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.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
1
6
8
9
~
1
6
9
6
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/
ijece
.
v
11
i
2
.
pp
1
6
8
9
-
1
6
9
6
1689
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
M
a
chine learning
mo
del f
o
r
clinica
l
na
med en
tit
y
r
e
co
g
nition
Ra
v
ik
um
a
r
J
.
1
,
R
a
m
a
k
a
nth
K
um
a
r
P
.
2
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
Dr.
Am
b
e
d
k
a
r
In
stit
u
te o
f
Tec
h
n
o
lo
g
y
,
Be
n
g
a
l
u
ru
,
I
n
d
ia
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
Ra
sh
tree
y
a
Vi
d
y
a
lay
a
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
Be
n
g
a
lu
r
u
,
I
n
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
2
,
2
0
20
R
ev
is
ed
Au
g
1
,
2
0
2
0
Acc
ep
ted
Sep
2
5
,
2
0
2
0
To
e
x
trac
t
imp
o
rta
n
t
c
o
n
c
e
p
ts
(
n
a
m
e
d
e
n
ti
ti
e
s)
fro
m
c
li
n
ica
l
n
o
tes
,
m
o
st
wid
e
ly
u
se
d
NL
P
tas
k
is
n
a
m
e
d
e
n
ti
ty
re
c
o
g
n
it
i
o
n
(NER).
I
t
is
f
o
u
n
d
fro
m
th
e
li
tera
tu
re
t
h
a
t
se
v
e
ra
l
re
se
a
rc
h
e
rs
h
a
v
e
e
x
ten
siv
e
l
y
u
se
d
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
fo
r
c
li
n
ica
l
NER.
T
h
e
m
o
st
fu
n
d
a
m
e
n
tal
tas
k
s
a
m
o
n
g
t
h
e
m
e
d
ica
l
d
a
ta
m
in
in
g
tas
k
s
a
re
m
e
d
ica
l
n
a
m
e
d
e
n
ti
ty
re
c
o
g
n
it
io
n
a
n
d
n
o
r
m
a
li
z
a
ti
o
n
.
M
e
d
ica
l
n
a
m
e
d
e
n
ti
t
y
re
c
o
g
n
it
io
n
is
d
iffere
n
t
fr
o
m
g
e
n
e
ra
l
NER
in
v
a
ri
o
u
s
wa
y
s.
H
u
g
e
n
u
m
b
e
r
o
f
a
l
t
e
r
n
a
t
e
s
p
e
l
l
i
n
g
s
a
n
d
s
y
n
o
n
y
m
s
c
r
e
a
t
e
e
x
p
l
o
s
i
o
n
o
f
w
o
r
d
v
o
c
a
b
u
l
a
r
y
s
i
z
e
s
.
T
h
i
s
r
e
d
u
c
e
s
t
h
e
m
e
d
i
c
i
n
e
d
i
c
t
i
o
n
a
r
y
e
f
f
i
c
i
e
n
c
y
.
E
n
t
i
t
i
e
s
o
ften
c
o
n
sist o
f
l
o
n
g
se
q
u
e
n
c
e
s o
f
to
k
e
n
s,
m
a
k
i
n
g
h
a
rd
e
r
to
d
e
tec
t
b
o
u
n
d
a
ries
e
x
a
c
tl
y
.
Th
e
n
o
tes
writt
e
n
b
y
c
li
n
icia
n
s
writt
e
n
n
o
tes
a
re
les
s
stru
c
tu
re
d
a
n
d
a
re
in
m
in
ima
l
g
ra
m
m
a
ti
c
a
l
fo
rm
with
c
ry
p
ti
c
sh
o
rt
h
a
n
d
.
Be
c
a
u
se
o
f
t
h
is,
it
p
o
se
s
c
h
a
ll
e
n
g
e
s
in
n
a
m
e
d
e
n
ti
t
y
re
c
o
g
n
it
i
o
n
.
G
e
n
e
ra
ll
y
,
NER
sy
ste
m
s
a
re
e
i
t
h
e
r
r
u
l
e
b
a
s
e
d
o
r
p
a
t
t
e
r
n
b
a
s
e
d
.
T
h
e
r
u
l
e
s
a
n
d
p
a
t
t
e
r
n
s
a
r
e
n
o
t
g
e
n
e
r
a
l
i
z
a
b
l
e
b
e
c
a
u
s
e
o
f
t
h
e
d
i
v
e
r
s
e
w
r
i
t
i
n
g
s
t
y
l
e
o
f
c
l
i
n
i
c
i
a
n
s
.
Th
e
sy
ste
m
s
th
a
t
u
se
m
a
c
h
in
e
lea
rn
in
g
b
a
se
d
a
p
p
ro
a
c
h
t
o
re
so
l
v
e
th
e
se
issu
e
s
fo
c
u
s
o
n
c
h
o
o
sin
g
e
ffe
c
ti
v
e
fe
a
tu
re
s
fo
r
c
las
sifier
b
u
il
d
i
n
g
.
In
th
is
wo
r
k
,
m
a
c
h
in
e
lea
rn
i
n
g
b
a
se
d
a
p
p
ro
a
c
h
h
a
s b
e
e
n
u
se
d
t
o
e
x
trac
t
th
e
c
li
n
ica
l
d
a
ta i
n
a
re
q
u
ire
d
m
a
n
n
e
r.
K
ey
w
o
r
d
s
:
C
lin
ical
NE
R
Ma
ch
in
e
lear
n
in
g
Nam
ed
en
tity
r
ec
o
g
n
itio
n
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
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
av
ik
u
m
ar
J
.
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
Dr
.
Am
b
ed
k
a
r
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
B
en
g
alu
r
u
,
I
n
d
ia
E
m
ail:
r
av
ij0
4
1
@
d
r
-
ait.
o
r
g
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
atien
t’
s
d
ata
r
an
g
in
g
f
r
o
m
d
ia
g
n
o
s
es,
tr
ea
tm
en
ts
,
p
r
o
b
lem
s
,
m
e
d
icatio
n
s
to
im
ag
in
g
an
d
clin
ical
n
o
tes
lik
e
d
is
ch
ar
g
e
s
u
m
m
ar
ies
ar
e
av
ailab
le
in
elec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
s
(
E
HR
)
.
Fo
r
q
u
ality
,
b
illi
n
g
an
d
o
u
tco
m
e
s
tr
u
ctu
r
ed
d
ata
ar
e
im
p
o
r
tan
t.
On
th
e
o
th
e
r
h
an
d
,
n
a
r
r
ativ
e
tex
t
is
m
o
r
e
en
g
ag
in
g
,
m
o
r
e
ex
p
r
ess
iv
e
an
d
ca
p
tu
r
es
p
atien
t’
s
d
ata
m
o
r
e
ac
cu
r
ately
.
C
lin
ical
n
o
tes
also
co
n
tain
d
ata
i
n
d
icatin
g
th
e
lev
el
o
f
co
n
ce
r
n
an
d
u
n
ce
r
tain
ty
t
o
o
t
h
er
s
wh
o
a
r
e
r
e
v
iewin
g
t
h
e
n
o
te.
Hen
ce
,
in
o
r
d
er
to
o
b
tain
clea
r
p
er
s
p
ec
tiv
e
o
n
th
e
co
n
d
itio
n
o
f
t
h
e
p
atie
n
t,
a
n
an
aly
s
is
o
f
n
a
r
r
ativ
e
tex
t
n
e
ed
s
to
b
e
d
o
n
e.
B
u
t,
th
e
m
an
u
al
an
aly
s
is
o
f
h
u
g
e
n
u
m
b
er
o
f
n
ar
r
ativ
e
te
x
t is tim
e
co
n
s
u
m
in
g
an
d
p
r
o
n
e
to
er
r
o
r
s
.
T
o
r
eso
lv
e
th
is
is
s
u
e,
m
ac
h
in
e
lear
n
in
g
b
ased
s
y
s
tem
s
ca
n
b
e
u
s
e
d
.
I
t
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
th
e
liter
atu
r
e
th
at
v
a
r
io
u
s
m
ac
h
in
e
lear
n
er
s
h
a
v
e
b
ee
n
u
s
ed
.
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
es
(
SVMs)
[
1
]
a
n
d
h
id
d
e
n
m
ar
k
o
v
m
o
d
el
(
HM
M)
[
2
]
ar
e
ex
am
p
les
o
f
s
u
ch
lear
n
e
r
s
.
T
o
u
n
d
er
s
tan
d
th
e
n
atu
r
al
la
n
g
u
ag
e
[
3
]
,
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
th
at
f
o
cu
s
es
o
n
d
ev
elo
p
m
en
t
o
f
m
o
d
el
s
is
b
ein
g
u
s
ed
.
