The likelihood ratio. An improved measure for reporting and evaluating diagnostic test results.

Abstract

The principles and use of likelihood ratios are presented as an aid to the reporting and interpretation of diagnostic data. Likelihood ratios can be determined for multiple levels of test results and provide a readily comprehensible and convenient measure for computing the posttest probability of disease. Unlike sensitivity and specificity, they convey an immediate and direct description of a test's ability to revise the initial probability of disease upward or downward. By incorporating all the raw data, the use of likelihood ratios can improve the assessment of the clinical utility of test results. Their application to the diagnostic performance of serum creatine kinase concentrations in predicting patients with suspected myocardial infarction is discussed.