An Unsupervised Data-Driven Model to Classify Gait Patterns in Children with Cerebral Palsy

Machine learning applied to gait analysis data in cerebral palsy and stroke: A systematic review

BACKGROUND

Among neurological pathologies, cerebral palsy and stroke are the main contributors to walking disorders. Machine learning methods have been proposed in the recent literature to analyze gait data from these patients. However, machine learning methods still fail to translate effectively into clinical applications. This systematic review addressed the gaps hindering the use of machine learning data analysis in the clinical assessment of cerebral palsy and stroke patients.

RESEARCH QUESTION

What are the main challenges in transferring proposed machine learning methods to clinical applications?

METHODS

PubMed, Web of Science, Scopus, and IEEE databases were searched for relevant publications on machine learning methods applied to gait analysis data from stroke and cerebral palsy patients until February the 23rd, 2023. Information related to the suitability, feasibility, and reliability of the proposed methods for their effective translation to clinical use was extracted, and quality was assessed based on a set of predefined questions.

RESULTS

From 4120 resulting references, 63 met the inclusion criteria. Thirty-one studies used supervised, and 32 used unsupervised machine learning methods. Artificial neural networks and k-means clustering were the most used methods in each category. The lack of rationale for features and algorithm selection, the use of unrepresentative datasets, and the lack of clinical interpretability of the clustering outputs were the main factors hindering the clinical reliability and applicability of these methods.

SIGNIFICANCE

The literature offers numerous machine learning methods for clustering gait data from cerebral palsy and stroke patients. However, the clinical significance of the proposed methods is still lacking, limiting their translation to real-world applications. The design of future studies must take into account clinical question, dataset significance, feature and model selection, and interpretability of the results, given their criticality for clinical translation.

Three-Dimensional Instrumented Gait Analysis for Children With Cerebral Palsy: An Evidence-Based Clinical Practice Guideline

BACKGROUND

Children with cerebral palsy (CP) who walk have complex gait patterns and deviations often requiring physical therapy (PT)/medical/surgical interventions. Walking in children with CP can be assessed with 3-dimensional instrumented gait analysis (3D-IGA) providing kinematics (joint angles), kinetics (joint moments/powers), and muscle activity.

PURPOSE

This clinical practice guideline provides PTs, physicians, and associated clinicians involved in the care of children with CP, with 7 action statements on when and how 3D-IGA can inform clinical assessments and potential interventions. It links the action statement grades with specific levels of evidence based on a critical appraisal of the literature.

CONCLUSIONS

This clinical practice guideline addresses 3D-IGA's utility to inform surgical and non-surgical interventions, to identify gait deviations among segments/joints and planes and to evaluate the effectiveness of interventions. Best practice statements provide guidance for clinicians about the preferred characteristics of 3D-IGA laboratories including instrumentation, staffing, and reporting practices.Video Abstract: Supplemental digital content available at http://links.lww.com/PPT/A524.

3D gait analysis in children using wearable sensors: feasibility of predicting joint kinematics and kinetics with personalized machine learning models and inertial measurement units

Introduction: Children's walking patterns evolve with age, exhibiting less repetitiveness at a young age and more variability than adults. Three-dimensional gait analysis (3DGA) is crucial for understanding and treating lower limb movement disorders in children, traditionally performed using Optical Motion Capture (OMC). Inertial Measurement Units (IMUs) offer a cost-effective alternative to OMC, although challenges like drift errors persist. Machine learning (ML) models can mitigate these issues in adults, prompting an investigation into their applicability to a heterogeneous pediatric population. This study aimed at 1) quantifying personalized and generalized ML models' performance for predicting gait time series in typically developed (TD) children using IMUs data, 2) Comparing random forest (RF) and convolutional neural networks (CNN) models' performance, 3) Finding the optimal number of IMUs required for accurate predictions. Methodology: Seventeen TD children, aged 6 to 15, participated in data collection involving OMC, force plates, and IMU sensors. Joint kinematics and kinetics (targets) were computed from OMC and force plates' data using OpenSim. Tsfresh, a Python package, extracted features from raw IMU data. Each target's ten most important features were input in the development of personalized and generalized RF and CNN models. This procedure was initially conducted with 7 IMUs placed on all lower limb segments and then performed using only two IMUs on the feet. Results: Findings suggested that the RF and CNN models demonstrated comparable performance. RF predicted joint kinematics with a 9.5% and 19.9% NRMSE for personalized and generalized models, respectively, and joint kinetics with an NRMSE of 10.7% for personalized and 15.2% for generalized models in TD children. Personalized models provided accurate estimations from IMU data in children, while generalized models lacked accuracy due to the limited dataset. Furthermore, reducing the number of IMUs from 7 to 2 did not affect the results, and the performance remained consistent. Discussion: This study proposed a promising personalized approach for gait time series prediction in children, involving an RF model and two IMUs on the feet.

How does a systematic tuning protocol for ankle foot orthosis-footwear combinations affect gait in children in cerebral palsy?

