gms | German Medical Science

54. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie e.V. (GMDS)

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie

07. bis 10.09.2009, Essen

Linguistic processing and classification of semi structured bibliographic data on Complementary Medicine

Meeting Abstract

Search Medline for

  • Thomas Ostermann - Chair of Medical Theory and Complementary Medicine, University Witten/Herdecke, Herdecke
  • Christa K. Raak - Chair of Medical Theory and Complementary Medicine, University Witten/Herdecke, Herdecke
  • Hartmut Zillmann - 3 IDM – Intelligent Data Management, Osnabrück

Deutsche Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie. 54. Jahrestagung der Deutschen Gesellschaft für Medizinische Informatik, Biometrie und Epidemiologie (gmds). Essen, 07.-10.09.2009. Düsseldorf: German Medical Science GMS Publishing House; 2009. Doc09gmds245

doi: 10.3205/09gmds245, urn:nbn:de:0183-09gmds2454

Published: September 2, 2009

© 2009 Ostermann et al.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en). You are free: to Share – to copy, distribute and transmit the work, provided the original author and source are credited.


Outline

Text

Background: Many patients have discovered the World Wide Web as a resource for information on Complementary and alternative therapies (CAM). Some observations suggest that with chronic diseases like cancer increasingly search professional sources of clinical evidence in the internet, such as patient guidelines or databases [1], [2]. In particular, there is an increasing demand for information on CAM among cancer patients. Thus, physicians need a simple tool to overview the scientific publications on CAM, particularly those that are not listed in common bibliographic databases like MEDLINE.

Methods: Based on a inverted file structure and the implementation of extended markup language (XML) together with the linguistic algorithms like morphological analysis , stemming and Lemmatisation, grammatical analysis and the analysis of word frequencies and collocations we have developed a search engine which creates CAM-landscapes for every single search query based on elementary bibliographic data.

Results: This search engine is implemented in CAMbase http://www.cambase.de, an XML-based bibliographical database on CAM containing metadata of more than 40 journals of CAM. A custom front end search engine performs semantic analysis of textual input enabling users to quickly find information relevant to the search queries. Up to now, more than 50.000 users have visited CAMbase [3].

Discussion: The semantic web standard XML can be used to unite structural properties of databases, web requirements and the demands of end users. In CAMbase we were able to show how XML together with other algorithmic features like linguistic processing may aid the user to find his way through incomplete and often only semi-structured data in the field of CAM. Longer term, our approach may lead to a creation of a CAM ontology as currently described for other areas of biomedical research.


References

1.
Pal SK, Pandey GS, Kesari A, Choudhuri G, Mittal B. Fighting cancer in the information age: the role of Internet. Indian J Exp Biol. 2003;41(3):189-200.
2.
Ostermann T, Zillmann H, Matthiessen PF. Literatur zur Komplementärmedizin bei Krebs – Recherchemöglichkeit im Internet mit der CAMbase-Datenbank. Dt. Zs. Onkol. 2004;36:165-169.
3.
Ostermann T, Zillmann H, Raak CK, Büssing A, Matthiessen PF. CAMbase – A XML-based bibliographical database on Complementary and Alternative Medicine (CAM). Biomedical Digital Libraries. 2007;4:2