2019/10/04 by Allison Meisner, Meisner, Allison, Marco Carone +5
Mathematics · #Statistical Methods in Clinical Trials #Statistical Methods and Inference #Statistical Methods and Bayesian Inference
paper · pdf · doi:10.48550/arxiv.1910.02087
Biomarkers abound in many areas of clinical research, and often investigators\nare interested in combining them for diagnosis, prognosis, or screening. In\nmany applications, the true positive rate for a biomarker combination at a\nprespecified, clinically acceptable false positive rate is the most relevant\nmeasure of predictive capacity. We propose a distribution-free method for\nconstructing biomarker combinations by maximizing the true positive rate while\nconstraining the false positive rate. Theoretical results demonstrate desirable\nproperties of biomarker combinations produced by the new method. In\nsimulations, the biomarker combination provided by our method demonstrated\nimproved operating characteristics in a variety of scenarios when compared with\nalternative methods for constructing biomarker combinations.\n