
e
n
t,
ea
ch
r
e
p
r
esen
tin
g
2
2
%.
T
h
ese
o
b
jec
tiv
es
h
ig
h
lig
h
t
th
e
p
r
io
r
ity
g
iv
e
n
to
ad
v
an
cin
g
alg
o
r
ith
m
ic
ap
p
r
o
ac
h
es
an
d
cr
e
atin
g
ef
f
ec
tiv
e
p
r
ed
ictio
n
m
o
d
els.
Oth
er
im
p
o
r
tan
t
o
b
jectiv
es
in
clu
d
e
f
ea
tu
r
e
an
aly
s
is
,
clin
ical
ap
p
licatio
n
s
,
a
n
d
alg
o
r
ith
m
ev
alu
at
io
n
,
ea
c
h
co
n
s
titu
tin
g
1
4
%
.
T
h
ese
ca
teg
o
r
ies
d
em
o
n
s
tr
ate
a
b
alan
ce
d
em
p
h
asis
o
n
u
n
d
er
s
tan
d
in
g
m
o
d
el
f
ea
tu
r
es,
ev
alu
atin
g
alg
o
r
ith
m
p
er
f
o
r
m
an
ce
,
a
n
d
a
p
p
ly
in
g
f
in
d
in
g
s
in
clin
ical
c
o
n
tex
ts
.
Me
th
o
d
o
lo
g
y
r
e
v
iew
an
d
im
p
r
o
v
in
g
p
r
o
g
n
o
s
is
ac
cu
r
ac
y
ac
co
u
n
t f
o
r
7
%,
u
n
d
er
s
co
r
in
g
th
eir
em
er
g
in
g
r
elev
an
ce
with
in
th
e
f
ield
.
4
.
4
.
3
.
T
he
m
o
s
t
a
do
pte
d
ma
c
hin
e
lea
rning
da
t
a
s
et
s
f
ro
m
t
he
lite
ra
t
ure
Fig
u
r
e
4
illu
s
tr
ates
th
at
th
e
C
l
ev
elan
d
h
ea
r
t
d
is
ea
s
e
UC
I
r
ep
o
s
ito
r
y
,
ac
co
u
n
tin
g
f
o
r
3
3
%,
is
th
e
m
o
s
t
f
r
eq
u
e
n
tly
ad
o
p
ted
d
ataset
in
I
HD
p
r
ed
ictio
n
d
u
e
to
its
d
etailed
clin
ical
in
f
o
r
m
atio
n
,
a
id
in
g
r
o
b
u
s
t
m
o
d
el
tr
ain
in
g
.
Kag
g
le
an
d
E
lectr
o
c
ar
d
io
g
r
a
m
d
atasets
,
ea
ch
at
1
5
%,
ar
e
also
p
o
p
u
la
r
,
o
f
f
er
in
g
d
iv
er
s
e
f
ea
tu
r
es
f
o
r
v
ar
ied
ML
ap
p
licatio
n
s
.
Oth
er
s
o
u
r
ce
s
c
o
n
tr
ib
u
te
s
m
aller
p
o
r
tio
n
s
,
h
ig
h
lig
h
tin
g
a
r
elian
ce
o
n
estab
lis
h
ed
d
atasets
an
d
a
p
o
ten
tial n
ee
d
f
o
r
b
r
o
ad
er
d
ata
d
iv
e
r
s
ity
to
en
h
an
ce
m
o
d
el
g
en
e
r
aliza
b
ilit
y
.
4
.
4
.
4
.
T
he
m
o
s
t
a
do
pte
d
ma
c
hin
e
lea
rning
m
o
del e
v
a
lua
t
io
n m
et
rics f
ro
m
t
he
lite
ra
t
ure
Fig
u
r
e
5
s
h
o
ws
th
at
th
e
F1
-
s
co
r
e,
at
1
7
%,
is
th
e
m
o
s
t
wid
ely
ad
o
p
ted
e
v
alu
atio
n
m
etr
ic
f
o
r
I
HD
p
r
ed
ictio
n
,
h
ig
h
lig
h
tin
g
its
u
tili
ty
in
b
alan
cin
g
p
r
ec
is
io
n
a
n
d
r
ec
all.
