The 1971 preliminary criteria for the classification of systemic lupus erythematosus (SLE) were revised and updated to incorporate new immunological knowledge and improve disease classification. The 1982 revised criteria include fluorescence antinuclear antibody (FANA) and antibody to native DNA and Sm antigen. Some criteria involving the same organ systems were aggregated into single criteria. Raynaud's phenomenon and alopecia were not included because of low sensitivity and specificity. The new criteria were 96% sensitive and 96% specific when tested with SLE and control patient data gathered from 18 participating clinics. When compared with the 1971 criteria, the 1982 revised criteria showed gains in sensitivity and specificity. Development of criteria sets is inherently circular, since the standard of evaluation must consist of the clinical diagnosis. Validation of the diagnosis over time can reduce but not eliminate the circularity. Selection of controls also influences sensitivity and specificity and, ideally, criteria should be developed with controls who represent particularly difficult problems of discrimination. Because the low "prior probability" of the diagnosis in many populations will result in a large number of false positives, preference in general should be for specificity over sensitivity. The 1982 criteria were developed from 177 patients with SLE and 162 control patients from 18 institutions using the next age-, race- and sex-matched patient seen as the control whenever possible. Results of a training sample were validated against a test sample of patients and against 500 patients from other databanks.