I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
,
p
p
.
4
5
2
0
~
4
5
3
2
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
6
.
p
p
4
5
2
0
-
4
5
3
2
4520
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Cla
ss
ificatio
n alg
o
rithm wi
th
a
rti
fi
cia
l int
ellig
enc
e f
o
r t
he
dia
g
no
stic proces
s o
f
o
bstruc
tive sl
eep apnea
J
ehil
Vent
ura
-
T
ec
co
,
J
esú
s
F
a
j
a
rdo
-
Av
a
lo
s
,
M
icha
el
Ca
ba
nil
la
s
-
Ca
rbo
nell
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
d
a
d
P
r
i
v
a
d
a
d
e
l
N
o
r
t
e
,
Li
m
a
,
P
e
r
ú
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
2
9
,
2
0
2
4
R
ev
is
ed
Oct
7
,
2
0
2
5
Acc
ep
ted
Oct
1
8
,
2
0
2
5
Ob
stru
c
ti
v
e
sle
e
p
a
p
n
e
a
(OSA)
i
s
a
d
ise
a
se
th
a
t
a
ffe
c
ts
m
il
li
o
n
s
o
f
p
e
o
p
le
wo
rld
wi
d
e
,
a
n
d
a
larg
e
p
ro
p
o
rti
o
n
o
f
th
e
m
re
m
a
in
u
n
d
ia
g
n
o
se
d
d
u
e
to
th
e
h
ig
h
c
o
st
o
f
p
o
l
y
so
m
n
o
g
ra
p
h
y
(
P
S
G
)
tes
ts.
F
o
r
th
is
re
a
so
n
,
it
is
c
ru
c
ial
to
d
e
v
e
lo
p
a
ffo
r
d
a
b
le
d
iag
n
o
stic
t
o
o
ls
to
fa
c
il
it
a
te
e
a
rly
d
e
tec
ti
o
n
o
f
t
h
is
c
o
n
d
i
ti
o
n
.
Th
is
stu
d
y
a
ims
to
a
n
a
ly
z
e
h
o
w
a
n
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI)
-
b
a
se
d
c
las
sifica
ti
o
n
a
l
g
o
ri
th
m
i
m
p
a
c
ts
th
e
d
ia
g
n
o
stic
p
r
o
c
e
ss
o
f
OSA
in
Li
m
a
,
P
e
ru
.
Th
e
a
lg
o
rit
h
m
wa
s
d
e
v
e
lo
p
e
d
fo
l
lo
wi
n
g
th
e
Ka
n
b
a
n
m
e
th
o
d
o
l
o
g
y
,
wh
ich
g
u
a
ra
n
tee
d
a
n
e
fficie
n
t
a
n
d
tran
sp
a
re
n
t
fo
ll
o
w
-
up
d
u
ri
n
g
t
h
e
d
e
v
e
lo
p
m
e
n
t
c
y
c
le,
wh
ich
is
k
e
y
i
n
th
e
m
e
d
ica
l
c
o
n
tex
t
wh
e
re
so
ftwa
re
q
u
a
li
t
y
a
n
d
trac
e
a
b
il
it
y
a
re
fu
n
d
a
m
e
n
tal.
A
d
e
c
isio
n
tree
(DT)
wa
s
u
se
d
fo
r
d
iag
n
o
sis
a
n
d
c
las
sifica
ti
o
n
,
e
m
p
lo
y
in
g
a
train
in
g
d
a
tas
e
t
p
ro
v
id
e
d
b
y
t
h
e
Na
ti
o
n
a
l
S
lee
p
Re
se
a
rc
h
Re
so
u
rc
e
(
N
S
RR),
fro
m
wh
ich
si
x
re
lev
a
n
t
a
tt
rib
u
tes
we
re
se
lec
ted
fo
r
a
n
a
ly
sis.
Th
e
re
se
a
rc
h
re
su
lt
s
in
d
ic
a
ted
th
a
t,
a
lt
h
o
u
g
h
th
e
imp
r
o
v
e
m
e
n
t
i
n
c
li
n
ica
l
d
iag
n
o
stic
a
c
c
u
ra
c
y
wa
s
m
in
ima
l
a
t
1
0
.
8
1
%
,
p
o
siti
v
e
re
su
lt
s
we
re
o
b
t
a
in
e
d
in
o
th
e
r
a
sp
e
c
ts:
d
iag
n
o
stic
ti
m
e
wa
s
sig
n
ifi
c
a
n
t
ly
re
d
u
c
e
d
b
y
2
8
.
1
7
%
,
a
n
d
th
e
n
u
m
b
e
r
o
f
tes
ts
re
q
u
ired
d
e
c
re
a
se
d
b
y
2
4
.
0
7
%
.
K
ey
w
o
r
d
s
:
Alg
o
r
ith
m
C
las
s
if
icatio
n
Diag
n
o
s
is
Ma
ch
in
e
lear
n
in
g
Ob
s
tr
u
ctiv
e
s
leep
ap
n
ea
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
:
Mic
h
ae
l Cab
an
illas
-
C
ar
b
o
n
ell
Sch
o
o
l o
f
E
n
g
in
ee
r
in
g
,
U
n
iv
er
s
id
ad
Priv
ad
a
d
el
No
r
te
L
im
a,
Per
ú
E
m
ail:
m
ca
b
an
illas
@
ieee
.
o
r
g
1.
I
NT
RO
D
UCT
I
O
N
Sleep
is
a
p
r
im
o
r
d
ial
an
d
ess
en
tial
ac
tiv
ity
in
wh
ich
we
in
v
est
ap
p
r
o
x
im
ately
o
n
e
-
th
ir
d
o
f
o
u
r
liv
es
[
1
]
.
No
wad
a
y
s
,
th
e
q
u
ality
a
n
d
d
u
r
atio
n
o
f
s
leep
a
r
e
s
ig
n
if
i
ca
n
tly
af
f
ec
ted
b
y
p
e
o
p
le'
s
lif
esty
les,
wh
ich
ca
n
h
av
e
n
eg
ativ
e
r
ep
er
cu
s
s
io
n
s
o
n
lo
n
g
-
ter
m
h
ea
lth
,
g
i
v
in
g
r
is
e
to
wh
at
ar
e
k
n
o
wn
as
s
leep
d
is
o
r
d
er
s
(
SDs
)
[
2
]
.
SDs
ar
e
a
co
m
m
o
n
p
ath
o
lo
g
y
am
o
n
g
p
eo
p
le,
wh
ich
d
e
p
en
d
in
g
o
n
th
eir
co
n
d
itio
n
ca
n
b
e
is
o
lated
o
r
ass
o
ciate
d
with
o
th
er
d
is
o
r
d
er
s
[
3
]
.
Sin
ce
1
9
7
9
,
th
e
in
ter
n
at
io
n
al
class
if
icatio
n
o
f
s
leep
d
i
s
o
r
d
er
s
(
I
C
SD)
h
as
b
ee
n
in
u
s
e,
wh
ich
in
its
f
i
r
s
t
v
er
s
io
n
class
if
ied
SDs
in
to
f
o
u
r
g
r
o
u
p
s
:
d
y
s
s
o
m
n
ias,
p
ar
a
s
o
m
n
ias,
d
is
o
r
d
er
s
ass
o
ciate
d
with
o
th
er
d
is
ea
s
es
,
an
d
u
n
q
u
alif
iab
le
SDs
[
4
]
,
[
5
]
.
T
h
an
k
s
t
o
th
is
,
m
o
r
e
t
h
an
8
0
SDs
h
av
e
b
ee
n
r
ec
o
g
n
ized
an
d
class
if
ied
[
6
]
.
T
h
ese
d
is
o
r
d
er
s
n
eg
ativ
el
y
af
f
ec
t
m
illi
o
n
s
o
f
p
eo
p
le
wo
r
ld
w
id
e,
ca
u
s
in
g
lo
s
s
o
f
life
,
an
d
ac
ci
d
en
ts
,
am
o
n
g
o
th
er
s
[
7
]
,
[
8
]
.
Am
o
n
g
th
e
m
o
s
t
s
ev
er
e
SDs
,
is
o
b
s
tr
u
ctiv
e
s
leep
ap
n
ea
(
OSA
)
,
wh
ich
af
f
ec
ts
4
%
o
f
th
e
wo
r
ld
'
s
p
o
p
u
latio
n
[
9
]
.
OSA
ep
is
o
d
es
o
cc
u
r
wh
en
th
e
air
way
s
u
d
d
en
ly
co
llap
s
es
d
u
r
in
g
s
leep
,
cu
ttin
g
o
f
f
o
x
y
g
en
atio
n
to
t
h
e
b
o
d
y
[
1
0
]
.
T
h
is
co
n
d
itio
n
ca
n
last
m
o
r
e
t
h
an
1
0
s
ec
o
n
d
s
an
d
o
cc
u
r
s
with
a
c
o
n
cu
r
r
en
ce
o
f
5
tim
es
p
er
h
o
u
r
o
f
s
leep
.
I
t
af
f
ec
ts
m
o
r
e
m
en
th
an
wo
m
en
b
etwe
en
4
0
a
n
d
5
0
y
ea
r
s
o
f
ag
e
[
1
1
]
.
OSA
is
u
s
u
ally
d
iv
id
ed
i
n
to
th
r
ee
lev
e
ls
o
f
s
ev
er
ity
:
m
ild
,
wh
en
th
e
in
cid
en
ce
is
g
r
ea
ter
th
an
5
b
u
t
less
th
an
1
5
ev
en
t
s
p
er
h
o
u
r
;
m
o
d
er
ate,
b
etwe
en
1
5
a
n
d
3
0
ev
e
n
ts
p
er
h
o
u
r
;
an
d
s
ev
er
e,
g
r
ea
te
r
th
an
3
0
ev
en
ts
p
er
h
o
u
r
[
1
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fica
tio
n
a
lg
o
r
ith
m
w
ith
a
r
tifi
cia
l in
tellig
en
ce
fo
r
th
e
d
ia
g
n
o
s
tic
…
(
Je
h
il V
e
n
tu
r
a
-
Te
cc
o
)
4521
I
n
th
e
Un
ited
States
,
it
af
f
ec
ts
2
2
%
o
f
m
en
a
n
d
1
7
%
o
f
wo
m
en
,
with
r
ates
ex
ce
ed
in
g
f
iv
e
ep
is
o
d
es
p
er
h
o
u
r
[
1
3
]
,
[
1
4
]
.
Similar
f
i
g
u
r
es
ar
e
r
e
p
o
r
ted
in
Sp
ain
a
n
d
Ho
n
g
Ko
n
g
,
wh
ile
s
ig
n
if
i
ca
n
t
in
cr
ea
s
es
h
av
e
b
ee
n
r
ep
o
r
ted
in
J
ap
an
,
r
ea
c
h
in
g
3
7
%
in
m
en
an
d
5
0
%
in
wo
m
en
[
1
5
]
–
[
1
8
]
.
I
n
L
atin
Am
er
ica,
p
r
ev
alen
ce
v
ar
ies
b
y
r
eg
io
n
,
with
s
tu
d
ies
h
ig
h
lig
h
tin
g
cities
s
u
ch
as
Mo
n
tev
id
eo
an
d
San
tiag
o
d
e
C
h
ile.
Ho
wev
er
,
in
Per
u
,
th
e
lack
o
f
ac
cu
r
ate
d
at
a
h
in
d
er
s
a
clea
r
ass
e
s
s
m
en
t
o
f
th
e
p
r
o
b
lem
[
1
9
]
.
A
r
ev
ie
w
o
f
m
ed
ical
r
ec
o
r
d
s
s
u
g
g
ests
th
at
2
9
.
2
%
o
f
p
atien
ts
p
r
esen
t
with
m
ild
OSA
an
d
2
6
.
7
%
with
s
ev
er
e
OSA
[
2
0
]
.
T
h
ese
f
in
d
in
g
s
r
ef
lect
a
p
o
ten
tially
g
r
o
win
g
p
u
b
lic
h
ea
lth
ch
allen
g
e
an
d
u
n
d
er
s
co
r
e
th
e
im
p
o
r
tan
ce
o
f
o
p
tim
izin
g
d
iag
n
o
s
tic
m
eth
o
d
s
.
Giv
en
th
e
p
au
city
o
f
d
ata
in
L
atin
Am
er
ica,
esp
ec
i
ally
in
Per
u
,
it is
cr
u
cial
to
ex
p
lo
r
e
n
ew
s
tr
ateg
ies
to
im
p
r
o
v
e
t
h
e
d
etec
tio
n
a
n
d
m
an
ag
em
en
t
o
f
OSA.
I
n
th
i
s
co
n
tex
t,
ar
tific
ial
in
tellig
en
ce
(
AI
)
,
p
ar
ticu
la
r
ly
m
ac
h
in
e
lear
n
i
n
g
(
ML
)
,
h
as
d
em
o
n
s
tr
ated
its
p
o
ten
tial
t
o
an
aly
ze
co
m
p
le
x
d
ata
p
atter
n
s
an
d
im
p
r
o
v
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
[
2
1
]
–
[
2
3
]
.
ML
alg
o
r
ith
m
s
ca
n
p
r
o
ce
s
s
s
leep
d
ata
an
d
clin
ical
s
y
m
p
t
o
m
s
m
o
r
e
q
u
ic
k
ly
an
d
ac
c
u
r
ately
,
f
ac
ilit
atin
g
ea
r
ly
d
etec
tio
n
an
d
tim
ely
in
ter
v
en
tio
n
[
2
4
]
.
I
n
a
d
d
itio
n
,
th
e
in
teg
r
atio
n
o
f
AI
in
to
s
leep
m
o
n
ito
r
in
g
d
ev
ices
allo
ws
f
o
r
o
p
tim
ized
d
ata
c
o
llectio
n
an
d
co
n
tin
u
o
u
s
ass
es
s
m
en
ts
,
wh
ich
co
u
l
d
tr
an
s
f
o
r
m
th
e
clin
ical
ap
p
r
o
ac
h
to
OSA,
esp
ec
ially
in
r
eso
u
r
ce
-
lim
ited
r
eg
io
n
s
[
2
5
]
–
[
2
7
]
.
T
h
e
r
elatio
n
s
h
ip
b
etwe
en
AI
an
d
th
e
d
iag
n
o
s
is
o
f
OSA
r
e
p
r
esen
ts
a
p
r
o
m
is
in
g
ar
ea
th
at
in
teg
r
ates
ad
v
an
ce
d
tech
n
o
lo
g
y
in
te
n
d
i
n
g
to
im
p
r
o
v
e
h
ea
lth
o
u
tco
m
es.
Dee
p
en
in
g
th
is
in
te
r
ac
tio
n
an
d
f
o
s
ter
in
g
co
n
tin
u
ed
r
esear
ch
in
th
is
ar
e
a
m
ay
lead
t
o
in
n
o
v
ativ
e
d
ev
elo
p
m
en
ts
th
at
tr
an
s
f
o
r
m
h
o
w
SD
ar
e
d
iag
n
o
s
ed
an
d
tr
ea
ted
.
I
n
th
is
co
n
tex
t,
th
e
p
r
esen
t
s
tu
d
y
aim
s
to
e
v
a
lu
ate
h
o
w
an
AI
-
b
ased
class
if
icatio
n
alg
o
r
ith
m
in
f
lu
en
ce
s
th
e
d
ia
g
n
o
s
tic
p
r
o
c
ess
o
f
OSA
in
L
im
a,
Per
u
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
is
s
e
cti
o
n
p
r
ese
n
ts
s
o
m
e
w
o
r
k
r
ela
te
d
t
o
th
e
t
o
p
ic
o
f
s
t
u
d
y
.
Alm
az
ay
d
eh
et
a
l.
[
2
8
]
d
ev
el
o
p
e
d
a
s
u
p
p
o
r
t
v
e
ct
o
r
m
ac
h
i
n
e
(
SV
M)
-
b
ase
d
al
g
o
r
i
th
m
th
at
u
s
es
ele
ct
r
o
ca
r
d
i
o
g
r
am
(
E
C
G
)
d
at
a
t
o
class
i
f
y
p
a
tie
n
ts
wit
h
a
n
d
wi
th
o
u
t
OSA,
a
ch
ie
v
in
g
a
n
ac
cu
r
ac
y
o
f
9
6
.
5
%
.
H
o
wev
er
,
th
is
a
p
p
r
o
ac
h
f
o
c
u
s
es
o
n
l
y
o
n
th
e
an
al
y
s
is
o
f
E
C
G
s
i
g
n
als
,
w
h
ic
h
l
im
i
ts
i
ts
ap
p
l
ica
b
i
lit
y
i
n
m
o
r
e
co
m
p
l
ex
cli
n
ic
al
s
c
e
n
a
r
i
o
s
t
h
at
r
e
q
u
i
r
e
t
h
e
in
te
g
r
ati
o
n
o
f
m
u
lti
p
l
e
s
o
u
r
c
es
o
f
p
h
y
s
i
o
l
o
g
ic
al
d
a
ta
.
I
n
c
o
n
tr
ast
,
t
h
e
p
r
ese
n
t
s
t
u
d
y
p
r
o
p
o
s
es
t
h
e
in
c
o
r
p
o
r
ati
o
n
o
f
p
h
y
s
i
o
l
o
g
i
ca
l
a
n
d
cl
in
ica
l d
ata
,
all
o
wi
n
g
f
o
r
g
r
e
ate
r
r
o
b
u
s
t
n
e
s
s
i
n
OSA
d
ete
cti
o
n
.
A
cc
o
r
d
in
g
to
L
u
o
et
a
l
.
[
2
9
]
,
f
i
v
e
M
L
m
o
d
els
a
n
d
t
wo
d
ia
g
n
o
s
tic
s
c
h
em
es
w
e
r
e
u
s
ed
t
o
d
ev
el
o
p
a
l
o
w
-
c
o
s
t
s
y
s
te
m
t
h
at
d
et
ec
ts
OS
A
in
r
ea
l
tim
e
u
s
i
n
g
s
n
o
r
i
n
g
r
ec
o
r
d
in
g
s
an
d
p
o
ly
s
o
m
n
o
g
r
a
p
h
y
(
PS
G
)
d
at
a,
wit
h
9
7
%
ac
cu
r
a
c
y
.
D
es
p
ite
its
ef
f
ec
t
iv
en
ess
,
it
d
o
es
n
o
t
a
d
d
r
ess
t
h
e
i
n
t
eg
r
ati
o
n
o
f
v
a
r
i
o
u
s
p
h
y
s
i
o
l
o
g
i
ca
l
s
o
u
r
ce
s
.
Sim
ila
r
l
y
,
H
ai
d
a
r
et
a
l
.
[
3
0
]
e
m
p
lo
y
e
d
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
s
with
r
esp
ir
ato
r
y
d
ata,
ac
h
iev
in
g
an
ac
cu
r
ac
y
o
f
8
3
.
5
%,
alth
o
u
g
h
with
o
u
t
co
n
s
id
er
in
g
o
th
er
p
h
y
s
io
lo
g
ical
an
d
clin
ical
v
ar
ia
b
les.
Al
-
Ab
ed
et
a
l.
[
3
1
]
p
r
o
p
o
s
es
an
alg
o
r
ith
m
b
ased
o
n
tex
tu
r
al
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
n
o
r
m
alize
d
g
r
ay
-
lev
el
c
o
n
cu
r
r
en
ce
m
atr
ices
(
NGL
C
M)
o
b
tain
ed
b
y
s
h
o
r
t
-
tim
e
d
is
cr
ete
Fo
u
r
ier
tr
an
s
f
o
r
m
(
STDFT
)
f
o
r
OSA
d
etec
tio
n
.
Alth
o
u
g
h
th
is
ap
p
r
o
ac
h
o
f
f
e
r
s
p
r
o
m
is
in
g
r
esu
lts
,
with
an
ac
cu
r
ac
y
o
f
9
0
.
1
6
%,
i
t
r
elies
o
n
co
m
p
lex
m
ath
em
ati
ca
l
tr
an
s
f
o
r
m
atio
n
s
th
at
co
u
l
d
m
ak
e
it
d
if
f
icu
lt
to
im
p
lem
en
t
in
clin
ical
p
r
ac
tice
.
Acc
o
r
d
in
g
to
Kr
is
tian
s
en
et
a
l.
[
3
2
]
,
2
9
p
atien
ts
with
s
u
s
p
ec
ted
OSA
wer
e
in
v
esti
g
ated
u
s
in
g
a
lo
w
-
co
s
t
s
tr
ain
g
au
g
e
r
esp
ir
ato
r
y
b
elt
to
r
ec
o
r
d
v
ar
io
u
s
b
r
ea
th
in
g
p
ar
am
eter
s
.
I
n
th
e
s
tu
d
y
,
v
ar
io
u
s
ML
-
b
ased
d
ia
g
n
o
s
tic
to
o
ls
wer
e
em
p
lo
y
e
d
,
y
i
eld
in
g
an
ac
c
u
r
ac
y
o
f
7
6
.
0
9
% a
n
d
a
s
en
s
itiv
ity
o
f
7
8
.
3
3
%.
Ho
wev
e
r
,
th
e
lo
wer
ac
cu
r
ac
y
an
d
e
x
clu
s
iv
e
f
o
cu
s
o
n
r
esp
ir
ato
r
y
d
ata
ar
e
s
ig
n
if
ican
t
lim
itatio
n
s
.
On
th
e
o
th
er
h
a
n
d
,
B
o
u
s
co
u
let
et
a
l.