T
h
e
f
r
am
ewo
r
k
o
f
NL
P
in
clu
d
es
m
o
d
u
les
f
o
r
s
y
n
tactic
p
r
o
ce
s
s
in
g
lik
e
to
k
en
izatio
n
,
p
ar
ts
o
f
s
p
ee
ch
ta
g
g
in
g
an
d
s
en
ten
ce
d
etec
tio
n
.
Mo
d
u
les
f
o
r
n
am
ed
en
tity
r
ec
o
g
n
itio
n
tag
g
in
g
,
ex
tr
ac
tio
n
o
f
r
elatio
n
an
d
co
n
ce
p
t
id
en
tific
atio
n
a
r
e
in
clu
d
ed
in
th
e
NL
P
s
y
s
tem
s
.
An
NL
P
s
y
s
te
m
th
at
h
as
s
em
an
tic
p
r
o
ce
s
s
in
g
m
o
d
els
f
o
r
e
x
tr
ac
tio
n
o
f
p
r
e
-
d
ef
in
ed
i
n
f
o
r
m
atio
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.
11
,
No
.
2
,
Ap
r
il
2
0
2
1
:
1
6
8
9
-
1696
1690
is
in
f
o
r
m
atio
n
ex
tr
ac
tio
n
s
y
s
tem
.
I
n
th
e
m
e
d
ical
f
ield
,
r
esear
ch
er
s
ar
e
u
s
in
g
NL
P
s
y
s
tem
s
f
o
r
id
en
tific
atio
n
o
f
b
io
m
ed
ical
co
n
ce
p
ts
an
d
clin
i
ca
l sy
n
d
r
o
m
es f
r
o
m
r
ad
io
lo
g
y
r
ep
o
r
ts
[
4
]
an
d
d
is
ch
ar
g
e
s
u
m
m
ar
ies [
5
]
.
C
lin
ical
r
esear
ch
er
s
an
d
o
th
er
m
ed
ical
o
p
er
atio
n
s
m
ak
e
u
s
e
o
f
im
p
o
r
tan
t
in
f
o
r
m
atio
n
e
x
tr
ac
ted
b
y
an
aly
s
is
o
f
clin
ical
n
o
tes
in
d
etailed
m
a
n
n
er
.
T
h
ese
cl
i
n
ical
n
o
tes
p
r
o
v
id
e
r
ich
an
d
d
etailed
m
ed
ical
in
f
o
r
m
atio
n
.
I
n
th
e
p
r
esen
t
wo
r
k
,
we
h
av
e
b
u
ilt
a
m
ac
h
i
n
e
lear
n
in
g
m
o
d
el
f
o
r
e
x
tr
ac
tio
n
o
f
m
ed
ical
NE
R
s
n
am
ely
d
is
ea
s
e,
test
an
d
tr
ea
tm
en
t.
An
an
aly
s
is
h
as
b
ee
n
d
o
n
e
f
r
o
m
th
e
tex
t
o
f
d
o
cto
r
’
s
n
o
tes
an
d
r
ec
o
r
d
s
g
en
er
ated
d
u
r
in
g
in
ter
ac
tio
n
with
p
atien
t.
2.
RE
L
AT
E
D
WO
RK
Dec
is
io
n
tr
ee
b
ased
NE
R
m
o
d
el
was
b
u
ilt
b
y
Sek
in
e
et
a
l
.
[
6
]
th
at
u
s
ed
f
ea
tu
r
es
s
u
ch
as
p
ar
t
-
of
-
s
p
ee
ch
tag
s
ex
tr
ac
ted
b
y
m
o
r
p
h
o
lo
g
ical
an
aly
ze
r
,
s
p
ec
iali
ze
d
d
ictio
n
ar
y
a
n
d
ch
a
r
ac
ter
b
ased
in
f
o
r
m
ati
o
n
.
T
h
is
was
d
ev
elo
p
ed
f
o
r
J
ap
a
n
ese.
B
ik
el
et
a
l.
[
7
]
u
s
ed
h
id
d
en
m
ar
k
o
v
m
o
d
el
(
HM
M)
f
o
r
i
d
en
tific
atio
n
o
f
n
am
ed
en
tity
.
Featu
r
es
lik
e
b
i
-
g
r
am
an
d
o
r
th
o
g
r
ap
h
ic
f
ea
tu
r
es
lik
e
wo
r
d
ca
s
e,
wo
r
d
s
h
ap
e
etc.
wer
e
u
s
ed
.
I
n
h
is
Ph
.
D
th
esis
,
B
o
r
th
wick
[
8
]
u
s
ed
m
ax
im
u
m
e
n
tr
o
p
y
(
M
ax
E
n
t)
alg
o
r
ith
m
.
Mc
C
allu
m
et
a
l.
[
9
]
ex
tr
ac
ted
NE
R
u
s
in
g
alg
o
r
ith
m
b
ased
o
n
co
n
d
itio
n
al
r
an
d
o
m
f
ield
s
.
A
s
em
i
Ma
r
k
o
v
co
n
d
itio
n
al
r
an
d
o
m
f
ield
alg
o
r
ith
m
was
p
r
o
p
o
s
ed
b
y
Sar
awa
g
i
e
t
a
l.
[
1
0
]
f
o
r
e
x
tr
ac
tio
n
o
f
n
am
ed
en
tity
.
T
h
e
r
esear
ch
es
ex
ten
d
ed
th
e
s
em
i
Ma
r
k
o
v
m
o
d
el
with
u
s
e
o
f
d
i
ctio
n
ar
y
an
d
n
o
tio
n
o
f
s
im
ilar
ity
f
u
n
ctio
n
.
An
o
v
er
all
s
u
r
v
e
y
o
f
NE
R
r
esear
ch
was p
r
o
v
id
ed
b
y
Naid
u
an
d
Sek
in
e
[
1
1
]
.
L
u
u
[
1
2
]
p
r
o
p
o
s
ed
a
f
r
am
e
wo
r
k
th
at
is
b
a
s
ed
o
n
d
if
f
e
r
en
t
tex
t
m
in
in
g
an
d
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
s
f
o
r
ad
d
r
ess
in
g
th
e
ch
allen
g
es
o
f
clin
ical
n
am
ed
en
tity
r
ec
o
g
n
itio
n
.
T
h
e
f
r
am
e
wo
r
k
p
r
o
p
o
s
ed
h
as
m
u
l
t
i
p
l
e
l
e
v
e
l
s
a
n
d
b
u
i
l
d
s
c
o
m
p
l
e
x
N
E
R
t
a
s
k
s
.
D
i
f
f
e
r
e
n
t
d
a
t
a
s
e
t
s
-
t
h
e
C
L
E
F
2
0
1
6
c
h
a
l
l
e
n
g
e
a
n
d
B
I
O
N
L
P
/
N
L
P
B
P
A
2
0
0
4
w
e
r
e
u
s
e
d
f
o
r
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
a
n
d
t
h
e
r
e
s
u
l
t
s
v
a
l
i
d
a
t
e
d
t
h
e
f
r
am
ewo
r
k
.
Ma
o
et
a
l
.
[
1
3
]
o
p
in
e
th
at
im
p
o
r
tan
t
clin
ical
in
f
o
r
m
atio
n
r
elate
d
to
d
ia
g
n
o
s
is
is
av
ailab
le
in
E
lectr
o
n
ic
m
e
d
ical
r
ec
o
r
d
.
B
y
d
ata
m
in
i
n
g
o
f
elec
tr
o
n
ic
m
e
d
ical
r
ec
o
r
d
,
r
ec
o
g
n
itio
n
o
f
m
ed
ical
n
am
ed
en
tity
is
d
o
n
e.
I
n
th
is
r
esear
ch
wo
r
k
,
au
th
o
r
s
h
av
e
tak
en
o
p
h
th
alm
i
c
elec
tr
o
n
ic
m
ed
ical
r
e
co
r
d
as
r
esear
ch
o
b
ject.
I
n
th
e
b
eg
in
n
in
g
,
u
n
d
er
th
e
g
u
id
an
ce
o
f
s
p
ec
ialis
t,
tr
ain
in
g
co
r
p
u
s
is
an
n
o
tated
.
L
ater
,
t
r
ain
ed
HM
M
m
o
d
el
is
u
s
ed
in
test
s
et
f
o
r
r
ec
o
g
n
itio
n
o
f
en
tity
.
Fin
ally
,
ex
p
er
im
e
n
t is co
n
d
u
cted
f
o
r
m
a
k
in
g
co
m
p
ar
is
o
n
b
etwe
en
t
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
i
t
h
m
a
n
d
t
h
e
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
w
o
r
d
s
e
g
m
e
n
t
a
t
i
o
n
m
o
d
e
l
.
