Abstract:
|
This paper focuses on quantifying and estimating the predictive accuracy of prognostic models for time-to-event outcomes with competing events. We consider the time-dependent discrimination and calibration metrics including the Receiver Operating Characteristics (ROC) curve and the Brier score in the context of competing risks. To address censoring, we propose a unified estimation framework for both discrimination and calibration measures, by weighting the censored subjects using non-parametrically estimated conditional probability of the event of interest given the observed data. We demonstrated through simulations that the proposed estimator is unbiased, efficient and robust against model misspecification in comparison to other published methods in the literature. In addition, proposed method can be extended to time-dependent predictive accuracy metrics constructed from a general class of loss functions. We illustrate the methodology with a data set from the African American Study of Kidney Disease and Hypertension.
|