Sensitivity

Sensitivity is the proportion of people who truly have a condition that a test correctly identifies as positive. It answers the question "among those with the disease, how many does the test catch?" and is one of the two intrinsic accuracy measures, alongside specificity, used to evaluate diagnostic and screening tests against a reference standard.

Definition

Sensitivity is the conditional probability that a test result is positive given that the disease is truly present, calculated as the number of true positives divided by the total number of people with the disease (true positives plus false negatives).

Scope

This entry defines sensitivity as the true-positive rate, situates it within the 2x2 table of test result against true disease status, explains its complement (the false-negative rate), and notes how it is estimated, why it can vary across patient spectra, and how it relates to likelihood ratios. It is a methodological topic and does not advise on the use of any particular test.

Key concepts

• True-positive rate
• False-negative rate (1 - sensitivity)
• Reference (gold) standard
• Conditional probability given disease
• Spectrum bias
• Positive likelihood ratio

Mechanisms

Sensitivity is computed down the diseased column of the 2x2 table: of all subjects whose true status (set by the reference standard) is diseased, it is the fraction the test calls positive. Because it conditions on true disease status, sensitivity is in principle independent of how common the disease is in the tested group; it characterises the test rather than the population. Its complement, one minus sensitivity, is the false-negative rate — the proportion of diseased people the test misses. A highly sensitive test, when negative, helps rule a condition out, because few true cases produce negative results. Sensitivity combines with specificity to form the positive likelihood ratio, which expresses how much a positive result raises the odds of disease. Estimates of sensitivity can shift with the clinical spectrum of cases studied, so a value measured in severe, clear-cut cases may overstate performance in milder presentations.

Clinical relevance

Sensitivity is a standard yardstick for judging how well a test detects disease and is especially emphasised where missing a case carries serious consequences, as in many screening contexts. The concept supports critical appraisal of diagnostic evidence; it describes a property of a test and is not a basis for individual diagnostic or treatment decisions.

Epidemiology

In screening, high sensitivity is often prioritised so that few true cases are missed, accepting more false positives as a trade-off. Reported sensitivity is sensitive to study design: spectrum bias and incomplete or differential application of the reference standard can inflate it, which is part of why reporting standards such as STARD ask for explicit description of how participants and the reference standard were handled.

Evidence & guidelines

The STARD statement asks diagnostic accuracy studies to report how participants were selected and how the reference standard was applied, both of which directly affect estimated sensitivity.

History

The paired notions of sensitivity and specificity entered medical statistics from the broader theory of classification and signal detection and were made widely accessible to clinicians through expository work in the medical literature in the 1990s. Earlier methodological writing in the 1970s drew attention to how the spectrum of patients studied could bias these measures.

Debates

Is sensitivity truly independent of the population tested?

Although defined to be a property of the test, measured sensitivity can vary with the clinical spectrum of cases, so reported values may not transfer to populations with a different mix of disease severity.

Key figures

• Douglas Altman
• Martin Bland
• Jonathan Deeks
• David Ransohoff
• Alvan Feinstein

Seminal works

• altman-bland-1994a
• ransohoff-feinstein-1978
• deeks-altman-2004

Frequently asked questions

Does a highly sensitive test confirm disease when positive?

No. High sensitivity means a negative result is reassuring because few true cases are missed; a positive result still needs specificity and the underlying prevalence to judge how likely disease really is.

What is the false-negative rate?

It is one minus sensitivity: the proportion of people who have the condition but are wrongly classified as negative by the test.