Abstract

 Clinical decision support system (CDSS) is promising in assisting physicians for improving decision-making process and facilitates healthcare services. In medicine, causality has become the main concern
 throughout healthcare and decision-making. Causality is necessary for understanding all structures ofscientific reasoning and for providing a coherent and sufficient explanation for any event. However, thereare lack of existing CDSS that provide causal reasoning for the presented outcomes or decisions. Theseare necessary for showing reliability of the outcomes, and helping the physicians in making properdecisions. In this study, an ontology-based CDSS model is developed based on several key concepts andfeatures of causality and graphical modeling techniques. For the evaluation process, the Pellet reasoneris used to evaluate the consistency of the developed ontology model. In addition, an evaluation toolknown as Ontology Pitfall Scanner is used for validating the ontology model through pitfalls detection.The developed ontology-based CDSS model has potentials to be applied in clinical practice and helpingthe physicians in decision-making process.
 Keywords: clinical decision support system, ontology, causality, causal reasoning, graphical modeling
Highlights
Clinical decision support system (CDSS) is defined as a health information system designed to assist the physicians in decision-making process
Ontology verification refers to the task of evaluating if the ontology was built in the right way, while ontology validation refers to the task of evaluating if the right ontology was built (Vrandečić, 2010)
As regards verification, Pellet reasoner is used to evaluate the consistency of the developed ontology model
Summary
Clinical decision support system (CDSS) is defined as a health information system designed to assist the physicians in decision-making process. Semantics should be considered to develop a CDSS, since in healthcare each description should have a unique and understandable meaning (Lam et al, 2015; Sanchez, 2014) It can improve medical knowledge handling and reutilization as it facilitates faster knowledge access and gathering of relevant knowledge and evidence in supporting decision-making process (Lam et al, 2015; Sanchez, 2014). It enables the system to be adaptive to clinical practice as it supports the knowledge repository to be updated and modified for incorporating new clinical cases or evidences into the system (Lam et al, 2015; Sanchez, 2014)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
