Machine Learning Derived Lifting Technique in People without Low Back Pain

Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul:2023:1-4. doi: 10.1109/EMBC40787.2023.10340260.

Abstract

This paper presents a method for determining the number of lifting techniques used by healthy individuals through the analysis of kinematic data collected from 115 participants utilizing an motion capture system. The technique utilizes a combination of feature extraction and Ward's method to analyse the range of motion in the sagittal plane of the knee, hip, and trunk. The findings identified five unique lifting techniques in people without low back pain. The multivariate analysis of variance statistical analysis reveals a significant difference in the range of motion in the trunk, hip and knee between each cluster for healthy people (F (12, 646) = 125.720, p < 0.0001).Clinical Relevance- This information can assist healthcare professionals in choosing effective treatments and interventions for those with occupational lower back pain by focusing rehabilitation on specific body parts associated with problematic lifting techniques, such as the trunk, hip, or knee, which may lead to improved pain and disability outcomes, exemplifying precision medicine.

MeSH terms

  • Humans
  • Knee
  • Knee Joint
  • Lifting
  • Low Back Pain* / diagnosis
  • Low Back Pain* / therapy
  • Lower Extremity
  • Machine Learning