Statistical Evaluation of Medical Tests

In this review, we present an overview of the main aspects related to statistical evaluation medical tests for diagnosis and prognosis. Measures diagnostic performance binary tests, such as sensitivity, specificity, predictive values, are introduced, extensions case continuous-outcome detailed. Special focus is placed on receiver operating characteristic (ROC) curve its estimation, with emphasis topic covariate adjustment. The extension time-dependent ROC curves evaluating prognostic accuracy also touched upon. We apply several approaches described a data set derived from study aimed evaluate ability homeostasis model assessment insulin resistance (HOMA-IR) levels identify individuals at high cardio-metabolic risk how discriminatory might be influenced by age gender. outline software available implementation methods.