Search

Motivated by a study of acute kidney injury, we consider the setting of biomarker studies involving patients at multiple centers where the goal is to develop a biomarker combination for diagnosis, prognosis, or screening. As biomarker studies become larger, this type of data structure will be encountered more frequently. In the presence of multiple centers, one way to assess the predictive capacity of a given combination is to consider the center-adjusted AUC (aAUC), a summary of the ability of the combination to discriminate between cases and controls in each center. Rather than using a general method, such as logistic regression, to construct the biomarker combination, we propose directly maximizing the aAUC. Furthermore, it may be desirable to have a biomarker combination with similar performance across centers. To that end, we allow for penalization of the variability in the center-specific AUCs. We demonstrate desirable asymptotic properties of the resulting combinations. Simulations provide small-sample evidence that maximizing the aAUC can lead to combinations with improved performance. We also use simulated data to illustrate the utility of constructing combinations by maximizing the aAUC while penalizing variability. Finally, we apply these methods to data from the study of acute kidney injury., Comment: 31 pages (including appendices)

We consider variable selection in competing risks regression for multi-center data. Our research is motivated by deceased donor kidney transplants, from which recipients would experience graft failure, death with functioning graft (DWFG), or graft survival. The occurrence of DWFG precludes graft failure from happening and therefore is a competing risk. Data within a transplant center may be correlated due to a latent center effect, such as varying patient populations, surgical techniques, and patient management. The proportional subdistribution hazard (PSH) model has been frequently used in the regression analysis of competing risks data. Two of its extensions, the stratified and the marginal PSH models, can be applied to multi-center data to account for the center effect. In this paper, we propose penalization strategies for the two models, primarily to select important variables and estimate their effects whereas correlations within centers serve as a nuisance. Simulations demonstrate good performance and computational efficiency for the proposed methods. It is further assessed using an analysis of data from the United Network of Organ Sharing., Comment: 24 pages