A modified ROC analysis for the selection of cut-off values and the definition of intermediate results of serodiagnostic tests.

A total number of 50 sera from clinically confirmed cases of canine Borrelia (B.) burgdorferi infection and 44 negative control sera were tested with a B. burgdorferi specific antibody ELISA. The data were submitted to the 'two-graph receiver operating characteristic' (TG-ROC) analysis which is a plot of the test sensitivity (Se) and specificity (Sp) against the threshold (cut-off) value assuming the latter to be an independent variable. Thus, in contrast to the conventional ROC analysis, valid pairs of Se and Sp can be read for pre-assigned threshold values directly from the TG-ROC plots. A cut-off that realises equal test parameters (Se = Sp = theta 0 (theta-zero)) can be obtained as the intersection point of the two graphs. Since the value for theta 0 is below a preselected accuracy level (95% or 90%), two cut-off values are selected that represent the bounds of an 'intermediate range' (IR). IR can be considered as a 'borderline' range for the clinical interpretation of test results. The proportion of the measurement range (MR) that gives unambiguous test results can be expressed using IR as the 'valid range proportion' (VRP = (MR-IR)/MR). VRP and theta 0 are useful parameters for test comparison since they do not depend upon the selection of a single cut-off point. In addition, the selection of cut-off values is supported by graphical displays of efficiency, Youden's index and likelihood ratios which can be considered as functions of the pre-assigned cut-off value. TG-ROC was derived as a user-defined template for a commercially available spreadsheet programme (MS-EXCEL, Microsoft).