Authors:
Michel Bessani
1
;
Daniel Rodrigues de Lima
1
;
Emery Cleiton Cabral Correia Lins
2
and
Carlos Dias Maciel
3
Affiliations:
1
University of São Paulo, Brazil
;
2
Federal University of Pernambuco, Brazil
;
3
University of Sao Paulo, Brazil
Keyword(s):
Clinical Decision Support System, Dental Caries Management, Bayesian Networks, Decision Support System Evaluation.
Abstract:
Decision Support Systems (DSSs) aims to support professionals decision process. A specific area of application
is the Clinical one, resulting in Clinical Decision Support Systems (CDSSs), focusing on Clinical
Decision problems, like oncology, geriatrics, and dentistry. DSSs integrate expert knowledge through pattern-based
approaches. Bayesian Networks are probabilistic graph models that allow representation and inference
on complex scenarios. BNs are used in different decision-making fields, e.g., Clinical Decision Support Systems.
Traditionally, such models are learned using established databases. However, in situations where such
data set is unavailable, the BN can be manually constructed converting expert knowledge in conditional probabilities.
In this paper, we evaluate a Dental Caries Clinical Decision Support System which uses a BN to
provide suggestions and represent clinical patterns. The evaluation methodology uses forward sampling to
generated data from the BN. The
generated data are separated into three groups, and each one is analyzed.
The results show the certainty of the Bayesian Network for some scenarios. The analysis of the CDSS BN
indicates that the system efficiently infers according to the pattern presented in the literature.
(More)