Formula
Sens = TP/(TP+FN) · Spec = TN/(TN+FP) · PPV = TP/(TP+FP) · NPV = TN/(TN+FN) · LR+ = sens/(1−spec) · LR− = (1−sens)/spec · Prevalence = (TP+FN)/N · Accuracy = (TP+TN)/N
Clinical pearls
- PPV and NPV depend on prevalence: they apply only to populations with a disease prevalence similar to the study sample.
- Sensitivity and specificity (and LRs) are more portable between settings, but can still vary with disease spectrum.
Examples
2x2 table tp 90 fp 20 fn 10 tn 80sensitivity and specificity with 45 true positives, 5 false negatives, 15 false positives, 135 true negativesppv npv tp 30 fp 70 fn 3 tn 897
FAQ
What is the difference between sensitivity and PPV?
Sensitivity is the proportion of people with disease who test positive; PPV is the proportion of positive tests that truly have disease, and it changes with prevalence.
What does SnNout and SpPin mean?
A highly Sensitive test, when Negative, rules out disease; a highly Specific test, when Positive, rules in disease.