What is a false positive or false negative in AI diagnostics?

A false positive is a case where an AI tool flags a finding that is not actually present; a false negative is a case where the AI misses a finding that is actually present. These are captured by a tool's sensitivity and specificity statistics, and the acceptable balance between them depends on the clinical use case: a screening tool for a serious, treatable condition is often tuned to minimize false negatives even if that means more false positives to review.