EEG based Functional Connectivity Analysis of Alzheimer's Disease Subjects

• Published in: 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) pp. 356 - 361
• Main Authors: Vijayakumaran, P. P., Narzary, D., Gonuguntla, V., Lee, Ho-Won, Veluvolu, Kalyana C.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.02.2020
• Subjects: Alzheimer's disease (AD); Dementia; Electrodes; Electroencephalography; Entropy; mild cognitive impairment; neural disorder; spectral entropy (SE); Time-frequency analysis; wavelet transform; Wavelet transforms
• DOI: 10.1109/ICAIIC48513.2020.9065285

In the past few years, the study on functional connectivity of the human brain has led to various innovations in neuroscience. Functional connectivity reveals the simultaneity between the electrode pairs while performing neurophysiological activities. In this paper, the functional connectivity networks of healthy subjects, mild cognitive impairment (MCI), Alzheimer's disease (AD), and dementia patients were analysed by measuring the irregularity of the signals through wavelet spectral entropy (WSE) and were quantified using network measures. Depending on the discordance between the networks of all the four conditions, significant electrode pairs and their reactive networks were identified. These networks demonstrate the importance of most reactive electrode pairs that show significant variations. The identified functional connectivity networks that respond to the different pathologies shows the progression of the disease in patients. Further, the quantification of networks with graph theory network measures highlight differences between various progressive stages of the AD and its potential for development of EEG network biomarker in future.