Predicting the future risk of lung cancer: development and validation of QCancer2 (10-year risk) lung model and evaluating the model performance of nine prediction models

Abstract Objectives To develop and validate the QCancer2 (10-year risk) lung model for estimation of future risk of lung cancer and to compare the model performance against other prediction models for lung cancer screening Design open cohort study using linked electronic health records (EHRs) from the QResearch database (1 January 2005 – 31 March 2020) Setting English primary care Participants 12.99 million patients aged 25-84 years were in the derivation cohort to develop the models and 4.14 million patients were in the validation cohort. All patients were free of lung cancer at baseline. Main outcome measure Incident lung cancer cases Methods There were two stages in this study. First, Cox proportional hazards models were used in the derivation cohort to update the QCancer (10-year risk) lung model in men and women for a 10-year predictive horizon, including two new predictors (pneumonia and venous thromboembolism) and more recent data. Discrimination measures (Harrell’s C, D statistic, and ) and calibration plots were used to evaluate model performance in the validation cohort by sex. Secondly, seven prediction models for lung cancer screening (LLP v2 , LLP v3 , LCRAT, PLCO M2012 , PLCO M2014 , Pittsburgh, and Bach) were selected to compare the model performance with the QCancer2 (10-year risk) lung model in two subgroups: (1) smokers and non-smokers aged 40-84 years and (2) ever-smokers aged 55-74 years. Results 73,380 incident lung cancer cases were identified in the derivation cohort and 22,838 in the validation cohort during follow-up. The updated models explained 65% of the variation in time to diagnosis of lung cancer in both sexes. Harrell’s C statistics were close to 0.9 (indicating excellent discrimination), and the D statistics were around 2.8. Compared with the original models, the discrimination measures in the updated models improved slightly in both sexes. Compared with other prediction models, the QCancer2 (10-year risk) lung model had the best model performance in discrimination, calibration, and net benefit across three predictive horizons (5, 6, and 10 years) in the two subgroups. Conclusion Developed and validated using large-scale EHRs, the QCancer2 (10-year risk) lung model can estimate the risk of an individual patient aged 25-84 years for up to 10 years. It has the best model performance among other prediction models. It has potential utility for risk stratification of the English primary care population and selection of eligible people at high risk for the targeted lung health check programme or lung cancer screening. What is already known on this topic Using risk prediction models to stratify people at the population level and selecting those at the highest risks is an efficient and cost-effective strategy for screening programmes. It avoids waste of resources in screening patients at low risk. An ideal prediction model should have excellent discrimination and calibration in the target population. The Liverpool Lung Project (LLP v2 ) and the Prostate Lung Colorectal and Ovarian (PLCO M2012 ) models had only moderate discrimination and were not well-calibrated when externally validated using the Clinical Practice Research Datalink (CPRD) data for the English primary care population. What this study adds Developed and validated using robust statistical methodologies, the QCancer2 (10-year risk) lung model shows excellent discrimination and calibration in both sexes. It can estimate an individual adult patient’s risk for each year of follow-up, for up to 10 years. The QCancer2 (10-year risk) lung model has the best model performance in discrimination and calibration when compared with the other eight models (QCancer (10-year risk), LLP v2 , LLP v3 , LCRAT, PLCO M2012 , PLCO M2014 , Pittsburgh, and Bach) in three predictive horizons (5/6/10 years) and two sub-populations (smokers and non-smokers aged 40-84 years and ever-smokers aged 55-74 years). The QCancer2 (10-year risk) lung model can be applied to the English primary care population to select eligible patients for the Targeted Lung Health Check programme or lung cancer screening using low dose CT.