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 unknowns. 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 modes were categorised as three patterns, i.e., normal, pre- and post-treatments. RESULTS: 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 models can be used in clinical practice to recognise the gait pattern for cerebral palsy patients.
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 unknowns. 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 modes were categorised as three patterns, i.e., normal, pre- and post-treatments. RESULTS: 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 models can be used in clinical practice to recognise the gait pattern for cerebral palsypatients.
Authors: Bhargava Teja Nukala; Taro Nakano; Amanda Rodriguez; Jerry Tsay; Jerry Lopez; Tam Q Nguyen; Steven Zupancic; Donald Y C Lie Journal: Biosensors (Basel) Date: 2016-11-29