Sensitivity and Specificity
Two standard statistics used to measure a diagnostic test's ability to correctly identify positive and negative cases.
Sensitivity measures how well a diagnostic test (including an AI diagnostic tool) correctly identifies patients who truly have a condition (true positive rate). Specificity measures how well it correctly identifies patients who truly do not have the condition (true negative rate). Both are standard statistics reported in AI diagnostic validation studies.
A tool can be tuned to favor sensitivity over specificity, or vice versa, which trades off missed cases (false negatives) against unnecessary follow-up (false positives). Neither number alone tells the full story of clinical usefulness.