A voting approach to identify a small number of highly predictive genes using multiple classifiers
2009

Identifying Predictive Genes for Breast Cancer Prognosis

Sample size: 97 publication 10 minutes Evidence: high

Author Information

Author(s): Hassan Md Rafiul, Hossain M Maruf, Bailey James, Macintyre Geoff, Ho Joshua WK, Ramamohanarao Kotagiri

Primary Institution: The University of Melbourne

Hypothesis

Can a new voting approach identify a compact set of predictive genes for breast cancer prognosis across multiple classifiers?

Conclusion

The study demonstrates that a new voting approach can identify a compact gene set that accurately predicts breast cancer prognosis.

Supporting Evidence

  • The gene sets identified were more compact than those previously proposed.
  • The method demonstrated higher prediction accuracies compared to previous work.
  • Most genes in the identified sets are known to be related to cancer.

Takeaway

Researchers found a small group of genes that can help predict if breast cancer will come back, using a new method that works well with different types of analysis.

Methodology

The study used a multi-classifier voting approach to select genes based on their predictive power across various classifiers.

Potential Biases

Potential bias in gene selection due to the reliance on specific datasets.

Limitations

The study's findings may not generalize to all breast cancer types due to the specific datasets used.

Participant Demographics

The study involved 97 breast cancer patients, with varying treatment backgrounds.

Statistical Information

P-Value

0.005

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2105-10-S1-S19

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication