Course contentsShow
← Mathematics
Lesson 2818 of 3,12155. Probability — FoundationsFree lesson

Medical Testing and Screening Problems

Applying Bayes' Theorem to interpret sensitivity, specificity, and predictive values in diagnostic tests.

Medical Testing and Screening Problems

What you'll learn: How to use Bayes' Theorem to correctly interpret medical test results by combining sensitivity, specificity, and disease prevalence.

The Core Challenge

When a medical test comes back positive, what's the probability you actually have the disease? Surprisingly, even with a highly accurate test, this probability can be quite low if the disease is rare. Medical testing problems apply Bayes' Theorem to navigate this counterintuitive reality.

Key Terms in Medical Testing

  • Sensitivity (True Positive Rate): P(Positive Test | Disease Present) — how good the test is at detecting the disease when you have it
  • Specificity (True Negative Rate): P(Negative Test | Disease Absent) — how good the test is at returning negative when you're healthy
  • Prevalence: P(Disease Present) — the prior probability, how common the disease is in the population
  • Positive Predictive Value (PPV): P(Disease Present | Positive Test) — what we actually want to know!

Applying Bayes' Theorem

The formula becomes:

P(Disease | Positive) = [P(Positive | Disease) × P(Disease)] / P(Positive)

Where P(Positive) uses the Law of Total Probability:

P(Positive) = P(Positive | Disease) × P(Disease) + P(Positive | No Disease) × P(No Disease)

Note: P(Positive | No Disease) = 1 - Specificity

A Simple Example

A disease affects 1% of the population (prevalence). The test has 95% sensitivity and 90% specificity. If you test positive, what's the probability you have the disease?

  • P(Disease) = 0.01
  • P(Positive | Disease) = 0.95
  • P(Positive | No Disease) = 0.10

P(Positive) = 0.95(0.01) + 0.10(0.99) = 0.0095 + 0.099 = 0.1085

P(Disease | Positive) = 0.0095 / 0.1085 ≈ 0.088 or 8.8%

Even with this "accurate" test, a positive result means less than 9% chance of disease!

Key Takeaway: Bayes' Theorem reveals that even highly sensitive and specific tests can have low positive predictive values when screening for rare diseases — the prior probability (prevalence) dramatically affects interpretation.