Skip to content
Open access

Personalized Gait Phase Estimation for Post-Stroke Individuals via Supervised Domain Adaptation With Limited Gait Data

Oct 2026 · IEEE transactions on neural systems and rehabilitation engineering · Vol 34, pp. 4179-4189 · 0 citations · 40 references
Medicine

TL;DR

A personalized gait phase estimation framework based on supervised domain adaptation (SDA) with a multi-phase maximum mean discrepancy (MP-MMD) objective that aligns source and target latent features separately during stance and swing using stride-specific toe-off labels is proposed.

Abstract

Accurate gait phase estimation is important for characterizing locomotor progression and enabling phase-dependent monitoring and intervention across gait analysis, rehabilitation, neuroprosthetic, and wearable assistive systems. However, this remains challenging in post-stroke individuals because pathological gait patterns vary substantially across subjects, while patient-specific gait data are often limited. To address this issue, this study proposes a personalized gait phase estimation framework based on supervised domain adaptation (SDA) with a multi-phase maximum mean discrepancy (MP-MMD) objective. This objective aligns source and target latent features separately during stance and swing using stride-specific toe-off labels. A shared feature extractor and domain-specific regressors are jointly trained using data from non-disabled individuals and limited labeled data from each post-stroke participant to construct a subject-specific model. Leave-One-Trial-Out evaluation of seven participants yielded a Root Mean Square Error (RMSE) of <inline-formula> <tex-math notation="LaTeX">$4.37 \pm 1.26\%$ </tex-math></inline-formula> and a Maximum Absolute Error (MaxAE) of <inline-formula> <tex-math notation="LaTeX">$8.64 \pm 1.90\%$ </tex-math></inline-formula>. After Holm correction, the proposed SDA method achieved significantly lower RMSE than Source Only and Fine-Tuning and lower MaxAE than all three baselines (all adjusted <inline-formula> <tex-math notation="LaTeX">$p=0.047$ </tex-math></inline-formula>). Relative to Target Only and Fine-Tuning, RMSE showed numerical reductions of 13.32% and 57.51%, respectively, and MaxAE decreased by 26.50% and 72.17%. Compared with conventional global MMD, MP-MMD yielded numerical reductions of 2.87% in RMSE and 2.77% in MaxAE. These results constitute a proof-of-concept for data-efficient within-subject personalization of gait phase estimation.

Read PDF

Similar papers

Preprint Nov 2026

GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment

Gait assessment supports the diagnosis, monitoring, and prognosis of diverse movement-related conditions, such as neurological and musculoskeletal disorders. Recent advances in deep learning using everyday wearable inertial measurement units (IMUs) offer an accessible and low-cost approach to automated gait assessment....

Yi-Ze Cai, Zhi-Qing Hong · 0 citations
Open access Oct 2026

A Wearable IMU-Based Gait Assessment Framework Utilizing Sequential Multivariate Dynamic Time Warping for Clinical Rehabilitation

Impairment resulting from stroke significantly affects patient mobility, making recovering the ability to walk a primary rehabilitation goal. While wearable inertial measurement units (IMUs) offer a cost-effective alternative to subjective clinical observations, conventional gait analysis often struggles with the high...

Hao-Pu Lin, Yu-Chi Wu, Yu-Wei Wen et al. · 0 citations
Open access Oct 2026

In-Home Free-Living Gait Monitoring Using a Single Lumbar IMU Reveals Nonlinear Complexity Changes During Intensive Stroke Rehabilitation

Conventional clinical assessments of stroke rehabilitation are limited to supervised environments and fail to capture continuous real-world motor behavior. This proof-of-concept pilot study (case series, n = 3) evaluated the feasibility and longitudinal sensitivity of wearable IMU-derived digital biomarkers of three in...

R. Soangra, Susan V. Duff, A. Mckenzie · 0 citations
Oct 2026

Phase-Guided Self-Supervised Latent Representation Learning for sEMG-Based Gait Decoding.

Surface electromyography (sEMG) provides a non-invasive measure of neuromuscular activity and is widely used for gait decoding in wearable and rehabilitation systems. Existing sEMG-based approaches rely on end-to-end supervised regression with dense kinematic labels, limiting scalability, generalization, and interpreta...

Chen Wang, Jia-Tong Cui, Liang Peng et al. · 0 citations
Oct 2026

Sensor-integrated AI-assisted gait training in dementia and Parkinson's disease: A single-session pre-post study.

BackgroundGait impairment in dementia and Parkinson's disease (PD) contributes to falls, reduced mobility, and loss of independence. Sensor-integrated, AI-assisted gait training systems may provide standardized rehabilitation with real-time feedback and quantitative gait assessment.Objective: To investigate whether a s...

Chien-Tai Hong, Li-Kai Huang, Cheng-Hsing Liu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.