Acc
u
r
ac
y
a
n
d
p
r
ec
is
io
n
ea
ch
f
o
llo
w
clo
s
ely
at
1
6
%,
with
s
en
s
itiv
ity
an
d
r
ec
all
at
1
3
%,
s
h
o
wc
asin
g
th
e
im
p
o
r
tan
ce
o
f
p
r
ed
ictiv
e
r
eliab
ilit
y
in
h
ea
lth
ca
r
e
co
n
tex
ts
.
Sp
ec
if
icity
,
ar
ea
-
u
n
d
e
r
-
th
e
-
c
u
r
v
e
(
AUC),
an
d
r
eg
r
ess
io
n
ea
ch
h
av
e
s
m
aller
s
h
ar
es,
with
s
p
ec
if
icity
an
d
AUC
em
p
h
asizin
g
d
iag
n
o
s
tic
p
o
we
r
.
T
h
is
d
is
tr
ib
u
tio
n
s
u
g
g
ests
a
f
o
cu
s
o
n
m
etr
ics
t
h
at
b
alan
ce
d
if
f
er
en
t
p
r
e
d
ictio
n
asp
ec
ts
,
wh
ich
is
cr
u
cial
in
d
ev
elo
p
in
g
m
o
d
els
th
at
clin
i
cian
s
ca
n
tr
u
s
t
f
o
r
ac
cu
r
ate
an
d
d
ep
en
d
ab
le
d
iag
n
o
s
is
.
4
.
4
.
5
.
T
he
m
o
s
t
prev
a
lent
li
m
it
a
t
io
ns
of
t
he
curr
ent
a
pp
ro
a
ches
Fig
u
r
e
6
id
e
n
tifie
s
d
ata
p
r
i
v
ac
y
is
s
u
es
as
th
e
m
o
s
t
s
ig
n
if
ican
t
lim
it
atio
n
in
I
HD
p
r
ed
ictio
n
r
esear
ch
,
ac
co
u
n
tin
g
f
o
r
2
0
%
o
f
co
n
ce
r
n
s
.
Scalab
ilit
y
an
d
in
ter
o
p
er
ab
ilit
y
is
s
u
es
ea
ch
f
o
llo
w
at
1
5
%,
in
d
icatin
g
th
e
ch
allen
g
es
o
f
im
p
lem
e
n
tin
g
m
o
d
els
ac
r
o
s
s
s
y
s
tem
s
an
d
p
atien
t
d
atasets
.
Secu
r
ity
co
n
ce
r
n
s
an
d
c
o
s
t
m
an
ag
em
en
t,
ea
ch
at
1
0
%,
h
ig
h
lig
h
t
th
e
i
m
p
o
r
ta
n
ce
o
f
s
ec
u
r
e
an
d
co
s
t
-
ef
f
ec
tiv
e
s
o
l
u
tio
n
s
.
T
h
e
“
o
t
h
er
”
ca
teg
o
r
y
co
n
s
titu
tes
3
0
%,
e
n
c
o
m
p
ass
in
g
v
a
r
io
u
s
ad
d
itio
n
al
lim
itatio
n
s
,
s
h
o
win
g
th
at
m
u
lt
ip
le
f
ac
to
r
s
h
in
d
er
I
HD
p
r
ed
ictio
n
m
o
d
el
ad
o
p
ti
o
n
.
T
h
ese
f
in
d
i
n
g
s
u
n
d
er
s
co
r
e
th
e
n
e
e
d
to
ad
d
r
ess
p
r
iv
ac
y
,
s
ca
lab
ilit
y
,
an
d
in
ter
o
p
er
a
b
ilit
y
to
en
h
a
n
ce
th
e
p
r
ac
tical
u
s
e
o
f
ML
m
o
d
els in
clin
ical
s
ettin
g
s
.
4
.
4
.
6
.
