Inferring conceptual relationships to improve medical records search

Limsopatham, N., Macdonald, C. and Ounis, I. (2013) Inferring conceptual relationships to improve medical records search. In: OAIR 2013, Lisbon, Portugal, 22-24 May 2013,

Abstract

Medical records search is challenging because of the inherent implicit knowledge within medical records and queries. Such knowledge is known to the medical practitioners but may be hidden from a search system. For example, when searching for the medical records of patients with a heart disease, medical practitioners commonly know that the medical records of patients taking the amiodarone medicine are relevant, since this drug is used to combat a heart disease. In this paper, we argue that leveraging such implicit knowledge improves the retrieval effectiveness, since it provides new evidence to infer the relevance of medical records towards a query. Specifically, using a novel concept-based representation for both medical records and queries, we expand the queries by inferring additional conceptual relationships from domain-specific resources as well as by extracting informative concepts from the top-ranked medical records. We evaluate the retrieval effectiveness of our proposed approach in the context of the TREC 2011 and 2012 Medical Records track. Our results show the effectiveness of our approach to model the implicit knowledge in medical records search, whereby the infAP retrieval performance is significantly improved up to 14.43% over an effective concept based representation baseline. Moreover, our proposed approach could achieve retrieval effectiveness comparable to the performance of the best TREC 2011 and 2012 systems

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Macdonald, Professor Craig and Ounis, Professor Iadh
• Authors: Limsopatham, N., Macdonald, C., and Ounis, I.
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• College/School: College of Science and Engineering > School of Computing Science