EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accelerometer- and Gyroscope-Based Sensor System for Detecting Swallowing, Speaking, and Coughing Events in ICU Patients

Constantijn Coppers, Stijn Van de Velde iD, Guylian Stevens iD, Jonas Van Der Donckt iD, Marija Stojchevska iD, Sofie Van Hoecke iD, Pascal Verdonck iD

Sensors · 09.11.2026 · 26 (21) · 7089

DOI: 10.3390/s26217089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.11.2026. Verfasst von Constantijn Coppers und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Information Systems-IBiTech, Ghent University, Korneel Heymanslaan, 9000 Ghent, Belgium. Hauptthemen laut MEDLINE: Cough, Deglutition, Accelerometry, Speech. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

(1)

Background

Swallowing, coughing, and speaking are clinically relevant physiological events, but they are not routinely and continuously monitored in intensive care. This study evaluates the feasibility of detecting these events using inertial measurement unit (IMU) signals acquired from the cricoid and thoracic regions. (2)

Methods

Data were collected from 29 patients in the intensive care unit (ICU) during predefined swallowing, coughing, speaking, and movement tasks. A classical machine learning pipeline was developed and evaluated using leave-one-patient-out cross-validation. (3)

Results

Cricoid and thoracic accelerometer signals were informative for event detection, with the thoracic sensor particularly contributing to cough detection. Speaking (F1=0.80), coughing (F1=0.72), and aggregated swallowing (F1=0.74) were detected in this controlled experimental setting. (4)

Conclusions

The results support the feasibility of IMU-based detection of prompted swallowing, coughing, and speaking events in ICU patients. Further validation under spontaneous and clinically heterogeneous conditions is required before continuous clinical monitoring can be assessed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CoughDeglutitionAccelerometrySpeechHumansIntensive Care UnitsMonitoring, PhysiologicFemaleMaleAgedMiddle AgedSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

cough detectioninertial measurement unitintensive care unitspeech detectionswallowing detection

Autor:innen und Institutionen

  • Department of Electronics and Information Systems-IBiTech, Ghent University, Korneel Heymanslaan, 9000 Ghent, Belgium.
  • Partnership of Anesthesia, vzw Maria Middelares, Buitenring Sint-Denijs 30, 9000 Ghent, Belgium.
  • Department CTO, vzw Maria Middelares, Buitenring Sint-Denijs 30, 9000 Ghent, Belgium.
  • IDLab, Department of Electronics and Information Systems, Ghent University-Imec, Technologiepark-Zwijnaarde 122, 9052 Zwijnaarde, Belgium.

ORCID-Profile: Stijn Van de Velde, Guylian Stevens, Jonas Van Der Donckt, Marija Stojchevska, Sofie Van Hoecke, Pascal Verdonck

Zitieren

APA

Coppers, C., Velde, S. V., Stevens, G., Donckt, J. V., Stojchevska, M., Van Hoecke, S., & Verdonck, P. (2026). Accelerometer- and Gyroscope-Based Sensor System for Detecting Swallowing, Speaking, and Coughing Events in ICU Patients. Sensors, 26(21), 7089. https://doi.org/10.3390/s26217089

Vancouver

Coppers C, Velde SV, Stevens G, Donckt JV, Stojchevska M, Van Hoecke S, et al. Accelerometer- and Gyroscope-Based Sensor System for Detecting Swallowing, Speaking, and Coughing Events in ICU Patients. Sensors. 2026;26(21):7089. doi:10.3390/s26217089

BibTeX
@article{Coppers2026,
  author = {Coppers, Constantijn and Velde, Stijn Van de and Stevens, Guylian and Donckt, Jonas Van Der and Stojchevska, Marija and Van Hoecke, Sofie and Verdonck, Pascal},
  title = {Accelerometer- and Gyroscope-Based Sensor System for Detecting Swallowing, Speaking, and Coughing Events in ICU Patients},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {7089},
  doi = {10.3390/s26217089}
}
Kostenlos starten →