BMC Biomed Eng. 2026 Aug 8;8(1):15. doi: 10.1186/s42490-026-00118-7.
ABSTRACT
BACKGROUND: Gait speed is a key clinical indicator in neurological and orthopaedic conditions, yet waveform-level adaptations in ground reaction forces (GRF) and multi-muscle electromyography (EMG) remain poorly characterised. Existing approaches often analyse discrete outcomes or individual modalities, leaving limited integration of continuous waveform inference, dimensionality reduction, explainable machine learning, and equivalence testing within a unified multimodal framework.
OBJECTIVE: To compare three-axis GRF and six-muscle EMG between slow (0.5 m/s) and fast (1.0 m/s) treadmill walking using statistical parametric mapping (SPM), functional principal component analysis (fPCA), explainable machine learning, and equivalence testing.
METHODS: Fifty-eight healthy adults were analysed (55 with complete EMG). Paired SPM with cluster-based permutation assessed waveform differences. fPCA-derived features entered a Random Forest with leave-one-subject-out cross-validation and SHAP interpretability. Two one-sided tests (TOST) assessed equivalence of the vertical GRF.
RESULTS: No significant cluster-level SPM differences were found for any GRF component. In contrast, significant EMG clusters were detected in tibialis anterior (ten clusters), gastrocnemius medial and lateral, vastus lateralis, rectus femoris, and semitendinosus. The Random Forest achieved 87.2% accuracy (95% CI: 79.3-92.3%), improving 14.7% points over simple amplitude features, with tibialis anterior PC1 the most important predictor. TOST did not confirm equivalence within ± 0.2 N/kg, though no GRF clusters appeared.
CONCLUSIONS: Moderate speed increases elicited distributed multi-muscle activation changes, whereas GRF waveform differences did not reach cluster-level significance within the present analytical framework. The integrated SPM-fPCA-SHAP-TOST pipeline provides an interpretable signal-processing framework for multimodal gait analysis and could serve as a foundation for future investigations in rehabilitation engineering, digital biomarkers, and wearable sensing, pending validation in clinical populations.
PMID:42571017 | DOI:10.1186/s42490-026-00118-7
