Combining pulmonary and cardiac computed tomography biomarkers for disease-specific risk modelling in lung cancer screening
Schreuder, Anton; Jacobs, Colin; Lessmann, Nikolas; Broeders, Mireille J.M.; Silva, Mario; Išgum, Ivana; de Jong, Pim A.; Sverzellati, Nicola; Prokop, Mathias; Pastorino, Ugo; Schaefer-Prokop, Cornelia M.; van Ginneken, Bram
(2021) European Respiratory Journal, volume 58, issue 3
(Article)
Abstract
Objectives Combined assessment of cardiovascular disease (CVD), COPD and lung cancer may improve the effectiveness of lung cancer screening in smokers. The aims were to derive and assess risk models for predicting lung cancer incidence, CVD mortality and COPD mortality by combining quantitative computed tomography (CT) measures from each disease,
... read more
and to quantify the added predictive benefit of self-reported patient characteristics given the availability of a CT scan. Methods A survey model (patient characteristics only), CT model (CT information only) and final model (all variables) were derived for each outcome using parsimonious Cox regression on a sample from the National Lung Screening Trial (n=15000). Validation was performed using Multicentric Italian Lung Detection data (n=2287). Time-dependent measures of model discrimination and calibration are reported. Results Age, mean lung density, emphysema score, bronchial wall thickness and aorta calcium volume are variables that contributed to all final models. Nodule features were crucial for lung cancer incidence predictions but did not contribute to CVD and COPD mortality prediction. In the derivation cohort, the lung cancer incidence CT model had a 5-year area under the receiver operating characteristic curve of 82.5% (95% CI 80.9-84.0%), significantly inferior to that of the final model (84.0%, 82.6-85.5%). However, the addition of patient characteristics did not improve the lung cancer incidence model performance in the validation cohort (CT model 80.1%, 74.2-86.0%; final model 79.9%, 73.9-85.8%). Similarly, the final CVD mortality model outperformed the other two models in the derivation cohort (survey model 74.9%, 72.7-77.1%; CT model 76.3%, 74.1-78.5%; final model 79.1%, 77.0-81.2%), but not the validation cohort (survey model 74.8%, 62.2-87.5%; CT model 72.1%, 61.1-83.2%; final model 72.2%, 60.4-84.0%). Combining patient characteristics and CT measures provided the largest increase in accuracy for the COPD mortality final model (92.3%, 90.1-94.5%) compared to either other model individually (survey model 87.5%, 84.3-90.6%; CT model 87.9%, 84.8-91.0%), but no external validation was performed due to a very low event frequency. Conclusions CT measures of CVD and COPD provides small but reproducible improvements to nodule-based lung cancer risk prediction accuracy from 3 years onwards. Self-reported patient characteristics may not be of added predictive value when CT information is available.
show less
Download/Full Text
The full text of this publication is not available.
Keywords: Biomarkers, Early Detection of Cancer, Humans, Lung Neoplasms/diagnostic imaging, Lung/diagnostic imaging, Tomography, X-Ray Computed, Pulmonary and Respiratory Medicine, Journal Article
ISSN: 0903-1936
Publisher: European Respiratory Society
Note: Funding Information: Acknowledgements: The authors thank Gabriel Humpire Mamani (Radboud University Medical Center, Nijmegen, the Netherlands), Jean-Paul Charbonnier and Leticia Gallardo-Estrella (Thirona, Nijmegen) for their technical support in obtaining quantitative CT measures, and Claudio Jacomelli and Frederica Sabia (Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy) for extracting the requested Multicentric Italian Lung Detection (MILD) trial data. The authors also thank the MILD research teams for access to MILD data, and the National Cancer Institute (NCI) for access to the NCI’s data collected by the National Lung Screening Trial under project number NLST-437. The statements contained herein are solely those of the authors and do not represent or imply concurrence or endorsement by NCI. Funding Information: Conflict of interest: A. Schreuder has nothing to disclose. C. Jacobs reports grants from MeVis Medical Solutions AG, Bremen, Germany, outside the submitted work. N. Lessmann has nothing to disclose. M.J.M. Broeders has nothing to disclose. M. Silva has nothing to disclose. I. Išgum has nothing to disclose. P.A. de Jong reports other (research support to institution) from Philips Healthcare, during the conduct of the study. N. Sverzellati has nothing to disclose. M. Prokop reports personal fees for lectures from Bracco, Bayer, Toshiba and Siemens, grants from Toshiba, other (department spin-off) from Thiroux, outside the submitted work. U. Pastorino has nothing to disclose. C.M. Schaefer-Prokop has nothing to disclose. B. van Ginneken reports other (co-founder/shareholder) from Thirona, grants/royalties from Mevis Medical Solutions and Delft Imaging Systems, outside the submitted work. Publisher Copyright: Copyright © The authors 2021.
(Peer reviewed)