M
o
s
t
a
do
pte
d
m
a
chine le
a
rning
t
o
o
ls
f
ro
m
lite
ra
t
ur
e
Fig
u
r
e
7
s
h
o
ws th
e
m
o
s
t a
d
o
p
ted
ML
to
o
ls
f
o
r
I
HD
p
r
ed
ictio
n
,
with
Py
th
o
n
lib
r
ar
ies lea
d
in
g
at
2
5
%.
Py
th
o
n
’
s
p
o
p
u
lar
ity
s
tem
s
f
r
o
m
its
v
er
s
atile
lib
r
ar
ies an
d
v
is
u
aliza
tio
n
ca
p
ab
ilit
ies,
ess
en
ti
al
f
o
r
ef
f
ec
tiv
e
d
ata
h
an
d
lin
g
an
d
m
o
d
el
b
u
ild
in
g
.
W
ek
a
f
o
llo
ws
with
1
9
%,
v
a
lu
ed
f
o
r
its
s
u
ite
o
f
ML
alg
o
r
ith
m
s
.
T
o
o
ls
li
k
e
NVI
VO
1
0
,
Flas
k
,
J
u
p
y
ter
No
teb
o
o
k
,
an
d
MA
T
L
AB
e
ac
h
h
o
l
d
s
m
aller
s
h
ar
es,
o
f
f
er
in
g
s
p
ec
ialized
f
u
n
ctio
n
alities
.
T
h
is
d
is
tr
ib
u
tio
n
r
ef
lects
a
s
tr
o
n
g
p
r
ef
e
r
e
n
ce
f
o
r
Py
th
o
n
-
b
ased
to
o
ls
,
h
ig
h
lig
h
tin
g
t
h
eir
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
r
ev
iew
o
n
is
ch
emic
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
fr
a
mewo
r
ks u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
K
a
b
o
C
liff
o
r
d
B
h
en
d
e
)
367
f
lex
ib
ilit
y
,
co
m
p
u
tatio
n
al
p
o
wer
,
an
d
ea
s
e
o
f
u
s
e,
m
ak
i
n
g
th
em
id
ea
l
f
o
r
I
HD
p
r
ed
ictio
n
r
esear
ch
an
d
d
ev
elo
p
m
e
n
t.
Fig
u
r
e
3
.
Mo
s
t a
d
o
p
ted
r
esear
ch
o
b
jectiv
es f
r
o
m
th
e
liter
atu
r
e
f
o
r
I
HD
p
r
ed
ictio
n
Fig
u
r
e
4
.
Mo
s
t a
d
o
p
ted
ML
d
a
tasets
f
r
o
m
liter
atu
r
e
f
o
r
I
HD
p
r
ed
ictio
n
Fig
u
r
e
5
.
Mo
s
t a
d
o
p
ted
ML
m
etr
ics f
r
o
m
liter
atu
r
e
f
o
r
I
HD
p
r
ed
ictio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
6
1
-
372
368
Fig
u
r
e
6
.
Mo
s
t p
r
ev
alen
t lim
it
atio
n
s
with
cu
r
r
en
t a
p
p
r
o
ac
h
es f
o
r
I
HD
p
r
ed
ictio
n
Fig
u
r
e
7
.
Mo
s
t a
d
o
p
ted
ML
to
o
ls
f
r
o
m
th
e
liter
atu
r
e
f
o
r
I
HD
p
r
ed
ictio
n
4
.
4
.
7
.
Rela
t
ed
wo
r
k
s
perf
o
r
m
a
nce
Fig
u
r
e
8
s
h
o
ws
th
e
p
r
ed
ictio
n
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
o
f
v
ar
i
o
u
s
ML
m
o
d
els
u
s
ed
in
I
HD
p
r
ed
ictio
n
f
r
am
ewo
r
k
s
.
T
h
e
p
er
f
o
r
m
a
n
c
e
m
etr
ics
o
f
r
elate
d
wo
r
k
s
a
n
d
th
eir
v
alu
es
ar
e
clea
r
l
y
p
r
esen
ted
in
T
a
b
le
1
u
n
d
er
t
h
e
“
ML
ev
alu
atio
n
m
etr
ics
an
d
p
er
f
o
r
m
a
n
ce
”
c
o
lu
m
n
.
