OBJECTIVES: More than one third of adults in the United States have obesity. Orlistat was approved by the FDA for long-term antiobesity treatment in 1999. In 2009, after reviewing 32 case reports describing severe liver injury, the FDA issued a warning on the use of orlistat. In 2010, the FDA revised the label of orlistat to include new safety information about the potential risk of severe liver injury. The objective of this study was to assess the association between the use of orlistat and the risk of acute liver injury. METHODS: A retrospective cohort study was conducted with Truven MarketScan® Commercial Claims data (2003-2004). Patients prescribed orilistat, sibutramine or phentermine were included.  Propensity-score matching was used to balance the baseline characteristics between the group of patients on orlistat and the group prescribed sibutramine or phentermine. A COX proportional hazard regression was estimated to compute risks for acute liver injury.   RESULTS: A total of 13,792 patients on antiobesity medication were identified. Overall, 145 patients (2.10%) in the orlistat group had at least one acute liver injury event, and 99 patients (1.44%) in the sibutramine/phentermine group experienced one. After propensity-score matching, orlistat patients were found to be significantly more likely to experience acute liver injury than patients in the sibutramine/phentermine group (Hazard Ratio (HR), 1.364; 95% CI: 1.055-1.763; p-value=0.0177).  In addition, elderly patients (HR, 1.021; 95% CI: 1.006-1.036; p-value=0.0054), patients with type 2 diabetes (HR, 1.534; 95% CI: 1.155-2.038; p-value=0.0032),  patients with hyperlipidemia (HR, 1.476; 95% CI: 1.126-1.934; p-value=0.0048), and patients who took hepatotoxic drugs in the washout period or up to 3 months before the liver event (HR, 1.840; 95% CI: 1.426-2.374; p-value<0.0001) had an increased risk of injury.  CONCLUSIONS: Orlistat is associated with an increased risk of acute liver injury. Future research is needed to guide clinical decision making.