Incorporating higher-order representative features improves prediction in network-based cancer prognosis analysis
2011

Improving Cancer Prognosis Predictions with Advanced Gene Features

Sample size: 6 publication 10 minutes Evidence: moderate

Author Information

Author(s): Ma Shuangge, Kosorok Michael R, Huang Jian, Dai Ying

Primary Institution: Yale University

Hypothesis

Can higher-order representative features improve prediction in cancer prognosis analysis?

Conclusion

Incorporating higher-order representative features significantly enhances prediction performance in cancer prognosis studies.

Supporting Evidence

  • The study found that using higher-order features improved prediction performance in six cancer prognosis studies.
  • Logrank statistics indicated significant predictive power when higher-order features were included.
  • The analysis showed that different datasets responded variably to different sets of representative features.

Takeaway

This study shows that using more complex features from gene data can help doctors better predict cancer outcomes.

Methodology

The study used weighted coexpression networks and principal component analysis to analyze gene expression data from six cancer prognosis studies.

Potential Biases

Potential biases may arise from the selection of datasets and the methods used for feature selection.

Limitations

The study's findings may not be generalizable due to the small sample sizes and the specific datasets used.

Participant Demographics

The study analyzed data from various cancer types, including lymphoma and breast cancer, with sample sizes ranging from 71 to 240.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1755-8794-4-5

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication