Unified ROC Curve Estimator for Diagnosis and Prognosis Studies: The sMSROC Package

The binary classification problem is a hot topic in Statistics. Its close relationship with the diagnosis and the prognosis of diseases makes it crucial in biomedical research. In this context, it is important to identify biomarkers that may help to classify individuals into different classes, for example, diseased vs. not diseased. The Receiver Operating-Characteristic (ROC) curve is a graphical tool commonly used to assess the accuracy of such classification. Given the diverse nature of diagnosis and prognosis problems, the ROC curve estimation has been tackled from separate perspectives in each setting. The Two-stages Mixed-Subjects (sMS) ROC curve estimator fits both scenarios. Besides, it can handle data with missing or incomplete outcome values. This paper introduces the R package sMSROC which implements the sMS ROC estimator, and includes tools that may support researchers in their decision making. Its practical application is illustrated on three real -world datasets.