Classification of chronic whiplash associated disorders with artificial neural networks

Author

Öhberg, F. ; Grip, H. ; Sterner, Y. ; Wiklund, U. ; Nystrom, L. ; Karlsson, S. ; Bäcklund, T. ; Gerdle, B.

Author_Institution

Dept. of Biomed. Eng. & Informatics, Univ. Hosp., Linkoping, Sweden

Volume

2

fYear

2001

fDate

2001

Firstpage

1951

Abstract

This study present a new method for classification of subjects suffering from whiplash associated disorders (WAD) with a supervised resilient backpropagation neural network (BPN). The only input needed, from each subject, is features extracted from 3-dimensional motion data collected by a ProReflex system. The analysis with BPN results in a correct prediction for 84% of normal subjects and 89% percent of subjects with WAD.

Keywords

backpropagation; biomechanics; data reduction; feature extraction; feedforward neural nets; mechanoception; medical diagnostic computing; principal component analysis; ProReflex system; cervical motion; chronic whiplash associated disorders; classification method; feedforward ANN; head movements; helical angle; neck movement pattern; principal component analysis; proprioception; reaction time; software-based method; supervised resilient backpropagation neural network; three dimensional motion data; whiplash injury; Accidents; Artificial neural networks; Back; Biological neural networks; Biomedical engineering; Biomedical imaging; Injuries; Motion analysis; Neck; Optical imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE

ISSN

1094-687X

Print_ISBN

0-7803-7211-5

Type

conf

DOI

10.1109/IEMBS.2001.1020610

Filename

1020610