Preprint Graph-Neural-Network-Based Brain Connectivity Analysis for Early Detection of Long-COVID Cognitive Impairments Using MRI/fMRI, 2026, Dubey et al

forestglip

Moderator
Staff member
Graph-Neural-Network-Based Brain Connectivity Analysis for Early Detection of Long-COVID Cognitive Impairments Using MRI/fMRI

Dubey, Supriya; Singh, Jitendra; Bhardwaj, Manish

[Line breaks added]


Abstract
Long-term COVID are frequently causing neurological problems that persist for long time, like cognitive damage and changes in the structure of the brain that are very difficult to find with conventional clinical testing. When coupled with AI, neuroimaging might serve as a useful tool for finding small problems.

To build a deep learning-based neuroimaging framework that automatically recognizes and describe neurological diseases in long-term COVID patients. Deep learning models, such as CNNs, transformers, and graph neural networks, were used to find problems, and explainable AI tools gave us biomarker insights that we could use.

The suggested framework proved better than traditional methods at enhancing classification accuracy, sensitivity, and AUC. Connectivity-based deep models 10 revealed that long-term COVID subjects damaged up brain pathways that corresponded to cognitive decline.

Deep-learning-assisted neuroimaging can effectively find and articulate changes in the neurological systems of persistent COVID patients, which makes it a useful tool for early diagnosisand decision making.

Web | DOI | PDF | MDPI AG | Preprint
 
Back
Top Bottom