Identifying Predictive Genes for Breast Cancer Prognosis
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)
Want to read the original?
Access the complete publication on the publisher's website