The first objective of this research project is to address the urgent need for accessible and cost-effective diagnostic tools for early dementia diagnosis. This will be achieved by leveraging clinical-grade EEG devices, machine learning (ML), and a multi-modal approach (integrating cognitive and motor function measurements) to identify characteristic features of cognitive impairment.

Early diagnosis of dementia is crucial for effective treatment planning. Traditional diagnostic methods often face limitations:

  • Neuropsychological tests lack sensitivity and have high variability.
  • Medical procedures like cerebrospinal fluid (CSF) analysis, magnetic resonance imaging (MRI), and positron emission tomography (PET) scans are invasive, costly, and have limited availability.
  • Blood-based biomarkers have shown promise but are not yet in routine use.
  • EEG biomarkers provide cost-effective and objective measurements of neural activity; however, they have not yet been translated into clinical practice.

Modern neurotechnology and state-of-the-art learning algorithms offer significant potential to enhance computer-aided diagnosis of dementia.

The project will utilize EEG data from elderly people in the local community, collected in real-world settings.

The outcome of this project will be the development of a novel diagnostic tool that integrates EEG-based features with machine learning to provide an accurate, non-invasive, and cost-effective method for early dementia assessment. This project aims to bridge the gap between promising EEG biomarkers and practical clinical application, ultimately contributing to better treatment planning and improved quality of life for individuals with dementia.