I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
,
p
p
.
321
~
332
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
1
.
pp
3
2
1
-
3
3
2
321
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
H
y
brid ma
chi
ne l
ea
rning
f
ra
mewo
rk f
o
r c
hro
nic dis
ea
se risk
a
ss
ess
ment
H
a
rini Sha
da
k
s
ha
ra
pp
a
1
,
Ra
s
hm
i K
.
B.
2
,
Sh
re
y
a
s
D.
K.
3
,
So
m
a
na
t
h M
ik
a
li
4
,
Vis
hes
h
P
.
G
o
wda
5
,
Uda
y
Sh
a
nk
a
r
C.
A.
6
,
Sid
da
rt
h B
.
I
y
er
r
7
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
B
.
M
.
S
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
e
n
g
a
l
u
r
u
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
1
1
,
2
0
2
5
R
ev
is
ed
Oct
1
5
,
2
0
2
5
Acc
ep
ted
No
v
2
3
,
2
0
2
5
Ch
ro
n
ic
d
ise
a
se
s
li
k
e
a
sth
m
a
,
d
iab
e
tes
,
stro
k
e
,
a
n
d
h
e
a
rt
d
ise
a
se
a
re
th
e
m
a
jo
r
c
a
u
se
s
o
f
m
o
rb
id
it
y
g
l
o
b
a
l
ly
,
wh
ich
e
m
p
h
a
siz
e
s
th
e
n
e
e
d
fo
r
e
fficie
n
t
p
re
d
ictiv
e
m
o
d
e
ls
to
fa
c
il
i
tate
e
a
rly
d
e
tec
ti
o
n
a
n
d
p
re
c
a
u
ti
o
n
a
r
y
m
e
a
su
re
s.
P
re
v
io
u
s
stu
d
ies
h
a
v
e
u
se
d
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
e
s
f
o
r
si
n
g
l
e
-
d
ise
a
se
p
re
d
ictio
n
,
wh
e
re
m
o
d
e
ls
a
re
d
e
si
g
n
e
d
fo
r
sp
e
c
ifi
c
d
ise
a
se
s,
su
c
h
a
s
d
iab
e
tes
o
r
h
e
a
rt
d
ise
a
se
.
Ho
we
v
e
r,
v
e
ry
fe
w
a
tt
e
m
p
ts
h
a
v
e
b
e
e
n
m
a
d
e
t
o
d
e
v
e
lo
p
u
n
ifi
e
d
fra
m
e
wo
rk
s
fo
r
p
re
d
icti
n
g
m
u
lt
ip
le
d
ise
a
se
s
sim
u
lt
a
n
e
o
u
sly
.
T
h
is
wo
rk
p
re
se
n
ts
a
n
o
v
e
l
,
u
n
ifi
e
d
fra
m
e
wo
rk
u
sin
g
a
n
e
n
se
m
b
le
o
f
e
x
trem
e
g
ra
d
ien
t
b
o
o
sti
n
g
c
las
sifier
(XG
BClas
sifier)
a
n
d
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
s
(AN
N) as
in
d
iv
id
u
a
l
c
las
sifiers
to
c
o
n
c
u
rre
n
tl
y
p
re
d
ict
t
h
e
risk
o
f
d
e
v
e
lo
p
i
n
g
a
sth
m
a
,
d
iab
e
tes
,
str
o
k
e
,
a
n
d
h
e
a
rt
d
ise
a
se
.
Th
is
wo
r
k
f
o
ll
o
ws
a
q
u
e
stio
n
n
a
ire
-
b
a
se
d
a
p
p
ro
a
c
h
t
h
a
t
u
ti
li
z
e
s
d
e
m
o
g
ra
p
h
ic,
li
fe
sty
l
e
,
h
e
a
lt
h
m
e
tri
c
s,
sy
m
p
to
m
s
a
n
d
e
x
p
o
su
r
e
-
re
late
d
d
a
ta
t
o
c
re
a
te
p
e
rso
n
a
li
z
e
d
risk
a
ss
e
ss
m
e
n
ts.
Th
e
m
o
d
e
l
a
c
h
iev
e
s
sa
ti
sfa
c
to
ry
a
c
c
u
ra
c
y
ra
tes
o
f
9
5
.
8
2
%
fo
r
a
sth
m
a
,
9
6
.
6
8
%
fo
r
d
ia
b
e
tes
,
9
4
.
9
1
%
fo
r
stro
k
e
,
a
n
d
9
4
.
5
2
%
fo
r
h
e
a
rt
d
ise
a
se
.
Th
e
fin
d
in
g
s
h
i
g
h
li
g
h
t
h
o
w
t
h
is
n
o
v
e
l
h
y
b
rid
m
o
d
e
l
se
rv
e
s
a
s
a
n
e
ffe
c
ti
v
e
a
p
p
ro
a
c
h
to
tac
k
le
t
h
e
in
tri
c
a
te
i
n
tera
c
ti
o
n
s
b
e
twe
e
n
c
h
ro
n
ic
a
il
m
e
n
ts.
Th
e
re
se
a
rc
h
a
lso
i
n
c
lu
d
e
s
a
u
se
r
-
frien
d
l
y
we
b
site
th
a
t
c
o
m
p
rise
s
a
q
u
e
stio
n
n
a
ire
a
n
d
m
a
k
e
s
u
se
o
f
th
e
b
e
st
p
e
rf
o
rm
in
g
m
o
d
e
l
to
p
re
d
ict
th
e
p
ro
b
a
b
il
it
ies
o
f
d
e
v
e
lo
p
in
g
d
iffere
n
t
d
ise
a
se
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
C
h
r
o
n
ic
d
is
ea
s
es
Hea
lth
m
etr
ics
Ma
ch
in
e
lear
n
in
g
Pre
d
ictiv
e
m
o
d
el
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
:
R
ash
m
i K
.
B.
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Scien
ce
an
d
E
n
g
in
ee
r
i
n
g
,
B
.
M.
S
.
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
P.O.
B
o
x
No
.
:
1
9
0
8
,
B
u
ll T
em
p
le
R
o
ad
,
B
an
g
alo
r
e
-
5
6
0
0
1
9
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail:
r
ash
m
ik
b
.
is
e@
b
m
s
ce
.
ac
.
in
1.
I
NT
RO
D
UCT
I
O
N
Ov
er
th
e
last
f
ew
d
ec
ad
es,
ch
r
o
n
ic
d
is
ea
s
es
h
av
e
r
ea
c
h
ed
u
n
p
r
ec
ed
en
ted
lev
els
ac
r
o
s
s
th
e
g
lo
b
e.
T
h
e
m
o
s
t
p
r
o
m
in
e
n
t
o
n
es
in
clu
d
e
asth
m
a,
d
iab
etes,
s
tr
o
k
e
,
an
d
ca
r
d
io
v
ascu
lar
d
is
ea
s
e.
T
h
ese
co
n
d
itio
n
s
,
ta
k
e
n
to
g
eth
er
,
f
o
r
m
a
h
u
g
e
b
u
r
d
e
n
o
n
th
e
h
ea
lth
ca
r
e
s
y
s
tem
s
ar
o
u
n
d
th
e
wo
r
ld
[
1
]
.
Hea
r
t
d
is
ea
s
es
a
lo
n
e
ar
e
r
esp
o
n
s
ib
le
f
o
r
alm
o
s
t
1
7
.
9
m
illi
o
n
d
ea
th
s
a
n
n
u
ally
,
as
cl
aim
ed
b
y
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
an
d
o
v
er
5
0
0
m
illi
o
n
p
e
o
p
le
s
u
f
f
er
f
r
o
m
ch
r
o
n
ic
r
esp
ir
ato
r
y
ailm
en
ts
,
in
clu
d
in
g
asth
m
a
[
2
]
.
Diab
etes
af
f
ec
ts
alm
o
s
t
5
0
0
m
illi
o
n
p
e
o
p
le,
an
d
th
e
f
ig
u
r
e
is
p
r
o
jecte
d
to
in
cr
ea
s
e
b
y
2
5
%
in
2
0
3
0
[
3
]
.
P
r
ev
en
tiv
e
d
etec
tio
n
an
d
p
r
ev
e
n
tio
n
o
f
th
ese
d
is
ea
s
es
h
av
e
b
ec
o
m
e
o
n
e
o
f
th
e
k
ey
ch
allen
g
es
in
m
o
d
er
n
h
ea
lth
ca
r
e
s
y
s
tem
s
,
esp
ec
ially
in
ar
ea
s
wh
er
e
th
er
e
is
a
lack
o
f
m
o
d
e
r
n
m
e
d
ical
f
ac
ilit
ies
an
d
d
iag
n
o
s
tic
eq
u
ip
m
e
n
t.
T
h
ese
co
n
d
itio
n
s
ar
e
esp
ec
ially
p
r
ev
alen
t
in
d
ev
elo
p
in
g
co
u
n
tr
ies,
wh
er
e
h
ea
lth
ca
r
e
ac
ce
s
s
m
ay
b
e
lim
ited
.
T
r
ad
itio
n
al
d
iag
n
o
s
tic
ap
p
r
o
a
ch
es
g
en
er
ally
n
ee
d
s
o
p
h
is
tic
ated
lab
o
r
at
o
r
y
test
in
g
,
s
k
illed
m
ed
ical
p
e
r
s
o
n
n
el,
an
d
ad
e
q
u
ate
r
eso
u
r
ce
s
,
wh
ic
h
h
am
p
er
s
p
r
o
m
p
t
id
e
n
tific
atio
n
an
d
tr
ea
tm
en
t.
T
h
ese
is
s
u
e
s
ar
e
ex
ac
er
b
ate
d
in
r
u
r
al
an
d
im
p
o
v
er
is
h
ed
c
o
m
m
u
n
ities
,
wh
er
e
ac
ce
s
s
to
s
p
ec
ialized
h
ea
lth
s
er
v
ices is lim
ited
o
r
n
o
n
ex
is
ten
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
2
1
-
332
322
T
h
e
ad
v
e
n
t
o
f
co
m
p
u
tatio
n
al
m
eth
o
d
s
in
m
ac
h
in
e
lear
n
in
g
an
d
th
e
s
p
h
er
e
o
f
ar
tific
ial
in
t
ellig
en
ce
,
esp
ec
ially
en
s
em
b
le
lear
n
in
g
t
ec
h
n
iq
u
es,
h
as
ch
an
g
ed
th
e
m
eth
o
d
o
lo
g
ies
th
at
ar
e
u
s
ed
in
d
is
ea
s
e
p
r
ed
ictio
n
.
W
h
ile
th
e
tr
ad
itio
n
al
m
eth
o
d
s
u
s
ed
in
m
ed
ical
d
ia
g
n
o
s
is
d
ep
en
d
o
n
a
co
m
b
in
atio
n
o
f
cl
in
ical
ac
u
m
en
an
d
lab
o
r
ato
r
y
ass
ess
m
en
ts
,
en
s
em
b
le
s
tr
ateg
ies
lik
e
v
o
tin
g
cl
ass
if
ier
s
,
in
th
e
p
r
esen
ce
o
f
p
o
wer
f
u
l
alg
o
r
ith
m
s
s
u
ch
as
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
ti
n
g
(
XGBo
o
s
t)
an
d
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
in
ter
c
h
an
g
ea
b
l
y
u
s
ed
as
m
u
lti
-
lay
er
p
e
r
ce
p
tr
o
n
(
ML
P)
as
u
s
ed
in
t
h
is
ap
p
r
o
ac
h
[
4
]
,
ar
e
in
d
ee
d
v
alid
alter
n
ativ
e
s
f
o
r
ex
ac
t
d
is
ea
s
e
f
o
r
ec
asti
n
g
.
