A machine learning approach using gait parameters to cluster TKA subjects into stable and unstable joints for discovery analysis.

Journal: The Knee
Published Date: Mar 11, 2025

Abstract

BACKGROUND: Patient-reported joint instability after total knee arthroplasty (TKA) is difficult to quantify objectively. Here, we apply machine learning to cluster TKA subjects using nine literature-proposed gait parameters as knee instability predictors and explore cluster reliability and consistency with self-organizing map (SOM) and k-means computation.

Authors

  • Erica M Ramirez
    Department of Orthopedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL 60612, USA.
  • Kathrin Ebinger
    Department of Orthopedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL 60612, USA.
  • Denis Nam
    Department of Orthopedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL 60612, USA.
  • Christopher Ferrigno
    Department of Orthopedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL 60612, USA.
  • Markus A Wimmer
    Department of Orthopedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL 60612, USA. Electronic address: markus_a_wimmer@rush.edu.

Keywords

External Resources

Popular Topics
Recent Journals