Organizations: Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan. · Department of Otolaryngology Head and Neck Surgery, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Taipei, Taiwan. · Tzu Chi University, School of Medicine, Hualien, Taiwan. · Department of Oral & Maxillofacial Surgery, Nova Southeastern University College of Dental Medicine and College of Allopathic Medicine, Florida, USA. · All Vista Healthcare Center and Center for AI and Advanced Robotics, National Taiwan University, Taipei, Taiwan. · Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan. · Department of Artificial Intelligence, Chang Gung University College of Intelligent Computing, Taoyuan, Taiwan · Heroic Faith Medical Science Co., Ltd., New Taipei, Taiwan. · School of Medicine, Chung Shan Medical University, Taichung, Taiwan. · Department of Internal Medicine, Chung Shan Medical University, Taichung, Taiwan. · Hospital Development Affairs Office, Chung Shan Medical University Hospital, Taichung, Taiwan.
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.
Department of Medical Engineering and Technomathematics, FH Aachen University of Applied Sciences, 52428 Jülich, Germany · Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands · Institute for Data-Driven Technologies, FH Aachen University of Applied Sciences, 52428 Jülich, Germany