Post-Stroke Gait Kinematic and sEMG Waveforms for 43 Patients

A 2026 secondary analysis of a public multimodal gait dataset comprising 138 able-bodied adults and 50 adults with stroke. The study derived side-aware gait-state representations from 11 waveform domains, including sagittal kinematics and surface electromyography, focusing on a strict complete-case cohort of 43 stroke patients. The dataset was authored by Rocco Salvatore Calabrò and shared under a CC-BY-4.0 license.

Use Cases

• Developing side-aware gait-state representations for adaptive neurorobotic controllers based on kinematic and sEMG waveform data.
• Clustering post-stroke walking patterns into interpretable states based on fused multimodal signals like ankle angle and vastus lateralis sEMG.
• Analyzing the contribution of specific waveform domains (e.g., ankle angle, gastrocnemius sEMG) to gait-state differentiation after stroke.
• Testing the sensitivity of gait representations to methodological choices like robust scaling or component reduction.

Strengths

• Derived from a public dataset with 188 total participants (138 able-bodied, 50 with stroke).
• Analysis is based on 11 waveform domains, each represented by 1,001 time-normalized points.
• Provides a specific, interpretable three-state clustering solution for a cohort of 43 stroke patients.
• Identifies the strongest domain contributors with specific weights (e.g., ankle angle 1.000, vastus lateralis sEMG 0.898).

Limitations

• The primary data file is a 29.8 KB DOCX document, which is a tiny analysis report, not the raw waveform data.
• Row count and column-level documentation for the underlying source data are unknown.
• The analysis is exploratory and representational, not validated for clinical or real-time controller use.

Provenance

Source

Secondary analysis of an unspecified public multimodal gait dataset.

Collection Method

Functional principal component analysis and clustering (Ward hierarchical, K-means) performed on time-normalized kinematic and sEMG waveforms.

Freshness

Last updated 2026-05-25.