Now posted with cited references and e-mail address - Bernstam EV, Herskovic JR, Aphinyanaphongs Y, Aliferis CF, Sriram MG, Hersh WR "Using citation data to improve retrieval from MEDLINE "

[Eugene Garfield]

Elmer V. Bernstam : E-mail Addresses: elmer.v.bernstam at uth.tmc.edu


Title: Using citation data to improve retrieval from MEDLINE

Author(s): Bernstam EV, Herskovic JR, Aphinyanaphongs Y, Aliferis CF,
Sriram MG, Hersh WR

Source: JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 13 (1): 96-
105 JAN-FEB 2006

Document Type: Article      Language: English Cited References: 34
Times Cited: 0

Abstract:
Objective: To determine whether algorithms developed for the World Wide Web
can be applied to the biomedical literature in order to identify articles
that are important as well as relevant.
Design and Measurements: A direct comparison of eight algorithms: simple
PubMed queries, clinical queries (sensitive and specific versions), vector
cosine comparison, citation count, journal impact factor, PageRank, and
machine learning based on polynomial support vector machines. The objective
was to prioritize important articles, defined as being included in a pre-
existing bibliography of important literature in surgical oncology.
Results: Citation-based algorithms were more effective than noncitation-
based algorithms at identifying important articles. The most effective
strategies were simple citation count and PageRank, which on average
identified over six important articles in the first 100 results compared to
0.85 for the best noncitation-based algorithm (p < 0.001). The authors saw
similar differences between citation-based and noncitation-based algorithms
at 10, 20, 50, 200, 500, and 1,000 results (p < 0.001). Citation lag
affects performance of PageRank more than simple citation count. However,
in spite of citation lag, citation-based algorithms remain more effective
than noncitation-based algorithms.
Conclusion: Algorithms that have proved successful on the World Wide Web
can be applied to biomedical information retrieval. Citation-based
algorithms can help identify important articles within large sets of
relevant results. Further studies are needed to determine whether citation-
based algorithms can effectively meet actual user information needs.

Addresses: Bernstam EV (reprint author), Univ Texas, Hlth Sci Ctr, Sch Hlth
Informat Sci, 7000 Fannin St,Suite 600, Houston, TX 77030 USA
Univ Texas, Hlth Sci Ctr, Sch Hlth Informat Sci, Houston, TX 77030 USA
Vanderbilt Univ, Dept Biomed Informat, Nashville, TN USA
Oregon Hlth & Sci Univ, Dept Med Informat & Clin Epidemiol, Portland, OR
USA

E-mail Addresses: elmer.v.bernstam at uth.tmc.edu

Publisher: HANLEY & BELFUS INC, 210 S 13TH ST, PHILADELPHIA, PA 19107 USA

IDS Number: 004AI
ISSN: 1067-5027


COMPUTATION RELATED : 2003
 *MI HLTH SCI LIB A
RES COMM REP U MICH : 1992
 *NLM
NLM RES LISTS BIBL : 2003
 *NLM
PUBM CLIN QUER TABL
 *THOMS ISI
J CITATION REPORTS : 2003
 *THOMS ISI
SCI CIT IND EXP 2004 : 2004
 APHINYANAPHONGS Y
Text categorization models for high-quality article retrieval in internal
medicine
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 12 : 207 2005
 APHINYANAPHONGS Y
MED SAN FRANC CA : 2004
 BACHMANN LM
Identifying diagnostic studies in MEDLINE: Reducing the number needed to
read
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 9 : 653 2002
 BAEZAYATES R
MODERN INFORM RETRIE : 1999
 BORODIN A
ACM T INTERNET TECHN 5 : 231 2005
 BRIN S
WWW7 COMPUTER NETWOR 30 : 107 1998
 GARFIELD E
Journal impact factor: a brief review
CANADIAN MEDICAL ASSOCIATION JOURNAL 161 : 979 1999
 GARFIELD E
CITATION INDEXING AU 1 : 1977
 HAYNES RB
ACP J CLUB 142 : A8 2005
 HAYNES RB
DEVELOPING OPTIMAL SEARCH STRATEGIES FOR DETECTING CLINICALLY SOUND STUDIES
IN MEDLINE
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION 1 : 447 1994
 HERSH WR
How well do physicians use electronic information retrieval systems? A
framework for investigation and systematic review
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION 280 : 1347 1998
 HERSH WR
MED INFORMATICS COMP : 539 2000
 HERSH WR
SIGIR 94 DUBL IR : 1994
 HERSKOVIC JR
AM MED INF ASS FALL : 2005
 JOACHIMS T
SIGIR WORKSH MATH FO : 2002
 KING DN
THE CONTRIBUTION OF HOSPITAL LIBRARY INFORMATION-SERVICES TO CLINICAL CARE -
 A STUDY IN 8 HOSPITALS
BULLETIN OF THE MEDICAL LIBRARY ASSOCIATION 75 : 291 1987
 KLEINBERG J
9 ANN ACM SIAM S DIS : 1998
 LANCASTER F
INFORM RETRIEVAL TOD : 1993
 MANNING CD
FDN STAT NATURAL LAN : 1999
 MARSHALL JG
IMPACT INFORM PROVID : 1991
 OPTHOF T
Sense and nonsense about the impact factor
CARDIOVASCULAR RESEARCH 33 : 1 1997
 PAGE L
PAGERANK CITATION RA : 1998
 STEGMANN J
How to evaluate journal impact factors
NATURE 390 : 550 1997
 WILKINSON R
INFORMATION RETRIEVA : 257 1996

WILLIAMS H
ZETTAIR SEARCH ENGIN : 2004
 WILSON SR
USE CRITICAL INCIDEN : 1989
 ZHU M
JOINT STAT M BIOPH S : 2003
 ZIPSER J
MEDLINE PUBMED BEYON