Utilizing Motor-Imagery Brain-Computer Interfaces for the Assessment of Developmental Coordination Disorder in...

Area of Science:

• Neuroscience
• Developmental Psychology
• Biomedical Engineering

Background:

• Developmental Coordination Disorder (DCD) presents significant motor challenges impacting daily life.
• Current DCD assessments rely heavily on behavioral observation, lacking objective neuroscientific measures.
• There is a need for advanced diagnostic tools for early and accurate DCD identification.

Purpose of the Study:

• To develop and evaluate an electroencephalography (EEG)-based brain-computer interface (BCI) classification system for assessing DCD in children.
• To investigate the efficacy of entropy-based data screening in enhancing BCI classification performance for DCD.
• To explore the potential of using specific EEG frequency bands, like mu band power, for DCD detection.

Main Methods:

• An EEG-based BCI system was designed for motor imagery classification in children.
• Entropy-based algorithms were implemented for data preprocessing and feature selection.
• A Support Vector Machine (SVM) classifier was trained using EEG data, focusing on mu band power.

Main Results:

• The implemented entropy-based data screening significantly improved the classification performance of the BCI system.
• The system achieved a notable accuracy rate of 79.0% in classifying DCD using mu band power and SVM.
• This demonstrates the potential of EEG-based metrics in differentiating individuals with DCD.

Conclusions:

• The developed EEG-based BCI system with entropy screening shows promise as a novel tool for DCD evaluation.
• This approach offers a more objective, neuroscientifically grounded method compared to traditional behavioral assessments.
• Further research can lead to a clinical tool aiding professionals in the early identification of DCD in children.