Although joint use of nonsteroidal anti-inflammatory drugs (NSAIDs) and oral anticoagulants may increase the risk of gastrointestinal tract hemorrhage in elderly persons, no epidemiologic studies have been performed to quantify this risk. We performed a retrospective cohort study of Tennessee Medicaid enrollees aged 65 years or older from 1984 through 1986. A total of 103,954 individuals contributed 209,066 person-years of follow-up, including 2203 person-years of current oral anticoagulant use, to the study. Of the cohort members, 1371 had confirmed hospitalizations for peptic ulcer disease. Of these, 661 (48%) presented with frank hematemesis or melena and thus met the definition for hemorrhagic peptic ulcer disease. Among current users of oral anticoagulants, the adjusted incidence of hospitalization for peptic ulcer disease was 14.3 per 1000 person-years, and the adjusted incidence of hospitalization for hemorrhagic peptic ulcer disease was 10.2 per 1000 person-years. Compared with nonusers, current anticoagulant users were at increased risk for hospitalization for ulcer disease (relative risk, 2.2; 95% confidence interval, 1.6 to 3.1), primarily due to the increased risk of hospitalization for hemorrhagic ulcers (relative risk, 3.3; 95% confidence interval, 2.3 to 4.9). Compared with nonusers of either drug, the relative risk of hemorrhagic peptic ulcer disease among current users of both anticoagulants and NSAIDs was 12.7 (95% confidence interval, 6.3 to 25.7). However, the prevalence of NSAID use among anticoagulant users was 13.5%, the same as in those who were not using anticoagulants. The nearly 13-fold increase in the risk of developing hemorrhagic peptic ulcer disease in concurrent users of oral anticoagulants and NSAIDs suggests that NSAIDs should be prescribed with extreme caution in patients undergoing anticoagulation therapy.