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

Jennifer M Wang; Wassim W Labaki; Susan Murray; Fernando J Martinez; Jeffrey L Curtis; Eric A Hoffman; Sundaresh Ram; Alexander J Bell; Craig J Galban; MeiLan K Han; Charles Hatt

doi:10.3389/fphys.2023.1144192

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

Front Physiol. 2023 Apr 21:14:1144192. doi: 10.3389/fphys.2023.1144192. eCollection 2023.

Authors

Jennifer M Wang¹, Wassim W Labaki¹, Susan Murray², Fernando J Martinez³, Jeffrey L Curtis^{1

4}, Eric A Hoffman⁵, Sundaresh Ram^{6

7}, Alexander J Bell⁶, Craig J Galban⁶, MeiLan K Han¹, Charles Hatt^{6

8}

Affiliations

¹ Division of Pulmonary and Critical Care Medicine, University of Michigan, Ann Arbor, MI, United States.
² Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, United States.
³ Weill Cornell Medical College, New York, NY, United States.
⁴ Medical Service, VA Ann Arbor Healthcare System, Ann Arbor, MI, United States.
⁵ Department of Radiology, University of Iowa, Iowa City, IA, United States.
⁶ Department of Radiology, University of Michigan, Ann Arbor, MI, United States.
⁷ Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI, United States.
⁸ Imbio Inc., Minneapolis, MN, United States.

Abstract

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 PRM_{lower 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.

Keywords: chronic obstructive pulmonary disease; computed tomography; lung function decline; machine learning; quantitative imaging.

Abstract

Grants and funding