OBJECTIVES: To develop an evidence-based, real world data driven interactive model to predict LDL reduction and National Cholesterol Education Program (NCEP) LDL goal attainment in patients receiving statin monotherapy. METHODS: An interactive model was developed using data from patients receiving statins between January 1, 2001 and December 1, 2005 from two large Southeastern US health plans' administrative claims with integrated lab results data. Multivariate OLS regression was used to predict the percent change in LDL associated with different doses of statin monotherapies for various patient characteristics such as age, gender, NCEP risk factors, presence of coronary heart disease (CHD) /CHD risk equivalents, and baseline lipid values. Each patient was assigned a NCEP risk classification and corresponding LDL goal, and the patient's probability of reaching goal was calculated by simulating a distribution of the expected percent change and its 95%CI obtained from the regression. RESULTS: A total of 33,706 patients were used to build the model. The cohort had a mean age of 54(+10) years and was 51% male. A total of 41% of patients were classified as low, 22% as moderate, 30% as high, and 7% as very high risk based on NCEP criteria. LDL reduction associated with atorvastatin 10-80mg, rosuvastatin 5-40mg and simvastatin 10-80mg ranged from 35-38%, 31-39% and 24-34%, respectively. The multivariate regression indicated that NCEP risk status and baseline LDL values were significantly associated with higher reduction in LDL (p<0.05), independent of type and dose of statin monotherapy. CONCLUSION: Real world, data driven interactive models may help decision makers identify patients that are ideal candidates for cost-effective statin prescribing that results in substantial cost savings while improving health outcomes. Models such as this will allow clinicians, health plan administrators and patients to maximize the economic benefit of marketplace changes such as generic simvastatin availability in a clinically appropriate fashion.