Radiol Artif Intell 2021 Nov 13;3(6):e210032. Epub 2021 Oct 13.
Departments of Computer Science (R.G., K.X., Y.H., B.A.L.) and Electrical and Computer Engineering (Y.T., Y.H., B.A.L.), Vanderbilt University, 400 24th Ave S, Featheringill Hall, Room 371, Nashville, TN 37235; and Departments of Radiology and Radiological Sciences (A.B.P., K.L.S.), Thoracic Surgery (S.S., S.D.), General Internal Medicine and Public Health (M.S.K.), Biomedical Informatics (M.S.K.), and Medicine, Division of Allergy, Pulmonary and Critical Care Medicine (P.P.M.), Vanderbilt University Medical Center, Nashville, Tenn.
Purpose: To develop a model to estimate lung cancer risk using lung cancer screening CT and clinical data elements (CDEs) without manual reading efforts.
Materials And Methods: Two screening cohorts were retrospectively studied: the National Lung Screening Trial (NLST; participants enrolled between August 2002 and April 2004) and the Vanderbilt Lung Screening Program (VLSP; participants enrolled between 2015 and 2018). Fivefold cross-validation using the NLST dataset was used for initial development and assessment of the co-learning model using whole CT scans and CDEs. Read More