Deep learning model for classifying shoulder pain rehabilitation exercises using IMU sensor.

Journal: Journal of neuroengineering and rehabilitation
PMID: 38539223

Abstract

BACKGROUND: Artificial intelligence is being used for rehabilitation, including monitoring exercise compliance through sensor technology. AI classification of shoulder exercise wearing an IMU sensor has only been reported in normal (i.e. painless) subjects. To prove the feasibility of monitoring exercise compliance, we aimed to classify 11 types of shoulder rehabilitation exercises using an AI (artificial intelligence) algorithm in patients with shoulder pain. We had the patients wear an IMU-based sensor, collected data during exercise, and determined the accuracy of exercise classification.

Authors

  • Kyuwon Lee
    Dept. of Rehabilitation Medicine, Seoul Metropolitan Government Boramae Medical Center, Seoul, South Korea.
  • Jeong-Hyun Kim
    Department of Medicine, University of Ulsan College of Medicine, Seoul, 05505, Republic of Korea.
  • Hyeon Hong
    Dept. of Rehabilitation Medicine, Seoul Metropolitan Government Boramae Medical Center, Seoul, South Korea.
  • Yeji Jeong
    Dept. of Rehabilitation Medicine, Seoul Metropolitan Government Boramae Medical Center, Seoul, South Korea.
  • Hokyoung Ryu
    Dept. of Graduate School of Technology and Innovation Management, Hanyang University, Seoul, South Korea.
  • Hyundo Kim
    Dept. of Intelligence Computing, Hanyang University, Seoul, South Korea.
  • Shi-Uk Lee

Keywords

External Resources

Popular Topics
Recent Journals