Knowledge-based query expansion to support scenario-specific retrieval of medical free text

• Authors: Zhenyu Liu;Wesley W. Chu
• Venue: Proceedings of the 2005 ACM symposium on Applied computing
• Year: 2005

In retrieving medical free text, users are often interested in answers relevant to certain scenarios, scenarios that correspond to common tasks in medical practice, e.g., "treatment" or "diagnosis" of a disease. Consequently, the queries they pose are often scenario-specific, e.g., "lung cancer, treatment." A fundamental challenge in handling such queries is that scenario terms in the query (e.g. "treatment") are too general to match specialized terms in relevant documents (e.g. "lung excision"). In this paper we propose a knowledge-based query expansion method that exploits the UMLS knowledge source to append the original query with additional terms that are specifically relevant to the query's scenario(s). We compare the proposed method with statistical expansion that only explores statistical term correlation and expands terms that are not necessarily scenario specific. Our study on the OHSUMED testbed shows that the knowledge-based method which results in scenario-specific expansion is able to improve more than 5% over the statistical method on average, and about 10% for queries that mention certain scenarios, such as "treatment of a disease" and "differential diagnosis of a symptom/disease."