• Jan Muhammad Department of Orthopaedic and Trauma Surgery, University of Dundee
  • Sheila Gibbs Department of Orthopaedic and Trauma Surgery, University of Dundee
  • Rami Abbound Department of Orthopaedic and Trauma Surgery, University of Dundee
  • Sambandam Anand Department of Orthopaedic and Trauma Surgery, University of Dundee
  • Weijie Wang Ninewells Hospital and Medical School, Dundee


Background: Interpretation of gait data obtained from modern 3D gait analysis is a challenging and time consuming task. The aim of this study was to create neural network models which can recognise the gait patterns from pre- and post-treatment and the normal ones. Neural network is a method which works on the principle of learning from experience and then uses the obtained knowledge to predict the unknown. Methods: Twenty-eight patients with cerebral palsy were recruited as subjects whose gait was analysed in pre- and post-treatment. A group of twenty-six normal subjects also participated in this study as control group. All subjects’ gait was analysed using Vicon Nexus® to obtain the gait parameters and kinetic and kinematic parameters of hip, knee and ankle joints in three planes of both limbs. The gait data was used as input to create neural network models. A total of approximately 300 trials were split into 70% and 30% to train and test the models, respectively. Different models were built using different parameters. The gait was categorised as three patterns, i.e., normal, pre- and post-treatments. Result: The results showed that the models using all parameters or using the joint angles and moments could predict the gait patterns with approximately 95% accuracy. Some of the models e.g., the models using joint power and moments, had lower rate in recognition of gait patterns with approximately 70–90% successful ratio. Conclusion: Neural network model can be used in clinical practice to recognise the gait pattern for cerebral palsy patients.


Bax MC. Terminology and classification of cerebral palsy. Dev Med Child Neurol 1964;6:295–307.

Lofterød B, Terjesen T, Skaaret I, Huse A-B, Jahnsen R. Preoperative gait analysis has a substantial effect on orthopedic decision making in children with cerebral palsy: comparison between clinical evaluation and gait analysis in 60 patients. Acta Orthop 2007;78(1):74–80.

Gage JR. Gait Analysis. An essential tool in the treatment of cerebral palsy. Clin Orthop Relat Res 1993;(288):126–34.

Desloover K, Molenares G, Jonkers I, De Cat J, De Borre L, Nijs J, et al. A randomised study of combined botulinum toxin type measures. Eur J Neurol 2001;8(Suppl 5):75–87.

Deluca PA, Davis RB 3rd, Ounpuu S, Rose S, Sirkin R. Alterations in surgical decision making in patients with cerebral palsy based on three-dimensional gait analysis. J Paediatr Orthop 1997;17(5):608–14.

Miller A. Gait event detection using a multilayer neural network. Gait Posture 2009;29(4):542–5.

Hersh LA, Sun JQ, Richards JG, Miller F. The prediction of post-operative gait patterns using neural networks. Gait Posture 1997;5(2):151.

Kaczmarczyk K, Wit A, Krawczyk M, Zaborski J. Gait classification in post-stroke patients using artificial neural networks. Gait Posture 2009;30(2):207–10.

Barton G, Lisboa P, Lees A, Attfield S. Gait quality assessment using self-organising artificial neural networks. Gait Posture 2007;25(3):374–9.

Holzreiter SH, Kohle ME. Assessment of gait patterns using neural networks. J Biomech 1993;26(6):645–51.