UMLS-BASED CONCEPTUAL QUERIES TO BIOMEDICAL INFORMATION DATABASES - AN OVERVIEW OF THE PROJECT ARIANE

Objective: The aim of the project ARIANE is to model and implement sea mless, natural, and easy-to-use interfaces with various kinds of heter ogeneous biomedical information databases. Design: A conceptual model of some of the Unified Medical Language System (UMLS) knowledge source s has been developed to help end-users to query information databases. A query is represented by a conceptual graph that translates the deep structure of an end-user's interest in a topic. A computational model exploits this conceptual model to build a query interactively represe nted as query graph. A query graph is then matched to the data graph b uilt with data issued from each record of a database by means of a pat tern-matching (projection) rule that applies to conceptual graphs. Res ults: Prototypes have been implemented to test the feasibility of the model with different kinds of information databases. Three cases are s tudied: 1) information in records is structured according to the UMLS knowledge sources; 2) information is able to be structured without err or in the frame of the UMLS knowledge; 3) information cannot be struct ured. In each case the pattern-matching is processed by the projection rule according to the structure of information that has been implemen ted in the databases. Conclusion: The conceptual graphs theory provide s with a homogeneous and powerful formalism able to represent both con cepts, instances of concepts in medical contexts, and associations by means of relationships, and to represent data at different levels of d etails. The conceptual-graphs formalism allows powerful capabilities t o operate a semantic integration of information databases using the UM LS knowledge sources.