Research Progress of Electroencephalogram and Eye Movement in the Diagnosis of Alzheimer's Disease

Early diagnosis of Alzheimer's disease (AD) is decisive for intervening in the progression of the disease and improving the quality of life of patients. Traditional clinical diagnostic methods often face limitations such as difficulty in early identification, high cost and low popularity. In recent years, electroencephalogram (EEG) and eye-tracking (ET) techniques have shown great potential in the development of digital biomarkers for AD, thanks to their non-invasive nature, high temporal resolution, low cost and ease of operation. This article provides a comprehensive review of the latest research progress of EEG and ET techniques in the field of AD diagnosis. The article first analyzed the characteristic changes in electroencephalogram (EEG) rhythms and functional network topologies in AD patients. Subsequently, abnormal behavior indicators under multiple eye movement paradigms were explored, and the integration strategies of electroencephalogram and eye movement data under feature stitching and deep learning architectures were expounded. Finally, this paper explores technological advancements such as digital cognitive twins, federated learning, and XR high ecological validity assessment in light of the latest frontier trends.