[
3
3
]
was
ca
r
r
ied
o
u
t
a
co
m
p
ar
is
o
n
o
f
t
h
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
o
f
p
o
r
ta
b
le
m
o
n
ito
r
s
,
e
v
alu
atin
g
th
e
d
esatu
r
atio
n
in
d
ex
o
f
th
e
r
esp
ir
ato
r
y
in
d
e
x
.
I
n
th
is
s
tu
d
y
,
a
to
tal
o
f
3
8
p
atien
ts
wer
e
ev
alu
ated
,
ac
h
iev
in
g
a
d
iag
n
o
s
tic
co
n
f
id
en
ce
o
f
9
5
%.
Alth
o
u
g
h
th
e
r
esu
lts
ar
e
r
ele
v
an
t,
th
e
s
tu
d
y
d
o
es
n
o
t
ex
p
lo
r
e
th
e
u
s
e
o
f
a
d
v
an
ce
d
ML
alg
o
r
ith
m
s
,
a
lim
itatio
n
a
d
d
r
ess
ed
in
t
h
is
wo
r
k
b
y
co
m
b
in
in
g
ML
tech
n
i
q
u
es
with
o
th
er
v
ar
ia
b
les.
Fin
ally
,
Po
lat
et
a
l.
[
3
4
]
i
n
v
esti
g
ated
PS
G
d
ev
ices
u
s
in
g
ML
al
g
o
r
ith
m
s
,
ac
h
iev
in
g
9
7
.
1
%
ac
c
u
r
ac
y
in
8
3
p
atien
t
s
.
Alth
o
u
g
h
r
o
b
u
s
t,
th
is
ap
p
r
o
ac
h
f
o
cu
s
es
o
n
a
lim
ited
n
u
m
b
er
o
f
v
ar
iab
les.
Similar
ly
,
Kan
g
et
a
l.
[
3
5
]
e
m
p
lo
y
ed
s
n
o
r
in
g
s
o
u
n
d
s
in
2
4
p
atien
ts
,
ac
h
ie
v
in
g
an
ac
c
u
r
ac
y
o
f
9
0
.
6
5
%
f
o
r
ap
n
ea
p
r
ed
ictio
n
.
Ho
wev
er
,
its
u
s
e
o
f
a
s
in
g
le
ac
o
u
s
tic
s
ig
n
al
lim
it
s
it
s
ap
p
licab
ili
ty
.
Ou
r
s
tu
d
y
,
b
y
co
n
tem
p
latin
g
p
h
y
s
io
lo
g
ical
an
d
clin
ical
v
ar
iab
les,
p
r
esen
ts
a
d
if
f
er
en
t
ap
p
r
o
ac
h
th
a
n
o
th
er
s
tu
d
ies,
s
in
ce
m
o
s
t
p
r
ev
i
o
u
s
r
esear
ch
ten
d
s
to
f
o
c
u
s
o
n
th
e
an
aly
s
is
o
f
a
s
i
n
g
le
d
ata
s
o
u
r
ce
o
r
is
o
lated
s
i
g
n
als,
s
u
ch
as
E
C
G,
r
esp
ir
ato
r
y
s
ig
n
als,
o
r
s
n
o
r
in
g
s
o
u
n
d
s
.
I
n
s
tead
,
b
y
in
teg
r
atin
g
b
o
th
p
h
y
s
io
lo
g
ical
v
a
r
iab
les
(
s
u
ch
as
b
r
ea
th
in
g
p
atter
n
s
,
h
ea
r
t
r
ate,
o
r
o
x
y
g
en
atio
n
lev
els)
an
d
clin
ical
d
ata
(
m
ed
ical
h
is
to
r
y
,
r
ep
o
r
ted
s
y
m
p
to
m
s
,
an
d
p
atien
t
d
em
o
g
r
a
p
h
ics),
th
is
ap
p
r
o
ac
h
allo
ws f
o
r
a
m
o
r
e
co
m
p
lete
an
d
ac
cu
r
ate
v
iew
o
f
th
e
p
atien
t'
s
co
n
d
itio
n
.
3.
M
E
T
H
O
D
Fo
r
th
e
d
ev
elo
p
m
en
t
o
f
t
h
e
cl
ass
if
icatio
n
alg
o
r
ith
m
with
AI
,
th
e
k
an
b
a
n
m
eth
o
d
o
l
o
g
y
wa
s
ch
o
s
en
.
T
h
is
m
eth
o
d
o
lo
g
y
is
a
to
o
l
o
f
th
e
l
ea
n
m
eth
o
d
o
lo
g
y
th
at
is
wid
ely
u
s
ed
in
s
o
f
twar
e
d
ev
el
o
p
m
en
t
[
3
6
]
.
I
t
is
a
v
is
u
al
s
y
s
tem
to
m
an
ag
e
th
e
d
ev
elo
p
m
e
n
t
o
f
a
p
r
o
ject;
it
u
s
es
a
b
o
ar
d
d
iv
id
e
d
in
to
co
l
u
m
n
s
th
at
r
e
p
r
esen
t
d
if
f
er
en
t
s
tag
es
o
f
th
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
[
3
7
]
.
Nex
t,
we
a
n
aly
ze
th
e
ac
tiv
ities
th
at
we
w
ill
h
av
e
to
d
ev
elo
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
2
0
-
4
5
3
2
4522
f
o
r
th
e
cr
ea
tio
n
o
f
th
e
alg
o
r
ith
m
.
T
h
e
ac
tiv
ities
wer
e
d
iv
id
ed
in
to
th
r
ee
s
tag
es:
p
r
o
b
le
m
d
ef
in
itio
n
,
p
r
o
b
lem
an
aly
s
is
,
an
d
alg
o
r
ith
m
d
esig
n
with
th
eir
r
esp
ec
tiv
e
task
s
,
as d
etailed
in
T
ab
le
1
.
T
ab
le
1
.
T
o
-
d
o
lis
t
P
h
a
se
N°
P
e
n
d
i
n
g
t
a
sk
s
D
e
scri
p
t
i
o
n
P
r
i
o
r
i
t
y
P
r
o
b
l
e
m
d
e
f
i
n
i
t
i
o
n
T1
D
e
f
i
n
e
t
h
e
p
r
o
b
l
e
m
W
e
d
e
f
i
n
e
d
t
h
e
p
r
o
b
l
e
m
o
f
t
h
e
st
u
d
y
.
M
e
d
i
a
P
r
o
b
l
e
m
a
n
a
l
y
s
i
s
T2
D
e
f
i
n
e
i
n
p
u
t
d
a
t
a
W
e
d
e
f
i
n
e
w
h
a
t
d
a
t
a
t
h
e
a
l
g
o
r
i
t
h
m
r
e
q
u
i
r
e
s
t
o
p
r
o
v
i
d
e
u
s
w
i
t
h
t
h
e
e
x
p
e
c
t
e
d
r
e
s
u
l
t
s.
H
i
g
h
T3
D
e
f
i
n
e
t
h
e
o
u
t
p
u
t
d
a
t
a
W
e
d
e
f
i
n
e
h
o
w
t
h
e
a
l
g
o
r
i
t
h
m
w
i
l
l
e
x
p
r
e
ss
t
h
e
r
e
s
u
l
t
a
f
t
e
r
so
r
t
i
n
g
t
h
e
i
n
p
u
t
d
a
t
a
.
H
i
g
h
T4
D
e
f
i
n
e
f
o
r
m
u
l
a
s
a
n
d
met
h
o
d
s
W
e
d
e
f
i
n
e
t
h
e
f
o
r
mu
l
a
s
a
n
d
m
e
t
h
o
d
s
r
e
q
u
i
r
e
d
f
o
r
a
l
g
o
r
i
t
h
m
d
e
v
e
l
o
p
me
n
t
.
M
e
d
i
a
A
l
g
o
r
i
t
h
m
d
e
si
g
n
T5
D
e
si
g
n
t
h
e
p
se
u
d
o
c
o
d
e
W
i
t
h
t
h
e
i
n
f
o
r
mat
i
o
n
g
a
t
h
e
r
e
d
p
r
e
v
i
o
u
s
l
y
,
w
e
d
e
si
g
n
e
d
t
h
e
p
se
u
d
o
c
o
d
e
o
f
t
h
e
a
l
g
o
r
i
t
h
m.
D
o
w
n
l
o
a
d
T6
D
e
si
g
n
t
h
e
f
l
o
w
c
h
a
r
t
A
s i
n
t
h
e
p
r
e
c
e
d
i
n
g
t
a
s
k
,
t
h
e
f
l
o
w
c
h
a
r
t
i
s
d
e
si
g
n
e
d
D
o
w
n
l
o
a
d
T7
I
mp
l
e
me
n
t
t
h
e
c
o
d
e
W
e
w
r
o
t
e
t
h
e
c
o
d
e
w
i
t
h
t
h
e
P
y
t
h
o
n
p
r
o
g
r
a
mm
i
n
g
l
a
n
g
u
a
g
e
.
H
i
g
h
T8
R
e
v
i
e
w
a
n
d
o
p
t
i
mi
z
e
t
h
e
c
o
d
e
W
e
c
o
r
r
e
c
t
a
n
d
o
p
t
i
mi
z
e
t
h
e
p
a
r
t
s
o
f
t
h
e
c
o
d
e
t
h
a
t
ma
y
c
a
u
s
e
e
r
r
o
r
s wh
e
n
e
x
e
c
u
t
i
n
g
t
h
e
c
o
d
e
.
M
e
d
i
a
3
.
1
.
K
a
nb
a
n bo
a
rd
elem
ent
s
3.
1
.
1
.
To
-
do
lis
t
Fo
r
th
e
co
r
r
ec
t
im
p
lem
e
n
tatio
n
o
f
th
e
class
if
icatio
n
alg
o
r
ith
m
b
ased
o
n
AI
,
th
e
k
an
b
an
m
eth
o
d
o
lo
g
y
h
as
b
ee
n
u
s
ed
,
wh
ich
allo
ws
a
v
is
u
al
an
d
s
tr
u
ctu
r
ed
m
an
a
g
em
en
t
o
f
th
e
task
s
to
b
e
d
ev
elo
p
ed
.
W
ith
in
th
is
m
eth
o
d
o
l
o
g
y
,
o
n
e
o
f
th
e
k
e
y
elem
en
ts
is
th
e
“T
o
-
d
o
lis
t”,
wh
ich
g
r
o
u
p
s
an
d
o
r
g
an
izes
t
h
e
ess
en
tial
ac
tiv
ities
ac
co
r
d
in
g
to
th
e
d
if
f
er
e
n
t
s
tag
es
o
f
th
e
alg
o
r
ith
m
d
ev
el
o
p
m
en
t.
T
h
ese
task
s
in
clu
d
e
d
e
f
in
in
g
t
h
e
p
r
o
b
lem
,
id
en
tify
in
g
an
d
an
aly
zin
g
th
e
in
p
u
t
an
d
o
u
tp
u
t
d
ata,
s
elec
tin
g
ap
p
r
o
p
r
iate
f
o
r
m
u
las
an
d
m
eth
o
d
s
,
as
well
as
d
esig
n
in
g
th
e
p
s
eu
d
o
c
o
d
e,
an
d
im
p
lem
en
tin
g
th
e
co
d
e
in
Py
th
o
n
.
