Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.16030 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915095351656448 |
|---|---|
| author | Hsu, Ying-Chieh Liu, Stanley Yung-Chuan Huang, Chao-Jung Wu, Chi-Wei Cheng, Ren-Kai Hsu, Jane Yung-Jen Huang, Shang-Ran Cheng, Yuan-Ren Hsu, Fu-Shun |
| author_facet | Hsu, Ying-Chieh Liu, Stanley Yung-Chuan Huang, Chao-Jung Wu, Chi-Wei Cheng, Ren-Kai Hsu, Jane Yung-Jen Huang, Shang-Ran Cheng, Yuan-Ren Hsu, Fu-Shun |
| contents | This study investigated the use of deep learning to identify multi-level upper airway collapses in obstructive sleep apnea (OSA) patients based on snoring sounds. We fi-ne-tuned ResNet-50 and Audio Spectrogram Transformer (AST) models using snoring recordings from 37 subjects undergoing drug-induced sleep endoscopy (DISE) between 2020 and 2021. Snoring sounds were labeled according to the VOTE (Velum, Orophar-ynx, Tongue Base, Epiglottis) classification, resulting in 259 V, 403 O, 77 T, 13 E, 1016 VO, 46 VT, 140 OT, 39 OE, 30 VOT, and 3150 non-snoring (N) 0.5-second clips. The models were trained for two multi-label classification tasks: identifying obstructions at V, O, T, and E levels, and identifying retropalatal (RP) and retroglossal (RG) obstruc-tions. Results showed AST slightly outperformed ResNet-50, demonstrating good abil-ity to identify V (F1-score: 0.71, MCC: 0.61, AUC: 0.89), O (F1-score: 0.80, MCC: 0.72, AUC: 0.94), and RP obstructions (F1-score: 0.86, MCC: 0.77, AUC: 0.97). However, both models struggled with T, E, and RG classifications due to limited data. Retrospective analysis of a full-night recording showed the potential to profile airway obstruction dynamics. We expect this information, combined with polysomnography and other clinical parameters, can aid clinical triage and treatment planning for OSA patients. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_16030 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Learning-Based Automatic Multi-Level Airway Collapse Monitoring on Obstructive Sleep Apnea Patients Hsu, Ying-Chieh Liu, Stanley Yung-Chuan Huang, Chao-Jung Wu, Chi-Wei Cheng, Ren-Kai Hsu, Jane Yung-Jen Huang, Shang-Ran Cheng, Yuan-Ren Hsu, Fu-Shun Sound Artificial Intelligence Machine Learning Audio and Speech Processing This study investigated the use of deep learning to identify multi-level upper airway collapses in obstructive sleep apnea (OSA) patients based on snoring sounds. We fi-ne-tuned ResNet-50 and Audio Spectrogram Transformer (AST) models using snoring recordings from 37 subjects undergoing drug-induced sleep endoscopy (DISE) between 2020 and 2021. Snoring sounds were labeled according to the VOTE (Velum, Orophar-ynx, Tongue Base, Epiglottis) classification, resulting in 259 V, 403 O, 77 T, 13 E, 1016 VO, 46 VT, 140 OT, 39 OE, 30 VOT, and 3150 non-snoring (N) 0.5-second clips. The models were trained for two multi-label classification tasks: identifying obstructions at V, O, T, and E levels, and identifying retropalatal (RP) and retroglossal (RG) obstruc-tions. Results showed AST slightly outperformed ResNet-50, demonstrating good abil-ity to identify V (F1-score: 0.71, MCC: 0.61, AUC: 0.89), O (F1-score: 0.80, MCC: 0.72, AUC: 0.94), and RP obstructions (F1-score: 0.86, MCC: 0.77, AUC: 0.97). However, both models struggled with T, E, and RG classifications due to limited data. Retrospective analysis of a full-night recording showed the potential to profile airway obstruction dynamics. We expect this information, combined with polysomnography and other clinical parameters, can aid clinical triage and treatment planning for OSA patients. |
| title | Deep Learning-Based Automatic Multi-Level Airway Collapse Monitoring on Obstructive Sleep Apnea Patients |
| topic | Sound Artificial Intelligence Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.16030 |