Conceptual Graphs Based Information Retrieval in HealthAgents

Abstract

This paper focuses on the problem of representing, in a meaningful way, the knowledge involved in the HealthAgents project. Our work is motivated by the complexity of representing Electronic Healthcare Records in a consistent manner. We present HADOM (HealthAgents Domain Ontology) which conceptualises the required HealthAgents information and propose describing the sources knowledge by the means of Conceptual Graphs (CGs). This allows to build upon the existing ontology permit-ting for modularity and flexibility. The novelty of our approach lies in the ease with which CGs can be placed above other formalisms and their potential for optimised querying and retrieval.

Framework Architecture for Improving Healthcare Information Systems using Agent Technology

“…These e-health applications share notable features: loosely coupled heterogeneous systems, dynamic management of distributed resources, and accessibility by remote e-health actors, which corresponds with the characteristics of software agents [30,31]. Multi-agent systems can be used for the recognition of diagnosis applications and Health Agents IHKA [32], OHDS [33][34][35]. Lee et al [36] and Kifor et al [37] proposed intelligent agent-based healthcare models.…”

Advancements in Healthcare: Multi-Agent Based Intelligent Sensor Approach

“…Diagnosing Diseases Computer-based technologies are heavily involved in the healthcare process in diagnosis, from measuring data using sensors to making sense out of data using machine learning and data analysis. Applications using multi-agent systems in this domain are, IHKA [22], HealthAgents [22,23] and ODHS [24]. IHKA [22] was based on five different typed of agents with different functionalities, (1) query knowledge retrieval agent, (2) UI agent, (3) Query optimizer agent, (4) Query knowledge adaption agent and (5) Query knowledge procurement agent, the broken case if everything fails it will search different sources for information autonomously.…”

Cognitive agents and machine learning by example: Representation with conceptual graphs

“…Other advantages are the simplification of the representation and relations through labeled edges; their expressiveness, which is similar to natural language (NL); and their accuracy and highly structural information. () Furthermore, other researchers state that CGs are intuitive and semantically sound means of KR. Most importantly, CGs have been demonstrated to offer a computationally tractable and sound way of representing text and NL .…”