Display options
Cite
Thompson P, Madan JC, Moore JH. Prediction of relevant biomedical documents: a human microbiome case study. BioData Min. 2015;8:28doi: 10.1186/s13040-015-0061-5.
Thompson, P., Madan, J. C., & Moore, J. H. (2015). Prediction of relevant biomedical documents: a human microbiome case study. BioData mining, 828. https://doi.org/10.1186/s13040-015-0061-5
Thompson, Paul, et al. "Prediction of relevant biomedical documents: a human microbiome case study." BioData mining vol. 8 (2015): 28. doi: https://doi.org/10.1186/s13040-015-0061-5
Thompson P, Madan JC, Moore JH. Prediction of relevant biomedical documents: a human microbiome case study. BioData Min. 2015 Sep 10;8:28. doi: 10.1186/s13040-015-0061-5. eCollection 2015. PMID: 26361503; PMCID: PMC4564977.
Copy Download .nbib Format: NLM
Share it on

BioData Min. 2015 Sep 10;8:28. doi: 10.1186/s13040-015-0061-5. eCollection 2015.

Prediction of relevant biomedical documents: a human microbiome case study.

BioData mining

Paul Thompson, Juliette C Madan, Jason H Moore

Affiliations

  1. Program in Linguistics, Dartmouth College, Hanover, NH 03755 USA.
  2. Department of Pediatrics, Division of Neonatology, Dartmouth-Hitchcock Medical Center, One Medical Center Drive, Lebanon, NH 03756 USA.
  3. Institute for Biomedical Informatics, Departments of Genetics and Biostatistics and Epidemiology, Perelman School of Medicine, University of Pennsylvania, 3535 Market Street, Philadelphia, PA 19104 USA.

PMID: 26361503 PMCID: PMC4564977 DOI: 10.1186/s13040-015-0061-5

Abstract

BACKGROUND: Retrieving relevant biomedical literature has become increasingly difficult due to the large volume and rapid growth of biomedical publication. A query to a biomedical retrieval system often retrieves hundreds of results. Since the searcher will not likely consider all of these documents, ranking the documents is important. Ranking by recency, as PubMed does, takes into account only one factor indicating potential relevance. This study explores the use of the searcher's relevance feedback judgments to support relevance ranking based on features more general than recency.

RESULTS: It was found that the researcher's relevance judgments could be used to accurately predict the relevance of additional documents: both using tenfold cross-validation and by training on publications from 2008-2010 and testing on documents from 2011.

CONCLUSIONS: This case study has shown the promise for relevance feedback to improve biomedical document retrieval. A researcher's judgments as to which initially retrieved documents are relevant, or not, can be leveraged to predict additional relevant documents.

References

  1. Bioinformatics. 2007 Jul 1;23(13):i41-8 - PubMed
  2. Bioinformatics. 2009 Apr 1;25(7):974-6 - PubMed
  3. BMC Bioinformatics. 2010 Apr 16;11 Suppl 2:S6 - PubMed
  4. Database (Oxford). 2011 Jan 18;2011:baq036 - PubMed

Publication Types

Grant support