OBJECTIVE: To assess the incidence of liver failure in association with anti-diabetic treatment using pioglitazone versus other oral anti-diabetic medications. METHODS: The study was a retrospective analysis of claims data from the PharMetrics Patient-Centric Database that had over 1.12 million enrollees with type 2 diabetes. All patients = 18 years of age with type 2 diabetes who had initiated treatment with either a thiazolidinedione (pioglitazone and rosiglitazone), sulfonylurea, or metformin were identified and matched on the basis of propensity scores, which served as a proxy for severity of disease. The primary measure of interest was the incidence of liver failure or hepatitis post-index date. In addition to unadjusted comparisons, Cox proportional hazards models were employed to estimate the risk of developing liver failure or hepatitis. RESULTS: There was no significant difference in the 1-year and 2-year incidence rates of liver failure or hepatitis (primary and secondary diagnosis) between the pioglitazone monotherapy group and respective comparator groups (pairs matched with rosiglitazone, n = 1,847 (p > 0.808); with sulfonylurea, n = 1,474 (p > 0.219); and with metformin, n = 1,137 (p > 0.284)). Cox proportional hazards models controlling for age, pre-index total health care costs, charlson comorbidity index, procedures and a hospitalization or ER visit for pre-index hyperglycemia echoed these results. Further, no primary or secondary diagnosis of liver failure was reported in the pioglitazone group during the follow-up period. CONCLUSION: Results of retrospective data analysis using the PharMetrics cohort of patients with type 2 diabetes demonstrate that there is no evidence of increased risk of liver failure or hepatitis for patients initiating therapy on pioglitazone compared to other oral anti-diabetic agents. Pioglitazone therapy was not associated with an increased risk of liver failure at 2 years relative to other oral anti-diabetic therapies.