Bayesian Networks as Clinical Decision Support

hartebeestgrassAI and Robotics

Nov 7, 2013 (3 years and 7 months ago)

103 views

Bayesian Networks as Clinical Decision Support
Systems in Medical Settings:

A Review




Health

managers

and

clinicians

are

frequently

asked

to

provide

quantifiable

information

to

support

their

decision,

which

is

not

always

easy

to

obtain
.




Therefore,

some

artificial

intelligence

systems

are

idealized

to

support

healthcare

professionals

with

responsibility

based

on

the

manipulation

of

information

and

knowledge
.







Clinical

Decision

Support

Systems

(CDSS)

are

considered

to

combine

medical

knowledge

base,

patient

data

and

an

inference

engine

to

generate

case

specific

advice
.
[
2
]

(
Classen,

1998
)




These

Bayesian

networks

can

be

used

to

represent

the

probabilistic

relationships

and

interdependencies

among

a

set

of

variables,

namely

diseases

and

symptoms
.


Medical
Knowledge

Artificial Intelligence
System (such as
Bayesian Networks
)

Patient
Data

Advice


In which healthcare domains and
clinical fields are Bayesian networks
being used as clinical decision support
systems in Medicine?




Identify

the

healthcare

domains

and

point

out

which

fields

(diagnosis,

therapy

and

prognosis)

are

usually

targeted

by

BN

as

CDSS

in

real
-
world

clinical

practice
.




Discuss

the

efficacy,

effectiveness

and

efficiency

of

BN

in

CDSS

expressed

in

the

included

studies
.



Review
:


The

articles/papers

used

in

systematic

review

are

searched

in

Medline
,

ISI

Web

of

Knowledge

and

Scopus
.

This

literature

search

is

conducted

by

a

conjunction

of

keywords

(and

their

synonyms)

with

other

words

related

with

variables
.


keywords
:

-

Decision Support Systems, Clinical

-

Bayes Theorem


All

the

articles

are

collected

using

EndNote

and

are

reviewed

by

two

peers
.

Initially,

these

two

reviewers

analyze

the

title

and

the

abstract,

registering

briefly

the

causes

of

non
-
selection
.

Then,

the

chosen

articles

are

read

integrally

and

are

applied

the

inclusion

and

exclusion

criteria
,

previously

elaborated
.

The

divergent

opinions

are

solved

by

a

third

reviewer

and

the

exclusion

causes

are

registered
.

It

is

necessary

to

evaluate

this

process’

reproducibility

and

to

register

the

exclusion

motives
.


Finally,

a

specific

formulary

is

created

for

data

extraction

and

processed

using

SPSS
.


If

possible,

a

meta
-
analysis

will

be

applied
.

The

final

results

are

interpreted,

discussed

and

the

final

article

is

elaborated
.









Types

of

Study

(e
.
g
.

Experimental

vs

observational)

and

Data

types

(primary

data

vs

secondary

data)



Articles’

information

(First

author’s

country

affiliation,

publication

date,

institution)



Healthcare

domains

(emergency,

critical

care,

stroke

service

)



Clinical

fields

(diagnosis,

therapy,

prognosis)



Efficacy,

Effectiveness

and

Efficiency

of

Bayesian’s

techniques


Inclusion Criteria:




Applied to diagnosis or prognosis or therapeutic
related to Bayes theorem



Include results



Paper

provides

details

so

that

the

study

can

be

reproduced



Written in English



Exclusion Criteria:




Meta
-
analysis and reviews



Not applied to humans






Most

of

the

articles

found

refer

to

Diagnostic

tests

of

CDSS

based

on

BN
.




CDSS

based

on

BN

are

more

frequently

used

in

diagnosis
.




CDSS

based

on

BN

have

been

applied

in

Rapid

Assessment

Unit

and

in

Emergency
.




CDSS

based

on

BN

are

efficacious

and

effective

but

not

efficient
.



Start

1.
Tan J,
Sheps

S (1998). Health Decision Support Systems. Jones & Bartlett Publishers.

2.
Classen DC. Clinical decision support systems to improve clinical practice and quality of care. JAMA.
1998 Oct
21;280(15):1360
-
1.

3.
Coiera

E (2003). The Guide to Health Informatics (2nd Edition). Arnold, London.

4.
Sim

I, Sanders GD, McDonald KM. Evidence
-
based practice for mere mortals: the role of informatics and
health services research. J Gen Intern Med. 2002 Apr;17(4):302
-
8.

5.
Fieschi

M,
Dufour

JC,
Staccini

P,
Gouvernet

J,
Bouhaddou

O. Medical decision support systems: old
dilemmas and new paradigms? Methods
Inf

Med. 2003;42(3):190
-
8.

Erratum

in
:
Methods

Inf

Med
.
2003;42(4):VI.

6.
Miller RA. Medical diagnostic decision support systems
--
past, present, and future: a threaded
bibliography and brief commentary. J Am Med Inform Assoc. 1994 Jan
-
Feb;1(1):8
-
27. Erratum in: J Am
Med Inform Assoc. 1994 Mar
-
Apr;1(2):160.

7.
Wong HJ,
Legnini

MW, Whitmore HH. The diffusion of decision support systems in healthcare: are we
there yet? J
Healthc

Manag
. 2000 Jul
-
Aug;45(4):240
-
9; discussion 249
-
53.