T
h
e
o
r
g
an
izatio
n
o
f
th
ese
task
s
in
a
lis
t
f
ac
ilit
ates
p
lan
n
in
g
a
n
d
p
r
o
g
r
ess
tr
ac
k
in
g
,
allo
win
g
to
p
r
io
r
itize
th
o
s
e
ac
tiv
ities
th
at
ar
e
m
o
s
t
cr
itical
an
d
en
s
u
r
in
g
an
o
r
d
er
ly
a
n
d
ef
f
icien
t p
r
o
g
r
ess
io
n
in
th
e
d
ev
elo
p
m
en
t o
f
th
e
p
r
o
ject.
3.
1
.
2
.
B
o
a
rd
As
p
ar
t
o
f
th
e
k
an
b
an
m
eth
o
d
o
lo
g
y
,
it
is
n
ec
ess
ar
y
to
u
s
e
a
b
o
ar
d
d
iv
id
e
d
i
n
to
c
o
lu
m
n
s
t
o
v
is
u
alize
th
e
p
r
o
g
r
ess
in
th
e
d
ev
el
o
p
m
e
n
t
o
f
th
e
alg
o
r
ith
m
.
T
o
ca
r
r
y
o
u
t
th
is
task
,
we
u
s
ed
th
e
d
ig
i
tal
p
latf
o
r
m
T
r
ello
,
in
wh
ich
we
c
o
n
f
ig
u
r
ed
a
b
o
ar
d
co
n
s
is
tin
g
o
f
th
e
f
o
llo
wi
n
g
co
l
u
m
n
s
:
task
lis
t,
in
p
r
o
g
r
ess
,
an
d
d
o
n
e,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
I
n
ad
d
i
tio
n
,
to
f
ac
ilit
ate
th
e
u
s
e
o
f
th
e
ac
tiv
ity
tab
le
an
d
th
e
p
r
o
g
r
e
s
s
o
f
th
e
p
r
o
ject,
we
estab
lis
h
ed
th
e
p
o
licies o
r
wo
r
k
r
u
les as sh
o
wn
in
T
a
b
le
2
.
Fig
u
r
e
1
.
Kan
b
an
m
et
h
o
d
o
lo
g
y
b
o
ar
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fica
tio
n
a
lg
o
r
ith
m
w
ith
a
r
tifi
cia
l in
tellig
en
ce
fo
r
th
e
d
ia
g
n
o
s
tic
…
(
Je
h
il V
e
n
tu
r
a
-
Te
cc
o
)
4523
3
.
1
.
3
.
Rules
f
o
r
t
he
us
e
o
f
t
h
e
bo
a
rd
T
o
en
s
u
r
e
e
f
f
icien
t
p
r
o
ject
m
an
ag
em
en
t,
s
p
ec
if
ic
r
u
les
wer
e
estab
lis
h
ed
f
o
r
th
e
u
s
e
o
f
t
h
e
Kan
b
an
b
o
ar
d
.
T
h
ese
r
u
les aim
to
o
p
tim
ize
th
e
wo
r
k
f
lo
w
,
av
o
id
ex
c
ess
iv
e
ac
cu
m
u
latio
n
o
f
task
s
in
a
s
in
g
le
s
tag
e,
an
d
m
ain
tain
a
s
tr
u
ctu
r
ed
ex
ec
u
ti
o
n
o
f
th
e
p
r
o
ject.
Am
o
n
g
th
e
m
ain
r
u
les
estab
li
s
h
ed
is
t
h
e
lim
itatio
n
o
f
th
e
n
u
m
b
er
o
f
task
s
th
at
ca
n
b
e
d
ev
elo
p
e
d
s
im
u
ltan
eo
u
s
ly
,
en
s
u
r
in
g
th
at
n
o
b
o
ttlen
ec
k
s
ar
e
g
en
er
ate
d
in
th
e
p
r
o
ce
s
s
.
L
ik
ewise,
it
was
d
ete
r
m
in
ed
th
at
th
e
task
s
in
p
r
o
g
r
ess
m
u
s
t
b
elo
n
g
to
th
e
s
am
e
d
ev
elo
p
m
en
t
p
h
ase,
av
o
id
in
g
th
e
s
im
u
ltan
eo
u
s
ex
e
cu
tio
n
o
f
ac
tiv
ities
f
r
o
m
d
if
f
er
en
t
s
tag
es,
wh
ich
co
u
ld
g
en
e
r
ate
in
co
n
s
is
ten
cies
an
d
d
elay
s
.
T
h
ese
r
u
les
ar
e
i
n
ten
d
ed
to
im
p
r
o
v
e
p
r
o
d
u
ctiv
ity
,
m
ain
tain
a
clea
r
f
o
cu
s
i
n
ea
ch
p
h
ase,
an
d
g
u
ar
an
tee
a
n
o
r
g
an
ized
d
ev
elo
p
m
en
t a
lig
n
e
d
with
th
e
p
r
in
cip
les o
f
th
e
k
an
b
an
m
et
h
o
d
o
lo
g
y
.
T
ab
le
2
.
Kan
b
an
b
o
ar
d
u
s
ag
e
p
o
licies/
r
u
les
N°
U
sag
e
p
o
l
i
c
i
e
s
P1
To
a
v
o
i
d
t
h
e
b
o
t
t
l
e
n
e
c
k
,
o
n
l
y
2
t
a
s
k
s
c
a
n
b
e
p
e
r
f
o
r
me
d
si
mu
l
t
a
n
e
o
u
s
l
y
P2
Th
e
t
a
sk
s
t
o
b
e
p
e
r
f
o
r
me
d
m
u
s
t
b
e
l
o
n
g
t
o
t
h
e
s
a
me
p
h
a
s
e
P3
Ta
sk
s
t
h
a
t
b
e
l
o
n
g
t
o
d
i
f
f
e
r
e
n
t
p
h
a
s
e
s
may
n
o
t
b
e
d
e
v
e
l
o
p
e
d
3
.
2
.
E
x
ec
utio
n o
f
t
he
t
a
s
k
s
3
.
2
.
1
.
T
1
-
def
ine
t
he
pro
blem
Fo
r
th
is
r
esear
ch
wo
r
k
,
we
p
r
o
p
o
s
ed
th
e
d
ev
elo
p
m
e
n
t
o
f
a
class
if
ica
tio
n
alg
o
r
ith
m
with
AI
to
d
iag
n
o
s
e
OSA.
W
ith
th
e
an
aly
s
is
o
f
liter
atu
r
e
r
elate
d
to
th
i
s
d
is
ea
s
e,
we
k
n
o
w
th
at
f
o
r
th
e
d
iag
n
o
s
is
o
f
OSA,
th
e
f
o
llo
win
g
d
ata
ar
e
co
n
te
m
p
lated
,
th
e
E
p
wo
r
th
s
leep
in
ess
s
ca
le,
wh
ich
g
iv
es
u
s
a
d
iag
n
o
s
is
o
f
clin
ical
s
u
s
p
icio
n
,
p
h
y
s
ical
ex
am
in
ati
o
n
,
an
d
h
is
to
r
y
o
f
p
r
e
-
e
x
is
tin
g
d
is
ea
s
es.
I
n
ad
d
itio
n
,
th
e
s
leep
ap
n
ea
/h
y
p
o
p
n
ea
in
d
ex
is
o
b
tain
ed
b
y
d
i
v
id
in
g
th
e
n
u
m
b
er
o
f
ap
n
ea
ev
e
n
ts
b
y
th
e
h
o
u
r
s
o
f
s
leep
(
in
m
in
u
tes)
an
d
m
u
ltip
ly
in
g
b
y
6
0
,
b
u
t
f
o
r
an
ap
n
ea
ev
en
t
to
b
e
co
n
s
id
er
ed
as
s
u
ch
,
th
e
air
way
co
llap
s
e
m
u
s
t
b
e
g
r
ea
ter
th
an
1
0
s
ec
o
n
d
s
.
[
3
8
]
.
T
o
k
n
o
w
th
e
n
u
m
b
er
o
f
ap
n
ea
ev
en
ts
s
u
f
f
er
in
g
d
u
r
i
n
g
th
e
n
ig
h
t,
PS
G
s
tu
d
ies
ar
e
p
er
f
o
r
m
ed
,
wh
ich
m
ea
s
u
r
e
r
esp
ir
atio
n
,
a
n
d
h
ea
r
t
r
ate,
am
o
n
g
o
th
e
r
s
.
3
.
2
.
2
.
T
2
/T
3
/T
4
-
def
ini
ng
in
p
ut
da
t
a
/
def
ini
ng
t
he
o
utput
da
t
a
/def
in
e
t
he
f
o
r
m
ula
s
a
nd
m
et
ho
ds
C
o
n
tin
u
in
g
with
wh
at
was
ad
d
r
ess
ed
in
th
e
p
r
ev
io
u
s
task
,
we
id
en
tifie
d
th
e
f
o
llo
wi
n
g
g
en
er
al
in
f
o
r
m
atio
n
in
p
u
t
d
ata
s
u
ch
as
th
e
a
g
e
a
n
d
s
ex
o
f
th
e
p
atien
t
,
in
ad
d
itio
n
,
to
m
ed
ical
h
is
to
r
y
in
f
o
r
m
atio
n
s
u
ch
as
th
e
p
r
esen
ce
o
f
s
n
o
r
in
g
,
l
ev
el
o
f
d
ay
tim
e
s
leep
in
ess
,
h
o
u
r
s
o
f
s
leep
,
d
iag
n
o
s
is
o
f
ar
ter
ial
h
y
p
er
ten
s
io
n
,
b
o
d
y
m
ass
in
d
ex
(
B
MI
)
a
n
d
t
h
e
E
p
wo
r
t
h
in
d
e
x
.
T
h
e
alg
o
r
it
h
m
m
u
s
t
b
e
a
b
le
to
d
eter
m
in
e
wh
eth
er
th
e
p
atien
t
s
u
f
f
er
s
f
r
o
m
OSA
o
r
n
o
t.
T
h
is
in
f
o
r
m
atio
n
ca
n
b
e
p
r
ese
n
ted
in
two
way
s
:
in
b
in
ar
y
f
o
r
m
,
wh
er
e
it
is
r
ep
r
esen
ted
b
y
'
1
'
if
th
e
p
atien
t
h
as
OSA
an
d
'
0
'
if
h
e/sh
e
d
o
es
n
o
t,
o
r
in
tex
tu
al
f
o
r
m
.
Fu
r
th
er
m
o
r
e
,
co
n
s
id
er
in
g
th
at
t
h
e
alg
o
r
it
h
m
will
b
e
im
p
lem
en
ted
in
P
y
th
o
n
v
er
s
io
n
3
,
it
was
ess
e
n
tial
to
ex
am
in
e
th
e
m
eth
o
d
s
o
f
f
er
e
d
b
y
th
e
la
n
g
u
ag
e.
