Automated error detection in physiotherapy training

Marko Jovanović, Johannes Seiffarth, Ekaterina Kutafina, Stephan M. Jonas

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Background: Manual skills teaching, such as physiotherapy education, requires immediate teacher feedback for the students during the learning process, which to date can only be performed by expert trainers. Objectives: A machinelearning system trained only on correct performances to classify and score performed movements, to identify sources of errors in the movement and give feedback to the learner. Methods: We acquire IMU and sEMG sensor data from a commercial-grade wearable device and construct an HMM-based model for gesture classification, scoring and feedback giving. We evaluate the model on publicly available and self-generated data of an exemplary movement pattern executions. Results: The model achieves an overall accuracy of 90.71% on the public dataset and 98.9% on our dataset. An AUC of 0.99 for the ROC of the scoring method could be achieved to discriminate between correct and untrained incorrect executions. Conclusion: The proposed system demonstrated its suitability for scoring and feedback in manual skills training.

Original languageEnglish
Title of host publicationHealth Informatics Meets eHealth
Subtitle of host publicationBiomedical Meets eHealth - From Sensors to Decisions - Proceedings of the 12th eHealth Conference
EditorsGunter Schreier, Dieter Hayn
PublisherIOS Press BV
Pages164-171
Number of pages8
ISBN (Electronic)9781614998570
DOIs
StatePublished - 2018
Externally publishedYes
Event12th Annual Conference on Health Informatics Meets eHealth, eHealth 2018 - Vienna, Austria
Duration: 8 May 20189 May 2018

Publication series

NameStudies in Health Technology and Informatics
Volume248
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference12th Annual Conference on Health Informatics Meets eHealth, eHealth 2018
Country/TerritoryAustria
CityVienna
Period8/05/189/05/18

Keywords

  • Education
  • Feedback
  • Gestures
  • Machine Learning
  • Wearable Technology
  • mHealth

Fingerprint

Dive into the research topics of 'Automated error detection in physiotherapy training'. Together they form a unique fingerprint.

Cite this