Computed tomography screening for lung cancer is now being tested in a number of international trials. The long-term success of the approach in the future National Screening Programme is dependent upon identifying populations at sufficient risk of lung cancer that the benefit-harm ratio of the intervention is likely to be high. There are a number of lung cancer risk prediction models currently available. We review these, and demonstrate, using the Liverpool Lung Project risk prediction model as a case study, the potential for use of a risk prediction model in the design of a randomized trial of lung cancer screening and in the planning of a service screening program.