I
t
was
d
ec
id
e
d
t
o
u
s
e
th
e
d
ec
is
io
n
tr
ee
(
DT
)
class
if
icatio
n
m
o
d
el
as
th
e
AI
co
m
p
o
n
en
t
t
o
d
iag
n
o
s
e
OSA,
alo
n
g
with
o
th
er
ap
p
r
o
ac
h
es,
s
u
ch
as
len
(
)
,
f
it()
,
p
r
ed
ict(
)
,
ac
cu
r
ac
y
_
s
co
r
e(
)
,
an
d
co
n
f
u
s
io
n
_
m
atr
ix
(
)
.
3
.
2
.
3
.
T
5
/T
6
-
des
ig
nin
g
t
he
ps
eudo
co
de/
d
esig
n t
he
f
lo
wcha
rt
W
ith
th
e
in
f
o
r
m
atio
n
g
ath
er
e
d
in
th
e
p
r
ev
io
u
s
task
s
,
a
p
s
eu
d
o
co
d
e
h
as
b
ee
n
d
esig
n
ed
th
at
co
v
er
s
th
e
r
ea
d
in
g
o
f
t
h
e
p
atien
t'
s
d
ata
a
n
d
th
eir
s
leep
h
a
b
its
.
C
o
m
p
lem
en
ted
with
th
e
cr
ea
tio
n
o
f
t
h
e
tr
ain
in
g
an
d
test
s
ets,
to
p
r
ep
r
o
ce
s
s
th
e
d
ata
a
n
d
p
r
ep
a
r
e
th
em
f
o
r
th
e
tr
ain
in
g
o
f
t
h
e
m
o
d
el.
On
ce
th
is
s
tag
e
is
co
m
p
leted
,
we
p
r
o
ce
ed
with
th
e
cr
ea
tio
n
an
d
tr
ain
in
g
o
f
th
e
m
o
d
el,
f
o
llo
wed
b
y
th
e
p
r
e
d
ictio
n
p
h
ase.
T
h
e
f
lo
wch
a
r
t
o
f
th
e
alg
o
r
ith
m
was
also
d
esig
n
ed
co
n
s
id
er
in
g
th
e
p
s
eu
d
o
co
d
e
d
ev
elo
p
e
d
in
th
e
p
r
ev
io
u
s
task
.
T
h
e
d
iag
r
am
is
s
h
o
wn
in
Fig
u
r
e
2
.
So
m
e
p
ar
t
s
o
f
th
e
f
lo
wch
ar
t
u
s
e
f
u
n
ctio
n
s
u
n
iq
u
e
to
th
e
Py
th
o
n
p
r
o
g
r
am
m
in
g
lan
g
u
ag
e
th
at
ar
e
im
p
o
s
s
ib
le
to
illu
s
tr
ate
in
th
e
g
r
a
p
h
ic.
3
.
2
.
4
.
T
7
/T
8
-
im
plem
ent
ing
t
he
co
de/
r
ev
iew
a
nd
o
ptim
ize
t
he
co
de
B
ased
o
n
th
e
wo
r
k
d
o
n
e
in
t
ask
s
5
an
d
6
,
we
d
ev
elo
p
e
d
th
e
co
d
e.
First,
we
im
p
o
r
t
th
e
lib
r
ar
ies
tr
ain
_
test
_
s
p
lit
to
s
p
lit
th
e
d
ataset
f
o
r
tr
ain
in
g
an
d
test
in
g
,
f
o
llo
wed
b
y
Dec
is
io
n
T
r
ee
C
lass
if
ier
to
class
if
y
th
e
d
ata,
an
d
f
in
ally
th
e
lib
r
ar
ies
ac
cu
r
ac
y
_
s
co
r
e
a
n
d
c
o
n
f
u
s
io
n
_
m
atr
ix
to
ev
al
u
ate
th
e
class
if
icatio
n
ac
cu
r
ac
y
.
As in
p
u
t d
ata,
th
er
e
ar
e
two
b
lo
ck
s
,
th
e
p
atien
t'
s
d
ata
an
d
h
is
s
leep
d
ata.
I
n
th
e
p
atien
t's
d
at
a,
th
e
p
atien
t'
s
ag
e,
g
en
d
er
,
an
d
th
e
E
p
w
o
r
th
s
leep
in
ess
s
ca
le
ar
e
r
e
q
u
ested
,
in
th
e
s
leep
d
ata,
th
e
d
u
r
atio
n
o
f
s
leep
a
n
d
th
e
f
r
eq
u
e
n
cy
o
f
ap
n
ea
s
p
er
n
ig
h
t.
Su
b
s
eq
u
en
tly
,
we
cr
ea
te
tw
o
lis
ts
o
r
tu
p
les
f
o
r
tr
ain
in
g
an
d
test
in
g
,
ea
ch
o
f
th
ese
tu
p
les
s
to
r
es
3
r
elev
an
t
p
atien
t
d
ata,
s
u
ch
as
p
at
ien
t
d
ata,
s
leep
d
ata,
an
d
d
iag
n
o
s
is
.
Fo
r
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
we
m
u
s
t
s
ep
ar
ate
th
e
in
f
o
r
m
atio
n
c
o
n
tai
n
ed
in
th
e
tu
p
le
'
tr
ain
in
g
_
s
et'
in
to
two
lis
t
s
,
o
n
e
co
n
tain
i
n
g
th
e
f
ir
s
t
two
d
ata
(
p
atien
t
an
d
d
r
ea
m
d
ata
)
an
d
th
e
last
o
n
e
th
e
d
iag
n
o
s
is
.
W
e
cr
ea
te
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
2
0
-
4
5
3
2
4524
v
ar
iab
le
'
m
o
d
el'
wh
ich
in
s
tan
tiates
th
e
DT
class
an
d
with
th
e
m
eth
o
d
'
f
it'
we
tr
ain
th
e
m
o
d
el
with
th
e
tr
ain
i
n
g
liS
Ds
'
x
'
an
d
'
y
'
.
m
o
d
el=
Dec
is
io
n
T
r
ee
C
lass
if
ie
r
(
)
m
o
d
el.
f
it(x
_
tr
ain
in
g
,
y
_
t
r
ain
in
g
)
As
a
p
r
e
-
f
in
aliza
tio
n
p
ar
t,
we
u
s
e
th
e
'
p
r
ed
ict'
m
eth
o
d
to
p
r
e
d
ict
th
e
d
ata,
with
th
e
'
ac
cu
r
ac
y
_
s
co
r
e
(
)
'
m
eth
o
d
we
ca
lcu
late
th
e
ac
c
u
r
ac
y
o
f
th
e
p
r
ed
ictio
n
m
ad
e
,
an
d
with
'
co
n
f
u
s
io
n
_
m
atr
ix
(
)
'
we
ca
n
s
ee
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
eth
o
d
.
F
in
ally
,
th
e
p
r
e
d
ictio
n
is
m
ad
e,
if
th
e
p
r
ed
ictio
n
o
f
th
e
m
o
d
e
l
is
eq
u
al
to
1
th
e
p
atien
t
is
d
iag
n
o
s
ed
with
OSA,
o
th
er
wis
e,
th
e
co
n
d
itio
n
i
s
d
is
ca
r
d
ed
.
Fin
ally
,
to
o
p
tim
ize
th
e
d
ata
en
tr
y
p
r
o
ce
s
s
we
h
a
v
e
ch
a
n
g
ed
th
e
d
ata
r
ea
d
in
g
to
t
h
e
r
ea
d
_
c
s
v
m
eth
o
d
p
r
o
v
id
e
d
b
y
th
e
‘
Pan
d
as’
lib
r
ar
y
f
o
r
r
ea
d
in
g
'
csv
'
f
iles
.
T
h
is
is
th
e
o
n
ly
ch
a
n
g
e
a
p
p
lied
to
t
h
e
alg
o
r
ith
m
.
Fig
u
r
e
2
.
Flo
w
d
ia
g
r
am
3
.
3
.
Alg
o
rit
hm
t
r
a
ini
ng
3
.
3
.
1
.
T
ra
ini
ng
da
t
a
s
et
Fo
r
th
e
tr
ain
in
g
o
f
th
e
class
if
icatio
n
alg
o
r
ith
m
,
ac
ce
s
s
was
r
eq
u
ested
to
th
e
d
atab
ase
o
f
th
e
Natio
n
al
Sleep
R
esear
ch
R
eso
u
r
ce
(
N
SR
R
)
,
wh
ich
h
as
a
r
ep
o
s
ito
r
y
o
f
d
ata
o
n
s
leep
,
b
ased
o
n
q
u
esti
o
n
n
air
es
a
n
d
tr
ials
.
Fo
u
r
d
atab
ases
wer
e
ac
ce
s
s
ed
:
ap
n
ea
p
o
s
itiv
e
p
r
ess
u
r
e
lo
n
g
-
ter
m
ef
f
icac
y
s
tu
d
y
,
ap
n
ea
,
b
ar
iatr
ic
s
u
r
g
er
y
,
a
nd
co
n
tin
u
o
u
s
p
o
s
itiv
e
air
way
p
r
ess
u
r
e
(
C
PAP
)
s
tu
d
y
,
Mr
OS
s
leep
s
tu
d
y
,
an
d
NC
H
s
leep
Data
B
an
k
.
Af
ter
r
ev
iewin
g
t
h
e
f
o
u
r
d
atab
ases
,
th
e
v
a
r
iab
l
es
r
elev
an
t
to
th
is
p
r
o
ject
we
r
e
s
elec
ted
an
d
ar
e
d
escr
ib
ed
in
T
a
b
le
3
.
T
h
e
f
in
al
v
er
s
io
n
o
f
th
e
tr
ain
i
n
g
d
ata
b
a
s
e
was m
ad
e
in
E
x
ce
l w
ith
th
e
f
o
r
m
at
'
.
c
s
v'
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fica
tio
n
a
lg
o
r
ith
m
w
ith
a
r
tifi
cia
l in
tellig
en
ce
fo
r
th
e
d
ia
g
n
o
s
tic
…
(
Je
h
il V
e
n
tu
r
a
-
Te
cc
o
)
4525
T
ab
le
3
.
