EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed

Eliza Becker iD, Siavash Khaksar iD, Harry Booker, Kylie Hill iD, Yifei Ren, Tele Tan iD, Carol Watson, Ethan Wordsworth iD, Meg Harrold

Sensors · 2025

DOI: 10.3390/s25020499 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Eliza Becker und 8 weiteren Autor:innen. Beteiligte Einrichtung: Curtin School of Allied Health, Curtin University, Perth 6102, Australia. Hauptthemen laut MEDLINE: Machine Learning, Posture. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: RPH Research Foundation, Royal Perth Hospital Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In hospitals, timely interventions can prevent avoidable clinical deterioration. Early recognition of deterioration is vital to stopping further decline. Measuring the way patients position themselves in bed and change their positions may signal when further assessment is necessary. While inertial measurement units (IMUs) have been used in health research, their use inside hospitals has been limited. This study explores the use of IMUs with machine learning to continuously capture, classify and visualise patient positions in hospital beds. The participants attended a data collection session in a simulated hospital bedspace and were asked to adopt nine positions. Movement data were captured using five IMU Xsens DOTs attached to the forehead, wrists and ankles. Support Vector Machine (SVM) and K-Nearest Neighbours classifiers were trained using five different combinations of sensors (e.g., right wrist only, right and left wrist) to determine body positions. Data from 30 participants were analysed. The highest accuracy (87.7%) was achieved by SVM using forehead and wrist sensors. Adding data from ankle sensors reduced the accuracy. To preserve patient privacy in a hospital setting, a 3D visualisation was developed in Unity, offering a non-identifiable representation of patient positions. This system could help clinicians monitor changes in position which may signal clinical deterioration.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPostureHumansSupport Vector MachineAdultMaleFemaleBedsMonitoring, PhysiologicHospitalsMovementWrist

Stichwörter der Autor:innen

healthcareinertial measurement unitsmachine learningmonitoring

Autor:innen und Institutionen

  • Curtin School of Allied Health, Curtin University, Perth 6102, Australia.
  • Virtual Care and Community Care, East Metropolitan Health Service, Perth 6000, Australia.
  • School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Perth 6102, Australia.
  • Physiotherapy Department, Royal Perth Hospital, Perth 6000, Australia.

ORCID-Profile: Eliza Becker, Siavash Khaksar, Kylie Hill, Tele Tan, Ethan Wordsworth

Förderung

  • RPH Research Foundation
  • Royal Perth Hospital Research Foundation

Zitieren

APA

Becker, E., Khaksar, S., Booker, H., Hill, K., Ren, Y., Tan, T., Watson, C., Wordsworth, E., & Harrold, M. (2025). Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed. Sensors. https://doi.org/10.3390/s25020499

Vancouver

Becker E, Khaksar S, Booker H, Hill K, Ren Y, Tan T, et al. Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed. Sensors. 2025. doi:10.3390/s25020499

BibTeX
@article{Becker2025,
  author = {Becker, Eliza and Khaksar, Siavash and Booker, Harry and Hill, Kylie and Ren, Yifei and Tan, Tele and Watson, Carol and Wordsworth, Ethan and Harrold, Meg},
  title = {Using Inertial Measurement Units and Machine Learning to Classify Body Positions of Adults in a Hospital Bed},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25020499}
}
Kostenlos starten →