The requirements for the design and implementation of a medical information retrieval system for expert and consumer users are discussed. The proposed approach is based on the integration of state-of-the-art tools and methodologies of systems design and document management. Relying on term extraction by natural language processing, the system supports automatic categorization as well as, indexing and retrieval of medical documents by user profile (novice users and experts). This is achieved by mapping document terms to external lexical resources such as WordNet, and MeSH (the medical thesaurus of NLM). Evaluation results of all methods are presented and discussed as well.
展开▼