T
r
ai
n
in
g
d
ata
s
et
N
a
me
D
a
t
a
t
y
p
e
D
e
scri
p
t
i
o
n
n
sr
r
i
d
i
n
t
6
4
P
a
t
i
e
n
t
r
e
g
i
st
r
a
t
i
o
n
ID
n
sr
r
_
a
g
e
i
n
t
6
4
A
g
e
n
sr
r
_
se
x
i
n
t
6
4
S
e
x
n
sr
r
_
b
mi
f
l
o
a
t
6
4
B
o
d
y
mas
s i
n
d
e
x
n
sr
r
_
a
h
i
_
h
p
3
u
f
l
o
a
t
6
4
A
p
n
e
a
-
h
y
p
o
p
n
e
a
i
n
d
e
x
n
sr
r
_
t
t
l
d
u
r
sp
_
f
1
i
n
t
6
4
S
l
e
e
p
i
n
g
h
o
u
r
s
e
ss_
t
o
t
a
l
i
n
t
6
4
Ep
w
o
r
t
h
i
n
d
e
x
sn
o
r
i
n
g
i
n
t
6
4
S
n
o
r
i
n
g
a
r
t
e
r
i
a
l
_
h
y
p
e
r
t
e
n
si
o
n
i
n
t
6
4
A
r
t
e
r
i
a
l
h
y
p
e
r
t
e
n
si
o
n
d
a
y
t
i
me
_
sl
e
e
p
i
n
e
ss
i
n
t
6
4
D
a
y
t
i
me
sl
e
e
p
i
n
e
ss
d
i
a
g
n
o
si
s
O
r
i
g
i
n
a
l
l
y
o
b
j
e
c
t
,
t
h
e
n
mo
d
i
f
i
e
d
t
o
i
n
t
6
4
D
i
a
g
n
o
si
s
o
f
O
S
A
3.
3
.
1
.
T
ra
ini
ng
Du
r
in
g
th
e
tr
ain
in
g
p
h
ase
o
f
th
e
m
o
d
el,
two
d
if
f
er
e
n
t
d
ata
s
ets
wer
e
in
co
r
p
o
r
ated
.
On
e
was
co
m
p
o
s
ed
u
s
in
g
d
ata
f
r
o
m
t
h
e
NSR
R
,
wh
ile
th
e
o
th
er
was
cr
ea
ted
with
in
f
o
r
m
atio
n
co
ll
ec
ted
f
r
o
m
a
s
leep
clin
ic
in
L
im
a,
Per
u
,
d
u
r
in
g
t
h
e
f
ir
s
t
q
u
ar
ter
o
f
2
0
2
3
,
in
v
o
l
v
in
g
3
9
p
atien
ts
.
Af
ter
co
m
p
letin
g
th
e
alg
o
r
ith
m
tr
ain
in
g
p
r
o
ce
s
s
,
th
e
m
o
d
el
g
en
er
ates
a
DT
.
I
n
th
is
tr
ee
,
th
e
m
ain
v
ar
iab
le
g
u
id
in
g
t
h
e
d
iv
is
io
n
s
is
th
e
E
p
wo
r
th
test
s
co
r
e.
I
f
th
is
s
co
r
e
is
less
th
an
9
.
5
,
th
e
tr
ee
b
r
a
n
ch
es
to
th
e
r
ig
h
t.
I
n
ca
s
e
th
e
r
esu
lt
is
eq
u
al
to
o
r
g
r
ea
ter
th
an
9
.
5
,
th
e
b
i
f
u
r
ca
t
io
n
o
cc
u
r
s
to
th
e
lef
t,
c
o
n
s
id
er
in
g
ag
e
as
th
e
m
ain
v
a
r
iab
le
in
th
is
ca
s
e,
a
s
illu
s
tr
ated
in
Fig
u
r
e
3
.
Su
b
s
eq
u
en
tly
,
test
d
ata
ar
e
lo
ad
ed
to
p
r
ed
ict
an
d
class
if
y
th
e
co
n
d
itio
n
o
f
p
atien
ts
,
wh
er
e
1
is
d
iag
n
o
s
ed
with
OSA
an
d
0
is
n
o
t
s
u
f
f
e
r
in
g
f
r
o
m
it.
I
n
a
d
d
itio
n
,
t
h
e
ac
cu
r
a
cy
o
f
th
e
m
o
d
el
is
ca
lcu
lated
,
an
d
th
e
c
o
n
f
u
s
io
n
m
atr
ix
is
p
r
in
ted
.
Acc
o
r
d
in
g
t
o
T
ab
le
4
,
we
ca
n
s
ee
th
at
in
p
r
ed
ictin
g
n
e
g
ativ
e
OSA
ca
s
es
th
e
alg
o
r
ith
m
h
as
an
ac
cu
r
a
cy
o
f
8
5
.
7
1
%
an
d
r
e
ca
ll
o
f
4
6
.
1
5
%,
in
p
r
e
d
ictin
g
p
o
s
itiv
e
OSA
ca
s
es,
th
e
alg
o
r
ith
m
h
as
an
ac
cu
r
ac
y
o
f
7
8
.
1
2
%
an
d
r
ec
all
o
f
9
6
.
1
5
%.
W
ith
th
ese
r
esu
lts
,
th
e
alg
o
r
ith
m
h
as
an
ac
cu
r
ac
y
o
f
7
9
.
4
9
%.
I
n
Fig
u
r
e
4
,
we
ca
n
ap
p
r
ec
iate
th
e
cr
o
s
s
in
g
o
f
th
e
d
ata
to
b
e
p
r
e
d
i
cted
v
er
s
u
s
w
h
at
is
b
ein
g
p
r
e
d
icted
,
in
th
e
g
r
ap
h
t
h
e
v
alu
e
0
is
eq
u
iv
alen
t
to
n
o
t
h
av
in
g
OSA
an
d
1
is
eq
u
iv
al
en
t
to
h
av
in
g
it.
I
n
r
o
w
0
,
a
to
tal
o
f
1
3
ca
s
es
wit
h
o
u
t
OSA
s
h
o
u
ld
h
av
e
b
ee
n
p
r
ed
icted
,
6
p
r
e
d
ictio
n
s
wer
e
co
r
r
ec
t
an
d
7
wer
e
wr
o
n
g
s
in
ce
th
ey
wer
e
p
r
ed
ict
ed
with
a
n
eg
ativ
e
d
iag
n
o
s
is
o
f
OSA,
b
u
t th
ey
wer
e
p
o
s
itiv
e
ca
s
es.
Fro
m
r
o
w
1
,
2
6
ca
s
es with
OSA
s
h
o
u
ld
h
av
e
b
ee
n
p
r
ed
icted
,
2
5
ca
s
es we
r
e
p
r
ed
icted
c
o
r
r
ec
tly
,
an
d
o
n
e
ca
s
e
was w
r
o
n
g
.
Fig
u
r
e
3
.
D
ec
is
io
n
tr
ee
g
r
ap
h
T
ab
le
4
.
T
r
ai
n
in
g
r
esu
lts
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
S
u
p
p
o
r
t
0
0
.
8
5
7
1
0
.
4
6
1
5
0
.
6
0
0
0
13
1
0
.
7
8
1
2
0
.
9
6
1
5
0
.
8
6
2
1
26
a
c
c
u
r
a
c
y
0
.
7
9
4
9
39
mac
r
o
a
v
g
0
.
8
1
9
2
0
.
7
1
1
5
0
.
7
3
1
0
39
w
e
i
g
h
t
e
d
a
v
g
0
.
8
0
6
5
0
.
7
9
4
9
0
.
7
7
4
7
39
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
2
0
-
4
5
3
2
4526
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
Resul
t
s
T
h
is
s
tu
d
y
aim
ed
to
d
eter
m
in
e
h
o
w
an
AI
class
if
icatio
n
alg
o
r
ith
m
in
f
lu
en
ce
s
th
e
d
iag
n
o
s
tic
p
r
o
ce
s
s
o
f
OSA
.
Acc
o
r
d
in
g
to
t
h
e
th
e
o
r
y
,
th
r
ee
k
ey
p
er
f
o
r
m
an
ce
in
d
icato
r
s
(
KPI
s
)
wer
e
d
eter
m
in
ed
th
at
ar
e
p
r
esen
t
in
th
e
d
iag
n
o
s
tic
p
r
o
ce
s
s
.
Pre
-
an
d
p
o
s
t
-
r
esu
lts
ar
e
d
etailed
in
in
d
icato
r
1
(
KPI
1
)
to
k
n
o
w
th
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
o
f
th
e
clin
ical
ev
alu
a
tio
n
,
in
d
icato
r
2
(
KPI
2
)
to
m
e
asu
r
e
th
e
d
iag
n
o
s
tic
tim
e,
an
d
in
d
icato
r
3
(
KPI
3
)
to
d
eter
m
in
e
th
e
n
u
m
b
er
o
f
test
s
with
p
o
r
tab
le
m
o
n
ito
r
s
.
4
.
1
.
1.
I
nd
ica
t
o
r
1
(
K
P
I
1
)
I
n
th
is
s
ec
tio
n
,
we
p
er
f
o
r
m
ed
a
d
escr
ip
tiv
e
an
aly
s
is
o
f
th
e
i
n
d
icato
r
"d
iag
n
o
s
tic
ac
cu
r
ac
y
o
f
clin
ical
ev
alu
atio
n
".
T
h
e
c
o
n
tr
ast
was
m
ad
e
with
th
e
co
n
f
ir
m
atio
n
o
f
ca
s
es
o
f
s
u
cc
ess
f
u
l
d
iag
n
o
s
is
o
f
OSA
wi
th
th
e
u
s
e
o
f
clin
ical
ass
ess
m
en
t,
as
s
h
o
wn
in
T
ab
le
5
.
I
n
t
h
e
p
r
etest,
a
m
ea
n
o
f
0
.
7
4
was
o
b
tain
ed
an
d
f
o
r
th
e
p
o
s
ttes
t,
it
was
0
.
8
2
.
I
n
a
d
d
itio
n
,
in
Fig
u
r
e
5
,
we
ca
n
s
ee
th
at
in
th
e
p
r
etest
th
er
e
is
a
p
e
r
c
en
tag
e
f
r
e
q
u
en
c
y
o
f
7
4
.
4
%
o
f
s
u
cc
ess
f
u
l
d
iag
n
o
s
es
with
o
u
t
th
e
u
s
e
o
f
PS
G,
an
d
in
th
e
p
o
s
ttes
t
8
2
.
1
%
o
f
s
u
cc
ess
f
u
l
d
iag
n
o
s
es
with
th
e
u
s
e
o
f
th
e
alg
o
r
ith
m
.
At
th
e
s
am
e
tim
e,
d
iag
n
o
s
tic
er
r
o
r
s
d
ec
r
ea
s
ed
f
r
o
m
2
5
.
6
%
in
th
e
p
r
etest
to
1
7
.
9
%
in
th
e
p
o
s
ttes
t.
T
h
ese
r
esu
lts
s
h
o
w
an
in
cr
ea
s
e
o
f
1
0
.
8
1
%
in
th
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
o
f
th
e
clin
ical
ev
alu
atio
n
.
R
eg
ar
d
in
g
th
e
h
y
p
o
th
esis
test
,
Mc
Nem
ar
's
test
wa
s
ap
p
lied
f
o
r
q
u
alitativ
e
v
ar
iab
les.
A
s
ig
n
if
ican
ce
lev
el
o
f
0
.
5
0
8
was
o
b
tain
ed
,
wh
ich
is
g
r
ea
ter
th
an
t
h
e
s
ig
n
if
ican
c
e
lev
el
o
f
0
.
