Exploring Mild Cognitive Impairment Data Using Symbolic Information Approaches

Identifying early markers of Alzheimer's disease is crucial for enhancing diagnosis and intervention strategies. One such early-stage condition is mild cognitive impairment (MCI), a syndrome associated with a high risk of progression to Alzheimer's disease. This study analyzes magnetoencephalography (MEG) data from two groups of individuals with MCI: one that rapidly progressed to Alzheimer's disease and another that remained cognitively stable. The objective is to classify individuals who eventually develop dementia versus those who do not. To achieve this, we employed ordinal pattern analysis, followed by the computation of information theory quantifiers such as Shannon’s permutation entropy and statistical complexity. The initial findings reveal intriguing patterns in entropy and complexity measures between the two groups, suggesting that these biomarkers may hold the potential for distinguishing individuals at higher risk of rapid progression to dementia.



The seminar will be streamed live via Zoom.



https://us06web.zoom.us/j/98286706234?pwd=bm1JUFVYcTJkaVl1VU55L0FiWDRIUT09