Abstract
Background A baseline computed tomography (CT) scan for lung cancer (LC) screening may reveal information indicating that certain LC screening participants can be screened less, and instead require dedicated early cardiac and respiratory clinical input. We aimed to develop and validate competing death (CD) risk models using CT information to identify participants with a low LC risk and a high CD risk.
Methods Participant demographics and quantitative CT measures of LC, cardiovascular disease and chronic obstructive pulmonary disease were considered for deriving a logistic regression model for predicting 5-year CD risk using a sample from the National Lung Screening Trial (n=15 000). Multicentric Italian Lung Detection data were used to perform external validation (n=2287).
Results Our final CD model outperformed an external pre-scan model (CD Risk Assessment Tool) in both the derivation (area under the curve (AUC) 0.744 (95% CI 0.727–0.761) and 0.677 (95% CI 0.658–0.695), respectively) and validation cohorts (AUC 0.744 (95% CI 0.652–0.835) and 0.725 (95% CI 0.633–0.816), respectively). By also taking LC incidence risk into consideration, we suggested a risk threshold where a subgroup (6258/23 096 (27%)) was identified with a number needed to screen to detect one LC of 216 (versus 23 in the remainder of the cohort) and ratio of 5.41 CDs per LC case (versus 0.88). The respective values in the validation cohort subgroup (774/2287 (34%)) were 129 (versus 29) and 1.67 (versus 0.43).
Conclusions Evaluating both LC and CD risks post-scan may improve the efficiency of LC screening and facilitate the initiation of multidisciplinary trajectories among certain participants.
Abstract
Lung cancer CT screening participants with a relatively low risk of lung cancer incidence and a high risk of competing death can be identified by applying two respective post-scan risk models, and in turn may benefit from other personalised trajectories https://bit.ly/2ZDe62K
Footnotes
This article has supplementary material available from erj.ersjournals.com
An online risk calculator for the models described can be accessed at: https://docs.google.com/spreadsheets/d/1lU-UH1mxOmI-O--sNo8IhAgu2WLzRkcOQBCEm4rLdb4/edit?usp=sharing
Author contributions: A. Schreuder: conceived and designed the analysis, performed the analysis, and wrote the paper. C. Jacobs: conceived the analysis, supervised the analysis, collected the data, contributed data and analysis tools, and critically appraised the paper. N. Lessmann: conceived the analysis, collected the data, contributed data and analysis tools, and critically appraised the paper. M.J.M. Broeders: conceived the analysis, supervised the analysis and critically appraised the paper. M. Silva: conceived the analysis, collected the data, contributed data, and critically appraised the paper. I. Išgum: conceived the analysis, contributed analysis tools and critically appraised the paper. P.A. de Jong: conceived the analysis, contributed analysis tools and critically appraised the paper. M.M. van den Heuvel: conceived the analysis and critically appraised the paper. N. Sverzellati: conceived the analysis, collected the data, contributed data and critically appraised the paper. M. Prokop: conceived the analysis and critically appraised the paper. U. Pastorino: conceived the analysis, collected the data, contributed data and critically appraised the paper. C.M. Schaefer-Prokop: conceived the analysis and critically appraised the paper. B. van Ginneken: conceived the analysis, supervised the analysis, contributed analysis tools and critically appraised the paper.
Conflict of interest: A. Schreuder has nothing to disclose.
Conflict of interest: C. Jacobs reports grants from MeVis Medical Solutions AG, Bremen, Germany, outside the submitted work.
Conflict of interest: N. Lessmann has nothing to disclose.
Conflict of interest: M.J.M. Broeders has nothing to disclose.
Conflict of interest: M. Silva has nothing to disclose.
Conflict of interest: I. Išgum has nothing to disclose.
Conflict of interest: P.A. de Jong reports departmental research support from Philips Healthcare, during the conduct of the study.
Conflict of interest: M.M. van den Heuvel has nothing to disclose.
Conflict of interest: N. Sverzellati has nothing to disclose.
Conflict of interest: M. Prokop reports personal fees for lectures from Bracco, Bayer, Toshiba and Siemens, grants from Toshiba, other (departmental spin-off with no personal financial interest) from Thiroux, outside the submitted work.
Conflict of interest: U. Pastorino has nothing to disclose.
Conflict of interest: C.M. Schaefer-Prokop has nothing to disclose.
Conflict of interest: B. van Ginneken reports royalties from MeVis Medical Solutions and Delft Imaging Systems, and is co-founder and shareholder of Thirona, outside the submitted work.
- Received June 7, 2021.
- Accepted September 17, 2021.
- Copyright ©The authors 2022. For reproduction rights and permissions contact permissions{at}ersnet.org