In the preceding table, there are four numerical cells, labeled TP, FP, FN, and TN. These abbreviations stand for true positives, false positives, false negatives, and true negatives, respectively. The first word (true/false) indicates whether or not the test result matched the presence of disease as measured by the gold standard. The second word (positive/negative) indicates what the test result was. True positives and true negatives are desirable; this means that the test result is correct and the higher these numbers, the better the test is. On the other hand, false positives and false negatives are undesirable.

Two important quantities that can be calculated from the true/false positives/negatives include the sensitivity and the specificity. The sensitivity is a measure of how powerful the test is in detecting disease. It is expressed as the ratio of positive test results over the number of total patients who had the disease:

On the other hand, the specificity is a measure of how good the test is at identifying patients who do not have the disease. It is expressed as the following:

These concepts can be confusing initially, so it may take some time and iterations before you get used to them, but the sensitivity and specificity are important concepts in biostatistics and machine learning.