EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

A Taxonomy of Machine Learning Approaches for Obstructive Sleep Apnea Detection and Management in Pregnancy: Methods, Challenges, and Future Directions

Vandana Roy, Shalini Stalin, Nikhar Vishwakarma, Anuj Nayak

International Journal of Communication Systems and Network Technologies · 30.04.2026 · 15 (1) · 01-32

DOI: 10.18486/ijcsnt/15.1.001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Communication Systems and Network Technologies, online erschienen am 30.04.2026. Verfasst von Vandana Roy und 3 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the well-recognized association between obstructive sleep apnea (OSA) and adverse maternal and fetal outcomes, OSA remains one of the most underdiagnosed conditions during pregnancy. Physiological changes occurring throughout pregnancy, including hormonal fluctuations, upper airway alterations, and increased blood volume, reduce the effectiveness of conventional screening questionnaires designed for the general population. This review analyzes 38 selected studies from more than 100 publications to examine the application of machine learning (ML) and artificial intelligence (AI) techniques for detecting OSA in pregnant women. The reviewed approaches range from traditional questionnaire-based classifiers, achieving accuracies between 0.79 and 0.85, to advanced deep learning models based on physiological signals that report accuracies exceeding 0.92 and sensitivities up to 0.977. Multimodal approaches integrating physiological signals, anthropometric measurements, and clinical information consistently outperform single-modality models. Furthermore, explainable AI techniques such as SHAP and LIME improve clinical interpretability, while wearable and contactless sensing technologies facilitate continuous monitoring beyond laboratory environments. The review also identifies critical challenges, including the absence of standardized datasets, inconsistent apnea–hypopnea definitions, and limited prospective validation in diverse obstetric populations. Future progress requires standardized benchmarks, lightweight and transparent AI architectures, and fairness-aware model development to enable reliable clinical deployment.

Zitieren

APA

Roy, V., Stalin, S., Vishwakarma, N., & Nayak, A. (2026). A Taxonomy of Machine Learning Approaches for Obstructive Sleep Apnea Detection and Management in Pregnancy: Methods, Challenges, and Future Directions. International Journal of Communication Systems and Network Technologies, 15(1), 01-32. https://doi.org/10.18486/ijcsnt/15.1.001

Vancouver

Roy V, Stalin S, Vishwakarma N, Nayak A. A Taxonomy of Machine Learning Approaches for Obstructive Sleep Apnea Detection and Management in Pregnancy: Methods, Challenges, and Future Directions. International Journal of Communication Systems and Network Technologies. 2026;15(1):01-32. doi:10.18486/ijcsnt/15.1.001

BibTeX
@article{Roy2026,
  author = {Roy, Vandana and Stalin, Shalini and Vishwakarma, Nikhar and Nayak, Anuj},
  title = {A Taxonomy of Machine Learning Approaches for Obstructive Sleep Apnea Detection and Management in Pregnancy: Methods, Challenges, and Future Directions},
  journal = {International Journal of Communication Systems and Network Technologies},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {01--32},
  doi = {10.18486/ijcsnt/15.1.001}
}
Kostenlos starten →