The clinical effect of glucocorticoids in patients with rheumatoid arthritis may be masked by decreased use of additional therapies

Abstract

Objective: Our previous analysis of patients with early active rheumatoid arthritis (RA) treated with prednisone or placebo revealed the following discrepancy: although a significant retardation of joint damage was observed in the prednisone group compared with the placebo group, no differences in clinical variables between the 2 groups were observed, due to greater use of additional therapy in the placebo group. We sought to investigate whether this discrepancy would extend to variables of well-being.

Methods: We conducted a double-blind, randomized, placebo-controlled clinical trial of prednisone (10 mg) in patients with RA; the duration of the study was 2 years. Following the placebo-controlled trial, a 1-year open-label followup study was conducted in 81 patients with early (</=1 year) active, previously untreated RA. Forty-one patients were allocated to receive oral prednisone, 10 mg/day, and 40 patients were assigned to the placebo group. Analgesics, nonsteroidal antiinflammatory drugs (NSAIDs), local injections of a glucocorticoid (only when absolutely necessary), and use of physiotherapy were allowed in both groups. After 6 months, sulfasalazine (2 gm/day) could be prescribed as rescue therapy in both groups. At the beginning of the study and every 6 months thereafter, 2 questionnaires (the VDF [Dutch version of the Health Assessment Questionnaire] and the IRGL [Dutch version of the Arthritis Impact Measurement Scales]) were administered. A visual analog scale (VAS) for morning pain was administered every 3 months. Disease activity and radiologic scores were assessed.

Results: VDF scores in the 2 groups were not statistically significantly different. No statistically significant differences between groups were observed in almost all parameters of the IRGL. In the prednisone group (and only at 6 months), the VAS scores for morning pain and general well-being showed improvement comparable with the transient improvement in some of the disease activity variables. In the prednisone group, use of NSAIDs, analgesics, local injections of glucocorticoids, and physiotherapy sessions was approximately 50% that in the placebo group.

Conclusion: Although significant retardation of joint damage in the prednisone group indicates better disease control, no differences between the groups for variables of well-being were found. This discrepancy may be attributed to greater use of additional therapy in the placebo group. In future clinical trials, the use of additional therapies should be taken into account when analyzing the differences in effect between drugs.