Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Reducing workload in systematic review preparation using automated citation classification.

A M Cohen1, W R Hersh, K Peterson

  • 1Department of Medical Informatics and Clinical Epidemiology, School of Medicine, Oregon Health & Science University, 3181 S.W. Sam Jackson Park Road, Mail Code BICC, Portland, OR 97239-3098, USA. cohenaa@ohsu.edu

Journal of the American Medical Informatics Association : JAMIA
|December 17, 2005
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Fixing the problem.

British dental journal·2003
Same author

On the mechanism of post-splenectomy leukocytosis in mice.

European journal of clinical investigation·2003
Same author

Results after rectal cancer resection with in-continuity partial vaginectomy and total mesorectal excision.

Annals of surgical oncology·2003
Same author

Resection of locally recurrent colorectal cancer in the presence of distant metastases: can it be justified?

Annals of surgical oncology·2003
Same author

Classification of lymphoproliferative disorders by spectral imaging of the nucleus.

Histology and histopathology·2002
Same author

Preoperative radiation with or without chemotherapy and full-thickness transanal excision for selected T2 and T3 distal rectal cancers.

International journal of colorectal disease·2002

Automated citation classification can help experts save time when updating systematic reviews on drug efficacy. This tool reduced the number of articles needing manual review in most studies.

Area of Science:

  • Medical Informatics
  • Evidence-Based Medicine
  • Pharmacology

Background:

  • Systematic reviews require continuous updates to incorporate new research on drug efficacy.
  • Manual review of numerous journal articles is time-consuming for experts.

Purpose of the Study:

  • To evaluate the utility of automated document citation classification in streamlining the update process for systematic reviews.
  • To assess if automated classification can reduce expert workload in identifying relevant literature for drug class efficacy reviews.

Main Methods:

  • Developed an automated citation classification system using a voting perceptron algorithm.
  • Utilized annotated reference files from 15 systematic drug class reviews for training and testing.
  • Evaluated system performance using precision, recall, and F-measure, with work saved as the primary metric.

Related Experiment Videos

Main Results:

  • Automated classification reduced the number of articles requiring manual review for 11 out of 15 drug review topics.
  • A significant reduction (50% or greater) in manual review was achieved for three of the studied topics.
  • The system demonstrated potential value in optimizing the literature screening process for systematic reviews.

Conclusions:

  • Automated document citation classification shows promise as a valuable tool for maintaining and updating systematic reviews on drug efficacy.
  • Further refinement of the classification system and its integration into review workflows are recommended.
  • This technology can enhance the efficiency of evidence synthesis in pharmacotherapy research.