跳到正文
原文
Nature 健康护理主题·· 11 天前AI 评分35

机器学习模型用于诊断和预测阻塞性睡眠呼吸暂停严重程度

Decoding the night: a machine learning approach to diagnose and predict the severity of obstructive sleep apnea through clinical parameters

AI 导读

本研究开发了一种人工神经网络模型,利用18个临床参数预测阻塞性睡眠呼吸暂停(OSA)的存在及其严重程度。该模型在不同严重程度的OSA分类中表现出良好的区分性能,AUC值范围为0.89至0.96。研究结果支持基于机器学习的工具在资源有限的环境中用于筛查和早期风险分层。

正文

Abstract

Obstructive sleep apnea (OSA) is a common sleep-related disorder associated with cardiovascular and metabolic comorbidities. Early diagnosis is essential; however, access to polysomnography is limited. Machine learning approaches may support clinical decision-making by predicting OSA using easily obtainable variables. This study aimed to develop an artificial neural network (ANN) model to predict the presence and severity of OSA. This multicenter study included adult patients who underwent diagnostic polysomnography at ten different sleep centers. Eighteen demographic and clinical parameters were used as input features, and four OSA severity categories served as output classes. The ANN architecture consisted of one hidden layer with 50 neurons (ReLU activation) and a Softmax output layer. The dataset was randomly divided into training (80%) and testing (20%) sets. A total of 1,954 participants (70.2% male) were included. Polysomnography classified 39.2% of participants as severe OSA, 29.4% as mild OSA, 15.0% as moderate OSA, and 16.4% as non-OSA. The ANN model demonstrated good discriminative performance across OSA severity categories, with class-specific AUC values ranging from 0.89 to 0.96. These findings support the potential utility of ML-based tools for screening and early risk stratification, particularly in resource-limited settings.

Acknowledgements

The authors gratefully acknowledge the Recep Tayyip Erdoğan University Development Foundation for its financial support.

Funding

This study was supported by the Recep Tayyip Erdoğan University Development Foundation (grant number: 02026002004095).

Author information

Authors and Affiliations

  1. Medical Faculty, Department of Pulmonary Medicine, Recep Tayyip Erdogan University, Rize, Turkey

    Neslihan Özçelik, Elvan Şentürk Topaloğlu, Songül Özyurt, Aziz Gümüş, Bilge Yılmaz Kara, Hasan Veysel Keskin & Ünal Şahin

  2. Faculty of Engineering-Architecture, Department of Computer Engineering, Nevşehir Haci Bektas Veli University, Nevşehir, Turkey

    Emre Bendeş

  3. Faculty of Engineering and Architecture, Department of Landscape Architecture, Recep Tayyip Erdogan University, Rize, Turkey

    Ali Erdem Özçelik

  4. Faculty of Medicine, Department of Pulmonary Medicine, Bursa Uludag University, Bursa, Turkey

    Mehmet Karadağ, Özge Aydın Güçlü & Merve Nur Yıldız

  5. Faculty of Medicine, Department of Pulmonary Medicine, Dicle University, Diyarbakır, Turkey

    Hadice Selimoğlu Şen

  6. Faculty of Medicine, Department of Pulmonary Medicine, Erciyes University, Kayseri, Turkey

    Nur Aleyna Yetkin & Burcu Baran

  7. Faculty of Medicine, Department of Pulmonary Medicine, Süleyman Demirel University, Isparta, Turkey

    Önder Öztürk, Merve Erçelik & Hilal Türkmen Kaya

  8. Faculty of Medicine, Department of Pulmonary Medicine, Balikesir University, Balikesir, Turkey

    Nurhan Sarıoğlu & Mustafa Çolak

  9. Department of Pulmonary Medicine, Medipol University School of Medicine, Istanbul, Turkey

    Muhammed Emin Akkoyunlu & Abdullah Kansu

  10. Erzurum City Hospital, Pulmonary Medicine Clinic, Erzurum, Turkey

    Abdurrahman Kotan & Fatma Gülsüm Karakaş

  11. Faculty of Medicine, Department of Chest Diseases, Karadeniz Technical University, Trabzon, Turkey

    Yılmaz Bülbül

  12. Faculty of Medicine, Department of Chest Diseases, Gaziantep University, Gaziantep, Turkey

    Sibel Doğru

  13. Department of Thoracic Surgery, Yedikule Training and Research Hospital, İstanbul, Turkey

    Gizem Özçıbık Işık

  14. Medical Faculty, Department of Thoracic Surgery, Recep Tayyip Erdogan University, Rize, Turkey

    Ömer Topaloğlu

Authors

  1. Neslihan Özçelik
  2. Emre Bendeş
  3. Ali Erdem Özçelik
  4. Elvan Şentürk Topaloğlu
  5. Songül Özyurt
  6. Mehmet Karadağ
  7. Özge Aydın Güçlü
  8. Merve Nur Yıldız
  9. Hadice Selimoğlu Şen
  10. Nur Aleyna Yetkin
  11. Burcu Baran
  12. Önder Öztürk
  13. Merve Erçelik
  14. Hilal Türkmen Kaya
  15. Nurhan Sarıoğlu
  16. Mustafa Çolak
  17. Muhammed Emin Akkoyunlu
  18. Abdullah Kansu
  19. Abdurrahman Kotan
  20. Fatma Gülsüm Karakaş
  21. Yılmaz Bülbül
  22. Sibel Doğru
  23. Aziz Gümüş
  24. Gizem Özçıbık Işık
  25. Ömer Topaloğlu
  26. Bilge Yılmaz Kara
  27. Hasan Veysel Keskin
  28. Ünal Şahin

Corresponding author

Correspondence to Ali Erdem Özçelik.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

Institutional approval was obtained from each participating center, and ethical clearance was granted by the Recep Tayyip Erdoğan University Faculty of Medicine Clinical Research Ethics Committee (Approval No: 2024/142). The requirement for obtaining informed consent was waived by the ethics committee due to the retrospective nature of the study.

Consent for publication

Obtained from the authors.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Özçelik, N., Bendeş, E., Özçelik, A.E. et al. Decoding the night: a machine learning approach to diagnose and predict the severity of obstructive sleep apnea through clinical parameters. Sci Rep (2026). https://doi.org/10.1038/s41598-026-79860-w

Download citation

  • Received: 05 February 2026

  • Accepted: 03 November 2026

  • Published: 09 November 2026

  • DOI: https://doi.org/10.1038/s41598-026-79860-w

Keywords

来源:Nature 健康护理主题 · nature.com