Uncertainty of Measurement and Diagnostic Accuracy Measures
This Demonstration compares various diagnostic accuracy measures of two diagnostic tests. The two tests measure the same measurand, for normally distributed healthy and diseased populations, for various values of the prevalence of the disease, of the mean and standard deviation of the populations, and of the uncertainty of measurement of the tests. A normal distribution of the uncertainty is assumed. The mean and the standard deviation of each population and the uncertainty of each test are measured in arbitrary units. The measures compared are the positive prognostic value (PPV), the negative prognostic value (NPV), the (diagnostic) odds ratio (OR), the likelihood ratio for a positive result (LR+), and the likelihood ratio for a negative result (LR-). The measures are calculated versus the sensitivity or the specificity of each test. That can be selected by clicking the respective button. The types of plot are: both measures (first test: blue plot, second test: orange plot), partial derivatives of both measures with respect to uncertainty (first test: blue plot, second test: orange plot), difference, and ratio of the two measures.
In addition to the receiver operating characteristic (ROC) curves, various measures are used in the evaluation of the clinical accuracy of a diagnostic test applied to a diseased or a nondiseased population. They can be calculated versus the sensitivity or the specificity of the test. Sensitivity is the fraction of the diseased population with a positive test, while specificity is the fraction of the nondiseased population with a negative test. In addition, if we denote by the sensitivity, the specificity, and the prevalence, we have:
, , , , .
This Demonstration could be useful in evaluating the maximum medically permissible uncertainty of measurement of a diagnostic test. For example, in the thumbnail and the snapshots the populations data describes a bimodal distribution of serum glucose measurements with a nondiabetic and a diabetic population (Lim et al. 2002). The first test has a state-of-the-art performance, while the second test has a greater uncertainty.
 T. O. Lim, R. Bakri, Z. Morad, and M. A. Hamid, "Bimodality in Blood Glucose Distribution: Is It Universal?," Diabetes Care,25(12), 2002 pp. 2212–2217.