0
5
,
th
er
ef
o
r
e,
th
e
n
u
ll
h
y
p
o
t
h
esis
(
H0
)
is
ac
ce
p
ted
,
an
d
t
h
e
alter
n
ati
v
e
h
y
p
o
t
h
esis
(
H1
)
is
r
ejec
ted
.
T
h
er
ef
o
r
e,
a
class
if
icatio
n
alg
o
r
ith
m
with
AI
d
o
es
n
o
t
s
ig
n
if
ican
tly
in
f
l
u
en
ce
th
e
clin
i
ca
l
ev
alu
atio
n
o
f
p
atien
ts
with
s
u
s
p
ec
ted
OSA
in
L
im
a
-
Per
u
,
as sh
o
wn
in
T
ab
le
6
.
Fig
u
r
e
5
.
B
ar
ch
a
r
t o
f
p
r
e
a
n
d
p
o
s
t
o
f
KPI
1
: d
ia
g
n
o
s
is
ac
cu
r
a
cy
o
f
clin
ical
ev
alu
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fica
tio
n
a
lg
o
r
ith
m
w
ith
a
r
tifi
cia
l in
tellig
en
ce
fo
r
th
e
d
ia
g
n
o
s
tic
…
(
Je
h
il V
e
n
tu
r
a
-
Te
cc
o
)
4527
T
ab
le
5
.
I
n
d
icato
r
1
f
r
e
q
u
en
c
y
d
ata
P
r
e
_
C
o
n
f
i
r
ma
t
i
o
n
P
o
st
_
C
o
n
f
i
r
ma
t
i
o
n
N
V
a
l
i
d
39
39
Lo
st
0
0
M
e
d
i
a
0
.
7
4
0
.
8
2
M
e
d
i
a
n
1
1
F
a
sh
i
o
n
1
1
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
0
.
4
4
2
0
.
3
8
9
V
a
r
i
a
n
c
e
0
.
1
9
6
0
.
1
5
1
M
i
n
i
m
u
m
0
0
M
a
x
i
m
u
m
1
1
S
u
m
29
32
P
e
r
c
e
n
t
i
l
e
s
25
0
1
50
1
1
75
1
1
T
ab
le
6
.
Sp
ec
if
ic
h
y
p
o
th
esis
test
1
P
r
e
_
C
o
n
f
i
r
ma
t
i
o
n
a
n
d
P
o
st
_
C
o
n
f
i
r
ma
t
i
o
n
N
39
Ex
a
c
t
si
g
n
i
f
i
c
a
n
c
e
(
b
i
l
a
t
e
r
a
l
)
.
5
0
8
b
a.
M
c
N
e
mar
t
e
s
t
b
.
B
i
n
o
mi
a
l
d
i
st
r
i
b
u
t
i
o
n
u
s
e
d
4
.
1.
2
.
I
nd
ica
t
o
r
2
(
K
P
I
2
)
Acc
o
r
d
in
g
to
th
e
r
esu
lts
in
Fig
u
r
e
6
,
th
e
s
ig
n
if
ican
ce
le
v
el
in
th
e
p
r
etest
was
0
.
0
5
0
an
d
,
i
n
th
e
p
o
s
ttes
t,
it wa
s
0
.
0
2
1
,
in
th
is
ca
s
e,
o
n
e
o
f
th
e
v
alu
es d
id
n
o
t
ex
ce
ed
0
.
0
5
,
s
o
we
ca
n
af
f
ir
m
th
at
th
e
d
ata
d
o
n
o
t
f
o
llo
w
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
.
T
h
er
e
f
o
r
e,
th
e
W
ilco
x
o
n
te
s
t
is
u
s
ed
f
o
r
h
y
p
o
th
esis
test
in
g
.
As
s
h
o
w
n
in
T
ab
le
7
,
af
ter
ap
p
ly
in
g
f
o
r
th
e
W
ilco
x
o
n
test
,
a
s
ig
n
if
ican
ce
lev
el
o
f
0
.
0
0
1
was
o
b
tain
ed
,
s
o
th
e
alter
n
ativ
e
h
y
p
o
th
esis
(
H1
)
is
ac
ce
p
ted
,
an
d
th
e
n
u
ll
h
y
p
o
th
esis
(
H0
)
is
r
ejec
ted
.
T
h
er
ef
o
r
e,
a
class
if
icatio
n
alg
o
r
ith
m
with
AI
s
ig
n
if
ican
tly
in
f
lu
en
c
es
th
e
u
s
e
o
f
PS
G
in
p
atien
ts
with
s
u
s
p
ec
ted
OSA
in
L
im
a
-
Per
u
.
I
n
a
d
d
itio
n
,
Fig
u
r
e
7
d
etails
th
e
p
r
e
an
d
p
o
s
t
KP
I
2
:
d
iag
n
o
s
tic
tim
e.
Ac
co
r
d
in
g
to
th
e
r
esu
lts
,
in
th
e
p
r
etest,
a
m
ea
n
o
f
1
2
.
8
5
was o
b
tain
e
d
an
d
f
o
r
th
e
p
o
s
t
-
test
,
it wa
s
9
.
2
3
.
W
ith
th
ese
r
esu
lts
,
a
2
8
.
1
7
% d
ec
r
ea
s
e
in
d
iag
n
o
s
tic
tim
e
is
o
b
s
er
v
ed
.
Fig
u
r
e
6
.
No
r
m
ality
p
lo
t
o
f
in
d
icato
r
2
T
ab
le
7
.
Sp
ec
if
ic
h
y
p
o
th
esis
co
n
tr
ast 2
P
o
st
_
T
i
me
a
n
d
P
r
e
_
Ti
m
e
Z
-
4
.
4
0
4
b
S
i
g
.
a
s
i
n
.
(
b
i
l
a
t
e
r
a
l
)
<
.
0
0
1
a
.
W
i
l
c
o
x
o
n
si
g
n
e
d
-
r
a
n
k
t
e
s
t
b
.
I
t
i
s
b
a
se
d
o
n
p
o
s
i
t
i
v
e
r
a
n
g
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
2
0
-
4
5
3
2
4528
Fig
u
r
e
7
.
B
ar
ch
a
r
t o
f
p
r
e
a
n
d
p
o
s
t
o
f
KPI
2
: th
e
d
iag
n
o
s
tic
tim
e
4
.
1.
3
.
I
nd
ica
t
o
r
3
(
K
P
I
3
)
Fo
r
in
d
icato
r
3
,
wh
ich
m
ea
s
u
r
es
th
e
n
u
m
b
er
o
f
test
s
wi
t
h
p
o
r
tab
le
m
o
n
ito
r
s
f
o
r
th
e
d
iag
n
o
s
is
o
f
OSA
in
p
atien
ts
,
th
e
n
o
r
m
ality
test
was
p
er
f
o
r
m
ed
as
s
h
o
wn
in
Fig
u
r
e
8
.
Acc
o
r
d
in
g
t
o
th
e
r
esu
lts
,
in
th
e
p
r
etest,
a
lev
el
o
f
0
.
0
5
8
was
o
b
tain
ed
an
d
in
th
e
p
o
s
ttes
t,
it
was
0
.
1
0
5
,
s
in
ce
b
o
th
v
alu
es
d
id
n
o
t
e
x
ce
ed
0
.
0
5
,
we
ca
n
af
f
ir
m
th
at
th
e
d
ata
d
o
n
o
t
f
o
llo
w
a
n
o
r
m
al
d
is
tr
i
b
u
tio
n
.
T
h
er
ef
o
r
e,
t
h
e
W
ilco
x
o
n
test
is
u
s
ed
f
o
r
h
y
p
o
th
esis
test
in
g
.
Acc
o
r
d
in
g
to
T
ab
le
8
,
u
s
in
g
th
e
W
ilco
x
o
n
test
,
a
s
ig
n
if
ican
ce
lev
el
o
f
0
.
0
0
1
was
o
b
tain
e
d
,
th
er
ef
o
r
e,
th
e
alter
n
ativ
e
h
y
p
o
th
esis
(
H1
)
is
ac
ce
p
ted
,
an
d
th
e
n
u
ll
h
y
p
o
th
esis
(
H0
)
is
r
e
jecte
d
.
T
h
er
e
f
o
r
e,
a
class
if
icatio
n
alg
o
r
ith
m
with
AI
s
ig
n
if
ican
tly
in
f
lu
e
n
ce
s
th
e
u
s
e
o
f
p
o
r
ta
b
le
m
o
n
ito
r
s
in
p
atien
ts
with
s
u
s
p
ec
ted
OSA
in
L
im
a
-
Per
u
.
Fo
r
KPI
3
,
wh
ich
m
ea
s
u
r
es
th
e
n
u
m
b
er
o
f
test
s
r
eq
u
ested
f
o
r
th
e
d
iag
n
o
s
is
o
f
OSA,
a
m
ea
n
p
r
etest
o
f
8
.
6
4
was
ac
h
iev
ed
an
d
f
o
r
th
e
p
o
s
t
-
test
,
it
wa
s
6
.
5
6
.
T
h
ese
r
esu
lts
s
h
o
w
a
d
ec
r
ea
s
e
o
f
2
4
.
0
7
% in
th
e
n
u
m
b
er
o
f
test
s
r
eq
u
ested
with
p
o
r
tab
le
m
o
n
ito
r
s
,
as sh
o
wn
in
Fig
u
r
e
9
.
Fig
u
r
e
8
.
No
r
m
ality
p
lo
t
o
f
in
d
icato
r
3
T
ab
le
8
.
Sp
ec
if
ic
h
y
p
o
th
esis
test
3
P
o
st
_
Q
u
a
n
t
i
t
y
a
n
d
P
r
e
_
Q
u
a
n
t
i
t
y
Z
-
5
.
8
8
9
b
S
i
g
.
a
s
i
n
.
(
b
i
l
a
t
e
r
a
l
)
<
.
0
0
1
a
.
W
i
l
c
o
x
o
n
si
g
n
e
d
-
r
a
n
k
t
e
s
t
b
.
I
t
i
s
b
a
se
d
o
n
p
o
s
i
t
i
v
e
r
a
n
g
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
la
s
s
i
fica
tio
n
a
lg
o
r
ith
m
w
ith
a
r
tifi
cia
l in
tellig
en
ce
fo
r
th
e
d
ia
g
n
o
s
tic
…
(
Je
h
il V
e
n
tu
r
a
-
Te
cc
o
)
4529
Fig
u
r
e
9
.
B
ar
ch
a
r
t o
f
p
r
e
a
n
d
p
o
s
t
o
f
KPI
3
:
n
u
m
b
e
r
o
f
test
s
with
p
o
r
tab
le
m
o
n
ito
r
s
4
.
2
.
Dis
cus
s
io
n
T
h
e
r
esu
lts
o
b
tain
ed
in
th
is
s
tu
d
y
r
ev
ea
l
a
m
o
d
er
ate
im
p
r
o
v
em
en
t
o
f
1
0
.
