When referring to the accuracy of a medical test, statisticians use the words sensitivity and specificity. 1 Sensitivity refers to the proportion of the times that a test yields true positives. The closer the sensitivity is to 100%, the more likely a positive result actually means that the patient has a disease. Specificity refers to the proportion of the time that a test yields true negatives. The closer the specificity is to 100%, the more likely a negative result means that the patient is truly disease-free.
A perfect test gives only true positives and true negatives, and the worst possible test would be the same as guessing. While many medical tests are highly accurate, all tests used in medicine fall somewhere in between these two extremes. This uncertainty raises some difficult issues. A test that yields a positive result will usually lead to the performance of a second, more accurate test. If the second test used is still simple and non-invasive, then a preliminary test that yields a high number of false positives may be acceptable. If the second test is difficult to perform or risky, the initial blood test may lead many people to have unnecessary medical procedures.
If the first test is imperfect it may incorrectly indicate that patients are healthy, when in fact they are not. If the disease is mild and will probably not hurt the patient's health, then the blood test does little harm when it is wrong. If the disease is serious, the blood test may prevent patients from obtaining necessary treatments. The value of any blood test is a balance between the sensitivity and specificity of the test, and the severity of the disease detected. It is important that patients discuss the sensitivity and specificity of tests given with their physician.
Click on the image below to view a documentary on sensitivity and specificity.
To learn more about medical testing, also watch our documentary on false positives and negatives.
- 1. Huda W, Slone R. Review of Radiologic Physics. Lippincott Williams & Wilkins: Philadelphia, 1995.