Comparison of computational EEG analysis techniques for classifying elderly people at different stages of Alzheimer's disease

• Grant number: 24/05536-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2024
• End date: June 30, 2025
• Field of knowledge: Engineering - Biomedical Engineering
• Principal Investigator: Andriana Susana Lopes de Oliveira Campanharo
• Grantee: Marceline Esperança Gomes
• Host Institution: Instituto de Biociências (IBB). Universidade Estadual Paulista (UNESP). Campus de Botucatu. Botucatu , SP, Brazil

Abstract

Alzheimer's disease (AD) can be understood as a degenerative and progressive dementia of the Central Nervous System, irreversible and of unknown cause. AD is mainly characterized by memory loss, disorientation in time and space, in addition to accelerated intellectual deterioration. AD is the main dementia among elderly people over 65 years old and affects approximately 30 million individuals worldwide. Mild Cognitive Impairment (MCI) is a transitional stage between aging and AD and is often an early warning of this disease. DCL is characterized by loss of recent memory and difficulty in reasoning. The progression of this condition can last decades, from the appearance of its first signs to its most severe clinical symptoms, which include the loss of the ability to communicate, move around and even eat. The differentiation between MCI and AD plays an important role in the early detection of AD and in the monitoring of patients with the disease, as well as in the future search for treatment methods. Recent research has been performed to identify MCI and AD from electroencephalogram (EEG) data. However, due to the high frequency used to obtain EEG data, they culminate in time series of significant length, contaminated by artifacts (noise) and require significant time for visual analysis. Therefore, the use of automatic EEG analysis methods has become a relevant research topic in differentiating between MCI and AD and, consequently, in identifying the first signs of AD. In this sense, in the present research project we will apply the map from a time series into a complex network, recently proposed by Campanharo et al., to study the dynamics of EEG signals from patients with MCI and AD. More specifically, in the distinction between aging and MCI, in classifying the stages of AD and in detecting the brain regions most affected by AD.