Simultaneous clustering of gene expression data with clinical chemistry and pathological evaluations reveals phenotypic prototypes
2007

New Algorithm for Clustering Gene Expression Data with Clinical Information

Sample size: 303 publication 10 minutes Evidence: moderate

Author Information

Author(s): Bushel Pierre R, Wolfinger Russell D, Gibson Greg

Primary Institution: National Center for Toxicogenomics, National Institute of Environmental Health Sciences

Hypothesis

Can the modk-prototypes algorithm effectively cluster gene expression data with clinical chemistry and histopathological evaluations?

Conclusion

The modk-prototypes algorithm successfully clustered data, achieving an accuracy of 79% in distinguishing between heart disease samples.

Supporting Evidence

  • The modk-prototypes algorithm achieved an accuracy of 79% in clustering heart disease samples.
  • The algorithm effectively distinguished between different levels of necrosis in rat liver samples.
  • Clustering results were validated using the adjusted Rand index, showing good agreement with histopathological evaluations.

Takeaway

Researchers created a new way to group data about genes and health to better understand diseases, and it worked really well.

Methodology

The study used the modk-prototypes algorithm to cluster gene expression data alongside clinical and histopathological data.

Potential Biases

Potential biases in weighting the different data domains could affect clustering results.

Limitations

The study may not generalize to all types of data or diseases.

Participant Demographics

The study involved 303 patients from the Cleveland Clinic heart disease database.

Statistical Information

P-Value

0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1752-0509-1-15

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication