Lung Cancer Risk Prediction Model

The National Lung Screening Trial (NLST) uses risk factors for lung cancer (e.g., ≥30 pack-years of smoking and <15 years since quitting) as selection criteria for lung-cancer screening. Researchers from Canada and the US modified their Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial criteria to ensure applicability to NLST data, and validated the model (PLCO_M2012) with data from the 80,375 persons in the PLCO control and intervention groups who had ever smoked. In the validation data set, 14,144 of 37,332 persons (37.9%) met NLST criteria. For comparison, 14,144 highest-risk persons were considered positive (eligible for screening) according to PLCO_M2012 criteria.

The PLCO trial added factors as level of education, family history of lung cancer, and COPD status, in addition to history and duration of smoking and quit time. As compared with NLST criteria, PLCO_M2012 criteria had significantly improved sensitivity and positive predictive value without loss of specificity. The new PLCO model found 81 more patients for screening who ended up having a diagnosis of lung cancer who were not caught by NLST criteria. The PLCO model is a work in progress toward refining lung cancer risk and screening criteria, and hopefully will lead to earlier detection of lung cancer.

Reference

Tammemagi MC, Katki, HA, Hocking, WG, et al. Selection criteria for lung cancer screening. N Engl J Med 2013; 368: 728-736.