BoW is an on-line bibliographic Dynamic Ranked Informationspace (DyRI). It provides the infrastructure for users to add bibliographical information, classify it, index it, and evaluate it. Thus users cooperate by contributing and sharing their experience in order to advance the most problematic aspects of information retrieval: nding the most relevant and high quality information for their needs. 1

The Semantic Knowledge Representation (SKR) project at the National Library of Medicine (NLM) develops programs that extract usable semantic information from biomedical text by building on resources currently available at NLM. Two programs in particular, MetaMap and SemRep, are being applied to a variety of problems in biomedical informatics. Both programs depend on the biomedical domain knowledge available in the Unified Medical Language System (UMLS ). In representing concepts and relationships extracted from text, the semantic predications produced by these programs support a variety of applications in biomedical information management, including automatic indexing of MEDLINE citations, concept-based query expansion, accurate identification of anatomical terminology and relationships in clinical records, and the mining of biomedical text for drug-disease relations and molecular biology information.

The BoW project aims to create tools for the construction of an on-line bibliographic repository. The repository itself will be created and maintained by its users. Thus it will have a growth potential far beyond that possible with a repository maintained by an individual or small group. But with size come the problems of searching and data quality. The searching problem is solved by a hypertext concept index, to which all items may be linked dynamically by any user. The data quality problem is solved by a dual rating system. First, all search paths executed by users are recorded by the system, and rated according to the number of successes. In addition, users may add annotations to links and items. Thus each user can benefit from the experience of all others. These concepts can lead to a truly on-line publishing system. 1 Introduction Many contemporary scientists (and indeed people in other fields) complain of information overload --- they cannot keep up with the informatio...

Abstract not found

Background: The medical problem list is an important part of the electronic medical record in development in our institution. To serve the functions it is designed for, the problem list has to be as accurate and timely as possible. However, the current problem list is usually incomplete and inaccurate, and is often totally unused. To alleviate this issue, we are building an environment where the problem list can be easily and effectively maintained. Methods: For this project, 80 medical problems were selected for their frequency of use in our future clinical field of evaluation (cardiovascular). We have developed an Automated Problem List system composed of two main components: a background and a foreground application. The background application uses Natural Language Processing (NLP) to harvest potential problem list entries from the list of 80 targeted problems detected in the multiple free-text electronic documents available in our electronic medical record. These proposed medical problems drive the foreground application designed for management of the problem list. Within this application, the extracted problems are proposed to the physicians for addition to the official problem list. Results: The set of 80 targeted medical problems selected for this project covered about 5 % of