Identification of Onset and Progression of Alzheimer’s Disease Using Topological Data Analysis

Structural changes that can occur in a network as time progresses are difficult to capture. To handle such data, one of the methods used is Topological Data Analysis(TDA), which can transform the data, in order to extract and analyze the data. Alzheimer’s disease networks show the changes that happen in the brain network as the disease progresses. Methods should be devised to capture these changes efficiently. In this work, two powerful tools of Topological data analysis, “persistent homology” and “mapper algorithm” are applied on the disease networks to gain insights about the changes happening during onset and progression of the disease. From the results, it can be concluded that more fragmentation is happening within the brain network as the disease progresses. The interconnections within the community(or cluster) are stronger as compared to the connections with other communities(or clusters). This may lead to difficulties in various cognitive functions such as attention, memory, language, and problem-solving.