Find sensitivity and specificity — the two standard statistics for evaluating how well a binary test or classifier distinguishes positive from negative cases.
How it works
Sensitivity (true positive rate) is TP ÷ (TP + FN); specificity (true negative rate) is TN ÷ (TN + FP). With 90 true positives and 10 false negatives, sensitivity is 90%; with 80 true negatives and 20 false positives, specificity is 80%.
What this does not include
This is a statistics formula for evaluating a classifier or test’s performance characteristics — it does not diagnose anything itself, and interpreting what a specific sensitivity/specificity pair means for any individual result requires additional context this calculator doesn’t provide.
How to use this calculator
- Enter the counts of true positives, false negatives, true negatives, and false positives.
What’s the tradeoff between sensitivity and specificity?
Adjusting a test’s decision threshold typically raises one at the expense of the other — a more sensitive test catches more true positives but also flags more false positives, lowering specificity.
Why do both matter, rather than just overall accuracy?
A test can have high overall accuracy while performing terribly on the class that actually matters — for example, if positives are rare, a test that always predicts “negative” can have high accuracy but zero sensitivity.
What does 100% sensitivity mean?
Every actual positive case was correctly identified — no false negatives at all, though this says nothing on its own about how many false positives the test also produced.
