Geometric Deep Learning on Graphs for EEG Datasets
This project improves neurological disorder diagnosis by developing geometric deep learning models for EEG data, making assessments more accessible and cost-effective.
Identifying neurological disorders presents significant challenges due to the reliance on costly diagnostic tools like MRI and fMRI, as well as limited access to expert medical personnel, particularly in remote regions. Traditional methods fall short in providing affordable and accessible solutions for early detection and treatment.
Our goal is to develop and implement a geometric deep learning model for EEG datasets to enhance diagnostic accuracy while reducing costs. We aim to improve accessibility to neurological disorder diagnosis, especially in remote regions where traditional diagnostic infrastructure is limited.
This project developed a geometric deep learning model specifically designed for EEG datasets to improve the diagnosis of neurological disorders. The model demonstrated promising accuracy in classifying brain states and laid the groundwork for more accessible, cost-effective neurological assessment tools, particularly beneficial for healthcare delivery in remote and underserved regions.