Year: 2024
Type: article
Abstract: This study explores the efficacy of using EEG-based parameters to diagnose bipolar disorder. A synthetic dataset was generated, including both correctly diagnosed and misdiagnosed cases, simulating realistic clinical conditions. EEG features such as thetaalpha mean, beta band mean, and coherence measures were used to train a multi-layer perceptron (MLP) model. The model achieved a validation accuracy of 92%, demonstrating strong potential for EEG-based diagnostics. However, challenges such as standardization of electrode configurations and addressing equipment differences are crucial for broader applicability and validity of the findings in diverse clinical settings.
Author: Richard Murdoch Mongomery
Institution: University of Aveiro
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: bronze
OpenAlex ID: W4402692530