Download PDF
Methods Inf Med 2010; 49(02): 141-147
DOI: 10.3414/ME9303
Special Topic – Original Articles
Schattauer GmbH

Subword-based Semantic Retrieval of Clinical and Bibliographic Documents

P. Daumke
1   AVERBIS GmbH, Freiburg, Germany
2   Freiburg University Hospital, Medical Informatics Group, Freiburg, Germany
,
S. Schulz
2   Freiburg University Hospital, Medical Informatics Group, Freiburg, Germany
,
M. L. Müller
3   Freiburg University Hospital, Department of Dermatology, Freiburg, Germany
,
W. Dzeyk
4   German National Library of Medicine, Cologne, Germany
,
L. Prinzen
5   Bertelsmann Stiftung, Gütersloh, Germany
,
E. J. Pacheco
6   Paraná Catholic University, Health Informatics Laboratory, Curitiba, Brazil
7   Universidade Tecnológica Federal do Paraná, CPGEI, Curitiba, Brazil
,
P. Secco Cancian
6   Paraná Catholic University, Health Informatics Laboratory, Curitiba, Brazil
,
P. Nohama
6   Paraná Catholic University, Health Informatics Laboratory, Curitiba, Brazil
7   Universidade Tecnológica Federal do Paraná, CPGEI, Curitiba, Brazil
,
K. Markó
1   AVERBIS GmbH, Freiburg, Germany
2   Freiburg University Hospital, Medical Informatics Group, Freiburg, Germany
› Author Affiliations
Further Information

Publication History



22 February 2010

Publication Date:
17 January 2018 (online)

    Permissions and Reprints

Summary

Objectives: The increasing amount of electronically available documents in bibliographic databases and the clinical documentation requires user-friendly techniques for content retrieval.

Methods: A domain-specific approach on semantic text indexing for document retrieval is presented. It is based on a subword thesaurus and maps the content of texts in different European languages to a common interlingual representation, which supports the search across multilingual document collections.

Results: Three use cases are presented where the semantic retrieval method has been implemented: a bibliographic database, a department EHR system, and a consumer-oriented Web portal.

Conclusions: It could be shown that a semantic indexing and retrieval approach, the performance of which had already been empirically assessed in prior studies, proved useful in different prototypical and routine scenarios and was well accepted by several user groups.

Keywords

Thesauri - semantic information retrieval - document indexing - cross-language information retrieval - bibliographic databases - consumer health informatics - electronic health record
 