L
atest
tech
n
o
lo
g
i
ca
l
ad
v
an
ce
m
en
ts
g
r
ea
tly
af
f
ec
t
p
r
ev
en
tiv
e
ca
r
e
as
ea
r
ly
d
iag
n
o
s
is
o
f
h
ea
lth
p
r
o
b
lem
s
h
as tr
em
e
n
d
o
u
s
ly
im
p
r
o
v
e
d
p
atien
t
o
u
tco
m
es a
n
d
d
ec
r
ea
s
ed
h
ea
lth
ca
r
e
co
s
ts
.
C
o
m
p
r
eh
en
s
iv
e
ap
p
r
o
ac
h
es
t
o
d
is
ea
s
e
p
r
e
d
ictio
n
ar
e
also
v
ital
b
ec
au
s
e
c
h
r
o
n
ic
d
is
ea
s
es
ar
e
o
f
ten
in
ter
r
elate
d
with
co
m
m
o
n
r
is
k
f
ac
to
r
s
an
d
co
e
x
is
tin
g
s
y
m
p
to
m
s
.
Fo
r
in
s
tan
ce
,
th
e
r
is
k
f
ac
to
r
s
r
elate
d
to
en
v
ir
o
n
m
en
tal
asp
ec
ts
ca
n
s
im
u
ltan
eo
u
s
ly
i
n
cr
ea
s
e
r
esp
ir
a
to
r
y
a
n
d
ca
r
d
io
v
ascu
lar
co
n
d
itio
n
s
,
s
u
ch
as
air
q
u
ality
o
r
p
o
llu
tio
n
lev
el.
Ho
wev
er
,
d
iab
etes is wid
ely
r
eg
a
r
d
ed
as a
f
ac
to
r
th
at
s
ig
n
if
ican
tly
elev
a
tes
th
e
p
o
ten
tial
f
o
r
h
ea
r
t
co
n
d
itio
n
s
an
d
s
tr
o
k
e
[
5
]
.
T
h
e
in
ter
ac
tio
n
am
o
n
g
th
ese
ch
r
o
n
ic
illn
ess
es
m
ak
es
a
ca
ll
f
o
r
h
o
lis
tic
m
eth
o
d
o
lo
g
ies in
p
r
ed
ictin
g
th
em
,
in
v
o
lv
in
g
ass
ess
m
en
t o
f
m
an
y
in
ter
c
o
n
n
ec
te
d
r
is
k
f
ac
to
r
s
an
d
th
eir
co
m
p
lex
ities
.
T
h
is
r
esear
ch
ad
d
r
ess
es
th
ese
p
r
o
b
lem
s
th
r
o
u
g
h
an
i
n
n
o
v
at
iv
e
m
u
ltip
le
d
is
ea
s
e
p
r
ed
ictiv
e
s
y
s
tem
;
th
e
en
s
em
b
le
co
m
b
i
n
es
XGBC
las
s
if
ier
an
d
ANN
t
o
ev
al
u
a
te
s
im
u
ltan
eo
u
s
ly
t
h
e
h
az
a
r
d
o
f
b
r
o
n
c
h
ial
asth
m
a,
d
iab
etes,
s
tr
o
k
e,
an
d
co
r
o
n
ar
y
h
ea
r
t
d
is
ea
s
e.
T
h
e
in
teg
r
ate
d
ap
p
r
o
ac
h
will
u
s
e
a
s
y
s
tem
b
ased
o
n
q
u
esti
o
n
s
th
at
will
b
e
d
em
o
g
r
ap
h
ic,
life
s
ty
le,
h
ea
lth
m
etr
ics,
s
y
m
p
to
m
s
,
an
d
ex
p
o
s
u
r
e
-
b
ased
to
cr
e
ate
p
er
s
o
n
alize
d
r
is
k
an
aly
s
is
.
T
h
e
u
n
iq
u
e
n
ess
in
m
eth
o
d
o
l
o
g
y
is
r
ef
lecte
d
in
its
in
teg
r
ated
f
r
am
ewo
r
k
d
esig
n
ed
f
o
r
m
u
ltip
le
d
is
ea
s
e
p
r
ed
ictio
n
,
th
er
eb
y
a
d
d
r
ess
in
g
a
n
o
tab
le
g
ap
with
in
th
e
e
x
is
tin
g
f
r
am
e
o
f
r
esear
c
h
,
wh
ich
p
r
im
a
r
ily
f
o
cu
s
es o
n
m
o
d
els f
o
r
t
h
e
p
r
e
d
ictio
n
o
f
s
in
g
le
d
is
ea
s
es.
T
h
e
r
est
o
f
th
is
p
ap
er
is
p
r
ep
ar
ed
as
f
o
llo
ws:
s
ec
tio
n
2
af
f
o
r
d
s
an
in
-
d
ep
th
r
ev
iew
o
f
liter
atu
r
e
p
er
tain
in
g
to
th
e
s
co
p
e
o
f
m
ac
h
in
e
lear
n
in
g
in
d
is
ea
s
e
p
r
e
d
ictio
n
.
Sectio
n
3
ad
d
r
ess
es
th
e
m
eth
o
d
o
l
o
g
ies
th
at
in
clu
d
e
d
ata
co
llectio
n
/p
r
e
-
p
r
o
ce
s
s
in
g
to
th
e
v
o
tin
g
class
if
ier
with
XGB
C
las
s
if
ier
an
d
ANN.
Fu
r
th
er
m
o
r
e
,
s
ec
tio
n
4
d
ea
ls
with
th
e
ex
p
er
im
en
t
r
esu
lts
o
n
d
if
f
er
en
t
m
et
r
ics.
L
astl
y
,
s
ec
tio
n
5
h
as
a
s
u
m
m
ar
y
o
f
f
in
d
in
g
s
with
a
f
u
tu
r
e
p
er
s
p
ec
tiv
e.
2.
RE
L
AT
E
D
WO
RK
R
ec
en
t
r
esear
ch
h
as
s
h
o
wn
s
u
b
s
tan
tial
ad
v
an
ce
s
in
th
e
d
ev
elo
p
m
e
n
t
o
f
in
teg
r
ated
s
y
s
tem
s
f
o
r
p
r
ed
ictin
g
n
u
m
er
o
u
s
d
is
ea
s
es
at
o
n
ce
.
Go
p
is
etti
et
a
l.
[
6
]
s
u
g
g
ested
a
m
eth
o
d
to
f
o
r
ec
a
s
t
s
ev
er
al
d
is
ea
s
es
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
,
d
em
o
n
s
tr
atin
g
th
e
ab
ilit
y
to
c
r
ea
te
u
s
er
-
f
r
ie
n
d
ly
o
n
lin
e
ap
p
licatio
n
s
in
h
ea
lth
ca
r
e
d
iag
n
o
s
tics
u
tili
zin
g
f
r
am
ewo
r
k
s
s
u
ch
as
Stre
am
lit.
R
ay
et
a
l.
[
7
]
d
is
cu
s
s
ed
d
if
f
er
en
t
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
f
o
r
f
o
r
ec
asti
n
g
a
v
ar
iety
o
f
d
is
ea
s
es
an
d
h
ig
h
l
ig
h
ted
th
e
im
p
o
r
tan
ce
o
f
d
ia
g
n
o
s
tic
to
o
ls
in
an
in
teg
r
ated
m
an
n
er
in
m
o
d
e
r
n
h
ea
lth
ca
r
e
co
n
d
itio
n
s
.
Sig
n
if
ican
t
ad
v
an
ce
m
en
ts
h
av
e
b
ee
n
m
a
d
e
in
s
tr
o
k
e
p
r
e
d
ictio
n
in
r
ec
e
n
t
y
ea
r
s
.
T
h
e
latest
r
esear
ch
ca
r
r
ied
o
u
t
b
y
Gu
p
ta
et
a
l.
[
8
]
ac
h
iev
e
d
an
ac
cu
r
ac
y
o
f
9
5
.
1
6
%
in
n
e
u
r
al
n
etwo
r
k
s
wh
ich
is
an
im
p
o
r
tan
t
m
iles
to
n
e
in
th
e
p
r
ed
ictio
n
o
f
s
tr
o
k
es.
R
ah
m
an
et
a
l.
[
9
]
to
o
k
th
eir
f
in
d
in
g
s
a
s
tep
f
o
r
war
d
to
p
r
o
d
u
ce
9
9
%
ac
cu
r
ac
y
with
th
e
aid
o
f
R
a
n
d
o
m
Fo
r
est
en
s
em
b
le
alg
o
r
i
th
m
s
.
T
h
er
e
is
,
h
o
wev
er
an
im
p
o
r
tan
t
w
o
r
k
b
y
Mr
id
h
a
et
a
l.
[
1
0
]
th
at
em
p
h
a
s
izes
p
r
o
p
er
v
alid
atio
n
tech
n
i
q
u
es
wh
er
ein
th
ey
p
r
o
v
ed
h
o
w
alth
o
u
g
h
r
an
d
o
m
f
o
r
est
o
b
tain
e
d
9
0
.
3
6
%
ac
cu
r
a
cy
o
n
th
e
en
tire
d
ataset,
with
t
h
e
m
o
r
e
r
ea
lis
tic
tr
ain
-
test
s
p
li
t,
it
ca
m
e
o
u
t
to
b
e
8
2
.
2
3
%,
th
er
e
b
y
p
r
o
v
in
g
th
e
s
ig
n
if
ican
ce
o
f
av
o
id
in
g
d
ata
le
ak
ag
e
in
m
o
d
el
ev
alu
atio
n
.
E
lan
g
o
v
a
n
et
a
l.
[
1
1
]
s
ig
n
if
ican
tly
co
n
tr
ib
u
ted
to
th
e
liter
atu
r
e
b
y
d
is
cu
s
s
in
g
th
e
cr
itical
p
r
o
b
lem
o
f
im
b
ala
n
ce
d
d
atasets
in
s
tr
o
k
e
p
r
ed
ictio
n
,
o
f
f
e
r
in
g
v
er
y
u
s
ef
u
l in
s
ig
h
ts
o
n
h
o
w
to
d
ea
l w
ith
th
is
u
b
iq
u
ito
u
s
p
r
o
b
lem
i
n
m
e
d
ical
d
ata
an
aly
s
is
.
Sev
er
al
m
ajo
r
s
tu
d
ies
h
av
e
c
o
m
e
o
u
t
o
n
d
iab
etes
p
r
ed
icti
o
n
.
Hasan
et
a
l.
