# Gait pattern stratification in persons with incomplete spinal cord injury: a data-driven approach

## TL;DR

This study uses data-driven methods to identify distinct gait patterns in people with incomplete spinal cord injury, aiming to improve personalized rehabilitation.

## Contribution

A novel framework using unsupervised learning and explainable AI to stratify gait heterogeneity in iSCI patients.

## Key findings

- Six distinct gait clusters were identified among iSCI patients using dynamic time warping and clustering.
- Gait patterns with low walking speed showed reduced step length and ankle plantarflexion compared to controls.
- Clinical factors like muscle strength, walking speed, and step width varied significantly between clusters.

## Abstract

Incomplete spinal cord injury (iSCI) often causes heterogeneous locomotion dysfunctions, depending on remaining sensorimotor function. Clinical tests and traditional gait analysis have limited ability to quantify the diversity of gait impairments. Unsupervised learning techniques can objectively identify common gait patterns among the overall heterogeneity. Explainable artificial intelligence approaches, when combined with machine learning models, can reveal important features often missed by traditional gait analyses. This study presents a framework to characterize gait heterogeneity among persons with iSCI based on several data-driven methods. We aimed to stratify overall gait heterogeneity by deriving clusters with similarities without a priori identification of parameters, and to assess possible clinical correlations in the derived clusters.

A cohort of 28 adults with iSCI and control group of 21 non-disabled adults were recruited. The iSCI group underwent a standard physical assessment of overall mobility, lower extremity strength, and spasticity. Both groups underwent instrumented 3D gait analysis, walking at self-selected pace. Distinct iSCI gait pattern subgroups were identified with dependent dynamic time warping and hierarchical agglomerative clustering. Distribution of clinical descriptives and outcome measures among and between groups were evaluated. Gait predictors that distinguish each cluster from control gait were identified with a random forest classifier and explainable AI.

Six distinct gait clusters were identified among the 280 iSCI gait cycles. Clusters with relatively low walking speed exhibited shorter step lengths and less ankle plantarflexion in pre-swing than controls. Gait patterns and walking performance in clusters with high walking speed were relatively similar to controls. Overall muscle strength, walking independence, walking speed, step length, step width, sex distribution, and types of walking aids significantly differed between all six clusters. Ankle plantarflexion angle in pre-swing correlated strongly with walking speed and step length.

Through a series of advanced data-driven approaches, common gait patterns can be objectively identified and comprehensively characterized within a heterogeneous iSCI population. This work represents an initial step in developing individualized rehabilitation programs for persons with iSCI.