GsymPoint: An R Package to Estimate the Generalized Symmetry Point, an Optimal Cut-off Point for Binary Classification in Continuous Diagnostic Tests

Abstract

In clinical practice, it is very useful to select an optimal cutpoint in the scale of a continuous biomarker or diagnostic test for classifying individuals as healthy or diseased. Several methods for choosing optimal cutpoints have been presented in the literature, depending on the ultimate goal. One of these methods, the generalized symmetry point, recently introduced, generalizes the symmetry point by incorporating the misclassification costs. Two statistical approaches have been proposed in the literature for estimating this optimal cutpoint and its associated sensitivity and specificity measures, a parametric method based on the generalized pivotal quantity and a nonparametric method based on empirical likelihood. In this paper, we introduce GsymPoint, an R package that implements these methods in a user-friendly environment, allowing the end-user to calculate the generalized symmetry point depending on the levels of certain categorical covariates. The practical use of this package is illustrated using three real biomedical datasets.

Confidence intervals for the symmetry point: an optimal cutpoint in continuous diagnostic tests

“…Bearing in mind the necessity of implementing the GPQ and EL techniques proposed in this paper in a user‐friendly environment to make them available to epidemiologists, clinicians and other professionals interested in them, we have recently developed an R package called GsymPoint that includes these techniques. This package is available at http://CRAN.R-project.org/package=GsymPoint.…”

Convergence Behavior of Optimal Cut-Off Points Derived from Receiver Operating Characteristics Curve Analysis: A Simulation Study

“…López-Ratón et al, focused on the symmetry point (also known as the point of equivalence) in optimal cut-off point determination [29,30]. The symmetry point is defined by the intersection of the ROC curve and the line y = 1 − x and can be interpreted as the point that maximizes simultaneously both types of correct classifications; that is, true-positives and true-negatives.…”