Key result
Random forest and support vector regression models for automated EMG channel quality quantification achieved a very strong correlation (rs=0.90) and excellent reliability (ICC=0.95).
Why the study?
Adequate electromyography (EMG) signal quality is important for correct interpretations in diagnostics and EMG-based control.
Automated regression models, particularly random forest and support vector regression, show excellent reliability in quantifying high-density surface EMG signal quality.
Supports automated EMG quality assessment in research; leaves open clinical validation before adoption.
Adequate electromyography (EMG) signal quality is important for obtaining correct interpretations for EMG diagnostics and EMG-based control. In this pilot study, a dataset (N = 2) of high-density recordings of the biceps and triceps was rated on a four-point scale by two expert EMG raters. The intra-rater reliability was good-to-excellent (ICC (2,1) > 0.76) and the inter-rater reliability was good (ICC (3,k) = 0.85). Four regression models were developed to label electrodes automatically: 1) linear regression, 2) random forest regression, 3) support vector regression, and 4) a combination of the models obtained via majority voting. Using the human raters as a ground truth, the random forest and support vector regression obtained a very strong correlation (rs= 0.90) and excellent reliability (ICC (3,k) = 0.95). These results demonstrate the potential for the development of an automated process to quantify EMG channel quality.
No takes yet. Share an insight, caveat, or question.
Farago et al. (2023) studied this question. Automated regression models (random forest and support vector regression) vs. Human expert raters was evaluated on Correlation and reliability of automated electrode labeling (rs= 0.90). Random forest and support vector regression models for automated EMG channel quality quantification achieved a very strong correlation (rs=0.90) and excellent reliability (ICC=0.95).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: