Medical information retrieval: Development and evaluation of a context-based document representation for searching the medical literature

Conventional full-text systems represent documents as sets of index terms, and queries to these systems often retrieve irrelevant material when search terms occur in inappropriate contexts. We have developed document representations that capture the semantic contexts in which text words occur. Many bodies of literature contain stereotypic categories of information. For example, articles describing medical research consistently discuss interventions and outcomes. These semantic themes provide context for terms in the text, and thus, can facilitate precise full-text searches. We have used a contextual model of clinical research articles, case reports, and review articles as the basis for a document representation in a full-text retrieval system. In this paper, we describe the creation of context models for medical publications and the evaluation of these models using interindexer consistency. We demonstrate that such models are easily understood and employed by readers of the literature (and thus, the searchers). Accordingly, these models may constitute a powerful representation for information retrieval. We discuss the suitability of this technique for other domains. © Springer-Verlag 1997.