BACKGROUND Currently recommended traditional spirometry outputs do not reflect the relative contributions of emphysema and airway disease to airflow obstruction. We hypothesized that machine-learning algorithms can be trained on spirometry data to identify these structural phenotypes.METHODS Participants enrolled in a large multicenter study (COPDGene) were included. The data points from expiratory flow-volume curves were trained using a deep-learning model to predict structural phenotypes of chronic obstructive pulmonary disease (COPD) on CT, and results were compared with traditional spirometry metrics and an optimized random forest classifier. Area under the receiver operating characteristic curve (AUC) and weighted F-score were used to measure the discriminative accuracy of a fully convolutional neural network, random forest, and traditional spirometry metrics to phenotype CT as normal, emphysema-predominant (>5% emphysema), airway-predominant (Pi10 > median), and mixed phenotypes. Similar comparisons were made for the detection of functional small airway disease phenotype (>20% on parametric response mapping).RESULTS Among 8980 individuals, the neural network was more accurate in discriminating predominant emphysema/airway phenotypes (AUC 0.80, 95%CI 0.79–0.81) compared with traditional measures of spirometry, FEV1/FVC (AUC 0.71, 95%CI 0.69–0.71), FEV1% predicted (AUC 0.70, 95%CI 0.68–0.71), and random forest classifier (AUC 0.78, 95%CI 0.77–0.79). The neural network was also more accurate in discriminating predominant emphysema/small airway phenotypes (AUC 0.91, 95%CI 0.90–0.92) compared with FEV1/FVC (AUC 0.80, 95%CI 0.78–0.82), FEV1% predicted (AUC 0.83, 95%CI 0.80–0.84), and with comparable accuracy with random forest classifier (AUC 0.90, 95%CI 0.88–0.91).CONCLUSIONS Structural phenotypes of COPD can be identified from spirometry using deep-learning and machine-learning approaches, demonstrating their potential to identify individuals for targeted therapies.TRIAL REGISTRATION ClinicalTrials.gov NCT00608764.FUNDING This study was supported by NIH grants K23 HL133438 and R21EB027891 and an American Thoracic Foundation 2018 Unrestricted Research Grant. The COPDGene study is supported by NIH grants NHLBI U01 HL089897 and U01 HL089856. The COPDGene study (NCT00608764) is also supported by the COPD Foundation through contributions made to an Industry Advisory Committee comprising AstraZeneca, Boehringer-Ingelheim, GlaxoSmithKline, Novartis, and Sunovion.
Sandeep Bodduluri, Arie Nakhmani, Joseph M. Reinhardt, Carla G. Wilson, Merry-Lynn McDonald, Ramaraju Rudraraju, Byron C. Jaeger, Nirav R. Bhakta, Peter J. Castaldi, Frank C. Sciurba, Chengcui Zhang, Purushotham V. Bangalore, Surya P. Bhatt
Usage data is cumulative from March 2023 through March 2024.
Usage | JCI | PMC |
---|---|---|
Text version | 590 | 422 |
89 | 104 | |
Figure | 97 | 6 |
Table | 55 | 0 |
Supplemental data | 55 | 11 |
Citation downloads | 34 | 0 |
Totals | 920 | 543 |
Total Views | 1,463 |
Usage information is collected from two different sources: this site (JCI) and Pubmed Central (PMC). JCI information (compiled daily) shows human readership based on methods we employ to screen out robotic usage. PMC information (aggregated monthly) is also similarly screened of robotic usage.
Various methods are used to distinguish robotic usage. For example, Google automatically scans articles to add to its search index and identifies itself as robotic; other services might not clearly identify themselves as robotic, or they are new or unknown as robotic. Because this activity can be misinterpreted as human readership, data may be re-processed periodically to reflect an improved understanding of robotic activity. Because of these factors, readers should consider usage information illustrative but subject to change.