Methodological Challenges When Comparing Demographic and Clinical Characteristics of International Observational Registries

Objective Comparisons of data from different registries can be helpful in understanding variations in many aspects of rheumatoid arthritis (RA). The study aim was to assess and improve the comparability of demographic, clinical, and comorbidity data from 5 international RA registries. Methods Using predefined definitions, 2 subsets of patients (main cohort and subcohort) from 5 international observational registries (Consortium of Rheumatology Researchers of North America Registry [CORRONA], the Swedish Rheumatology Quality of Care Register [SRR], the Norfolk Arthritis Register [NOAR], the Institute of Rheumatology Rheumatoid Arthritis cohort [IORRA], and CORRONA International) were evaluated and compared. Patients ages >18 years with RA, and present in or recruited to the registry from January 1, 2000, were included in the main cohort. Patients from the main cohort with positive rheumatoid factor and/or erosive RA who had received ≥1 synthetic disease‐modifying antirheumatic drug (DMARD), and switched to or added another DMARD, were included in the subcohort at time of treatment switch. Results Age and sex distributions were fairly similar across the registries. The percentage of patients with a high Disease Activity Score in 28 joints score varied between main cohorts (17.5% IORRA, 18.9% CORRONA, 24.7% NOAR, 27.7% CORRONA International, and 36.8% SRR), with IORRA, CORRONA, and CORRONA International including more prevalent cases of RA; the differences were smaller for the subcohort. Prevalence of comorbidities varied across registries (e.g., coronary artery disease ranged from 1.5% in IORRA to 7.9% in SRR), partly due to the way comorbidity data were captured and general cultural differences; the pattern was similar for the subcohorts. Conclusion Despite different inclusion criteria for the individual RA registries, it is possible to improve the comparability and interpretability of differences across RA registries by applying well‐defined cohort definitions.