Reduction, classification and ranking of motion analysis data: an application to osteoarthritic and normal knee function data

Abstract

There are certain major obstac les to using motion analysis as an aid to clinical decision making. These include: the difficulty in comprehending large amounts of both corroborating and conflicting information; the subjectivity of data interpretation; the need for visualization; and the quantitative comparison of temporal waveform data. This paper seeks to overcome these obstacles by applying a hybrid approach to the analysis of motion analysis data using principal component analysis (PCA), the Dempster–Shafer (DS) theory of evidence and simplex plots. Specifically, the approach is used to characterise the differences between osteoarthritic (OA) and normal (NL) knee function data and to produce a hierarchy of those variables that are most discriminatory in the classification process. Comparisons of the results obtained with the hybrid approach are made with results from artificial neural network analyses.

Keywords:

• Classification
• Dempster–Shafer theory
• Artificial neural network
• Principal component analysis
• Knee function
• Gait analysis

Acknowledgements

The authors would like to thank Mr Richard Evans and Mr Chris Wilson, Orthopaedic Consultants, University Hospital of Wales, Cardiff; Mr Stuart Roy, Orthopaedic Consultant, Royal Glamorgan Hospital, Pontypridd; and Professor Colin Dent, Orthopaedics and Trauma, University of Wales, College of Medicine.