CT Imaging With Machine Learning for Predicting Progression to COPD in Individuals at Risk

Background Identifying individuals at risk of progressing to COPD may allow for initiation of treatment to potentially slow the progression of the disease or the selection of subgroups for discovery of novel interventions. Research Question Does the addition of CT imaging features, texture-based radiomic features, and established quantitative CT scan to conventional risk factors improve the performance for predicting progression to COPD in individuals who smoke with machine learning? Study Design and Methods Participants at risk (individuals who currently or formerly smoked, without COPD) from the Canadian Cohort Obstructive Lung Disease (CanCOLD) population-based study underwent CT imaging at baseline and spirometry at baseline and follow-up. Various combinations of CT scan features, texture-based CT scan radiomics (n = 95), and established quantitative CT scan (n = 8), as well as demographic (n = 5) and spirometry (n = 3) measurements, with machine learning algorithms were evaluated to predict progression to COPD. Performance metrics included the area under the receiver operating characteristic curve (AUC) to evaluate the models. DeLong test was used to compare the performance of the models. Results Among the 294 at-risk participants who were evaluated (mean age, 65.6 ± 9.2 years; 42% female; mean pack-years, 17.9 ± 18.7), 52 participants (23.7%) in the training data set and 17 participants (23.0%) in the testing data set progressed to spirometric COPD at follow-up (2.5 ± 0.9 years from baseline). Compared with machine learning models with demographics alone (AUC, 0.649), the addition of CT imaging features to demographics (AUC, 0.730; P < .05) or CT imaging features and spirometry to demographics (AUC, 0.877; P < .05) significantly improved the performance for predicting progression to COPD. Interpretation Heterogeneous structural changes occur in the lungs of individuals at risk that can be quantified using CT imaging features, and evaluation of these features together with conventional risk factors improves performance for predicting progression to COPD. Identifying individuals at risk of progressing to COPD may allow for initiation of treatment to potentially slow the progression of the disease or the selection of subgroups for discovery of novel interventions. Does the addition of CT imaging features, texture-based radiomic features, and established quantitative CT scan to conventional risk factors improve the performance for predicting progression to COPD in individuals who smoke with machine learning? Participants at risk (individuals who currently or formerly smoked, without COPD) from the Canadian Cohort Obstructive Lung Disease (CanCOLD) population-based study underwent CT imaging at baseline and spirometry at baseline and follow-up. Various combinations of CT scan features, texture-based CT scan radiomics (n = 95), and established quantitative CT scan (n = 8), as well as demographic (n = 5) and spirometry (n = 3) measurements, with machine learning algorithms were evaluated to predict progression to COPD. Performance metrics included the area under the receiver operating characteristic curve (AUC) to evaluate the models. DeLong test was used to compare the performance of the models. Among the 294 at-risk participants who were evaluated (mean age, 65.6 ± 9.2 years; 42% female; mean pack-years, 17.9 ± 18.7), 52 participants (23.7%) in the training data set and 17 participants (23.0%) in the testing data set progressed to spirometric COPD at follow-up (2.5 ± 0.9 years from baseline). Compared with machine learning models with demographics alone (AUC, 0.649), the addition of CT imaging features to demographics (AUC, 0.730; P < .05) or CT imaging features and spirometry to demographics (AUC, 0.877; P < .05) significantly improved the performance for predicting progression to COPD. Heterogeneous structural changes occur in the lungs of individuals at risk that can be quantified using CT imaging features, and evaluation of these features together with conventional risk factors improves performance for predicting progression to COPD. Seeing and Not Seeing Is Believing: Predicting COPD With Lung ImagingCHESTVol. 164Issue 5PreviewCOPD affects approximately 29 million people in the United States and is the third leading cause of death.1 Individuals with COPD experience chronic respiratory symptoms, exercise intolerance, and progression of their lung function. Identifying individuals at risk of developing COPD is crucial to prevent disease and improve patient care. Various approaches are used to assess the risk of developing COPD, including spirometry; history of smoking, symptoms, and exacerbations; and genetic factors. For instance, people who never reached peak lung function in young adulthood are at risk of developing COPD2; similarly, individuals exposed to cigarette smoking for a long term and individuals who smoke with repeated acute respiratory exacerbations may develop COPD. Full-Text PDF