Related Experiment Video
Updated: Sep 16, 2025
3D Kinematic Gait Analysis for Preclinical Studies in Rodents
Published on: August 3, 2019
Entropy, Irreversibility, and Time-Series Deep Learning of Kinematic and Kinetic Data for Gait Classification in
Alfonso de Gorostegui1,2, Massimiliano Zanin3, Juan-Andrés Martín-Gonzalo4
1PhD Program in Neuroscience, Universidad Autonoma de Madrid-Cajal Institute, 28029 Madrid, Spain.
Insights
Statistical physics metrics accurately differentiate paediatric gait disorders like idiopathic toe walking (ITW), cerebral palsy (CP), and hereditary spastic paraplegia (HSP), matching Deep Learning model performance. Gait analysis shows disease-specific patterns but inter-laboratory data variations impact generalizability.
Area of Science:
- Biomechanical analysis
- Computational physics
- Paediatric neurology
Background:
- Current gait analysis methods for paediatric neurological conditions lack precision, leading to misdiagnosis.
- Existing approaches often analyze isolated gait variables, neglecting complex biomechanical patterns and motor control strategies.
- Previous studies explored statistical physics for gait, but integrating kinematic/kinetic data and comparing with Deep Learning models is needed.
Purpose of the Study:
- To evaluate the robustness of statistical physics metrics in differentiating normal and abnormal paediatric gait patterns.
- To quantify the impact of data source on model performance for gait analysis.
- To compare the classification accuracy of statistical physics metrics against Deep Learning models.
Main Methods:
- Gait data from 81 children with ITW, 300 with CP, 20 with HSP, and 127 controls were analyzed.
- Shannon's entropy, permutation entropy, weighted permutation entropy, and time irreversibility metrics were derived from kinematic and kinetic data.
- Random Forest models were used, and their performance was compared to a ResNet Deep Learning model.
Main Results:
- Statistical physics metrics achieved classification scores comparable to ResNet, differentiating impaired gait patterns.
- Disease-specific patterns in gait predictability and temporal organization related to age and walking speed were observed.
- Inter-laboratory performance variations were noted, limiting model generalizability.
Conclusions:
- Statistical physics metrics are valuable for classifying paediatric gait disorders, including various toe walking conditions.
- Multimetric integration is essential for improving diagnostic accuracy and understanding gait disorders.
- Further research should address inter-laboratory data consistency for enhanced model generalizability.
Abstract:
The use of gait analysis to differentiate among paediatric populations with neurological and developmental conditions such as idiopathic toe walking (ITW), cerebral palsy (CP), and hereditary spastic paraplegia (HSP) remains challenging due to the insufficient precision of current diagnostic approaches, leading in some cases to misdiagnosis. Existing methods often isolate the analysis of gait variables, overlooking the whole complexity of biomechanical patterns and variations in motor control strategies. While previous studies have explored the use of statistical physics principles for the analysis of impaired gait patterns, gaps remain in integrating both kinematic and kinetic information or benchmarking these approaches against Deep Learning models. This study evaluates the robustness of statistical physics metrics in differentiating between normal and abnormal gait patterns and quantifies how the data source affects model performance. The analysis was conducted using gait data sets from two research institutions in Madrid and Dublin, with a total of 81 children with ITW, 300 with CP, 20 with HSP, and 127 typically developing children as controls. From each kinematic and kinetic time series, Shannon's entropy, permutation entropy, weighted permutation entropy, and time irreversibility metrics were derived and used with Random Forest models. The classification accuracy of these features was compared to a ResNet Deep Learning model. Further analyses explored the effects of inter-laboratory comparisons and the spatiotemporal resolution of time series on classification performance and evaluated the impact of age and walking speed with linear mixed models. The results revealed that statistical physics metrics were able to differentiate among impaired gait patterns, achieving classification scores comparable to ResNet. The effects of walking speed and age on gait predictability and temporal organisation were observed as disease-specific patterns. However, performance differences across laboratories limit the generalisation of the trained models. These findings highlight the value of statistical physics metrics in the classification of children with different toe walking conditions and point towards the need of multimetric integration to improve diagnostic accuracy and gain a more comprehensive understanding of gait disorders.
