Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2005:2005:316-20.

Using incomplete citation data for MEDLINE results ranking

Jorge R Herskovic  1 , Elmer V Bernstam
Affiliations

Using incomplete citation data for MEDLINE results ranking

Jorge R Herskovic et al. AMIA Annu Symp Proc. 2005.

Abstract

Information overload is a significant problem for modern medicine. Searching MEDLINE for common topics often retrieves more relevant documents than users can review. Therefore, we must identify documents that are not only relevant, but also important. Our system ranks articles using citation counts and the PageRank algorithm, incorporating data from the Science Citation Index. However, citation data is usually incomplete. Therefore, we explore the relationship between the quantity of citation information available to the system and the quality of the result ranking. Specifically, we test the ability of citation count and PageRank to identify "important articles" as defined by experts from large result sets with decreasing citation information. We found that PageRank performs better than simple citation counts, but both algorithms are surprisingly robust to information loss. We conclude that even an incomplete citation database is likely to be effective for importance ranking.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Growth of PubMed measured in articles added per year (data retrieved from PubMed itself)
Figure 2
Figure 2
Basic system architecture. A query is passed to PubMed (Retrieval Engine) for processing. The original ordering is discarded and a new ranking is computed locally. The full PubMed entries are retrieved from a local store (Content Retrieval) and displayed.
Figure 3
Figure 3
Recall/precision curves for the simple citation count with progressively smaller datasets (intermediate curves omitted for clarity)
Figure 4
Figure 4
Recall/precision curves for the PageRank algorithm with progressively smaller datasets (intermediate curves omitted for clarity)
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. US National Library of Medicine [homepage on the Internet]. PubMed Milestone - 15 Millionth Journal Citation [published July 7, 2004; cited January 15, 2005]. NLM Technical Bulletin. Available from: http://www.nlm.nih.gov/pubs/techbull/ja04/ja04_technote.html
    1. Hersh W. Health and Biomedical Information. In: Hersh W, editor. Information Retrieval. New York: Springer; 2002. p. 22–82.
    1. US National Library of Medicine [homepage on the Internet]. PubMed Help - Display Order [updated March 11, 2005; cited March 16, 2005]. Available from: http://www.ncbi.nlm.nih.gov/entrez/query/static/help/pmhelp.html#Display...
    1. Saracevic, T. Information science: Integration in perspectives. In: Ingwersen P, Pors NO editors. Proceedings of the Second Conference on Conceptions of Library and Information Science (CoLIS 2); 14–17 Oct. 1996; Copenhagen (Denmark). Copenhagen: The Royal School of Librarianship; 1996. p. 201–218.
    1. Dictionary.com [database on the Internet]. The American Heritage® Dictionary of the English Language, Fourth Edition. Houghton Mifflin Company; 2000 [cited March 15, 2005]. Relevance. Available from: http://dictionary.reference.com/search?q=relevance

Publication types

LinkOut - more resources