OBJECTIVE: To investigate the cardiovascular risk associated with pioglitazone monotherapy as compared to insulin monotherapy in a large retrospective database. METHOD: Patients = 18 years of age with a diagnosis of type-2 diabetes and initiated with pioglitazone or insulin monotherapy for at least 6 months with no cardiovascular events reported at baseline were selected from GE Medical Systems (GEMS) database of electronic medical records from physician offices. Patients prescribed other oral anti-diabetic drugs were excluded. Cardiovascular events included one or more of the following forms of coronary artery disease: myocardial infarction, angina pectoris, unstable angina, other ischemic heart disease and surgical procedures of coronary artery bypass and angioplasty, and congestive heart failure. To avoid selection bias, patients were matched 1:1 on pioglitazone and insulin using propensity scores. Baseline demographics and clinical characteristics such as duration of disease, co-morbidities, medical therapies, and duration of treatment were included in the propensity score analysis. Logistic regression was used to calculate the odds ratio of the cardiovascular event in the follow-up period with treatment as the factor and significant (p <0.1) baseline characteristics as the adjusting covariates in the model. RESULTS: A total of 381 patients on pioglitazone monotherapy were compared with an equal number of patients on insulin monotherapy. The crude cardiovascular event rate in the pioglitazone group was 1.84% compared with 9.71% in the insulin group (p<0.001). The hazard ratio was 0.174 for pioglitazone (95% CI = 0.077, 0.396; p <0.001). The significant risk reduction projected for the pioglitazone group could not be completely explained by baseline laboratory measurements of lipids, serum creatinine, systolic and diastolic blood pressure, or duration of diabetes. CONCLUSION: In a retrospective propensity-matched cohort analysis in patients with type-2 diabetes, patients treated with pioglitazone monotherapy had a significantly lower incidence of cardiovascular events than those taking insulin monotherapy.