Application of risk prediction models to lung cancer screening: a review

Abstract

Globally, lung cancer is the leading cause of cancer death and is a major public health problem. Because lung cancer is usually diagnosed at an advanced stage, survival is generally poor. In recent decades, clinical advances have not led to marked improvements in outcomes. A recent advance of importance arose when the National Lung Screening Trial (NLST) findings indicated that low-dose computed tomography screening of high-risk individuals can lead to a lung cancer mortality reduction of 20%. NLST identified high-risk individuals using the following criteria: age 55 to 74 years; ≥30 pack-years of smoking; and number of years since smoking cessation ≤15 years. Medical screening is most effective when applied to high-risk individuals. The NLST criteria for high risk were practical for enrolling individuals into a clinical trial but are not optimal for risk estimation. Lung cancer risk prediction models are expected to be superior. Indeed, recently, 3 studies have provided quantitative evidence that selection of individuals for lung screening on the basis of estimates from high-quality risk prediction models is superior to using NLST criteria or similar criteria, such as the United States Preventive Services Task Force (USPSTF) criteria. Compared with NLST/USPSTF criteria, selection of individuals for screening using high-quality risk models should lead to fewer individuals being screened, more cancers being detected, and fewer false positives. More lives will be saved with greater cost-effectiveness. In this paper, we review methodological background for prediction modeling, existing lung cancer risk prediction models and some of their findings, and current issues in lung cancer risk prediction modeling and discuss future research.