Sensitivity is the proportion of people with a condition that a test correctly identifies; specificity is the proportion without it that it correctly excludes. Neither tells you what a result means for one person: predictive value depends on how common the condition is, so the same test produces far more false positives in a population where the disease is rare.
This topic covers how accuracy is measured and how it is reported, including for algorithmic tools, where a headline accuracy figure from a curated dataset is the weakest form of evidence available.
How medical imaging works: X-ray, CT, MRI, ultrasound, nuclear medicine and PET compared — what each detects, radiation exposure, and how images are interpreted.
Medical diagnostics explained: laboratory tests, molecular and point-of-care diagnostics, imaging, sensitivity and specificity, screening, and companion diagnostics.
How AI supports medical diagnosis and clinical decision-making: imaging, pathology, ECG, risk prediction, validation requirements, and clinician oversight.