Use of Computerized Gait Analysis in Neurological Pathologies

Background: Altered motor control is common in cerebral palsy (CP). Understanding how altered motor control affects movement and treatment outcomes is important but challenging due to complex interactions with other neuromuscular impairments. While regression can be used to examine associations between impairments and movement, causal modeling provides a mathematical framework to specify assumed causal relationships, identify covariates that may introduce bias, and test model plausibility. The goal of this research was to quantify the causal effects of altered motor control and other impairments on gait, before and after single-event multi-level orthopedic surgery (SEMLS).

Methods: We evaluated the impact of SEMLS on change in Gait Deviation Index (ΔGDI) between gait analyses. We constructed our causal model with a Directed Acyclic Graph that included the assumed causal relationships between SEMLS, ΔGDI, baseline GDI (GDI_pre), baseline neurologic and orthopedic impairments (Imp_pre), age, and surgical history. We identified the adjustment set to evaluate the causal effect of SEMLS on ΔGDI and the impact of Imp_pre on ΔGDI and GDI_pre. We used Bayesian Additive Regression Trees (BART) and accumulated local effects to assess relative effects.

Results: We prospectively recruited a cohort of children with bilateral CP undergoing SEMLS (N = 55, 35 males, age: 10.5 ± 3.1 years) and identified a control cohort with bilateral CP who did not undergo SEMLS (N = 55, 30 males, age: 10.0 ± 3.4 years). There was a small positive causal effect of SEMLS on ΔGDI (1.70 GDI points). Altered motor control (i.e., dynamic and static motor control) and strength had strong effects on GDI_pre, but minimal effects on ΔGDI. Spasticity and orthopedic impairments had minimal effects on GDI_pre or ΔGDI.

Conclusion: Altered motor control did have a strong effect on GDI_pre, indicating that these impairments do have a causal effect on a child’s gait pattern, but minimal effect on expected changes in GDI after SEMLS. Heterogeneity in outcomes suggests there are other factors contributing to changes in gait. Identifying these factors and employing causal methods to examine the complex relationships between impairments and movement will be required to advance our understanding and care of children with CP.

Prolonging ambulation is an important treatment goal in children with Duchenne muscular dystrophy (DMD). Three-dimensional gait analysis (3DGA) could provide sensitive parameters to study the efficacy of clinical trials aiming to preserve ambulation. However, quantitative descriptions of the natural history of gait features in DMD are first required. The overall goal was to provide a full delineation of the progressive gait pathology in children with DMD, covering the entire period of ambulation, by performing a so-called mixed cross-sectional longitudinal study. Firstly, to make our results comparable with previous literature, we aimed to cross-sectionally compare 31 predefined gait features between children with DMD and a typically developing (TD) database (1). Secondly, we aimed to explore the longitudinal changes in the 31 predefined gait features in growing boys with DMD using follow-up 3DGA sessions (2). 3DGA-sessions (n = 124) at self-selected speed were collected in 27 boys with DMD (baseline age: 4.6–15 years). They were repeatedly measured over a varying follow-up period (range: 6 months–5 years). The TD group consisted of 27 children (age: 5.4–15.6 years). Per measurement session, the spatiotemporal parameters, and the kinematic and kinetic waveforms were averaged over the selected gait cycles. From the averaged waveforms, discrete gait features (e.g., maxima and minima) were extracted. Mann-Whitney U tests were performed to cross-sectionally analyze the differences between DMD at baseline and TD (1). Linear mixed effect models were performed to assess the changes in gait features in the same group of children with DMD from both a longitudinal (i.e., increasing time) as well as a cross-sectional perspective (i.e., increasing baseline age) (2). At baseline, the boys with DMD differed from the TD children in 17 gait features. Additionally, 21 gait features evolved longitudinally when following-up the same boys with DMD and 25 gait features presented a significant cross-sectional baseline age-effect. The current study quantitatively described the longitudinal alterations in gait features in boys with DMD, thereby providing detailed insight into how DMD gait deteriorates. Additionally, our results highlight that gait features extracted from 3DGA are promising outcome measures for future clinical trials to quantify the efficacy of novel therapeutic strategies.

Introduction: The assessments of the motor symptoms in Parkinson’s disease (PD) are usually limited to clinical rating scales (MDS UPDRS III), and it depends on the clinician’s experience. This study aims to propose a machine learning technique algorithm using the variables from upper and lower limbs, to classify people with PD from healthy people, using data from a portable low-cost device (RGB-D camera). And can be used to support the diagnosis and follow-up of patients in developing countries and remote areas.

Methods: We used Kinect^®eMotion system to capture the spatiotemporal gait data from 30 patients with PD and 30 healthy age-matched controls in three walking trials. First, a correlation matrix was made using the variables of upper and lower limbs. After this, we applied a backward feature selection model using R and Python to determine the most relevant variables. Three further analyses were done using variables selected from backward feature selection model (Dataset A), movement disorders specialist (Dataset B), and all the variables from the dataset (Dataset C). We ran seven machine learning models for each model. Dataset was divided 80% for algorithm training and 20% for evaluation. Finally, a causal inference model (CIM) using the DoWhy library was performed on Dataset B due to its accuracy and simplicity.

Results: The Random Forest model is the most accurate for all three variable Datasets (Dataset A: 81.8%; Dataset B: 83.6%; Dataset C: 84.5%) followed by the support vector machine. The CIM shows a relation between leg variables and the arms swing asymmetry (ASA) and a proportional relationship between ASA and the diagnosis of PD with a robust estimator (1,537).

Conclusions: Machine learning techniques based on objective measures using portable low-cost devices (Kinect^®eMotion) are useful and accurate to classify patients with Parkinson’s disease. This method can be used to evaluate patients remotely and help clinicians make decisions regarding follow-up and treatment.