Title : Diagnosis of alzheimer's disease using the effective communication of brain signals by granger causality method
Alzheimer's disease is a degenerative and progressive disease of the human central nervous system (brain) that causes intellectual decline. So that 5% of people over 70 years old and 20% of people over 80 years old suffer from this disease. If Alzheimer's is not detected on time, even the most recent and up-to-date treatment methods will not work. So far, many tools and methods have been provided to diagnose Alzheimer's disease. But in most of these methods, the interactions and connections of different parts of the brain are not considered. But since Alzheimer's disease can affect all parts of the brain, it can be said that damage to any part of the brain disrupts their interaction with other parts. We extracted the indicators of effective communication between different parts of the brain of two groups of healthy people and sick people through Granger causality analysis and after statistical comparison between the quantitative values ??of the indicators in different EEG channels, we checked the effective communication. Then we used linear differential analysis to separate the two groups. The data used in the research includes EEG signal, 10 healthy subjects and 8 subjects with Alzheimer's disease (mild and severe). Findings: With the correct diagnosis of all patients and with only one wrong diagnosis of a healthy subject, accuracy of 83.33%, accuracy of 90%, sensitivity of 100% and diagnosis of 80% were obtained for the test data. The effective communication rate of Fz and Cz channels for healthy people is higher than the effective communication of Pz channel, while for Alzheimer's patients, the least effective brain communication was observed in Fz channel and the highest communication was observed in Pz channel and sometimes in Cz channel.
Keywords: effective brain communication, functional brain communication, Granger causality analysis, linear differential analysis.