Prediction of Muscle Response to Functional Electrical Stimulation Therapy after Cervical Spinal Cord Injuries Using Surface Electromyography
Bibliographic record
Abstract
Spinal cord injury (SCI) can severely affect neuromuscular function and quality of life, particularly for individuals with cervical injuries. Functional electrical stimulation (FES) therapy has shown promise in restoring upper extremity (UE) function, yet variability in muscle responsiveness has limited its broader adoption. This thesis explores the potential of surface electromyography (sEMG) as a sensitive, non-invasive tool to enhance SCI rehabilitation and inform personalized FES therapy. Through three interconnected studies, we address key challenges in understanding neuromuscular changes post-SCI, identifying distinct muscle electrophysiological profiles, and predicting muscle responsiveness to FES therapy.Study 1 developed a computational model to simulate sEMG signal alterations under different SCI scenarios. Results showed that commonly used amplitude-based features (e.g., root mean square and mean absolute value) lack specificity in neuromuscular disruptions. In contrast, non-amplitude-based features, such as slope sign changes (SSC) and autoregression coefficients, provided greater sensitivity. Studies 2 and 3 analyzed sEMG signals recorded from 184 UE muscle groups across 22 participants with cervical SCI. Study 2 applied clustering algorithms to the full dataset and identified distinct and reproducible clusters. These clusters were only partially aligned with clinical variables such as myotome level and neurological level of injury. It indicated that sEMG captures additional physiological nuances, such as residual motor pathways or compensatory mechanisms, that are not readily assessed through standard clinical evaluations. Study 3 focused on developing predictive models using a subset of 132 muscles groups from 17 participants with known responsiveness to FES therapy. A Random Forest classifier with forward-selected features (SSC, mean and median frequencies, second-order moment) achieved the best performance (accuracy = 76%, macro F1 = 0.68, Matthews correlation coefficient = 0.41). Stratifying participants by motor completeness (AIS A-B vs. C-D) further improved modeling performance, underscoring the value of tailored approaches. These studies collectively highlight the potential of sEMG to bridge critical gaps in SCI rehabilitation by providing nuanced insights into neuromuscular changes and enabling personalized therapy planning. This work offers valuable evidence to support the integration of sEMG into clinical practice to optimize FES therapy outcomes and improve quality of life for individuals with SCI.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".