Modeling Genetic Pathway Effects on Disease Outcomes
Author Information
Author(s): Liu Dawei, Ghosh Debashis, Lin Xihong
Primary Institution: Center for Statistical Sciences, Brown University
Hypothesis
Can a logistic kernel machine regression model effectively estimate and test the effect of a genetic pathway on disease outcomes?
Conclusion
The logistic kernel machine regression model provides a flexible and effective statistical tool for modeling the effects of genetic pathways on disease outcomes.
Supporting Evidence
- The proposed model allows for both parametric and nonparametric modeling of genetic pathway effects.
- The study demonstrated the model's application using a prostate cancer dataset.
- The score test developed showed high statistical significance for the pathway effect.
Takeaway
This study created a new way to look at how groups of genes work together to affect diseases, making it easier to understand their impact.
Methodology
The study used logistic kernel machine regression to model the relationship between genetic pathways and disease outcomes, applying it to prostate cancer data.
Limitations
The study primarily focused on a single pathway and may not generalize to multiple pathways without further research.
Participant Demographics
The study involved 81 patients, with 22 diagnosed as non-cancerous and 59 with prostate cancer.
Statistical Information
P-Value
< 0.0001
Statistical Significance
p<0.0001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website