OBJECTIVE: The suggested approach (models and the database) enables one to evaluate changes in disease-specific health care utilization and associated costs which could result from a health care intervention, including the introduction of new medicines in various therapeutic areas. METHODS: Disease-specific estimates of health care utilization and associated medical expenses distributed by types of care and sources of payment have been constructed by applying a linear model with exogenous population weights and normalizing coefficients to relational data files derived from the National Medical Expenditure Survey data. A proportional attributable risk model, which incorporates exogenous parameters accounting for causality, inflation, discounting, human costs associated with lost earnings, and population structural changes, has been developed for estimating direct and indirect costs of diseases. These constructed cost estimates (direct, direct by types of care and indirect) have been used as input variables for benefit-cost and cost-effectiveness models. RESULTS: Health care utilization profiles have been constructed for lung cancer, non-small cell lung cancer (NSCLC), and NSCLC in stage III-IV. For a regimen including a new drug in addition to Taxol and Carboplatin, which will add at least 97 days to a median survival, to be cost saving, it has to reduce the individual disease cost by 28.3%. For the same regimen to enable a system cost saving it has to ensure 34.6% changes in a system health care cost. This new product will be cost-effective at the threshold of $80,000 per life year gained if it is priced within $8,000 - $13,700. Within this price range, the estimated individual averted cost might reach $7,000-$17,000. CONCLUSIONS: The suggested approach allows one to link clinical efficacy to plausible changes in health outcomes, health care utilization and attendant costs at any of the levels and types of health care delivery.