Purpose: Recent clinical studies indicate that patients with advanced non-small cell lung cancer (NSCLC) whose tumors over-express EGFR may respond better to EGFR tyrosine kinase inhibitors such as gefitinib and erlotinib. Targeted therapy based on EGFR status may thus influence clinical practice. The purpose of this study was to estimate the clinical and economic outcomes associated with a targeted therapy approach and to assess the value created via utilization of a diagnostic test. Methods: We developed a disease simulation model using decision analytic techniques. Data reported in the package insert based on a randomized controlled trial of erlotinib versus best supportive care (BSC) in 731 patients with locally advanced or metastatic NSCLC after failure of at least one chemotherapy regimen were used to inform the model. Adverse event and disease progression costs were estimated from the literature. We estimated life expectancy and direct medical costs for a targeted versus a non-targeted strategy, and calculated incremental cost effectiveness ratios (ICERs). Transition probabilities were derived from survival curves observed in the trial when available; otherwise exponential functions were used based on median time to progression. Sensitivity analyses were conducted to assess the uncertainty in our results. Results: For all patients in the clinical trial, treatment with erlotinib versus BSC increased life expectancy by 0.15 years at an additional cost of $12,492, thus yielding an ICER of $83,000/LY. In the subgroup of patients with known EGFR status (N=238, 33%), targeted therapy (erlotinib for EGFR(+) patients) versus non-targeted therapy (erlotinib for all patients) resulted in decreased costs of $5,096 and a negligible difference in life expectancy; targeted therapy vs. BSC resulted in an ICER of $58,000/LY. The prevalence of EGFR(+) tumors was one of the most influential parameters in the analysis. Conclusions: Our analysis indicates utilizing an approximately $90 EGFR expression assay results in value creation of $5,000 per patient. Because the initial prices for the diagnostic and therapeutic were based on on-market therapies, patients and insurers may be able to capture a substantial share of this value given price inflexibility. Additional analyses based on more complete EGFR data, and incorporating traditional 2nd-line chemotherapy for EGFR(-) patients, will be important.