arXiv cs.AI· Ying-Chieh Hsu, Stanley Yung-Chuan Liu, Chao-Jung Huang, Chi-Wei Wu, Ren-Kai Cheng, Jane Yung-Jen Hsu, Shang-Ran Huang, Yuan-Ren Cheng, Fu-Shun Hsu·· 12 小时前AI 评分31
基于鼾声的深度学习多层级气道塌陷定位，用于阻塞性睡眠呼吸暂停患者
Deep learning-based multi-level airway collapse site localization on obstructive sleep apnea patients based on snoring sounds
AI 导读
研究用 ResNet-50 与 Audio Spectrogram Transformer（AST）基于鼾声识别阻塞性睡眠呼吸暂停患者的多层级上气道塌陷，AST 显著优于 ResNet-50（Bonferroni 校正后 P<0.05）。
正文 · 原文
Abstract:Objective This study evaluated deep learning models, specifically ResNet-50 and Audio Spectrogram Transformer (AST), to identify multi-level upper airway collapses in obstructive sleep apnea (OSA) patients using snoring sounds. Methods Snoring recordings from 37 subjects undergoing drug-induced sleep endoscopy (DISE) between 2020 and 2021 were used to train models for two multi-label tasks: identifying obstructions at the Velum (V), Oropharynx (O), Tongue-base (T), and Epiglottis (E) levels, and the retropalatal (RP) vs. retroglossal (RG) levels. Results The AST model significantly outperformed ResNet-50 (P <0.05 after Bonferroni correction), effectively identifying V-, O-, and RP-level obstructions (F1-score: 0.59-0.87, Matthews Correlation Coefficient: 0.50-0.80, and AUC: 0.87-0.97). However, the performance of both models at the T, E, and RG levels remained limited due to small sample sizes, even with the Synthetic Minority Over-sampling Technique. A full-night recording analysis further demonstrated the feasibility of acoustic profiling for airway dynamics. Conclusion The AST models can effectively identify airway obstruction at V, O, and RP levels via snoring sounds. The proposed models offer a promising non-invasive tool for tracking overnight airway dynamics and assisting in clinical treatment planning.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2408.16030 [cs.SD] |
| (or arXiv:2408.16030v3 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2408.16030 arXiv-issued DOI via DataCite |
Submission history
From: Shang Ran Huang [view email]
[v1]
Wed, 28 Aug 2024 09:30:20 UTC (583 KB)
[v2]
Thu, 9 Jan 2025 06:33:24 UTC (1,247 KB)
[v3]
Tue, 20 Oct 2026 10:55:14 UTC (1,578 KB)
来源：arXiv cs.AI · arxiv.org