Predictive Accuracy of the PanCan Lung Cancer Risk Prediction Model -External Validation based on CT from the Danish Lung Cancer Screening Trial
Lung cancer risk models should be externally validated to test generalizability and clinical usefulness. The Danish Lung Cancer Screening Trial (DLCST) is a population-based prospective cohort study, used to assess the discriminative performances of the PanCan models.
From the DLCST database, 1,152 nodules from 718 participants were included. Parsimonious and full PanCan risk prediction models were applied to DLCST data, and also coefficients of the model were recalculated using DLCST data. Receiver operating characteristics (ROC) curves and area under the curve (AUC) were used to evaluate risk discrimination.
AUCs of 0.826–0.870 were found for DLCST data based on PanCan risk prediction models. In the DLCST, age and family history were significant predictors (p = 0.001 and p = 0.013). Female sex was not confirmed to be associated with higher risk of lung cancer; in fact opposing effects of sex were observed in the two cohorts. Thus, female sex appeared to lower the risk (p = 0.047 and p = 0.040) in the DLCST.
High risk discrimination was validated in the DLCST cohort, mainly determined by nodule size. Age and family history of lung cancer were significant predictors and could be included in the parsimonious model. Sex appears to be a less useful predictor.
• High accuracy in logistic modelling for lung cancer risk stratification of nodules.
• Lung cancer risk prediction is primarily based on size of pulmonary nodules.
• Nodule spiculation, age and family history of lung cancer are significant predictors.
• Sex does not appear to be a useful risk predictor.
KeywordsLung cancer screening Diagnostic imaging Computed tomography Risk Solitary pulmonary nodules
Area under the curve
British Columbia Cancer Agency
Danish Lung Cancer Screening Trial
National Lung Screening Trial
Pan-Canadian Early Detection of Lung Cancer Study
Receiver operating characteristics
The scientific guarantor of this publication is Asger Dirksen. The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article. Bram Van Ginneken works for Fraunhofer MEVIS in Bremen, Germany. This study has received funding by The Danish Ministry of Health and AstraZeneca. One of the authors has significant statistical expertise. Institutional review board approval was obtained. Written informed consent was obtained from all subjects (patients) in this study. Some study subjects have been previously reported in DLCST studies regarding lung cancer screening, lung function, lung density, airway segmentation, and visual assessment of emphysema, airway abnormalities and interstitial abnormalities in the Danish Lung Cancer Screening Trial. However, analyses of this study are new and have not been published before. All relevant references are disclosed. Methodology: prospective, diagnostic study, performed at two institutions.
- 2.Aberle DR, Adams AM, Berg CD et al (2011) Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med 5:395–409Google Scholar
- 7.Cassidy A, Myles JP, Liloglou T, Duffy SW, Field JK (2006) Defining high-risk individuals in a population-based molecular-epidemiological study of lung cancer. Int J Oncol 5:1295–1301Google Scholar
- 15.Tas F, Ciftci R, Kilic L, Karabulut S (2013) Age is a prognostic factor affecting survival in lung cancer patients. Oncol Lett 5:1507–1513Google Scholar