Information Retrieval from Heterogeneous Data Sources: An Application for Managing Medical Records
Creating digital medical records and retrieve relevant information from them is a complex task. This complexity is given by the mixture of structured and unstructured information found in traditional medical records and that such information could be distributed in different data sources. The main contribution of this paper is the design of an architecture for an Information Retrieval (IR) system that integrates heterogeneous data sources, with a query interface in natural language. This system uses Natural Language Processing (NLP) techniques in order to transform the user query in subqueries to be executed on different data sources, profiting the query capabilities of Database (DB) and IR technologies. The system is connected to the MedlinePlus Medical Encyclopedia to extend the results obtained from a query showing relevant articles to it. In addition, a general application of this design is proposed to address the medical records management problem in a Cuban hospital.
KeywordsInformation Retrieval Databases Heterogeneous Data Sources Integration Natural Language Query Interface
Unable to display preview. Download preview PDF.
- 1.Telang, A., Chakravarthy, S.: Information Integration across Heterogeneous Domains: Current Scenario, Challenges and the InfoMosaic Approach. Technical report, University of Texas at Arlington, Texas (2007) Google Scholar
- 2.Clark, J., DeRose, S.: XML Path Language (XPath). Technical report, World-Wide-Web Consortium (W3C) (1999) Google Scholar
- 8.Fuhr, N., Großjohann, K.: XIRQL: A query language for information retrieval in XML documents. In: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 172–180. ACM, New Orleans (2001)Google Scholar
- 10.Theobald, M., Schenkel, R., Weikum, G.: An efficient and versatile query engine for TopX search. In: Proceedings of the 31st International Conference on Very Large Data Bases, VLDB Endowment, Trondheim, Norway, pp. 625–636 (2005)Google Scholar
- 14.Tannier, X.: From Natural Language to NEXI, an Interface for INEX 2005 Queries. In: Fuhr, N., Lalmas, M., Malik, S., Kazai, G. (eds.) INEX 2005. LNCS, vol. 3977, pp. 373–387. Springer, Heidelberg (2006)Google Scholar
- 15.Popescu, A.-M., Etzioni, O., Kautz, H.: Towards a theory of natural language interfaces to databases. In: Proceedings of the 8th International Conference on Intelligent User Interfaces, pp. 149–157. ACM, Miami (2003)Google Scholar
- 17.U.S. National Library of Medicine, http://www.nlm.nih.gov/medlineplus/