EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Systematic Literature Review: Predicting Sleep Disorders with Machine Learning

Henry Prajna Susanto, Wella, Friska Natalia

International Journal on Advanced Science, Engineering and Information Technology · 25.04.2026 · 16 (2) · 619-630

DOI: 10.18517/ijaseit.16.2.20726 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift International Journal on Advanced Science, Engineering and Information Technology, online erschienen am 25.04.2026. Verfasst von Henry Prajna Susanto und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study comprehensively investigates the application of machine learning (ML) to forecasting and mitigating sleep problems. The study focuses on identifying significant opportunities, evaluating existing platforms, and assessing the challenges of implementing ML in sleep health management. This research synthesizes recent methodologies that employ deep learning, neural networks, and multimodal data integration techniques to predict and manage sleep-related problems. A structured review of 32 peer-reviewed articles published between 2020 and 2024 was conducted to examine current advancements and limitations. The findings are classified into three dimensions: predictive capacities, practical implementations, and operational constraints. Results indicate that ML models, particularly those using adaptive, personalized, and hybrid architectures, have the potential to identify and prevent sleep disorders such as obstructive sleep apnea, hypersomnia, and early insomnia. However, persistent concerns remain regarding the accuracy of sensor data, limited dataset diversity, and the absence of standardized benchmarking frameworks. Wearable devices that enable continuous, real-time monitoring have also emerged as promising tools, yet issues related to sensor calibration and data synchronization remain. Also, this study highlights the challenges of ensuring the generalizability and interpretability of ML models across diverse populations in terms of physiology, demographics, and environments. Future research should prioritize expanding dataset representativeness, enhancing wearable sensor precision, refining multi-modal data fusion techniques, and incorporating explainable AI to improve model transparency. Addressing these challenges will strengthen scalability, accuracy, and clinical integration. Overall, this study underscores the transformative potential of ML in advancing personalized, preventive, and data-driven strategies for managing sleep disorders.

Zitieren

APA

Susanto, H. P., Wella, & Natalia, F. (2026). Systematic Literature Review: Predicting Sleep Disorders with Machine Learning. International Journal on Advanced Science, Engineering and Information Technology, 16(2), 619-630. https://doi.org/10.18517/ijaseit.16.2.20726

Vancouver

Susanto HP, Wella, Natalia F. Systematic Literature Review: Predicting Sleep Disorders with Machine Learning. International Journal on Advanced Science, Engineering and Information Technology. 2026;16(2):619-630. doi:10.18517/ijaseit.16.2.20726

BibTeX
@article{Susanto2026,
  author = {Susanto, Henry Prajna and Wella and Natalia, Friska},
  title = {Systematic Literature Review: Predicting Sleep Disorders with Machine Learning},
  journal = {International Journal on Advanced Science, Engineering and Information Technology},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {619--630},
  doi = {10.18517/ijaseit.16.2.20726}
}
Kostenlos starten →