Sensitivity

The proportion of individuals who truly have a condition who are correctly identified as positive by a diagnostic test.

Source: Altman & Bland 1994

Sensitivity is the proportion of people who truly have a condition that a test correctly identifies as positive. It measures how well a test catches disease when it is present, so a highly sensitive test misses few true cases and produces few false negatives. This makes sensitivity important for ruling disease out, since a negative result from a very sensitive test is strong reassurance the condition is absent. How well a test detects true cases is what it captures. Sackett and colleagues (1991) describe this measure.

Source: Sackett et al. 1991

Sensitivity is calculated as the number of true positives divided by the total number of people who truly have the condition, that is true positives plus false negatives. It requires a reference standard to establish who genuinely has the condition. So sensitivity is calculated from the proportion of those with the condition who test positive, giving the true positive rate, which is determined by the test itself and does not depend on how common the condition is, distinguishing it from predictive values, and it is estimated by comparing test results against a definitive reference standard in people known to have or not have the condition.

Source: Altman & Bland 1994

High sensitivity means a test correctly identifies most people who have the condition, producing few false negatives, so a negative result from a highly sensitive test is fairly reliable for ruling the condition out. This is why highly sensitive tests are valued when missing a case would be serious, such as in screening. So high sensitivity indicates that the test rarely misses the condition when it is present, which makes a negative result useful for excluding disease, though a highly sensitive test may still give false positives, so sensitivity is considered alongside specificity to judge overall performance.

Source: Sackett et al. 1991

Sensitivity is the proportion of those with the condition who test positive, the true positive rate, while specificity is the proportion of those without the condition who test negative, the true negative rate. Sensitivity concerns detecting the condition when present, and specificity correctly excluding it when absent. There is often a trade-off between the two, since making a test more sensitive can reduce its specificity. So sensitivity and specificity are complementary measures of a test's performance, one capturing how well it finds the condition and the other how well it rules it out, and both are needed to characterise a diagnostic test.

Source: Altman & Bland 1994

Sensitivity is important because it shows how well a test detects a condition when it is present, which matters greatly where missing cases has serious consequences, as in screening or ruling out dangerous conditions. A highly sensitive test gives confidence that a negative result is unlikely to be a missed case. So sensitivity matters for judging a test's ability to catch disease, guiding its use where failing to detect the condition would be harmful, and because it is a property of the test independent of prevalence, it characterises the test's detection ability consistently across settings, complementing specificity and the prevalence-dependent predictive values.

Source: Altman & Bland 1994