Logo image
Back
Oropharyngeal enlargement in obstructive lung disease: quantification and machine learning
Journal article   Open access   Peer reviewed

Oropharyngeal enlargement in obstructive lung disease: quantification and machine learning

Asma Abdolijomoor, David H. Lee, So Ri Kim, Seoung Ju Park, Gong Yong Jin, Eric A. Hoffman, Mario Castro, Chang Hyun Lee, Jiwoong Choi and Kum Ju Chae
ERJ open research, Vol.11(5), pp.00961-2024
09/2025
DOI: 10.1183/23120541.00961-2024
PMCID: PMC12434485
PMID: 40959168
url
https://doi.org/10.1183/23120541.00961-2024View
Published (Version of record) Open Access

Abstract

Background While lower airway remodeling of obstructive lung diseases (OLDs), such as asthma and chronic obstructive pulmonary disease (COPD), is comprehensively studied, the understanding of upper airway remodeling in OLD remains limited. This study aimed to investigate upper airway dimensions in OLD patients using quantitative computed tomography (QCT) imaging and to identify relevant parameters for predicting OLD using machine learning techniques. Methods A prospective cohort of 26 healthy controls, 73 COPD patients, and 86 asthma patients underwent upper airway CT scans from the oral cavity to the subglottal region. Multiscale lung structure and function were assessed using ITK-SNAP and in-house qCT software. Feature importance estimation methods from STREAMLINE were utilized to select potentially relevant upper airway metrics. The Wilcoxon rank-sum test and Pearson's correlation were employed for pairwise comparisons and correlation analysis, respectively. The Youden index was used to determine optimal cutoff values of relevant upper airway features. Results After standardizing QCT results, OLD patients exhibited greater mouth-to-supraglottal metrics, notably greater oral space air fraction and pharyngeal length. Both metrics showed a negative correlation with FEV1/FVC (R=-0.24, p=0.001). Feature importance analysis identified oral space air fraction and normalized pharyngeal length as key features discriminating OLD from healthy controls. An oral space air fraction value of 0.8 or higher predicted OLD with approximately 100% sensitivity and 69% specificity. Conclusions Quantitative upper airway CT measurement combined with machine learning analysis revealed oropharyngeal enlargement in patients with obstructive lung disease.

Details

Metrics

3 Record Views
Logo image