EUVIMEDEUVIMED entdecken
Crossref

The Combination of Topological Data Analysis and Mathematical Modeling Improves Sleep Stage Prediction From Consumer-Grade Wearables

Minki P Lee iD, Dae Wook Kim, Caleb Mayer iD, Olivia Walch, Daniel B Forger

Journal of Biological Rhythms · 2024-12 · 39 (6) · 535-553

DOI: 10.1177/07487304241288607 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Biological Rhythms, online erschienen am 18.11.2024. Verfasst von Minki P Lee und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, University of Michigan, Ann Arbor, Michigan, USA. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Polysomnography, Sleep Stages, Algorithms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: NSF DMS, Human Frontiers Science Program Organization, ARO MURI.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wearable devices have become commonplace tools for tracking behavioral and physiological parameters in real-world settings. Nonetheless, the practical utility of these data for clinical and research applications, such as sleep analysis, is hindered by their noisy, large-scale, and multidimensional characteristics. Here, we develop a neural network algorithm that predicts sleep stages by tracking topological features (TFs) of wearable data and model-driven clock proxies (CPs) reflecting the circadian propensity for sleep. To evaluate its accuracy, we apply it to motion and heart rate data from the Apple Watch worn by young subjects undergoing polysomnography (PSG) and compare the predicted sleep stages with the corresponding ground truth PSG records. The neural network that includes TFs and CPs along with raw wearable data as inputs shows improved performance in classifying Wake/REM/NREM sleep. For example, it shows significant improvements in identifying REM and NREM sleep (AUROC/AUPRC improvements >13% and REM/NREM accuracy improvement of 12%) compared with the neural network using only raw data inputs. We find that this improvement is mainly attributed to the heart rate TFs. To further validate our algorithm on a different population, we test it on elderly subjects from the Multi-ethnic Study of Atherosclerosis cohort. This confirms that TFs and CPs contribute to the improvements in Wake/REM/NREM classification. We next compare the performance of our algorithm with previous state-of-the-art wearable-based sleep scoring algorithms and find that our algorithm outperforms them within and across different populations. This study demonstrates the benefits of combining topological data analysis and mathematical modeling to extract hidden inputs of neural networks from puzzling wearable data.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesPolysomnographySleep StagesAlgorithmsHumansMaleFemaleAdultNeural Networks, ComputerHeart RateData AnalysisYoung AdultModels, TheoreticalCircadian Rhythm

Stichwörter der Autor:innen

heart ratemathematical modelingmotionneural network classificationsleep scoringtopological data analysiswearables

Autor:innen und Institutionen

  • Department of Mathematics, University of Michigan, Ann Arbor, Michigan, USA.
  • Department of Brain and Cognitive Sciences, KAIST, Daejeon, Republic of Korea.
  • Department of Mathematics, Sogang University, Seoul, Republic of Korea.
  • Department of Genetics, Stanford University, Stanford, California, USA.
  • Arcascope, Arlington, Virginia, USA.
  • Department of Neurology, University of Michigan, Ann Arbor, Michigan, USA.

ORCID-Profile: Minki P Lee, Caleb Mayer

Förderung

  • NSF DMS
  • Human Frontiers Science Program Organization
  • ARO MURI

Zitieren

APA

Lee, M. P., Kim, D. W., Mayer, C., Walch, O., & Forger, D. B. (2024). The Combination of Topological Data Analysis and Mathematical Modeling Improves Sleep Stage Prediction From Consumer-Grade Wearables. Journal of Biological Rhythms, 39(6), 535-553. https://doi.org/10.1177/07487304241288607

Vancouver

Lee MP, Kim DW, Mayer C, Walch O, Forger DB. The Combination of Topological Data Analysis and Mathematical Modeling Improves Sleep Stage Prediction From Consumer-Grade Wearables. Journal of Biological Rhythms. 2024;39(6):535-553. doi:10.1177/07487304241288607

BibTeX
@article{Lee2024,
  author = {Lee, Minki P and Kim, Dae Wook and Mayer, Caleb and Walch, Olivia and Forger, Daniel B},
  title = {The Combination of Topological Data Analysis and Mathematical Modeling Improves Sleep Stage Prediction From Consumer-Grade Wearables},
  journal = {Journal of Biological Rhythms},
  year = {2024},
  volume = {39},
  number = {6},
  pages = {535--553},
  doi = {10.1177/07487304241288607}
}
Kostenlos starten →