Quantitative Chest Computed Tomography and Machine Learning for Subphenotyping Small Airways Disease in Long COVID
The integration of inspiratory and expiratory chest CT with quantitative analysis and ML enables the identification of distinct imaging phenotypes in long COVID patients, including a unique SAD cluster strongly associated with specific pulmonary function abnormalities.
Authors
- Eduardo Kaiser Ururahy Nunes Fonseca (ORCID: https://orcid.org/0000-0002-0233-0041)
- Fernando Uliana Kay (ORCID: https://orcid.org/0000-0002-9467-2013)
- P. Amaral (ORCID: https://orcid.org/0000-0003-2918-7190)
- Márcio Valente Yamada Sawamura (ORCID: https://orcid.org/0000-0002-9424-9776)
- Carlos Roberto Ribeiro de Carvalho (ORCID: https://orcid.org/0000-0002-1618-8509)
- Celina de Almeida Lamas (ORCID: https://orcid.org/0000-0002-7808-0800)
- Luis Augusto Visani de Luna (ORCID: https://orcid.org/0000-0003-0375-1064)
- João Marcos Salge (ORCID: https://orcid.org/0000-0001-5121-0129)
- César Higa Nomura (ORCID: https://orcid.org/0000-0002-7131-6614)
- Rodrigo Caruso Chate (ORCID: https://orcid.org/0000-0002-4193-7647)
- Antonildes Nascimento Assunção
Institutions
- Hospital Israelita Albert Einstein (BR)
- Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (BR)
- The University of Texas Southwestern Medical Center (US)
Publication Details
- Journal
- Journal of Thoracic Imaging
- Published
- 2025-10-16
- DOI
- https://doi.org/10.1097/rti.0000000000000861
- Primary Topic
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00