[
1
2
]
in
v
esti
g
ated
th
e
ap
p
licatio
n
o
f
en
s
em
b
le
al
g
o
r
ith
m
s
in
p
r
e
d
ictin
g
d
ia
b
etes,
wh
er
ea
s
Mu
ju
m
d
a
r
an
d
Vaid
eh
i
[
1
3
]
r
e
p
o
r
te
d
s
ig
n
if
ican
t
o
u
tco
m
es
u
tili
zin
g
d
if
f
er
en
t
alg
o
r
ith
m
s
—
s
p
ec
if
ically
,
th
eir
g
r
a
d
ien
t
b
o
o
s
t
m
o
d
el
d
em
o
n
s
tr
ated
an
ac
cu
r
ac
y
o
f
9
3
%,
wh
e
r
ea
s
th
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
ac
h
iev
ed
an
o
u
ts
tan
d
i
n
g
ac
c
u
r
ac
y
o
f
9
6
%.
Diab
etes
p
r
ed
ictio
n
is
alwa
y
s
b
ein
g
im
p
r
o
v
e
d
,
an
d
R
an
i'
s
r
esear
ch
[
1
4
]
claim
ed
9
9
%
ac
cu
r
ac
y
u
s
in
g
d
ec
is
io
n
tr
ee
s
.
So
m
e
s
tu
d
ies,
lik
e
So
n
i
a
n
d
Var
m
a
[
1
5
]
,
s
h
o
we
d
m
o
r
e
m
o
d
est
r
esu
lts
,
as
r
a
n
d
o
m
f
o
r
est
o
b
tain
e
d
7
7
%
ac
cu
r
ac
y
,
s
h
o
win
g
t
h
e
d
iv
e
r
s
ity
o
f
m
o
d
els'
p
er
f
o
r
m
an
ce
o
n
d
if
f
er
en
t
d
atasets
an
d
ap
p
r
o
ac
h
es.
Yah
y
ao
u
i
et
a
l.
[
1
6
]
s
u
g
g
ested
v
alu
a
b
le
in
s
ig
h
ts
d
esp
ite
u
s
in
g
a
s
m
aller
d
ataset
o
f
7
6
8
s
am
p
les,
ac
h
iev
in
g
8
3
.
6
7
% a
cc
u
r
ac
y
.
T
h
e
r
esear
ch
i
n
asth
m
a
p
r
ed
ictio
n
h
as
f
o
c
u
s
ed
s
ig
n
if
ican
tly
o
n
ec
o
lo
g
ical
f
ac
t
o
r
s
.
T
h
e
tr
en
d
i
n
m
ed
ical
ca
r
e
u
s
ag
e
d
u
e
to
en
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
h
as
b
ee
n
d
is
cu
s
s
ed
b
y
J
o
et
a
l.
[
1
7
]
,
an
d
Hwa
n
g
et
a
l.
[
1
8
]
h
av
e
ap
p
lied
d
ee
p
lear
n
in
g
m
eth
o
d
s
f
o
r
p
r
ed
ictin
g
th
e
c
o
u
n
t
o
f
asth
m
a
p
atien
ts
th
r
o
u
g
h
en
v
ir
o
n
m
en
tal
in
f
o
r
m
atio
n
.
L
o
u
is
ias
et
a
l.
[
1
9
]
s
tu
d
ied
t
h
e
en
v
ir
o
n
m
en
tal
d
eter
m
in
an
ts
o
f
asth
m
a
with
r
eg
ar
d
to
its
s
y
m
p
to
m
s
,
esp
ec
ially
t
h
e
r
o
le
o
f
p
o
llen
,
aller
g
en
s
,
a
n
d
d
u
s
t.
A
s
y
s
tem
atic
r
ev
iew
b
y
J
ay
a
m
in
i
et
a
l.
[
2
0
]
h
as
an
aly
ze
d
an
e
x
ten
s
iv
e
r
an
g
e
o
f
m
ac
h
in
e
lea
r
n
in
g
tec
h
n
iq
u
es,
wh
ich
in
clu
d
es
tech
n
iq
u
e
s
s
u
ch
as
lo
g
is
tic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
ch
r
o
n
ic
d
is
ea
s
e
r
i
s
k
a
s
s
es
s
men
t
(
Ha
r
in
i S
h
a
d
a
k
s
h
a
r
a
p
p
a
)
323
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
s
an
d
en
s
em
b
le
m
eth
o
d
s
lik
e
r
an
d
o
m
f
o
r
ests
,
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
es,
an
d
n
e
u
r
al
n
etwo
r
k
s
to
p
r
ed
ict
asth
m
a
ex
ac
er
b
atio
n
s
.
Var
io
u
s
r
esear
ch
s
tu
d
ies
o
n
th
e
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
e
h
av
e
p
r
o
v
en
t
o
b
e
e
f
f
ec
ti
v
e
u
s
in
g
d
if
f
er
en
t
m
eth
o
d
o
l
o
g
ies.
Dr
its
as
an
d
T
r
ig
k
a
[
2
1
]
ac
h
iev
ed
h
ig
h
ac
cu
r
ac
y
with
8
7
.
8
%
a
n
d
ar
ea
u
n
d
er
th
e
cu
r
v
e
(
AUC)
o
f
9
8
.
2
%
u
s
in
g
a
s
tack
in
g
en
s
em
b
le
m
o
d
e
l
ap
p
lied
a
f
ter
s
y
n
t
h
etic
m
in
o
r
ity
o
v
er
-
s
am
p
lin
g
tech
n
iq
u
e
(
SMOT
E
)
,
u
tili
zin
g
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
.
B
h
at
t
et
a
l.
[
2
2
]
s
h
o
wed
s
u
cc
ess
with
ML
P
m
o
d
els
at
8
7
.
2
3
%.
Kav
ith
a
et
a
l.
[
2
3
]
p
r
o
p
o
s
ed
a
h
y
b
r
i
d
m
o
d
el
with
ac
cu
r
ac
y
8
8
.
7
%,
an
d
Sar
r
a
e
t
a
l.
[
2
4
]
ac
h
iev
ed
b
etter
p
er
f
o
r
m
a
n
ce
u
s
in
g
an
A
NN
m
o
d
el,
w
h
ich
d
e
p
icted
u
p
to
9
3
.
4
4
%
in
ac
c
u
r
ac
y
an
d
AUC
o
f
0
.
9
5
.
R
ec
en
t
wo
r
k
b
y
Yad
av
et
a
l.
[
2
5
]
ac
h
iev
ed
9
4
.
5
1
%
ac
cu
r
ac
y
with
Ad
aBo
o
s
t
an
d
r
a
n
d
o
m
f
o
r
est
f
ea
tu
r
e
s
elec
tio
n
,
th
o
u
g
h
t
h
eir
p
r
ec
is
io
n
(
4
8
.
3
3
)
an
d
r
ec
all
(
3
9
.
5
2
)
m
etr
ics o
n
t
est d
ata
h
ig
h
lig
h
t p
er
s
is
ten
t c
h
allen
g
es in
clin
ical
ap
p
licab
ilit
y
.
Ov
e
r
all,
th
e
s
et
o
f
s
tu
d
ies
r
ep
r
esen
ts
th
e
d
ev
elo
p
m
en
t
an
d
ad
v
an
ce
m
e
n
t
o
f
h
ea
r
t
d
is
ea
s
e
p
r
ed
ictio
n
m
o
d
els,
wh
ich
i
n
s
ev
er
al
co
n
tex
ts
,
d
em
o
n
s
tr
ate
p
r
o
m
is
in
g
p
r
o
g
r
ess
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
cu
r
r
en
t
wo
r
k
attem
p
ts
to
d
ev
elo
p
a
s
tr
o
n
g
an
d
in
t
eg
r
ated
f
r
am
ewo
r
k
f
o
r
p
r
e
d
ictin
g
th
e
d
ev
elo
p
in
g
r
is
k
o
f
ch
r
o
n
ic
co
n
d
itio
n
s
,
in
cl
u
d
in
g
asth
m
a,
d
i
ab
etes,
s
tr
o
k
e,
an
d
h
ea
r
t
d
is
ea
s
es.
T
h
e
m
o
tiv
atio
n
b
eh
in
d
d
ev
elo
p
i
n
g
s
u
ch
a
f
r
am
ewo
r
k
is
to
ass
is
t
p
r
ac
titi
o
n
er
s
as
well
as
p
atien
ts
d
u
r
in
g
h
ea
lth
ca
r
e
b
y
p
r
o
v
id
i
n
g
tim
ely
war
n
i
n
g
s
a
n
d
s
u
itab
le
ad
v
ice.
Fo
r
t
h
is
p
u
r
p
o
s
e,
we
u
s
ed
m
u
ltip
le
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
,
ap
p
lied
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
to
im
p
r
o
v
e
d
ata
q
u
ality
,
an
d
ad
o
p
ted
an
en
s
em
b
le
-
b
ased
ap
p
r
o
ac
h
to
im
p
r
o
v
e
ac
cu
r
ac
y
in
p
r
ed
ictio
n
as h
ig
h
lig
h
ted
b
y
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Flo
w
d
ia
g
r
am
o
f
m
o
d
el
3
.
1
.
Da
t
a
s
o
urce
T
h
e
cu
r
r
en
t
s
tu
d
y
u
s
ed
d
atasets
f
r
o
m
f
r
ee
s
o
u
r
ce
to
p
r
ed
ict
th
e
lik
elih
o
o
d
o
f
f
o
u
r
c
h
r
o
n
ic
d
is
ea
s
es:
asth
m
a,
d
iab
etes,
s
tr
o
k
e,
an
d
h
ea
r
t
d
is
ea
s
e.
T
h
ese
d
atasets
in
clu
d
ed
v
ast
am
o
u
n
ts
o
f
d
ata
co
n
tain
i
n
g
d
em
o
g
r
a
p
h
ic,
m
e
d
ical,
an
d
lif
esty
le
attr
ib
u
tes r
elev
an
t to
ea
ch
d
is
ea
s
e.
˗
D
i
a
b
e
t
es
d
a
t
a
s
e
t
(
h
t
t
p
s
:
/
/w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
s
et
s
/
i
a
m
m
u
s
t
a
f
a
t
z
/
d
i
a
b
e
t
e
s
-
p
r
e
d
i
ct
i
o
n
-
d
a
t
a
s
et
)
:
I
t
c
o
n
t
a
i
n
e
d
1
0
0
,
0
0
0
i
n
s
t
a
n
c
e
s
w
it
h
f
e
a
t
u
r
e
d
e
s
c
r
i
p
ti
o
n
s
i
n
c
l
u
d
i
n
g
a
g
e
,
g
e
n
d
e
r
,
b
o
d
y
m
a
s
s
i
n
d
e
x
(
B
M
I
)
,
h
is
t
o
r
y
o
f
h
y
p
e
r
t
e
n
s
i
o
n
,
f
a
c
t
o
r
s
s
u
c
h
a
s
a
h
i
s
t
o
r
y
o
f
h
e
a
r
t
d
i
s
e
a
s
e
,
s
m
o
k
i
n
g
h
a
b
i
t
s
,
G
l
y
c
a
t
e
d
h
e
m
o
g
l
o
b
i
n
(
H
b
A
1
c
)
l
e
v
e
l
s
,
a
n
d
b
l
o
o
d
g
l
u
c
o
s
e
m
e
asu
r
e
m
e
n
t
s
.
T
h
e
t
a
r
g
et
v
a
r
i
a
b
l
e
f
o
r
d
i
a
b
e
t
e
s
is
b
i
n
a
r
y
.
˗
S
t
r
o
k
e
d
a
t
as
e
t
(
h
t
t
p
s
:
/
/w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
s
et
s
/
f
e
d
es
o
r
i
a
n
o
/s
tr
o
k
e
-
p
r
e
d
i
ct
i
o
n
-
d
a
t
a
s
et
)
:
I
t
co
m
p
r
i
s
e
s
5
,
1
1
0
r
e
c
o
r
d
s
w
i
t
h
f
e
a
t
u
r
es
t
h
a
t
i
n
cl
u
d
e
a
g
e
,
g
e
n
d
e
r
,
m
a
r
i
t
a
l
s
t
at
u
s
,
h
y
p
e
r
t
e
n
s
i
o
n
,
h
e
a
r
t
d
i
s
ea
s
e
,
s
m
o
k
in
g
,
g
lu
c
o
s
e
lev
els,
B
MI
,
an
d
ty
p
e
o
f
wo
r
k
,
an
d
r
esid
en
ce
with
a
b
in
ar
y
ta
r
g
et
v
ar
iab
le
f
o
r
t
h
e
s
tr
o
k
e.
˗
A
s
t
h
m
a
d
a
t
as
e
t
(
h
t
t
p
s
:
/
/w
w
w
.
ka
g
g
l
e
.
c
o
m
/
d
a
t
a
s
et
s
/r
a
b
i
e
el
k
h
a
r
o
u
a
/
a
s
t
h
m
a
-
d
is
e
a
s
e
-
d
a
t
a
s
e
t
)
:
T
h
e
r
e
a
r
e
2
,
3
9
2
s
a
m
p
l
es
a
n
d
2
9
v
a
r
i
a
b
l
e
s
i
n
t
h
e
a
s
t
h
m
a
d
a
t
as
e
t
.
T
h
e
v
ar
i
ab
les
co
m
p
r
is
e
d
em
o
g
r
ap
h
ic
s
(
ag
e,
g
en
d
e
r
,
eth
n
icity
)
,
life
s
ty
le
f
ac
to
r
s
(
s
m
o
k
in
g
,
p
h
y
s
ical
ac
tiv
ity
,
d
ie
t,
s
leep
)
,
e
n
v
ir
o
n
m
en
tal
ex
p
o
s
u
r
es
(
p
o
llu
tio
n
,
p
o
llen
,
d
u
s
t)
,
m
e
d
ical
h
is
to
r
y
(
f
am
ily
asth
m
a,
aller
g
ies,
ec
ze
m
a)
,
clin
ical
test
s
(
f
o
r
ce
d
ex
p
ir
ato
r
y
v
o
lu
m
e
in
1
s
ec
o
n
d
,
f
o
r
ce
d
v
ital
ca
p
ac
ity
)
,
an
d
s
y
m
p
to
m
s
(
wh
ee
z
in
g
,
d
y
s
p
n
ea
,
ch
est
tig
h
t
n
ess
,
co
u
g
h
in
g
)
.
T
h
e
tar
g
et
v
ar
iab
le
is
th
e
asth
m
a
d
iag
n
o
s
is
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
2
1
-
332
324
˗
H
e
a
r
t
d
i
s
e
a
s
e
d
a
t
a
s
e
t
(
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
s
e
t
s
/
t
a
r
e
k
m
u
h
a
m
m
e
d
/
p
a
t
i
e
n
t
s
-
d
a
t
a
-
f
o
r
-
m
e
d
i
c
a
l
-
f
i
e
l
d
/
d
a
t
a
)
:
T
h
is
d
ataset
co
n
tain
ed
2
3
7
,
6
3
0
r
ec
o
r
d
s
.
I
t
in
clu
d
e
d
d
em
o
g
r
ap
h
ics,
alo
n
g
with
h
ei
g
h
t
an
d
weig
h
t,
B
MI
,
m
ed
ical
h
is
to
r
y
s
u
ch
as a
h
ea
r
t a
ttack
,
an
g
in
a,
s
tr
o
k
e,
d
iab
et
es,
o
r
asth
m
a,
life
s
ty
le
f
ac
to
r
s
lik
e
s
m
o
k
in
g
o
r
e
-
cig
ar
ettes,
p
r
e
v
en
tiv
e
ca
r
e
li
k
e
v
ac
cin
atio
n
s
,
ch
est
s
ca
n
s
,
a
n
d
r
ec
e
n
t
h
ea
lth
ev
e
n
ts
,
s
u
ch
as
C
o
r
o
n
av
ir
u
s
d
is
ea
s
e
o
f
2
0
1
9
(
C
OVI
D
-
1
9
)
.
Hea
r
t d
is
ea
s
e
h
is
to
r
y
was th
e
b
in
ar
y
tar
g
et
v
ar
iab
le
.
3
.
2
.
Da
t
a
p
re
-
pro
ce
s
s
ing
3
.
2
.
1
.
Da
t
a
clea
nin
g
E
v
er
y
d
ataset
was
clea
n
ed
a
n
d
f
r
ee
d
o
f
r
e
d
u
n
d
an
cy
b
y
r
em
o
v
in
g
d
u
p
licate
en
tr
ies
an
d
im
p
u
tin
g
m
is
s
in
g
v
alu
es.
Nu
m
er
ical
f
e
atu
r
es
wer
e
h
an
d
le
d
u
s
in
g
m
ed
ian
im
p
u
tatio
n
wh
ile
ca
teg
o
r
ical
f
ea
tu
r
es
wer
e
h
an
d
led
u
s
in
g
m
o
d
e
im
p
u
tatio
n
.
I
r
r
elev
a
n
t
attr
ib
u
tes,
s
u
ch
as
p
atien
t
I
Ds,
wer
e
elim
in
ated
in
o
r
d
er
to
ac
h
ie
v
e
g
o
o
d
a
cc
u
r
ac
y
.
3
.
2
.
2
.
F
ea
t
ure
eng
ineering
T
h
e
f
ea
tu
r
e
en
g
in
ee
r
in
g
m
eth
o
d
was
u
s
ed
to
e
n
h
an
ce
th
e
p
r
ed
ictio
n
ab
ilit
y
o
f
th
e
m
o
d
el.
Nu
m
er
ical
f
ea
tu
r
es,
in
clu
d
in
g
ag
e,
B
MI
,
b
lo
o
d
g
lu
co
s
e,
b
lo
o
d
p
r
ess
u
r
e
,
an
d
Hb
A1
c,
wer
e
s
ca
led
u
s
in
g
s
tan
d
ar
d
s
ca
lin
g
to
alig
n
th
em
o
n
th
e
s
am
e
s
ca
le.
B
in
ar
y
f
ea
tu
r
es
wer
e
s
u
b
jecte
d
f
o
r
lab
el
en
co
d
in
g
s
u
ch
a
s
g
en
d
er
,
p
r
esen
c
e
o
f
ce
r
tain
d
is
o
r
d
er
an
d
o
n
e
-
h
o
t
en
co
d
in
g
was
im
p
lem
e
n
ted
f
o
r
m
u
lti
-
class
o
n
es
lik
e
th
e
m
ed
ical
co
n
d
itio
n
s
,
th
e
ty
p
e
o
f
wo
r
k
,
ed
u
ca
tio
n
a
n
d
r
ac
e/eth
n
icity
.
T
h
is
allo
wed
f
o
r
p
r
o
p
er
in
ter
p
r
etatio
n
o
f
t
h
e
ca
teg
o
r
ical
d
ata.
Usi
n
g
h
ea
tm
ap
an
aly
s
is
,
a
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
b
ased
o
n
co
r
r
elatio
n
was
em
p
lo
y
ed
t
o
d
eter
m
in
e
w
h
ich
p
r
ed
icto
r
s
ar
e
m
o
s
t p
er
tin
en
t a
n
d
r
ed
u
ce
th
e
n
u
m
b
e
r
o
f
d
im
e
n
s
io
n
s
wh
ile
k
ee
p
in
g
t
h
e
ab
ilit
y
to
p
r
e
d
ict.
3
.
3
.
M
o
delin
g
3
.
3
.
1
.
XG
B
o
o
s
t
c
la
s
s
if
ier
E
x
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
,
o
r
XGBo
o
s
t
f
o
r
s
h
o
r
t,
is
a
p
o
ten
t
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
f
o
r
task
s
in
v
o
lv
in
g
r
e
g
r
ess
io
n
an
d
class
if
icatio
n
.
I
t
u
s
es
a
b
o
o
s
tin
g
tech
n
iq
u
e
to
ex
p
a
n
d
o
n
d
ec
is
io
n
tr
ee
s
,
wh
er
e
in
r
elev
an
t
v
ar
iab
les
ar
e
g
iv
en
m
o
r
e
weig
h
t
an
d
u
s
e
d
in
th
e
s
u
b
s
eq
u
en
t
d
ec
is
io
n
tr
ee
in
ca
s
e
th
e
tr
ee
m
ak
es
a
f
alse
p
r
ed
ictio
n
.
T
h
e
o
u
tp
u
ts
o
f
ea
ch
class
if
ier
o
r
p
r
ed
icto
r
a
r
e
s
u
b
s
eq
u
e
n
tly
in
t
eg
r
ated
to
f
o
r
m
a
m
o
r
e
r
o
b
u
s
t
an
d
ac
cu
r
ate
m
o
d
el.
B
y
alter
in
g
weig
h
ts
ac
co
r
d
in
g
t
o
p
r
ev
i
o
u
s
er
r
o
r
s
,
XGBo
o
s
t
m
ix
es
th
e
o
u
tp
u
ts
o
f
s
ev
er
al
tr
ee
s
ad
d
iti
v
ely
,
in
co
n
t
r
ast
to
R
an
d
o
m
Fo
r
est,
wh
ich
av
e
r
ag
es
th
em
.
T
h
is
en
ab
les
m
o
r
e
co
m
p
lex
p
r
ed
ictio
n
s
.
R
eg
u
lar
i
za
tio
n
to
av
o
i
d
o
v
e
r
f
itti
n
g
,
p
ar
allel
p
r
o
ce
s
s
in
g
f
o
r
p
er
f
o
r
m
an
ce
,
an
d
a
weig
h
ted
q
u
an
tile
s
k
etch
tech
n
iq
u
e
f
o
r
h
an
d
lin
g
s
p
a
r
s
e
d
ata
ar
e
im
p
o
r
tan
t
asp
ec
ts
.
T
h
e
lo
s
s
f
u
n
ctio
n
,
alg
o
r
ith
m
o
f
XGBo
o
s
t
clas
s
if
ier
is
as f
o
llo
ws:
=
∑
(
,
(
)
)
=
1
+
∑
(
ℎ
)
=
1
(
ℎ
)
=
+
1
2
|
|
2
|
|
h
er
e,
(
ᵢ
,
(
ᵢ
)
)
is
lo
g
lo
s
s
f
u
n
ctio
n
,
(
ℎ
)
is
r
eg
u
lar
izatio
n
ter
m
f
o
r
ea
ch
t
r
ee
ℎ
,
is
n
u
m
b
er
o
f
leav
es
o
f
th
e
tr
ee
,
is
p
ar
am
ete
r
to
co
n
tr
o
l
lo
west
lo
s
s
r
ed
u
ctio
n
g
ai
n
t
o
s
p
lit
a
n
o
d
e
,
an
d
is
o
u
tp
u
t
v
alu
es
f
r
o
m
th
e
leav
es
.
Alg
o
r
ith
m
o
f
XGBo
o
s
t c
lass
if
ier
1.
Model initialization
Initialize F
0
(x)=0
2.
Iterative boosting process
for t = 1 to T:
˗
Calculate the gradient of the loss function
=
(
,
(
)
)
(
)
˗
Fits decision tree to predict these gradients
˗
Computes tree predictions h
t
(x)
˗
Updating the model as F
t+1
(x)=F
t
(x)+h
t
(x)
where is
the learning rate (0<
≤1)
˗
Application of regularization components as:
L2 regularization on leaf weights (
∑
2
)
Complexity penalty on number of leaves (T)
Total objective:
+
∑
2
+
3.
Th
e
fi
na
l
mo
de
l
is
an
en
se
mb
le
of
T
tr
ee
s
co
mb
in
ed
ad
di
ti
ve
ly
an
d
pr
ed
ic
t
io
ns
ba
se
d
on
cumulative tree outputs.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
ch
r
o
n
ic
d
is
ea
s
e
r
i
s
k
a
s
s
es
s
men
t
(
Ha
r
in
i S
h
a
d
a
k
s
h
a
r
a
p
p
a
)
325
3
.
3
.
2
.
M
ulti
-
la
y
er
perc
ept
ro
n
Am
o
n
g
th
e
ty
p
es
o
f
ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
is
a
m
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P).
T
h
e
a
r
ch
itectu
r
e
ac
co
m
m
o
d
ates
a
n
in
p
u
t
lay
e
r
,
o
n
e
o
r
m
o
r
e
h
id
d
e
n
lay
er
s
,
an
d
an
o
u
tp
u
t
lay
er
.
T
h
e
weig
h
t
ed
s
u
m
o
f
i
n
p
u
ts
o
f
ea
ch
lay
er
in
a
n
e
u
r
al
n
etwo
r
k
is
u
s
ed
b
y
th
e
n
eu
r
o
n
s
f
o
r
p
er
f
o
r
m
in
g
ac
tiv
atio
n
f
u
n
ctio
n
s
.
ML
Ps
ca
n
lear
n
co
m
p
lex
p
atter
n
s
th
r
o
u
g
h
t
h
e
p
r
o
ce
s
s
o
f
b
ac
k
p
r
o
p
ag
atio
n
wh
er
ein
th
e
weig
h
ts
ar
e
m
o
d
if
i
ed
b
y
r
ev
er
s
in
g
t
h
e
p
r
o
p
a
g
atio
n
o
f
er
r
o
r
s
.
T
h
ey
d
o
ex
ce
e
d
in
g
ly
well
o
n
task
s
s
u
ch
as
im
ag
e
r
ec
o
g
n
itio
n
an
d
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
b
ec
au
s
e
th
e
y
ca
n
m
im
ic
n
o
n
lin
ea
r
in
ter
ac
tio
n
s
.
A
p
icto
r
ial
r
ep
r
esen
tatio
n
o
f
a
n
ML
P
ar
ch
itectu
r
e
is
s
h
o
wn
in
Fig
u
r
e
2
.
Per
f
o
r
m
an
ce
r
e
q
u
ir
em
e
n
ts
f
o
r
ML
Ps
r
eq
u
ir
e
o
p
tim
al
s
ettin
g
s
o
f
ch
ar
ac
ter
is
tic
p
ar
am
eter
s
lik
e
th
e
lear
n
in
g
r
a
te
an
d
th
e
c
o
u
n
t
o
f
h
id
d
en
lay
er
s
am
o
n
g
o
th
er
s
.
Fig
u
r
e
2
.
A
m
u
lti
-
u
n
it p
e
r
ce
p
t
r
o
n
with
2
h
id
d
e
n
lay
er
s
o
f
6
4
an
d
3
2
n
eu
r
o
n
s
in
ea
ch
lay
er
r
esp
ec
tiv
ely
Alg
o
r
ith
m
1.
Mu
lti
-
u
n
it p
e
r
ce
p
tr
o
n
1.
Model initialization
Weights W
(l)
and biases b
(l)
are initialized for each layer of MLP.
2.
Defining the architecture of MLP namely:
˗
L: Total number of layers in MLP.
˗
h
l
: Number of neurons in each layer l.
˗
: Learning rate.
˗
E: Number of iterations/epochs.
˗
Rectified Linear Unit (ReLU
) activation for the hidden layers,
(
)
=
max
(
0
,
)
˗
Sigmoid activation function for the output layer, (z)
1
1
+
−
3.
Training the model
for e = 1 to E:
a.
Forward propagation
˗
Input to network a
(0)
=x
˗
For each layer l=1 to L
-
1 (all hidden layers):
z
(l)
=W
(l)
.a
(l
-
1)
+
b
(l)
a
(l)
=ReLU((z
(l)
))
˗
When
output layer reached l=L:
z
(L)
=W
(L)
.a
(L
-
1)
+b
(L)
a
(L)
= Sigmoid(z(L))
a
(L)
represents the predicted output
̂
.
b.
Loss computation
Since classification loss is computed using binary cross
-
entropy function
=
−
1
∑
[
(
̂
)
+
(
1
−
)
(
1
−
̂
)
]
=
1
c.
Backward propagation
˗
Computation of gradient of loss with respect to output
(
)
=
(
)
⊙
′
(
(
)
)
˗
Propagating the error through hidden layers backward
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
2
1
-
332
326
For
=
−
1
to 1:
(
)
=
(
(
+
1
)
)
.
(
+
1
)
⊙
′
(
(
)
)
d.
Updating parameters using Adam optimizer
4.
Th
e
en
d
mo
de
l
co
ns
is
ts
of
co
mp
ut
ed
we
ig
ht
s
an
d
bi
as
es
fo
r
al
l
la
ye
rs
an
d
ou
tp
ut
is
predicted using forward propagation through the trained parameters given by formula
̂
=
(
(
)
)
3
.
3
.
3
.
Vo
t
ing
cla
s
s
if
ier
I
t
is
an
en
s
em
b
le
tech
n
iq
u
e
t
h
at
u
s
es
s
ev
er
al
m
o
d
els
to
e
n
h
an
ce
th
e
ac
cu
r
ac
y
o
f
class
if
icatio
n
.
I
t
u
s
es
m
ajo
r
ity
v
o
tin
g
o
r
p
r
o
b
ab
ilit
y
av
er
ag
in
g
to
co
m
b
i
n
e
p
r
ed
ictio
n
s
f
r
o
m
v
ar
i
o
u
s
class
if
ier
s
(
s
u
ch
as
d
ec
is
io
n
tr
ee
s
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
)
.
B
y
u
tili
zin
g
th
e
ad
v
an
tag
es
o
f
v
ar
io
u
s
m
o
d
els,
th
is
m
eth
o
d
im
p
r
o
v
es r
esil
ien
ce
an
d
lo
wer
s
th
e
p
o
s
s
ib
ilit
y
o
f
o
v
e
r
f
itti
n
g
.
4.
RE
SU
L
T
ANAL
YSI
S
T
h
e
m
o
d
els
wer
e
test
ed
to
f
o
r
ec
ast
h
ea
lth
co
n
d
itio
n
s
s
u
ch
as
Ast
h
m
a,
Diab
etes,
Stro
k
e,
an
d
h
ea
r
t
d
is
ea
s
es.
Fo
r
th
at
p
u
r
p
o
s
e,
tw
o
p
r
im
a
r
y
m
o
d
els
h
a
v
e
b
ee
n
u
tili
ze
d
:
XGBo
o
s
t
c
lass
if
ier
(
XGB
C
)
an
d
ANN.
Fu
r
th
er
r
ef
i
n
in
g
o
f
r
esu
lts
was a
ch
iev
ed
u
s
in
g
v
o
tin
g
class
if
ier
b
y
tak
i
n
g
b
o
th
m
o
d
els to
g
et
h
er
.
T
h
e
ap
p
r
o
ac
h
u
s
es
th
e
XG
B
o
o
s
t
m
o
d
el
with
th
e
XG
B
C
la
s
s
if
ier
f
r
o
m
th
e
XG
B
o
o
s
t
lib
r
ar
y
,
o
p
tim
ized
with
_
_
=
an
d
ev
alu
ated
u
s
in
g
lo
g
lo
s
s
.
T
h
e
f
o
r
m
er
is
tr
ain
ed
u
s
in
g
d
ef
au
lt
p
ar
am
eter
s
an
d
th
e
r
esu
lts
wer
e
r
o
b
u
s
t
ac
r
o
s
s
all
tar
g
et
d
i
s
ea
s
es.
T
h
e
m
o
d
el
d
e
m
o
n
s
tr
a
ted
h
ig
h
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
,
b
en
ef
itti
n
g
f
r
o
m
XGBo
o
s
t’
s
ab
ilit
y
to
h
an
d
le
m
is
s
in
g
d
ata
an
d
ca
p
t
u
r
e
co
m
p
lex
r
elatio
n
s
h
ip
s
.
T
h
e
ANN
was d
esig
n
ed
u
s
in
g
th
e
Ker
as lib
r
ar
y
in
T
en
s
o
r
Flo
w,
with
a
s
eq
u
en
tial a
r
ch
itectu
r
e
h
av
in
g
th
r
ee
f
u
lly
co
n
n
ec
ted
lay
er
s
:
6
4
n
eu
r
o
n
s
with
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U)
ac
tiv
atio
n
in
th
e
f
ir
s
t
lay
e
r
,
3
2
n
eu
r
o
n
s
with
R
eL
U
in
t
h
e
h
id
d
en
lay
e
r
,
an
d
a
s
in
g
le
n
eu
r
o
n
with
s
ig
m
o
id
ac
ti
v
atio
n
f
o
r
b
i
n
ar
y
class
if
icatio
n
r
u
n
n
in
g
f
o
r
5
0
e
p
o
ch
s
.
T
h
e
m
o
d
el
u
s
ed
th
e
A
d
am
o
p
tim
izer
,
b
in
ar
y
cr
o
s
s
-
e
n
tr
o
p
y
lo
s
s
f
u
n
ctio
n
with
ac
cu
r
ac
y
as
th
e
ev
alu
at
io
n
cr
iter
io
n
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
m
o
d
el
as
ev
alu
ated
o
n
th
e
d
atasets
is
as
tab
u
lated
in
T
ab
le
1
.
T
ab
le
1
.
Acc
u
r
ac
y
o
f
d
if
f
e
r
en
t
m
o
d
els f
o
r
d
is
ea
s
e
p
r
ed
ictio
n
D
i
sea
s
e
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
A
st
h
m
a
X
G
B
C
ANN
V
o
t
i
n
g
C
l
a
ssi
f
i
e
r
9
5
.
8
2
9
5
.
8
2
9
5
.
8
2
D
i
a
b
e
t
e
s
X
G
B
C
ANN
V
o
t
i
n
g
C
l
a
ssi
f
i
e
r
9
7
.
0
8
5
9
6
.
7
6
9
6
.
6
8
S
t
r
o
k
e
X
G
B
C
ANN
V
o
t
i
n
g
C
l
a
ssi
f
i
e
r
9
4
.
2
8
9
4
.
9
1
9
4
.
9
1
H
e
a
r
t
d
i
s
e
a
s
e
X
G
B
C
ANN
V
o
t
i
n
g
C
l
a
ssi
f
i
e
r
9
4
.
4
5
9
4
.
6
1
9
4
.
5
2
T
h
e
class
if
icatio
n
r
e
p
o
r
ts
f
o
r
s
tr
o
k
e,
d
iab
etes,
asth
m
a,
an
d
h
ea
r
t
d
is
ea
s
e
p
r
e
d
ictio
n
s
ar
e
illu
s
tr
ated
in
Fig
u
r
es
3
to
6
.
Fo
r
s
tr
o
k
e
an
d
asth
m
a
in
Fig
u
r
es
3
a
n
d
5
,
th
e
m
o
d
el
ac
h
iev
ed
ex
ce
llen
t
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
es
f
o
r
th
e
n
eg
ativ
e
cl
ass
(
all
ab
o
v
e
0
.
9
5
)
,
wh
ile
p
o
s
itiv
e
class
m
etr
ic
s
wer
e
a
b
s
en
t
d
u
e
to
class
im
b
alan
ce
;
n
o
n
eth
eless
,
m
ac
r
o
an
d
weig
h
ted
av
e
r
ag
es
r
em
ain
ed
r
o
b
u
s
t.
I
n
d
iab
etes
p
r
e
d
ictio
n
in
Fig
u
r
e
4
,
s
tr
o
n
g
p
e
r
f
o
r
m
an
ce
was
o
b
s
er
v
ed
f
o
r
b
o
th
class
es,
with
p
o
s
itiv
e
class
p
r
ec
is
io
n
,
r
e
ca
ll,
an
d
F1
-
s
co
r
es
ex
ce
ed
in
g
0
.
7
5
,
a
n
d
o
v
er
all
a
v
er
ag
es
ab
o
v
e
0
.
9
5
,
r
e
f
lectin
g
b
alan
ce
d
d
etec
tio
n
.
Fo
r
h
ea
r
t
d
is
ea
s
e
in
Fig
u
r
e
6
,
th
e
m
o
d
el
m
ain
tain
e
d
h
ig
h
s
co
r
es
f
o
r
th
e
n
e
g
ativ
e
class
,
w
h
ile
p
o
s
itiv
e
class
m
etr
ics
wer
e
m
o
d
e
r
ate,
lead
i
n
g
to
s
o
lid
m
ac
r
o
a
n
d
weig
h
t
ed
av
er
ag
es.
T
h
ese
r
esu
lts
u
n
d
er
s
co
r
e
th
e
m
o
d
el’
s
s
tr
o
n
g
an
d
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
i
n
ac
c
u
r
ately
i
d
en
tify
in
g
b
o
th
n
e
g
ativ
e
a
n
d
p
o
s
itiv
e
ca
s
es
ac
r
o
s
s
all
d
is
e
ase
ca
teg
o
r
ies
an
d
d
em
o
n
s
tr
ate
th
e
m
o
d
el’
s
r
o
b
u
s
t c
ap
ab
ilit
y
an
d
p
o
s
itiv
e
im
p
a
ct
in
m
u
lti
-
d
is
ea
s
e
p
r
ed
ictio
n
.
T
h
e
u
s
er
in
ter
f
ac
e
d
ash
b
o
ar
d
p
r
o
v
id
es
u
s
er
s
with
a
clea
r
a
n
d
in
ter
ac
tiv
e
m
ea
n
s
to
i
n
p
u
t
th
eir
d
ata
an
d
v
iew
p
r
elim
in
ar
y
r
esu
lts
.
Data
co
llectio
n
was
f
ac
ilit
ated
b
y
th
e
s
tr
u
ctu
r
e
d
q
u
esti
o
n
n
air
e
illu
s
tr
ated
in
Fig
u
r
e
7
,
wh
ic
h
en
s
u
r
e
d
co
m
p
r
eh
en
s
iv
e
a
n
d
s
tan
d
ar
d
ized
i
n
p
u
t
f
r
o
m
all
u
s
er
s
.
T
h
e
o
u
t
p
u
t
o
f
th
e
p
r
ed
ictiv
e
m
o
d
el,
p
r
esen
ted
in
Fig
u
r
e
8
,
v
is
u
ally
d
is
p
lay
s
th
e
p
er
ce
n
tag
e
r
is
k
o
f
ea
c
h
d
is
ea
s
e
f
o
r
ev
er
y
p
ar
ticip
an
t
,
h
ig
h
lig
h
tin
g
v
ar
iatio
n
s
a
n
d
en
ab
lin
g
tar
g
eted
an
aly
s
is
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
ch
r
o
n
ic
d
is
ea
s
e
r
i
s
k
a
s
s
es
s
men
t
(
Ha
r
in
i S
h
a
d
a
k
s
h
a
r
a
p
p
a
)
327
Fig
u
r
e
3
.
C
lass
if
icatio
n
r
ep
o
r
t
f
o
r
s
tr
o
k
e
p
r
ed
ictio
n
r
ep
r
esen
tin
g
p
r
ec
is
io
n
,
r
ec
all,
F
1
-
s
co
r
e
f
o
r
p
o
s
itiv
e,
n
eg
ativ
e
class
es a
lo
n
g
with
m
ac
r
o
an
d
weig
h
ted
a
v
er
ag
e
Fig
u
r
e
4
.
C
lass
if
icatio
n
r
ep
o
r
t
f
o
r
d
ia
b
etes p
r
ed
ictio
n
r
ep
r
ese
n
tin
g
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e
f
o
r
p
o
s
itiv
e,
n
eg
ativ
e
class
es a
lo
n
g
with
m
ac
r
o
an
d
weig
h
ted
a
v
er
ag
e
Fig
u
r
e
5
.
C
lass
if
icatio
n
r
ep
o
r
t
f
o
r
asth
m
a
p
r
ed
ictio
n
r
ep
r
esen
tin
g
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e
f
o
r
p
o
s
itiv
e,
n
eg
ativ
e
class
es a
lo
n
g
with
m
ac
r
o
an
d
weig
h
ted
a
v
er
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
2
1
-
332
328
Fig
u
r
e
6
.
C
lass
if
icatio
n
r
ep
o
r
t
f
o
r
h
ea
r
t d
is
ea
s
e
p
r
ed
ictio
n
r
e
p
r
esen
tin
g
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e
f
o
r
p
o
s
itiv
e,
n
eg
ativ
e
class
es a
lo
n
g
with
m
ac
r
o
a
n
d
weig
h
ted
av
er
ag
e
Fig
u
r
e
7
.
Qu
esti
o
n
n
air
e
to
c
o
llect
d
ata
f
o
r
a
n
aly
s
is
Fig
u
r
e
8
.
Dis
ea
s
e
r
is
k
o
u
tp
u
t o
f
th
e
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Hyb
r
id
ma
ch
in
e
lea
r
n
in
g
fr
a
mewo
r
k
fo
r
ch
r
o
n
ic
d
is
ea
s
e
r
i
s
k
a
s
s
es
s
men
t
(
Ha
r
in
i S
h
a
d
a
k
s
h
a
r
a
p
p
a
)
329
5.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
in
tr
o
d
u
ce
s
a
s
y
s
tem
d
ev
el
o
p
ed
to
p
r
e
d
ict
th
e
r
is
k
o
f
f
o
u
r
o
f
th
e
m
o
s
t
s
ig
n
if
ic
an
t
ch
r
o
n
ic
d
is
ea
s
es
n
am
ely
asth
m
a,
d
iab
etes,
s
tr
o
k
e,
an
d
ca
r
d
io
v
ascu
l
ar
d
is
ea
s
e,
b
y
m
ak
in
g
u
s
e
o
f
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es.
T
h
e
m
o
d
el
ac
h
ie
v
es
r
em
ar
k
a
b
le
ac
cu
r
ac
y
f
o
r
all
f
o
u
r
d
is
ea
s
es
v
ia
en
s
em
b
le
lear
n
in
g
u
s
in
g
XGBo
o
s
t
clas
s
if
ier
an
d
ANN
with
a
h
ar
d
v
o
tin
g
class
if
ier
ap
p
r
o
ac
h
.
T
h
e
r
esu
lts
ar
e
as
f
o
l
lo
ws:
I
n
th
e
ca
s
e
o
f
asth
m
a
p
r
ed
ictio
n
,
XGBo
o
s
t
class
if
ier
an
d
ANN
ac
h
iev
ed
ac
cu
r
ac
ies
o
f
9
5
.
8
2
%
an
d
9
5
.
8
2
%
r
esp
ec
tiv
ely
,
wh
er
ea
s
th
e
v
o
tin
g
class
if
ier
m
ain
tain
ed
an
ac
cu
r
ac
y
o
f
9
5
.
8
2
%.
I
n
d
ia
b
etes
p
r
o
g
n
o
s
is
,
XGBo
o
s
t
cla
s
s
if
ier
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
7
.
0
8
5
%,
ANN
lo
g
g
ed
9
6
.
7
6
%
w
h
ile
th
e
v
o
tin
g
class
if
ier
ev
alu
ated
th
e
m
etr
ics
to
9
6
.
6
8
%
ac
c
u
r
ac
y
.
Stro
k
e
p
r
ed
ictio
n
m
o
d
els
also
p
e
r
f
o
r
m
ed
well,
with
XGBo
o
s
t
class
if
ier
at
9
4
.
2
8
%,
ANN
at
9
4
.
9
1
%,
an
d
th
e
v
o
tin
g
class
if
ier
r
em
ain
i
n
g
c
o
n
s
is
ten
t
at
9
4
.
9
1
%.
T
h
e
p
r
ed
ictio
n
o
f
h
ea
r
t
d
is
ea
s
e
p
r
o
d
u
ce
d
an
ac
cu
r
ac
y
o
f
9
4
.
4
5
%
f
o
r
X
GB
o
o
s
t
clas
s
if
ier
,
9
4
.
6
1
%
f
o
r
ANN,
an
d
9
4
.
5
2
%
f
o
r
t
h
e
v
o
tin
g
class
if
ier
.
T
h
e
f
in
d
in
g
s
em
p
h
asize
th
e
d
ep
en
d
ab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
,
wh
ich
co
n
s
is
ten
tly
attain
s
ac
cu
r
ac
ies
ex
ce
ed
in
g
9
4
%.
T
h
is
ac
ce
n
tu
ates
th
e
p
r
o
m
is
e
o
f
en
s
em
b
le
lear
n
in
g
a
p
p
r
o
ac
h
es
in
th
e
h
e
alth
ca
r
e
d
o
m
ai
n
b
y
h
ar
n
ess
in
g
th
e
ad
v
an
tag
es o
f
i
n
d
iv
id
u
al
m
o
d
els wh
ile
allev
i
atin
g
th
eir
lim
itatio
n
s
.
A
w
e
b
ap
p
l
i
c
a
t
io
n
t
h
a
t
i
s
d
es
i
g
n
e
d
t
o
b
e
u
s
e
r
-
f
r
i
en
d
ly
wa
s
b
u
i
l
t
f
o
r
t
h
i
s
r
e
s
e
a
r
ch
t
o
en
h
an
c
e
th
e
a
c
c
e
s
s
i
b
i
l
i
t
y
o
f
t
h
i
s
ap
p
l
i
ca
t
io
n
t
o
h
e
a
l
th
c
a
r
e
p
r
o
v
id
er
s
a
n
d
p
a
t
i
e
n
t
s
.
I
t
i
n
c
lu
d
e
s
a
s
m
o
o
t
h
in
t
er
f
a
c
e
f
o
r
g
a
t
h
er
i
n
g
r
ea
l
-
t
i
m
e
i
n
p
u
t
s
th
r
o
u
g
h
a
q
u
e
s
t
i
o
n
n
a
i
r
e
t
h
a
t
c
a
n
c
o
n
tr
i
b
u
t
e
i
n
m
ak
i
n
g
a
c
cu
r
a
te
p
r
ed
i
c
t
io
n
s
o
f
t
h
e
f
o
u
r
c
h
r
o
n
i
c
co
n
d
i
t
i
o
n
s
.
I
n
co
n
c
lu
s
i
o
n
,
t
h
i
s
r
e
s
e
a
r
ch
c
a
l
l
s
a
t
t
e
n
t
i
o
n
t
o
th
e
p
r
o
m
i
s
e
o
f
m
a
c
h
in
e
l
e
ar
n
in
g
t
e
c
h
n
iq
u
e
s
i
n
a
c
cu
r
a
t
e
l
y
p
r
ed
i
c
t
i
n
g
a
r
a
n
g
e
o
f
ch
r
o
n
i
c
d
i
s
e
a
s
e
s
.
T
h
e
c
r
ea
t
i
o
n
o
f
an
e
r
g
o
n
o
m
i
c
w
e
b
a
p
p
l
i
ca
t
i
o
n
s
i
g
n
if
i
c
an
t
l
y
im
p
r
o
v
e
s
i
t
s
a
p
p
l
i
c
a
b
i
l
i
ty
,
s
u
c
c
es
s
f
u
l
l
y
co
n
n
e
c
t
in
g
cu
t
t
i
n
g
-
ed
g
e
t
e
ch
n
o
l
o
g
y
w
i
th
t
h
e
p
r
a
c
t
i
c
a
l
d
em
a
n
d
s
o
f
h
e
a
l
t
h
c
ar
e
i
n
r
e
a
l
-
w
o
r
l
d
s
e
t
t
in
g
s
.
T
h
i
s
r
e
s
ea
r
ch
o
p
e
n
s
u
p
n
e
w
a
v
en
u
e
s
f
o
r
a
d
v
an
c
em
e
n
t
s
in
p
r
e
d
i
ct
i
v
e
h
e
a
l
t
h
c
a
r
e
a
n
d
f
ac
i
l
i
t
a
t
e
s
t
h
e
o
n
g
o
in
g
d
i
g
i
t
a
l
e
v
o
l
u
t
io
n
in
m
e
d
i
ca
l
d
i
ag
n
o
s
i
s
a
n
d
p
r
o
g
n
o
s
i
s
.
T
h
er
e
a
r
e
n
u
m
er
o
u
s
ar
ea
s
wh
er
e
th
e
estab
lis
h
ed
s
y
s
te
m
co
u
l
d
b
e
im
p
r
o
v
ed
in
t
h
e
f
u
tu
r
e.
I
n
co
r
p
o
r
atin
g
d
ata
f
r
o
m
r
ea
l
-
tim
e
h
ea
lth
m
o
n
ito
r
in
g
wo
u
ld
s
ig
n
if
ican
tly
en
h
a
n
ce
th
e
s
y
s
tem
's
ca
p
ac
ity
f
o
r
d
y
n
am
ic
p
r
e
d
ictio
n
.
Fu
r
th
e
r
m
o
r
e,
in
clu
s
io
n
o
f
a
wid
er
v
ar
i
ety
o
f
d
is
ea
s
es
an
d
ailm
en
ts
co
u
ld
im
p
r
o
v
e
th
e
s
y
s
tem
'
s
ef
f
icac
y
f
o
r
th
o
r
o
u
g
h
h
ea
lth
an
aly
s
is
.
Als
o
,
s
tu
d
y
in
g
th
e
ef
f
ec
t
o
f
d
em
o
g
r
ap
h
ic
an
d
r
eg
io
n
al
d
if
f
er
en
ce
s
o
n
m
o
d
el
p
er
f
o
r
m
an
ce
wo
u
ld
lead
t
o
lar
g
e
-
s
ca
l
e
im
p
lem
en
tatio
n
o
f
th
e
m
o
d
el.
I
t
co
u
ld
also
b
e
u
s
ed
to
d
etec
t
d
is
ea
s
e
p
r
o
g
r
es
s
io
n
p
atter
n
s
an
d
to
m
ak
e
th
e
p
r
ed
ictio
n
m
o
r
e
p
er
s
o
n
alize
d
g
en
o
m
ic
d
ata
s
et
ca
n
b
e
in
p
u
t
.
T
o
en
h
an
ce
t
h
e
u
s
er
ex
p
er
ien
ce
wh
ile
u
s
in
g
th
e
p
latf
o
r
m
,
i
n
ter
p
r
etab
le
Ar
tific
ial
I
n
tellig
en
ce
tech
n
iq
u
es c
an
b
e
u
s
ed
to
p
r
o
v
id
e
ex
p
la
n
atio
n
s
o
f
t
h
e
f
ac
to
r
s
u
s
ed
d
u
r
in
g
p
r
e
d
ictio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
f
u
n
d
s
,
g
r
a
n
ts
,
o
r
o
th
e
r
s
u
p
p
o
r
t
wer
e
r
ec
eiv
ed
d
u
r
in
g
t
h
e
p
r
e
p
ar
atio
n
o
f
th
is
m
an
u
s
cr
ip
t.
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
Har
in
i Sh
ad
ak
s
h
ar
ap
p
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
ash
m
i K
.
B
.
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sh
r
ey
as D.
K.
✓
✓
✓
✓
✓
✓
✓
✓
So
m
an
ath
Mik
ali
✓
✓
✓
✓
✓
✓
Vis
h
esh
P.
Go
wd
a
✓
✓
✓
✓
Ud
ay
Sh
an
k
a
r
C
.
A.
✓
✓
✓
✓
✓
✓
✓
✓
Sid
d
ar
th
B
.
I
y
er
r
✓
✓
✓
✓
✓
✓
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.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
3
2
1
-
332
330
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
t
h
ey
h
av
e
n
o
co
n
f
lict
o
f
in
ter
est
(
f
in
an
cial,
p
er
s
o
n
al,
o
r
p
r
o
f
ess
io
n
al)
in
co
n
n
ec
tio
n
with
m
an
u
s
cr
ip
ts
an
d
h
a
v
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
i
n
ter
ests
o
r
p
e
r
s
o
n
al
r
elatio
n
s
h
ip
s
th
at
co
u
ld
h
a
v
e
ap
p
ea
r
ed
to
in
f
lu
e
n
ce
th
e
wo
r
k
r
ep
o
r
ted
in
th
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
R
KB
.
T
h
e
d
ata,
wh
ich
co
n
tain
in
f
o
r
m
atio
n
th
at
co
u
ld
co
m
p
r
o
m
is
e
th
e
p
r
iv
ac
y
o
f
r
esear
c
h
p
ar
ticip
an
ts
,
ar
e
n
o
t p
u
b
licly
a
v
ailab
le
d
u
e
to
ce
r
tain
r
estrictio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
H
a
c
k
e
r
,
“
T
h
e
b
u
r
d
e
n
o
f
c
h
r
o
n
i
c
d
i
s
e
a
s
e
,
”
M
a
y
o
C
l
i
n
i
c
Pro
c
e
e
d
i
n
g
s
:
I
n
n
o
v
a
t
i
o
n
s
,
Q
u
a
l
i
t
y
\
&
O
u
t
c
o
m
e
s
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
1
1
2
–
1
1
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ma
y
o
c
p
i
q
o
.
2
0
2
3
.
0
8
.
0
0
5
.
[
2
]
W
H
O
,
“
C
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
s
e
a
s
e
s
(
C
V
D
s)
.
”
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
A
c
c
e
ss
e
d
:
Ja
n
.
0
5
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
w
h
o
.
i
n
t
/
n
e
w
s
-
r
o
o
m
/
f
a
c
t
-
sh
e
e
t
s
/
d
e
t
a
i
l
/
c
a
r
d
i
o
v
a
s
c
u
l
a
r
-
d
i
s
e
a
se
s
-
(
c
v
d
s)
.
[
3
]
P
.
S
a
e
e
d
i
e
t
a
l
.
,
“
O
P
-
0
2
5
6
–
G
l
o
b
a
l
a
n
d
r
e
g
i
o
n
a
l
d
i
a
b
e
t
e
s
p
r
e
v
a
l
e
n
c
e
:
e
s
t
i
ma
t
e
s
f
o
r
2
0
1
9
a
n
d
p
r
o
j
e
c
t
i
o
n
s
f
o
r
2
0
3
0
a
n
d
2
0
4
5
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
D
i
a
b
e
t
e
s
Fe
d
e
ra
t
i
o
n
,
v
o
l
.
1
5
7
,
p
.
2
0
4
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
a
b
r
e
s.
2
0
1
9
.
1
0
7
8
4
.
[
4
]
B
.
B
o
e
h
m
k
e
a
n
d
B
.
G
r
e
e
n
w
e
l
l
,
H
a
n
d
s
-
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
S
K
L
e
rn
i
,
K
e
r
a
s
a
n
d
T
e
n
s
o
rF
l
o
w
,
2
n
d
e
d
.
S
e
b
a
s
t
o
p
o
l
,
C
A
:
O
’
R
e
i
l
l
y
M
e
d
i
a
,
2
0
1
9
.
[
5
]
N
I
D
D
K
,
“
D
i
a
b
e
t
e
s
,
h
e
a
r
t
d
i
s
e
a
se
,
&
s
t
r
o
k
e
,
”
N
a
t
i
o
n
a
l
I
n
s
t
i
t
u
t
e
o
f
D
i
a
b
e
t
e
s
a
n
d
D
i
g
e
s
t
i
v
e
a
n
d
K
i
d
n
e
y
D
i
s
e
a
s
e
s
,
A
c
c
e
s
s
e
d
:
J
a
n
.
0
5
,
2
0
2
5
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
n
i
d
d
k
.
n
i
h
.
g
o
v
/
h
e
a
l
t
h
-
i
n
f
o
r
m
a
t
i
o
n
/
d
i
a
b
e
t
e
s
/
o
v
e
r
v
i
e
w
/
p
r
e
v
e
n
t
i
n
g
-
p
r
o
b
l
e
ms
/
h
e
a
r
t
-
d
i
s
e
a
se
-
st
r
o
k
e
.
[
6
]
L.
D
.
G
o
p
i
s
e
t
t
i
,
S
.
K
.
L.
K
u
mm
e
r
a
,
S
.
R
.
P
a
t
t
a
mse
t
t
i
,
S
.
K
u
n
a
,
N
.
P
a
r
s
i
,
a
n
d
H
.
P
.
K
o
d
a
l
i
,
“
M
u
l
t
i
p
l
e
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
sy
s
t
e
m
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
S
t
r
e
a
ml
i
t
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
r
t
S
y
s
t
e
m
s
a
n
d
I
n
v
e
n
t
i
v
e
T
e
c
h
n
o
l
o
g
y
,
I
C
S
S
I
T
2
0
2
3
,
2
0
2
3
,
p
p
.
9
2
3
–
9
3
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
S
I
T5
5
8
1
4
.
2
0
2
3
.
1
0
0
6
0
9
0
3
.
[
7
]
S
.
R
a
y
,
S
.
A
l
i
,
a
n
d
A
.
K
a
t
i
y
a
r
,
“
M
u
l
t
i
p
l
e
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
M
L,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
I
EEE
2
0
2
3
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
C
o
n
t
r
o
l
a
n
d
N
e
t
w
o
r
k
i
n
g
,
I
C
AC
3
N
2
0
2
3
,
2
0
2
3
,
p
p
.
3
1
0
–
3
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
3
N
6
0
0
2
3
.
2
0
2
3
.
1
0
5
4
1
4
0
6
.
[
8
]
A
.
G
u
p
t
a
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
n
g
st
r
o
k
e
r
i
s
k
:
A
n
e
f
f
e
c
t
i
v
e
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
J
o
u
rn
a
l
o
f
N
e
u
ro
r
e
st
o
r
a
t
o
l
o
g
y
,
v
o
l
.
1
3
,
n
o
.
1
,
p
.
1
0
0
1
5
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
n
r
t
.
2
0
2
4
.
1
0
0
1
5
6
.
[
9
]
S
.
R
a
h
m
a
n
,
M
.
H
a
s
a
n
,
a
n
d
A
.
K
.
S
a
r
k
a
r
,
“
P
r
e
d
i
c
t
i
o
n
o
f
b
r
a
i
n
st
r
o
k
e
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
a
n
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
t
e
c
h
n
i
q
u
e
s,
”
E
u
ro
p
e
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
2
3
–
3
0
,
2
0
2
3
,
d
o
i
:
1
0
.
2
4
0
1
8
/
e
j
e
c
e
.
2
0
2
3
.
7
.
1
.
4
8
3
.
[
1
0
]
K
.
M
r
i
d
h
a
,
S
.
G
h
i
m
i
r
e
,
J
.
S
h
i
n
,
A
.
A
r
a
n
,
M
.
M
.
U
d
d
i
n
,
a
n
d
M
.
F
.
M
r
i
d
h
a
,
“
A
u
t
o
m
a
t
e
d
s
t
r
o
k
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
:
a
n
e
x
p
l
a
i
n
a
b
l
e
a
n
d
e
x
p
l
o
r
a
t
o
r
y
s
t
u
d
y
w
i
t
h
a
w
e
b
a
p
p
l
i
c
a
t
i
o
n
f
o
r
e
a
r
l
y
i
n
t
e
r
v
e
n
t
i
o
n
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
2
2
8
8
–
5
2
3
0
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
7
8
2
7
3
.
[
1
1
]
V
.
S
.
E
l
a
n
g
o
v
a
n
,
R
.
D
e
v
a
r
a
j
a
n
,
O
.
I
.
K
h
a
l
a
f
,
M
.
S
.
S
h
a
r
i
f
,
a
n
d
W
.
El
m
e
d
a
n
y
,
“
A
n
a
l
y
si
n
g
a
n
i
m
b
a
l
a
n
c
e
d
st
r
o
k
e
p
r
e
d
i
c
t
i
o
n
d
a
t
a
s
e
t
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
K
a
r
b
a
l
a
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Mo
d
e
r
n
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
2
4
6
–
2
5
9
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
6
4
0
/
2
4
0
5
-
6
0
9
X
.
3
3
5
5
.
[
1
2
]
M
.
K
.
H
a
sa
n
,
M
.
A
.
A
l
a
m,
D
.
D
a
s,
E.
H
o
s
sai
n
,
a
n
d
M
.
H
a
sa
n
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
e
n
s
e
mb
l
i
n
g
o
f
d
i
f
f
e
r
e
n
t
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
e
r
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
7
6
5
1
6
–
7
6
5
3
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
8
9
8
5
7
.
[
1
3
]
A
.
M
u
j
u
md
a
r
a
n
d
V
.
V
a
i
d
e
h
i
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
6
5
,
p
p
.
2
9
2
–
2
9
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.2
0
2
0
.
0
1
.
0
4
7
.
[
1
4
]
K
.
J
.
R
a
n
i
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
t
i
f
i
c
Re
s
e
a
r
c
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
p
p
.
2
9
4
–
3
0
5
,
Ju
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
2
6
2
8
/
C
S
EI
T2
0
6
4
6
3
.
[
1
5
]
M
.
S
o
n
i
a
n
d
D
.
S
.
V
a
r
m
a
,
“
D
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
Re
se
a
rc
h
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
0
9
,
n
o
.
0
9
,
2
0
2
0
.
[
1
6
]
A
.
Y
a
h
y
a
o
u
i
,
A
.
Jam
i
l
,
J
.
R
a
s
h
e
e
d
,
a
n
d
M
.
Y
e
si
l
t
e
p
e
,
“
A
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
sy
s
t
e
m
f
o
r
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
i
n
1
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
f
o
rm
a
t
i
c
s
a
n
d
S
o
f
t
w
a
re
E
n
g
i
n
e
e
r
i
n
g
C
o
n
f
e
re
n
c
e
:
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
D
i
g
i
t
a
l
T
r
a
n
s
f
o
rm
a
t
i
o
n
,
I
I
S
E
C
2
0
1
9
-
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
9
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
U
B
M
Y
K
4
8
2
4
5
.
2
0
1
9
.
8
9
6
5
5
5
6
.
[
1
7
]
E
.
J
.
J
o
e
t
a
l
.
,
“
P
a
t
t
e
r
n
s
o
f
m
e
d
i
c
a
l
c
a
r
e
u
t
i
l
i
z
a
t
i
o
n
a
c
c
o
r
d
i
n
g
t
o
e
n
v
i
r
o
n
m
e
n
t
a
l
f
a
c
t
o
r
s
i
n
a
s
t
h
m
a
a
n
d
c
h
r
o
n
i
c
o
b
s
t
r
u
c
t
i
v
e
p
u
l
m
o
n
a
r
y
d
i
s
e
a
s
e
p
a
t
i
e
n
t
s
,
”
K
o
r
e
a
n
J
o
u
r
n
a
l
o
f
I
n
t
e
r
n
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
3
6
,
n
o
.
5
,
p
p
.
1
1
4
6
–
1
1
5
6
,
2
0
2
1
,
d
o
i
:
1
0
.
3
9
0
4
/
K
J
I
M
.
2
0
2
0
.
1
6
8
.
[
1
8
]
H
.
H
w
a
n
g
,
J.
H
.
Ja
n
g
,
E.
Le
e
,
H
.
S
.
P
a
r
k
,
a
n
d
J.
Y
.
L
e
e
,
“
P
r
e
d
i
c
t
i
o
n
o
f
t
h
e
n
u
m
b
e
r
o
f
a
st
h
m
a
p
a
t
i
e
n
t
s u
si
n
g
e
n
v
i
r
o
n
m
e
n
t
a
l
f
a
c
t
o
r
s
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
R
e
sp
i
ra
t
o
ry
Re
se
a
r
c
h
,
v
o
l
.
2
4
,
n
o
.
1
,
p
.
3
0
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
9
3
1
-
0
2
3
-
0
2
6
1
6
-
x.
[
1
9
]
M
.
Lo
u
i
si
a
s
,
A
.
R
a
ma
d
a
n
,
A
.
S
.
N
a
j
a
,
a
n
d
W
.
P
h
i
p
a
t
a
n
a
k
u
l
,
“
T
h
e
e
f
f
e
c
t
s
o
f
t
h
e
e
n
v
i
r
o
n
me
n
t
o
n
a
st
h
m
a
d
i
s
e
a
se
a
c
t
i
v
i
t
y
,
”
I
m
m
u
n
o
l
o
g
y
a
n
d
Al
l
e
r
g
y
C
l
i
n
i
c
s
o
f
N
o
rt
h
Am
e
ri
c
a
,
v
o
l
.
3
9
,
n
o
.
2
,
p
p
.
1
6
3
–
1
7
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
a
c
.
2
0
1
8
.
1
2
.
0
0
5
.
[
2
0
]
W
.
K
.
D
.
Ja
y
a
m
i
n
i
,
F
.
M
i
r
z
a
,
M
.
A
si
f
N
a
e
e
m,
a
n
d
A
.
H
.
Y
.
C
h
a
n
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
p
r
e
d
i
c
t
i
n
g
r
i
sk
o
f
a
s
t
h
ma
e
x
a
c
e
r
b
a
t
i
o
n
s
:
A
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
Me
d
i
c
a
l
S
y
st
e
m
s
,
v
o
l
.
4
8
,
n
o
.
1
,
p
.
4
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
9
1
6
-
024
-
0
2
0
6
1
-
3.
[
2
1
]
E.
D
r
i
t
s
a
s
a
n
d
M
.
Tr
i
g
k
a
,
“
Ef
f
i
c
i
e
n
t
d
a
t
a
-
d
r
i
v
e
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
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
s
r
i
s
k
p
r
e
d
i
c
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
3
,
p
.
1
1
6
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
0
3
1
1
6
1
.
[
2
2
]
C
.
M
.
B
h
a
t
t
,
P
.
P
a
t
e
l
,
T.
G
h
e
t
i
a
,
a
n
d
P
.
L.
M
a
z
z
e
o
,
“
Ef
f
e
c
t
i
v
e
h
e
a
r
t
d
i
sea
se
p
r
e
d
i
c
t
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
Al
g
o
r
i
t
h
m
s
,
v
o
l
.
1
6
,
n
o
.
2
,
p
.
8
8
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
6
0
2
0
0
8
8
.
[
2
3
]
M
.
K
a
v
i
t
h
a
,
G
.
G
n
a
n
e
sw
a
r
,
R
.
D
i
n
e
sh
,
Y
.
R
.
S
a
i
,
a
n
d
R
.
S
.
S
u
r
a
j
,
“
H
e
a
r
t
d
i
se
a
se
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
h
y
b
r
i
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
v
e
n
t
i
v
e
C
o
m
p
u
t
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s,
I
C
I
C
T
2
0
2
1
,
2
0
2
1
,
p
p
.
1
3
2
9
–
1
3
3
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
T5
0
8
1
6
.
2
0
2
1
.
9
3
5
8
5
9
7
.
[
2
4
]
R
.
R
.
S
a
r
r
a
,
A
.
M
.
D
i
n
a
r
,
a
n
d
M
.
A
.
M
o
h
a
mm
e
d
,
“
En
h
a
n
c
e
d
a
c
c
u
r
a
c
y
f
o
r
h
e
a
r
t
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
9
,
n
o
.
1
,
p
p
.
3
7
5
–
3
8
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
9
.
i
1
.
p
p
3
7
5
-
3
8
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.