sEMG Feature Analysis for Trauma and Electrical-Burn Transradial Amputation Etiologies: A Pilot Study

Background: Despite advances in myoelectric control of hand prostheses, their dropout rate remains high. Methods: We analyzed 37 features extracted from surface electromyography (sEMG) recordings from 15 participants, distributed into three groups: non-impaired individuals, impaired individuals with limb loss due to trauma, and impaired individuals with limb loss due to electrical burn. Feature relationships were examined with correlation heatmaps and two feature-selection methods (ReliefF and Minimal Redundancy Maximum Relevance), and classification performance was evaluated using machine-learning models to characterize sEMG behavior across groups. Results: Individuals with electrical-burn injury exhibited increased forearm co-contraction on the affected side across normalized isometric contractions, indicating altered motor coordination and likely higher energetic cost for prosthetic control. Feature selection and model results revealed etiology-dependent differences in the most informative sEMG features, underscoring the need for personalized, etiology-aware myoelectric control strategies. Conclusions: These findings inform the design of adaptive prosthetic controllers and targeted rehabilitation protocols that account for injury-specific motor control adaptations.