Improving the Robustness and Clinical Applicability of Automatic Respiratory Sound Classification Using Deep Learning–Based Audio Enhancement: Algorithm Development and Validation
Incorporating an audio enhancement algorithm significantly enhances the robustness and clinical utility of automatic respiratory sound classification systems, improving performance in noisy environments and fostering greater trust among medical professionals.
Authors
- Jeng-Lin Li (ORCID: https://orcid.org/0000-0002-9261-1524)
- Edward Pei‐Chuan Huang (ORCID: https://orcid.org/0000-0002-4800-2561)
- Chu-Hsiang Huang (ORCID: https://orcid.org/0000-0003-3097-153X)
- Cheng‐Yi Fan (ORCID: https://orcid.org/0000-0002-1585-0038)
- Chi-Chun Lee (ORCID: https://orcid.org/0000-0003-0186-4321)
- Huanyu Chen (ORCID: https://orcid.org/0000-0002-0055-8034)
- Chi‐Hsin Chen (ORCID: https://orcid.org/0000-0003-1826-6598)
- Jing-Tong Tzeng (ORCID: https://orcid.org/0000-0002-2053-0581)
Institutions
- National Tsing Hua University (TW)
- National Taiwan University Hospital (TW)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-01-27
- DOI
- https://doi.org/10.2196/67239
- Citations
- 9
- Primary Topic
- Phonocardiography and Auscultation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 13.67