 Alzheimer's disease, AD, is the most common form of dementia characterized by progressive cognitive decline and impaired memory. It is believed to be caused by a combination of genetic and environmental factors with changes in the brain structure and function being key indicators of the disease. Functional connectivity, FC, measures have been used to identify patterns of brain activity associated with AD as they can detect subtle differences in brain activity between healthy individuals and those with AD. In this study, researchers evaluated eight different FC measures to determine which was most effective at distinguishing between healthy and AD subjects. They found that a graph neural network, GNN, model outperformed all other methods, achieving an AUC score of 0.984 and an accuracy of 92%. This suggests that GNN may be a promising tool for identifying AD patients early on. This article was authored by Dominic Kleppel, Fahy, Min Woo, and others. We are article.tv, links in the description below.