Estimation of elbow flexion torque using equilibrium optimizer on feature selection of NMES MMG signals and hyperparameter tuning of random forest regression.
Raphael Uwamahoro, Kenneth Sundaraj, Farah Shahnaz Feroz
PMID 40046456WHAT IT FOUND
A new algorithm estimates elbow flexion torque from muscle vibration signals in healthy young men.
It reduced the number of features needed by 33% and improved prediction accuracy on unseen data, but has not yet been tested in patients with muscle weakness.
Key findings
01The hybrid model improved torque estimation accuracy on unseen test data compared to a standard random forest, reducing error and increasing correlation.
02The algorithm selected an optimal subset of features, achieving a 33.33% reduction in feature size while maintaining performance.
03The study was conducted exclusively on healthy young male participants, limiting immediate generalizability to clinical populations.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study included only healthy young men. Results may not apply to women, older adults, or people with neuromuscular disorders like stroke or spinal cord injury. The model was tested on data from a single muscle (biceps brachii). It does not account for the contribution of other elbow flexors like the brachialis or brachioradialis. The study did not explicitly test whether the model works equally well across different forearm postures or elbow angles, though data were collected from them. This is a laboratory-based engineering study. The equipment (accelerometers, force transducers, specific NMES protocols) is not currently available as a clinical tool.
Declared interests
The authors declare that no financial support was received for the research, authorship, and/or publication of this article.
The easy way to misread this
Do not interpret the improved prediction accuracy as evidence that this device can currently measure strength in your patients. The study was performed only on healthy young men in a controlled laboratory setting using specialized equipment. Its application to clinical populations with muscle weakness or pathology has not been tested.