Project Abstract

This report presents a comprehensive study on the application of Artificial Intelligence (AI) in predicting and diagnosing Mild Cognitive Impairment (MCI) using Magnetoencephalography (MEG) signals. MCI is a precursor to Dementia, a degenerative disease affecting cognitive functions such as memory and attention. The project aims to create an AI healthcare system for early detection of MCI based on MEG waves generated in brain regions. The methodology includes data collection, pre-processing, feature extraction, classification, and evaluation. The report discusses the use of various AI techniques, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), and machine learning algorithms like Support Vector Machine (SVM) and Deep Learning. The report also explores the use of different features such as Relative power in bands, Coherence, and Phase Locking Value (PLV) for model development. The BioFIND dataset, consisting of MEG and MRI scans from individuals with and without MCI, is used for this study. The report concludes with an analysis of the data and a statistical overview. The proposed AI system holds promise for improving early detection and management of cognitive decline, potentially enhancing the quality of life for affected individuals.

Keywords: Artificial Intelligence, Healthcare System, Deep Learning

 Conference Details

Session: Presentation Stream 7 at Presentation Slot 3

Location: GH018 at Tuesday 7th 13:30 – 17:00

Markers: Sofya Lyakhova, Troy Astarte

Course: MSc Data Science, Masters PG

Future Plans: I’m looking for work