Identifying and predicting gait stability metrics in people with stroke in uneven-surface walking using machine learning

TL;DR

This study uses machine learning to analyze gait stability in stroke patients during uneven walking, identifying key metrics that could help improve rehabilitation.

Contribution

The novel use of interpretable machine learning to predict gait stability metrics in stroke patients using wearable sensor data.

Findings

ML models accurately distinguished stroke patients from healthy controls using trunk acceleration features.

Gait speed below 0.8 m/s on even surfaces predicted instability on uneven surfaces in stroke patients.

Nonlinear associations were found between even-surface gait parameters and uneven-surface stability metrics.

Abstract

People with stroke (PwS) face increased fall risk on uneven surfaces; however, gait stability under such conditions remains unexplored. This study used machine learning (ML) to identify acceleration features distinguishing PwS from healthy controls (HC) during uneven-surface walking and to predict them from even-surface gait parameters. Trunk acceleration data from 71 PwS and 39 HC were analyzed using classification and regression models. The ML classifiers achieved an accuracy of over 95%. The key discriminative features included the vertical root mean square (RMS_VT), anterior-posterior sample entropy (SampEn_AP), and harmonic ratio (HR_AP). In PwS, even-surface gait speed < 0.8 m/s predicted reduced speed and higher RMS_VT on uneven surfaces. SampEn_AP and HR_AP were influenced by ankle kinematics and their even-surface values, respectively, showing nonlinear associations. These findings support the use of wearable sensor data and interpretable ML to assess gait stability and adaptability, facilitating development of digital biomarkers for personalized stroke rehabilitation aimed at improving outdoor mobility.

The online version contains supplementary material available at 10.1038/s41598-026-35966-9.

Figures