OBJECTIVES: Limited guidance exists for healthcare providers deciding when to treat patients with adjuvant chemotherapy (ACT) in early NSCLC. This leads to high-risk untreated patients that could benefit, and low-risk patients who could avoid the toxicity and cost, from ACT. This study examined the cost-effectiveness of the prognostic test myPlan Lung Cancer vs. current standard of care (SoC) in directing ACT treatment decisions in stage I/II NSCLC. METHODS: A Markov model was created to examine costs (2011 US$) and effectiveness (quality-adjusted life-years [QALYs]), from a US third-party payer perspective over a lifetime horizon. Patients were classified as high or low risk based on a prognostic score derived from stage and an expression signature based on cell cycle progression. The probability of receiving ACT was estimated from a physician survey. Benefit of ACT treatment was based on stage and prognostic score. Other model inputs were literature-derived or assumption-based. Costs and QALYs were discounted at a 3% annual rate. One-way and probabilistic sensitivity analyses examined the relative impact of model inputs. RESULTS: In the base case scenario 44% of patients received ACT using the prognostic test vs. 38% based on SoC. Total costs were $131,287 and $125,594 and total QALYs gained were 5.33 and 5.16 for the prognostic test and SoC, respectively. The incremental cost-effectiveness ratio (ICER) for the prognostic test was $34,055/QALY gained. One-way sensitivity analyses indicated the probability of receiving ACT for high-risk, stage Ib patients and the ACT treatment benefit were the largest drivers of cost-effectiveness. The probabilistic sensitivity analysis ICER was $44,196/QALY gained. The prognostic test was cost-effective in 51.1% of the simulations at a willingness-to-pay threshold of $50,000/QALY gained. CONCLUSIONS: The results of this study suggest that using myPlan Lung Cancer to guide ACT decisions is cost-effective compared to a SoC approach according to globally accepted thresholds.