T
h
is
s
ec
tio
n
will
p
r
esen
t
th
e
liter
atu
r
e
p
er
f
o
r
m
an
ce
r
esu
lts
an
d
g
iv
e
a
cr
itical
p
er
f
o
r
m
an
ce
an
al
y
s
is
to
d
ed
u
ce
an
y
tr
en
d
s
o
r
p
at
ter
n
s
th
at
em
er
g
e.
T
h
e
h
ig
h
est
ac
cu
r
ac
y
r
e
p
o
r
te
d
in
Fig
u
r
e
8
is
b
y
Ali
et
a
l
.
[
1
7
]
at
1
0
0
%,
f
o
llo
wed
b
y
T
ay
lo
r
et
a
l.
[
1
8
]
at
9
8
.
8
3
%,
an
d
Hass
an
et
a
l
.
[
1
2
]
at
9
6
.
2
8
%.
Mo
s
t
f
r
am
ewo
r
k
s
d
em
o
n
s
tr
ate
ac
cu
r
ac
y
ab
o
v
e
9
0
%,
in
d
icatin
g
s
tr
o
n
g
m
o
d
el
r
eliab
ilit
y
.
Ku
m
ar
an
d
Ku
m
a
r
[
1
9
]
s
h
o
w
th
e
l
o
west
ac
cu
r
ac
y
at
7
3
.
8
%.
T
h
e
tr
en
d
s
u
g
g
ests
th
at
r
ec
en
t
m
o
d
els
co
n
s
is
ten
tly
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
,
h
i
g
h
lig
h
tin
g
ad
v
an
ce
m
e
n
ts
i
n
ML
tech
n
iq
u
es
f
o
r
m
ed
ical
p
r
ed
ictio
n
s
.
Oth
er
f
r
am
ewo
r
k
s
[
2
0
]
–
[
2
2
]
ar
e
s
h
o
wn
in
Fig
u
r
e
8
.
Fig
u
r
e
9
s
h
o
ws
th
e
s
en
s
itiv
ity
p
er
f
o
r
m
an
ce
o
f
v
ar
i
o
u
s
ML
m
o
d
els
u
s
ed
in
I
HD
p
r
ed
ictio
n
f
r
am
ewo
r
k
s
.
T
h
e
h
ig
h
est
s
en
s
itiv
ity
is
r
ep
o
r
ted
b
y
Sh
eh
za
d
i
et
a
l
.
[
8
]
a
n
d
Ali
et
a
l
.
[
1
7
]
,
b
o
t
h
ac
h
iev
in
g
1
0
0
%.
T
h
is
in
d
icate
s
th
ese
m
o
d
els'
s
tr
o
n
g
ab
ilit
y
to
co
r
r
ec
tly
id
en
tify
tr
u
e
p
o
s
itiv
e
ca
s
es
o
f
h
ea
r
t
d
is
ea
s
e.
Ma
in
i
et
a
l
.
[
9
]
,
Hass
an
et
a
l
.
[
1
2
]
,
an
d
Say
ad
i
et
a
l
.
[
1
3
]
a
ls
o
d
em
o
n
s
tr
ate
h
ig
h
s
en
s
itiv
ity
,
ex
ce
e
d
in
g
9
0
%
.
B
ak
ar
et
a
l
.
[
1
6
]
a
n
d
Mu
h
am
m
ad
et
a
l
.
[
1
4
]
s
h
o
w
s
lig
h
tly
lo
wer
s
en
s
itiv
ity
at
8
3
.
8
%,
in
d
icatin
g
r
o
o
m
f
o
r
im
p
r
o
v
em
e
n
t in
ca
p
t
u
r
in
g
tr
u
e
p
o
s
itiv
es.
Fig
u
r
e
1
0
illu
s
tr
ates
th
e
s
p
ec
i
f
icity
p
e
r
f
o
r
m
an
ce
o
f
d
i
f
f
er
en
t
ML
m
o
d
els
u
s
ed
f
o
r
p
r
e
d
ictin
g
I
HD.
