A Class of Inference Procedure for Comparing Risk Scoring Systems Beyond the Receiver Operating Characteristic Curve Paradigm in Survival Analysis

• Activity Number: 55
• Type: Invited
• Date/Time: Sunday, July 31, 2011 : 4:00 PM to 5:50 PM
• Sponsor: Biometrics Section
• Author(s): Hajime Uno*+ and Lu Tian and Tianxi Cai and LJ Wei
• Companies: Dana-Farber Cancer Institute and Stanford University and Harvard University and Harvard University
• Keywords: Area under the ROC curve ; C-statistic ; Cox's regression ; Integrated discrimination improvement ; Net reclassification improvement ; Risk prediction

Abstract

Risk prediction procedures can be quite useful for the patient's treatment selection, prevention strategy, or disease management in evidence-based medicine. Often, potentially important new predictors are available in addition to the conventional markers. The question is how to quantify the improvement from the new markers for prediction of the patient's risk in order to aid cost-benefit decisions. The standard method, using the area under the receiver operating characteristic curve (AUROC), to measure the added value may not be sensitive enough to capture incremental improvements from the new markers. Recently, some novel alternatives to AUROC, such as integrated discrimination improvement, net reclassification improvement, were proposed. We consider a class of measures for evaluating the incremental values of new markers, which includes the above two as special cases. We also present a unified procedure for making inferences about these measures with censored event time data. The large sample properties of our procedures are theoretically justified. The new proposal is illustrated with data from a cancer study to evaluate a new gene score for prediction of the patient's survival.