Bayes Theorem
Probability of having disease
Bayes’ theorem updates the probability of a hypothesis by combining prior probability with new evidence.
Indications for Use
Start by applying it when pretest probability is uncertain, and a new test meaningfully updates probability of disease. It is useful for interpreting diagnostic tests, combining clinical suspicion with test characteristics, and deciding post‑test management (rule‑in vs rule‑out). Clinically, it guides whether further testing, treatment, or no action is appropriate by quantifying how much a result shifts probability using likelihood ratios.
Insights & Cautions
Start with: It updates diagnostic probability by multiplying the pre-test odds by the test’s likelihood ratio, yielding the post-test odds, which convert back to probability.
- Insights: Clarifies how much a test truly shifts disease probability; prevents overinterpreting small probability changes.
- Cautions: Misuse arises from inaccurate pre-test probability, misapplied likelihood ratios, or ignoring disease prevalence—leading to overdiagnosis or false reassurance.