Maldonado F, Varghese C, Rajagopalan S, Duan F, Balar AB, Lakhani DA, Antic SL, Massion PP, Johnson TF, Karwoski RA, Robb RA, Bartholmai BJ, and Peikert T
Introduction: Implementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use of cross-sectional imaging are resulting in the identification of many screen- and incidentally detected indeterminate pulmonary nodules. While the management of nodules with low or high pre-test probability of malignancy is relatively straightforward, those with intermediate pre-test probability commonly require advanced imaging or biopsy. Noninvasive risk stratification tools are highly desirable., Methods: We previously developed the BRODERS classifier (Benign versus aggRessive nODule Evaluation using Radiomic Stratification), a conventional predictive radiomic model based on eight imaging features capturing nodule location, shape, size, texture and surface characteristics. Herein we report its external validation using a dataset of incidentally identified lung nodules (Vanderbilt University Lung Nodule Registry) in comparison to the Brock model. Area under the curve (AUC), as well as sensitivity, specificity, negative and positive predictive values were calculated., Results: For the entire Vanderbilt validation set (n=170, 54% malignant), the AUC was 0.87 (95% CI 0.81-0.92) for the Brock model and 0.90 (95% CI 0.85-0.94) for the BRODERS model. Using the optimal cut-off determined by Youden's index, the sensitivity was 92.3%, the specificity was 62.0%, the positive (PPV) and negative predictive values (NPV) were 73.7% and 87.5%, respectively. For nodules with intermediate pre-test probability of malignancy, Brock score of 5-65% (n=97), the sensitivity and specificity were 94% and 46%, respectively, the PPV was 78.4% and the NPV was 79.2%., Conclusions: The BRODERS radiomic predictive model performs well on an independent dataset and may facilitate the management of indeterminate pulmonary nodules., Competing Interests: Conflict of interest: F. Maldonado reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110), during the conduct of the study; and holds intellectual property rights as an inventor of the CANARY software and BRODERS classifier, but does not receive any financial relationships regarding this software. Conflict of interest: C. Varghese has nothing to disclose. Conflict of interest: S. Rajagopalan reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110 to F. Maldonado), during the conduct of the study; CALIPER software is licensed to Imbio, LLC, from whom The Mayo Clinic and B.J. Bartholmai receive royalties related to CALIPER (also known as Imbio Lung Texture Analysis, LTA); and S. Rajagoplan holds intellectual property rights as an inventor of the CANARY software and BRODERS classifier, but does not receive any financial relationships regarding this software. Conflict of interest: F. Duan reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110 to F. Maldonado), during the conduct of the study. Conflict of interest: A.B. Balar has nothing to disclose. Conflict of interest: D.A. Lakhani has nothing to disclose. Conflict of interest: S.L. Antic has nothing to disclose. Conflict of interest: P.P. Massion has nothing to disclose. Conflict of interest: T.F. Johnson reports grants from Department of Defense, during the conduct of the study. Conflict of interest: R.A. Karwoski reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110 to F. Maldonado), during the conduct of the study; CALIPER software is licensed to Imbio, LLC, from whom The Mayo Clinic and B.J. Bartholmai receive royalties related to CALIPER (also known as Imbio Lung Texture Analysis, LTA); and R.A. Karwoski holds intellectual property rights as an inventor of the CANARY software and BRODERS classifier, but does not receive any financial relationships regarding this software. Conflict of interest: R.A. Robb reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110 to F. Maldonado), during the conduct of the study; CALIPER software is licensed to Imbio, LLC, from whom The Mayo Clinic and B.J. Bartholmai receive royalties related to CALIPER (also known as Imbio Lung Texture Analysis, LTA); and R.A. Robb holds intellectual property rights as an inventor of the CANARY software and BRODERS classifier, but does not receive any financial relationships regarding this software. Conflict of interest: B.J. Bartholmai reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110 to F. Maldonado), during the conduct of the study; personal fees for advisory board work from Promedior, LLC, outside the submitted work; CALIPER software is licensed to Imbio, LLC, from whom The Mayo Clinic and B.J. Bartholmai receive royalties related to CALIPER (also known as Imbio Lung Texture Analysis, LTA); and B.J. Bartholmai holds intellectual property rights as an inventor of the CANARY software and BRODERS classifier, but does not receive any financial relationships regarding this software. Conflict of interest: T. Peikert reports grants from Department of Defense (Lung Cancer Research Program under award number W81XWH-15-1-0110 to F. Maldonado), during the conduct of the study; fees paid to institution for advisory board work from AstraZeneca and Novocure, outside the submitted work; and holds intellectual property rights as an inventor of the CANARY software and BRODERS classifier, but does not receive any financial relationships regarding this software., (Copyright ©ERS 2021.)