Abstract
Threshold analysis and likelihood ratios were used to determine the usefulness of a diagnostic test. Eleven staff rheumatologists or rheumatology fellows provided probability estimates for the most likely diagnoses both before and after synovial fluid analyses were performed on 180 patients with joint effusions. They also indicated whether the planned therapy was altered by the test results. The therapeutic thresholds and log likelihood ratios were derived for the 6 most frequent diagnoses. Synovial fluid analysis was most useful for patients likely to have gout, pseudogout or infectious arthritis. The derived therapeutic thresholds were consistent with recommended medical practice, for example, with a lower threshold for possible septic arthritis (20%) than for possible gout (65%). Threshold analysis and likelihood ratios can be used to assess the clinical contribution of diagnostic tests.