T
h
e
r
e
s
u
l
t
s
o
f
t
h
e
ex
p
er
im
en
tatio
n
in
d
icate
th
at
t
h
e
alg
o
r
ith
m
ac
h
iev
es
g
o
o
d
r
esu
lts
in
t
h
e
n
a
m
ed
en
tity
r
ec
o
g
n
itio
n
o
f
e
l
e
c
t
r
o
n
i
c
m
e
d
i
c
a
l
r
e
c
o
r
d
.
L
i
e
t
a
l
.
[
1
4
]
p
r
o
p
o
s
e
d
a
d
e
e
p
n
e
u
r
a
l
m
o
d
e
l
B
i
L
S
T
M
-
A
t
t
-
C
R
F
t
h
a
t
i
s
a
c
o
m
b
i
n
a
t
i
o
n
o
f
b
i
d
i
r
e
c
t
i
o
n
a
l
l
o
n
g
-
s
h
o
r
t
t
i
m
e
m
e
m
o
r
y
n
e
t
w
o
r
k
a
n
d
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
s
m
.
T
h
i
s
i
m
p
r
o
v
e
d
t
h
e
p
er
f
o
r
m
an
ce
o
f
NE
R
in
C
h
in
ese
e
l
e
c
t
r
o
n
i
c
m
e
d
i
c
a
l
r
e
c
o
r
d
s
(
E
M
R
s
)
.
T
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
a
c
h
i
e
v
e
d
b
e
t
t
e
r
r
e
s
u
l
t
s
t
h
a
n
o
t
h
e
r
w
i
d
e
l
y
u
s
e
d
m
o
d
e
l
s
.
Qiu
et
a
l
.
[
1
5
]
wr
ite
th
at
th
e
g
o
al
o
f
t
h
e
clin
ical
n
am
ed
en
t
ity
r
ec
o
g
n
itio
n
(
C
NE
R
)
is
id
en
tific
atio
n
an
d
class
if
icatio
n
o
f
clin
ical
ter
m
s
lik
e
s
y
m
p
to
m
s
,
ex
a
m
s
,
tr
ea
tm
en
ts
,
d
is
ea
s
es.
T
h
is
is
a
cr
u
cial
an
d
f
u
n
d
am
e
n
tal
task
f
o
r
clin
ical
an
d
tr
a
n
s
latio
n
r
esear
ch
.
I
n
r
ec
en
t
y
ea
r
s
,
d
ee
p
lear
n
in
g
m
o
d
els
h
av
e
b
ee
n
s
u
cc
ess
f
u
l
in
C
NE
R
task
s
.
T
h
ese
m
o
d
els
d
ep
en
d
o
n
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
wh
ic
h
m
ain
tain
a
v
ec
to
r
o
f
h
id
d
en
ac
tiv
atio
n
s
t
h
at
p
r
o
p
a
g
ate
th
r
o
u
g
h
tim
e.
T
h
is
ca
u
s
es
to
o
m
u
ch
tim
e
f
o
r
m
o
d
el
tr
ain
in
g
.
I
n
th
e
p
r
esen
t
wo
r
k
,
th
e
r
esear
c
h
er
s
h
av
e
p
r
o
p
o
s
ed
a
r
esid
u
al
d
ilated
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
with
co
n
d
itio
n
al
r
a
n
d
o
m
f
ield
(
R
D
-
CN
N
-
C
R
F)
to
s
o
lv
e
it.
I
n
th
is
m
et
h
o
d
,
d
ictio
n
a
r
y
f
ea
tu
r
es
an
d
C
h
in
ese
ch
a
r
a
cter
s
ar
e
p
r
o
jecte
d
f
ir
s
t
in
to
d
en
s
e
v
ec
t
o
r
r
ep
r
es
en
tatio
n
s
.
L
ater
,
th
ey
ar
e
f
e
d
in
to
th
e
r
esid
u
al
d
ilated
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
to
ca
p
tu
r
e
c
o
n
tex
tu
al
f
ea
tu
r
es.
L
i
et
a
l
.
[
1
6
]
p
r
o
p
o
s
ed
a
m
o
d
el
co
m
b
in
in
g
lan
g
u
a
g
e
m
o
d
el
co
n
d
itio
n
al
r
an
d
o
m
f
ield
alg
o
r
ith
m
(
C
R
F)
an
d
bi
-
d
ir
ec
tio
n
al
l
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
n
etwo
r
k
s
(
B
iLST
M)
to
r
ea
lize
au
to
m
atic
r
ec
o
g
n
itio
n
a
n
d
en
tity
ex
tr
ac
tio
n
in
u
n
s
tr
u
ctu
r
ed
m
ed
ical
tex
ts
.
T
h
e
r
esear
ch
er
s
cr
awle
d
8
0
4
s
p
ec
if
icatio
n
s
o
f
d
r
u
g
f
o
r
asth
m
a
tr
ea
tm
en
t
f
r
o
m
th
e
I
n
ter
n
et.
L
ater
q
u
an
tizatio
n
is
d
o
n
e
f
o
r
t
h
e
n
o
r
m
alize
d
f
ield
o
f
d
r
u
g
s
p
ec
if
icatio
n
wo
r
d
b
y
a
v
ec
to
r
as
th
e
in
p
u
t
to
th
e
n
eu
r
al
n
etwo
r
k
.
E
x
p
er
im
en
tati
o
n
in
d
icate
d
t
h
at
r
ec
all,
s
y
s
tem
ac
cu
r
ac
y
a
n
d
F1
va
lu
e
ar
e
im
p
r
o
v
ed
b
y
5
.
2
%,
6
.
1
8
%
a
n
d
4
.
8
7
%
co
m
p
ar
ed
to
tr
ad
itio
n
al
m
ac
h
in
e
l
ea
r
n
in
g
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
ca
n
b
e
ap
p
lie
d
to
ex
tr
ac
t
n
am
ed
e
n
tity
in
f
o
r
m
atio
n
f
r
o
m
d
r
u
g
s
p
ec
if
icatio
n
.
Su
m
m
ar
is
in
g
th
e
co
n
ce
p
ts
,
th
e
elec
tr
o
n
ic
m
ed
ical
r
ec
o
r
d
is
a
d
e
s
cr
ip
tio
n
o
f
p
atien
ts
p
h
y
s
ical
c
o
n
d
i
t
i
o
n
[
1
7
]
.
N
a
m
e
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
i
s
t
h
e
m
e
t
h
o
d
u
s
e
d
f
o
r
c
l
i
n
i
c
a
l
d
a
t
a
e
x
t
r
a
c
t
i
o
n
.
T
h
e
N
E
R
w
a
s
a
c
o
m
b
i
n
a
t
i
o
n
o
f
d
i
c
t
i
o
n
a
r
y
a
n
d
r
u
l
e
s
[
1
8
]
.
I
n
c
l
i
n
i
c
a
l
d
e
c
i
s
i
o
n
,
N
L
P
h
a
s
b
e
c
o
m
e
r
e
c
e
n
t
t
r
e
n
d
[
1
9
]
.
R
e
s
e
a
r
c
h
e
r
s
h
a
v
e
e
v
a
l
u
a
t
e
d
v
a
r
i
o
u
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
w
i
t
h
v
a
r
i
o
u
s
f
e
a
t
u
r
e
s
[
2
0
]
.
U
M
L
S
,
C
t
a
k
e
s
a
n
d
M
e
d
l
i
n
e
w
e
r
e
i
n
t
r
o
d
u
c
e
d
a
s
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
a
n
d
u
s
i
n
g
s
e
m
i
-
M
a
r
k
o
v
m
o
d
e
l
,
a
n
a
c
c
u
r
a
c
y
o
f
8
5
.
2
3
%
w
a
s
a
c
h
i
e
v
e
d
[
2
1
]
.
W
a
n
g
e
t
a
l
.
[
2
2
]
c
o
n
s
t
r
u
c
t
e
d
t
a
g
g
e
d
s
y
m
p
t
o
m
c
o
r
p
u
s
i
n
c
l
u
d
i
n
g
1
1
,
6
1
3
c
h
i
e
f
c
o
m
p
l
a
i
n
t
s
.
W
an
g
et
a
l
.
[
2
3
]
co
m
p
leted
m
an
u
al
an
n
o
tatio
n
f
o
r
1
2
d
ata
o
f
liv
er
ca
n
ce
r
in
1
1
5
m
ed
ical
r
ec
o
r
d
s
.
Yan
et
a
l
.
[
2
4
]
p
u
t
f
o
r
war
d
a
u
n
ited
m
o
d
el
o
f
wo
r
d
s
eg
m
en
tatio
n
an
d
n
am
e
d
en
tity
r
ec
o
g
n
itio
n
b
ased
o
n
d
u
al
d
ec
o
m
p
o
s
itio
n
.