8
1
%
in
clin
ical
d
iag
n
o
s
tic
ac
cu
r
ac
y
,
wh
ich
co
n
tr
asts
wi
th
p
r
ev
io
u
s
s
tu
d
ies,
s
u
ch
as
th
at
o
f
[
3
4
]
,
wh
e
r
e
an
in
cr
e
ase
in
ac
cu
r
ac
y
o
f
1
7
.
5
6
%
was
r
ep
o
r
ted
wh
en
u
s
in
g
ML
m
o
d
els
i
n
a
d
atas
et
co
m
p
o
s
ed
o
f
8
3
p
atien
ts
with
a
m
ea
n
a
g
e
o
f
4
7
y
ea
r
s
.
T
h
is
d
is
cr
ep
an
c
y
co
u
ld
b
e
d
u
e
to
s
ev
e
r
al
f
ac
to
r
s
,
i
n
clu
d
in
g
d
if
f
er
e
n
ce
s
in
th
e
d
atasets
u
s
ed
,
s
u
ch
as
s
am
p
le
s
ize,
p
atien
t
d
iv
er
s
ity
,
an
d
ca
s
e
s
ev
er
ity
.
I
t
is
p
o
s
s
ib
le
th
at
clin
ical
d
ata
f
r
o
m
p
atien
ts
with
m
o
r
e
h
eter
o
g
en
e
o
u
s
ch
a
r
ac
ter
is
tics
o
r
with
a
d
if
f
er
en
t
d
is
tr
ib
u
t
io
n
o
f
d
is
ea
s
e
s
ev
er
ity
wer
e
u
s
ed
in
o
u
r
s
tu
d
y
,
wh
ich
co
u
l
d
ex
p
lain
a
less
p
r
o
n
o
u
n
ce
d
im
p
r
o
v
e
m
en
t.
Als
o
,
th
e
m
eth
o
d
a
p
p
lied
f
o
r
alg
o
r
ith
m
d
ev
el
o
p
m
en
t
in
th
is
s
tu
d
y
m
ay
h
av
e
in
f
l
u
en
ce
d
th
e
r
esu
lts
.
W
h
ile
s
tu
d
ies
s
u
ch
as
[
3
2
]
o
b
s
er
v
ed
r
e
d
u
ctio
n
s
in
d
iag
n
o
s
tic
tim
e
b
etwe
en
3
8
.
1
6
%
an
d
5
1
.
8
1
%
,
h
er
e
a
r
ed
u
ctio
n
o
f
2
8
.
1
7
%
was
ac
h
iev
ed
.
I
t
is
im
p
o
r
ta
n
t
to
n
o
te
th
at
th
e
alg
o
r
ith
m
s
u
s
ed
i
n
[
3
2
]
wer
e
b
ased
o
n
d
if
f
er
e
n
t
ML
a
p
p
r
o
a
ch
es,
s
o
m
e
o
f
wh
ich
m
a
y
h
a
v
e
b
ee
n
m
o
r
e
r
o
b
u
s
t
o
r
in
teg
r
ate
d
m
o
r
e
h
is
to
r
ical
d
ata,
p
o
s
s
ib
ly
f
ac
ilit
atin
g
a
g
r
ea
ter
r
ed
u
ctio
n
in
d
iag
n
o
s
tic
tim
e.
I
n
c
o
n
tr
ast,
in
o
u
r
s
tu
d
y
,
th
e
alg
o
r
ith
m
ic
a
p
p
r
o
ac
h
was
m
o
r
e
co
n
s
er
v
ativ
e
an
d
f
o
cu
s
ed
o
n
im
p
r
o
v
in
g
d
iag
n
o
s
tic
ac
cu
r
ac
y
with
o
u
t
s
ig
n
if
ican
tly
in
cr
ea
s
i
n
g
c
o
m
p
u
tatio
n
al
c
o
m
p
lex
ity
.
I
n
ad
d
itio
n
,
wh
en
an
aly
zin
g
th
e
u
s
e
o
f
p
o
r
ta
b
le
m
o
n
ito
r
s
,
t
h
is
s
tu
d
y
r
ep
o
r
ted
a
2
4
.
0
7
%
r
e
d
u
ctio
n
in
th
e
n
u
m
b
er
o
f
test
s
r
eq
u
ir
ed
,
wh
ich
p
a
r
tly
co
in
ci
d
es
with
th
e
f
in
d
in
g
s
o
f
[
3
3
]
,
wh
e
r
e
9
5
%
ef
f
ec
tiv
en
ess
was
o
b
s
er
v
ed
in
th
e
u
s
e
o
f
th
ese
d
ev
i
ce
s
co
m
p
ar
ed
with
tr
ad
itio
n
al
PS
G.
Ho
wev
er
,
a
p
o
s
s
ib
le
ex
p
lan
atio
n
f
o
r
th
e
d
if
f
er
en
ce
s
lies
in
th
e
f
ac
t
th
at
s
t
u
d
ies
s
u
ch
as
[
3
3
]
u
s
ed
m
o
r
e
ad
v
a
n
ce
d
m
o
n
ito
r
in
g
eq
u
ip
m
e
n
t
o
r
ap
p
lied
m
o
r
e
r
ig
o
r
o
u
s
ev
alu
atio
n
cr
iter
ia.
T
h
er
ef
o
r
e
,
it
is
s
u
g
g
ested
th
at
th
e
r
esu
lts
o
f
t
h
is
s
tu
d
y
co
u
ld
b
e
im
p
r
o
v
ed
b
y
in
teg
r
atin
g
m
o
r
e
ac
cu
r
ate
d
ev
ices
an
d
ap
p
ly
in
g
h
y
b
r
id
ap
p
r
o
ac
h
es
th
at
c
o
m
b
in
e
b
o
th
al
g
o
r
ith
m
ic
a
n
aly
s
is
an
d
clin
ical
ex
p
er
ien
ce
.
Fin
ally
,
alth
o
u
g
h
n
o
s
tu
d
ies
wer
e
id
en
tifie
d
th
at
ex
p
licitly
ad
d
r
ess
ed
th
e
r
elatio
n
s
h
ip
b
etwe
en
r
e
d
u
ce
d
d
iag
n
o
s
tic
tim
e
an
d
th
e
u
s
e
o
f
p
o
r
tab
le
m
o
n
ito
r
s
,
r
esear
c
h
s
u
ch
as
th
at
o
f
[
3
2
]
s
u
g
g
ests
th
at
th
e
in
teg
r
atio
n
o
f
m
o
r
e
s
o
p
h
is
ticated
d
ata
co
llectio
n
m
eth
o
d
s
an
d
m
o
r
e
ad
v
an
ce
d
m
o
d
els
co
u
l
d
g
e
n
er
ate
an
e
v
en
g
r
ea
ter
r
ed
u
cti
o
n
in
th
e
tim
e
a
n
d
n
u
m
b
er
o
f
test
s
r
eq
u
ir
ed
.
T
h
is
r
ein
f
o
r
ce
s
th
e
im
p
o
r
tan
ce
o
f
ex
p
l
o
r
in
g
m
o
r
e
a
d
v
an
ce
d
ML
m
eth
o
d
s
an
d
co
n
s
id
er
in
g
m
o
r
e
d
iv
er
s
e
d
ata
b
ases
to
ac
h
iev
e
b
etter
r
esu
lts
in
f
u
tu
r
e
s
tu
d
ies.
5.
CO
NCLU
SI
O
N
T
h
e
p
r
esen
t
s
tu
d
y
h
as
d
e
m
o
n
s
tr
ated
th
at
th
e
im
p
lem
e
n
tatio
n
o
f
a
class
if
icatio
n
alg
o
r
ith
m
with
AI
ca
n
in
f
lu
en
ce
th
e
d
iag
n
o
s
tic
p
r
o
ce
s
s
o
f
OSA
in
L
im
a,
Per
u
.
Up
o
n
r
e
v
iew
o
f
th
e
r
esu
lts
,
it
was
o
b
s
er
v
ed
th
at
th
e
alg
o
r
ith
m
h
a
d
a
lim
ited
im
p
ac
t
o
n
th
e
ac
cu
r
ac
y
o
f
cli
n
ical
d
iag
n
o
s
is
,
with
an
im
p
r
o
v
em
en
t
o
f
1
0
.
8
1
%.
Ho
wev
er
,
a
s
ig
n
if
ican
t
r
e
d
u
cti
o
n
in
th
e
tim
e
r
eq
u
ir
e
d
f
o
r
d
ia
g
n
o
s
is
was
ac
h
iev
ed
,
with
a
d
ec
r
ea
s
e
o
f
2
8
.
1
7
%.
T
h
is
f
ac
t
in
d
icate
s
a
p
o
s
itiv
e
im
p
ac
t
o
f
th
e
alg
o
r
ith
m
i
n
th
is
asp
ec
t.
L
ik
ewise,
an
im
p
r
o
v
e
m
en
t
in
th
e
ef
f
icien
cy
o
f
r
eq
u
esti
n
g
test
s
with
p
o
r
tab
le
m
o
n
ito
r
s
was
o
b
s
er
v
ed
,
with
a
d
ec
r
ea
s
e
o
f
2
4
.
0
7
%
in
th
e
n
u
m
b
e
r
o
f
r
e
q
u
ests
m
ad
e.
Ho
wev
e
r
,
th
e
an
aly
s
is
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
r
ev
ea
led
d
i
f
f
icu
lties
o
f
th
e
alg
o
r
ith
m
in
r
u
lin
g
o
u
t
f
alse
p
o
s
itiv
es
in
th
e
d
iag
n
o
s
is
o
f
OSA,
wh
ic
h
,
c
o
u
p
led
with
th
e
lim
itatio
n
s
o
f
th
e
tr
ain
in
g
d
ataset,
co
n
s
tr
u
cted
f
r
o
m
m
u
ltip
le
d
atab
ases
,
in
d
icate
s
th
e
n
ee
d
to
ex
p
lo
r
e
o
th
e
r
ML
tech
n
iq
u
es
an
d
im
p
r
o
v
e
d
ata
q
u
ality
to
o
p
tim
ize
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
o
d
ev
elo
p
f
u
tu
r
e
s
tu
d
ies,
it
wo
u
ld
b
e
ess
en
tial
to
co
n
d
u
ct
ad
d
itio
n
al
r
esear
ch
th
at
f
o
cu
s
es
o
n
e
x
p
a
n
d
in
g
a
n
d
d
iv
er
s
if
y
in
g
th
e
d
a
tasets
u
s
ed
to
tr
ain
th
e
alg
o
r
i
th
m
,
en
s
u
r
in
g
th
at
th
ey
ar
e
r
ep
r
esen
tativ
e
o
f
th
e
p
o
p
u
latio
n
an
d
clin
ical
c
o
n
d
itio
n
s
s
p
ec
if
ic
to
th
e
r
eg
i
o
n
.
I
n
a
d
d
itio
n
,
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.