Machine Learning Prediction of Progression in Forced Expiratory Volume in 1 Second in the COPDGene® Study

Machine learning for screening of at-risk, mild and moderate COPD patients at risk of FEV1 decline: results from COPDGene and SPIROMICS

Purpose: The purpose of this study was to train and validate machine learning models for predicting rapid decline of forced expiratory volume in 1 s (FEV1) in individuals with a smoking history at-risk-for chronic obstructive pulmonary disease (COPD), Global Initiative for Chronic Obstructive Lung Disease (GOLD 0), or with mild-to-moderate (GOLD 1-2) COPD. We trained multiple models to predict rapid FEV1 decline using demographic, clinical and radiologic biomarker data. Training and internal validation data were obtained from the COPDGene study and prediction models were validated against the SPIROMICS cohort. Methods: We used GOLD 0-2 participants (n = 3,821) from COPDGene (60.0 ± 8.8 years, 49.9% male) for variable selection and model training. Accelerated lung function decline was defined as a mean drop in FEV1% predicted of > 1.5%/year at 5-year follow-up. We built logistic regression models predicting accelerated decline based on 22 chest CT imaging biomarker, pulmonary function, symptom, and demographic features. Models were validated using n = 885 SPIROMICS subjects (63.6 ± 8.6 years, 47.8% male). Results: The most important variables for predicting FEV1 decline in GOLD 0 participants were bronchodilator responsiveness (BDR), post bronchodilator FEV1% predicted (FEV1.pp.post), and CT-derived expiratory lung volume; among GOLD 1 and 2 subjects, they were BDR, age, and PRMlower lobes fSAD. In the validation cohort, GOLD 0 and GOLD 1-2 full variable models had significant predictive performance with AUCs of 0.620 ± 0.081 (p = 0.041) and 0.640 ± 0.059 (p < 0.001). Subjects with higher model-derived risk scores had significantly greater odds of FEV1 decline than those with lower scores. Conclusion: Predicting FEV1 decline in at-risk patients remains challenging but a combination of clinical, physiologic and imaging variables provided the best performance across two COPD cohorts.

Predicting COPD Progression in Current and Former Smokers Using a Joint Model for Forced Expiratory Volume in 1 Second and Forced Expiratory Volume in 1 Second to Forced Vital Capacity Ratio

Understanding baseline characteristics that can predict the progression of lung disease such as chronic obstructive pulmonary disease (COPD) for current or former smokers may allow for therapeutic intervention, particularly for individuals at high risk of rapid disease progression or transition from non-COPD to COPD. Classic diagnostic criteria for COPD and disease severity such as the Global Initiative for Chronic Obstructive Lung Disease document are based on forced expiratory volume in 1 second (FEV1) and FEV1 to forced vital capacity (FVC) ratio. Modeling changes in these outcomes jointly is beneficial given that they are correlated, and they are both required for specific disease classifications. Here, linear mixed models were used to model changes in FEV1 and FEV1/FVC jointly for 5- and 10-year intervals, using important baseline predictors to better understand the factors that affect disease progression. Participants with predicted loss of FEV1 and/or FEV1/FVC of at least 5% tended to have more emphysema, higher functional residual capacity, higher airway wall thickness as measured by Pi10, lower FVC to total lung capacity ratio and a lower body mass index at baseline, all relative to overall cohort averages. The model developed can be used to predict progression for any potential COPD individual, based on demographic, symptom, computed tomography, and comorbidity variables.