Digital Health Transformation: Leveraging Knowledge Graphs Reasoning Framework and Conversational Agents for Enhanced Knowledge Management

The research focuses on utilizing AI systems, particularly conversational agents (CAs), to optimize information flow procedures within healthcare emergency departments (EDs), especially during peak hours. The authors adopted the Cross Industry Standard Process for Data Mining (CRISP-DM) approach to guide our research into a tailored CRISP-Knowledge Graph (CRISP-KG) methodology. Our approach involves harnessing the power of knowledge graphs (KGs) to construct an intelligent knowledge base (KBs) for conversational agents. This augmentation enhances their reasoning, knowledge management, and context awareness abilities. The development of these robust KBs is facilitated through a collaborative methodology (CM) and the implementation of ontology design patterns to create a formal ontological model. The ultimate objective is to empower conversational agents with intelligent KBs, enabling seamless interaction with end-users and enhancing the quality of care within EDs. Authors leveraged semantic web rule language (SWRL) for inference, utilizing the knowledge graph approach to assist healthcare practitioners and patients in efficiently managing information flow and information provision within EDs. The anticipated outcome is an improvement in care quality and better care outcomes.