Assessing the Potential of EEG in Early Detection of Alzheimer's Disease: A Systematic Comprehensive Review (2000-2023)

Background: As the prevalence of Alzheimer's disease (AD) grows with an aging population, the need for early diagnosis has led to increased focus on electroencephalography (EEG) as a non-invasive diagnostic tool. Objective: This review assesses advancements in EEG analysis, including the application of machine learning, for detecting AD from 2000 to 2023. Methods: Following PRISMA guidelines, a search across major databases resulted in 25 studies that met the inclusion criteria, focusing on EEG's application in AD diagnosis and the use of novel signal processing and machine learning techniques. Results: Progress in EEG analysis has shown promise for early AD identification, with techniques like Hjorth parameters and signal compressibility enhancing detection capabilities. Machine learning has improved the precision of differential diagnosis between AD and mild cognitive impairment. However, challenges in standardizing EEG methodologies and data privacy remain. Conclusions: EEG stands out as a valuable tool for early AD detection, with the potential to integrate into multimodal diagnostic approaches. Future research should aim to standardize EEG procedures and explore collaborative, privacy-preserving research methods.