作者: Holly Janes , Marshall D. Brown , Ying Huang , Margaret S. Pepe
关键词:
摘要: Despite the heightened interest in developing biomarkers predicting treatment response that are used to optimize patient decisions, there has been relatively little development of statistical methodology evaluate these markers. There is currently no unified framework for marker evaluation. This paper proposes a suite descriptive and inferential methods designed individual markers compare candidate An R software package developed which implements methods. Their utility illustrated breast cancer context, where evaluated their ability identify subset women who do not benefit from adjuvant chemotherapy can therefore avoid its toxicity.