Skip to content
DraconiticResearch
Search Sources API
194,226 studies31 sourcesUpdated 29 min ago
Peer-reviewedCC BY-NC-NDNature communications

Long-range interdependencies aware signal analysis for rapid and accurate obstructive sleep apnea prediction.

  • Zhenkun Wang1
  • Chenzhong Yin1
  • Anzhe Cheng1
  • Xinghe Chen1
  • Mingxi Cheng1
  • Li An1
  • Haoqing Wang2
  • Haofan Sun3
  • Li Ding1
  • Stefan Mihaicuta4,5
  • Lucretia Udrescu6,7
  • David Gozal8
9 more authors
  • Félix Del Campo9,10,11
  • Fernando Vaquerizo-Villar9,10
  • Roberto Hornero9,10
  • Jan Hedner12,13
  • Winfried Randerath14
  • David M Mannino15,16
  • Shahin Nazarian1
  • Mihai Udrescu17
  • Paul Bogdan18,19,20
20 affiliations
  1. 1Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA.
  2. 2Corwin D. Denney Research Center, Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA.
  3. 3School for Engineering of Matter, Transport and Energy, Arizona State University, Tempe, AZ, USA.
  4. 4Department of Pulmonology, "Victor Babeş" University of Medicine and Pharmacy Timişoara, Timişoara, Romania.
  5. 5Center for Research and Innovation in Personalized Medicine of Respiratory Diseases (CRIPMRD), "Victor Babeş" University of Medicine and Pharmacy Timişoara, Timişoara, Romania.
  6. 6Department I - Clinical Pharmacy and Drug Analysis, "Victor Babeş" University of Medicine and Pharmacy Timişoara, Timişoara, Romania.
  7. 7Center for Drug Data Analysis, Cheminformatics, and the Internet of Medical Things (CDDA-CIMT), "Victor Babeş" University of Medicine and Pharmacy Timişoara, Timişoara, Romania.
  8. 8Departments of Pediatrics, Biomedical Sciences and Dentistry and Maxillofacial Surgery, Joan C. Edwards School of Medicine, Marshall University, Huntington, WV, USA.
  9. 9Biomedical Engineering Group, University of Valladolid, Valladolid, Spain.
  10. 10CIBER de Bioingeniería, Biomateriales y Nanomedicina, Instituto de Salud Carlos III, Valladolid, Spain.
  11. 11Hospital Universitario Río Hortega. Valladolid, Valladolid, Spain.
  12. 12Pulmonary Department, Sleep Disorders Center, Sahlgrenska University Hospital, Gothenburg, Sweden.
  13. 13Center of Sleep and Wake Disorders, Sahlgrenska Academy, Gothenburg University, Göteborg, Sweden.
  14. 14Institute Für Pneumologie an der Universität Zu Köln, Cologne, Germany.
  15. 15College of Medicine, University of Kentucky, Lexington, KY, USA.
  16. 16COPD Foundation, Miami, FL, USA.
  17. 17Department of Computer and Information Technology, Politehnica University Timişoara, Timişoara, Romania. [email protected].
  18. 18Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA. [email protected].
  19. 19Center for Complex Particle Systems (COMPASS), University of Southern California, Los Angeles, CA, USA. [email protected].
  20. 20Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, CA, USA. [email protected].
Read full textPDFDOICite

Abstract

Obstructive sleep apnea, characterized by frequent interruptions in breathing and intermittent hypoxia, is a public health concern due to its potential to increase multiple organ system morbidity and mortality. Although polysomnography is the gold standard for diagnosis, it is laborious, costly, and complex. Here, we present a biological geometry-aware artificial intelligence framework that processes physiological signals to predict sleep apnea severity. This framework extracts multifractal coupling features that capture long-range dependencies among physiological processes and integrates them into deep learning for classification. We validate this approach across five heterogeneous cohorts comprising more than 35,000 subjects. The method achieves robust and consistent performance, with area-under-the-curve values exceeding 0.91 and improvements of 8-18% over state-of-the-art models. The extracted coupling representations exhibit rapid convergence and consistent performance across heterogeneous cohorts. This framework provides a robust representation of physiological dynamics and supports future developments in automated analysis of sleep-disordered breathing.

