Usage of Semantic Web Technologies (Web-3.0) Aiming to Facilitate the Utilisation of Computerized Algorithmic Medicine in Clinical Practice

Medicine 2.0

Introduction: Despite the proven benefits of algorithmic medicine in healthcare and the plethora of implemented medical algorithms solving Medical Computational Problems (MCPs) which are available on the web [1], their usage is limited in everyday clinical practice. This is mainly due to poor organisation of MCP information, difficulties in MCP search and the missing parameters in the description of medical cases, making their management by a single algorithm rather impossible. In this paper a comprehensive approach to the usage of semantic web technologies (web-3.0) is presented, aiming to facilitate the utilisation of computerized algorithmic medicine in clinical practice. In particular, there are 3 main goals achieved, namely, the semantic descriptions of MCPs, the efficient search of MCPs, and the dynamic semantic composition of a sequence of algorithms managing a certain medical case. Methods: For the Semantic representation of MCP knowledge the MCP OWL Ontology describes the MCPs as a triad: (Medical Problem-Algorithmic Solution-Implementation) Three interacting ontological schemes that refer to each part of the above triad were created. For efficient search, the method used is an adaptation of the classical Vector Space Model (VSM) in MCP Ontology, via which the similarity between MCP semantic descriptions and the user questions is calculated. The weights of MCP vectors are created utilizing the UMLS Ontology [2]. In order to dynamically composite a pathway of algorithms for managing a certain medical case SWLR semantic rules are used. These rules automatically associate different algorithms and construct a Finite State Machine (FSM) of algorithms. The description of a certain medical case via the MCP Ontology by a user constitutes the "language" for that case. If this language is recognised by an FSM of algorithms with the final algorithm that manages the case as the initial state and the algorithm of initiation by the user as the final state, then the sequence of these algorithms can manage the medical case. Results: A modular and expandable, Web-Based Knowledge System (KS) for the MCPs was developed. Preliminary results from its usage showed a more efficient search of MCPs, as well as, a proper management of medical cases through algorithmic pathways proposed by the system which were in agreement with international medical guidelines whenever these were available. Discussion: The developed methods of display and management of MCP knowledge along with the further utilization of the proposed KS are expected to enhance the dissemination and use of algorithmic solutions in everyday medical practice. Simultaneously, medical research and high quality medical education are bound to be benefited at a considerable level. For the dissemination of algorithmic medicine we believe that the future is the combination of web-2.0 and web-3.0 technologies and the transformation of our system to a semantic wiki of MCPs. [1] Iyengar MS, Svirbely JR: Computer-based medical algorithms: overview and experiences. Technol. Health Care 2005, 13(5):403-405 [2] Bratsas C, Koutkias V, Kaimakamis E, Bamidis PD, Pangalos G, Maglaveras N: KnowBaSICS-M: An ontology-based system for semantic management of medical problems and computerised algorithmic solutions. Comput. Meth. Progr. Biomed 2007, 88(1):39-51