Skip to Main Content

An official website of the United States government

About this Publication
Combining pulmonary and cardiac computed tomography biomarkers for disease-specific risk modelling in lung cancer screening.
Pubmed ID
33574075 (View this publication on the PubMed website)
Digital Object Identifier
Eur Respir J. 2021 Feb 11
Schreuder A, Jacobs C, Lessmann N, Broeders MJM, Silva M, Išgum I, de Jong PA, Sverzellati N, Prokop M, Pastorino U, Schaefer-Prokop CM, van Ginneken B
  • Dept of Radiology, Nuclear Medicine, and Anatomy, Radboud University Medical Center, Nijmegen, The Netherlands
  • Dept of Radiology, Nuclear Medicine, and Anatomy, Radboud University Medical Center, Nijmegen, The Netherlands.
  • Radboud University Medical Center, Radboud Institute for Health Sciences, Nijmegen, The Netherlands.
  • Unit of Thoracic Surgery, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy.
  • Image Sciences Institute, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Dept of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Section of Radiology, Unit of Surgical Sciences, Dept of Medicine and Surgery (DiMeC), University of Parma, Parma, Italy.

OBJECTIVES: Combined assessment of cardiovascular disease (CVD), chronic obstructive pulmonary disease (COPD), and lung cancer (LC) may improve the effectiveness of LC screening in smokers. The aims were to derive and assess risk models for predicting LC incidence, CVD mortality, and COPD mortality by combining quantitative CT measures from each disease, 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=15 000). 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 which contributed to all final models. Nodule features were crucial for LC incidence predictions but did not contribute to CVD and COPD mortality prediction. In the derivation cohort, the LC incidence CT model had a 5-year area under the receiver operating characteristic curve (AUC) of 82·5% (95% confidence interval=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 LC 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 LC risk prediction accuracy from 3 years' onwards. Self-reported patient characteristics may not be of added predictive value when CT information is available.

Related CDAS Studies
Related CDAS Projects