Sensitivity and specificity

Wikis > Research > Statistics > Statistical Tests > Sensitivity and specificity

Sensitivity and specificity:

Used in relation to laboratory tests, radiological examinations, clinical signs and symptoms.

Sensitivity - True positives. Expressed as the number of positives who have the disease divided by the total with the disease x 100 - a sensitive test has a high proportion of true case
- How good the test is at picking up those with the disease.

Specificity - True negatives. Expressed as the number of negatives who do not have the disease divided by the number without the disease x 100 - a specific test has few false positives
- How good is the test at excluding those without the disease

A good test will detect most people with the disease (high sensitivity) and exclude most people without the disorder (high specificity).

Likelihood ratio – how much more likely a positive test is to be found in someone with, as opposed to someone without the disease.
The likelihood of a positive test = sensitivity/(1-specificty)
The likelihood of a negative test = (1-sensitivity)/specificity

Comments are closed.