This prospective long-term cohort study investigated the incidence of malignancies in severe psoriasis patients treated with cyclosporine. A total of 1252 patients were followed prospectively for up to 5 y. Malignancies were recorded prospectively. Incidence rates for malignancies were compared with the general population using standardized incidence ratios. The effect of duration of exposure to cyclosporine and to previously administered anti-psoriatic treatments on the incidence of malignancies was investigated using Poisson regression models. The mean age of patients was 43 y and on average, patients received cyclosporine for 1.9 y. Malignancies were diagnosed in 47 patients (3.8%), 49% of them had skin malignancies. The standardized incidence ratio in the study cohort was 2.1 as compared with the general population. The higher incidence of malignancies was attributed to a 6-fold higher incidence of skin malignancies, most of which were squamous cell carcinoma. The incidence of nonskin malignancy overall was not significantly higher in this study than in the general population. Duration of exposure to cyclosporine, exposure to psoralen and ultraviolet A, exposure to methotrexate, and exposure to immunosuppressants showed a significant effect on the incidence of nonmelanoma skin malignancies. In conclusion, treatment of psoriasis with cyclosporine is associated with an increased risk of nonmelanoma skin cancer. Patients treated for more than 2 y with cyclosporine were shown to have a higher risk. In addition, exposure to psoralen and ultraviolet A and to other immunosuppressants was shown to contribute to the overall risk.