A Review of the Estimation of Sensitivity and Specificity in the Context of Time‐Dependent Outcomes

Abstract

Time is an essential element in the field of survival analysis. Time to an event is essential in adjudicating diagnostic utility and determining the effectiveness of treatment. However, time‐to‐event outcomes—in a sense—are complicated to deal with, since they involve both a binary component, which is the outcome itself (death or recurrence) and a continuous component, which is the time for the occurrence of the outcome. In such scenarios, simpler metrics such as sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve are insufficient to establish the utility of a diagnostic marker. Given the above constraint, this review discusses established ways in which sensitivity and specificity can be determined and are therefore sufficient in establishing utility in the context of time‐dependent outcomes. This review also discusses how studies investigating the sensitivity and specificity of a diagnostic marker in the context of time‐dependent outcomes can be improved through the use of existing user‐friendly statistical software.Level of Evidence5Technical EfficacyStage 3