Kh
d
air
an
d
D
asar
i
[
1
5
]
s
h
o
w
t
h
e
h
ig
h
est s
p
ec
if
icity
at
9
6
.
2
8
%,
in
d
icatin
g
a
s
tr
o
n
g
ab
ilit
y
to
co
r
r
ec
tly
id
en
tif
y
tr
u
e
n
eg
ativ
es.
Ma
in
i
et
a
l
.
[
9
]
an
d
Say
ad
i
et
a
l
.
[
1
3
]
f
o
llo
w
with
s
p
ec
if
icities
o
f
9
4
.
6
%
an
d
9
1
.
6
6
%,
r
esp
ec
tiv
ely
.
B
ak
ar
et
a
l
.
[
1
6
]
an
d
Mu
h
am
m
ad
et
a
l
.
[
1
4
]
r
ep
o
r
t
a
s
p
ec
if
icity
o
f
8
3
.
8
%.
T
h
ese
r
esu
lts
r
ef
lect
th
at
wh
ile
th
e
m
o
d
els
ar
e
g
en
er
ally
g
o
o
d
at
id
en
tify
in
g
th
o
s
e
with
o
u
t
d
is
ea
s
e,
th
er
e
is
v
ar
iab
ilit
y
in
th
eir
p
er
f
o
r
m
an
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
r
ev
iew
o
n
is
ch
emic
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
fr
a
mewo
r
ks u
s
in
g
ma
ch
in
e
lea
r
n
in
g
(
K
a
b
o
C
liff
o
r
d
B
h
en
d
e
)
369
Fig
u
r
e
8
.
Per
f
o
r
m
an
c
e
an
aly
s
i
s
o
f
r
elate
d
wo
r
k
s
b
ased
o
n
ac
cu
r
ac
y
m
etr
ic
Fig
u
r
e
9
.
Per
f
o
r
m
an
c
e
an
aly
s
i
s
o
f
r
elate
d
wo
r
k
s
b
ased
o
n
th
e
s
en
s
itiv
ity
p
er
f
o
r
m
a
n
ce
m
etr
ic
Fig
u
r
e
1
0
.
Per
f
o
r
m
a
n
ce
an
al
y
s
is
o
f
r
elate
d
wo
r
k
s
b
ased
o
n
s
p
ec
if
icity
p
er
f
o
r
m
an
ce
m
etr
ic
Fig
u
r
e
1
1
p
r
esen
ts
th
e
F1
-
s
co
r
e
p
er
f
o
r
m
a
n
ce
o
f
v
a
r
io
u
s
ML
m
o
d
els
u
s
ed
in
I
HD
p
r
ed
ictio
n
.
Sh
eh
za
d
i
et
a
l
.
[
8
]
lea
d
with
an
F1
-
s
co
r
e
o
f
1
0
0
%,
s
h
o
win
g
ex
ce
llen
t
b
alan
ce
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all.
T
h
e
lo
wer
en
d
o
f
th
e
s
p
ec
tr
u
m
in
clu
d
es
Kh
d
air
an
d
Dasar
i
[
1
5
]
,
B
ak
ar
et
a
l.
[
1
6
]
,
Ku
m
ar
an
d
Ku
m
ar
[
1
9
]
,
Mittas
et
a
l.
[
2
3
]
,
an
d
B
h
att
et
a
l.
[
2
4
]
,
i
n
d
icatin
g
th
ese
m
o
d
els
m
ay
s
tr
u
g
g
le
with
b
ala
n
cin
g
p
r
ec
is
io
n
an
d
r
ec
all
ef
f
ec
tiv
ely
.
Oth
er
h
i
g
h
p
er
f
o
r
m
er
s
in
clu
d
e
Say
ad
i
et
a
l.
[
1
3
]
a
n
d
C
h
an
d
r
asek
h
ar
a
n
d
Ped
d
ak
r
is
h
n
a
[
2
5
]
,
b
o
t
h
a
b
o
v
e
9
5
%
.
M
o
d
e
l
s
li
k
e
H
o
s
s
e
n
e
t
a
l
.
