Intelligent Approaches for Alzheimer's Disease Diagnosis from EEG Signals: Systematic Review

: Alzheimer’s disease (AD) is probably the most widespread neurodegenerative disorder a ff ecting millions of individuals worldwide. It is characterized by deficits in cognition, behavior, and intellectual functioning, with a high likelihood of progression. Accurate and timely diagnosis of AD is essential for halting the progression of AD and other forms of dementia. This systematic review explores the emerging field of AD diagnosis using recent advances in machine learning (ML) and deep learning (DL) methods applied to EEG signals. Focusing on 38 key articles published between January 2020 and February 2024, this review critically examines the integration of computational intelligence with neuroimaging to improve diagnostic accuracy and early detection of AD. AD poses significant diagnostic and treatment challenges exacerbated by the aging global population. Traditional diagnostic methods are often limited by their time-consuming nature, reliance on expert interpretation, and limited accessibility. EEG is a promising alternative, providing a non-invasive, cost-e ff ective way to record the brain’s electrical activity and identify neurophysiological markers indicative of AD. This review highlights the shift towards automated diagnostic processes, where ML and DL techniques are crucial in analyzing EEG data, extracting relevant features, and classifying AD stages with high accuracy. Although several advancements have been made, critical challenges and limitations remain, such as the need for more extensive and diverse datasets to increase model generalizability and integrate multi-modal data for a comprehensive diagnosis. The future of EEG-based AD diagnosis appears promising, driven by computational breakthroughs that pave the way for inclusive, precise, and early detection, ultimately enabling prompt intervention and individualized care.