EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Making Sense of Shoulder Exercise: Measuring the Accuracy of an Artificial Intelligence Model to Classify Shoulder Exercise via Wearable Sensors Among People With and Without Rotator Cuff Tendinopathy

Josh Naunton iD, Yanran Jiang, Rodrigo Bini, Dawson Kidgell, Kim Bennell, Terry Haines, Dana Kulić, Peter Malliaras

European Journal of Sport Science · 2026-05 · 26 (5)

DOI: 10.1002/ejsc.70167 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Sport Science, online erschienen am 08.04.2026. Verfasst von Josh Naunton und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physiotherapy, School of Primary and Allied Health Care, Faculty of Medicine, Nursing and Health Science, Monash Musculoskeletal Resear…. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Tendinopathy, Shoulder, Rotator Cuff. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aimed to compare the accuracy of machine learning classification for three commonly prescribed shoulder exercises in people with and without rotator cuff tendinopathy. Eighteen participants with rotator cuff tendinopathy (mean age 54.2, SD 13.2; 50% female), followed by eighteen matched controls completed a laboratory‐based shoulder strength testing protocol. Three exercises were performed (shoulder press, lateral raise and bent over row) while wearing three inertial measurement (IMU) sensors (Axivity, Ax6 ‐ 3 axis accelerometry and gyroscope at 100 Hz and 1000°/sec respectively) positioned on the wrist arm and trunk. Data were analysed and accuracy was compared between common machine learning algorithms for those with rotator cuff tendinopathy and healthy matched controls in a subject‐dependent and subject‐independent model. The best accuracy scores for the subject‐dependent results were achieved by a random forest algorithm; 96.12% (3‐sensor combined system) for those with rotator cuff tendinopathy. For the subject‐independent results best accuracy scores were achieved by a convolutional neural network algorithm; 94.55% (3‐sensors) for the healthy controls without shoulder pain. K‐fold cross validation confusion matrix results by exercise type for the entire cohort show 97% accuracy (shoulder press), 95.5% (lateral raise) and 90.7% (bent over row) (3‐sensors, CNN subject‐independent analysis). Machine learning classification of 3 different shoulder exercises in people with rotator cuff tendinopathy and matched healthy controls demonstrate most accurate results using a CNN algorithm for subject‐independent analysis and a RF algorithm for subject‐dependent analysis. Results were similar for both those with rotator cuff tendinopathy and their matched healthy controls.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesTendinopathyShoulderRotator CuffExerciseExercise TherapyArtificial IntelligenceHumansFemaleMiddle AgedMaleAdultMachine LearningAccelerometryAgedCase-Control StudiesRandom ForestAlgorithmsClassification AlgorithmsConvolutional Neural Networks

Stichwörter der Autor:innen

IMUexercisemachine learning artificial intelligencerotator cuff tendinopathywearables

Autor:innen und Institutionen

  • Department of Physiotherapy, School of Primary and Allied Health Care, Faculty of Medicine, Nursing and Health Science, Monash Musculoskeletal Research Unit (MMRU), Monash University, Melbourne, Australia.
  • Department of Rural Allied Health, La Trobe University Rural Health School, Bendigo, Australia.
  • Physiotherapy & Exercise Physiology, Allied Health and Continuing Care, Bendigo Health, Bendigo, Australia.
  • Department of Mechanical and Aerospace Engineering, Faculty of Engineering, Monash University, Melbourne, Australia.
  • Department of Physiotherapy, School of Primary and Allied Health Care, Faculty of Medicine, Nursing and Health Science, Monash Exercise Neuroplasticity Unit, Monash University, Melbourne, Australia.
  • Centre for Health, Exercise and Sports Medicine, Department of Physiotherapy, Faculty of Medicine, Dentistry and Health Sciences, Level 7, The University of Melbourne, Melbourne, Australia.

ORCID-Profile: Josh Naunton

Zitieren

APA

Naunton, J., Jiang, Y., Bini, R., Kidgell, D., Bennell, K., Haines, T., Kulić, D., & Malliaras, P. (2026). Making Sense of Shoulder Exercise: Measuring the Accuracy of an Artificial Intelligence Model to Classify Shoulder Exercise via Wearable Sensors Among People With and Without Rotator Cuff Tendinopathy. European Journal of Sport Science, 26(5). https://doi.org/10.1002/ejsc.70167

Vancouver

Naunton J, Jiang Y, Bini R, Kidgell D, Bennell K, Haines T, et al. Making Sense of Shoulder Exercise: Measuring the Accuracy of an Artificial Intelligence Model to Classify Shoulder Exercise via Wearable Sensors Among People With and Without Rotator Cuff Tendinopathy. European Journal of Sport Science. 2026;26(5). doi:10.1002/ejsc.70167

BibTeX
@article{Naunton2026,
  author = {Naunton, Josh and Jiang, Yanran and Bini, Rodrigo and Kidgell, Dawson and Bennell, Kim and Haines, Terry and Kulić, Dana and Malliaras, Peter},
  title = {Making Sense of Shoulder Exercise: Measuring the Accuracy of an Artificial Intelligence Model to Classify Shoulder Exercise via Wearable Sensors Among People With and Without Rotator Cuff Tendinopathy},
  journal = {European Journal of Sport Science},
  year = {2026},
  volume = {26},
  number = {5},
  doi = {10.1002/ejsc.70167}
}
Kostenlos starten →