J
ian
b
o
,
et
a
l
.,
[
2
5
]
s
elec
ted
8
0
0
m
ed
ical
r
ec
o
r
d
s
a
n
d
estab
lis
h
ed
n
am
e
d
en
tity
tag
g
e
d
c
o
r
p
u
s
am
o
n
g
wh
ich
wo
r
d
s
eg
m
en
tatio
n
a
n
d
p
ar
t
-
of
-
s
p
ee
ch
ta
g
g
in
g
u
tili
ze
to
o
ls
d
ev
elo
p
e
d
b
y
Stan
f
o
r
d
Un
iv
e
r
s
ity
.
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
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
fo
r
cl
in
ica
l n
a
med
e
n
tity reco
g
n
itio
n
(
R
a
viku
m
a
r
J.
)
1691
C
lin
ical
No
tes
Data
Pre
Pro
ce
s
s
in
g
NE
R
u
s
in
g
Ma
ch
in
e
L
ea
r
n
in
g
Fra
m
ewo
r
k
C
la
s
s
if
ied
an
d
lab
eled
Data
3.
T
H
E
P
RO
P
O
SE
D
M
O
D
E
L
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
class
if
ies
clin
ical
d
ata
an
d
p
r
o
v
id
es
th
e
d
ata
to
co
n
ce
r
n
ed
e
x
p
er
t
u
s
in
g
m
ac
h
in
e
lear
n
in
g
f
r
am
ewo
r
k
an
d
NL
P
tech
n
iq
u
e.
I
n
th
e
m
an
u
al
s
y
s
tem
,
p
h
y
s
ician
s
an
d
n
u
r
s
es
h
av
e
to
g
o
th
r
o
u
g
h
th
e
m
ed
ical
d
ata
an
d
d
ir
ec
ts
th
is
d
ata
to
co
n
ce
r
n
ed
ex
p
er
ts
.
I
t
is
tim
e
co
n
s
u
m
in
g
,
ex
p
e
n
s
iv
e
an
d
ch
allen
g
in
g
task
.
T
h
e
r
ec
o
r
d
s
o
f
th
e
p
atien
ts
in
clu
d
e
m
e
d
ical
h
is
to
r
y
,
f
am
ily
h
is
to
r
y
etc.
T
h
e
s
ig
n
if
ican
t
d
if
f
er
en
ce
b
etwe
e
n
class
if
icatio
n
o
f
m
ed
ical
r
ec
o
r
d
s
an
d
g
en
er
al
tex
t c
lass
i
f
icatio
n
is
wo
r
d
d
is
tr
ib
u
tio
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
u
s
es
m
ac
h
in
e
lear
n
i
n
g
f
r
am
ewo
r
k
f
o
r
r
ec
o
g
n
izin
g
an
d
ex
tr
ac
tio
n
o
f
c
o
n
ce
p
ts
f
r
o
m
clin
ical
d
ata.
T
h
e
f
r
a
m
ewo
r
k
in
clu
d
es
an
ap
p
r
o
ac
h
k
n
o
wn
a
s
b
id
ir
e
ctio
n
al
lo
n
g
s
h
o
r
t
tem
m
em
o
r
y
-
co
n
d
itio
n
al
r
a
n
d
o
m
f
ield
(
L
STM
-
C
R
F)
in
itialized
with
g
en
er
al
-
p
u
r
p
o
s
e,
o
f
f
-
th
e
-
s
h
elf
wo
r
d
em
b
ed
d
in
g
s
.
Fig
u
r
e
1
d
e
p
icts
th
e
d
a
ta
f
lo
w
u
s
ed
in
th
e
p
r
o
p
o
s
ed
m
o
d
el.
Fig
u
r
e
1
.
Ma
ch
i
n
e
lear
n
in
g
f
r
a
m
ewo
r
k
f
o
r
clin
ical
NE
R
T
h
e
in
p
u
t is
=
(
1
,
2
,
3
,
…
.
)
wh
ich
in
d
icate
th
e
wo
r
d
s
in
a
s
en
ten
ce
T
h
e
o
u
tp
u
t is
0
=
{
1
,
2
,
3
,
.
.
)
wh
ich
in
d
icate
n
am
ed
en
tity
ta
g
s
C
o
n
d
itio
n
al
p
r
o
b
ab
ilit
y
is
(
1
,
2
,
3
,
.
.
|
1
,
2
,
3
,
…
.
)
T
h
is
ca
n
b
e
d
o
n
e
b
y
d
e
f
in
in
g
f
ea
tu
r
e
m
ap
;
Φ
(
i1
,
…
,
im
,
o1
,
…
,
om
)
∈
Rd
(
1
)
T
h
i
s
i
s
a
m
a
p
p
i
n
g
o
f
e
n
t
i
r
e
i
n
p
u
t
s
e
q
u
e
n
c
e
p
a
i
r
e
d
w
i
t
h
a
n
e
n
t
i
r
e
s
t
a
t
e
s
e
q
u
e
n
c
e
t
o
s
o
m
e
d
i
m
e
n
s
i
o
n
a
l
f
e
a
t
u
r
e
v
e
c
t
o
r
.
T
h
e
p
r
o
b
ab
ilit
y
as a
lo
g
-
lin
ea
r
m
o
d
el
with
th
e
p
ar
am
eter
v
ec
t
o
r
h
as b
ee
n
m
o
d
eled
as
(
2
)
P
(
o
|
i
;
w
)
=
ex
p
(
ω
.
Φ
(
i
,
i
)
∑
of
ex
p
(
ω
.
Φ
(
i
,
of
)
)
(
3
)
wh
er
e
o
r
an
g
es
o
v
er
all
p
o
s
s
ib
le
o
u
tp
u
t
s
eq
u
en
c
es.
T
h
e
e
x
p
r
ess
io
n
.
ᶲ
(
,
)
=
(
,
)
in
d
icate
s
a
s
co
r
in
g
h
o
w
well
th
e
s
tate
s
eq
u
en
ce
f
its
th
e
g
iv
e
n
in
p
u
t seq
u
en
ce
.
Hen
ce
s
co
r
e
ca
n
b
e
d
ef
i
n
ed
as,
−
(
,
)
=
∑
=
0
−
1
,
.
(
)
+
−
1
,
(
4
)
wh
er
e
−
1
,
o
i a
r
e
weig
h
t v
ec
t
o
r
is
th
e
b
ias co
r
r
esp
o
n
d
in
g
t
o
th
e
tr
an
s
itio
n
f
r
o
m
−
1
to
o
j1
esp
ec
tiv
ely
.
T
h
e
alg
o
r
ith
m
u
s
ed
f
o
r
th
e
o
v
er
all
p
r
o
ce
s
s
is
g
iv
e
n
in
Fig
u
r
e
2
.
Me
d
ical
r
ec
o
r
d
s
th
at
co
n
s
is
t
o
f
test
co
n
d
u
cte
d
,
p
atien
t’
s
h
ea
lth
s
tatu
s
,
r
esp
o
n
s
e
t
o
th
e
tr
ea
tm
e
n
ts
an
d
d
is
ea
s
es
ar
e
g
iv
e
n
as
in
p
u
t.
I
n
th
e
n
ex
t
s
tag
e,
co
n
ce
p
ts
lik
e
m
ed
ical
test
s
,
d
iag
n
o
s
is
an
d
tr
ea
tm
en
ts
m
en
tio
n
e
d
in
th
e
clin
ical
r
ec
o
r
d
s
ar
e
class
if
ied
in
to
ca
teg
o
r
ies.
L
ater
,
t
h
e
r
e
co
r
d
s
ar
e
d
i
v
id
ed
in
t
o
tr
ai
n
in
g
d
ata
an
d
test
in
g
d
ata.
7
0
%
o
f
d
ata
is
u
s
ed
as
tr
ain
in
g
d
ata
an
d
it
is
f
ed
to
th
e
m
o
d
el.
T
esti
n
g
d
ata
(
3
0
%
o
f
d
ata)
th
at
co
n
s
is
ts
o
f
p
atien
t’
s
in
f
o
r
m
atio
n
ar
e
f
ed
to
th
e
m
o
d
el.
On
ce
th
e
m
o
d
el
is
tu
n
ed
f
o
r
ac
cu
r
ac
y
,
th
e
m
o
d
el
will
b
e
r
ea
d
y
to
r
e
ce
iv
e
th
e
r
ea
l
d
ata.
T
h
en
,
th
e
r
ea
l
d
ata
wh
ich
is
ac
tu
ally
clin
ical
r
ec
o
r
d
s
ar
e
f
ed
to
th
e
p
r
e
d
ev
elo
p
e
d
m
o
d
el.
