Early Prediction and Diagnosis of Alzheimer’s Disease Based on Gwangju Alzheimer’s and Related Dementia (GARD) Cohort

Abstract

ISSUE Alzheimer’s Disease (AD) is one of the well-known chronic diseases among older adults. A type of AD that onset over 65 years of age is currently uncurable. As the aging of the population proceeds, the number of people with AD diagnoses and the socio-economic burden on AD both increase. To discover the scientific mechanism underlying AD, we have established the cohort dedicated to AD research named Gwangju Alzheimer’s and Related Dementia (GARD) cohort. We collect magnetic resonance imaging (MRI), positron emission tomography (PET), fluid biomarker data, and cognitive test results of local elderly participants. Since 2014, we have gathered over 15,136 population data that could yield valuable results on Alzheimer’s Disease in older adults. CONTENT The current symposium introduces Alzheimer's bioinformatics research based on our elder population cohort data. Each research focused on 1) AI-based scoring on Visuospatial task, 2) Near-infrared spectroscopy, 3) Genome-wide association study, and 4) Personal microbiome to generate population statistics, which results converge into a single goal, the prediction of AD. STRUCTURE In our first talk, Prof. Kun Ho Lee will explain how we implemented artificial intelligence (AI) to predict biomarker pathology and grading complex visuospatial cognitive tasks. The second speaker, Prof. Jae Gwan Kim will demonstrate machine-learning-based AD stage prediction based on prefrontal near-infrared signals of participants. Next, Prof. Jungsoo Gim presents a prediction tool for amyloid PET positivity conversion based on personal genomic information. Finally, Prof. Sunjae Lee will demonstrate a microbiome project that aims to develop a probiotic solution for AD prevention and an oral-microbiome screening kit for detecting AD-risk microbes. CONCLUSION The presented talks demonstrate the current stage of AD prevention research based on our dementia cohort data. We believe the implementation of innovative gerontechnology on elderly population data will contribute to the healthy and happy lives of elders by unraveling the hidden causes of chronic diseases like AD.