Classification of diagnostic tests

A method is described for classifying diagnostic tests. It is valid for the large subgroup of tests for which the measured diagnostic variable has a normal distribution for the affected and non-affected individuals. It is based on placing each diagnostic test as a point on a two-dimensional graph, called a separation-asymmetry (SA) diagram, whose x-axis is the separation between the two normal distributions and whose y-axis is the logarithm of the ratio of their standard deviations. The SA diagram is partitioned into functional regions by curves of constant performance, as measured by the percent overlap between the two normal distributions. The concept of 'eccentricity' in a diagnostic test is defined, and the relationship between eccentricity and test validity is discussed. This quantity is also incorporated into SA diagrams, thus allowing a clinician to determine, by inspection, if a given diagnostic test positioned on an SA diagram is valid for clinical use. The logic engine used for calculating iso-performance curves is given, as well as the computer programs which utilize it. Possible ways of using this classification scheme are suggested.