Key result
Automated unsupervised learning pipeline retains ~52% of sEMG signals as usable while preserving biological characteristics.
Why the study?
Artifact contamination in sEMG data from individuals with neurological injuries requires subjective and time-consuming visual inspection to confirm signal utility.
An automated unsupervised learning pipeline can effectively filter artifact-compromised sEMG signals in patients with neurological injuries while preserving biologically relevant data.
Answers are grounded in this paper and cite their sources.
May aid sEMG quality control in neurological injury; hypothesis-generating and requires prospective validation before clinical use.
The contamination of surface electromyography (sEMG) data by artifacts is a critical issue, particularly when acquired from individuals with neurological injuries. This necessitates subjective and time-consuming visual inspection to verify signal utility. To address this, this work proposes an automated quality assessment method based on unsupervised learning to distinguish usable signals from those compromised by artifacts, such as electrode detachment or saturation. Features were extracted using the Time Series Feature Extraction Library (TSFEL), and the top 80 discriminative features across temporal, statistical, and spectral domains were selected via ANOVA. K-means and Agglomerative Clustering were employed to group the data, followed by an Isolation Forest stage to refine the selection of usable signals. Validation against an objective ground truth revealed the complexity of the task (ARI ≈ 0.20), yet the pipeline effectively retained 52% of the dataset as usable signals. Furthermore, a comparison between the retained injured signals and healthy controls demonstrated statistically significant differences (p < 0.001) with a medium-to-large effect size (Cohen’s d ≈ 0.72), confirming that the automated approach preserves signals with distinct and biologically relevant spectral characteristics.
No takes yet. Share an insight, caveat, or question.
Lourenção et al. (2026) studied Neurological injuries. Automated quality assessment method based on unsupervised learning vs. Healthy controls was evaluated on Retention of usable sEMG signals (Cohen's d 0.72, p=<0.001). An automated unsupervised learning pipeline retained 52% of sEMG signals as usable, preserving biologically relevant characteristics that differed from healthy controls.
Synapse has enriched 10 related papers. Consider them for comparative context: