Integrated assessment of total airway count and pneumonia volume on chest computed tomography as a prognostic biomarker for coronavirus disease.
Authors
Affiliations (22)
Affiliations (22)
- Division of Pulmonary Medicine, Department of Internal Medicine, Keio University School of Medicine, Tokyo, Japan.
- Department of Respiratory Medicine, National Hospital Organization Saitama National Hospital, Wako, Saitama, Japan.
- Department of Respiratory Medicine, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
- Division of Pulmonary Medicine, Department of Internal Medicine, Keio University School of Medicine, Tokyo, Japan. [email protected].
- Department of Clinical Medicine (Laboratory of Bioregulatory Medicine), Kitasato University School of Pharmacy, Tokyo, Japan.
- Department of Respiratory Medicine, Kitasato University, Kitasato Institute Hospital, Tokyo, Japan.
- Department of Infectious Diseases, Keio University School of Medicine, Tokyo, Japan.
- Internal Medicine, JCHO (Japan Community Health Care Organization) Saitama Medical Center, Saitama, Japan.
- Department of Respiratory Medicine, Juntendo University Faculty of Medicine and Graduate School of Medicine, Tokyo, Japan.
- Department of Pulmonary Medicine, Saitama City Hospital, Saitama, Japan.
- Department of Radiology, Keio University School of Medicine, Tokyo, Japan.
- Department of Statistical Genetics, Osaka University Graduate School of Medicine, Suita, Japan.
- Department of Genome Informatics, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.
- Laboratory for Systems Genetics, RIKEN Center for Integrative Medical Sciences, Kanagawa, Japan.
- Health Science Research and Development Center (HeRD), Tokyo Medical and Dental University, Tokyo, Japan.
- Department of Respiratory Medicine, Nagoya University Graduate School of Medicine, Nagoya, Japan.
- Institute of Research, Tokyo Medical and Dental University, Tokyo, Japan.
- Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan.
- M&D Data Science Center, Tokyo Medical and Dental University, Tokyo, Japan.
- Department of Pathology and Tumor Biology, Kyoto University, Kyoto, Japan.
- Institute for the Advanced Study of Human Biology (WPI-ASHBi), Kyoto University, Kyoto, Japan.
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, Tokyo, Japan.
Abstract
The clinical relevance of computed tomography (CT)-based airway tree structure is unclear. Herein, we used artificial intelligence to segment the airway tree and pneumonia regions, measuring total airway count (TAC) and pneumonia volume to examine whether their combination is more closely associated with clinical outcomes in patients with coronavirus disease (COVID-19) than pneumonia volume alone. We examined clinical data and chest CT from 781 hospitalized COVID-19 patients in a multicenter retrospective cohort in Japan, focusing on the percentage of critical outcomes (high-flow oxygen, invasive mechanical ventilation, or death). Additionally, 197 patients were followed up for 3 months to monitor TAC and pneumonia volume. Critical outcomes were observed in 63 (8.8%) patients, with higher TAC in those patients. Patients were divided into four groups based on cutoff values of 17.6% for pneumonia volume percent and 255 for TAC: Group A (low TAC, low pneumonia volume), Group B (high TAC, low pneumonia volume), Group C (low TAC, high pneumonia volume), and Group D (high TAC, high pneumonia volume). Group D had the worst outcomes, highest levels of inflammation, fibrosis markers, and complications, as well as a significantly higher risk of critical outcomes after adjusting for age, body mass index, sex, total lung volume and comorbidities. In the 3-month longitudinal analysis, pneumonia volume, but not TAC, improved in critical cases. The integrated assessment of TAC and pneumonia volume effectively predicted critical outcomes in COVID-19 patients and may be useful for various respiratory diseases, including infectious or interstitial pneumonia. Question Total airway counts (TAC) on computed tomography (CT) scan is associated with respiratory disease progression, but clinical relevance of CT-based airway tree structure is unclear. Findings The integrated assessment of TAC and pneumonia volume effectively predicted critical outcomes in COVID-19 patients. Clinical relevance This metric can potentially be applied to various respiratory diseases, including infectious or interstitial pneumonia.