Machine learning-driven strategies for enhanced pediatric wheezing detection
Mel-spectrograms, MFCC, and spectral contrast are effective for characterizing respiratory sounds in children. A machine learning model using spectral contrast demonstrated high detection performance, indicating its potential utility in ensuring accurate diagnosis of pediatric respiratory diseases.
Authors
- Baek Seung Kim
- Hye Jeong Moon (ORCID: https://orcid.org/0000-0002-7881-1343)
- Beom Joon Kim (ORCID: https://orcid.org/0000-0002-2719-3012)
- Kyunghoon Kim (ORCID: https://orcid.org/0000-0002-0707-6839)
- Hyunmin Ji
Institutions
- Seoul National University of Science and Technology (KR)
- Seoul National University (KR)
- Seoul National University Bundang Hospital (KR)
- Catholic University of Korea (KR)
Publication Details
- Journal
- Frontiers in Pediatrics
- Published
- 2025-05-20
- DOI
- https://doi.org/10.3389/fped.2025.1428862
- Citations
- 3
- Primary Topic
- Phonocardiography and Auscultation Techniques
- Type
- article
- Field-Weighted Citation Impact
- 4.56
Funders
- Seoul National University Bundang Hospital