Fusion of EEG and EMG signals for detecting pre-movement intention of sitting and standing in healthy individuals and patients with spinal cord injury

Frontiers in Neuroscience, 2025 · DOI: 10.3389/fnins.2025.1532099 · Published: January 24, 2025

Simple Explanation

This study introduces a new method for detecting a person's intention to sit or stand before they actually move. It combines two types of brain and muscle signals (EEG and EMG) to improve accuracy. This could help rehabilitation devices react more quickly and effectively. The researchers used a technique called functional connectivity to see how different parts of the brain and muscles communicate before movement. They found that a method called mutual information (MI) was particularly good at identifying these communication patterns. The method was tested on healthy individuals and patients with spinal cord injuries (SCI). The results showed that the combined EEG and EMG approach was more accurate than using either signal alone, even when the participants were experiencing muscle fatigue.

Study Duration

Not specified

Participants

8 healthy subjects and 5 spinal cord injury (SCI) patients

Evidence Level

Not specified

Key Findings

1
The MI-based EEG–EMG network showed the highest decoding performance (94.33%), outperforming both EEG (73.89%) and EMG (89.16%).
2
The fusion method achieved 92.87% accuracy during the post-fatigue stage, with no significant difference compared to the pre-fatigue stage (p > 0.05).
3
For the SCI patients, the fusion method showed improved accuracy, achieving 87.54% compared to single- modality methods.

Research Summary

This study proposes a multimodal fusion method for detecting sitting and standing intentions based on EEG–EMG functional connectivity, utilizing signals recorded prior to movement execution. The results demonstrated that the MI-based EEG–EMG network significantly outperformed COH and CC-based methods. The feasibility of the proposed method was validated through experiments with eight healthy subjects and five SCI patients with residual EMG signals.

Practical Implications

Improved Rehabilitation Systems

The proposed method can enhance the accuracy and timeliness of interventions within rehabilitation systems, leading to better patient outcomes.

Real-Time Intention Detection

The study provides a promising solution for real-time intention detection, allowing assistive devices to respond promptly to the patient’s voluntary movements.

Clinical Applications

The method's feasibility for SCI patients suggests its potential for practical rehabilitation applications in clinical settings.

Study Limitations

1
The choice of functional connectivity measures.
2
Limited by the sample size and the inclusion of SCI patients who have residual EMG activity.
3
Generalization to other functional lower limb movements remains to be explored.

Your Feedback

Was this summary helpful?

Back to Neurology