Related

  1. Development and validation of an interpretable machine learning model for early prediction of mortality in ICU patients with chronic obstructive pulmonary disease and heart failure
    Jiayi Shen, Yucheng Liu, Yikun Chen
    MedicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. A hybrid deep learning and ensemble approach for accurate prediction of hepatocellular carcinoma from sequence variants of hepatitis B virus (HBV) X gene
    Sadia Ejaz, Syed Ali Nawaz
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEpidemiology & public healthCrossref
  3. Risk factor analysis and development of a risk prediction model for facial pressure injury associated with noninvasive positive pressure ventilation in patients with chronic obstructive pulmonary disease based on symptom science theory
    Chen Cheng, Lulu Cui, Changhai Wang +14
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. KT-CBHNET: a spatio-temporal deep learning framework for interpretable ECG signal classification for cardiovascular disease prediction
    Krantee Singh, Vasudev Dehalwar
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textCardiovascular medicineCrossref
  5. Accurate stock movement prediction via centroid-based randomness smoothing
    Yejun Soun, Hosung Lee, U Kang
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceStatisticsPLOS

Cite

BibTeXRIS
BibTeX
@article{wang2026longrange,
  title = {{Long-range interdependencies aware signal analysis for rapid and accurate obstructive sleep apnea prediction.}},
  author = {Zhenkun Wang and Chenzhong Yin and Anzhe Cheng and Xinghe Chen and Mingxi Cheng and Li An and Haoqing Wang and Haofan Sun and Li Ding and Stefan Mihaicuta and Lucretia Udrescu and David Gozal and Félix Del Campo and Fernando Vaquerizo-Villar and Roberto Hornero and Jan Hedner and Winfried Randerath and David M Mannino and Shahin Nazarian and Mihai Udrescu and Paul Bogdan},
  journal = {Nature communications},
  year = {2026},
  month = sep,
  doi = {10.1038/s41467-026-76274-0},
  url = {https://europepmc.org/article/MED/42907459},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Long-range interdependencies aware signal analysis for rapid and accurate obstructive sleep apnea prediction.
AU  - Zhenkun Wang
AU  - Chenzhong Yin
AU  - Anzhe Cheng
AU  - Xinghe Chen
AU  - Mingxi Cheng
AU  - Li An
AU  - Haoqing Wang
AU  - Haofan Sun
AU  - Li Ding
AU  - Stefan Mihaicuta
AU  - Lucretia Udrescu
AU  - David Gozal
AU  - Félix Del Campo
AU  - Fernando Vaquerizo-Villar
AU  - Roberto Hornero
AU  - Jan Hedner
AU  - Winfried Randerath
AU  - David M Mannino
AU  - Shahin Nazarian
AU  - Mihai Udrescu
AU  - Paul Bogdan
PY  - 2026
DA  - 2026/09/22
JO  - Nature communications
DO  - 10.1038/s41467-026-76274-0
UR  - https://europepmc.org/article/MED/42907459
AB  - Obstructive sleep apnea, characterized by frequent interruptions in breathing and intermittent hypoxia, is a public health concern due to its potential to increase multiple organ system morbidity and mortality. Although polysomnography is the gold standard for diagnosis, it is laborious, costly, and complex. Here, we present a biological geometry-aware artificial intelligence framework that processes physiological signals to predict sleep apnea severity. This framework extracts multifractal coupling features that capture long-range dependencies among physiological processes and integrates them into deep learning for classification. We validate this approach across five heterogeneous cohorts comprising more than 35,000 subjects. The method achieves robust and consistent performance, with area-under-the-curve values exceeding 0.91 and improvements of 8-18% over state-of-the-art models. The extracted coupling representations exhibit rapid convergence and consistent performance across heterogeneous cohorts. This framework provides a robust representation of physiological dynamics and supports future developments in automated analysis of sleep-disordered breathing.
SN  - 2041-1723
ER  -