Rule-based system for effective clinical decision support

Abstract

Clinical Decision Support Systems (CDSS) are being increasingly requested and are an important role in health units. Due to the high number of data produced daily, it is necessary that these data are stored and manipulated in order to acquire knowledge to assist the decision-making processes. Representing knowledge in knowledge-based systems is one of the main tasks for achieving an effective CDSS. In this way, this narrative literature review article intends to identify different approaches to represent knowledge for rule-based CDSS. Four models are described, namely decision tables, decision trees, bayesian network and nearest neighbors, emphasizing the first two.