Related Experiment Video
Updated: Jun 16, 2026
Combining Multiple Data Acquisition Systems to Study Corticospinal Output and Multi-segment Biomechanics
Published on: January 9, 2016
Machine learning based EMG analysis of intermuscular coherence and cumulant density in tremor and myoclonus
Elina L van den Brandhof1, A M Madelein van der Stouwe2, Sterre van der Veen2
1Expertise Centre Movement Disorders Groningen, University Medical Centre Groningen, Groningen, the Netherlands; Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, the Netherlands; Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands.
Objectives:
Clinical distinction of essential tremor (ET) and cortical myoclonus (CM) remains challenging due to overlapping symptoms. This study aims to identify characteristics in muscle contraction patterns in individual muscles, as well as intermuscular EMG coupling between agonist antagonist pairs in ET and CM, and to evaluate their diagnostic suitability.
Methods:
We analyzed arm muscle activity in 19 ET and 19 CM patients during two postures with pronated outstretched arms: one with straight wrists and one with extended wrists. We analyzed power spectra, agonist-antagonist coherence, and cumulant density using classical statistical and machine learning methods.
Results:
Machine learning analysis achieved high classification performance using engineered features (AUROC: 0.93), power spectra (0.92), and coherence (0.93). Cumulant density-based analysis was less discriminative (0.67), though performance improved with reduced muscle activation. ET was characterized by regular contraction pattern and predominantly alternating bursts depending on the posture, while CM showed irregular, synchronous bursts.
Conclusion:
The identified EMG signatures - regular alternating bursts in ET and irregular synchronous bursts in CM - demonstrate strong potential to support objective diagnosis.
Significance:
These findings provide statistical evidence supporting clinically observed contraction patterns in ET and CM, which could enhance diagnostic accuracy.