T
h
e
o
u
tp
u
t
in
clu
d
es
lis
t
o
f
wo
r
d
s
t
h
at
in
d
icate
test
co
n
d
u
cte
d
,
p
r
o
b
lem
d
iag
n
o
s
ed
o
r
t
r
ea
tm
en
t g
iv
en
.
Fro
m
th
e
lis
t
o
f
d
is
ea
s
es
an
d
test
co
n
d
u
cted
,
th
e
s
p
ec
ializa
tio
n
s
ar
e
class
if
ied
an
d
d
is
p
lay
ed
.
T
h
e
b
en
ef
it
o
f
th
is
is
th
at
th
e
ex
p
er
ts
in
s
p
ec
if
ic
ar
ea
n
ee
d
n
o
t
r
ea
d
all
clin
ical
r
ec
o
r
d
,
th
ey
ca
n
d
ir
ec
tly
r
ea
d
s
u
m
m
ar
y
wh
ich
s
av
es
lo
t
o
f
tim
e.
Usi
n
g
L
STM
m
eth
o
d
wh
ich
is
b
ased
o
n
m
ac
h
in
e
lear
n
i
n
g
,
ex
tr
ac
ti
o
n
o
f
d
iag
n
o
s
is
an
d
test
n
am
e
s
is
ex
tr
ac
ted
.
NL
P
h
as b
ee
n
u
s
ed
f
o
r
th
is
.
T
h
e
s
cr
ee
n
s
h
o
t is sh
o
wn
in
Fig
u
r
e
3
.
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.
11
,
No
.
2
,
Ap
r
il
2
0
2
1
:
1
6
8
9
-
1696
1692
Step
1
Sta
rt
I
n
p
u
t: M
ed
ical
r
ec
o
r
d
s
co
n
s
is
tin
g
o
f
test
s
co
n
d
u
cted
,
p
atien
t’
s
h
ea
lth
s
tatu
s
,
d
is
ea
s
es a
n
d
r
esp
o
n
s
e
to
th
e
tr
ea
tm
e
n
ts
.
Step
2
Cla
s
s
if
ica
t
io
n M
o
del dev
elo
p
m
ent
C
o
n
ce
p
ts
lik
e
m
ed
ical
test
s
,
d
iag
n
o
s
is
an
d
tr
ea
tm
en
ts
m
e
n
tio
n
ed
in
th
e
clin
ical
r
ec
o
r
d
s
ar
e
class
if
ied
in
to
ca
teg
o
r
ies.
Step
3
M
o
del bu
ild
i
ng
us
ing
t
ra
ini
n
g
da
t
a
T
h
e
r
ec
o
r
d
s
ar
e
d
iv
i
d
ed
in
to
tr
ain
in
g
d
ata
a
n
d
test
in
g
d
ata.
7
0
% o
f
d
ata
is
u
s
ed
as tr
ain
in
g
d
ata
an
d
it is
f
ed
t
o
th
e
m
o
d
el.
Step
4
T
esting
t
he
m
o
del a
cc
ura
cy
T
esti
n
g
d
ata
(
3
0
%
o
f
d
ata)
th
a
t c
o
n
s
is
ts
o
f
p
atien
t’
s
in
f
o
r
m
at
io
n
ar
e
f
e
d
to
th
e
m
o
d
el.
Step
5
I
np
ut
M
edica
l r
ec
o
rds
T
h
e
r
ea
l d
ata
(
cli
n
ical
r
ec
o
r
d
s
)
ar
e
f
ed
t
o
th
e
p
r
e
d
ev
el
o
p
ed
m
o
d
el.
Step
6
O
bta
in o
utput
T
h
e
o
u
tp
u
t in
clu
d
es lis
t o
f
wo
r
d
s
th
at
in
d
icate
test
co
n
d
u
cte
d
,
p
r
o
b
lem
d
ia
g
n
o
s
ed
o
r
tr
ea
tm
en
t g
iv
en
.
Step
7
Cla
s
s
if
y
Fro
m
th
e
lis
t o
f
d
is
ea
s
es a
n
d
t
est co
n
d
u
cted
,
t
h
e
s
p
ec
ializatio
n
s
ar
e
class
if
ied
an
d
d
is
p
lay
e
d
.
Step
7
E
nd
Fig
u
r
e
2
.
Alg
o
r
ith
m
f
o
r
class
if
icatio
n
Fig
u
r
e
3
.
R
esu
lts
o
f
NE
R
ex
tr
ac
tio
n
,
d
is
ea
s
e
n
am
es (
r
ed
)
,
d
i
ag
n
o
s
is
(
g
r
ee
n
)
an
d
test
s
(
y
ello
w)
On
ce
NE
R
with
NL
P i
s
ap
p
lied
f
o
r
ex
tr
ac
tio
n
o
f
en
titi
es a
n
d
th
eir
r
elatio
n
s
h
ip
s
,
f
u
r
th
er
p
r
o
ce
s
s
in
g
i
s
d
o
n
e.
T
h
e
d
is
ea
s
e
n
am
es,
test
,
d
iag
n
o
s
is
test
ar
e
f
ed
as
in
p
u
t
to
m
ac
h
in
e
lea
r
n
in
g
f
r
a
m
e
wo
r
k
.
An
o
u
tp
u
t
o
f
th
e
m
o
d
el
will
b
e
class
if
ied
d
ata
lab
eled
with
s
p
ec
iali
za
tio
n
as
s
h
o
wn
in
Fig
u
r
e
4
.
Fig
u
r
e
5
a
n
d
Fig
u
r
e
6
s
h
o
w
s
th
e
ex
ec
u
tio
n
s
cr
ee
n
s
h
o
t d
u
r
in
g
class
if
icatio
n
.
'
v
aso
v
ag
al
s
y
n
co
p
e'
Pro
b
lem
Sp
ec
ializatio
n
1
'
f
all
'
Pro
b
lem
Sp
ec
ializatio
n
2
'
tr
au
m
atic
ar
th
r
itis
'
Pro
b
lem
Sp
ec
ializatio
n
3
'
h
y
p
er
ten
s
io
n
'
Pro
b
lem
Sp
ec
ializatio
n
4
'
p
h
y
s
ical
th
er
ap
y
'
T
r
ea
tm
en
t
'
ev
alu
atio
n
'
T
est
'
ce
r
v
ical
s
p
in
e'
T
est
'
p
ain
'
Pro
b
lem
Sp
ec
ializatio
n
5
‘
tr
au
m
atic
in
ju
r
y
o
f
h
er
k
n
ee
’
Pro
b
lem
Sp
ec
ializatio
n
6
'
h
y
p
er
ten
s
io
n
'
Pro
b
lem
Sp
ec
ializatio
n
3
‘
atr
o
v
en
t i
n
h
aler
’
T
r
ea
tm
en
t
'
a
s
ca
n
'
T
est
Fig
u
r
e
4
.
C
lass
if
icatio
n
as p
er
s
p
ec
ializatio
n
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
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
fo
r
cl
in
ica
l n
a
med
e
n
tity reco
g
n
itio
n
(
R
a
viku
m
a
r
J.
)
1693
F
ig
u
r
e
5
.
C
lin
ical
r
ec
o
r
d
Fig
u
r
e
6
.
C
lass
if
ied
d
ata
b
ef
o
r
e
lab
elin
g
s
p
ec
ializatio
n
4.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
I
n
th
e
p
r
o
p
o
s
ed
m
o
d
el
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
u
s
ed
a
r
e
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
,
n
aïv
e
b
ay
es,
lo
g
is
tic
r
eg
r
ess
io
n
,
d
ec
is
io
n
tr
ee
,
r
an
d
o
m
f
o
r
est
an
d
l
ig
h
t
GB
M.
T
h
e
s
cr
ee
n
s
h
o
t
r
elate
d
to
a
c
c
u
r
a
c
y
o
f
t
h
e
s
e
a
l
g
o
r
i
t
h
m
s
i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
7
.
T
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
a
l
g
o
r
i
t
h
m
s
u
s
e
d
i
s
p
r
e
s
e
n
t
e
d
i
n
g
r
a
p
h
ical
f
o
r
m
in
Fig
u
r
e
8
.
T
h
e
m
o
d
el
p
r
o
p
o
s
ed
ca
n
b
e
u
s
ed
f
o
r
ex
tr
ac
tio
n
o
f
m
ed
ical
d
ata
u
s
in
g
NE
R
an
d
NL
P
tech
n
iq
u
e.
T
h
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
b
u
ilt
in
to
m
ed
ical
a
u
to
m
atio
n
s
y
s
tem
s
ca
n
b
e
a
g
o
o
d
r
eso
u
r
ce
f
o
r
m
ed
ical
ex
p
er
ts
as
it
s
av
es
lo
t
o
f
tim
e
s
p
en
t
f
o
r
r
ef
er
r
in
g
clin
ical
r
ec
o
r
d
s
in
d
etail.
Als
o
,
ad
m
in
is
tr
ativ
e
task
s
ca
n
b
e
ea
s
ier
as
th
e
m
o
d
el
s
ep
ar
ates th
e
d
is
ea
s
es a
n
d
tr
ea
tm
en
t in
to
s
p
ec
ializatio
n
s
.
T
h
e
e
x
i
s
t
i
n
g
N
L
P
s
y
s
t
e
m
s
f
o
r
N
E
R
u
s
i
n
g
c
l
i
n
i
c
a
l
d
a
t
a
c
o
n
s
i
s
t
o
f
s
y
n
t
a
c
t
i
c
p
r
o
c
e
s
s
i
n
g
m
o
d
u
l
e
s
l
i
k
e
s
e
n
t
e
n
c
e
d
e
t
e
c
t
i
o
n
,
t
o
k
e
n
i
z
a
t
i
o
n
,
p
a
r
t
-
of
-
s
p
e
e
c
h
t
a
g
g
i
n
g
e
t
c
.
T
h
e
s
e
m
a
n
t
i
c
m
o
d
u
l
e
s
i
n
c
l
u
d
e
c
o
n
c
e
p
t
id
en
tific
atio
n
,
en
tity
r
ec
o
g
n
itio
n
,
r
elatio
n
ex
t
r
ac
tio
n
an
d
a
n
ap
h
o
r
ic
r
eso
lu
ti
o
n
etc.
So
f
ar
,
in
th
e
lite
r
atu
r
e
,
it
is
o
b
s
er
v
ed
th
at
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.
11
,
No
.
2
,
Ap
r
il
2
0
2
1
:
1
6
8
9
-
1696
1694
s
y
s
tem
s
ex
is
t
s
f
o
r
ex
tr
ac
tio
n
o
f
n
am
ed
en
titi
es lik
e
d
is
ea
s
e,
t
r
ea
tm
en
t e
tc
wh
ich
was u
s
ef
u
l f
o
r
d
o
cto
r
s
to
r
ea
d
s
u
m
m
ar
y
i
n
f
o
r
m
atio
n
with
o
u
t
r
ea
d
in
g
c
o
m
p
lete
clin
ical
r
ec
o
r
d
s
.
B
u
t,
th
e
p
r
o
p
o
s
ed
m
o
d
el
g
o
es
o
n
e
s
tep
f
u
r
t
h
e
r
b
y
c
l
a
s
s
i
f
y
i
n
g
t
h
e
n
a
m
e
d
e
n
t
i
t
i
e
s
a
s
p
e
r
s
p
e
c
i
a
l
i
z
a
t
i
o
n
.
T
h
i
s
c
a
n
b
e
e
m
b
e
d
d
e
d
i
n
h
e
a
l
t
h
a
u
t
o
m
a
t
i
o
n
s
y
s
t
e
m
f
o
r
e
f
f
i
c
i
e
n
t
d
e
l
i
v
e
r
y
o
f
s
e
r
v
i
c
e
s
s
a
v
i
n
g
l
o
t
o
f
t
i
m
e
.
H
e
n
c
e
t
h
e
p
r
o
p
o
s
e
d
s
y
s
t
e
m
c
a
n
b
e
a
g
o
o
d
ca
n
d
id
ate
f
o
r
th
e
r
esear
ch
in
th
e
a
r
ea
o
f
NE
R
in
m
ed
ical
f
iel
d.
Fig
u
r
e
7
.
Acc
u
r
ac
y
o
f
alg
o
r
ith
m
s
Fig
u
r
e
8
.
Acc
u
r
ac
y
c
o
m
p
ar
is
o
n
o
f
alg
o
r
ith
m
s
5.
CO
NCLU
SI
O
N
B
ec
au
s
e
o
f
d
iv
er
s
e
wr
itin
g
s
ty
le
o
f
clin
ician
s
,
th
e
r
u
les
an
d
p
atter
n
s
ar
e
n
o
t
g
en
e
r
aliza
b
le.
T
h
e
se
is
s
u
es
ca
n
b
e
ad
d
r
ess
ed
b
y
m
ak
in
g
u
s
e
o
f
tech
n
o
lo
g
ies
lik
e
m
ac
h
in
e
lear
n
in
g
.
Nam
e
d
en
tity
r
ec
o
g
n
itio
n
is
g
r
o
u
p
ed
in
to
th
r
ee
ap
p
r
o
ac
h
e
s
.
Ma
ch
in
e
lea
r
n
in
g
b
ased
ap
p
r
o
ac
h
es,
r
u
le
-
b
ased
a
p
p
r
o
ac
h
es
an
d
d
ictio
n
a
r
y
b
ased
ap
p
r
o
ac
h
es.
T
h
e
s
y
s
te
m
s
th
at
u
s
e
m
ac
h
in
e
lear
n
in
g
b
ased
a
p
p
r
o
ac
h
f
o
cu
s
o
n
ch
o
o
s
in
g
ef
f
ec
tiv
e
f
ea
tu
r
es
f
o
r
class
if
ier
b
u
ild
in
g
.
Sev
er
al
r
esear
ch
er
s
h
av
e
ex
ten
s
iv
ely
u
s
ed
m
ac
h
in
e
le
ar
n
in
g
m
o
d
els
f
o
r
clin
ical
NE
R
.
Data
b
ases
s
u
ch
as
Pu
b
Me
d
wh
ich
in
cl
u
d
e
m
ed
ical
p
u
b
licatio
n
s
h
av
e
g
en
e
r
ated
lo
t
o
f
in
ter
est
am
o
n
g
r
esear
ch
er
s
f
o
r
ap
p
ly
i
n
g
in
f
o
r
m
atio
n
ex
tr
ac
ti
o
n
tec
h
n
iq
u
es
to
m
ed
ical
liter
atu
r
e.
I
n
a
n
attem
p
t
to
co
n
tr
ib
u
te
to
th
e
r
esear
c
h
in
th
is
ar
ea
,
th
is
wo
r
k
p
r
o
p
o
s
ed
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
f
o
r
clin
ic
al
NE
R
.
T
h
e
m
o
d
el
p
r
o
p
o
s
ed
p
er
f
o
m
ed
b
etter
co
m
p
a
r
ed
to
s
o
m
e
o
f
t
h
e
ex
is
tin
g
m
eth
o
d
s
.
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
Ma
ch
in
e
lea
r
n
in
g
mo
d
el
fo
r
cl
in
ica
l n
a
med
e
n
tity reco
g
n
itio
n
(
R
a
viku
m
a
r
J.
)
1695
RE
F
E
R
E
NC
E
S
[1
]
T.
Jo
a
c
h
ims
,
C.
Ne
d
e
ll
e
c
,
a
n
d
C.
Ro
u
v
e
iro
l
.
“
Tex
t
c
a
teg
o
riza
ti
o
n
wit
h
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
s:
lea
rn
in
g
wit
h
m
a
n
y
re
lev
a
n
t.
In
M
a
c
h
in
e
Lea
rn
i
n
g
,
”
EC
M
L
-
E
u
ro
p
e
a
n
Co
n
fer
e
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
in
g
,
1
9
9
8
,
p
p
.
1
3
7
-
1
4
2
.
[2
]
L.
Ra
b
in
e
r
e
t
a
l.
,
“
A
tu
t
o
rial
o
n
h
id
d
e
n
M
a
rk
o
v
m
o
d
e
ls
a
n
d
se
lec
ted
a
p
p
l
ica
ti
o
n
s
in
s
p
e
e
c
h
re
c
o
g
n
it
io
n
,
”
Pro
c
e
e
d
in
g
s
o
f
t
h
e
IEE
E
,
v
o
l.
7
7
,
n
o
.
2
,
1
9
8
9
,
p
p
.
2
5
7
-
2
8
6
.
[3
]
S.
M
.
M
e
y
stre
,
G
.
K.
S
a
v
o
v
a
,
K.
C.
Kip
p
e
r
-
S
c
h
u
ler,
J.
F
.
Hu
r
d
le,
“
Ex
trac
ti
n
g
i
n
fo
rm
a
-
ti
o
n
fr
o
m
tex
t
u
a
l
d
o
c
u
m
e
n
ts
in
t
h
e
e
lec
tro
n
ic
h
e
a
lt
h
re
c
o
r
d
,”
Y
e
a
rb
o
o
k
o
f
M
e
d
ica
l
In
fo
rm
a
t
ics
,
v
o
l.
3
5
,
pp.
1
2
8
-
1
4
4
,
2
0
0
8
.
[4
]
R.
W.
V.
F
l
y
n
n
,
T.
M
.
M
a
c
d
o
n
a
ld
,
N.
S
c
h
e
m
b
ri
,
G
.
D.
M
u
rra
y
,
A.
S.
F
.
Do
n
e
y
,
“
Au
t
o
m
a
ted
d
a
t
a
c
a
p
tu
re
fro
m
fre
e
-
tex
t
ra
d
io
lo
g
y
re
p
o
rts
to
e
n
h
a
n
c
e
a
c
c
u
ra
c
y
o
f
h
o
sp
it
a
l
in
p
a
t
ien
t
stro
k
e
c
o
d
e
s,”
Ph
a
rm
a
c
o
e
p
i
d
e
mio
lo
g
y
a
n
d
Dr
u
g
S
a
f
e
ty
,
v
o
l
.
1
9
,
n
o
.
2
0
1
0
,
p
p
.
8
4
3
-
8
4
7
,
2
0
1
0
.
[5
]
H.
Ya
n
g
,
I
.
S
p
a
sic
,
J
.
A.
Ke
a
n
e
,
G
.
Ne
n
a
d
ic,
“
A
tex
t
m
in
in
g
a
p
p
ro
a
c
h
to
t
h
e
p
re
-
d
icti
o
n
o
f
d
ise
a
se
sta
tu
s
fro
m
c
li
n
ica
l
d
isc
h
a
r
g
e
su
m
m
a
ries
,
”
J
o
u
rn
a
l
o
f
th
e
Ame
ric
a
n
M
e
d
ica
l
In
fo
rm
a
t
ics
Asso
c
ia
t
io
n
(J
A
M
IA)
,
v
o
l.
1
6
,
n
o
.
4
,
p
p
.
5
9
6
-
6
0
0
,
2
0
0
9
.
[6
]
S
e
k
in
e
,
S
.
,
“
Ny
u
:
De
sc
rip
ti
o
n
o
f
th
e
Ja
p
a
n
e
se
NE
S
y
ste
m
Us
e
d
F
o
r
M
e
t
-
2
,
”
Pro
c
.
o
f
t
h
e
S
e
v
e
n
th
M
e
ss
a
g
e
Un
d
e
rs
ta
n
d
in
g
C
o
n
fer
e
n
c
e
(M
U
C
-
7)
,
1
9
9
8
.
[7
]
Bik
e
l,
D.
M
.
,
S
c
h
wa
rtz,
R
.
,
a
n
d
Weisc
h
e
d
e
l,
R.
M
.
,
“
An
a
lg
o
rit
h
m
th
a
t
lea
rn
s
w
h
a
t'
s
in
a
n
a
m
e
,
”
M
a
c
h
i
n
e
lea
r
n
in
g
,
v
o
l.
3
4
,
n
o
.
1
-
3,
p
p
.
2
1
1
-
2
3
1
,
1
9
9
9
.
[
8
]
B
o
r
t
h
w
i
c
k
,
A
.
,
“
A
m
a
x
i
m
u
m
e
n
t
r
o
p
y
a
p
p
r
o
a
c
h
t
o
n
a
m
e
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
,
”
P
h
D
d
i
s
s
.
,
N
e
w
Y
o
r
k
U
n
i
v
e
r
s
i
t
y
,
1
9
9
9
.
[9
]
M
c
Ca
ll
u
m
,
A
a
n
d
Wei
L.
,
“
Early
re
su
lt
s
fo
r
n
a
m
e
d
e
n
ti
ty
re
c
o
g
n
it
i
o
n
wit
h
c
o
n
d
it
io
n
a
l
ra
n
d
o
m
field
s,
fe
a
tu
r
e
in
d
u
c
ti
o
n
a
n
d
we
b
-
e
n
h
a
n
c
e
d
lex
i
c
o
n
s,”
In
Pro
c
e
e
d
i
n
g
s
o
f
th
e
se
v
e
n
th
c
o
n
fer
e
n
c
e
o
n
N
a
tu
r
a
l
la
n
g
u
a
g
e
l
e
a
r
n
in
g
a
t
HLT
-
NAA
C
L,
v
o
l.
4
,
2
0
0
3
,
p
p
.
1
8
8
-
1
9
1
.
[1
0
]
S
a
ra
wa
g
i,
S
.
a
n
d
Co
h
e
n
,
W.
W.
,
“
S
e
m
i
-
m
a
rk
o
v
c
o
n
d
it
io
n
a
l
ra
n
d
o
m
fi
e
ld
s
fo
r
i
n
fo
rm
a
ti
o
n
e
x
trac
ti
o
n
,
”
In
A
d
v
a
n
c
e
s
in
Ne
u
ra
l
In
f
o
rm
a
ti
o
n
Pro
c
e
ss
in
g
S
y
ste
ms
,
2
0
0
4
,
p
p
.
1
1
8
5
-
1
1
9
2
.
[1
1
]
Co
h
e
n
,
W
.
W
.
,
a
n
d
S
a
ra
wa
g
i,
S
.
,
“
E
x
p
l
o
it
i
n
g
d
ict
io
n
a
ries
in
n
a
m
e
d
e
n
ti
t
y
e
x
trac
ti
o
n
:
c
o
m
b
in
i
n
g
se
m
i
-
m
a
rk
o
v
e
x
trac
ti
o
n
p
r
o
c
e
ss
e
s
a
n
d
d
a
ta
in
teg
ra
ti
o
n
m
e
th
o
d
s,”
In
Pro
c
e
e
d
in
g
s
o
f
th
e
ten
t
h
ACM
S
IGKD
D
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
K
n
o
w
led
g
e
d
isc
o
v
e
ry
a
n
d
d
a
ta
mi
n
i
n
g
,
2
0
0
4
,
p
p
.
8
9
-
98
.
[1
2
]
T.
M
.
L
u
u
,
R
.
P
h
a
n
,
R.
Da
v
e
y
a
n
d
G
.
Ch
e
tt
y
,
"
A
M
u
lt
i
lev
e
l
NER
F
ra
m
e
wo
rk
fo
r
Au
t
o
m
a
ti
c
Cli
n
ic
a
l
Na
m
e
En
ti
ty
Re
c
o
g
n
it
i
o
n
,
"
2
0
1
7
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Da
t
a
M
i
n
in
g
W
o
rk
sh
o
p
s
(ICDM
W
)
,
Ne
w
Orle
a
n
s,
LA
,
2
0
1
7
,
p
p
.
1
1
3
4
-
1
1
4
3
.
[1
3
]
X
.
M
a
o
,
F
.
L
i
,
H
.
W
a
n
g
a
n
d
H
.
W
a
n
g
,
"
N
a
m
e
d
E
n
t
i
t
y
R
e
c
o
g
n
i
t
i
o
n
o
f
E
l
e
c
t
r
o
n
i
c
M
e
d
i
c
a
l
R
e
c
o
r
d
B
a
s
e
d
o
n
I
m
p
r
o
v
e
d
H
M
M
A
l
g
o
r
i
t
h
m
,
"
2
0
1
7
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
C
o
m
p
u
t
e
r
T
e
c
h
n
o
l
o
g
y
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
Co
mm
u
n
ica
ti
o
n
(ICCT
EC)
,
Da
li
a
n
,
Ch
i
n
a
,
2
0
1
7
,
p
p
.
4
3
5
-
4
3
8
.
[1
4
]
L.
Li
a
n
d
L.
Ho
u
,
"
C
o
m
b
i
n
e
d
At
ten
ti
o
n
M
e
c
h
a
n
ism
fo
r
Na
m
e
d
En
ti
ty
Re
c
o
g
n
it
io
n
in
Ch
in
e
se
El
e
c
tro
n
ic
M
e
d
ica
l
Re
c
o
rd
s,"
2
0
1
9
I
EE
E
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
He
a
lt
h
c
a
re
In
f
o
rm
a
ti
c
s (ICHI)
,
Xi'
a
n
,
Ch
i
n
a
,
2
0
1
9
,
p
p
.
1
-
2.
[1
5
]
J.
Qiu
,
Q.
Wan
g
,
Y.
Z
h
o
u
,
T
.
R
u
a
n
a
n
d
J.
G
a
o
,
"
F
a
st
a
n
d
Ac
c
u
ra
te Rec
o
g
n
it
i
o
n
o
f
Ch
i
n
e
se
Cli
n
ica
l
Na
m
e
d
En
ti
ti
e
s
with
Re
sid
u
a
l
Dilate
d
C
o
n
v
o
lu
ti
o
n
s,"
2
0
1
8
I
EE
E
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
B
io
i
n
fo
rm
a
ti
c
s
a
n
d
Bi
o
me
d
icin
e
(BI
BM
),
M
a
d
ri
d
,
S
p
a
in
,
2
0
1
8
,
p
p
.
9
3
5
-
9
4
2
.
[1
6
]
W.
Li
,
e
t
a
l.
,
"
Dr
u
g
S
p
e
c
ifi
c
a
ti
o
n
Na
m
e
d
En
ti
ty
Re
c
o
g
n
it
i
o
n
Ba
se
o
n
Bi
LS
TM
-
CR
F
M
o
d
e
l
,
"
2
0
1
9
I
EE
E
4
3
r
d
An
n
u
a
l
Co
mp
u
ter
S
o
ft
w
a
re
a
n
d
A
p
p
li
c
a
ti
o
n
s Co
n
fer
e
n
c
e
(COM
PS
AC)
,
M
il
wa
u
k
e
e
,
WI
,
U
S
A
,
2
0
1
9
,
p
p
.
4
2
9
-
4
3
3
.
[1
7
]
R
.
C
.
Was
se
rm
a
n
,
"
El
e
c
tro
n
ic
m
e
d
ica
l
re
c
o
rd
s
(EM
Rs)
e
p
i
d
e
m
io
l
o
g
y
a
n
d
e
p
iste
m
o
l
o
g
y
:
re
flec
ti
o
n
s
o
n
E
M
Rs
a
n
d
fu
tu
re
p
e
d
iatric cli
n
ica
l
re
se
a
rc
h
,
"
Aca
d
e
mic
p
e
d
ia
trics
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
2
8
0
-
2
8
7
,
2
0
1
1
.
[1
8
]
D
.
De
m
n
e
r
-
F
u
sh
m
a
n
,
W
.
W
.
Ch
a
p
m
a
n
a
n
d
C
.
J
.
M
c
Do
n
a
l
d
,
"
W
h
a
t
c
a
n
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
d
o
fo
r
c
li
n
ica
l
d
e
c
isio
n
s
u
p
p
o
rt?,
"
J
o
u
rn
a
l
o
f
b
i
o
me
d
ica
l
in
fo
rm
a
t
ics
,
v
o
l.
4
2
,
n
o
.
5
,
p
p
.
7
6
0
-
7
7
2
,
2
0
0
9
.
[1
9
]
A
.
R
.
Aro
n
so
n
a
n
d
F
.
M
.
La
n
g
,
"
An
o
v
e
rv
iew
o
f
M
e
taMap
:
h
isto
r
i
c
a
l
p
e
rsp
e
c
ti
v
e
a
n
d
re
c
e
n
t
a
d
v
a
n
c
e
s,"
J
o
u
rn
a
l
o
f
th
e
Ame
ric
a
n
M
e
d
ica
l
In
f
o
rm
a
ti
c
s A
ss
o
c
ia
ti
o
n
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
2
2
9
-
2
3
6
,
2
0
1
0
.
[2
0
]
M
.
Jia
n
g
,
Y
.
Ch
e
n
,
M
.
Li
u
,
e
t
a
l
.
,
"
A
stu
d
y
o
f
m
a
c
h
in
e
-
lea
rn
in
g
-
b
a
se
d
a
p
p
ro
a
c
h
e
s
t
o
e
x
trac
t
c
li
n
i
c
a
l
e
n
ti
ti
e
s
a
n
d
th
e
ir
a
ss
e
r
ti
o
n
s
fr
o
m
d
isc
h
a
r
g
e
su
m
m
a
ries
,
"
J
o
u
rn
a
l
o
f
t
h
e
Ame
ric
a
n
M
e
d
ica
l
In
f
o
rm
a
ti
c
s
Asso
c
i
a
ti
o
n
,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
6
0
1
-
6
0
6
,
2
0
1
1
.
[2
1
]
B
.
De
Bru
ij
n
,
e
t
a
l.
,
"
M
a
c
h
in
e
-
le
a
rn
e
d
so
l
u
ti
o
n
s
f
o
r
th
re
e
sta
g
e
s
o
f
c
li
n
ica
l
i
n
fo
rm
a
ti
o
n
e
x
trac
ti
o
n
:
th
e
sta
te
o
f
th
e
a
rt
a
t
i2
b
2
2
0
1
0
,
"
J
o
u
rn
a
l
o
f
t
h
e
Ame
ric
a
n
M
e
d
ica
l
I
n
fo
rm
a
ti
c
s A
s
so
c
ia
ti
o
n
,
v
o
l.
1
8
,
n
o
.
5
,
p
p
.
5
5
7
-
5
6
2
,
2
0
1
1
.
[2
2
]
Y
.
Wan
g
,
Z
.
Yu
,
L
.
Ch
e
n
,
e
t
a
l.
,
"
S
u
p
e
r
v
ise
d
m
e
th
o
d
s f
o
r
sy
m
p
to
m
n
a
m
e
re
c
o
g
n
it
io
n
in
fre
e
-
tex
t
c
li
n
ica
l
re
c
o
rd
s o
f
trad
it
io
n
a
l
Ch
in
e
s
e
m
e
d
icin
e
:
An
e
m
p
iri
c
a
l
stu
d
y
,
"
J
o
u
rn
a
l
o
f
b
io
m
e
d
ica
l
i
n
fo
rm
a
ti
c
s
,
v
o
l.
4
7
,
p
p
.
9
1
-
1
0
4
,
2
0
1
4
.
[2
3
]
H
.
Wan
g
,
W
.
Z
h
a
n
g
,
Q
.
Zen
g
,
e
t
a
l.
,
"
E
x
trac
ti
n
g
imp
o
rtan
t
i
n
fo
rm
a
ti
o
n
fr
o
m
C
h
in
e
se
Op
e
ra
ti
o
n
N
o
tes
with
n
a
tu
r
a
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
m
e
th
o
d
s,"
J
o
u
rn
a
l
o
f
b
i
o
me
d
ica
l
in
f
o
rm
a
ti
c
s
,
v
o
l.
4
8
,
p
p
.
1
3
0
-
1
3
6
,
2
0
1
4
.
[
2
4
]
Y
.
X
u
,
Y
.
W
a
n
g
,
T
.
Liu
,
e
t
a
l
.
,
"
J
o
i
n
t
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
n
a
m
e
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
d
u
a
l
d
e
c
o
m
p
o
s
i
t
i
o
n
i
n
C
h
i
n
e
s
e
d
i
s
c
h
a
r
g
e
s
u
m
m
a
r
i
e
s
,
"
J
o
u
r
n
a
l
o
f
t
h
e
A
m
e
r
i
c
a
n
M
e
d
i
c
a
l
I
n
f
o
r
m
a
t
i
c
s
A
s
s
o
c
i
a
t
i
o
n
,
v
o
l
.
2
1
,
n
o
.
e
1
,
p
p
.
e
8
4
-
e
9
2
,
2
0
1
4
.
[2
5
]
J
.
Lei,
B
.
Tan
g
,
X
.
Lu
,
e
t
a
l.
,
"
A c
o
m
p
re
h
e
n
si
v
e
stu
d
y
o
f
n
a
m
e
d
e
n
t
it
y
re
c
o
g
n
it
i
o
n
i
n
Ch
i
n
e
se
c
li
n
ica
l
te
x
t,
"
J
o
u
rn
a
l
o
f
t
h
e
Ame
ric
a
n
M
e
d
ica
l
In
f
o
rm
a
ti
c
s A
ss
o
c
ia
ti
o
n
,
v
o
l.
2
1
,
n
o
.
5
,
p
p
.
8
0
8
-
8
1
4
,
2
0
1
4
.
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.
11
,
No
.
2
,
Ap
r
il
2
0
2
1
:
1
6
8
9
-
1696
1696
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ra
v
ik
u
m
a
r
J
.
is
p
re
se
n
tl
y
wo
r
k
in
g
a
s
a
n
As
sista
n
t
p
ro
fe
ss
o
r
a
t
Dr.
Am
b
e
d
k
a
r
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Be
n
g
a
lu
r
u
.
He
h
a
s
8
y
e
a
rs
o
f
Tea
c
h
in
g
a
n
d
1
y
e
a
r
o
f
i
n
d
u
stry
Ex
p
e
rien
c
e
.
His
re
se
a
rc
h
in
tere
sts in
c
lu
d
e
Di
g
it
a
l
Im
a
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
ter n
e
tw
o
rk
s a
n
d
IOT.
Ra
m
a
k
a
n
t
h
K
u
m
a
r
P
.
is
p
re
se
n
tl
y
wo
rk
i
n
g
a
s
P
ro
fe
ss
o
r
&
Ho
D
o
f
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
R
V Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
.
He
h
a
s 2
5
y
e
a
rs o
f
Tea
c
h
in
g
a
n
d
1
4
y
e
a
rs
o
f
R&
D
E
x
p
e
rie
n
c
e
.
His
re
s
e
a
rc
h
in
tere
sts
i
n
c
lu
d
e
Dig
it
a
l
Im
a
g
e
P
r
o
c
e
ss
in
g
,
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
a
n
d
Na
tu
ra
l
Lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.