Multimodal data analysis of knee osteoarthritis assessment: factors selection for conservative care decision making

Abstract

When assessing a patient with knee osteoarthritis (OA), a number of factors are considered to guide treatment plan, namely, demographic, radiographic, clinical, musculoskeletal, and biomechanical factors. The aim of this study is to identify which of these factors are the most related to each other to potentially better prioritize the modifiable factors to be addressed as they may influence treatment outcomes. We investigated a multimodal canonical correlation analysis to evaluate associations between these factors. The analysis was performed on 415 OA patients who were not candidates for knee arthroplasty, to identify factors that are associated to the patients’ clinical conditions.

Keywords:

• Assessment factors
• biomechanical
• clinical
• canonical correlation
• musculoskeletal
• multimodal CCA
• knee osteoarthritis (OA)
• radiographic grade

Acknowledgements

The authors would like to thank the Dr. Manon Choinière, Dr. Nathalie Bureau, Dr. Madeleine Durand, professors, and researchers at the research center of the Centre hospitalier de l’Université de Montréal and Nathaly Gaudreault (professor, University of Sherbrooke) for their contribution in the conception and realization of the cluster randomized controlled trial (RCT).

Disclosure statement

The authors declare no conflict of interest.

Additional information

Funding

This research was supported by the Canada Research Chair on Biomedical Data Mining (950-231214) and The Fonds de partenariat pour un Québec innovant et en santé (Ministry of Economics, innovations and exportations, Province of Quebec, Canada).