Gene expression patterns that predict sensitivity to epidermal growth factor receptor tyrosine kinase inhibitors in lung cancer cell lines and human lung tumors
2006

Predicting Lung Cancer Response to EGFR Inhibitors

Sample size: 29 publication Evidence: high

Author Information

Author(s): Balko Justin M, Potti Anil, Saunders Christopher, Stromberg Arnold, Haura Eric B, Black Esther P

Primary Institution: University of Kentucky

Hypothesis

A multivariate predictor of EGFR TKI sensitivity based on gene expression data would offer a clinically useful method of accounting for variability in predicting response to EGFR TKI.

Conclusion

Multivariate predictors of response to EGFR TKI have potential for clinical use and provide a robust predictor of EGFR TKI sensitivity.

Supporting Evidence

  • Gene expression data from sensitive and resistant lung cancer cell lines were analyzed to identify predictive patterns.
  • Diagonal linear discriminant analysis was used to classify cell lines and human tumors based on their sensitivity to EGFR inhibitors.
  • The predictive model demonstrated a 0% misclassification rate in leave-one-out cross-validation.

Takeaway

Scientists created a special test to help doctors know which lung cancer patients will respond to a specific treatment, making it easier to choose the right medicine.

Methodology

The study used gene expression data from lung cancer cell lines and human tumors to develop predictive models for EGFR TKI sensitivity, employing diagonal linear discriminant analysis for classification.

Potential Biases

Potential bias due to unequal replicates used in the model and the reliance on specific cell line types for training.

Limitations

The study's predictive model may not account for all factors influencing EGFR TKI sensitivity, such as pharmacokinetic variability and markers of epithelial to mesenchymal transition.

Participant Demographics

The study involved lung cancer cell lines and human adenocarcinoma tumors, but specific demographic details of human participants were not provided.

Statistical Information

P-Value

0.0001

Statistical Significance

p<0.0001

Digital Object Identifier (DOI)

10.1186/1471-2164-7-289

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication