Skip to main content
Figure 3 | BMC Medical Informatics and Decision Making

Figure 3

From: Optimum binary cut-off threshold of a diagnostic test: comparison of different methods using Monte Carlo technique

Figure 3

The dependence of the cut-off levels and the associated sensitivities and specificities on P(D) for a representative example. The results of the Monte-Carlo computations of scenario 1 with 200 fictitious "individuals" are shown in dependence on pre-test probability P(D). The left column (panels a1, a2 and a3) shows the mean values of cut-off levels and the associated sensitivities and specificities; the right column (panels b1, b2 and b3) visualizes the respective SD values. The colours of the lines symbolize the three methods for determining optimum cut-off levels: blue, Mutual information method; red, Youden index method; black, LR method.

Back to article page