August 10, 2006--Two articles in this issue of The New England Journal of Medicine studied the use of gene-expression profiling to predict cancer prognosis.

One study compared predictions derived from distinct prognostic profiles (or gene sets). Five gene expression-based models were applied to 295 breast-tumor samples. The authors concluded that even though different gene sets were used for prognostication in patients with breast cancer, since four of the five models tested showed significant agreement in the outcome predictions for individual patients, they are probably tracking a common set of biologic phenotypes. NEJM 2006;355:560-569.

Another study identified gene-expression profiles that predicted the risk of recurrence in a cohort of 89 patients with early-stage non-small-cell lung cancer (the lung metagene model). The lung metagene model predicted recurrence for individual patients significantly better than did clinical prognostic factors and was consistent across all early stages of non-small-cell lung cancer. The authors concluded the lung metagene model provides a potential mechanism to refine the estimation of a patient's risk of disease recurrence. NEJM 2006;355:570-580