A-GAS: A Probabilistic Approach for Generating Automated Gait Assessment Score for Cerebral Palsy Children

Identification and interpretation of gait analysis features and foot conditions by explainable AI

Clinical gait analysis is a crucial step for identifying foot disorders and planning surgery. Automating this process is essential for efficiently assessing the substantial amount of gait data. In this study, we explored the potential of state-of-the-art machine learning (ML) and explainable artificial intelligence (XAI) algorithms to automate all various steps involved in gait analysis for six specific foot conditions. To address the complexity of gait data, we manually created new features, followed by recursive feature elimination using Support Vector Machines (SVM) and Random Forests (RF) to eliminate low-variance features. SVM, RF, K-nearest Neighbor (KNN), and Logistic Regression (LREGR) were compared for classification, with a Majority Voting (MV) model combining trained models. KNN and MV achieved mean balanced accuracy, recall, precision, and F1 score of 0.87. All models were interpreted using Local Interpretable Model-agnostic Explanation (LIME) method and the five most relevant features were identified for each foot condition. High success scores indicate a strong relationship between selected features and foot conditions, potentially indicating clinical relevance. The proposed ML pipeline, adaptable for other foot conditions, showcases its potential in aiding experts in foot condition identification and planning surgeries.

Towards a diagnostic tool for neurological gait disorders in childhood combining 3D gait kinematics and deep learning

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.

Interpretable classification for multivariate gait analysis of cerebral palsy

BACKGROUND

The Gross Motor Function Classification System (GMFCS) is a widely used tool for assessing the mobility of people with Cerebral Palsy (CP). It classifies patients into different levels based on their gross motor function and its level is typically determined through visual evaluation by a trained expert. Although gait analysis is commonly used in CP research, the functional aspects of gait patterns has yet to be fully exploited. By utilizing the gait patterns to predict GMFCS, we can gain a more comprehensive understanding of how CP affects mobility and develop more effective interventions for CP patients.

RESULT

In this study, we propose a multivariate functional classification method to examine the relationship between kinematic gait measures and GMFCS levels in both normal individuals and CP patients with varying GMFCS levels. A sparse linear functional discrimination framework is utilized to achieve an interpretable prediction model. The method is generalized to handle multivariate functional data and multi-class classification. Our method offers competitive or improved prediction accuracy compared to state-of-the-art functional classification approaches and provides interpretable discriminant functions that can characterize the kinesiological progression of gait corresponding to higher GMFCS levels.

CONCLUSION

We generalize the sparse functional linear discrimination framework to achieve interpretable classification of GMFCS levels using kinematic gait measures. The findings of this research will aid clinicians in diagnosing CP and assigning appropriate GMFCS levels in a more consistent, systematic, and scientifically supported manner.

Machine learning approach to gait deviation prediction based on isokinetic data acquired from biometric sensors

BACKGROUND

Analyzing gait deviation is one of the crucial factors during the diagnosis and treatment of children with Cerebral Palsy (CP). The typical diagnostic procedure requires an expensive and complicated three-dimensional gait analysis system based on visual sensors. In this work, we focus on predicting well-known gait pathology scores using only information collected from the BS4P, the affordable isokinetic dynamometer. Using such equipment, it is possible to determine gait pathological indices such as the gait deviation index (GDI) or the Gillette gait index (GGI).

RESEARCH QUESTION

Are there correlations between the results of examining patients with CP on the Biodex Pro 4 device and the gait quality metrics (GDI and GGI)?

METHODS

The isokinetic data acquired from biometric sensors (74 records) were analyzed using big data methods. We used several Machine Learning methods to find the correlation between gait deviation and isokinetic data: Adaptive Boosting Regression, K-nearest Neighbor, Decision Tree Regression, Random Forest Regression, and Gradient Boost Regression.

RESULTS

In this paper, we provided a detailed comparison of different machine learning regression models in predicting gait quality in patients with CP based only on the data gathered from affordable Biodex 4 Pro device. The best result was obtained using the gradient boosting regression model with Mean Absolute Percentage Error of 6%. However, it was not possible to precisely predict the GGI index using this method.

SIGNIFICANCE

The results obtained showed promising results in the evaluation of gait index scores, which gives the possibility of diagnosing patients with CP without the use of expensive optometric systems. Evaluating gait metrics using the approach proposed in this paper could be very helpful for both physicians and physiotherapists in assessing the condition of patients with CP, as well as other diseases related to gait problems.

Dynamic Musculoskeletal Simulation of a Passive Exoskeleton for Simulating Contracture

Gait assessment scores are used for quantifying the abnormalities in the gait. Evaluation of the performance of these scores is a must for their clinical acceptance. However, current methods of assessing the performance of the gait assessment scores for clinically relevant gait abnormalities are prone to error. For example, values of intra-observer reliability, inter-observer reliability and sensitivity calculated for a gait assessment score change with the population of patients and observers. Therefore, there is a need for a methodology for replicating musculoskeletal deformations such as contracture in healthy individuals for objectively evaluating the performance of gait assessment scores with variable severity of musculoskeletal deformations. In this study, a series of dynamic musculoskeletal simulations are performed to simulate and verify a mathematical model of a passive exoskeleton for simulating contractures. The proposed model achieved a root mean square error of 1.864° and a correlation of coefficient of 0.984 while testing on five unique combinations of linear and non-linear torques and seven degrees of severity of hamstring contracture. To understand the tolerance of the proposed model to environmental noises, its performance is also tested at various perturbations. The results indicate that a passive exoskeleton attached to an unimpaired musculoskeletal model can accurately simulate the contracture of the targeted muscles. Clinical relevance - The proposed methodology has a utility in evaluating performances of gait assessment scores and understanding the effect of contractures on biomechanics of gait.