[
1
0
]
a
n
d
M
u
h
a
m
m
a
d
e
t
a
l
.
[
1
4
]
a
c
h
i
e
v
e
F
1
-
s
c
o
r
e
s
a
r
o
u
n
d
8
5
%
.
0
10
20
30
40
50
60
70
80
90
100
Kum
ar
[
9
]
S
ay
ad
i
[
1
3]
S
ha
h
[
20]
R
ajd
ha
n
[
2
1]
Udd
i
n
[
22
]
M
ai
ni
[
9]
Nag
ave
l
l
i
[
3
]
H
a
s
sa
n
[
12]
T
a
y
l
o
r
[
18
]
Al
i
[17
]
A
CCURA
CY
P
E
R
F
O
MA
N
CE
(
%
)
F
R
A
ME
W
O
R
K
0
20
40
60
80
100
B
ak
ar
[
16]
M
uh
am
m
a
d
[
14]
M
ai
ni
[
9]
H
a
s
sa
n
[
12]
S
ayadi
[
1
3
]
S
he
hz
ad
i
[
8]
Al
i
[17
]
S
E
N
S
E
T
IV
IT
Y
(
%
)
F
R
A
ME
W
O
R
K
75
80
85
90
95
100
B
ak
ar
[
16]
M
uh
am
m
a
d
[
14]
S
ay
ad
i
[
1
3]
M
ai
ni
[
9]
H
a
s
sa
n
[
12]
S
PE
CIF
ICI
T
Y
(
%
)
F
R
A
ME
W
O
R
KS
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
6
1
-
372
370
Fig
u
r
e
1
1
.
Per
f
o
r
m
a
n
ce
an
al
y
s
is
o
f
r
elate
d
wo
r
k
s
b
ased
o
n
F
1
-
s
co
r
e
p
er
f
o
r
m
an
ce
m
etr
ic
5.
CO
NCLU
SI
O
N
T
h
is
r
ev
iew
p
r
esen
ted
t
h
e
cr
it
ical
r
o
le
o
f
ML
m
o
d
els
in
p
r
e
d
ictin
g
I
HD,
wh
ich
r
em
ain
s
o
n
e
o
f
th
e
lead
in
g
ca
u
s
es
o
f
d
ea
th
g
lo
b
ally
.
Desp
ite
th
e
ab
u
n
d
an
ce
o
f
s
tu
d
ies
f
o
cu
s
ed
o
n
ML
-
b
a
s
ed
I
HD
p
r
ed
ictio
n
,
ex
is
tin
g
liter
atu
r
e
r
ev
iews
o
f
t
en
f
ail
to
p
er
f
o
r
m
cr
itica
l
an
d
in
-
d
ep
t
h
an
aly
tics
o
f
g
a
p
s
,
o
b
jectiv
es,
m
o
d
els,
p
er
f
o
r
m
an
ce
,
t
o
o
ls
ad
o
p
te
d
,
d
ataset
d
iv
er
s
ity
,
in
ter
p
r
eta
b
ilit
y
,
an
d
clin
ical
a
p
p
licab
i
lity
.
C
u
r
r
en
t
I
HD
p
r
ed
ictio
n
f
r
am
ewo
r
k
s
also
e
x
h
ib
it
g
a
p
s
,
in
clu
d
in
g
s
m
all
a
n
d
im
b
ala
n
ce
d
d
atasets
,
lim
ited
f
o
c
u
s
o
n
f
ea
tu
r
e
s
elec
tio
n
,
an
d
c
h
allen
g
es
with
m
o
d
el
tr
an
s
p
ar
en
c
y
,
w
h
ich
h
i
n
d
er
t
h
eir
p
r
ac
tical
im
p
lem
en
t
atio
n
.
T
h
is
r
e
v
iew
co
n
tr
ib
u
tes
to
th
e
f
ield
b
y
s
y
s
tem
atica
lly
an
aly
zin
g
ML
m
o
d
els
s
u
ch
as
RF
an
d
SVM
,
a
n
d
co
m
p
ar
in
g
t
h
eir
s
tr
en
g
th
s
,
lim
itatio
n
s
,
an
d
p
er
f
o
r
m
an
ce
in
clin
ical
a
p
p
licatio
n
s
.
