Mapping various information sources to a semantic network.

Abstract

Giessen Data Dictionary Server (GDDS) provides context sensitive information services to disparate clinical applications by automatically navigating a semantic network that stores medical knowledge. Mapping multiple information sources to single clinical application becomes a challenge due to different organization of semi-structured information sources. Linking huge unstructured information sources such as medical literature is even more challenging because we need to develop a mechanism to organize unstructured information and take into account the scalability issue. In this paper, we have successfully mapped two drug information sources by developing an independent subnet for each source and linking them at proper nodes. For medical literature, we have demonstrated that the semantic network of the Unified Medical Language Systems and human assigned topics to each document can be used to organize the large amount of medical literature into the framework of the GDDS service.