Ground Glass Lesions on Chest Imaging: Evaluation of Reported Incidence in Cancer Patients Using Natural Language Processing

Abstract

Ground glass opacities (GGOs) on computed tomography (CT) have gained significant recent attention, with unclear incidence and epidemiologic patterns. Natural language processing (NLP) is a powerful computing tool that collects variables from unstructured data fields. Our objective was to characterize trends of GGO detection using NLP. Patients were identified at a large quaternary referral center who underwent chest CT from 2000 to 2016 via query of institutional databases. NLP was used to identify imaging reports with GGOs and to obtain additional demographic data. Incidence of reported GGOs was tracked over time. Multivariate regression was used to identify predictors of GGOs identified on chest CT. A total of 244,391 chest CTs were included, with 35,386 (14.5%) revealing GGOs. There was a significant relationship between advancing year of chest CT and likelihood of reported GGOs (p < 0.001). GGOs were more likely to occur in older subjects (60.5 vs 58.5 years, p < 0.001), males (54.6% vs 51.5%, p < 0.001), and nonwhite races (21.2% Asian, 15.6% Hispanic, 14.4% black, 14.0% white; p < 0.001). Certain occupational histories predicted more frequent GGOs (p < 0.001), including transportation labor (47.4%), metal workers (42.3%), iron workers (33.3%), cabinetry (32.6%), and foremen (29.6%). Multivariate regression revealed age, sex, nonsmokers, increasing year of chest CT, and race as significant independent predictors of identifying GGOs. NLP explored a large cohort of patients who underwent chest CT over the study period. Demographic features predicting reported GGOs include age, sex, race, and occupation. GGO recognition continues to increase with time, and further studies investigating etiology and prognostic implications are necessary.