GAPscreener: An automatic tool for screening human genetic association literature in PubMed using the support vector machine technique
2008

GAPscreener: A Tool for Screening Genetic Association Literature

Sample size: 20000 publication Evidence: high

Author Information

Author(s): Yu Wei, Clyne Melinda, Dolan Siobhan M, Yesupriya Ajay, Wulf Anja, Liu Tiebin, Khoury Muin J, Gwinn Marta

Primary Institution: National Office of Public Health Genomics, Centers for Disease Control and Prevention

Hypothesis

Can an SVM-based tool improve the efficiency and accuracy of screening genetic association studies in PubMed?

Conclusion

GAPscreener is an effective tool that significantly reduces the manual review burden while improving the accuracy of identifying genetic association literature.

Supporting Evidence

  • The SVM tool achieved 97.5% recall and 98.3% specificity in performance testing.
  • GAPscreener reduced the number of abstracts requiring individual review by about 90%.
  • The tool identified 47 articles missed by traditional screening methods.

Takeaway

GAPscreener is a computer program that helps scientists find important studies about genes and diseases much faster and more accurately than doing it by hand.

Methodology

The study used a support vector machine (SVM) to classify PubMed abstracts, comparing its performance against traditional manual screening methods.

Limitations

The tool may miss some articles and the processing speed could be improved with fewer keywords.

Statistical Information

P-Value

<0.0001

Confidence Interval

(0.958–0.975)

Statistical Significance

p<0.0001

Digital Object Identifier (DOI)

10.1186/1471-2105-9-205

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication