A dynamic problem to knowledge linking Semantic Web service based on clinical codes.

Abstract

Many information needs arise during everyday clinical practice. Problem to knowledge linking aims to answer these needs by providing contextually appropriate medical knowledge in the right place and at the right time. Empirical evidence shows that well-informed physicians and patients are able to make better clinical decisions that positively affect healthcare outcomes. This paper reports on the design and development of a re-usable and flexible Semantic Web problem to knowledge linking service. The service makes use of metadata and clinical codes contextually to link disparate Electronic Patient Record clients to resources in an online medical knowledge service (HealthCyberMap). Clinical codes act as crisp knowledge hooks, providing a reliable common backbone language for communication between Electronic Patient Records and HealthCyberMap. Ideas to improve the service are also discussed. By minimizing irrelevant leads (noise) and reducing the time needed to find relevant information (the right contextually relevant knowledge is linked to real patient data in the Electronic Patient Record), the system is potentially beneficial. The actual success of the system will depend on the quality and granularity of metadata it uses and the topical coverage and quality of resources to which it points.