Assessing the feasibility of classifying toe-walking severity in children with cerebral palsy using a sensorized shoe

The clinical management of children with cerebral palsy (CP) relies on monitoring changes in the severity of gait abnormalities and on planning appropriate clinical interventions. Currently available technology does not make it possible to perform clinical gait evaluations as often as it would be desirable from a clinical standpoint. The use of wearable technology (e.g. a sensorized shoe) could provide an effective means to monitor changes in the severity of gait abnormalities in children with CP. In this paper, we studied a group of children with CP who showed an equinus (i.e. toe-walking) gait pattern, a gait abnormality often observed in children with CP. The aim of the study was to determine the feasibility of relying upon a sensorized shoe to assess changes in the severity of toe-walking. We demonstrated that it is possible to use features extracted from the center of pressure trajectory and ankle kinematics to predict the severity of toe-walking. Our results motivate the development and clinical testing of a sensorized shoe to assess changes in gait patterns that accompany the development, and the response to clinical interventions, of children with CP.

[1]  Susan J Hillman,et al.  Edinburgh Visual Gait Score for Use in Cerebral Palsy , 2003, Journal of pediatric orthopedics.

[2]  Kimberly A. Ganley Augmentative and Alternative Communication , 1994 .

[3]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[4]  J. Perry,et al.  Toe walking: muscular demands at the ankle and knee. , 2003, Archives of physical medicine and rehabilitation.

[5]  B. Dan,et al.  A report: the definition and classification of cerebral palsy April 2006 , 2007, Developmental medicine and child neurology. Supplement.

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  Joseph A. Paradiso,et al.  Gait Analysis Using a Shoe-Integrated Wireless Sensor System , 2008, IEEE Transactions on Information Technology in Biomedicine.