The aim of the study was to assess whether the baseline risk of psychiatric and cardiovascular disease in patients with diabetes mellitus differs between those starting to use antiobesity drugs and those not starting to use these drugs. A retrospective nested case-control study within the General Practice Research Database (1987-2002) was done. The cohort included all patients with diabetes mellitus (n = 141,164). Information on patient characteristics (general, cardiovascular, and psychiatric characteristics) was extracted from the medical records. Crude odds ratios (ORs) and 95% confidence intervals (CIs) were calculated. A total of 511 patients starting to use antiobesity drugs (cases) and 3,065 controls were included in the study cohort. Starters were younger and more frequently female. Of the starters, 91.8% did not receive any dietary advice before starting treatment. Depression (in the year before index date) was associated with the use of antiobesity drugs (OR 2.2; 95% CI 1.7-2.8), as was anxiety (OR 1.6; 95% CI 1.1-2.4). Of the cases, 25.2% had multiple cardiovascular risk factors (>4) compared to 19.0% of the controls. The baseline risk for psychiatric disorders and cardiovascular disease was found to be higher in patients with diabetes mellitus starting to use antiobesity drugs compared to patients with diabetes mellitus not starting such treatment.