EUVIMEDOpdag EUVIMED
ValidierungsstudieOpen access

Unobtrusive Nighttime Movement Monitoring to Support Nursing Home Continence Care: Algorithm Development and Validation Study

Unaufdringliches nächtliches Bewegungsmonitoring zur Unterstützung der Kontinenzpflege im Pflegeheim: Entwicklung und Validierung eines Algorithmus

Hannelore Strauven iD, Chunzhuo Wang iD, Hans Hallez iD, Vero Vanden Abeele iD, Bart Vanrumste iD

JMIR Nursing · 2024-12-24 · 7 · e58094-e58094

DOI: 10.2196/58094 ↗

Auf einen Blick

Bei 6 Teilnehmenden wurde ein Sensor-System zur nächtlichen Bewegungsüberwachung im Pflegebett geprüft. Das Modell erreichte einen Gesamt-F1-Score von 79,56 % und für „Agitation“ 79,67 %.

Fragestellung

Kann ein unaufdringliches Sensorsystem nächtliche Bewegungen von Pflegeheimbewohner:innen zur Unterstützung der Kontinenzpflege erfassen?

Methode

6 Teilnehmende; 7-Schritte-Protokoll; 20-Sekunden-Fenster mit 50 % Überlappung; 4 Aktivitätsklassen; 1.416 Merkmale; XGBoost; Validierung per LOSOCV.

Ergebnisse

Das trainierte Modell erreichte einen Gesamt-F1-Score von 79,56 % für alle Klassen und einen F1-Score von 79,67 % für die Klasse „Agitation“.

Schlussfolgerung der Autor:innen

Die Ergebnisse liefern laut Autor:innen vielversprechende Hinweise für unaufdringliches nächtliches Bewegungsmonitoring und das Potenzial, die Pflegequalität in Pflegeheimen zu verbessern.

Kernaussagen

  • Gesamt-F1-Score: 79,56 %
  • F1-Score für „Agitation“: 79,67 %
  • Validierung mit LOSOCV bei 6 Teilnehmenden

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Validierungsstudie in JMIR Nursing, published online on 2024-12-24. Written by Hannelore Strauven and 4 co-authors. Institution: e-Media Research Lab/STADIUS, Department of Electrical Engineering, KU Leuven, Andreas Vesaliusstraat 13, Leuven, 3000, Belgium, +32 16377662. Major MEDLINE topics: Nursing Homes, Urinary Incontinence, Algorithms. Cited 8 times so far (Crossref); 49 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

The rising prevalence of urinary incontinence (UI) among older adults, particularly those living in nursing homes (NHs), underscores the need for innovative continence care solutions. The implementation of an unobtrusive sensor system may support nighttime monitoring of NH residents’ movements and, more specifically, the agitation possibly associated with voiding events.

Objective

This study aims to explore the application of an unobtrusive sensor system to monitor nighttime movement, integrated into a care bed with accelerometer sensors connected to a pressure-redistributing care mattress.

Methods

A total of 6 participants followed a 7-step protocol. The obtained dataset was segmented into 20-second windows with a 50% overlap. Each window was labeled with 1 of the 4 chosen activity classes: in bed, agitation, turn, and out of bed. A total of 1416 features were selected and analyzed with an XGBoost algorithm. At last, the model was validated using leave one subject out cross-validation (LOSOCV).

Results

The trained model attained a trustworthy overall F 1 -score of 79.56% for all classes and, more specifically, an F 1 -score of 79.67% for the class “Agitation.” Conclusions The results from this study provide promising insights in unobtrusive nighttime movement monitoring. The study underscores the potential to enhance the quality of care for NH residents through a machine learning model based on data from accelerometers connected to a viscoelastic care mattress, thereby driving progress in the field of continence care and artificial intelligence–supported health care for older adults.

Subjects

MeSH terms (MEDLINE)

Nursing HomesUrinary IncontinenceAlgorithmsHumansMaleFemaleAgedAged, 80 and overMonitoring, PhysiologicAccelerometryMovement

Author keywords

accelerometeragitationenuresisincontinencenursing homesensor technologyunobtrusive

Authors and institutions

  • e-Media Research Lab/STADIUS, Department of Electrical Engineering, KU Leuven, Andreas Vesaliusstraat 13, Leuven, 3000, Belgium, +32 16377662.
  • Research Group M-Group/DistriNet, Department of Computer Science, KU Leuven, Brugge, Belgium.
  • e-Media Research Lab/Human-Computer Interaction, Department of Computer Science, KU Leuven, Leuven, Belgium.

ORCID profiles: Hannelore Strauven, Chunzhuo Wang, Hans Hallez, Vero Vanden Abeele, Bart Vanrumste

Cite

APA

Strauven, H., Wang, C., Hallez, H., Vanden Abeele, V., & Vanrumste, B. (2024). Unobtrusive Nighttime Movement Monitoring to Support Nursing Home Continence Care: Algorithm Development and Validation Study. JMIR Nursing, 7, e58094-e58094. https://doi.org/10.2196/58094

Vancouver

Strauven H, Wang C, Hallez H, Vanden Abeele V, Vanrumste B. Unobtrusive Nighttime Movement Monitoring to Support Nursing Home Continence Care: Algorithm Development and Validation Study. JMIR Nursing. 2024;7:e58094-e58094. doi:10.2196/58094

BibTeX
@article{Strauven2024,
  author = {Strauven, Hannelore and Wang, Chunzhuo and Hallez, Hans and Vanden Abeele, Vero and Vanrumste, Bart},
  title = {Unobtrusive Nighttime Movement Monitoring to Support Nursing Home Continence Care: Algorithm Development and Validation Study},
  journal = {JMIR Nursing},
  year = {2024},
  volume = {7},
  pages = {e58094--e58094},
  doi = {10.2196/58094}
}
Start for free →