Statistical Method and Design: Identify the Subgroups Who Would Have Nontrivial Overall Benefit in the National Lung Screening Trial (NLST)

• Activity Number: 459
• Type: Invited
• Date/Time: Wednesday, August 7, 2013 : 8:30 AM to 10:20 AM
• Sponsor: SSC
• Author(s): Ping Hu*+
• Companies: Division of Cancer Prevention, National Cancer Institute
• Keywords: lung cancer ; screening ; efficiency ; NLST ; personalized medicine ; reciprocal control

Abstract

In comparing a screening exam with a control via a randomized screening trial, the assessment of screening benefit is usually based on a specific study population. The screening benefit/harm is often varies by the subgroup of the study population. Many approaches have been proposed to access screening benefits/harms. However, none of prior papers have been proposed to efficiently choose sub-groups who would have desired overall benefits from intervention screening. In this study, we used the methods and procedures developed by Zhao, Wei, etc, (JASA, 2013) to identify subgroups that are most likely to benefit or at high risk of harm, and thus may lead to personalized medicine. The procedures developed in this study can be quite useful for planning future screening trials in which screening may be targeted towards those who would receive non-trivial benefits to compensate for the benefit, harm and cost of the new screening. Application is made to the data from the National Lung Screening Trial (NLST). In addition, the reciprocal control design for the randomized cancer screening trial in China is briefly discussed.