Table 3.

Sensitivity, specificity and likelihood ratios: definitions and examples

Sensitivity	Example in a group of 100 patients with bacterial pneumonia, 80 had a raised C-reactive protein CRP: the sensitivity of CRP for diagnosing bacterial pneumonia is thus 80 %
How often is the test result correct for persons in whom the disease is known to be present?
Sensitivity—the proportion of people with disease who have a positive test
Specificity	Example in a group of 100 patients without pneumonia, 10 had a raised C-reactive protein CRP: the specificity of CRP for correctly excluding pneumonia is thus 90 %
How often is the test result correct for persons in whom the disease is known to be absent?
Specificity—the proportion of people without the disease who have a negative test
Likelihood ratio	Example A raised jugular venous pressure (JVP) in a patient with a history suggestive of congestive heart failure (CHF) has a positive likelihood ratio of 5.8 and a negative ratio of 0.66. Thus the presence of a raised JVP rules-in the diagnosis of CHF. Its absence is not as useful in ruling it out
The likelihood that a given test result would be expected in a patient with the target disorder compared with the likelihood that the same result would be expected in a patient without that disorder.
In general, a positive likelihood ratio of 4 or more is useful in ruling-in the target disorder. A negative likelihood ratio of <0.3 is useful in ruling-out the target disorder