  • References

  • 1 Scott RE. e-Records in health – Preserving our future. Int J Med Inform 2007; 76 5–6 427-431.
    CrossrefPubMedSearch in Google Scholar
  • 2 Lobach DF, Detmer DE. Research Challenges for Electronic Health Records. American Journal of Preventive Medicine 2007; 32 5, Suppl 1 S104-S11.
    CrossrefPubMedSearch in Google Scholar
  • 3 Wen H-C, Ho Y-S, Jian W-S, Li H-C, Hsu Y-HE. Scientific production of electronic health record research, 1991– 2005. Computer Methods and Programs in Biomedicine 2007; 86 (02) 191-196.
    CrossrefPubMedSearch in Google Scholar
  • 4 Markó K, Schulz S, Medelyan O, Hahn U. Bootstrapping Dictionaries for Cross-Language Information Retrieval. Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Salvador, Brasil, 2005 pp 528-535.
    PubMedSearch in Google Scholar
  • 5 Honeck M, Hahn U, Klar R, Schulz S. Text Retrieval Based on Medical Subwords. In: Surjan G, Engelbrecht R, McNair P. (eds). Health Data in the Information Society. Proceedings of the MIE2002. Amsterdam: IOS Press; 2002. pp 241-245.
    Search in Google Scholar
  • 6 Oard DW, He D, Wang J. User-assisted query translation for interactive cross-language information retrieval. Information Processing & Management 2008; 44 (01) 181-211.
    CrossrefPubMedSearch in Google Scholar
  • 7 Gey FC, Kando N, Peters C. Cross-Language Information Retrieval: the way ahead. Information Processing & Management 2005; 41 (03) 415-431.
    CrossrefPubMedSearch in Google Scholar
  • 8 Kishida K. Technical issues of cross-language information retrieval: a review. Pergamon Press, Inc.; 2005. pp 433-455.
    Search in Google Scholar
  • 9 Franz M, McCarley JS, Ward RT. Ad hoc, cross-language and spoken document information retrieval at IBM. TREC-8. Gaithersburg, MD: National Institute of Standards and Technology. 2000
    Search in Google Scholar
  • 10 Markó K, Hahn U, Schulz S, Daumke P, Nohama P. Interlingual Indexing across Different Languages. 7th International Conference “Recherche d’Information Assistée par Ordinateur” (RIAO’04). 2004. Avignon, France: Proceedings of RIAO’04; 2004. pp 82-99.
    Search in Google Scholar
  • 11 K. Markó P, Daumke S, Schulz R, Klar U. Hahn. Large-Scale Evaluation of a Medical Cross-Language Information Retrieval System. Proceedings of the 12th World Congress on Medical Informatics, Brisbane, Australia (Studies in Health Technology and Informatics, Vol. 129). 2007 pp 392-396.
    PubMedSearch in Google Scholar
  • 12 Markó K, Schulz S, Hahn U. Unsupervised Multi-lingual Word Sense Disambiguation via an Interlingua. Proceedings of the 20th National Conference on Artificial Intelligence (AAAI ’05), Pittsburgh, Pennsylvania. 2005 pp 1075-1080.
    PubMedSearch in Google Scholar
  • 13 Lewandowski D. Mit welchen Kennzahlen lässt sich die Qualität von Suchmaschinen messen?. In: Die Macht der Suchmaschinen. / The Power of Search Engines. Machill M, Beiler M. editors. Cologne: Herbert von Halem Verlag; 2007. pp 243-258.
    Search in Google Scholar
  • 14 Flavián C, Guinalíu M, Guerra R. The role played by perceived usability, satisfaction and consumer trust on website loyalty. Information & Management 2006; 43: 1-14.
    CrossrefPubMedSearch in Google Scholar
  • 15 Dzeyk W. Vertrauen in Internetangebote. Saarbrücken: VDM Verlag; 2007
    Search in Google Scholar
  • 16 Herskovic JR, Tanaka LY, Hersh W, Bernstam EV. A Day in the Life of PubMed: Analysis of a Typical Day’s Query Log. J Am Med Inform Assoc 2007; 14: 212-220.
    CrossrefPubMedSearch in Google Scholar
  • 17 Rustemeyer R. Praktisch-methodische Schritte der Inhaltsanalyse. Eine Einführung am Beispiel der Analyse von Interviewtexten. Münster: Aschendorff; 1992
    Search in Google Scholar
  • 18 Davies K. The information-seeking behaviour of doctors: a review of evidence. Health Information and Libraries Journal 2007; 24: 78-94.
    CrossrefPubMedSearch in Google Scholar
  • 19 Wirtz M, Caspar F. Beurteilerübereinstimmung und Beurteilerreliabilität. Methoden zur Bestim-mung und Verbesserung der Zuverlässigkeit von Einschätzungen mittels Kategoriensystemen und Ratingskalen. Göttingen: Hogrefe; 2002
    Search in Google Scholar
  • 20 Koch O, Kaltenborn R. Mehr Zeit für Patienten durch bessere Information. Deutsches Ärzteblatt 2005; 28-29: A2008-2011.
    PubMedSearch in Google Scholar
  • 21 Waegemann CP. The vision of electronic health records. J Med Pract Manage 2002; 18 (02) 63-65.
    PubMedSearch in Google Scholar
  • 22 Waegemann CP. The five levels of electronic health records. MD Comput 1996; 13 (03) 199-203.
    PubMedSearch in Google Scholar
  • 23 HIMSS Electronic Health Record, Definitional Model. http://www.himss.org/content/files/EHRAttributes.pdf. Last accessed: January 2009
    PubMedSearch in Google Scholar
  • 24 Dolin RH, Alschuler L, Boyer S, Beebe C, Behlen FM, Biron PV, Shabo SA. HL7 Clinical Document Architecture, Release 2. J Am Med Inform Assoc 2006; 13 (01) 30-39.
    CrossrefPubMedSearch in Google Scholar
  • 25 Müller ML, Uckert F, Bürkle T, Prokosch HU. Cross-institutional data exchange using the clinical document architecture (CDA). Int J Med Inform 2005; 74 2–4 245-256.
    CrossrefPubMedSearch in Google Scholar
  • 26 Scheinfeld N. Photographic images, digital imaging, dermatology, and the law. Arch Dermatol 2004; 140 (04) 473-476.
    PubMedSearch in Google Scholar
  • 27 The Cochrane library. http://www.cochrane.org.
    PubMed
  • 28 Weisse Liste. http://weisse-liste.de.
    PubMed
  • 29 Klassifikationen im Gesundheitswesen.. Deutsches Institut für Medizinische Dokumentation und Information (DIMDI). http://www.dimdi.de/static de/klassi/index.htm.
    PubMed