EUVIMEDEUVIMED entdecken
Crossref

Contactless Oxygen Desaturation Prediction and Oxygen Desaturation Index (ODI) Estimation from Nocturnal Breathing Sounds via Deep Learning

Hayun Choi, EunSung Cho, Seunghun Kim, Sungjin Heo, Sungeun Moon, Joonki Hong, Dongheon Lee, Sujin Lee, Jeong-Whun Kim, In-Young Yoon

SLEEP · 14.11.2026

DOI: 10.1093/sleep/zsag295 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SLEEP, online erschienen am 14.11.2026. Verfasst von Hayun Choi und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychiatry, Veteran Health Service Medical Center, Seoul, Republic of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Study Objectives Intermittent hypoxemia is increasingly recognized as a stronger predictor of cardiovascular morbidity and mortality in obstructive sleep apnea (OSA) than the apnea–hypopnea index (AHI). We developed a sound-based AI model to detect oxygen desaturation events and estimate the oxygen desaturation index (ODI) from nocturnal breathing sounds in a fully contactless manner.

Methods

The model was trained using 2,973 nights of synchronized polysomnography (PSG) and audio recordings obtained from hospital- and home-based settings. Validation and independent testing were performed on 664 and 802 nights, respectively. Audio signals were converted into Mel spectrograms and processed using a Vision Transformer–based architecture. Performance was evaluated at the 30-second epoch level using sensitivity, specificity, precision, F1 score, accuracy, and Cohen’s κ. ODI estimation was assessed using Pearson correlation, Bland–Altman analysis, mean absolute error (MAE), and root mean square error (RMSE).

Results

For epoch-by-epoch desaturation detection, the model achieved a sensitivity of 0.79, specificity of 0.95, precision of 0.78, F1 score of 0.79, overall accuracy of 0.92, and κ of 0.74. Estimated ODI showed agreement with PSG-derived ODI (r = 0.93, R² = 0.87, p < 0.001). Bland–Altman analysis demonstrated a mean bias of −0.29 events/h with 95% limits of agreement from −14.73 to 14.14 events/h.

Conclusions

Breathing sound–based deep learning enables contactless detection of oxygen desaturation events and reliable ODI estimation. This approach may provide a scalable, non-contact method for sleep-disordered breathing assessment in real-world settings.

Schlagwörter

Stichwörter der Autor:innen

breathing soundsdeep learninghypoxemiaobstructive sleep apneaoxygen desaturation indexpolysomnography

Autor:innen und Institutionen

  • Department of Psychiatry, Veteran Health Service Medical Center, Seoul, Republic of Korea.
  • Asleep Inc., Seoul, Republic of Korea.
  • Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.
  • Department of Psychiatry, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, Republic of Korea.

Zitieren

APA

Choi, H., Cho, E., Kim, S., Heo, S., Moon, S., Hong, J., Lee, D., Lee, S., Kim, J. W., & Yoon, I. Y. (2026). Contactless Oxygen Desaturation Prediction and Oxygen Desaturation Index (ODI) Estimation from Nocturnal Breathing Sounds via Deep Learning. SLEEP. https://doi.org/10.1093/sleep/zsag295

Vancouver

Choi H, Cho E, Kim S, Heo S, Moon S, Hong J, et al. Contactless Oxygen Desaturation Prediction and Oxygen Desaturation Index (ODI) Estimation from Nocturnal Breathing Sounds via Deep Learning. SLEEP. 2026. doi:10.1093/sleep/zsag295

BibTeX
@article{Choi2026,
  author = {Choi, Hayun and Cho, EunSung and Kim, Seunghun and Heo, Sungjin and Moon, Sungeun and Hong, Joonki and Lee, Dongheon and Lee, Sujin and Kim, Jeong-Whun and Yoon, In-Young},
  title = {Contactless Oxygen Desaturation Prediction and Oxygen Desaturation Index (ODI) Estimation from Nocturnal Breathing Sounds via Deep Learning},
  journal = {SLEEP},
  year = {2026},
  doi = {10.1093/sleep/zsag295}
}
Kostenlos starten →