OBJECTIVES: To compare direct health care costs and opioid use over a 1-year period following initiation with duloxetine versus other standard of care (SOC) treatments among patients with osteoarthritis (OA). METHODS: This retrospective cohort study assessed commercially-insured Marketscan OA patients aged 18-64 years who initiated duloxetine or other treatments (celecoxib, opioids, venlafaxine, gabapentin and pregabalin) in 2009. All selected patients had 12 months continuous enrollment in the pre- and post-index periods, and were grouped into the duloxetine or SOC cohort based on the index agent. The first dispense date was defined as the index date, but with no use of the study medications in the prior 90 days. Both cohorts were then matched via propensity score. The propensity score was estimated based on a logistic regression model that predicted the likelihood of initiating duloxetine adjusting for demographics, comorbidities, prior health care utilization and costs, and prior medication history. Healthcare costs and opioid use (those not initiated on opioids) over the 12-month post-index period were compared between cohorts. RESULTS: The matched sample included 1517 patients in both the duloxetine and SOC group. Both cohorts had a mean age of 54 years, and were mostly females. Over the 12-month post index period, duloxetine-treated patients had lower total health care costs than SOC-treated patients ($16,711 vs $18,447, p<0.05). They also had lower inpatient ($3,374 vs. $5,048) and outpatient costs ($8,427 vs. $9,581), while the pharmacy costs were higher in duloxetine-treated patients ($4,910 vs. $3,818) (all p<0.05). In addition, duloxetine-treated patients were less likely to use any opioids (52% vs 63%, p<0.05). CONCLUSIONS: Commercially-insured OA patients initiating duloxetine were associated with significantly lower health care costs and were less likely to use opioids. These results should be interpreted with caution due to the observational nature of the claims database.