Related Experiment Video
Updated: Jul 3, 2025
Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
Published on: March 4, 2018
Towards a diagnostic tool for neurological gait disorders in childhood combining 3D gait kinematics and deep learning
Zhengyang Lan1, Mathieu Lempereur2, Gwenael Gueret3
1Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; IMT Atlantique, LaTIM U1101 INSERM, Brest, France.
Insights
Deep learning combined with 3D gait analysis accurately diagnoses childhood gait disorders. This approach enhances diagnostic capabilities for various conditions, moving beyond simple assessment.
Area of Science:
- Biomedical Engineering
- Pediatric Neurology
- Data Science
Background:
- Gait abnormalities are common in children, stemming from diverse conditions like cerebral palsy and neuromuscular diseases.
- Three-dimensional (3D) gait analysis offers valuable clinical insights but is underutilized for diagnosis due to inconsistent data collection.
- Current 3D gait analysis primarily serves as an assessment tool rather than a diagnostic one.
Purpose of the Study:
- To investigate the potential of combining deep learning with 3D gait analysis for diagnosing pediatric gait disorders.
- To evaluate the diagnostic accuracy of deep learning models in differentiating between healthy and pathological gaits, and various etiologies.
Main Methods:
- Utilized 3D gait analysis data from 371 children, encompassing various pathologies and typically developing individuals, totaling 6400 gait cycles.
- Applied deep learning architectures (ResNet, LSTM, InceptionTime) for time-series data analysis to predict gait disorder diagnoses.
- Assessed model performance using accuracy, sensitivity, specificity, F1 score, AUC, and confusion matrix.
Main Results:
- Deep learning models achieved high diagnostic accuracy (0.77-0.99) in distinguishing healthy from pathological gaits and classifying different gait disorder etiologies.
- The Long Short-Term Memory (LSTM) architecture demonstrated the best overall performance among the evaluated models.
- The study confirmed that gait patterns contain specific, pathology-related information detectable by deep learning.
Conclusions:
- Deep learning integration with 3D gait analysis can effectively diagnose pediatric gait disorders, expanding its clinical utility from assessment to diagnosis.
- The proposed data-driven model operates without human intervention, offering a scalable diagnostic solution.
- This methodology holds promise for identifying and characterizing a broader range of gait pathologies and their onset times.
Abstract:
Gait abnormalities are frequent in children and can be caused by different pathologies, such as cerebral palsy, neuromuscular disease, toe walker syndrome, etc. Analysis of the "gait pattern" (i.e., the way the person walks) using 3D analysis provides highly relevant clinical information. This information is used to guide therapeutic choices; however, it is underused in diagnostic processes, probably because of the lack of standardization of data collection methods. Therefore, 3D gait analysis is currently used as an assessment rather than a diagnostic tool. In this work, we aimed to determine if deep learning could be combined with 3D gait analysis data to diagnose gait disorders in children. We tested the diagnostic accuracy of deep learning methods combined with 3D gait analysis data from 371 children (148 with unilateral cerebral palsy, 60 with neuromuscular disease, 19 toe walkers, 60 with bilateral cerebral palsy, 25 stroke, and 59 typically developing children), with a total of 6400 gait cycles. We evaluated the accuracy, sensitivity, specificity, F1 score, Area Under the Curve (AUC) score, and confusion matrix of the predictions by ResNet, LSTM, and InceptionTime deep learning architectures for time series data. The deep learning-based models had good to excellent diagnostic accuracy (ranging from 0.77 to 0.99) for discrimination between healthy and pathological gait, discrimination between different etiologies of pathological gait (binary and multi-classification); and determining stroke onset time. LSTM performed best overall. This study revealed that the gait pattern contains specific, pathology-related information. These results open the way for an extension of 3D gait analysis from evaluation to diagnosis. Furthermore, the method we propose is a data-driven diagnostic model that can be trained and used without human intervention or expert knowledge. Furthermore, the method could be used to distinguish gait-related pathologies and their onset times beyond those studied in this research.
