Abstract:
|
In practice, it is common to evaluate biomarkers in binary classification settings (e.g. non-cancer vs. cancer) where one or both main classes involve at least one subclass. For example, non-cancer class might consist of healthy subjects and benign cases, while cancer class might consist of subjects at early and late stages. The standard practice is pooling within each main class; i.e. all non-cancer sub-classes are pooled together to create a control group, and all cancer sub-classes are pooled together to create a case group. Based on the pooled data, the area under ROC curve (AUC) and other characteristics are estimated under binary classification for the purpose of biomarker evaluation. Despite the popularity of this pooling strategy in practice, its validity and implication in biomarker evaluation have never been carefully inspected. This presentation aims to investigate the impact of misuse of such pooling strategy on biomarker evaluation and to present our surprising and counter-intuitive findings. Furthermore, we present a new diagnostic framework as well as new accuracy measures for such settings to overcome the shortcomings possessed by pooling strategy.
|