Evaluation of a Dental Caries Clinical Decision Support System

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 patternbased 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.