Deep Learning for Respiratory Sound Analysis: A Systematic Review and Meta-Analysis (2019–2024)
Thamar University Journal of Natural & Applied Sciences · 28.06.2026 · 11 (1)
DOI: 10.59167/g1qw6p23 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Thamar University Journal of Natural & Applied Sciences, online erschienen am 28.06.2026. Verfasst von Shaima’a Mohammed Nasser Al-Jabali und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Respiratory diseases remain a significant global health burden, particularly in resource-limited settings.
Objective
To review and quantitatively analyze deep learning-based models for interpreting respiratory sounds. Methodology: A systematic search was conducted in the PubMed, IEEE Xplore, ScienceDirect, and Scopus databases for the period 2019–2024, using PRISMA 2020 criteria. Of the 678 records accessed, 98 studies met the qualitative criteria, while 42 met the quantitative analysis criteria.
Results
An exploratory meta-analysis conducted on a subset of studies reporting native accuracy (k = 9) yielded a pooled accuracy of approximately 90.0% (95% CI: 76.0%–97.0%), with substantial heterogeneity (I² = 99.2%).
Conclusion
Deep learning techniques demonstrate promising diagnostic capabilities, but they still face challenges related to reliance on limited databases, poor representation of rare diseases, and difficulty in interpreting their outputs.
Implications
Future research should focus on diversifying datasets, enhancing the integration of multimodal data, and developing interpretable or federated learning-based models to support their adoption in clinical settings
Zitieren
APA
Al-Jabali, S. M. N., Nashwan, F., & Altalabi, W. M. (2026). Deep Learning for Respiratory Sound Analysis: A Systematic Review and Meta-Analysis (2019–2024). Thamar University Journal of Natural & Applied Sciences, 11(1). https://doi.org/10.59167/g1qw6p23
Vancouver
Al-Jabali SMN, Nashwan F, Altalabi WM. Deep Learning for Respiratory Sound Analysis: A Systematic Review and Meta-Analysis (2019–2024). Thamar University Journal of Natural & Applied Sciences. 2026;11(1). doi:10.59167/g1qw6p23
BibTeX
@article{AlJabali2026,
author = {Al-Jabali, Shaima’a Mohammed Nasser and Nashwan, Farhan and Altalabi, Waleed M.},
title = {Deep Learning for Respiratory Sound Analysis: A Systematic Review and Meta-Analysis (2019–2024)},
journal = {Thamar University Journal of Natural & Applied Sciences},
year = {2026},
volume = {11},
number = {1},
doi = {10.59167/g1qw6p23}
}
EUVIMED