PURPOSE

To investigate the effects of a systematic tuning protocol for ankle foot orthosis footwear combinations (AFO-FC) using incrementing heel height on gait in children with cerebral palsy (CP).

METHODS

Eighteen children with CP (10.8 ± 3 years, Gross Motor Function Classification System (GMFCS) I-II) underwent 3D gait analysis on a treadmill, while the AFO heel surface was systematically incremented with wedges. Children were subdivided based on their gait pattern, i.e., knee hyperextension (EXT) and excessive knee flexion (FLEX). Outcome measures included sagittal hip and knee angles and moments, shank to vertical angle (SVA), foot to horizontal angle, and gait profile score (GPS).

RESULTS

For both groups, incrementing heel height resulted in increased knee flexion, more inclined SVA, and increased knee extension moments. This resulted in gait improvements for some children of the EXT-group, but not in FLEX. High variation was found between individuals and within-subject effects were not always consistent for kinematic and kinetics.

CONCLUSIONS

A systematic AFO-FC tuning protocol using incremented heel height can be effective to improve gait in children with CP walking with EXT. The current results emphasise the importance of including kinematics as well as kinetics of multiple instances throughout the gait cycle for reliable interpretation of the effect of AFO tuning on gait.Implications for rehabilitationA systematic ankle foot orthosis footwear combinations (AFO-FC) tuning protocol using incremented heel height can improve gait in children walking with knee hyperextension.Tuning results in changes throughout the gait cycle.Little evidence is found for an optimal SVA of 10-12° at midstance.For clinical interpretation, both joint kinematic and kinetic parameters should be considered throughout the gait cycle and evaluation should not be based on SVA only.

Breaking new grounds in injury risk screening in soccer by deploying unsupervised learning with a special focus on sex and fatigue effects

In injury prevention, a vertical drop jump (DJ) is often used for screening athletes at risk for injury; however, the large variation in individual movement patterns might mask potentially relevant strategies when analysed on a group-based level. Two movement strategies are commonly discussed as predisposing athletes to ACL injuries: a deficient leg axis and increased leg stiffness during landing. This study investigated the individual movement pattern of 39 female and male competitive soccer players performing DJs at rest and after being fatigued. The joint angles were used to train a Kohonen self-organising map. Out of 19,596 input vectors, the SOM identified 700 unique postures. Visualising the movement trajectories and adding the latent parameters contact time, medial knee displacement (MKD) and knee abduction moment allow identification of zones with presumably increased injury risk and whether the individual movement patterns pass these zones. This information can be used, e.g., for individual screening and for feedback purposes. Additionally, an athlete's reaction to fatigue can be explored by comparing the rested and fatigued movement trajectories. The results highlight the ability of unsupervised learning to visualise movement patterns and to give further insight into an individual athlete's status without the necessity of a priori assumptions.

Three decades of gait index development: A comparative review of clinical and research gait indices

BACKGROUND

A wide variety of indices have been developed to quantify gait performance markers and associate them with their respective pathologies. Indices scores have enabled better decisions regarding patient treatments and allowed for optimized monitoring of the evolution of their condition. The extensive range of human gait indices presented over the last 30 years is evaluated and summarized in this narrative literature review exploring their application in clinical and research environments.

METHODS

The analysis will explore historical and modern gait indices, focusing on the clinical efficacy with respect to their proposed pathology, age range, and associated parameter limits. Features, methods, and clinically acceptable errors are discussed while simultaneously assessing indices advantages and disadvantages. This review analyses all indices published between 1994 and February 2021 identified using the Medline, PubMed, ScienceDirect, CINAHL, EMBASE, and Google Scholar databases.

FINDINGS

A total of 30 indices were identified as noteworthy for clinical and research purposes and another 137 works were included for discussion. The indices were divided in three major groups: observational (13), instrumented (16) and hybrid (1). The instrumented indices were further sub-divided in six groups, namely kinematic- (4), spatiotemporal- (5), kinetic- (2), kinematic- and kinetic- (2), electromyographic- (1) and Inertial Measurement Unit-based indices (2).

INTERPRETATION

This work is one of the first reviews to summarize observational and instrumented gait indices, exploring their applicability in research and clinical contexts. The aim of this review is to assist members of these communities with the selection of the proper index for the group in analysis.

Estimation of Gross Motor Functions in Children with Cerebral Palsy Using Zebris FDM-T Treadmill

A standardized observational instrument designed to measure change in gross motor function over time in children with cerebral palsy is the Gross Motor Function Measure (GMFM). The process of evaluating a value for the GMFM index can be time consuming. It typically takes 45 to 60 min for the patient to complete all tasks, sometimes in two or more sessions. The diagnostic procedure requires trained and specialized therapists. The paper presents the estimation of the GMFM measure for patients with cerebral palsy based on the results of the Zebris FDM-T treadmill. For this purpose, the regression analysis was used. Estimations based on the Generalized Linear Regression were assessed using different error metrics. The results obtained showed that the GMFM score can be estimated with acceptable accuracy. Because the Zebris FDM-T is a widely used device in gait rehabilitation, our method has the potential to be widely adopted for objective diagnostics of children with cerebral palsy.