TUESDAY, July 22 (HealthDay News) -- A combination of tumor gene expression and clinical covariates may help predict survival in patients with lung adenocarcinoma, according to an article published online July 20 in Nature Medicine.
Kerby Shedden, Ph.D., of the Cancer Center at the University of Michigan in Ann Arbor, and colleagues report the results of a large, multisite, validation study to characterize the performance of models combining gene expression and clinical data to predict survival for 442 lung adenocarcinomas across four different cancer centers.
Overall, combinations of clinical data combined with gene expression data predicted survival outcomes better than gene expression data alone, the researchers report. Multiple clusters of specific genes were associated with subject outcomes, the report indicates.
"We observed in this study that clinical covariates improved upon gene expression alone as a mechanism for stratifying tumor samples," the authors conclude. "Although there still remain significant challenges to the use of gene expression-based classifiers in the clinical setting, the potential that these
tools can improve patient care and increase survival provides a strong impetus to continue to refine these approaches for eventual clinical use."
Abstract
Full Text (subscription or payment may be required)
