[Roaming through methodology. XXXVI. Likelihood ratios and Bayes' rule]

In practice, the terms 'sensitivity' and 'specificity' are often used in a different sense to that found in textbooks. Their value depends on the composition of the groups in which the test was applied. It is rarely recognised that sensitivity and specificity change during the course of a disease. The interpretation of their value appears to be difficult. The likelihood ratio combines sensitivity and specificity, and is therefore associated with the same problems. The likelihood ratio is Bayes' rule in its simplest form: how does a given probability (in this case that of a particular disease being present) change with the addition of a single new fact (i.e., the result of a diagnostic test)? The Bayesian approach is applied in various fields but rarely in clinical practice, because the prior probability of a diagnosis is difficult to quantify. Likelihood ratios are useful when studying the diagnostic process and when teaching the diagnostic thought process. They can also be applied in the statistical interpretation of clinical trial results.