Key
c
o
n
tr
ib
u
ti
o
n
s
in
clu
d
e
id
en
tify
in
g
wid
el
y
ad
o
p
ted
to
o
ls
an
d
ev
alu
atio
n
m
etr
ics,
ass
es
s
in
g
g
ap
s
in
c
u
r
r
en
t
m
eth
o
d
o
lo
g
ies,
an
d
p
r
o
v
id
in
g
g
u
id
an
ce
o
n
eth
ical
co
n
s
id
er
atio
n
s
an
d
m
o
d
el
tr
an
s
p
ar
en
cy
.
T
h
e
m
ajo
r
f
in
d
in
g
s
s
u
g
g
est
a
tr
en
d
to
war
d
en
s
em
b
le
m
o
d
els
f
o
r
h
i
g
h
ac
c
u
r
ac
y
;
h
o
wev
er
,
t
h
er
e
is
a
n
ee
d
f
o
r
d
iv
e
r
s
e
d
at
asets
an
d
in
ter
p
r
etab
le
f
r
am
e
wo
r
k
s
to
f
ac
ilit
ate
clin
ical
ad
o
p
tio
n
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
l
d
f
o
cu
s
o
n
en
h
a
n
ci
n
g
p
r
iv
ac
y
t
h
r
o
u
g
h
f
ed
er
ated
lear
n
in
g
,
e
x
p
an
d
in
g
d
ata
s
o
u
r
ce
s
to
in
clu
d
e
u
n
s
tr
u
ctu
r
ed
d
ata
f
o
r
a
r
ich
er
a
n
aly
s
is
,
an
d
in
teg
r
atin
g
e
x
p
lain
ab
le
AI
to
o
ls
lik
e
SHAP
an
d
L
I
ME
to
i
n
cr
ea
s
e
tr
an
s
p
a
r
en
cy
.
T
h
e
f
u
tu
r
e
r
ec
o
m
m
en
d
atio
n
en
ab
les
th
e
d
e
v
elo
p
m
e
n
t
o
f
m
o
r
e
r
eliab
le,
ad
ap
tab
le,
an
d
eth
ically
s
o
u
n
d
ML
m
o
d
els
th
at
ca
n
b
e
in
t
eg
r
ated
in
to
h
ea
lth
ca
r
e
f
o
r
ea
r
ly
I
HD
p
r
ed
ictio
n
,
u
ltima
tely
im
p
r
o
v
in
g
p
u
b
lic
h
ea
lth
o
u
tco
m
es.
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
Kab
o
C
liff
o
r
d
B
h
en
d
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
T
s
h
iam
o
Sig
wele
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
h
an
d
ap
iwa
Mo
k
g
et
h
i
✓
✓
✓
✓
✓
✓
Ao
n
e
Ma
eg
e
✓
✓
✓
✓
Ven
u
Ma
d
h
a
v
Ku
th
ad
i
✓
✓
✓
✓
✓
✓
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
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
a
v
aila
b
i
lit
y
is
n
o
t
a
p
p
li
ca
b
le
t
o
t
h
is
p
ap
er
as
n
o
n
e
w
d
a
t
a
w
er
e
cr
ea
te
d
o
r
an
al
y
z
e
d
i
n
t
h
is
s
t
u
d
y
.
0
20
40
60
80
100
Khda
i
r
[
15
]
M
i
t
t
as
[
2
3]
B
ak
ar
[
16]
K
um
ar
[
9
]
H
a
s
a
n
o
v
av
[
11]
B
ha
t
t
[
24]
Muham
m
a
d
[
1
4
]
H
os
se
n [
1
0
]
C
ha
nd
r
as
e
k
ha
r
[
25]
S
ay
ad
i
[
3
]
S
he
hz
ad
i
[
8]
F1
-
S
CO
R
E
(
%
)
F
R
A
ME
W
O
R
KS
Evaluation Warning : The document was created with Spire.PDF for Python.