Anton Schreuder1, Colin Jacobs2, Nikolas Lessmann2, Mireille J M Broeders3,4, Mario Silva5,6, Ivana Išgum7,8, Pim A de Jong9,10, Michel M van den Heuvel11, Nicola Sverzellati6, Mathias Prokop2, Ugo Pastorino5, Cornelia M Schaefer-Prokop2,12, Bram van Ginneken2,13. 1. Dept of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands antoniusschreuder@gmail.com. 2. Dept of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands. 3. Radboud Institute for Health Sciences, Radboud University Medical Center, Nijmegen, The Netherlands. 4. Dutch Expert Centre for Screening, Nijmegen, The Netherlands. 5. Unit of Thoracic Surgery, Fondazione IRCCS Istituto Nazionale dei Tumori, Milan, Italy. 6. Section of Radiology, Unit of Surgical Sciences, Dept of Medicine and Surgery (DiMeC), University of Parma, Parma, Italy. 7. Dept of Biomedical Engineering and Physics, Amsterdam UMC - Location AMC, Amsterdam, The Netherlands. 8. Dept of Radiology and Nuclear Medicine, Amsterdam UMC - Location AMC, Amsterdam, The Netherlands. 9. Dept of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands. 10. Utrecht University, Utrecht, The Netherlands. 11. Dept of Respiratory Diseases, Radboud University Medical Center, Nijmegen, The Netherlands. 12. Dept of Radiology, Meander Medisch Centrum, Amersfoort, The Netherlands. 13. Fraunhofer MEVIS, Bremen, Germany.
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.
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.