Nature and Science of Sleep (May 2022)

Fusion of Whole Night Features and Desaturation Segments Combined with Feature Extraction for Event-Level Screening of Sleep-Disordered Breathing

  • Liu R,
  • Li C,
  • Xu H,
  • Wu K,
  • Li X,
  • Liu Y,
  • Yuan J,
  • Meng L,
  • Zou J,
  • Huang W,
  • Yi H,
  • Sheng B,
  • Guan J,
  • Yin S

Journal volume & issue
Vol. Volume 14
pp. 927 – 940

Abstract

Read online

Ruhan Liu,1,2,* Chenyang Li,1,* Huajun Xu,1 Kejia Wu,1 Xinyi Li,1 Yupu Liu,1 Jie Yuan,1 Lili Meng,1 Jianyin Zou,1 Weijun Huang,1 Hongliang Yi,1 Bin Sheng,2 Jian Guan,1 Shankai Yin1 1Department of Otolaryngology Head and Neck Surgery and Shanghai Key Laboratory of Sleep Disordered Breathing & Otolaryngological Institute of Shanghai Jiao Tong University, Shanghai Jiao Tong University Affiliated Sixth People’s Hospital, Shanghai, People’s Republic of China; 2Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, People’s Republic of China*These authors contributed equally to this workCorrespondence: Bin Sheng; Jian Guan, Tel +86 13124853285, Email [email protected]; [email protected]: Misdiagnosis and missed diagnosis of sleep-disordered breathing (SDB) is common because polysomnography (PSG) is time-consuming, expensive, and uncomfortable. The use of recording methods based on the oxygen saturation (SpO2) signals detected by wearable devices is impractical and inaccurate for extracting signal features and detecting apnoeic events. We propose a method to automatically detect the apnoea-based SpO2 signal segments and compute the apnoea–hypopnea index (AHI) for SDB screening and grading.Patients and Methods: First, apnoea-related desaturation segments in raw SpO2 signals were detected; global features were extracted from whole night signals. Then, the SpO2 signal segments and global features were fed into a bi-directional long short-term memory convolutional neural network model to identify apnoea-related and non-apnoea-related events. The apnoea-related segments were used to assess the AHI.Results: The model was trained on 500 individuals and tested on 8131 individuals from two public hospitals and one private centre. In the testing data, the classification accuracy for apnoea-related segments was 84.3%. Individuals with SDB (AHI 15) were identified with a mean accuracy of 88.95%.Conclusion: Using automatic SDB detection based on SpO2 signals can accurately screen for SDB.Keywords: sleep apnea hypopnea syndrome, AHI, SDB severity classification, Bi-LSTM-CNN, desaturation events

Keywords