Comparison of discrimination performance of 11 lung cancer risk models for predicting lung cancer in a prospective cohort of screening-age adults from Germany followed over 17 years

•Randomized trials have demonstrated considerable reduction in lung cancer mortality by screening heavy smokers with LDCT.•Selecting people at highest risk for screening to optimize the benefit/harm ratio is a major challenge and several LC risk models have been established for this.•Evaluation of eleven risk models and LDCT trial criteria in prospective cohort showed that LCRAT, LCDRAT and Bach models perform best in predicting lung cancer incidence and mortality.